CN118095843A - Remote supervision system and method based on Internet of things technology - Google Patents
Remote supervision system and method based on Internet of things technology Download PDFInfo
- Publication number
- CN118095843A CN118095843A CN202410188366.XA CN202410188366A CN118095843A CN 118095843 A CN118095843 A CN 118095843A CN 202410188366 A CN202410188366 A CN 202410188366A CN 118095843 A CN118095843 A CN 118095843A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- remote supervision
- pollution
- tracing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000005516 engineering process Methods 0.000 title claims abstract description 20
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 52
- 238000012544 monitoring process Methods 0.000 claims abstract description 48
- 230000002159 abnormal effect Effects 0.000 claims abstract description 19
- 230000005856 abnormality Effects 0.000 claims abstract description 11
- 238000004458 analytical method Methods 0.000 claims description 71
- 238000001514 detection method Methods 0.000 claims description 39
- 239000003344 environmental pollutant Substances 0.000 claims description 24
- 231100000719 pollutant Toxicity 0.000 claims description 24
- 239000010865 sewage Substances 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 21
- 230000004044 response Effects 0.000 claims description 21
- 230000006399 behavior Effects 0.000 claims description 18
- 238000010183 spectrum analysis Methods 0.000 claims description 18
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 238000004891 communication Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 13
- 230000009466 transformation Effects 0.000 claims description 13
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 6
- 230000008030 elimination Effects 0.000 claims description 6
- 238000003379 elimination reaction Methods 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 6
- 238000004949 mass spectrometry Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000010219 correlation analysis Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 230000000737 periodic effect Effects 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000000556 factor analysis Methods 0.000 claims description 3
- 238000001506 fluorescence spectroscopy Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 3
- DOTMOQHOJINYBL-UHFFFAOYSA-N molecular nitrogen;molecular oxygen Chemical compound N#N.O=O DOTMOQHOJINYBL-UHFFFAOYSA-N 0.000 claims description 3
- 239000001301 oxygen Substances 0.000 claims description 3
- 229910052760 oxygen Inorganic materials 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 238000000611 regression analysis Methods 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 2
- 238000010561 standard procedure Methods 0.000 claims 1
- 230000001960 triggered effect Effects 0.000 claims 1
- 238000003911 water pollution Methods 0.000 abstract description 4
- 238000013500 data storage Methods 0.000 abstract description 2
- 238000009792 diffusion process Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 238000000746 purification Methods 0.000 description 5
- 238000005070 sampling Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 2
- 239000013049 sediment Substances 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000002189 fluorescence spectrum Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000008213 purified water Substances 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2131—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on a transform domain processing, e.g. wavelet transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/35—Utilities, e.g. electricity, gas or water
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/10—Detection; Monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
- G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Computing Systems (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Accounting & Taxation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a remote supervision system and a method based on the internet of things technology, which relate to the technical field of remote supervision and comprise a remote supervision data acquisition unit, an online abnormality early warning unit, a pollution tracing unit and an emergency checking and law enforcement unit. According to the invention, the on-line abnormal early warning unit is arranged in the remote monitoring system based on the Internet of things technology, the water quality time sequence is analyzed in real time through the sudden pollution dynamic early warning module, when sudden water pollution occurs, early warning can be timely carried out, the sudden pollution can be timely obtained through the remote monitoring system, then the sudden pollution is timely traced through the pollution tracing unit, the position of the sudden pollution is timely determined, the diffusion of the pollution is greatly reduced, the monitoring accuracy of the remote monitoring system is improved, in addition, the target enterprises are timely checked and law enforcement is carried out through the emergency checking and law enforcement unit, and the monitoring strength of the monitoring system is improved through early warning data storage and on-site checking.
Description
Technical Field
The invention relates to the technical field of remote supervision, in particular to a remote supervision system and method based on the internet of things technology.
Background
The internet of things refers to connecting any object with a network through information sensing equipment according to a stipulated protocol, and carrying out information exchange and communication on the object through an information transmission medium so as to realize functions of intelligent identification, positioning, tracking, supervision and the like, wherein the internet of things technology is widely applied to monitoring and controlling ecological environment such as water pollution, and the application number of the internet-based emergency sewage treatment on-line monitoring system and method are disclosed in China patent publication No. comprising: the sewage treatment system comprises a sewage area setting module, a sewage purification treatment module, a sewage parameter acquisition module, a purified water quality monitoring module, a biochemical index monitoring module, a sediment monitoring module, a comprehensive model construction module and an analysis and early warning module, wherein the monitoring range is determined by the sewage area setting module and is sequentially numbered, the sewage purification treatment module carries out primary purification, secondary purification and tertiary purification on sewage, the sewage parameter acquisition module acquires required parameter data, the water quality coefficient, the biochemical coefficient and the sediment coefficient of the purified sewage are calculated by a mathematical model, the comprehensive sewage index of each monitoring subarea is calculated by the comprehensive model construction module, and the analysis and early warning module analyzes whether the comprehensive sewage index of each monitoring subarea accords with a treatment standard or not based on the comprehensive sewage index;
The technical scheme only solves the problems of data monitoring and risk early warning on sewage, but the current supervision on environmental pollution is long in time interval and large in space distance, so that the problems of untimely discovery, untimely evidence obtaining and untimely treatment are solved in the supervision process, and the problem of difficulty in achieving the supervision on the large-area environment is solved.
Disclosure of Invention
The invention aims to provide a remote supervision system and a method based on the internet of things technology, so as to solve the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions: the remote supervision system based on the internet of things comprises a remote supervision data acquisition unit, an online abnormal early warning unit, a pollution tracing unit and an emergency checking and law enforcement unit;
the remote supervision data acquisition unit is used for acquiring data of the environment in the supervision area, transmitting the data to the cloud end through the internet of things, and transmitting the data of the cloud end;
The online abnormality early warning unit receives the data acquired by the remote supervision data acquisition unit, performs online analysis on the received data and early warning according to a processing result, and transmits early warning information to the cloud of the remote supervision data acquisition unit;
The pollution tracing unit receives the early warning information received by the remote supervision data acquisition unit, performs online and offline tracing analysis on the early warning data, and timely finds out a pollution source according to a tracing analysis result, and transmits an analysis conclusion to the cloud end of the remote supervision data acquisition unit;
The emergency checking and law enforcement unit receives the traceability result received by the remote supervision data acquisition unit, performs on-site checking on pollution forming reasons, timely performs illegal law enforcement, and transmits illegal behaviors to the cloud of the remote supervision data acquisition unit.
Preferably, the remote supervision data acquisition unit comprises a sensor module, a ZigBee terminal node and a ZigBee coordinator node, wherein the sensor module comprises a water quality sensor, a PH sensor, a turbidity sensor, a dissolved oxygen sensor, a nitrogen oxygen sensor and a Yu Fu sensor, the sensor module further comprises an automatic sample reserving device for reserving abnormal drainage, the ZigBee terminal node shares a plurality of sensors in the sensor module for use, and transmits data acquired by the sensors through the ZigBee terminal node, and the ZigBee coordinator node receives data transmitted by all the ZigBee terminal nodes and transmits all the data.
Preferably, the remote supervision data acquisition unit comprises a microprocessor, a 5G communication module, an Ethernet module and a remote supervision cloud platform, wherein the microprocessor is an STM32 processor, the microprocessor receives data transmitted by a ZigBee coordinator node, the 5G communication module is connected with the microprocessor and then transmits the data through a 5G network, the Ethernet module is connected with the microprocessor and then transmits the data through the Ethernet, the remote supervision cloud platform receives the data transmitted by the 5G communication module or the Ethernet module through the network, a database is established in the remote supervision cloud platform, and the data acquired by the sensor module is stored.
Preferably, the online anomaly early warning unit comprises an online data processing module and a spectrum analysis module, wherein the online data processing module processes data stored in the remote supervision cloud platform, firstly, preprocessing the original data acquired by the sensor, including noise elimination, correction and smoothing, then, converting the preprocessed original data into a time sequence, and the spectrum analysis module performs spectrum analysis on the data converted into the time sequence in the online data processing module, identifies periodic anomalies through Fourier transformation and identifies non-periodic anomalies through continuous wavelet transformation.
Preferably, the online anomaly early-warning unit comprises a sudden pollution dynamic early-warning module, wherein the sudden pollution dynamic early-warning module carries out anomaly early-warning based on a neural network based on a historical baseline, a small spectrum analysis algorithm and an overstep method, wherein a soft measurement time sequence of conventional online monitoring data production is subjected to time sequence anomaly detection early-warning, the occurrence of anomalies in the time sequence is early-warned through the time sequence anomaly early-warning based on a clustering algorithm, the historical monitoring data stored in a database of a remote supervision cloud platform is firstly clustered through training by adopting the clustering algorithm, then the anomaly degree is calculated by calculating the distance between the historical monitoring data and a clustering center for a data object to be monitored, the anomaly detection early-warning is carried out by constructing a soft measurement model based on water quality parameter correlation analysis and utilizing correlation analysis and multiple regression analysis, the sudden pollution dynamic early-warning module transmits early-warning data to the remote supervision cloud platform through constructing a wavelet neural network data flow anomaly detection model, and the wavelet neural network data flow anomaly detection model comprises a continuous wavelet transformation algorithm;
The continuous wavelet transform algorithm is as follows:
wherein C x represents a wavelet coefficient, a represents a scale factor or scale parameter, X (t) represents a time sequence, b represents a parameter shifted along a time axis, t represents a sampling interval, X represents a conjugate complex number, ψ a,b represents an input signal, ψ (t-b/a), a > 0 represents a scaled signal, a parent wavelet can be scaled by a wavelet scale to obtain a series of sub-wavelets, and the similarity between each step wavelet and the signal is measured by calculating a wavelet coefficient C x, a set of wavelet coefficients is generated for each frequency, the size of a wavelet window is transformed to obtain information of low-frequency and high-frequency events in water quality time variation, and continuous wavelet transformation consists of convolution ψ a(t) of the time sequence X (t) and the parent wavelet after the scale wavelet transformation is readjusted;
The wavelet scale determines the length of the water quality signal stretched in time inversely proportional to the signal frequency, which is the higher the scale factor, the lower the frequency indicated by the extended wavelet, the stretched wavelet helps to capture slowly occurring changes in the signal, while the scaled wavelet helps to capture abrupt changes, and the delay or shift of the advancing wavelet along the signal length helps to partially analyze the entire signal, thus capturing the dominant anomalies in the water quality signal with the optimal values of the scale range.
Preferably, the pollution tracing unit comprises an emergency response module and an analysis tracing module, wherein the emergency response module receives the early warning data uploaded by the sudden pollution dynamic early warning module in the remote supervision cloud platform, then judges the authenticity of the early warning data, if the sensor in the sensor module is confirmed to work normally and the data transmission process is normal, starts emergency response, otherwise, cancels emergency early warning and starts an operation and maintenance program, and the analysis tracing module analyzes and traces the early warning data through a statistical tracing technology comprising a principal component analysis PCA, a non-negative constraint factor analysis method and a PMF positive definite factor decomposition model;
the basic calculation equation for the PMF positive factorization model is as follows:
X＝GF+E
wherein X is a (n X m) sample concentration data matrix, each row in X represents a sampling point, each column represents a concentration of a perfluorinated compound, G is an n X r matrix representing a source contribution rate matrix, wherein r columns represent a number of different pollution sources, F is an r X m matrix representing a pollution source fingerprint matrix, and E represents an r X m residual matrix.
Preferably, the pollution tracing unit comprises a sample reserving detection module and an analysis conclusion module, the sample reserving detection module performs offline chromatographic mass spectrometry analysis manually to determine characteristic pollutants, a characteristic pollutant database of a possible pollution source is searched for pollution tracing, the detection is performed through a fluorescence spectrometry, the analysis conclusion module determines the final pollution source position according to an online tracing result of the analysis tracing module and an offline tracing result analysis conclusion of the sample reserving detection module, determines a tracing path, a pollution range and a pollutant concentration through the online tracing result, verifies online tracing authenticity through the offline tracing result, determines a target enterprise list, and the analysis conclusion module transmits analysis conclusion data to the remote supervision cloud platform.
Preferably, the emergency checking and law enforcement unit comprises a checking module, the checking module receives the traceability result transmitted in the remote supervision cloud platform, then pushes emergency information to a checking person, and checks pollution reasons through the checking person, wherein the checking module comprises the steps of detecting whether a facility normally operates, whether the emission behavior is abnormal, whether enterprise data is falsified or not, whether pollutant emission exceeds a standard and whether pollutant emission exceeds a standard, and uploading the checking result to the remote supervision cloud platform.
Preferably, the emergency checking and law enforcement unit comprises a rule violation information pushing module and a law enforcement module, wherein the rule violation information pushing module receives a checking result in the remote supervision cloud platform and judges whether a target enterprise is rule-violated or not, the rule violation information is uploaded to the remote supervision cloud platform after the rule violation is true, and the law enforcement module receives the rule violation enterprise information and rule violations pushed in the remote supervision cloud platform and informs law enforcement personnel to conduct law enforcement.
The remote supervision method based on the Internet of things technology comprises the following steps of:
Step one: the method comprises the steps that various water quality sensors in a sensor module are used for collecting water quality data of an enterprise sewage discharge port, a river sewage discharge port, a sewage discharge official network and a river cross section, data collected by the water quality sensors corresponding to the water quality sensors are transmitted through a plurality of ZigBee terminal nodes, the data transmitted by all ZigBee terminal nodes are received and transmitted through a ZigBee coordinator node, the data of each water quality sensor transmitted in the ZigBee coordinator node are received through a microprocessor, then raw data collected by the sensors are transmitted to a remote supervision cloud platform through a G communication module, or the data are transmitted to the remote supervision cloud platform through an Ethernet module, and the data of the sensors are stored through a database in the remote supervision cloud platform;
Step two: the data stored in the remote supervision cloud platform is preprocessed through an online data processing module, noise elimination, correction and smoothing are firstly carried out on the data, then data conversion is carried out, the preprocessed original data is converted into a time sequence, the time sequence in the online data processing module is analyzed through a spectrum analysis module, the data is returned to a sensor module, a sample retaining device is controlled to automatically retain samples of abnormal drainage measured by the sensor module, a sudden pollution dynamic early warning module is used for carrying out abnormal detection early warning on the sudden pollution, the dynamic early warning is carried out on the sudden pollution, firstly, historical monitoring data are trained and clustered through a clustering algorithm, then wavelet denoising is carried out, a wavelet low-frequency time sequence is predicted through an artificial neural network for a low-frequency part, and a high-frequency part, the high-frequency time sequence is zeroed through zeroing operation, then the low-frequency part and the high-frequency part are predicted by wavelet reconstruction, the post-time sequence and the actual monitoring time sequence are differenced to obtain a historical residual error time sequence, in addition, the current time residual error is obtained by differencing the actual monitoring value of the current time and the predicted value of the wavelet neural network, after the pre-warning threshold interval is set, whether the historical residual error and the current residual error are in the threshold interval range is judged, if yes, the time sequence of normal water quality is judged, if no, the duration of the residual error is compared with the appointed duration, if less than the appointed duration, the time sequence of normal water quality is still judged, if greater than the appointed duration, the pre-warning is that sudden pollution event is possible to happen, at the moment, the sudden pollution dynamic early warning module uploads the early warning information to the remote monitoring cloud platform;
Step three: the method comprises the steps of sending early warning information to an emergency response module through a remote supervision cloud platform, judging the authenticity of early warning data through the emergency response module, triggering early warning after eliminating sensor abnormal reasons and data transmission abnormal reasons, starting emergency response, carrying out online analysis tracing through an analysis tracing module, carrying out tracing analysis on project area pollution through a statistical tracing technology, carrying out manual offline analysis tracing through a sample-remaining detection module, carrying out pollution tracing through an offline chromatographic mass spectrometry analysis, determining characteristic pollutants, searching a characteristic pollutant database of a possible pollution source, carrying out pollution tracing through a three-dimensional fluorescent map qualitative tracing, firstly carrying out map characteristic recognition including water line intensity and density recognition, water line peak number recognition and water line peak position recognition, then carrying out map characteristic extraction, needing to firstly carry out non-closed curve density extraction, then carrying out curve fitting, then carrying out closed curve number and position extraction, finally carrying out ellipse fitting, carrying out map characteristic matching after the completion of the feature extraction, including carrying out three-dimensional fluorescent map database construction, carrying out non-matching algorithm establishment and supervision matching algorithm establishment, carrying out pollution tracing through the analysis conclusion module according to the analysis conclusion and the detection result of the analysis conclusion module, carrying out the online supervision matching algorithm establishment, carrying out the three-dimensional fluorescent map feature extraction and the analysis conclusion and carrying out the monitoring conclusion according to the detection result and the trace result and carrying out the monitoring and the monitoring conclusion on the cloud conclusion on the remote supervision module, and carrying out the monitoring result, and carrying out the monitoring and the cloud conclusion on the monitoring result, and the cloud monitoring;
Step four: the method comprises the steps of receiving a traceability result pushed by a remote supervision cloud platform through a checking module, informing a checking person to perform on-site checking, checking the working condition of a detection facility, checking enterprise emission behavior, comparing and checking enterprise data, avoiding the situation that the data uploaded by an enterprise are falsified, measuring and checking the emission standard and the emission quantity of pollutants, uploading the result to the remote supervision cloud platform, storing the checking result through the remote supervision cloud platform to serve as evidence, judging whether the enterprise has illegal behaviors according to the checking result in the checking module, receiving the enterprise illegal behavior information transmitted by the remote supervision cloud platform through an illegal behavior information pushing module, and informing law enforcement personnel to perform timely law enforcement through a law enforcement module.
Compared with the prior art, the invention has the beneficial effects that:
According to the invention, the on-line abnormal early warning unit is arranged in the remote monitoring system based on the Internet of things technology, the real-time analysis is carried out on the water quality time sequence through the sudden pollution dynamic early warning module, when sudden water pollution occurs, early warning can be carried out in time, the sudden pollution can be timely obtained through the remote monitoring system, then the sudden pollution is timely traced through the pollution tracing unit, the position of the sudden pollution is timely determined, the pollution diffusion is greatly reduced, the monitoring accuracy of the remote monitoring system is improved, in addition, the emergency checking and law enforcement unit is used for timely checking and enforcing a target enterprise, and the false work of the enterprise is reduced through early warning data storage and on-site checking, so that the monitoring strength of the monitoring system is improved.
Drawings
Fig. 1 is a block diagram of a remote supervision system based on the internet of things technology according to an embodiment of the present invention;
FIG. 2 is a block diagram of a remote supervisory data acquisition unit according to an embodiment of the present invention;
FIG. 3 is a block diagram of an online abnormality early warning unit according to an embodiment of the present invention;
FIG. 4 is a block diagram of a dynamic early warning module for sudden pollution according to an embodiment of the present invention;
FIG. 5 is a block diagram of a pollution tracing unit according to an embodiment of the present invention;
FIG. 6 is a block diagram of an emergency check and law enforcement unit according to an embodiment of the present invention.
In the figure: 1. a remote supervision data acquisition unit; 101. a sensor module; 102. ZigBee terminal node; 103. a ZigBee coordinator node; 104. a microprocessor; 105. a 5G communication module; 106. an Ethernet module; 107. remotely supervising the cloud platform; 2. an online abnormality early warning unit; 201. an online data processing module; 202. a spectrum analysis module; 203. a sudden pollution dynamic early warning module; 3. a pollution tracing unit; 301. an emergency response module; 302. the analysis tracing module; 303. a sample reserving detection module; 304. an analysis conclusion module; 4. an emergency checking and law enforcement unit; 401. a checking module; 402. the illegal behavior information pushing module; 403. and a law enforcement module.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-6, the present invention provides a technical solution: the remote supervision system and method based on the Internet of things technology comprises a remote supervision data acquisition unit 1, an online abnormality early warning unit 2, a pollution tracing unit 3 and an emergency checking and law enforcement unit 4;
The remote supervision data acquisition unit 1 is used for acquiring data of the environment in the supervision area, transmitting the data to the cloud end through the internet of things, and transmitting the data of the cloud end through the remote supervision data acquisition unit 1;
the online abnormality early-warning unit 2 receives the data acquired by the remote supervision data acquisition unit 1, performs online analysis on the received data, and early-warns according to the processing result, and the online abnormality early-warning unit 2 transmits early-warning information to the cloud of the remote supervision data acquisition unit 1;
The pollution tracing unit 3 receives the early warning information received by the remote supervision data acquisition unit 1, performs online and offline tracing analysis on the early warning data, timely finds out a pollution source according to a tracing analysis result, and transmits an analysis conclusion to the cloud of the remote supervision data acquisition unit 1 by the pollution tracing unit 3;
The emergency checking and law enforcement unit 4, the emergency checking and law enforcement unit 4 receives the traceability result received by the remote supervision data acquisition unit 1, performs illegal law enforcement in time by checking pollution forming reasons on site, and transmits illegal behaviors to the cloud of the remote supervision data acquisition unit 1.
The remote supervision data acquisition unit 1 comprises a sensor module 101, zigBee terminal nodes 102 and a ZigBee coordinator node 103, wherein the sensor module 101 comprises a water quality sensor, a PH sensor, a turbidity sensor, a dissolved oxygen sensor, a nitrogen oxygen sensor and a Yu Fu sensor, the sensor module 101 also comprises an automatic sample reserving device, abnormal drainage is reserved, the ZigBee terminal nodes 102 share a plurality of sensors in the sensor module 101 to be matched for use, data acquired by the sensors are transmitted through the ZigBee terminal nodes 102, and the ZigBee coordinator node 103 receives the data transmitted by all the ZigBee terminal nodes 102 and transmits all the data; data acquisition is carried out through the sensor module 101, and the data is transmitted through the ZigBee terminal node 102 and the ZigBee coordinator node 103;
The remote supervision data acquisition unit 1 comprises a microprocessor 104, a 5G communication module 105, an Ethernet module 106 and a remote supervision cloud platform 107, wherein the microprocessor 104 is an STM32 processor, the microprocessor 104 is used for receiving data transmitted by the ZigBee coordinator node 103, the 5G communication module 105 is connected with the microprocessor 104 and then transmits the data through a 5G network, the Ethernet module 106 is connected with the microprocessor 104 and then transmits the data through an Ethernet, the remote supervision cloud platform 107 is used for receiving the data transmitted by the 5G communication module 105 or the Ethernet module 106 through the network, a database is established in the remote supervision cloud platform 107, and the data acquired by the sensor module 101 is stored; receiving the data through the microprocessor 104, and then transmitting the data to the remote supervision cloud platform 107 through the 5G communication module 105 or the Ethernet module 106 by using a network;
The online anomaly early warning unit 2 comprises an online data processing module 201 and a spectrum analysis module 202, wherein the online data processing module 201 processes data stored in the remote supervision cloud platform 107, firstly, preprocessing raw data collected by a sensor, including noise elimination, correction and smoothing, is performed, then data conversion is performed, the preprocessed raw data is converted into a time sequence, the spectrum analysis module 202 performs spectrum analysis on the data converted into the time sequence by the online data processing module 201, periodic anomalies are identified through Fourier transformation, and aperiodic anomalies are identified through continuous wavelet transformation; preprocessing the original data transmitted by the sensors in the sensor module 101 through the online data processing module 201, and performing conversion analysis on the data processed by the online data processing module 201 through the spectrum analysis module 202;
The online anomaly early-warning unit 2 comprises a sudden pollution dynamic early-warning module 203, wherein the sudden pollution dynamic early-warning module 203 carries out anomaly early-warning based on a neural network of a historical baseline, a small spectrum analysis algorithm and an overstandard method, the soft measurement time sequence of conventional online monitoring data production is subjected to time sequence anomaly detection early-warning, the occurrence of anomalies in the time sequence is early-warned through the time sequence anomaly early-warning based on a clustering algorithm, the historical monitoring data stored in a database of a remote supervision cloud platform 107 is firstly subjected to training clustering by adopting the clustering algorithm, then the anomaly degree is calculated by calculating the distance between the data object to be monitored and a clustering center, the anomaly detection early-warning is carried out by constructing a soft measurement model based on water quality parameter correlation analysis and utilizing correlation analysis and multiple regression analysis, the early-warning data is transmitted to the remote supervision cloud platform 107 through constructing a wavelet neural network data flow anomaly detection model, and the sudden pollution dynamic early-warning module 203 directly carries out time sequence anomaly detection early-warning, and the wavelet neural network data flow anomaly detection model comprises a continuous wavelet transformation algorithm;
The continuous wavelet transform algorithm is as follows:
wherein C x represents a wavelet coefficient, a represents a scale factor or scale parameter, X (t) represents a time sequence, b represents a parameter shifted along a time axis, t represents a sampling interval, X represents a conjugate complex number, ψ a,b represents an input signal, ψ (t-b/a), a > 0 represents a scaled signal, a parent wavelet can be scaled by a wavelet scale to obtain a series of sub-wavelets, and the similarity between each step wavelet and the signal is measured by calculating a wavelet coefficient C x, a set of wavelet coefficients is generated for each frequency, the size of a wavelet window is transformed to obtain information of low-frequency and high-frequency events in water quality time variation, and continuous wavelet transformation consists of convolution ψ a(t) of the time sequence X (t) and the parent wavelet after the scale wavelet transformation is readjusted;
The wavelet scale determines the length of the water quality signal stretched in time inversely proportional to the signal frequency, which is the higher the scale factor, the lower the frequency is indicated by the extended wavelet, the stretched wavelet helps to capture slowly occurring changes in the signal, while the scaled wavelet helps to capture abrupt changes, and the delay or shift of the advancing wavelet along the signal length helps to partially analyze the whole signal, thus capturing the dominant anomalies in the water quality signal with the optimal values of the scale range; the data converted and analyzed by the spectrum analysis module 202 is subjected to early warning analysis by the sudden pollution dynamic early warning module 203, so that possible anomalies in the real-time data are found out, and the remote monitoring system can find out sudden water pollution in time;
the pollution tracing unit 3 comprises an emergency response module 301 and an analysis tracing module 302, wherein the emergency response module 301 receives early warning data uploaded by the sudden pollution dynamic early warning module 203 in the remote supervision cloud platform 107, then judges the authenticity of the early warning data, if the sensor in the sensor module 101 is confirmed to work normally and the data transmission process is normal, starts emergency response, otherwise, cancels emergency early warning and starts an operation and maintenance program, and the analysis tracing module 302 performs analysis tracing on the early warning data through a statistical tracing technology comprising principal component analysis PCA, a non-negative constraint factor analysis method and a PMF positive definite factor decomposition model;
the basic calculation equation for the PMF positive factorization model is as follows:
X＝GF+E
Wherein X is a (n X m) sample concentration data matrix, each row in X represents a sampling point, each column represents the concentration of a perfluorinated compound, G is an n X r matrix representing a source contribution rate matrix, wherein r columns represent the number of a plurality of different pollution sources, F is an r X m matrix representing a pollution source fingerprint matrix, and E represents an r X m residual matrix; the authenticity of the data is judged through the emergency response module 301, whether emergency response is started or not is determined according to the judging result, the stability and reliability of the remote supervision system are improved, and the analysis and tracing module 302 carries out online statistics and tracing on the water quality data so as to find out the pollution position conveniently;
The pollution tracing unit 3 comprises a sample reserving detection module 303 and an analysis conclusion module 304, wherein the sample reserving detection module 303 performs offline chromatographic mass spectrometry analysis manually to determine characteristic pollutants, a characteristic pollutant database of a possible pollution source is searched for pollution tracing, the pollution tracing is performed through a fluorescence spectrometry, the analysis conclusion module 304 determines a final pollution source position according to an online tracing result of the analysis tracing module 302 and an offline tracing result analysis conclusion of the sample reserving detection module 303, a tracing path, a pollution range and a pollutant concentration are determined through the online tracing result, online tracing authenticity is verified through the offline tracing result, a target enterprise list is determined, and the analysis conclusion module 304 transmits analysis conclusion data to the remote supervision cloud platform 107; offline tracing is performed through the sample-remaining detection module 303, fluorescence spectrum analysis is performed manually, comprehensive analysis is performed through the analysis conclusion module 304 according to the results of the analysis tracing module 302 and the analysis conclusion module 304, the final pollution position is determined, and the supervision accuracy of the remote supervision system is improved;
The emergency checking and law enforcement unit 4 comprises a checking module 401, wherein the checking module 401 receives a tracing result transmitted in the remote supervision cloud platform 107, then pushes emergency information to a checking person, checks pollution reasons through the checking person, and comprises detecting whether a facility normally operates, whether emission behaviors are abnormal, whether enterprise data are falsified or not, whether pollutant emission exceeds a standard and whether pollutant emission exceeds a standard, and uploads the checking result to the remote supervision cloud platform 107; the checking module 401 informs the checking personnel to perform accurate checking, so that enterprises are prevented from falsifying;
The emergency checking and law enforcement unit 4 comprises an illegal activity information pushing module 402 and a law enforcement module 403, wherein the illegal activity information pushing module 402 receives a checking result in the remote supervision cloud platform 107 and judges whether a target enterprise is illegal or not, and after the illegal activity is true, the illegal activity information is uploaded to the remote supervision cloud platform 107, and the law enforcement module 403 receives the illegal activity information and the illegal activity pushed in the remote supervision cloud platform 107 and informs law enforcement personnel to perform law enforcement; the law enforcement module 403 timely informs law enforcement personnel to perform law enforcement, so that the supervision of the remote supervision system is improved.
The remote supervision method based on the Internet of things technology comprises the following steps of:
Step one: the method comprises the steps of collecting water quality data of an enterprise sewage discharge port, a river sewage discharge port, a sewage discharge official network and a river section through various water quality sensors in a sensor module 101, transmitting data collected by the water quality sensors corresponding to the water quality data through a plurality of ZigBee terminal nodes 102, receiving and transmitting the data transmitted by all the ZigBee terminal nodes 102 through a ZigBee coordinator node 103, receiving the data of each water quality sensor transmitted by the ZigBee coordinator node 103 through a microprocessor 104, transmitting the raw data collected by the sensors to a remote supervision cloud platform 107 through a 5G network through a 5G communication module 105, or transmitting the data to the remote supervision cloud platform 107 through an Ethernet network through an Ethernet module 106, and storing the data of the sensors through a database in the remote supervision cloud platform 107;
Step two: the data stored in the remote monitoring cloud platform 107 is preprocessed through the online data processing module 201, noise elimination, correction and smoothing are firstly carried out on the data, then data conversion is carried out, the preprocessed original data is converted into a time sequence, the time sequence in the online data processing module 201 is analyzed through the spectrum analysis module 202, the data is returned to the sensor module 101, a sample retaining device is controlled to automatically retain samples of abnormal drainage measured by the sensor module 101, a time sequence abnormal detection early warning is carried out through the burst pollution dynamic early warning module 203, dynamic early warning is carried out on burst pollution, firstly, a clustering algorithm is used for training and clustering historical monitoring data, then wavelet denoising is carried out, a wavelet low-frequency time sequence is predicted through an artificial neural network, a high-frequency part is predicted through zero-resetting operation to zero a high-frequency time sequence, then the low-frequency part and the high-frequency part are predicted through wavelet reconstruction, a historical residual time sequence is obtained through difference between the rear time sequence and the actual monitoring time sequence, in addition, a current time actual value and a wavelet neural network predicted value are subjected to difference, if the current time is obtained, a water quality pollution duration is a water quality duration is smaller than a specified time duration, if a water quality duration is equal to a specified time duration, and a water quality pollution duration is longer than a specified time duration, if a water quality duration is a water quality duration of a water quality pollution duration, at this time, the sudden pollution dynamic early warning module 203 uploads the early warning information to the remote monitoring cloud platform 107;
Step three: the method comprises the steps of sending early warning information to an emergency response module 301 through a remote supervision cloud platform 107, judging the authenticity of early warning data through the emergency response module 301, starting emergency response after eliminating sensor abnormal reasons and data transmission abnormal reasons, triggering early warning, performing online analysis tracing through an analysis tracing module 302, performing tracing analysis on project area pollution through a statistical tracing technology, performing manual offline analysis tracing through a sample-remaining detection module 303, determining characteristic pollutants through offline chromatographic mass spectrometry, searching a characteristic pollutant database of a possible pollution source, performing pollution tracing through three-dimensional fluorescent spectrum qualitative tracing, performing map characteristic recognition including water line intensity and density recognition, water line peak number recognition and water line peak position recognition, performing map characteristic extraction, needing to perform non-closed curve density extraction firstly, performing curve fitting later, performing closed curve number and position extraction, performing ellipse after the map characteristic extraction is completed, performing map characteristic matching, including performing three-dimensional fluorescent map database, establishing and supervised matching algorithm establishment, performing remote supervision matching algorithm establishment according to the analysis conclusion 304 and performing online supervision cloud-remaining analysis conclusion module 303, and performing remote supervision cloud-remaining analysis conclusion on the pollution platform according to the trace result;
Step four: the traceability result pushed by the remote supervision cloud platform 107 is received through the checking module 401, then the checking personnel are notified to perform on-site checking, the working condition of the detection facility is checked, the enterprise emission behavior is checked, the enterprise data is compared and checked, the situation that the enterprise uploaded data is falsified and falsified is avoided, the emission standard and the emission quantity of pollutants are measured and checked, the result is uploaded to the remote supervision cloud platform 107, the checking result is stored through the remote supervision cloud platform 107 to serve as evidence for storage, whether the enterprise has illegal behaviors or not is judged according to the checking result in the checking module 401, the enterprise illegal behavior information transmitted by the remote supervision cloud platform 107 is received through the illegal behavior information pushing module 402, and then the law enforcement module 403 is notified to law enforcement personnel to perform timely law enforcement.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. Remote supervisory systems based on internet of things, including remote supervisory data acquisition unit (1), on-line unusual early warning unit (2), pollute tracing to source unit (3) and urgent check and law enforcement unit (4), its characterized in that:
The remote supervision data acquisition unit (1), the remote supervision data acquisition unit (1) is used for acquiring data of the environment in the supervision area and transmitting the data to the cloud end through the internet of things, and the remote supervision data acquisition unit (1) is used for transmitting the data of the cloud end;
The online abnormality early warning unit (2) receives the data acquired by the remote supervision data acquisition unit (1), performs online analysis on the received data and early warning according to a processing result, and the online abnormality early warning unit (2) transmits early warning information to the cloud of the remote supervision data acquisition unit (1);
The pollution tracing unit (3), the pollution tracing unit (3) receives the early warning information received by the remote supervision data acquisition unit (1), performs online and offline tracing analysis on the early warning data, and timely finds out a pollution source according to a tracing analysis result, and the pollution tracing unit (3) transmits an analysis conclusion to the cloud of the remote supervision data acquisition unit (1);
the system comprises an emergency checking and law enforcement unit (4), wherein the emergency checking and law enforcement unit (4) receives a traceability result received by the remote supervision data acquisition unit (1), performs on-site checking on pollution forming reasons, timely performs law enforcement against rules, and transmits the rules against rules to the cloud of the remote supervision data acquisition unit (1).
2. The internet of things-based remote supervision system according to claim 1, wherein: the remote supervision data acquisition unit (1) comprises a sensor module (101), zigBee terminal nodes (102) and a ZigBee coordinator node (103), wherein the sensor module (101) comprises a water quality sensor, a PH sensor, a turbidity sensor, a dissolved oxygen sensor, a nitrogen oxygen sensor and a Yu Fu sensor, the sensor module (101) further comprises an automatic sample reserving device for reserving abnormal drainage, the ZigBee terminal nodes (102) share a plurality of sensors matched with the sensor module (101) for use, data acquired by the sensors are transmitted through the ZigBee terminal nodes (102), and the ZigBee coordinator node (103) receives the data transmitted by all the ZigBee terminal nodes (102) and transmits all the data.
3. The internet of things-based remote supervision system according to claim 2, wherein: the remote supervision data acquisition unit (1) comprises a microprocessor (104), a 5G communication module (105), an Ethernet module (106) and a remote supervision cloud platform (107), wherein the microprocessor (104) is an STM32 processor, data transmitted by a ZigBee coordinator node (103) is received through the microprocessor (104), the 5G communication module (105) is connected with the microprocessor (104) and then transmits the data through a 5G network, the Ethernet module (106) is connected with the microprocessor (104) and then transmits the data through an Ethernet network, the remote supervision cloud platform (107) receives the data transmitted by the 5G communication module (105) or the Ethernet module (106) through the network, and a database is established in the remote supervision cloud platform (107) and stores the data acquired by the sensor module (101).
4. The internet of things-based remote supervision system according to claim 3, wherein: the online anomaly early warning unit (2) comprises an online data processing module (201) and a spectrum analysis module (202), wherein the online data processing module (201) processes data stored in the remote supervision cloud platform (107), firstly, preprocessing, including noise elimination, correction and smoothing, is performed on raw data collected by a sensor, then data conversion is performed, the preprocessed raw data is converted into a time sequence, and the spectrum analysis module (202) performs spectrum analysis on the data converted into the time sequence by the online data processing module (201), identifies periodic anomalies through Fourier transformation and identifies aperiodic anomalies through continuous wavelet transformation.
5. The internet of things-based remote supervision system according to claim 4, wherein: the online anomaly early-warning unit (2) comprises a sudden pollution dynamic early-warning module (203), the sudden pollution dynamic early-warning module (203) carries out anomaly early-warning based on a neural network of a historical baseline, a small spectrum analysis algorithm and an over-standard method, wherein a soft measurement time sequence of conventional online monitoring data production is subjected to time sequence anomaly detection early-warning, the occurrence of anomalies in the time sequence is early-warned through the time sequence anomaly early-warning based on a clustering algorithm, the historical monitoring data stored in a database of a remote supervision cloud platform (107) is firstly clustered through training by adopting the clustering algorithm, then the anomaly degree is calculated for a data object to be monitored through calculating the distance between the data object and a clustering center, the anomaly detection early-warning is carried out through constructing a soft measurement model based on water quality parameter correlation analysis and multiple regression analysis, the time sequence anomaly detection early-warning is directly carried out through constructing a wavelet neural network data flow anomaly detection model, and the sudden pollution dynamic early-warning module (203) transmits the early-warning data to the remote supervision cloud platform (107), and the wavelet neural network data flow anomaly detection model comprises a continuous wavelet transformation algorithm.
6. The internet of things-based remote supervision system according to claim 5, wherein: the pollution tracing unit (3) comprises an emergency response module (301) and an analysis tracing module (302), the emergency response module (301) receives early warning data uploaded by the sudden pollution dynamic early warning module (203) in the remote supervision cloud platform (107), then the authenticity of the early warning data is judged, if the fact that the sensor in the sensor module (101) works normally and the data transmission process is normal, emergency response is started, otherwise, emergency early warning is canceled, an operation and maintenance program is started, and the analysis tracing module (302) performs analysis tracing on the early warning data through a statistical tracing technology comprising a principal component analysis PCA, a non-negative constraint factor analysis method and a positive definite matrix decomposition method.
7. The internet of things-based remote supervision system according to claim 6, wherein: the pollution tracing unit (3) comprises a sample reserving detection module (303) and an analysis conclusion module (304), the sample reserving detection module (303) performs offline chromatographic mass spectrometry analysis manually to determine characteristic pollutants, a characteristic pollutant database of a possible pollution source is searched for pollution tracing, detection is performed through a fluorescence spectrometry, the analysis conclusion module (304) determines a final pollution source position according to an online tracing result of the analysis tracing module (302) and an offline tracing result analysis conclusion of the sample reserving detection module (303), a tracing path, a pollution range and a pollutant concentration are determined through the online tracing result, online tracing authenticity is verified through the offline tracing result, a target enterprise list is determined, and the analysis conclusion module (304) transmits analysis conclusion data to a remote supervision cloud platform (107).
8. The internet of things-based remote supervision system according to claim 7, wherein: the emergency checking and law enforcement unit (4) comprises a checking module (401), the checking module (401) receives a traceability result transmitted in the remote supervision cloud platform (107), then pushes emergency information to a checking person, checks pollution reasons through the checking person, and comprises the steps of detecting whether a facility normally operates, whether discharge behaviors are abnormal, whether enterprise data are falsified, whether pollutant discharge exceeds a standard and whether pollutant discharge exceeds a standard, and uploading the checking result to the remote supervision cloud platform (107).
9. The internet of things-based remote supervision system according to claim 8, wherein: the emergency checking and law enforcement unit (4) comprises a rule violation information pushing module (402) and a law enforcement module (403), the rule violation information pushing module (402) receives a checking result in the remote supervision cloud platform (107) and judges whether a target enterprise is in rule violation, the rule violation information is uploaded to the remote supervision cloud platform (107) after the rule violation is true, and the law enforcement module (403) receives the rule violation enterprise information and rule violation pushed in the remote supervision cloud platform (107) and informs law enforcement personnel to conduct law enforcement.
10. The remote supervision method based on the internet of things technology according to any one of claims 1-9, characterized by comprising the following steps:
Step one: the method comprises the steps of collecting water quality data of an enterprise sewage discharge port, a river sewage discharge port, a sewage drainage official network and a river section through various water quality sensors in a sensor module (101), transmitting data collected by the water quality sensors corresponding to the water quality data through a plurality of ZigBee terminal nodes (102), receiving and transmitting the data transmitted by all ZigBee terminal nodes (102) through a ZigBee coordinator node (103), receiving the data of each water quality sensor transmitted by the ZigBee coordinator node (103) through a microprocessor (104), transmitting the original data collected by the sensors to a remote supervision cloud platform (107) through a 5G network through a 5G communication module (105), or transmitting the data to the remote supervision cloud platform (107) through an Ethernet network through an Ethernet module (106), and storing the data of the sensors through a database in the remote cloud platform (107);
Step two: the data stored in the remote supervision cloud platform (107) is preprocessed through the online data processing module (201), noise elimination, correction and smoothing are firstly carried out on the data, then data conversion is carried out, the preprocessed original data is converted into a time sequence, the time sequence in the online data processing module (201) is analyzed through the spectrum analysis module (202), the data is returned to the sensor module (101), the sample retaining device is controlled to automatically retain samples of abnormal drainage measured by the sensor module (101), the burst pollution dynamic early warning module (203) is used for carrying out time sequence abnormal detection early warning, the burst pollution is carried out dynamic early warning, firstly, the history monitoring data is trained and clustered through a clustering algorithm, then wavelet denoising is carried out, for a low-frequency part, the wavelet low-frequency time sequence is predicted through the artificial neural network, for the high frequency part, the high frequency time sequence is zeroed through zeroing operation, then the low frequency part and the high frequency part are predicted to be the post time sequence through wavelet reconstruction, the post time sequence is differenced with the actual monitoring time sequence to obtain the historical residual time sequence, furthermore, the actual monitoring value of the current moment is differenced with the predicted value of the wavelet neural network to obtain the current moment residual, after the early warning threshold interval is set, whether the historical residual and the current residual are in the threshold interval range is judged, if yes, the time sequence of normal water quality is judged, if no, the duration of the residual is compared with the appointed duration, if less than the appointed duration, the time sequence of normal water quality is still judged, if more than the appointed duration, the early warning is that an emergency pollution accident possibly occurs, and the emergency pollution dynamic early warning module (203) uploads the early warning information to the remote monitoring cloud platform (107);
step three: the early warning information is sent to an emergency response module (301) through a remote supervision cloud platform (107), the authenticity of early warning data is judged through the emergency response module (301), after the sensor abnormality cause and the data transmission abnormality cause are eliminated, the early warning is triggered, the emergency response is started, online analysis tracing is carried out through an analysis tracing module (302), the project area pollution is traced by a statistical tracing technology, the project area pollution is analyzed in a tracing way, the manual offline analysis tracing is carried out through a sample reserving detection module (303), the characteristic pollutant is determined through offline chromatographic mass spectrometry, the pollution tracing is carried out by searching a characteristic pollutant database of the possible pollution source, the pollution tracing is carried out through three-dimensional fluorescent spectrum qualitative tracing, firstly, carrying out map feature recognition, including water line intensity and density recognition, water line peak number recognition and water line peak position recognition, then carrying out map feature extraction, namely carrying out non-closed curve density extraction, then carrying out curve fitting, then carrying out closed curve number and position extraction, finally carrying out ellipse fitting, carrying out map feature matching after the map feature extraction is finished, including carrying out three-dimensional fluorescent map database construction, unsupervised matching algorithm establishment and supervised matching algorithm establishment, determining a final pollution source position according to an online tracing result of an analysis tracing module (302) and an offline tracing result analysis conclusion of a reserved sample detection module (303) through an analysis conclusion module (304), and then uploading the conclusion to a remote supervision cloud platform (107);
Step four: the method comprises the steps of receiving a traceability result pushed by a remote supervision cloud platform (107) through a checking module (401), informing a checking person to perform on-site checking, checking the working condition of a detection facility, checking enterprise emission behaviors, comparing and checking enterprise data, avoiding the situation that the data uploaded by an enterprise are falsified, measuring and checking the emission standard and emission quantity of pollutants, uploading the result to the remote supervision cloud platform (107), storing the checking result through the remote supervision cloud platform (107) to serve as evidence for storage, judging whether the enterprise has illegal behaviors according to the checking result in the checking module (401), receiving the enterprise illegal behavior information transmitted by the remote supervision cloud platform (107) through an illegal behavior information pushing module (402), and informing law enforcement staff to perform timely law enforcement through a law enforcement module (403).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410188366.XA CN118095843A (en) | 2024-02-20 | 2024-02-20 | Remote supervision system and method based on Internet of things technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410188366.XA CN118095843A (en) | 2024-02-20 | 2024-02-20 | Remote supervision system and method based on Internet of things technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118095843A true CN118095843A (en) | 2024-05-28 |
Family
ID=91143321
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410188366.XA Pending CN118095843A (en) | 2024-02-20 | 2024-02-20 | Remote supervision system and method based on Internet of things technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118095843A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118520317A (en) * | 2024-07-23 | 2024-08-20 | 四川福莱宝生物科技有限公司 | Biological element data analysis method suitable for high-throughput analysis |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN210983490U (en) * | 2019-10-18 | 2020-07-10 | 重庆华悦生态环境工程研究院有限公司 | Water quality sudden pollution dynamic early warning information monitoring system |
| CN111898691A (en) * | 2020-08-05 | 2020-11-06 | 生态环境部华南环境科学研究所 | River sudden water pollution early warning tracing method, system, terminal and medium |
| CN216051361U (en) * | 2021-09-24 | 2022-03-15 | 佛山市奥博环保技术有限公司 | Water pollution early warning device of tracing to source |
| CN116071895A (en) * | 2023-02-06 | 2023-05-05 | 广东慧航天唯科技有限公司 | Industrial wastewater process emission monitoring and early warning method |
| US20230252487A1 (en) * | 2022-08-03 | 2023-08-10 | Sichuan academy of environmental Science | System and method for dynamic management and control of air pollution |
-
2024
- 2024-02-20 CN CN202410188366.XA patent/CN118095843A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN210983490U (en) * | 2019-10-18 | 2020-07-10 | 重庆华悦生态环境工程研究院有限公司 | Water quality sudden pollution dynamic early warning information monitoring system |
| CN111898691A (en) * | 2020-08-05 | 2020-11-06 | 生态环境部华南环境科学研究所 | River sudden water pollution early warning tracing method, system, terminal and medium |
| CN216051361U (en) * | 2021-09-24 | 2022-03-15 | 佛山市奥博环保技术有限公司 | Water pollution early warning device of tracing to source |
| US20230252487A1 (en) * | 2022-08-03 | 2023-08-10 | Sichuan academy of environmental Science | System and method for dynamic management and control of air pollution |
| CN116071895A (en) * | 2023-02-06 | 2023-05-05 | 广东慧航天唯科技有限公司 | Industrial wastewater process emission monitoring and early warning method |
Non-Patent Citations (4)
| Title |
|---|
| 丛北华: "《智慧社区物联网系统》", 31 January 2022, 上海科学技术出版社, pages: 15 - 16 * |
| 张剑锋: "《城市生活垃圾清洁直运》", 30 April 2021, 浙江工商大学出版社, pages: 75 - 76 * |
| 王时龙: "《中国战略性新兴产业研究与发展 智慧工业》", 31 December 2021, 机械工业出版社, pages: 70 - 74 * |
| 陈细亻毛: "城市居民生活饮用水水质异常检测方法研究", 科技经济市场, no. 12, 15 December 2013 (2013-12-15), pages 69 - 70 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118520317A (en) * | 2024-07-23 | 2024-08-20 | 四川福莱宝生物科技有限公司 | Biological element data analysis method suitable for high-throughput analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111898691B (en) | River burst water pollution early warning and tracing method, system, terminal and medium | |
| CN116128260B (en) | Data sample-based key enterprise environment analysis method | |
| CN210895538U (en) | Intelligent water quality supervision device and equipment | |
| CN118095843A (en) | Remote supervision system and method based on Internet of things technology | |
| CN116823067B (en) | Method and device for determining water quality cleaning state of pipe network and electronic equipment | |
| CN114429308A (en) | Enterprise security risk assessment method and system based on big data | |
| CN115561416A (en) | Method and device for detecting inlet water quality of sewage treatment plant in real time | |
| CN111191855B (en) | Water quality abnormal event identification and early warning method based on pipe network multi-element water quality time sequence data | |
| CN114330120A (en) | 24-hour PM prediction based on deep neural network2.5Method of concentration | |
| CN117291781B (en) | Sudden water pollution tracing method, equipment and medium | |
| CN112903946A (en) | Novel sporadic industrial wastewater collection water quality detection early warning method | |
| CN116522086B (en) | Data recovery and water quality detection method and device based on variation self-encoder | |
| CN115792165B (en) | Intelligent environmental water quality monitoring method and system | |
| CN113836813B (en) | Blast furnace tuyere water leakage detection method based on data analysis | |
| CN111522860B (en) | Water quality early warning analysis method and system based on biological behaviors | |
| CN117035230B (en) | Sewage treatment equipment running state evaluation method based on big data analysis | |
| CN115309845B (en) | Water pollution tracing method and system based on water system compiler and machine learning treatment | |
| CN112032567A (en) | Buried gas pipeline leakage risk prediction system | |
| CN118278829B (en) | Space-time simulation display system based on one-dimensional water quality simulation method | |
| CN118393111B (en) | Soil pollution condition sampling monitoring data analysis method | |
| CN117455268B (en) | Bus one-key emergency escape data analysis system and method based on Internet of things | |
| CN117912211B (en) | Garden environment data analysis and alarm system based on Internet of things | |
| CN118296513B (en) | Transformer substation foreign matter detection method and system | |
| CN118333465B (en) | Construction engineering quality detection supervision method, system and platform | |
| CN117349777B (en) | Intelligent identification system and method for online monitoring data of water environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |