CN118090977B - Water quality monitoring system based on wireless sensor network - Google Patents
Water quality monitoring system based on wireless sensor network Download PDFInfo
- Publication number
- CN118090977B CN118090977B CN202410289298.6A CN202410289298A CN118090977B CN 118090977 B CN118090977 B CN 118090977B CN 202410289298 A CN202410289298 A CN 202410289298A CN 118090977 B CN118090977 B CN 118090977B
- Authority
- CN
- China
- Prior art keywords
- mass spectrum
- mass
- pseudo
- generator
- representing
- 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.)
- Active
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 67
- 238000012544 monitoring process Methods 0.000 title claims abstract description 18
- 238000001819 mass spectrum Methods 0.000 claims abstract description 189
- 238000005070 sampling Methods 0.000 claims abstract description 44
- 238000004949 mass spectrometry Methods 0.000 claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000013528 artificial neural network Methods 0.000 claims abstract description 15
- 125000004122 cyclic group Chemical group 0.000 claims abstract description 14
- 238000005516 engineering process Methods 0.000 claims abstract description 5
- 238000004128 high performance liquid chromatography Methods 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims abstract description 4
- 238000004885 tandem mass spectrometry Methods 0.000 claims abstract description 4
- 230000003595 spectral effect Effects 0.000 claims description 13
- 150000001875 compounds Chemical class 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000011144 upstream manufacturing Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000000540 analysis of variance Methods 0.000 claims description 3
- 238000011109 contamination Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 239000003344 environmental pollutant Substances 0.000 abstract description 6
- 231100000719 pollutant Toxicity 0.000 abstract description 6
- 230000003042 antagnostic effect Effects 0.000 abstract description 2
- 238000001228 spectrum Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000003911 water pollution Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
- G01N30/62—Detectors specially adapted therefor
- G01N30/72—Mass spectrometers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
- G01N30/86—Signal analysis
- G01N30/8675—Evaluation, i.e. decoding of the signal into analytical information
- G01N30/8679—Target compound analysis, i.e. whereby a limited number of peaks is analysed
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
- G01N30/86—Signal analysis
- G01N30/8693—Models, e.g. prediction of retention times, method development and validation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0475—Generative networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/094—Adversarial learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q9/00—Arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/20—Controlling water pollution; Waste water treatment
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Pathology (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Library & Information Science (AREA)
- Other Investigation Or Analysis Of Materials By Electrical Means (AREA)
Abstract
The invention relates to the technical field of water quality monitoring, and discloses a water quality monitoring system based on a wireless sensor network, which comprises the following components: the water sample collection module is used for collecting water samples at n points in a target water area; the water body sample processing module is used for obtaining mass spectrum data of a water body sample through a high performance liquid chromatography tandem mass spectrometry technology; a mass spectrometry feature generation module that generates a sampling mass spectrometry feature and a real mass spectrometry feature based on mass spectrometry data; the mass spectrum data restoration module is used for inputting the sampled mass spectrum characteristics into the cyclic countermeasure neural network and outputting pseudo-restoration mass spectrum characteristics; the pollution source tracing module is used for judging the pollution source position; the invention considers the change and loss of the pollutant in the pollution source in the water quality flowing process, and eliminates the error of the mass spectrum characteristic of the pollution source and the real mass spectrum characteristic of the pollution source through the circulating antagonistic neural network, thereby accurately judging the position of the pollution source.
Description
Technical Field
The invention relates to the field of water quality monitoring, in particular to a water quality monitoring system based on a wireless sensor network.
Background
The Chinese patent with the bulletin number of CN116263444B, named high-resolution mass spectrum non-targeted analysis water pollution source identification and tracing method, discloses the following contents: collecting a plurality of point-location water body samples from upstream to downstream in a target water area, performing ultra-high performance liquid chromatography-high resolution mass spectrum non-targeted data collection on the plurality of samples to obtain an original data set, performing data preprocessing on the original data set subjected to high resolution mass spectrum non-targeted analysis to obtain a high resolution mass spectrum data set containing mass-to-charge ratio, retention time, peak height and peak area, performing statistical analysis on the high resolution mass spectrum data set to obtain a pollution source sample with abnormal mass spectrum data, determining a sampling point location interval of the pollution source, performing high resolution mass spectrum information difference calculation on the basis of the pollution source sample, a background sample and a previous pollution source sample to obtain a characteristic map of the pollution source, and determining the pollutant type of the pollution source by combining a pollution mass spectrum database to further determine the type of the pollution source.
According to the technical scheme, the water quality pollution source positioning is performed based on a chemical mass balance method, but the chemical mass balance method ignores the change and loss of pollutants in the transmission process, the change and loss of different pollutants in the transmission process are different, the data of the downstream data acquisition points of the pollution sources show the downstream transmission result of the pollutants of the pollution sources, the characteristic spectrum of the pollution sources obtained according to the difference of mass spectrum information is different from the characteristic spectrum of the real pollution sources, the larger the difference is, the larger the number of the pollution sources is, the larger the difference is the closer the pollution sources are, and the position of the pollution sources cannot be accurately judged.
Disclosure of Invention
The invention provides a water quality monitoring system based on a wireless sensor network, which solves the technical problem that the position of a pollution source cannot be accurately judged due to the fact that the characteristic spectrum of the pollution source obtained by the difference of mass spectrum information in the related technology is different from the characteristic spectrum of a real pollution source.
The invention provides a water quality monitoring system based on a wireless sensor network, which comprises:
the water sample collection module is used for sequentially collecting water samples of n points from upstream to downstream in the target water area;
The water body sample processing module is used for obtaining mass spectrum data of a water body sample through a high performance liquid chromatography tandem mass spectrometry technology;
A mass spectrometry feature generation module that generates a sampling mass spectrometry feature and a real mass spectrometry feature based on mass spectrometry data; the sampled mass spectrum features are expressed as: wherein 、、The 1 st, 2 nd and n th point positions which represent the characteristics of the sampling mass spectrum correspond to sequence units;
wherein Respectively representing the ionic strength of the 1~u th mass-to-charge ratio of the 1 st scanning times of the water body sample at the nth point,Respectively representing the ionic strength of the 1~u th mass-to-charge ratio of the 2 nd scanning times of the water body sample at the nth point,Respectively representing the ionic strength of the 1~u th mass-to-charge ratio of the nth point water sample in the v scanning times;
The true mass spectrum features are expressed as: wherein 、、The 1 st, 2 nd and n th point positions which represent the characteristics of the real mass spectrum correspond to sequence units;
Wherein the method comprises the steps of ，Representing a collection of pollution sources upstream of the nth point,A1 st sequence unit representing a sample mass spectrum feature;
The mass spectrum data restoration module is used for inputting the sampled mass spectrum characteristics into the cyclic countermeasure neural network and outputting pseudo-restoration mass spectrum characteristics; the pseudo repair mass spectrum characteristic and the real mass spectrum characteristic are the same in representation;
And the pollution source tracing module is used for outputting F values of adjacent sequence units in the pseudo-sampling mass spectrum characteristics sequentially through an analysis of variance method, and judging that pollution sources exist between the corresponding points of the adjacent sequence units if the F values are smaller than a critical F value.
Further, the distances between two adjacent points are equal.
Further, the method comprises the steps of,Mass spectral data representing a water sample of an ith pollution source;
；
Wherein the method comprises the steps of Respectively representing the ion intensity of the 1~u th mass-to-charge ratio of the 1 st scanning times of the ith pollution source,Respectively representing the ion intensity of the 1~u th mass-to-charge ratio of the 2 nd scanning times of the ith pollution source,The ion intensities of the 1~u th mass-to-charge ratios of the ith scan times of the ith contamination source are shown, respectively.
Further, on the premise that the position of each pollution source is known, acquiring a water body sample at the position of each pollution source to obtain mass spectrum data; the method for acquiring mass spectrum data of the water body sample acquired by the position of the point position, the background sample and the pollution source is the same, the adopted scanning times are v, the mass-to-charge ratio of the ion intensity between 0 and U is recorded in each scanning, the recorded actual discrete value is a plurality of mass-to-charge ratio discrete values after the value range mean value of the mass-to-charge ratio corresponding to 0 to U is discretized; both the number of scans and the recorded mass-to-charge ratio range are adjustable parameters, default v=1000, u=200.
Further, the cyclic countermeasure neural network includes: a first generator, a first arbiter, a second generator, and a second arbiter;
The first generator inputs the sampling mass spectrum characteristics and outputs the pseudo repair mass spectrum characteristics;
The first discriminator inputs a pseudo repair mass spectrum characteristic and a real mass spectrum characteristic, and is used for discriminating whether the pseudo repair mass spectrum characteristic is derived from the first generator or the real mass spectrum characteristic, and outputting a value between 0 and 1 to represent a probability value that the pseudo repair mass spectrum characteristic is the real mass spectrum characteristic;
the second generator inputs the pseudo repair mass spectrum characteristics and outputs pseudo sampling mass spectrum characteristics;
The second discriminator inputs the pseudo-sampling mass spectrum characteristic and the sampling mass spectrum characteristic input by the first generator, and is used for discriminating whether the pseudo-sampling mass spectrum characteristic is derived from the sampling mass spectrum characteristic input by the second generator or the first generator, and outputting a value between 0 and 1, wherein the value represents a probability value that the pseudo-sampling mass spectrum characteristic is the sampling mass spectrum characteristic;
Loss function of countermeasures against losses of first generator and first discriminator The calculation formula of (2) is as follows:
；
Wherein G represents the first generator and wherein, Representing a first discriminator, x representing the sampled mass spectrum characteristics input by the first generator, y representing the true mass spectrum characteristics,A pseudo-repair mass spectrum characteristic representing the output of the first generator,A probability value representing that the first discriminator discriminates that the real mass spectrum feature is a real mass spectrum feature,A probability value representing that the pseudo-repair mass spectrum feature output by the first discriminator discriminates as a true mass spectrum feature,Representing minimizing the loss function of the first generator,Representing maximizing a loss function of the first arbiter;
the calculation formula of the loss function of the countermeasures loss of the second generator and the second discriminator is as follows:
；
wherein F represents the second generator and wherein, A second of the discriminators is indicated as such,Representing a pseudo-repair mass spectrum characteristic of the second generator input,Representing the characteristics of a sample mass spectrum,Representing a pseudo-sampled mass spectrum characteristic of the output of the second generator,A probability value representing that the second discriminator discriminates that the sampled mass spectrum feature is a sampled mass spectrum feature,Representing the probability value that the second discriminator discriminates that the pseudo-sampled mass spectrum feature output by the second generator is a sampled mass spectrum feature,Representing minimizing the loss function of the second generator,Representing maximizing a loss function of the second arbiter;
the calculation formula of the loss function of the cyclic coherence loss of the cyclic countermeasure neural network is as follows:
；
Where G denotes a first generator, F denotes a second generator, x denotes a sampled mass spectrum characteristic of the first generator input, A pseudo-repair mass spectrum signature representing a first generated output,A pseudo-repair mass spectrum feature representing the output of the first generator is input to a pseudo-sample mass spectrum feature output by the second generator, y represents a true mass spectrum feature,Representing a pseudo-sampled mass spectrum characteristic of the output of the second generator,A pseudo-sampled mass spectrum characteristic representing the output of the second generator is input to a pseudo-repair mass spectrum characteristic of the output of the first generator,Representation ofNorms are used to measure differences between mass spectral features.
Further, the first generator, the first discriminator, the second generator and the second discriminator of the recurrent countermeasure neural network are trained in combination during training.
Further, the compound for analyzing the water body sample according to the pseudo-sampling mass spectrum characteristics comprises the following modules:
A mass spectrum generation module for generating a first mass spectrum from the pseudo-sampled mass spectrum features;
The number of the first mass spectrograms is n x v, v first mass spectrograms are generated for each point, the horizontal axis of the first mass spectrograms represents the mass-to-charge ratio, and the vertical axis represents the ion intensity;
the s-th sequence of pseudo-sampled mass spectral features is expressed as:
wherein Respectively representing the ion intensity of 1~u th mass-to-charge ratio of a first mass spectrogram of the 1 st scanning times of the generated s th point; Respectively representing the ion intensity of 1~u th mass-to-charge ratio of the first mass spectrogram of the generated 2 nd scanning times of the s th point; The ion intensity of 1~u th mass-to-charge ratio of the first mass spectrogram respectively representing the generated v scanning times of the s th point;
the total ion chromatogram generation module is used for generating a total ion chromatogram for each point position based on the characteristics of the pseudo-sampling mass spectrum;
the component analysis module extracts a first mass spectrogram mark of corresponding scanning times based on chromatographic peaks of the total ion chromatograms to be a second mass spectrogram; and searching a mass spectrogram-compound database based on the second mass spectrograms to obtain corresponding compounds, wherein all the compounds searched by the second mass spectrograms at one point are judged to be the compounds contained in the water body at the point.
Further, sequentially generating a first mass spectrogram through first mass spectrogram visualization software according to the ionic strength of the 1~u th mass-to-charge ratio of v scanning times of n sequence units of the pseudo-sampling mass spectrum characteristics.
Further, the data for generating the total ion chromatogram for the s-th spot is derived from the s-th sequence of pseudo-sampled mass spectral features.
Further, the abscissa of the total ion chromatogram is represented by the number of scans in peak time, and the ordinate is the total ion intensity, for example, the total ion intensity corresponding to the nth scan number is the cumulative sum of the ion intensities of the 1~u th mass-to-charge ratios of the nth scan number.
The invention has the beneficial effects that: the invention considers the change and loss of the pollutant in the pollution source in the water quality flowing process, and eliminates the error of the mass spectrum characteristic of the pollution source and the real mass spectrum characteristic of the pollution source through the circulating antagonistic neural network, thereby accurately judging the position of the pollution source.
Drawings
Fig. 1 is a system block diagram of the present invention.
Detailed Description
The subject matter described herein will now be discussed with reference to example embodiments. It is to be understood that these embodiments are merely discussed so that those skilled in the art may better understand and implement the subject matter described herein and that changes may be made in the function and arrangement of the elements discussed without departing from the scope of the disclosure herein. Various examples may omit, replace, or add various procedures or components as desired. In addition, features described with respect to some examples may be combined in other examples as well.
It is to be noted that unless otherwise defined, technical or scientific terms used in one or more embodiments of the present invention should be taken in a general sense as understood by one of ordinary skill in the art to which the present invention belongs. The use of the terms "first," "second," and the like in one or more embodiments of the present invention does not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or articles listed after the word are included in the word or "comprising", and equivalents thereof, but does not exclude other elements or articles "connected" or "connected", and the like, are not limited to physical or mechanical connections, but may include electrical connections, both direct and indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
As shown in fig. 1, a water quality monitoring system based on a wireless sensor network includes:
A water sample collection module 101, configured to collect water samples of n points sequentially from upstream to downstream in a target water area;
in one embodiment of the invention, the distances between two adjacent points are equal.
The water body sample processing module 102 is used for obtaining mass spectrum data of a water body sample through a high performance liquid chromatography tandem mass spectrometry technology;
A mass spectrometry feature generation module 103 that generates a sampling mass spectrometry feature and a real mass spectrometry feature based on mass spectrometry data;
The sampled mass spectrum features are expressed as: wherein 、、The 1 st, 2 nd and n th point positions which represent the characteristics of the sampling mass spectrum correspond to sequence units;
；
Wherein the method comprises the steps of Respectively representing the ionic strength of the 1~u th mass-to-charge ratio of the 1 st scanning times of the water body sample at the nth point,Respectively representing the ionic strength of the 1~u th mass-to-charge ratio of the 2 nd scanning times of the water body sample at the nth point,Respectively representing the ionic strength of the 1~u th mass-to-charge ratio of the nth point water sample in the v scanning times;
The true mass spectrum features are expressed as: wherein 、、The 1 st, 2 nd and n th point positions which represent the characteristics of the real mass spectrum correspond to sequence units;
Wherein the method comprises the steps of ，Representing a collection of pollution sources upstream of the nth point,A1 st sequence unit representing a sample mass spectrum feature,Mass spectral data representing a water sample of an ith pollution source;
；
Wherein the method comprises the steps of Respectively representing the ion intensity of the 1~u th mass-to-charge ratio of the 1 st scanning times of the ith pollution source,Respectively representing the ion intensity of the 1~u th mass-to-charge ratio of the 2 nd scanning times of the ith pollution source,Ion intensities of 1~u th mass-to-charge ratios, each representing a v-th scan number of an i-th contamination source;
acquiring a water body sample at the position of each pollution source on the premise of knowing the position of each pollution source to obtain mass spectrum data;
The method for acquiring mass spectrum data of the water body sample acquired by the position of the point position, the background sample and the pollution source is the same, the adopted scanning times are v, the mass-to-charge ratio of the ion intensity between 0 and U is recorded in each scanning, the recorded actual discrete value is a plurality of mass-to-charge ratio discrete values after the value range mean value of the mass-to-charge ratio corresponding to 0 to U is discretized; both the number of scans and the recorded mass-to-charge ratio range are adjustable parameters, default v=1000, u=200.
A mass spectrometry data repair module 104 for inputting the sampled mass spectrometry features into a cyclic countermeasure neural network, outputting pseudo-repair mass spectrometry features;
The pseudo-repair mass spectral features are identical to the real mass spectral features.
The cyclic countermeasure neural network includes: a first generator, a first arbiter, a second generator, and a second arbiter;
The first generator inputs the sampling mass spectrum characteristics and outputs the pseudo repair mass spectrum characteristics;
The first discriminator inputs a pseudo repair mass spectrum characteristic and a real mass spectrum characteristic, and is used for discriminating whether the pseudo repair mass spectrum characteristic is derived from the first generator or the real mass spectrum characteristic, and outputting a value between 0 and 1 to represent a probability value that the pseudo repair mass spectrum characteristic is the real mass spectrum characteristic;
the second generator inputs the pseudo repair mass spectrum characteristics and outputs pseudo sampling mass spectrum characteristics;
The second discriminator inputs the pseudo-sampling mass spectrum characteristic and the sampling mass spectrum characteristic input by the first generator, and is used for discriminating whether the pseudo-sampling mass spectrum characteristic is derived from the sampling mass spectrum characteristic input by the second generator or the first generator, and outputting a value between 0 and 1, wherein the value represents a probability value that the pseudo-sampling mass spectrum characteristic is the sampling mass spectrum characteristic;
Loss function of countermeasures against losses of first generator and first discriminator The calculation formula of (2) is as follows:
；
Wherein G represents the first generator and wherein, Representing a first discriminator, x representing the sampled mass spectrum characteristics input by the first generator, y representing the true mass spectrum characteristics,A pseudo-repair mass spectrum characteristic representing the output of the first generator,A probability value representing that the first discriminator discriminates that the real mass spectrum feature is a real mass spectrum feature,A probability value representing that the pseudo-repair mass spectrum feature output by the first discriminator discriminates as a true mass spectrum feature,Representing minimizing the loss function of the first generator,Representing maximizing a loss function of the first arbiter;
the calculation formula of the loss function of the countermeasures loss of the second generator and the second discriminator is as follows:
；
wherein F represents the second generator and wherein, A second of the discriminators is indicated as such,Representing a pseudo-repair mass spectrum characteristic of the second generator input,Representing the characteristics of a sample mass spectrum,Representing a pseudo-sampled mass spectrum characteristic of the output of the second generator,A probability value representing that the second discriminator discriminates that the sampled mass spectrum feature is a sampled mass spectrum feature,Representing the probability value that the second discriminator discriminates that the pseudo-sampled mass spectrum feature output by the second generator is a sampled mass spectrum feature,Representing minimizing the loss function of the second generator,Representing maximizing a loss function of the second arbiter;
the calculation formula of the loss function of the cyclic coherence loss of the cyclic countermeasure neural network is as follows:
；
Where G denotes a first generator, F denotes a second generator, x denotes a sampled mass spectrum characteristic of the first generator input, A pseudo-repair mass spectrum signature representing a first generated output,A pseudo-repair mass spectrum feature representing the output of the first generator is input to a pseudo-sample mass spectrum feature output by the second generator, y represents a true mass spectrum feature,Representing a pseudo-sampled mass spectrum characteristic of the output of the second generator,A pseudo-sampled mass spectrum characteristic representing the output of the second generator is input to a pseudo-repair mass spectrum characteristic of the output of the first generator,Representation ofA norm for measuring differences between mass spectral features;
in one embodiment of the invention, the first generator, the first arbiter, the second generator, and the second arbiter of the recurrent countermeasure neural network are trained in combination during training;
The pollution source tracing module 105 is used for outputting F values of adjacent sequence units in the pseudo-sampling mass spectrum characteristics sequentially through an analysis of variance method, and judging that pollution sources exist between the corresponding points of the adjacent sequence units if the F values are smaller than a critical F value;
a mass spectrum generation module 106 for generating a first mass spectrum from the pseudo-sampled mass spectrum features;
the number of the first mass spectrograms is n x v, v first mass spectrograms are generated for each point, the horizontal axis of the first mass spectrograms represents the mass-to-charge ratio, and the vertical axis represents the ion intensity.
The s-th sequence of pseudo-sampled mass spectral features is expressed as:
wherein Respectively representing the ion intensity of 1~u th mass-to-charge ratio of a first mass spectrogram of the 1 st scanning times of the generated s th point; Respectively representing the ion intensity of 1~u th mass-to-charge ratio of the first mass spectrogram of the generated 2 nd scanning times of the s th point; The ion intensity of 1~u th mass-to-charge ratio of the first mass spectrogram respectively representing the generated v scanning times of the s th point;
In one embodiment of the invention, the first mass spectrogram is generated by sequentially passing the ion intensity of 1~u mass-to-charge ratios of v scanning times of n sequence units of the pseudo-sampling mass spectrum characteristics through first mass spectrogram visualization software;
A total ion chromatogram generation module 107 that generates a total ion chromatogram for each point based on the pseudo-sampling mass spectrum characteristics;
Generating an s sequence of total ion chromatogram data from the pseudo-sampling mass spectrum characteristic for the s point location;
The abscissa of the total ion chromatogram is represented by the number of scans in peak time and the ordinate is the total ion intensity, e.g. the total ion intensity corresponding to the number of r scans is the cumulative sum of the ion intensities of the 1~u th mass-to-charge ratios of the number of r scans.
The component analysis module 108 extracts a first mass spectrogram mark of corresponding scanning times based on chromatographic peaks of the total ion chromatogram to be a second mass spectrogram; searching a mass spectrogram-compound database based on the second mass spectrogram to obtain corresponding compounds, wherein all the compounds searched by the second mass spectrogram of one point are judged to be the compounds contained in the water body of the point;
In one embodiment of the invention, the mass spectrum-compound database is a NIST mass spectrum library or a Willey mass spectrum library.
The embodiment has been described above with reference to the embodiment, but the embodiment is not limited to the above-described specific implementation, which is only illustrative and not restrictive, and many forms can be made by those of ordinary skill in the art, given the benefit of this disclosure, are within the scope of this embodiment.
Claims (9)
1. A water quality monitoring system based on wireless sensor network, characterized by comprising:
the water sample collection module is used for sequentially collecting water samples of n points from upstream to downstream in the target water area;
The water body sample processing module is used for obtaining mass spectrum data of a water body sample through a high performance liquid chromatography tandem mass spectrometry technology;
A mass spectrometry feature generation module that generates a sampling mass spectrometry feature and a real mass spectrometry feature based on mass spectrometry data; the sampled mass spectrum features are expressed as: wherein 、、The 1 st, 2 nd and n th point positions which represent the characteristics of the sampling mass spectrum correspond to sequence units;
wherein Respectively representing the ionic strength of the 1~u th mass-to-charge ratio of the 1 st scanning times of the water body sample at the nth point,Respectively representing the ionic strength of the 1~u th mass-to-charge ratio of the 2 nd scanning times of the water body sample at the nth point,Respectively representing the ionic strength of the 1~u th mass-to-charge ratio of the nth point water sample in the v scanning times;
The true mass spectrum features are expressed as: wherein 、、The 1 st, 2 nd and n th point positions which represent the characteristics of the real mass spectrum correspond to sequence units;
Wherein the method comprises the steps of ，Representing a collection of pollution sources upstream of the nth point,A1 st sequence unit representing a sample mass spectrum feature,Mass spectral data representing a water sample of an ith pollution source;
The mass spectrum data restoration module is used for inputting the sampled mass spectrum characteristics into the cyclic countermeasure neural network and outputting pseudo-restoration mass spectrum characteristics; the pseudo repair mass spectrum characteristic and the real mass spectrum characteristic are the same in representation;
The pollution source tracing module is used for outputting F values of adjacent sequence units in the pseudo-sampling mass spectrum characteristics sequentially through an analysis of variance method, and judging that pollution sources exist between the corresponding points of the adjacent sequence units if the F values are smaller than a critical F value;
The cyclic countermeasure neural network includes: a first generator, a first arbiter, a second generator, and a second arbiter;
The first generator inputs the sampling mass spectrum characteristics and outputs the pseudo repair mass spectrum characteristics;
The first discriminator inputs a pseudo repair mass spectrum characteristic and a real mass spectrum characteristic, and is used for discriminating whether the pseudo repair mass spectrum characteristic is derived from the first generator or the real mass spectrum characteristic, and outputting a value between 0 and 1 to represent a probability value that the pseudo repair mass spectrum characteristic is the real mass spectrum characteristic;
the second generator inputs the pseudo repair mass spectrum characteristics and outputs pseudo sampling mass spectrum characteristics;
The second discriminator inputs the pseudo-sampling mass spectrum characteristic and the sampling mass spectrum characteristic input by the first generator, and is used for discriminating whether the pseudo-sampling mass spectrum characteristic is derived from the sampling mass spectrum characteristic input by the second generator or the first generator, and outputting a value between 0 and 1, wherein the value represents a probability value that the pseudo-sampling mass spectrum characteristic is the sampling mass spectrum characteristic;
Loss function of countermeasures against losses of first generator and first discriminator The calculation formula of (2) is as follows:
；
Wherein G represents the first generator and wherein, Representing a first discriminator, x representing the sampled mass spectrum characteristics input by the first generator, y representing the true mass spectrum characteristics,A pseudo-repair mass spectrum characteristic representing the output of the first generator,A probability value representing that the first discriminator discriminates that the real mass spectrum feature is a real mass spectrum feature,A probability value representing that the pseudo-repair mass spectrum feature output by the first discriminator discriminates as a true mass spectrum feature,Representing minimizing the loss function of the first generator,Representing maximizing a loss function of the first arbiter;
the calculation formula of the loss function of the countermeasures loss of the second generator and the second discriminator is as follows:
；
wherein F represents the second generator and wherein, A second of the discriminators is indicated as such,Representing a pseudo-repair mass spectrum characteristic of the second generator input,Representing the characteristics of a sample mass spectrum,Representing a pseudo-sampled mass spectrum characteristic of the output of the second generator,A probability value representing that the second discriminator discriminates that the sampled mass spectrum feature is a sampled mass spectrum feature,Representing the probability value that the second discriminator discriminates that the pseudo-sampled mass spectrum feature output by the second generator is a sampled mass spectrum feature,Representing minimizing the loss function of the second generator,Representing maximizing a loss function of the second arbiter;
the calculation formula of the loss function of the cyclic coherence loss of the cyclic countermeasure neural network is as follows:
；
Where G denotes a first generator, F denotes a second generator, x denotes a sampled mass spectrum characteristic of the first generator input, A pseudo-repair mass spectrum signature representing a first generated output,A pseudo-repair mass spectrum feature representing the output of the first generator is input to a pseudo-sample mass spectrum feature output by the second generator, y represents a true mass spectrum feature,Representing a pseudo-sampled mass spectrum characteristic of the output of the second generator,A pseudo-sampled mass spectrum characteristic representing the output of the second generator is input to a pseudo-repair mass spectrum characteristic of the output of the first generator,Representation ofNorms are used to measure differences between mass spectral features.
2. The wireless sensor network-based water quality monitoring system of claim 1, wherein the distances between two adjacent points are equal.
3. The water quality monitoring system based on the wireless sensor network of claim 1,Mass spectral data representing a water sample of an ith pollution source;
；
Wherein the method comprises the steps of Respectively representing the ion intensity of the 1~u th mass-to-charge ratio of the 1 st scanning times of the ith pollution source,Respectively representing the ion intensity of the 1~u th mass-to-charge ratio of the 2 nd scanning times of the ith pollution source,The ion intensities of the 1~u th mass-to-charge ratios of the ith scan times of the ith contamination source are shown, respectively.
4. The water quality monitoring system based on the wireless sensor network according to claim 1, wherein on the premise that the position of each pollution source is known, a water body sample is collected at the position of each pollution source, and mass spectrum data are obtained; the method for acquiring mass spectrum data of the water body sample acquired by the position of the point position, the background sample and the pollution source is the same, the adopted scanning times are v, the mass-to-charge ratio of the ion intensity between 0 and U is recorded in each scanning, the recorded actual discrete value is a plurality of mass-to-charge ratio discrete values after the value range mean value of the mass-to-charge ratio corresponding to 0 to U is discretized; both the number of scans and the recorded mass-to-charge ratio range are adjustable parameters, default v=1000, u=200.
5. The wireless sensor network-based water quality monitoring system of claim 1, wherein the first generator, the first discriminator, the second generator, and the second discriminator of the cyclic countermeasure neural network are trained in combination.
6. The wireless sensor network-based water quality monitoring system of claim 4, wherein analyzing the compound of the water sample according to the pseudo-sampling mass spectrometry feature comprises the following modules:
A mass spectrum generation module for generating a first mass spectrum from the pseudo-sampled mass spectrum features;
The number of the first mass spectrograms is n x v, v first mass spectrograms are generated for each point, the horizontal axis of the first mass spectrograms represents the mass-to-charge ratio, and the vertical axis represents the ion intensity;
the s-th sequence of pseudo-sampled mass spectral features is expressed as:
wherein Respectively representing the ion intensity of 1~u th mass-to-charge ratio of a first mass spectrogram of the 1 st scanning times of the generated s th point; Respectively representing the ion intensity of 1~u th mass-to-charge ratio of the first mass spectrogram of the generated 2 nd scanning times of the s th point; The ion intensity of 1~u th mass-to-charge ratio of the first mass spectrogram respectively representing the generated v scanning times of the s th point;
the total ion chromatogram generation module is used for generating a total ion chromatogram for each point position based on the characteristics of the pseudo-sampling mass spectrum;
the component analysis module extracts a first mass spectrogram mark of corresponding scanning times based on chromatographic peaks of the total ion chromatograms to be a second mass spectrogram; and searching a mass spectrogram-compound database based on the second mass spectrograms to obtain corresponding compounds, wherein all the compounds searched by the second mass spectrograms at one point are judged to be the compounds contained in the water body at the point.
7. The wireless sensor network-based water quality monitoring system according to claim 6, wherein the first mass spectrogram is generated by sequentially generating the ion intensity of the 1~u th mass-to-charge ratio of v scanning times of n sequence units of the pseudo-sampling mass spectrum characteristic through the first mass spectrogram visualization software.
8. The wireless sensor network-based water quality monitoring system of claim 6, wherein the data for generating the total ion chromatogram for the s-th point location is derived from the s-th sequence of pseudo-sampled mass spectrum features.
9. The wireless sensor network-based water quality monitoring system of claim 6, wherein the abscissa of the total ion chromatogram is represented by the number of scans and the ordinate is the total ion intensity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410289298.6A CN118090977B (en) | 2024-03-14 | 2024-03-14 | Water quality monitoring system based on wireless sensor network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410289298.6A CN118090977B (en) | 2024-03-14 | 2024-03-14 | Water quality monitoring system based on wireless sensor network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118090977A CN118090977A (en) | 2024-05-28 |
| CN118090977B true CN118090977B (en) | 2024-06-28 |
Family
ID=91151438
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410289298.6A Active CN118090977B (en) | 2024-03-14 | 2024-03-14 | Water quality monitoring system based on wireless sensor network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118090977B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105158353A (en) * | 2015-07-29 | 2015-12-16 | 北华航天工业学院 | Source apportionment method for polycyclic aromatic hydrocarbon pollution in soil |
| CN106529738A (en) * | 2016-11-28 | 2017-03-22 | 中国环境科学研究院 | Groundwater polluted site repair technology optimization method |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110672804B (en) * | 2019-09-30 | 2022-05-06 | 华南师范大学 | Intelligent detection method for typical organic pollutants in urban river water body |
| CN111707741A (en) * | 2020-06-02 | 2020-09-25 | 南京大学 | Non-target identification method for trace organic pollutant conversion product in environment medium |
| CN111922068B (en) * | 2020-08-12 | 2022-08-09 | 生态环境部华南环境科学研究所 | Risk evaluation method for petroleum hydrocarbon in soil and underground water of industrial pollution site |
| CN114295749B (en) * | 2021-12-30 | 2022-10-25 | 南京大学 | Intelligent tracing method and system for organic pollution of water body |
| CN114970722A (en) * | 2022-05-27 | 2022-08-30 | 江苏蓝创智能科技股份有限公司 | Pollutant identification method and device, electronic equipment and storage medium |
| CN116297786A (en) * | 2023-01-06 | 2023-06-23 | 清华大学 | Three-dimensional mass spectrum imaging method and device based on sparse sampling and depth generation model |
| CN117250267A (en) * | 2023-01-30 | 2023-12-19 | 生态环境部华南环境科学研究所(生态环境部生态环境应急研究所) | High-resolution mass spectrum data processing method for non-targeted screening of new pollutants |
| CN116187861A (en) * | 2023-03-14 | 2023-05-30 | 恒天益科技（深圳）有限公司 | Isotope-based water quality traceability monitoring method and related device |
| CN116148400B (en) * | 2023-04-20 | 2023-06-27 | 北京大学 | Quantitative source analysis method based on pollution source and pollution receptor high-resolution mass spectrum data |
| CN116403092B (en) * | 2023-06-02 | 2023-08-18 | 北京建工环境修复股份有限公司 | Underground water NAPL pollution degree judging method and system based on image learning |
| CN117214398B (en) * | 2023-09-04 | 2024-05-14 | 江苏省连云港环境监测中心 | Deep underground water body pollutant detection method and system |
-
2024
- 2024-03-14 CN CN202410289298.6A patent/CN118090977B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105158353A (en) * | 2015-07-29 | 2015-12-16 | 北华航天工业学院 | Source apportionment method for polycyclic aromatic hydrocarbon pollution in soil |
| CN106529738A (en) * | 2016-11-28 | 2017-03-22 | 中国环境科学研究院 | Groundwater polluted site repair technology optimization method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118090977A (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fossati et al. | MUSE analysis of gas around galaxies (MAGG)–III. The gas and galaxy environment of z= 3–4.5 quasars | |
| CN114279982B (en) | Method and device for acquiring water pollution information | |
| CN110320197A (en) | Microminiature Raman blood specialized analyzer based on Raman spectrum analysis | |
| Brunt et al. | An outer Galaxy molecular cloud catalog | |
| JP7108136B2 (en) | Analysis equipment | |
| CN107315046A (en) | A kind of ICP MS signal processing methods | |
| CN118090977B (en) | Water quality monitoring system based on wireless sensor network | |
| EP4078600B1 (en) | Method and system for the identification of compounds in complex biological or environmental samples | |
| CN112505133B (en) | Mass spectrum detection method based on deep learning | |
| CN112289386B (en) | Method and device for determining molecular weight of compound | |
| CN113588597A (en) | Method for improving analysis precision of furnace slag | |
| CN110793920B (en) | Atmospheric remote measurement method combining chemical imaging and hyperspectral | |
| CN117589697A (en) | Detection method for pH value of plant soil | |
| CN109668862B (en) | Aluminum electrolyte molecular ratio detection method based on laser-induced breakdown spectroscopy | |
| CN115376005A (en) | Insulator pollution component identification method and system based on spectrum resolving network | |
| CN115541563A (en) | Element quantitative analysis method based on laser-induced breakdown spectroscopy | |
| De Grandi et al. | The steepness ratio technique: a new method to analyze rosat all-sky survey extended sources | |
| CN111044504B (en) | Coal quality analysis method considering uncertainty of laser-induced breakdown spectroscopy | |
| CN109614954B (en) | Qualitative classification method for hyperspectral migration of heavy metal pollution in soil | |
| KR102520763B1 (en) | Apparatus and Method for quantifying of Micro-Pollutants using Deep-learning model | |
| CN117630264B (en) | Analysis method and device for chromatography and mass spectrometry, storage medium and electronic equipment | |
| CN118190725B (en) | Source analysis method and system for organic matters in atmospheric particulates | |
| CN114581390B (en) | Particle flow laser detection method, device and storage medium based on plasma image | |
| Zheng et al. | Research on Automatic Wavelength Calibration of Passive DOAS Observations Based on Sequence Matching Method | |
| CN114509490B (en) | Ultra-high/extremely-high vacuum system mass spectrum measurement method based on spectrogram iterative analysis |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |