CN118070228A - Real-time fusion method and system for flow production safety multi-mode multi-parameter monitoring data - Google Patents
Real-time fusion method and system for flow production safety multi-mode multi-parameter monitoring data Download PDFInfo
- Publication number
- CN118070228A CN118070228A CN202410368109.4A CN202410368109A CN118070228A CN 118070228 A CN118070228 A CN 118070228A CN 202410368109 A CN202410368109 A CN 202410368109A CN 118070228 A CN118070228 A CN 118070228A
- Authority
- CN
- China
- Prior art keywords
- risk
- monitoring
- fluctuation
- interval
- parameter
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 156
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 93
- 238000007500 overflow downdraw method Methods 0.000 title claims description 6
- 238000000034 method Methods 0.000 claims abstract description 85
- 230000008569 process Effects 0.000 claims abstract description 56
- 230000004927 fusion Effects 0.000 claims abstract description 30
- 238000004458 analytical method Methods 0.000 claims abstract description 16
- 238000011156 evaluation Methods 0.000 claims description 41
- 230000000694 effects Effects 0.000 claims description 21
- 230000002159 abnormal effect Effects 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 14
- 230000008859 change Effects 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 6
- 238000013500 data storage Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 241000925028 Nitzschia sigma Species 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000007726 management method Methods 0.000 abstract description 4
- 230000007547 defect Effects 0.000 abstract description 3
- 238000013459 approach Methods 0.000 abstract description 2
- 230000005540 biological transmission Effects 0.000 abstract 1
- 239000013598 vector Substances 0.000 description 25
- 239000011159 matrix material Substances 0.000 description 24
- 238000010586 diagram Methods 0.000 description 4
- 238000012546 transfer Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 231100000279 safety data Toxicity 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000008054 signal transmission Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
- G06F18/256—Fusion techniques of classification results, e.g. of results related to same input data of results relating to different input data, e.g. multimodal recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for fusing flow production safety multi-mode multi-parameter monitoring data in real time, and belongs to the field of production safety monitoring. The method can make up the defect that the safety risk early warning in the current process production scene is often single parameter monitoring analysis, and can realize real-time data fusion analysis based on the combination relation of multiple risk characteristic parameters and the safety risk state layering hierarchical early warning function of a parameter layer, a mode layer and an object layer aiming at different safety risk modes of a process production movable object; the real-time data utilization rate of the process production is greatly improved through the collection, transmission and analysis of the safety risk monitoring data, and the safety risk supervision efficiency of the process production site is effectively improved; the safety risk early warning equipment is produced by a digital and intelligent technology energization process, so that the application threshold of the safety production early warning technology service is reduced, and a new safety management approach is widened.
Description
Technical Field
The invention belongs to the field of production safety monitoring, and particularly relates to a method and a system for fusing flow production safety multi-mode multi-parameter monitoring data in real time.
Background
Dangerous early warning based on multi-parameter monitoring data is a key technical means for safety production of various industries. The process production safety comprises a plurality of safety risk modes, and each safety risk mode comprises a plurality of types of parameters. Each parameter has a stable change rule in the production process period, and the production period is relatively fixed. Once the parameters are abnormal, this means that the risk occurrence probability increases, and the occurrence of risk often has multi-parameter abnormal signs. The characteristics of the safety multi-mode multi-parameter in the process production scene lead to the need of determining the parameter combination mode and the abnormal change rule of each unsafe risk mode in the risk state identification process, and real-time monitoring and early warning risk assessment are carried out.
Major problems with existing risk status recognition techniques include: (1) The safety production state monitoring is relatively perfect, and the safety production state is analyzed in real time and comprehensively evaluated in a deficient contradiction; (2) The intelligent monitoring and the safety production control decision depend on the contradiction of manpower; (3) The contradiction between risk multi-parameter and multi-mode real-time monitoring and early warning of safety production monitoring. Therefore, there is a strong need for a method and system for real-time monitoring data fusion of a safe multi-modal, selectable multi-risk parameter combination that accommodates production activities of varying parameters.
Disclosure of Invention
Aiming at the defects or improvement demands of the prior art, the invention provides a method and a system for fusing flow production safety multi-mode multi-parameter monitoring data in real time, which aim to solve the problems of the safety multi-mode multi-parameter real-time monitoring fusion analysis and risk grading early warning, improve the intellectualization and universality of a safety monitoring instrument, reduce the production safety supervision cost, deepen the scene application of the safety production pre-warning technical service, and promote the flow safety production number intellectualization.
To achieve the above object, according to a first aspect of the present invention, there is provided a process production safety multi-mode multi-parameter monitoring data real-time fusion method, including:
s1, acquiring monitoring fluctuation values delta d (i,j) of each risk characteristic parameter F i at the latest l moments in the current monitoring period, and determining fluctuation coefficients of F i at the latest l moments according to the fluctuation interval where delta d (i,j) is located Wherein i=1, 2,3, …, m, m is the number of risk characteristic parameters, j=p-l+1, p-l+2, …, p, p is the total time of the current monitoring period, and p is more than or equal to 3,l and less than or equal to p; Δd (i,j) is the monitoring value/>, in the current monitoring period, of the monitoring average values d (i,j) and F i of the time points corresponding to the latest l time points in the multiple historical complete monitoring periods, of F i in the safe stateIs a difference in (2); the fluctuation intervals are in one-to-one correspondence with the fluctuation coefficients, and the minimum value of the fluctuation interval with the large fluctuation coefficient is larger than the maximum value of the fluctuation interval with the small fluctuation coefficient;
S2, weighting omega (i,j) to obtain a risk state evaluation coefficient of F i at the current time T p According toDetermining the risk state grade of F i at T p in the numerical interval and carrying out grading early warning; wherein, the weight coefficient of T p is the largest in the latest l moments, and the weight coefficient is larger when the moment is closer to T p;
S3, weighting and calculating risk state evaluation coefficients of all risk characteristic parameters of each safety risk mode M k to obtain a risk state evaluation coefficient lambda (k,p) of M k at T p, determining a risk state grade of M k at T p according to a numerical interval where lambda (k,p) is located, and carrying out grading early warning;
S4, weighting and calculating risk state evaluation coefficients of all safety risk modes of the monitored process production movable object A to obtain a multi-mode fusion risk state coefficient theta p of the A at T p, determining the risk state grade of the A at T p according to a numerical interval where the theta p is located, and carrying out grading early warning;
the numerical intervals are in one-to-one correspondence with the risk state grades, and the minimum value of the numerical interval with the high risk state grade is larger than the maximum value of the numerical interval with the low risk state grade.
According to a second aspect of the present invention, there is provided a process production safety multi-mode multi-parameter monitoring data real-time fusion system, comprising:
The data fusion analysis module is used for acquiring monitoring fluctuation values delta d (i,j) of each risk characteristic parameter F i at the latest l moments in the current monitoring period respectively, and determining fluctuation coefficients of F i at the latest l moments respectively according to fluctuation intervals of delta d (i,j) Wherein i=1, 2,3, …, m, m is the number of risk characteristic parameters, j=p-l+1, p-l+2, …, p, p is the total time of the current monitoring period, and p is more than or equal to 3,l and less than or equal to p; Δd (i,j) is the monitoring value/>, in the current monitoring period, of the monitoring average values d (i,j) and F i of the time points corresponding to the latest l time points in the multiple historical complete monitoring periods, of F i in the safe stateIs a difference in (2); the fluctuation intervals are in one-to-one correspondence with the fluctuation coefficients, and the minimum value of the fluctuation interval with the large fluctuation coefficient is larger than the maximum value of the fluctuation interval with the small fluctuation coefficient; weighting calculation is carried out on omega (i,j) to obtain risk state evaluation coefficient/>, at the current time T p, of F i Weighting and calculating risk state evaluation coefficients of all risk characteristic parameters of each security risk mode M k to obtain a risk state evaluation coefficient of M k at T p; lambda (k,p); weighting and calculating risk state evaluation coefficients of all safety risk modes of the monitored process production movable object A to obtain a multi-mode fusion risk state coefficient theta p of the A at T p;
a risk status grade grading module for grading according to Determining the risk state grade of F i at T p in the numerical interval, and determining the risk state grade of M k at T p according to the numerical interval of lambda (k,p); determining the risk state grade of A at T p according to the numerical interval in which theta p is located; the numerical intervals are in one-to-one correspondence with the risk state grades, and the minimum value of the numerical interval with the high risk state grade is larger than the maximum value of the numerical interval with the low risk state grade;
The multi-level danger early warning module is used for carrying out grading early warning according to the risk state grade of F i at T p, carrying out grading early warning according to the risk state grade of M k at T p, and carrying out grading early warning according to the risk state grade of A at T p.
According to a third aspect of the present invention there is provided a computer readable storage medium storing computer instructions for causing a processor to perform the method of the first aspect.
In general, the above technical solutions conceived by the present invention, compared with the prior art, enable the following beneficial effects to be obtained:
(1) The method and the system provided by the invention can be used for solving the defect that the safety risk early warning in the current process production scene is often single parameter monitoring and analysis, and realizing the real-time data fusion analysis based on the combination relation of multiple risk characteristic parameters and the safety risk state layering and grading early warning function facing the parameter layer, the mode layer and the object layer aiming at different safety risk modes of the process production movable object.
(2) By collecting, transmitting and analyzing the safety risk monitoring data, the real-time data utilization rate of the process production is greatly improved, and the safety risk supervision efficiency of the process production site is effectively improved.
(3) The safety risk early warning equipment is produced by a digital and intelligent technology energization process, so that the application threshold of the safety production early warning technology service is reduced, and a new safety management approach is widened.
Drawings
Fig. 1 is a schematic flow chart of a process production safety multi-mode multi-parameter real-time monitoring data fusion method according to an embodiment of the invention;
fig. 2 is an example of a security risk status classification threshold interval setting manner provided in an embodiment of the present invention;
Fig. 3 is a schematic diagram of an updating process of a monitored value of a current moment of a feature parameter according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a calculation process of parameter risk classification according to an embodiment of the present invention;
fig. 5 is a schematic functional structure diagram of a flow production safety multi-mode multi-parameter real-time monitoring data fusion analysis and risk status grading early warning system provided by the embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. In addition, the technical features of the embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
The embodiment of the invention provides a method for fusing flow production safety multi-mode multi-parameter monitoring data in real time, and before introducing the method, definition of related terms is explained first.
Risk characteristic parameters: in the process of flow production, the variable of the safety risk state change characteristic of the movable object can be reflected by monitoring the change rule of the data.
Security risk modality: referring to a certain type of process safety accident, one safety risk mode corresponds to one or more risk characteristic parameters, namely, the risk state of one safety risk mode is jointly determined by the risk state of one or more corresponding risk characteristic parameters. Each risk characteristic parameter has a weight, and can be set according to an actual application scene.
The process produces an activity object: in general, a process production activity object corresponds to multiple security risk modes, i.e., the risk status of the process production activity object is determined by the risk status of one or more security risk modes corresponding to the process production activity object. Each security risk mode has a weight and can be set according to an actual application scene.
Taking the production process of ladle turret rotation casting operation as an example, the movable object of process production is ladle turret, the safety risk mode is collapse, explosion and fire, and the risk characteristic parameters comprise ladle weight, ladle support arm surface strain, turret inclination angle, rotation speed, combustible gas concentration, ambient temperature, ambient humidity and the like. The risk characteristic parameters corresponding to collapse are ladle weight, ladle support arm surface strain, turntable inclination angle and rotation speed; the risk characteristic parameters corresponding to explosion are the concentration of combustible gas and the ambient temperature, and the risk characteristic parameters corresponding to fire disaster are the concentration of combustible gas, the ambient temperature and the ambient humidity.
The embodiment of the invention provides a process production safety multi-mode multi-parameter monitoring data real-time fusion method, which is shown in fig. 1 and comprises the following steps:
S1, acquiring monitoring fluctuation values delta d (i,j) of the risk characteristic parameters F i at the latest moment in the current monitoring period in the current state, and determining fluctuation coefficients of F i at the latest moment according to the fluctuation interval of delta d (i,j) Wherein i=1, 2,3, … m, m is the number of risk characteristic parameters, j=p-l+1, p-l+2, …, p, p is the total time of the current monitoring period, and p is more than or equal to 3,l and less than or equal to p; Δd (i,j) is the monitoring value/>, in the current monitoring period, of the monitoring average values d (i,j) of the time points corresponding to the latest time points in the multiple complete monitoring periods, of F i in the safety state, and the monitoring value of the latest time points in the current monitoring period, of F i Is a difference in (2); the fluctuation intervals are in one-to-one correspondence with the fluctuation coefficients, and the minimum value of the fluctuation interval with the large fluctuation coefficient is larger than the maximum value of the fluctuation interval with the small fluctuation coefficient.
Specifically, S1 includes S11-S13.
S11, aiming at real-time monitoring data of a plurality of periods of safety states of flow production, constructing a multi-parameter combined space-time standard data matrix according to safety data sequence sets of all risk characteristic parameters acquired in a plurality of complete monitoring periods. The row represents the parameter dimension of the object space feature, the column represents the time dimension, the element is the normal data statistical average value corresponding to the monitoring time T j` of the feature parameter in a plurality of complete monitoring periods, and the element represents the numerical security feature of the parameter at the corresponding time.
That is, for the real-time monitoring of the safety risk of the process production, real-time monitoring data of a plurality of safety state periods are selected, and a multi-parameter combined space-time standard data matrix S T is constructed according to the safety data sequence set of all risk characteristic parameters acquired in a plurality of complete monitoring periods, wherein the general form is as follows:
The line of S T represents the spatial feature parameter dimension, the column represents the time dimension, and the elements And the normal data statistical average value corresponding to the monitoring time T j` of the characteristic parameter F i in a plurality of complete monitoring periods is used for representing the numerical security characteristic of the parameter at the corresponding time. Each complete monitoring cycle covers m risk profile parameters, namely F 1,F2,…,Fi,…,Fm (i=1, 2,3, …, m); each characteristic parameter contains n monitoring moments, i.e., T 1,T2,…,Tj`,…,Tn (j=1, 2,3, …, n).
S12, aiming at the process production safety real-time monitoring, a monitoring variable time sequence value matrix composed of original monitoring values of risk characteristic parameters in a current monitoring period is constructed, and the columns of the matrix are space characteristic parameter dimensions and behavior time dimensions. Forming a time sequence value matrix of the monitoring variable consisting of all parameter monitoring values in a period from an initial time to a current time in a current monitoring period, wherein matrix elements represent the monitoring values of the characteristic parameters at a certain time in the current monitoring period.
That is, for real-time monitoring of the process production safety risk, a monitoring matrix D new composed of all-parameter monitoring values is constructed in a period from an initial time T 1 to a current time T p (p.ltoreq.n) in the current monitoring period, wherein an element D (i,j) represents the monitoring value of the characteristic parameter F i at a time T j in the current monitoring period. Row vectors d i＝[d(i,1) … d(i,2) … d(i,j) …d(i,p), i=1, 2,3, …, m; the general form of the column vector d' j＝[d(1,j) d(2,j) … d(i,j) … d(m,j)]T,j＝1,2,3,…,p.Dnew is:
S13, aiming at flow production safety real-time monitoring, constructing a monitoring variable fluctuation characteristic value matrix composed of all parameter monitoring values in a period from an initial moment to a current moment in a current monitoring period, wherein matrix elements represent time sequence fluctuation values of monitoring parameters of characteristic parameters in the current monitoring period.
That is, for real-time monitoring of the safety risk of the process production, a monitoring variable fluctuation feature matrix delta composed of all-parameter monitoring values in the period from the initial time T 1 to the current time T p in the current monitoring period is constructed, wherein elements areJ=1, 2,3, …, p, representing the monitored fluctuation value of the characteristic parameter F i at time T j in the new monitoring period. The general form of Δ is:
S2, weighting omega (i,j) to obtain a risk state evaluation coefficient of F i at the current time T p According toThe numerical value interval where F i is located determines the risk state level of F p and carries out grading early warning, so that grading early warning of a parameter layer is realized; among the latest l times, the weight coefficient of T p is the largest, and the weight coefficient is the larger the closer to T p.
Specifically, S2 includes S21-S22.
S21, aiming at flow production safety real-time monitoring, calculating a risk time-varying matrix of the full-feature parameters in a period from a current monitoring period T 1 to a current time T p, wherein the specific process comprises the following steps:
S211, setting a section threshold value of characteristic parameter fluctuation state classification.
The characteristic parameter fluctuation state can be classified into a plurality of grades according to the type of the monitored specific production flow, and the embodiment of the invention does not limit uniqueness.
Taking the classification of the characteristic parameter fluctuation state into three stages as an example, the characteristic parameter fluctuation states are respectively: the characteristic parameter fluctuation state classification section comprises: normal state interval, low amplitude abnormal fluctuation interval and high amplitude abnormal fluctuation interval.
Preferably, the interval threshold of the characteristic parameter fluctuation state classification is set based on the data statistical distribution characteristics of the full parameter in the historical complete monitoring period in the safe state of the flow production in S11, that is:
A normal state interval (d' (i,j`)-h(ij`,0),d`(i,j`)+h('ij`,0));
Low amplitude abnormal fluctuation interval (d`(i,j`)-h(ij`,1),d`(i,j`)-h(ij`,0)]∪[d`(i,j`)+h('ij`,0),d`(i,j`)+h('ij`,1));
High amplitude abnormal fluctuation interval
Wherein, let theTaking d' (i,j`) as a statistical mean value, taking h (ij`,0)、h('ij`,0) as M standard deviations, h (ij`,1)、h('ij`,1) as N standard deviations based on a 3 sigma rule of statistics, wherein M is less than N, and M, N is a positive integer; for example: h (ij`,0)、h′(ij`,0) is taken as 2 standard deviations, and h (ij`,1)、h′(ij`,1) is taken as 3 standard deviations;
Preferably, the interval threshold for the characteristic parameter fluctuation state classification may also be set based on the accident cause parameter threshold for each risk characteristic parameter, that is: let d '(i,j`) be the threshold value of the accident cause parameter (which can be a value or a numerical interval), h (ij`,0)、h′(ij`,0) be B% of d' (i,j`), h (ij`,1)、h′(ij`,1) be C% of the threshold value, B < C, and B, C be positive integers; for example, h (ij`,0)、h′(ij`,0) is taken as 10% of the threshold value, h (ij`,1)、h′(ij`,1) is taken as 20% of the threshold value, and the upper or lower limit should be taken depending on the actual situation.
S212, calculating a state fluctuation coefficient of the characteristic parameter at the monitoring moment.
That is, the state fluctuation coefficient ω (i,j) of the characteristic parameter F i at the monitoring time T j is calculated. As shown in fig. 2, the smaller the new monitored fluctuation value Δd (i,j) of the characteristic parameter is, the smaller the fluctuation coefficient is; on the contrary, the more the new monitoring value deviates from the normal state interval, the stronger the abnormal fluctuation degree of the parameter is, and the larger the fluctuation coefficient is.
Taking the fluctuation coefficients of 0,1 and 2 as examples, the value formula of ω (i,j) is:
It can be understood that the fluctuation coefficient can be 1,2,3 or other values, so long as the principle of the above-mentioned "the more the new monitoring value deviates from the normal state interval, the stronger the abnormal fluctuation degree of the parameter, and the larger the fluctuation coefficient.
S213, constructing a full-feature parameter risk time-varying matrix composed of state fluctuation coefficients in a period from the initial time to the current time of the current monitoring period, wherein the columns of the matrix are parameter dimensions and behavior time dimensions. The matrix increases with time and the number of columns of the matrix increases.
That is, the general form of constructing the full-feature parameter risk time-varying matrix R (i,j),i＝1,2,3,…,m,j＝1,2,3,…,p,R(i,j) composed of the state fluctuation coefficient ω (i,j) in the period from the initial time T 1 to the current time T p of the current monitoring period is:
S22, parameter layer: the risk state grade of the characteristic parameter F i at the current time T p is judged, and the specific process is as follows:
S221, setting the length of a state evaluation time shift window of parameter risk identification as l according to the value condition of the parameter state fluctuation coefficient, and constructing a full parameter risk judgment matrix I (m,l) at the current moment T p, namely calculating the risk state grade of the full parameter risk judgment matrix by the parameter state fluctuation condition at the latest l moments, wherein the value of l is generally not less than 3 and l is less than or equal to p. I (m,l) is of the general form P-j+1=l is satisfied.
Taking m=3, l=5 as an example, fig. 3 shows the update process of 3 parameters at the current time T p as the production activity time period proceeds, and the state evaluation time shift window length l represents that the l monitoring times nearest to the current time are intercepted. The risk discrimination matrix I (3,5) consisting of 3 parameter state fluctuation coefficients within the state evaluation time shift window is in the form of
S222, extracting a parameter risk transfer row vector composed of the current moment and state fluctuation coefficients nearest to the current moment and a plurality of monitoring moments. That is, the parameter risk transfer row vector r (i,j) composed of its state fluctuation coefficients, the dimension being the state evaluation time shift window length l, and j=1, 2,3, …, l, r (i,j) at the current time T p (p≡3) and immediately preceding l-1 monitoring times thereof, is extracted as follows:
r(i,j)＝[ω(i,p-l+1) ω(i,p-l+2) … ω(i,p-j+1) … ω(i,p-1) ω(i,p)]。
s223, determining weight values of parameter risk states of different monitoring moments to the current moment, and constructing a weight column vector. The weight value setting principle is that the closer to the time monitoring value of the current time, the larger the weight value is.
That is, the weight values of the risk states of the parameters at the current moment at different monitoring moments are determined, a weight column vector v (i,j``) is constructed, and the dimension is the state evaluation time shift window length l. The principle is that the closer to the point of time of the current time T p, the larger the weight value thereof.
V (i,j``) is of general form [ v (i,p-l+1) v(i,p-l+2) … v(i,p-j``+1) … v(i,p-1) v(i,p)]T ] where v (i,p-j``1+) ε [0,1] andj``＝1，2，3，…，l。
It can be understood that the values of the weight coefficients at different monitoring moments can be set arbitrarily, the invention is not limited in uniqueness, as long as the moment point which is closer to the current moment T p is met, the weight value is larger, v (i,p-j``+1) E [0,1] andThe principle of (2) is just enough.
For example, one way to set weights at different monitoring moments isWherein the monitoring time importance index a p-j``+1 satisfies a p-j``+1 e [0,1] and a p-l+1＜ap-l+2＜…＜ap-j+1＜…＜ap-1＜ap (j=1, 2,3, …, l). That is, one specific form of the weight column vector v (i,j) at different monitoring moments is:
S224, calculating a parameter risk state evaluation coefficient of the characteristic parameter at the current moment, wherein the parameter is obtained by multiplying a parameter risk transfer vector and a weight column vector.
That is, the parameter risk state evaluation coefficient of the characteristic parameter F i at the present time T p
S225, constructing a risk state grading rule of the characteristic parameters according to the risk state grading ruleAnd determines the risk status of the characteristic parameter F i at the current time T p.
The risk status of the characteristic parameter may be classified into a plurality of levels according to the type of the specific monitored production process, which is not limited uniquely in the embodiment of the present invention. Similarly, the specific value of the risk status level interval of the characteristic parameter can be set according to the type of the specific monitored production process, and the embodiment of the invention does not limit the uniqueness.
Taking the example of classifying the risk status into four classes, respectively: a classification rule for the security state, representing the low risk state, the medium risk state, and the high risk state, and the characteristic parameter risk state level (FRSL) is as follows:
Wherein NS (Normal Safety) denotes a safe state, LR (Low-Risk) denotes a Low Risk state, MR (Medium-Risk) denotes a Medium Risk state, and HR (High-Risk) denotes a High Risk state.
Further preferably, FIG. 4 shows the parameter risk status evaluation coefficients at the current time T p And (3) a calculation process and a parameter risk state grading result. In this example, the user sets an importance index a p-2＝0.25,ap-1＝0.5,ap =1 for the latest l=3 monitoring moments, the weight column vector v (i,p)＝[1/7 2/7 4/7]T is available; the state fluctuation coefficient combination mode at 3 moments has 27 types, namely 27 types of parameter risk transfer row vectors r (i,p).
And S3, carrying out weighted calculation on risk state evaluation coefficients of all risk characteristic parameters of each safety risk mode M k to obtain a risk state evaluation coefficient lambda (k,p) of M k at T p, determining the risk state grade of M k at T p according to a numerical interval where lambda (k,p) is located, and carrying out grading early warning, thereby realizing grading early warning of a mode layer.
Step S3 is a mode layer: the risk state grade of the security risk mode M k at the current time T p is judged, and the specific process comprises the following steps:
s31, constructing a row vector u k for selecting all characteristic parameters contained in the security risk mode.
Preferably, u k is of general form u k＝[u1 u2 … ui … um, where u i = 0 or 1.
S32, constructing a parameter weight row vector for setting the weight of each selected characteristic parameter.
That is, a row vector v k is constructed for setting the weight of each feature parameter included in the security risk mode.
Preferably, v k is of general form v k＝[v1 v2 … vi … vm, where v i e (0, 1) and satisfies
S33, calculating a parameter combination vector by the parameter selection row vector and the parameter weight row vector, and quantifying a parameter combination relation of a security risk mode.
That is, a parameter combination vector C k is calculated for quantifying the parameter combination relationship of the security risk modality M k.
Preferably, the general form of calculation of C k is Ck＝uk⊙vk＝[u1v1 u2v2 … uivi … umvm].
S34, extracting column vectors of all-parameter risk state evaluation coefficients at the current time T p
Preferably, the method comprises the steps of,In the general form/>
S35, calculating a mode risk state evaluation coefficient of the safety risk mode at the current moment, wherein the mode risk state evaluation coefficient is used for evaluating the risk state of the safety risk mode, and the coefficient is obtained by multiplying a parameter combination vector by a column vector of a full-parameter risk state evaluation coefficient at the current moment.
That is, the modal risk state evaluation coefficient λ (k,p) of the security risk modality M k at the current time T p is calculated for evaluating the risk state thereof.
The general form of calculation of lambda (k,p) isAnd meets lambda (k,p) epsilon [0,2].
S36, constructing a security risk mode risk state grade discrimination rule, and determining the risk state of the security risk mode at the current moment according to the calculated value of lambda (k,p).
The security risk mode risk state can be classified into a plurality of grades according to the type of the specific monitored production flow, and the embodiment of the invention does not limit uniqueness. Similarly, the specific value of the security risk mode risk state level interval can be set according to the type of the specific monitored production process, and the embodiment of the invention does not limit uniqueness. Taking the example of classifying the risk status into four classes, respectively: a classification rule for the security state, representing a low risk state, a medium risk state, and a high risk state, a security risk Modality Risk State Level (MRSL) is as follows:
S4, weighting and calculating risk state evaluation coefficients of all safety risk modes of the monitored process production movable object A to obtain a multi-mode fusion risk state coefficient theta p of the A at T p, determining the risk state grade of the A at T p according to the numerical interval of the theta p, and carrying out grading early warning, so that grading early warning of an object layer is realized;
the numerical intervals are in one-to-one correspondence with the risk state grades, and the minimum value of the numerical interval with the high risk state grade is larger than the maximum value of the numerical interval with the low risk state grade.
Step S4 is an object layer, and judges that the monitored process produces an active object a, and at the current time T p, the overall risk state level fused by the security multi-mode comprises the following specific processes:
S41, for the security multi-mode M 1、M2…Mk…Mq (q is the total number of security multi-modes, k=1, 2,3, …, q), the user sets a weight row vector w of each security risk mode M k when multi-mode fusion is performed, so as to determine the influence of each security risk mode.
Preferably, w is of general form w= [ w 1 w2 … wk … wq ], where w k e (0, 1) and satisfies
S42, constructing a risk state column vector lambda p of the secure multi-mode fusion at the current time T p on the basis of the step S35.
Preferably, lambda p is of general form lambda p＝[λ(1,p) λ(2,p) … λ(k,p) … λ(q,p)]T, satisfying lambda (k,p) E [0,2].
S43, calculating an active risk state coefficient of the monitored flow production active object at the current moment through secure multi-mode fusion, wherein the active risk state coefficient is used for judging the overall risk state level at the current moment, and the active risk state coefficient is obtained by multiplying a modal weight column vector and the secure multi-mode fusion risk state column vector at the current moment.
That is, the safe multi-mode fusion risk state coefficient θ p of the monitored process production activity object a at the current time T p is calculated to determine the overall risk state level of a at the current time T p.
The general form of calculation of θ p isSatisfies θ p ε [0,2].
S44, constructing a general risk state grade discrimination rule of the active object A in the production of the monitored flow, and determining the risk state of the object A at the current moment T p according to the calculated value of θ p.
The risk status of the process production activity object may be classified into a plurality of levels according to the type of the specific production process being monitored, which is not limited uniquely by the embodiment of the present invention. Similarly, the specific value of the risk status level interval of the process production activity object can be set according to the type of the monitored specific production process, and the embodiment of the invention does not limit the uniqueness. Taking the example of classifying the risk status into four classes, respectively: a partitioning rule for the overall risk status level (ARSL) of a process production activity object, representing a safe state, a low risk state, a medium risk state, and a high risk state, is as follows:
After the feature parameter risk state grade (FRSL), the security risk mode risk state grade (MRSL) and the process production activity object overall risk state grade (ARSL) are divided, different-level risk grading early warning modes are constructed and used for realizing grading early warning functions of a parameter layer (S2), a mode layer (S3) and an object layer (S4) of the monitored production process.
The hierarchy of the risk classification early warning mode can be divided into a plurality of levels according to the type of the specific monitored production flow, and the embodiment of the invention does not limit uniqueness. The risk classification early warning mode is divided into the following layers: for example, the security, the level I early warning, the level II early warning and the level III early warning are classified according to the risk early warning grades of the characteristic parameter F i at the current moment T p:
One specific mode of risk early warning grade division of the current time T p and the security risk mode M k is as follows:
One specific mode of total risk early warning grade division of the current time T p and the flow production activity object A O is as follows:
the method provided by the invention can be used for the flow production safety multi-mode multi-parameter real-time monitoring data fusion of the flow operation multi-level safety number intelligent monitoring system shown in the patent 'a flow operation multi-level safety number intelligent monitoring system' (application number 2022111303888), and effectively improves the real-time monitoring efficiency of the flow production safety risk.
The embodiment of the invention provides a process production safety multi-mode multi-parameter monitoring data real-time fusion system, which comprises the following components:
The data fusion analysis module is used for acquiring monitoring fluctuation values delta d (i,j) of each risk characteristic parameter F i at the latest l moments in the current monitoring period respectively, and determining fluctuation coefficients of F i at the latest l moments respectively according to fluctuation intervals of delta d (i,j) Wherein i=1, 2,3, …, m, m is the number of risk characteristic parameters, j=p-l+1, p-l+2, …, p, p is the total time of the current monitoring period, and p is more than or equal to 3,l and less than or equal to p; Δd (i,j) is the monitoring value of the monitoring average value d (i,j) of the moment corresponding to the latest l moments in the multiple complete monitoring periods in the safety state of F i and the monitoring value of the latest l moments in the current monitoring period of F i Is a difference in (2); the fluctuation intervals are in one-to-one correspondence with the fluctuation coefficients, and the minimum value of the fluctuation interval with the large fluctuation coefficient is larger than the maximum value of the fluctuation interval with the small fluctuation coefficient; weighting calculation is carried out on omega (i,j) to obtain risk state evaluation coefficient/>, at the current time T p, of F i Weighting and calculating risk state evaluation coefficients of all risk characteristic parameters of each security risk mode M k to obtain a risk state evaluation coefficient of M k at T p; lambda (k,p); weighting and calculating risk state evaluation coefficients of all safety risk modes of the monitored process production movable object A to obtain a multi-mode fusion risk state coefficient theta p of the A at T p;
a risk status grade grading module for grading according to Determining the risk state grade of F i at T p in the numerical interval, and determining the risk state grade of M k at T p according to the numerical interval of lambda (k,p); determining the risk state grade of A at T p according to the numerical interval in which theta p is located; the numerical intervals are in one-to-one correspondence with the risk state grades, and the minimum value of the numerical interval with the high risk state grade is larger than the maximum value of the numerical interval with the low risk state grade.
The multi-level danger early warning module is used for carrying out grading early warning according to the risk state grade of F i at T p, carrying out grading early warning according to the risk state grade of M k at T p, and carrying out grading early warning according to the risk state grade of A at T p.
Further, the system further comprises:
the full-parameter data acquisition module is used for acquiring the change data of all security risk mode risk characteristic parameters covering the process production activity object selected by the user;
The data signal transmitting module is used for transmitting the acquired parameter data to the data signal receiving module in a wireless network communication protocol;
The data signal receiving module is used for receiving the monitoring data of each risk characteristic parameter from the signal sending module;
The period data storage module is used for storing monitoring data of all risk characteristic parameters in the whole working procedure working period by taking the parameter type and the monitoring time as identifiers;
the user basic setting module is used for a user to select a production activity object and a security risk mode type to be monitored, and sets risk characteristic parameters and weights of the parameters according to production procedure requirements.
Fig. 5 provides a functional structure schematic diagram of a process production safety multi-mode multi-parameter real-time monitoring data fusion analysis and risk classification early warning system, which includes: the system comprises a full-parameter data acquisition module, a data signal transmission module, a data signal receiving module, a period data storage module, a user base setting module, a data fusion analysis module, a risk state grading module and a multi-level risk early warning module;
the full-parameter data acquisition module is used for acquiring the change data of all security risk mode risk characteristic parameters covering the process production activity object selected by the user, and comprises various sensing elements capable of sensing the physical and chemical state change of the parameters, such as sensors and the like;
The data signal transmitting module is used for transmitting the acquired parameter data to the real-time data signal receiving module by a wireless network communication protocol, and the protocol comprises a serial port, wifi, 4G, 5G and the like;
The data signal receiving module is used for receiving the monitoring data of each risk characteristic parameter from the signal sending module;
the periodic data storage module is used for storing monitoring data of all risk characteristic parameters in a complete working procedure working period by taking the parameter type and the monitoring time as identifiers;
The user basic setting module is used for a user to select a production activity object and a security risk mode type to be monitored, sets risk characteristic parameters and weights of the parameters according to production procedure requirements, and comprises the following steps: the system comprises a movable object selection sub-module, a security risk mode selection sub-module, a mode weight setting sub-module, a characteristic parameter selection sub-module and a parameter weight setting sub-module;
The data fusion analysis module comprises a standard period data matrix construction unit, a full parameter monitoring matrix construction unit, a full parameter fluctuation feature matrix construction unit, a full parameter risk coefficient time-varying matrix calculation unit, a parameter risk state evaluation coefficient calculation unit, a modal risk state evaluation coefficient calculation unit and an activity risk state evaluation coefficient calculation unit, and is used for realizing the data fusion analysis calculation functions in the steps S1-S4 and outputting the risk evaluation coefficients of the production activities, the safety risk modes and the feature parameters selected by a user at the current moment to the risk state classification module;
the data fusion analysis module also has the function of updating the standard data matrix by utilizing the safety data of the current monitoring period;
The risk state grading module is used for grading the risk state grades of the production activities, the safety risk modes and the characteristic parameters selected by the user at the current moment, and realizing the multi-level risk state grading function in the steps S225, S36 and S44; preferably, the low risk corresponds to the first-level early warning, the middle risk corresponds to the second-level early warning, and the high risk corresponds to the third-level early warning;
The multi-level danger early warning module is used for carrying out danger early warning on the identified unsafe risk state, and is oriented to different levels of departments such as field operation workers, safety supervision personnel, management decision-making personnel and the like, so that the hierarchical real-time early warning function in the step S8 is realized;
Preferably, the safety state is continuously monitored, the unsafe state is subjected to dangerous early warning, the dangerous state is classified into 3 grades from low to high, the low-risk state corresponds to the grade I early warning, the medium-risk state corresponds to the grade II early warning, and the high-risk state corresponds to the grade III early warning;
Preferably, according to the patent 'a safety state real-time intelligent monitoring master, method and system' (application number: 2022114489681), a full-parameter data acquisition module and a data signal transmission module are integrated to manufacture an intelligent sensor. For sensing parameter status values in real time;
Preferably, according to the patent 'a safety state multi-mode real-time intelligent control master, method and system' (patent number: 2022114412779), an intelligent control instrument is manufactured by integrating a data signal receiving module, a periodic data storage module, a user base setting module, a data fusion analysis module, a risk state grading module and a multi-level risk early warning module. The system is used for monitoring and early warning the security risk of the management and control scene in real time in a multi-mode and multi-parameter manner.
The embodiment of the invention provides a process production safety multi-mode multi-parameter monitoring data real-time fusion system, which comprises the following components: a computer readable storage medium and a processor;
the computer-readable storage medium is for storing executable instructions;
The processor is configured to read executable instructions stored in the computer readable storage medium and perform a method as in any of the embodiments described above.
Embodiments of the present invention provide a computer readable storage medium storing computer instructions for causing a processor to perform a method as described in any of the embodiments above.
It will be readily appreciated by those skilled in the art that the foregoing description is merely a preferred embodiment of the invention and is not intended to limit the invention, but any modifications, equivalents, improvements or alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. The process production safety multi-mode multi-parameter monitoring data real-time fusion method is characterized by comprising the following steps of:
s1, acquiring monitoring fluctuation values delta d (i,j) of each risk characteristic parameter F i at the latest l moments in the current monitoring period, and determining fluctuation coefficients of F i at the latest l moments according to the fluctuation interval where delta d (i,j) is located Wherein i=1, 2,3, … m, m is the number of risk characteristic parameters, j=p-l+1, p-l+2, …, p, p is the total time of the current monitoring period, and p is more than or equal to 3,l and less than or equal to p; Δd (i,j) is the monitoring value/>, in the current monitoring period, of the monitoring average values d (i,j) and F i of the time points corresponding to the latest l time points in the multiple historical complete monitoring periods, of F i in the safe stateIs a difference in (2); the fluctuation intervals are in one-to-one correspondence with the fluctuation coefficients, and the minimum value of the fluctuation interval with the large fluctuation coefficient is larger than the maximum value of the fluctuation interval with the small fluctuation coefficient;
S2, weighting omega (i,j) to obtain a risk state evaluation coefficient of F i at the current time T p According to/>Determining the risk state grade of F i at T p in the numerical interval and carrying out grading early warning; wherein, the weight coefficient of T p is the largest in the latest l moments, and the weight coefficient is larger when the moment is closer to T p;
s3, weighting and calculating risk state evaluation coefficients of all risk characteristic parameters of each safety risk mode M k to obtain a risk state evaluation coefficient lambda (k,p) of M k at T p, determining a risk state grade of M k at T p according to a numerical interval where lambda (k,p) is located, and carrying out grading early warning;
S4, weighting and calculating risk state evaluation coefficients of all safety risk modes of the monitored process production movable object A to obtain a multi-mode fusion risk state coefficient theta p of the A at T p, determining the risk state grade of the A at T p according to a numerical interval where the theta p is located, and carrying out grading early warning;
the numerical intervals are in one-to-one correspondence with the risk state grades, and the minimum value of the numerical interval with the high risk state grade is larger than the maximum value of the numerical interval with the low risk state grade.
2. The method of claim 1, wherein the fluctuation interval comprises a normal interval, a low amplitude abnormal fluctuation interval, and a high amplitude abnormal fluctuation interval.
3. The method of claim 2, wherein the normal interval is (d' (i,j`)-h(ij`,0),d`(i,j`)+h′(ij`,0));
The low-amplitude abnormal fluctuation interval is (d' (i,j`)-h(ij`,1),d`(i,j`)-h(ij`,0)]∪[d`(i,j`)+h′(ij`,0),d`(i,j`)+h′(ij`,1));
The high-amplitude abnormal fluctuation interval is (- ≡, d' (i,j`)-h(ij`,1)]∪[d`(i,j`)+h′(ij`,1), the number of the parts of the product, ++ infinity a) is provided;
wherein, For the monitoring average value of F i in the safety state and in a plurality of history complete monitoring periods, j' =1, 2,3, …, N, N is the total time of the complete monitoring periods, h (ij`,0)、h′(ij`,0) is M.sigma, h (ij`,1)、h′(ij`,1) is N.sigma, sigma is the standard deviation of F i in the safety state and in a plurality of history complete monitoring periods, M is less than N, and M, N are all positive integers.
4. The method of claim 2, wherein the normal interval is (d' (i,j`)-h(ij`,0),d`(i,j`)+h′(ij`,0));
The low-amplitude abnormal fluctuation interval is (d`(i,j`)-h(ij`,1),d`(i,j`)-h(ij`,0)]∪[d`(i,j`)+h′(ij`,0),d`(i,j`)+h′(ij`,1));
The high-amplitude abnormal fluctuation interval is
Wherein d '(i,j`) is the accident cause threshold of F i, h (ij`,0)、h′(ij`,0) is B% of d' (i,j`), h (ij`,1)、h′(ij`,1) is C% of the threshold, B is less than C, and B, C are positive integers.
5. The method of claim 1, wherein the weight coefficient v (i,p-j``+1) e [0,1] for each of the most recent l times and
6. The method of claim 5, wherein,A p-j``+1 ε [0,1] and a p-l+1＜ap-l+2＜…＜ap-j+1＜…＜ap-1＜ap.
7. The method of claim 1, wherein the risk status level comprises a safe status, a low risk status, a medium risk status, and a high risk status;
The low risk state, the medium risk state and the high risk state correspond to I, II and III level early warning respectively.
8. The utility model provides a process production safety multimode multi-parameter monitoring data real-time fusion system which characterized in that includes:
The data fusion analysis module is used for acquiring monitoring fluctuation values delta d (i,j) of each risk characteristic parameter F i at the latest l moments in the current monitoring period respectively, and determining fluctuation coefficients of F i at the latest l moments respectively according to fluctuation intervals of delta d (i,j) Wherein i=1, 2,3, …, m, m is the number of risk characteristic parameters, j=p-l+1, p-l+2, …, p, p is the total time of the current monitoring period, and p is more than or equal to 3,l and less than or equal to p; Δd (i,j) is the monitoring value of the monitoring average value d (i,j) of the moment corresponding to the latest l moments in the multiple historical complete monitoring periods of F i in the safe state and the monitoring value of the latest l moments in the current monitoring period of F i Is a difference in (2); the fluctuation intervals are in one-to-one correspondence with the fluctuation coefficients, and the minimum value of the fluctuation interval with the large fluctuation coefficient is larger than the maximum value of the fluctuation interval with the small fluctuation coefficient; weighting calculation is carried out on omega (i,j) to obtain risk state evaluation coefficient/>, at the current time T p, of F i Weighting and calculating risk state evaluation coefficients of all risk characteristic parameters of each security risk mode M k to obtain a risk state evaluation coefficient of M k at T p; lambda (k,p); weighting and calculating risk state evaluation coefficients of all safety risk modes of the monitored process production movable object A to obtain a multi-mode fusion risk state coefficient theta p of the A at T p;
a risk status grade grading module for grading according to Determining the risk state grade of F i at T p in the numerical interval, and determining the risk state grade of M k at T p according to the numerical interval of lambda (k,p); determining the risk state grade of A at T p according to the numerical interval in which theta p is located; the numerical intervals are in one-to-one correspondence with the risk state grades, and the minimum value of the numerical interval with the high risk state grade is larger than the maximum value of the numerical interval with the low risk state grade;
The multi-level danger early warning module is used for carrying out grading early warning according to the risk state grade of F i at T p, carrying out grading early warning according to the risk state grade of M k at T p, and carrying out grading early warning according to the risk state grade of A at T p.
9. The system as recited in claim 7, further comprising:
the full-parameter data acquisition module is used for acquiring the change data of all security risk mode risk characteristic parameters covering the process production activity object selected by the user;
The data signal transmitting module is used for transmitting the acquired parameter data to the data signal receiving module in a wireless network communication protocol;
The data signal receiving module is used for receiving the monitoring data of each risk characteristic parameter from the signal sending module;
The period data storage module is used for storing monitoring data of all risk characteristic parameters in the whole working procedure working period by taking the parameter type and the monitoring time as identifiers;
the user basic setting module is used for a user to select a production activity object and a security risk mode type to be monitored, and sets risk characteristic parameters and weights of the parameters according to production procedure requirements.
10. A computer readable storage medium storing computer instructions for causing a processor to perform the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410368109.4A CN118070228A (en) | 2024-03-28 | 2024-03-28 | Real-time fusion method and system for flow production safety multi-mode multi-parameter monitoring data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410368109.4A CN118070228A (en) | 2024-03-28 | 2024-03-28 | Real-time fusion method and system for flow production safety multi-mode multi-parameter monitoring data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118070228A true CN118070228A (en) | 2024-05-24 |
Family
ID=91111334
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410368109.4A Pending CN118070228A (en) | 2024-03-28 | 2024-03-28 | Real-time fusion method and system for flow production safety multi-mode multi-parameter monitoring data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118070228A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118607931A (en) * | 2024-07-04 | 2024-09-06 | 青岛朗夫科技股份有限公司 | Monitoring and early warning system for four-corner carton manufacturing process |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210390469A1 (en) * | 2020-06-16 | 2021-12-16 | Huazhong University Of Science And Technology | Multimodal sensing positioning model oriented to high-risk production environment and system thereof |
| CN115494802A (en) * | 2022-09-16 | 2022-12-20 | 华中科技大学 | Flow operation multi-level safety digital intelligent monitoring system |
| CN116258302A (en) * | 2021-12-09 | 2023-06-13 | 浙江华东测绘与工程安全技术有限公司 | Multi-parameter dynamic intelligent judgment method, equipment and storage medium for foundation pit engineering safety risk state |
| CN117521008A (en) * | 2023-11-09 | 2024-02-06 | 北京德众国良环保科技有限公司 | Sewage treatment monitoring control method and system based on data fusion |
-
2024
- 2024-03-28 CN CN202410368109.4A patent/CN118070228A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210390469A1 (en) * | 2020-06-16 | 2021-12-16 | Huazhong University Of Science And Technology | Multimodal sensing positioning model oriented to high-risk production environment and system thereof |
| CN116258302A (en) * | 2021-12-09 | 2023-06-13 | 浙江华东测绘与工程安全技术有限公司 | Multi-parameter dynamic intelligent judgment method, equipment and storage medium for foundation pit engineering safety risk state |
| CN115494802A (en) * | 2022-09-16 | 2022-12-20 | 华中科技大学 | Flow operation multi-level safety digital intelligent monitoring system |
| CN117521008A (en) * | 2023-11-09 | 2024-02-06 | 北京德众国良环保科技有限公司 | Sewage treatment monitoring control method and system based on data fusion |
Non-Patent Citations (3)
| Title |
|---|
| 但佳兵 等: "基于多参数信息融合的无缝钢管产线关键设备健康管理", 《冶金自动化》, 31 December 2022 (2022-12-31) * |
| 赵挺生 等: "架桥机架桥作业流程安全监测系统", 《中国工程机械学报》, 31 December 2023 (2023-12-31) * |
| 马瑞;: "智能预警信息系统在建设项目安全生产管理中的应用", 工程建设与设计, no. 09, 10 May 2020 (2020-05-10) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118607931A (en) * | 2024-07-04 | 2024-09-06 | 青岛朗夫科技股份有限公司 | Monitoring and early warning system for four-corner carton manufacturing process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115578015A (en) | Sewage treatment overall process supervision method and system based on Internet of things and storage medium | |
| CN101718634B (en) | Equipment state comprehensive dynamic alarming method based on multivariate probability model | |
| CN114548637A (en) | AHP-RST-based power communication backbone data network security comprehensive evaluation method | |
| CN110348752B (en) | Large industrial system structure safety assessment method considering environmental interference | |
| CN108768745A (en) | A kind of group system brittleness assessment method based on complex network | |
| CN118070228A (en) | Real-time fusion method and system for flow production safety multi-mode multi-parameter monitoring data | |
| CN108650139A (en) | A kind of powerline network monitoring system | |
| JP7469991B2 (en) | Diagnosis device and parameter adjustment method | |
| CN116105802B (en) | Underground facility safety monitoring and early warning method based on Internet of things | |
| CN106780266B (en) | Principal component contribution degree parameter-based accident hotspot internal characteristic analysis and driving guidance method | |
| CN115848176A (en) | Electric vehicle charging early warning method and system based on A-LSTM algorithm | |
| CN114565162A (en) | Aircraft transportation state monitoring and safety protection method and system | |
| CN115906663A (en) | Building safety evaluation model establishing method, evaluation method, server and system | |
| CN116108445A (en) | Intelligent risk early warning management method and system for information system | |
| CN112991096A (en) | Monitoring and managing device and method for configuration type bridge cluster structure | |
| CN112598199A (en) | Monitoring and early warning method based on decision tree algorithm | |
| CN114827211B (en) | Abnormal monitoring area detection method driven by node data of Internet of things | |
| CN116306062A (en) | Intelligent monitoring method, system, device and storage medium for construction engineering | |
| CN114863170A (en) | Deep learning-based new energy vehicle battery spontaneous combustion early warning method and device | |
| CN118381629A (en) | Deep learning-based automobile network intrusion detection and prevention system and method | |
| CN116432864A (en) | Prediction method and system for regional operation driver group security situation | |
| CN115452047A (en) | Intelligent structure detection method and system | |
| CN114912872A (en) | Supply chain transportation safety monitoring method based on big data | |
| CN116311739A (en) | Multi-sensor fire detection method based on long-short-term memory network and environment information fusion | |
| CN112052952B (en) | Monitoring parameter optimization selection method in diesel engine fault diagnosis based on genetic algorithm |
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 |