CN116862081A - Operation and maintenance method and system for pollution treatment equipment - Google Patents
Operation and maintenance method and system for pollution treatment equipment Download PDFInfo
- Publication number
- CN116862081A CN116862081A CN202311135408.5A CN202311135408A CN116862081A CN 116862081 A CN116862081 A CN 116862081A CN 202311135408 A CN202311135408 A CN 202311135408A CN 116862081 A CN116862081 A CN 116862081A
- Authority
- CN
- China
- Prior art keywords
- operation data
- equipment
- data
- sub
- book
- 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.)
- Granted
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 120
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012544 monitoring process Methods 0.000 claims abstract description 26
- 230000002159 abnormal effect Effects 0.000 claims description 44
- 230000007613 environmental effect Effects 0.000 claims description 29
- 238000012549 training Methods 0.000 claims description 28
- 238000004458 analytical method Methods 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 12
- 235000012571 Ficus glomerata Nutrition 0.000 claims description 9
- 244000153665 Ficus glomerata Species 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 7
- 238000012097 association analysis method Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 abstract description 3
- 239000003344 environmental pollutant Substances 0.000 description 20
- 231100000719 pollutant Toxicity 0.000 description 19
- 230000008054 signal transmission Effects 0.000 description 12
- 230000008859 change Effects 0.000 description 9
- 230000005540 biological transmission Effects 0.000 description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004146 energy storage Methods 0.000 description 4
- 238000013508 migration Methods 0.000 description 4
- 230000005012 migration Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 239000003570 air Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000356 contaminant Substances 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Marketing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of equipment operation state monitoring, in particular to an operation and maintenance method and system for pollution treatment equipment, wherein a dynamic data prediction model is constructed to obtain a predicted operation data book of each piece of equipment in the treatment equipment based on time sequences in an operation and maintenance time period; clustering actual operation data in the characteristic database by a hierarchical clustering method to obtain an initial clustering operation data base of each piece of sub-equipment in the treatment equipment based on time sequences in an operation and maintenance time period; evaluating actual operation data in the initial cluster operation data book through a Z-Score algorithm to obtain a final cluster operation data book of each piece of sub-equipment in the treatment equipment based on a time sequence in an operation and maintenance time period; and an operation and maintenance report is generated, and remote management, data analysis and automatic monitoring and maintenance of the equipment are realized, so that the operation and maintenance cost is reduced, and the consumption of human resources is reduced.
Description
Technical Field
The invention relates to the technical field of equipment operation state monitoring, in particular to an operation and maintenance method and system for pollution treatment equipment.
Background
Pollution abatement equipment refers to equipment or systems for reducing or eliminating environmental pollutant emissions that are capable of treating or filtering pollutants in air, water, or soil to ensure improved and protected environmental quality. However, the conventional operation and maintenance method of the pollution control equipment has problems such as low manual inspection efficiency, difficult equipment failure, untimely data monitoring and the like; conventional pollution control equipment often requires manual operation and maintenance, which not only requires a great deal of human resource investment, but also has lower efficiency. In order to improve the operation and maintenance efficiency of equipment, the invention provides an operation and maintenance method of pollution treatment equipment.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides an operation and maintenance method and system for pollution treatment equipment.
The technical scheme adopted by the invention for achieving the purpose is as follows:
the invention discloses an operation and maintenance method of pollution control equipment, which comprises the following steps:
S102: constructing a dynamic data prediction model, acquiring actual environmental parameters of treatment equipment in an operation and maintenance time period, importing the actual environmental parameters into the dynamic data prediction model, and predicting to obtain a predicted operation data book of each piece of equipment in the treatment equipment based on a time sequence in the operation and maintenance time period;
s104: continuously acquiring actual operation data of treatment equipment in an operation and maintenance time period through each monitoring sensor, constructing a database, inputting the actual operation data continuously acquired by each monitoring sensor into the database, and acquiring a characteristic database after acquisition is completed;
s106: clustering actual operation data in the characteristic database by a hierarchical clustering method to cluster each actual operation data into a corresponding cluster, so as to obtain an initial clustering operation data book of each piece of sub-equipment in the treatment equipment based on a time sequence in an operation and maintenance time period;
s108: evaluating actual operation data in the initial clustering operation data book through a Z-Score algorithm, so as to screen out outlier data, and re-clustering the outlier data to obtain a final clustering operation data book of each sub-device in the treatment device based on time sequences in an operation and maintenance time period;
S110: pairing and analyzing the predicted operation data book corresponding to each piece of sub-equipment and the final clustering operation data book to obtain abnormal operation data sub-equipment; and performing fault analysis on the operation data abnormal sub-equipment, generating an operation and maintenance report, and transmitting the operation and maintenance report to a remote user side.
Further, in a preferred embodiment of the present invention, a dynamic data prediction model is constructed, an actual environmental parameter of a abatement device in an operation and maintenance time period is obtained, the actual environmental parameter is imported into the dynamic data prediction model, and a predicted operation data book of each sub-device in the abatement device based on a time sequence in the operation and maintenance time period is obtained by prediction, specifically including:
acquiring historical operation data information corresponding to the treatment equipment when the environment parameters are preset, constructing a dynamic data prediction model based on a deep learning network, and dividing the historical operation data information into a training data book and a test data book;
importing the training data book into a dynamic data prediction model, carrying out back propagation training on the dynamic data prediction model through a cross loss function based on the training data book, and storing training parameters of the dynamic data prediction model after training errors are converged to a preset value;
Testing training parameters of the dynamic data prediction model through a test data book, and outputting the training parameters after the test result meets the preset requirement to obtain a trained dynamic data prediction model;
the method comprises the steps of obtaining actual environment parameters of treatment equipment in an operation and maintenance time period, guiding the actual environment parameters into a dynamic data prediction model after training is completed to conduct prediction, and obtaining a prediction operation data base of each piece of sub equipment in the treatment equipment based on time sequence in the operation and maintenance time period.
Further, in a preferred embodiment of the present invention, clustering is performed on actual operation data in the characteristic database by a hierarchical clustering method, so as to cluster each actual operation data into a corresponding cluster, and obtain an initial cluster operation data book of each sub-device in the treatment device based on a time sequence in an operation and maintenance time period, which specifically includes:
s202: acquiring actual operation data in a characteristic database, regarding each actual operation data as an independent cluster, and acquiring Euclidean distance between each cluster and the rest clusters;
s204: constructing a distance matrix according to Euclidean distance between each cluster and the rest clusters, searching two clusters closest to each other in the distance matrix, and combining the two clusters closest to each other into a new cluster;
S206: updating the distance matrix, adding the new cluster into the distance matrix, and recalculating Euclidean distance between the new cluster and the rest clusters;
s208: repeating the steps S204-S206 until the number of clusters reaches the preset number of clusters, and stopping iteration; generating a clustering result, and representing the clustering result as a clustering tree; the cluster tree is used for visualizing a cluster result and selecting the optimal cluster number;
s210: and distributing the actual operation data in the characteristic database to different cluster clusters according to the cluster tree, and dividing each cluster in the cluster tree after the distribution is finished to obtain an initial cluster operation data book of each sub-device in the treatment device based on the time sequence in the operation and maintenance time period.
Further, in a preferred embodiment of the present invention, the actual operation data in the initial cluster operation data book is evaluated by a Z-Score algorithm, so as to screen out outlier data, and the outlier data is reclustered, so as to obtain a final cluster operation data book based on time sequence of each sub-device in the treatment device in the operation and maintenance time period, which specifically includes:
acquiring an average value and a standard deviation of each actual running data in each initial clustering running data book, and calculating according to the average value and the standard deviation to obtain a Z-Score value of each actual running data in each initial clustering running data book;
Constructing a Z-Score data set, and importing a Z-Score value of each actual operation data in each initial clustering operation data book into the Z-Score data set; judging whether the Z-Score value is larger than a preset threshold one by one, marking actual operation data with the Z-Score value larger than the preset threshold as outlier data, and picking out the outlier data from an initial clustering operation data book to which the current operation data belongs;
acquiring outlier data which is picked out from an initial clustering operation data book, inputting the outlier data which is picked out from the initial clustering operation data book into other initial clustering operation data books, and acquiring Z-Score values of the outlier data in the other initial clustering operation data books;
if the Z-Score values of the outlier data in the rest initial clustering operation data books are all larger than a preset threshold value, marking the outlier data as invalid data, and thoroughly eliminating the invalid data;
if Z-Score values of the outlier data in the rest initial clustering operation data books are not larger than a preset threshold value, sorting the sizes of the Z-Score values of the outlier data in the rest initial clustering operation data books, extracting a minimum Z-Score value, and clustering the outlier data into an initial clustering operation data book corresponding to the minimum Z-Score value;
And after the outlier data of each initial clustering operation data book is processed, converting each processed initial clustering operation data book into a final clustering operation data book based on a time sequence.
Further, in a preferred embodiment of the present invention, the pairing analysis is performed on the predicted operation data book corresponding to each piece of sub-equipment and the final clustered operation data book, so as to obtain an abnormal piece of operation data sub-equipment, which specifically includes:
s302: acquiring a predicted operation data book and a final clustering operation data book corresponding to each piece of equipment, and pairing the predicted operation data book and the operation data of the final clustering operation data book at the same time node according to a time sequence to obtain a plurality of pairs of operation data point pairs;
s304: calculating the Manhattan distance of each pair of operation data points through a Manhattan distance algorithm, calculating the average value of all the Manhattan distances, taking the average value as the average Manhattan distance between the predicted operation data book and the final clustering operation data book of the corresponding sub-equipment, and determining the similarity between the predicted operation data book and the final clustering operation data book of the corresponding sub-equipment according to the average Manhattan distance;
s306: comparing the similarity with a preset similarity; if the similarity is greater than the preset similarity, marking the corresponding sub-equipment as normal sub-equipment of the operation data; if the similarity is not greater than the preset similarity, marking the corresponding sub-equipment as abnormal sub-equipment of the operation data;
S308: repeating the steps until the final clustering operation data book of all the sub-equipment is judged, and outputting the abnormal operation data sub-equipment.
Further, in a preferred embodiment of the present invention, fault analysis is performed on the operation data abnormal sub-device, an operation and maintenance report is generated, and the operation and maintenance report is transmitted to a remote user side, specifically:
acquiring service data corresponding to the operation data abnormal sub-equipment, and acquiring a predicted operation data book and a final clustering operation data book corresponding to the operation data abnormal sub-equipment;
regarding the service data as random variables, and analyzing the correlation between the random variables according to the predicted operation data book; assigning prior probability to each random variable, and calculating a conditional probability table of each random variable according to the joint probability distribution of the random variables with the prior probability;
constructing a Bayesian network according to the correlation among the random variables and the conditional probability table of each random variable;
importing a final clustering operation data book corresponding to the operation data abnormal sub-equipment into the Bayesian network to carry out fault deduction to obtain posterior probability of the operation data abnormal sub-equipment, and comparing the posterior probability with a preset probability value;
If the posterior probability is larger than a preset probability value, marking the operation data abnormal sub-equipment corresponding to the posterior probability larger than the preset probability value as fault sub-equipment;
acquiring assembly information among all sub-equipment in the treatment equipment, calculating the association degree between the fault sub-equipment in the treatment equipment and other sub-equipment through a gray association analysis method according to the assembly information, and calibrating the sub-equipment corresponding to the association degree larger than the preset association degree as the fault sub-equipment; the assembly information comprises an assembly position, an assembly relation and an assembly sequence;
and generating an operation and maintenance report according to the fault sub-equipment, and transmitting the operation and maintenance report to a remote user side.
The second aspect of the present invention discloses a pollution control device operation and maintenance system, which includes a memory and a processor, wherein the memory stores a pollution control device operation and maintenance method program, and when the pollution control device operation and maintenance method program is executed by the processor, the following steps are implemented:
constructing a dynamic data prediction model, acquiring actual environmental parameters of treatment equipment in an operation and maintenance time period, importing the actual environmental parameters into the dynamic data prediction model, and predicting to obtain a predicted operation data book of each piece of equipment in the treatment equipment based on a time sequence in the operation and maintenance time period;
Continuously acquiring actual operation data of treatment equipment in an operation and maintenance time period through each monitoring sensor, constructing a database, inputting the actual operation data continuously acquired by each monitoring sensor into the database, and acquiring a characteristic database after acquisition is completed;
clustering actual operation data in the characteristic database by a hierarchical clustering method to cluster each actual operation data into a corresponding cluster, so as to obtain an initial clustering operation data book of each piece of sub-equipment in the treatment equipment based on a time sequence in an operation and maintenance time period;
evaluating actual operation data in the initial clustering operation data book through a Z-Score algorithm, so as to screen out outlier data, and re-clustering the outlier data to obtain a final clustering operation data book of each sub-device in the treatment device based on time sequences in an operation and maintenance time period;
pairing and analyzing the predicted operation data book corresponding to each piece of sub-equipment and the final clustering operation data book to obtain abnormal operation data sub-equipment; and performing fault analysis on the operation data abnormal sub-equipment, generating an operation and maintenance report, and transmitting the operation and maintenance report to a remote user side.
The invention solves the technical defects existing in the background technology, and has the following beneficial effects: according to the method, the pollution treatment equipment is connected with the cloud platform by utilizing the Internet of things technology, so that real-time monitoring and analysis of data are realized, fault early warning and maintenance guidance of the equipment are performed through an intelligent algorithm, and the operation and maintenance efficiency is improved; through intelligent monitoring and control system, realize remote management, data analysis and the automatic monitoring maintenance of equipment to the fortune dimension reduce cost, reduce the consumption of manpower resources.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other embodiments of the drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a first method flow diagram of a pollution abatement device operation and maintenance method;
FIG. 2 is a second method flow diagram of a pollution abatement device operation and maintenance method;
FIG. 3 is a third method flow diagram of a pollution abatement device operation and maintenance method;
Fig. 4 is a system block diagram of a pollution abatement device operation and maintenance system.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, the present application may be practiced in other ways than those described herein, and therefore the scope of the present application is not limited to the specific embodiments disclosed below.
As shown in fig. 1, the first aspect of the present application discloses a method for operating and maintaining a pollution control device, comprising the steps of:
s102: constructing a dynamic data prediction model, acquiring actual environmental parameters of treatment equipment in an operation and maintenance time period, importing the actual environmental parameters into the dynamic data prediction model, and predicting to obtain a predicted operation data book of each piece of equipment in the treatment equipment based on a time sequence in the operation and maintenance time period;
s104: continuously acquiring actual operation data of treatment equipment in an operation and maintenance time period through each monitoring sensor, constructing a database, inputting the actual operation data continuously acquired by each monitoring sensor into the database, and acquiring a characteristic database after acquisition is completed;
S106: clustering actual operation data in the characteristic database by a hierarchical clustering method to cluster each actual operation data into a corresponding cluster, so as to obtain an initial clustering operation data book of each piece of sub-equipment in the treatment equipment based on a time sequence in an operation and maintenance time period;
s108: evaluating actual operation data in the initial clustering operation data book through a Z-Score algorithm, so as to screen out outlier data, and re-clustering the outlier data to obtain a final clustering operation data book of each sub-device in the treatment device based on time sequences in an operation and maintenance time period;
s110: pairing and analyzing the predicted operation data book corresponding to each piece of sub-equipment and the final clustering operation data book to obtain abnormal operation data sub-equipment; and performing fault analysis on the operation data abnormal sub-equipment, generating an operation and maintenance report, and transmitting the operation and maintenance report to a remote user side.
The method utilizes the internet of things technology to connect pollution treatment equipment with the cloud platform, realizes real-time monitoring and analysis of data, performs fault early warning and maintenance guidance of the equipment through an intelligent algorithm, and improves operation and maintenance efficiency; through intelligent monitoring and control system, realize remote management, data analysis and the automatic monitoring maintenance of equipment to the fortune dimension reduce cost, reduce the consumption of manpower resources.
Further, in a preferred embodiment of the present invention, a dynamic data prediction model is constructed, an actual environmental parameter of a abatement device in an operation and maintenance time period is obtained, the actual environmental parameter is imported into the dynamic data prediction model, and a predicted operation data book of each sub-device in the abatement device based on a time sequence in the operation and maintenance time period is obtained by prediction, specifically including:
acquiring historical operation data information corresponding to the treatment equipment when the environment parameters are preset, constructing a dynamic data prediction model based on a deep learning network, and dividing the historical operation data information into a training data book and a test data book;
importing the training data book into a dynamic data prediction model, carrying out back propagation training on the dynamic data prediction model through a cross loss function based on the training data book, and storing training parameters of the dynamic data prediction model after training errors are converged to a preset value;
testing training parameters of the dynamic data prediction model through a test data book, and outputting the training parameters after the test result meets the preset requirement to obtain a trained dynamic data prediction model;
the method comprises the steps of obtaining actual environment parameters of treatment equipment in an operation and maintenance time period, guiding the actual environment parameters into a dynamic data prediction model after training is completed to conduct prediction, and obtaining a prediction operation data base of each piece of sub equipment in the treatment equipment based on time sequence in the operation and maintenance time period.
It should be noted that, the environmental parameters include temperature, humidity, air pressure, etc.; the operation data comprise consumption of power, fuel, water and other resources required by the operation of the equipment, pollutant concentration, temperature, flow and the like after the equipment is processed, noise, vibration, gear shift, oil temperature and the like of the reduction gearbox. The historical operation data information corresponding to the treatment equipment when the preset environment parameters are combined is obtained through searching in a big data network, for example, the historical operation data information corresponding to the treatment equipment under the preset environment parameter combination condition that the working temperature is 35 ℃, the humidity is 38% and the air pressure is 101325Pa is obtained, and then the training is carried out according to the historical operation data to obtain a trained dynamic data prediction model. Then, the actual environmental parameters of the treatment equipment in the operation and maintenance time period are predicted by a series of sensors (such as a temperature sensor, a humidity sensor and the like), so that a predicted operation data book based on time sequences of all sub-equipment in the treatment equipment in the operation and maintenance time period, such as the power consumption of an energy storage battery and the like, is obtained according to the actual environmental parameters, and therefore the influence of the equipment working environmental parameters on the predicted operation data book can be eliminated through the steps, and the predicted operation data book with high accuracy is obtained. For example, the energy storage battery may be excessively worn in a low temperature environment because the ambient temperature may affect the discharge efficiency of the energy storage battery.
Further, in a preferred embodiment of the present invention, clustering is performed on actual operation data in the characteristic database by a hierarchical clustering method, so as to cluster each actual operation data into a corresponding cluster, and obtain an initial cluster operation data base of each sub-device in the treatment device based on a time sequence in an operation and maintenance time period, as shown in fig. 2, specifically:
s202: acquiring actual operation data in a characteristic database, regarding each actual operation data as an independent cluster, and acquiring Euclidean distance between each cluster and the rest clusters;
s204: constructing a distance matrix according to Euclidean distance between each cluster and the rest clusters, searching two clusters closest to each other in the distance matrix, and combining the two clusters closest to each other into a new cluster;
s206: updating the distance matrix, adding the new cluster into the distance matrix, and recalculating Euclidean distance between the new cluster and the rest clusters;
s208: repeating the steps S204-S206 until the number of clusters reaches the preset number of clusters, and stopping iteration; generating a clustering result, and representing the clustering result as a clustering tree; the cluster tree is used for visualizing a cluster result and selecting the optimal cluster number;
S210: and distributing the actual operation data in the characteristic database to different cluster clusters according to the cluster tree, and dividing each cluster in the cluster tree after the distribution is finished to obtain an initial cluster operation data book of each sub-device in the treatment device based on the time sequence in the operation and maintenance time period.
It should be noted that, the actual operation data of a plurality of preset time nodes (the intervals may be 1s, 5s, 10s, etc.) in the operation and maintenance time period of the treatment device are continuously collected through each monitoring sensor (such as a pollutant concentration sensor, a battery power sensor, etc.), then a database is constructed, the actual operation data continuously collected by each monitoring sensor is input into the database, and after the collection is completed, a characteristic database is obtained. Since the actual operational data stored in the characteristics database is extensive and unorganized, the cloud platform is unaware of what is electricity consumption data, what is water consumption data, or what is contaminant concentration data, etc. Therefore, in the above steps, the actual operation data collected in the characteristic database is clustered by the hierarchical clustering method, and the center of the cluster, the number of samples of the cluster, the characteristics of the cluster and the like can be calculated by further analyzing the partitioned cluster, so as to obtain understanding and explanation of the clustering result, and the collected actual operation data is classified, so that operation data of different categories such as power consumption data, water consumption data or pollutant concentration and the like can be quickly obtained.
Further, in a preferred embodiment of the present invention, the actual operation data in the initial cluster operation data book is evaluated by a Z-Score algorithm, so as to screen out outlier data, and the outlier data is reclustered, so as to obtain a final cluster operation data book based on time sequence of each sub-device in the treatment device in the operation and maintenance time period, which specifically includes:
acquiring an average value and a standard deviation of each actual running data in each initial clustering running data book, and calculating according to the average value and the standard deviation to obtain a Z-Score value of each actual running data in each initial clustering running data book;
constructing a Z-Score data set, and importing a Z-Score value of each actual operation data in each initial clustering operation data book into the Z-Score data set; judging whether the Z-Score value is larger than a preset threshold one by one, marking actual operation data with the Z-Score value larger than the preset threshold as outlier data, and picking out the outlier data from an initial clustering operation data book to which the current operation data belongs;
acquiring outlier data which is picked out from an initial clustering operation data book, inputting the outlier data which is picked out from the initial clustering operation data book into other initial clustering operation data books, and acquiring Z-Score values of the outlier data in the other initial clustering operation data books;
If the Z-Score values of the outlier data in the rest initial clustering operation data books are all larger than a preset threshold value, marking the outlier data as invalid data, and thoroughly eliminating the invalid data;
if Z-Score values of the outlier data in the rest initial clustering operation data books are not larger than a preset threshold value, sorting the sizes of the Z-Score values of the outlier data in the rest initial clustering operation data books, extracting a minimum Z-Score value, and clustering the outlier data into an initial clustering operation data book corresponding to the minimum Z-Score value;
and after the outlier data of each initial clustering operation data book is processed, converting each processed initial clustering operation data book into a final clustering operation data book based on a time sequence.
It should be noted that, due to the algorithm defect of the hierarchical clustering method, when the actual operation data in the characteristic database is clustered, a phenomenon of clustering may occur, such as clustering certain electric consumption data into water consumption data, and reliability of the clustered data is still low, so that corresponding subsequent analysis results may be obtained. Therefore, in the above steps, the initial clustering operation data book obtained by hierarchical clustering is checked by a Z-Score algorithm (standard Score algorithm), so that data with a clustering error is identified, and the error data is re-divided into suitable clusters. Arithmetic average is carried out on all data in a data book to obtain an average value; the standard deviation is a measure of the degree of dispersion of a set of numbers themselves. The sum of squares of the deviations (i.e., the value of each value minus the average) for all the data in the dataset is then divided by the number of data to yield the variance, which is the square root of the variance. Then, calculating according to the average value and the standard deviation to obtain a Z-Score value of each actual operation data in each initial clustering operation data book, wherein the Z-Score of one data point is greater than 3, and then the data point is considered as abnormal data, at the moment, the actual operation data with the Z-Score value greater than 3 is marked as outlier data, and the outlier data is removed from the initial clustering operation data book to which the current data point belongs; then obtaining Z-Score values of the outlier data in the rest initial clustering operation data books by the same method, if the Z-Score values of the outlier data in the rest initial clustering operation data books are all larger than 3, indicating that the data do not belong to any clustering clusters, marking the outlier data as invalid data if the data are not the data required for monitoring, and thoroughly eliminating the invalid data; and if the Z-Score value of the outlier data in the rest initial clustering operation data books is not more than 3, extracting a minimum Z-Score value, and clustering the outlier data into the initial clustering operation data book corresponding to the minimum Z-Score value. Through the steps, the initial clustering operation data book can be checked, so that data with clustering errors are identified, the error data is re-divided into proper clustering clusters, the final clustering operation data book is obtained, the accuracy of the data in the clustered data book is improved, and the reliability of analysis results is improved.
Further, in a preferred embodiment of the present invention, the predicted operation data book corresponding to each piece of sub-equipment and the final clustered operation data book are paired and analyzed to obtain an abnormal piece of operation data sub-equipment, as shown in fig. 3, specifically:
s302: acquiring a predicted operation data book and a final clustering operation data book corresponding to each piece of equipment, and pairing the predicted operation data book and the operation data of the final clustering operation data book at the same time node according to a time sequence to obtain a plurality of pairs of operation data point pairs;
s304: calculating the Manhattan distance of each pair of operation data points through a Manhattan distance algorithm, calculating the average value of all the Manhattan distances, taking the average value as the average Manhattan distance between the predicted operation data book and the final clustering operation data book of the corresponding sub-equipment, and determining the similarity between the predicted operation data book and the final clustering operation data book of the corresponding sub-equipment according to the average Manhattan distance;
s306: comparing the similarity with a preset similarity; if the similarity is greater than the preset similarity, marking the corresponding sub-equipment as normal sub-equipment of the operation data; if the similarity is not greater than the preset similarity, marking the corresponding sub-equipment as abnormal sub-equipment of the operation data;
S308: repeating the steps until the final clustering operation data book of all the sub-equipment is judged, and outputting the abnormal operation data sub-equipment.
It should be noted that, by acquiring the predicted operation data book and the final clustering operation data book corresponding to the sub-devices such as the energy storage battery and the reduction gearbox, and pairing the predicted operation data book and the final clustering operation data book at the same time node according to the time sequence, a plurality of pairs of operation data point pairs are obtained, for example, the actual oil temperature of the reduction gearbox at the 5 th second is paired with the predicted oil temperature, so as to obtain the oil temperature data point pair. The smaller the average Manhattan distance, the more similar the two data books are; the larger the distance, the more dissimilar the two data books are represented. If the similarity is larger than the preset similarity, indicating that the actual operation data of the corresponding sub-equipment is highly matched with the predicted operation data, and marking the corresponding sub-equipment as normal sub-equipment of the operation data; if the similarity is not greater than the preset similarity, indicating that the matching degree of the actual operation data and the predicted operation data of the corresponding sub-equipment is low, marking the corresponding sub-equipment as the abnormal operation data sub-equipment. Through the steps, whether the operation data of all the sub-equipment in the treatment equipment is normal or not in the operation and maintenance time period can be effectively judged.
Further, in a preferred embodiment of the present invention, fault analysis is performed on the operation data abnormal sub-device, an operation and maintenance report is generated, and the operation and maintenance report is transmitted to a remote user side, specifically:
acquiring service data corresponding to the operation data abnormal sub-equipment, and acquiring a predicted operation data book and a final clustering operation data book corresponding to the operation data abnormal sub-equipment;
regarding the service data as random variables, and analyzing the correlation between the random variables according to the predicted operation data book; assigning prior probability to each random variable, and calculating a conditional probability table of each random variable according to the joint probability distribution of the random variables with the prior probability;
constructing a Bayesian network according to the correlation among the random variables and the conditional probability table of each random variable;
importing a final clustering operation data book corresponding to the operation data abnormal sub-equipment into the Bayesian network to carry out fault deduction to obtain posterior probability of the operation data abnormal sub-equipment, and comparing the posterior probability with a preset probability value;
if the posterior probability is larger than a preset probability value, marking the operation data abnormal sub-equipment corresponding to the posterior probability larger than the preset probability value as fault sub-equipment;
Acquiring assembly information among all sub-equipment in the treatment equipment, calculating the association degree between the fault sub-equipment in the treatment equipment and other sub-equipment through a gray association analysis method according to the assembly information, and calibrating the sub-equipment corresponding to the association degree larger than the preset association degree as the fault sub-equipment; the assembly information comprises an assembly position, an assembly relation and an assembly sequence;
and generating an operation and maintenance report according to the fault sub-equipment, and transmitting the operation and maintenance report to a remote user side.
It should be noted that the service data includes total running time, lifetime stage, on/off state, working mode, performance index, equipment configuration information, system version, etc. of the sub-equipment. The Bayesian network fault prediction model is a prediction method based on a probability map model and is used for identifying possible faults and abnormal conditions of a system. It predicts the occurrence of a fault by constructing a probabilistic correlation between random variables based on bayesian theorem and conditional independence assumption. In a bayesian network, random variables represent states or properties of a system, and conditional probabilities represent dependencies between them. By observing known variable values, bayesian reasoning can be used to calculate posterior probability distributions of other variables, and the fault prediction model uses the service data and the prediction operation data to train the Bayesian network, thereby establishing a probability model between the variables. Through the steps, whether the operation data abnormal sub-equipment is in a fault state or not can be further judged.
In addition, in a abatement device, when one sub-device fails, it may cause the associated other sub-device to also fail, and the associated sub-device may have a physical relationship or dependency. When one sub-device fails, it may apply additional load or pressure to the other sub-device, resulting in failure of the other sub-device. For example, failure of the heat sinks of the abatement device may cause other components to overheat, thereby causing failure of the other components. Therefore, the association degree between the fault sub-equipment and other sub-equipment in the treatment equipment is calculated through a gray association analysis method, and the sub-equipment corresponding to which the association degree is larger than the preset association degree is marked as the fault sub-equipment, so that whether the current fault sub-equipment also contains the other sub-equipment for fault is further analyzed, and comprehensive fault early warning and monitoring are carried out on all the sub-equipment, thereby improving the operation and maintenance efficiency and reducing the cost.
In addition, the pollution control device operation and maintenance method further comprises the following steps:
acquiring wireless signal transmission channels between the treatment equipment and the cloud platform, and acquiring real-time environmental factors of the wireless signal transmission channels;
acquiring signal-to-noise ratios corresponding to the wireless signal transmission channels under the preset environmental factor combination condition through big data, constructing a knowledge graph, and importing the signal-to-noise ratios corresponding to the wireless signal transmission channels under the preset environmental factor combination condition into the knowledge graph;
The real-time environmental factors are imported into the knowledge graph, hash values between the real-time environmental factors and each preset environmental factor combination are calculated through a hash algorithm, and a plurality of hash values are obtained;
extracting a maximum hash value from the plurality of hash values, acquiring a preset environment factor combination corresponding to the maximum hash value, and determining the actual signal-to-noise ratio of the transmission signals of each wireless signal transmission channel under the condition of real-time loop factors according to the preset environment factor combination corresponding to the maximum hash value;
comparing the actual signal-to-noise ratio of the transmission signal of each wireless signal transmission channel under the real-time loop factor condition with a preset signal-to-noise ratio, and providing a wireless signal transmission channel corresponding to the actual signal-to-noise ratio being larger than the preset signal-to-noise ratio;
the method comprises the steps of obtaining transmission distances of wireless signal transmission channels corresponding to the actual signal to noise ratio being larger than the preset signal to noise ratio, obtaining a plurality of transmission distances, and calibrating the wireless signal transmission channel with the smallest transmission distance as an optimal wireless signal transmission channel, so that the cloud platform receives data signals of treatment equipment through the optimal wireless signal transmission channel.
The wireless signal transmission channel between the treatment equipment with high transmission quality and stable signal and the cloud platform can be screened through the steps.
In addition, the pollution control device operation and maintenance method further comprises the following steps:
acquiring pollutant concentration data information in a preset area, constructing a pollutant concentration change curve graph according to the pollutant concentration data information, and acquiring the concentration change rate of pollutants in preset time according to the pollutant concentration change curve graph;
if the concentration change rate is larger than the preset change rate, acquiring treatment area information of corresponding treatment equipment, and acquiring the pollutant concentration change rate of each subarea in the treatment area;
and predicting a migration flow direction region of the pollutants according to the pollutant concentration change rate of each subarea, and adjusting the positions of corresponding treatment equipment according to the migration flow direction region of the pollutants.
It should be noted that, if the concentration change rate of the pollutant in the preset area is greater than the preset change rate, it is indicated that the pollutant treatment condition in the area is abnormal, and this may be that the pollutant is further migrated due to weather reasons, for example, the pollutant is migrated due to flooding, at this time, it is indicated that the pollutant has migrated to the other areas, at this time, even if the preset area is continuously treated, it is not significant, at this time, the migration position of the pollutant needs to be further predicted, and then the position of the corresponding treatment device is adjusted according to the migration position, so as to improve the rationality of the layout of the treatment device.
As shown in fig. 4, the second aspect of the present invention discloses a pollution control device operation and maintenance system, which includes a memory 41 and a processor 42, wherein the memory 41 stores a pollution control device operation and maintenance method program, and when the pollution control device operation and maintenance method program is executed by the processor 42, the following steps are implemented:
constructing a dynamic data prediction model, acquiring actual environmental parameters of treatment equipment in an operation and maintenance time period, importing the actual environmental parameters into the dynamic data prediction model, and predicting to obtain a predicted operation data book of each piece of equipment in the treatment equipment based on a time sequence in the operation and maintenance time period;
continuously acquiring actual operation data of treatment equipment in an operation and maintenance time period through each monitoring sensor, constructing a database, inputting the actual operation data continuously acquired by each monitoring sensor into the database, and acquiring a characteristic database after acquisition is completed;
clustering actual operation data in the characteristic database by a hierarchical clustering method to cluster each actual operation data into a corresponding cluster, so as to obtain an initial clustering operation data book of each piece of sub-equipment in the treatment equipment based on a time sequence in an operation and maintenance time period;
Evaluating actual operation data in the initial clustering operation data book through a Z-Score algorithm, so as to screen out outlier data, and re-clustering the outlier data to obtain a final clustering operation data book of each sub-device in the treatment device based on time sequences in an operation and maintenance time period;
pairing and analyzing the predicted operation data book corresponding to each piece of sub-equipment and the final clustering operation data book to obtain abnormal operation data sub-equipment; and performing fault analysis on the operation data abnormal sub-equipment, generating an operation and maintenance report, and transmitting the operation and maintenance report to a remote user side.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (7)
1. An operation and maintenance method for pollution control equipment is characterized by comprising the following steps:
s102: constructing a dynamic data prediction model, acquiring actual environmental parameters of treatment equipment in an operation and maintenance time period, importing the actual environmental parameters into the dynamic data prediction model, and predicting to obtain a predicted operation data book of each piece of equipment in the treatment equipment based on a time sequence in the operation and maintenance time period;
s104: continuously acquiring actual operation data of treatment equipment in an operation and maintenance time period through each monitoring sensor, constructing a database, inputting the actual operation data continuously acquired by each monitoring sensor into the database, and acquiring a characteristic database after acquisition is completed;
s106: clustering actual operation data in the characteristic database by a hierarchical clustering method to cluster each actual operation data into a corresponding cluster, so as to obtain an initial clustering operation data book of each piece of sub-equipment in the treatment equipment based on a time sequence in an operation and maintenance time period;
s108: evaluating actual operation data in the initial clustering operation data book through a Z-Score algorithm, so as to screen out outlier data, and re-clustering the outlier data to obtain a final clustering operation data book of each sub-device in the treatment device based on time sequences in an operation and maintenance time period;
S110: pairing and analyzing the predicted operation data book corresponding to each piece of sub-equipment and the final clustering operation data book to obtain abnormal operation data sub-equipment; and performing fault analysis on the operation data abnormal sub-equipment, generating an operation and maintenance report, and transmitting the operation and maintenance report to a remote user side.
2. The method for operating and maintaining pollution control equipment according to claim 1, wherein a dynamic data prediction model is constructed, actual environmental parameters of the pollution control equipment in an operation and maintenance time period are obtained, the actual environmental parameters are imported into the dynamic data prediction model, and prediction is carried out to obtain a predicted operation data book of each sub-equipment in the pollution control equipment based on time sequence in the operation and maintenance time period, specifically:
acquiring historical operation data information corresponding to the treatment equipment when the environment parameters are preset, constructing a dynamic data prediction model based on a deep learning network, and dividing the historical operation data information into a training data book and a test data book;
importing the training data book into a dynamic data prediction model, carrying out back propagation training on the dynamic data prediction model through a cross loss function based on the training data book, and storing training parameters of the dynamic data prediction model after training errors are converged to a preset value;
Testing training parameters of the dynamic data prediction model through a test data book, and outputting the training parameters after the test result meets the preset requirement to obtain a trained dynamic data prediction model;
the method comprises the steps of obtaining actual environment parameters of treatment equipment in an operation and maintenance time period, guiding the actual environment parameters into a dynamic data prediction model after training is completed to conduct prediction, and obtaining a prediction operation data base of each piece of sub equipment in the treatment equipment based on time sequence in the operation and maintenance time period.
3. The operation and maintenance method of pollution control equipment according to claim 1, wherein clustering is performed on actual operation data in the characteristic database by a hierarchical clustering method to cluster each actual operation data into a corresponding cluster, so as to obtain an initial cluster operation data book of each sub-equipment in the pollution control equipment based on a time sequence in an operation and maintenance time period, which specifically comprises:
s202: acquiring actual operation data in a characteristic database, regarding each actual operation data as an independent cluster, and acquiring Euclidean distance between each cluster and the rest clusters;
s204: constructing a distance matrix according to Euclidean distance between each cluster and the rest clusters, searching two clusters closest to each other in the distance matrix, and combining the two clusters closest to each other into a new cluster;
S206: updating the distance matrix, adding the new cluster into the distance matrix, and recalculating Euclidean distance between the new cluster and the rest clusters;
s208: repeating the steps S204-S206 until the number of clusters reaches the preset number of clusters, and stopping iteration; generating a clustering result, and representing the clustering result as a clustering tree; the cluster tree is used for visualizing a cluster result and selecting the optimal cluster number;
s210: and distributing the actual operation data in the characteristic database to different cluster clusters according to the cluster tree, and dividing each cluster in the cluster tree after the distribution is finished to obtain an initial cluster operation data book of each sub-device in the treatment device based on the time sequence in the operation and maintenance time period.
4. The method for operating and maintaining pollution control equipment according to claim 1, wherein the actual operation data in the initial clustering operation data book is evaluated through a Z-Score algorithm, so as to screen out outlier data, and the outlier data is reclustered, so as to obtain a final clustering operation data book of each sub-equipment in the pollution control equipment based on time sequence in an operation and maintenance time period, which is specifically as follows:
Acquiring an average value and a standard deviation of each actual running data in each initial clustering running data book, and calculating according to the average value and the standard deviation to obtain a Z-Score value of each actual running data in each initial clustering running data book;
constructing a Z-Score data set, and importing a Z-Score value of each actual operation data in each initial clustering operation data book into the Z-Score data set; judging whether the Z-Score value is larger than a preset threshold one by one, marking actual operation data with the Z-Score value larger than the preset threshold as outlier data, and picking out the outlier data from an initial clustering operation data book to which the current operation data belongs;
acquiring outlier data which is picked out from an initial clustering operation data book, inputting the outlier data which is picked out from the initial clustering operation data book into other initial clustering operation data books, and acquiring Z-Score values of the outlier data in the other initial clustering operation data books;
if the Z-Score values of the outlier data in the rest initial clustering operation data books are all larger than a preset threshold value, marking the outlier data as invalid data, and thoroughly eliminating the invalid data;
if Z-Score values of the outlier data in the rest initial clustering operation data books are not larger than a preset threshold value, sorting the sizes of the Z-Score values of the outlier data in the rest initial clustering operation data books, extracting a minimum Z-Score value, and clustering the outlier data into an initial clustering operation data book corresponding to the minimum Z-Score value;
And after the outlier data of each initial clustering operation data book is processed, converting each processed initial clustering operation data book into a final clustering operation data book based on a time sequence.
5. The operation and maintenance method of pollution control equipment according to claim 1, wherein the pairing analysis is performed on the predicted operation data book corresponding to each piece of equipment and the final clustering operation data book to obtain abnormal piece of operation data equipment, specifically:
s302: acquiring a predicted operation data book and a final clustering operation data book corresponding to each piece of equipment, and pairing the predicted operation data book and the operation data of the final clustering operation data book at the same time node according to a time sequence to obtain a plurality of pairs of operation data point pairs;
s304: calculating the Manhattan distance of each pair of operation data points through a Manhattan distance algorithm, calculating the average value of all the Manhattan distances, taking the average value as the average Manhattan distance between the predicted operation data book and the final clustering operation data book of the corresponding sub-equipment, and determining the similarity between the predicted operation data book and the final clustering operation data book of the corresponding sub-equipment according to the average Manhattan distance;
S306: comparing the similarity with a preset similarity; if the similarity is greater than the preset similarity, marking the corresponding sub-equipment as normal sub-equipment of the operation data; if the similarity is not greater than the preset similarity, marking the corresponding sub-equipment as abnormal sub-equipment of the operation data;
s308: repeating the steps until the final clustering operation data book of all the sub-equipment is judged, and outputting the abnormal operation data sub-equipment.
6. The method for operating and maintaining a pollution control device according to claim 1, wherein the fault analysis is performed on the abnormal sub-device of the operation data, an operation and maintenance report is generated, and the operation and maintenance report is transmitted to a remote user side, specifically:
acquiring service data corresponding to the operation data abnormal sub-equipment, and acquiring a predicted operation data book and a final clustering operation data book corresponding to the operation data abnormal sub-equipment;
regarding the service data as random variables, and analyzing the correlation between the random variables according to the predicted operation data book; assigning prior probability to each random variable, and calculating a conditional probability table of each random variable according to the joint probability distribution of the random variables with the prior probability;
Constructing a Bayesian network according to the correlation among the random variables and the conditional probability table of each random variable;
importing a final clustering operation data book corresponding to the operation data abnormal sub-equipment into the Bayesian network to carry out fault deduction to obtain posterior probability of the operation data abnormal sub-equipment, and comparing the posterior probability with a preset probability value;
if the posterior probability is larger than a preset probability value, marking the operation data abnormal sub-equipment corresponding to the posterior probability larger than the preset probability value as fault sub-equipment;
acquiring assembly information among all sub-equipment in the treatment equipment, calculating the association degree between the fault sub-equipment in the treatment equipment and other sub-equipment through a gray association analysis method according to the assembly information, and calibrating the sub-equipment corresponding to the association degree larger than the preset association degree as the fault sub-equipment; the assembly information comprises an assembly position, an assembly relation and an assembly sequence;
and generating an operation and maintenance report according to the fault sub-equipment, and transmitting the operation and maintenance report to a remote user side.
7. The operation and maintenance system of the pollution control equipment is characterized by comprising a memory and a processor, wherein the memory stores an operation and maintenance method program of the pollution control equipment, and when the operation and maintenance method program of the pollution control equipment is executed by the processor, the following steps are realized:
Constructing a dynamic data prediction model, acquiring actual environmental parameters of treatment equipment in an operation and maintenance time period, importing the actual environmental parameters into the dynamic data prediction model, and predicting to obtain a predicted operation data book of each piece of equipment in the treatment equipment based on a time sequence in the operation and maintenance time period;
continuously acquiring actual operation data of treatment equipment in an operation and maintenance time period through each monitoring sensor, constructing a database, inputting the actual operation data continuously acquired by each monitoring sensor into the database, and acquiring a characteristic database after acquisition is completed;
clustering actual operation data in the characteristic database by a hierarchical clustering method to cluster each actual operation data into a corresponding cluster, so as to obtain an initial clustering operation data book of each piece of sub-equipment in the treatment equipment based on a time sequence in an operation and maintenance time period;
evaluating actual operation data in the initial clustering operation data book through a Z-Score algorithm, so as to screen out outlier data, and re-clustering the outlier data to obtain a final clustering operation data book of each sub-device in the treatment device based on time sequences in an operation and maintenance time period;
Pairing and analyzing the predicted operation data book corresponding to each piece of sub-equipment and the final clustering operation data book to obtain abnormal operation data sub-equipment; and performing fault analysis on the operation data abnormal sub-equipment, generating an operation and maintenance report, and transmitting the operation and maintenance report to a remote user side.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311135408.5A CN116862081B (en) | 2023-09-05 | 2023-09-05 | Operation and maintenance method and system for pollution treatment equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311135408.5A CN116862081B (en) | 2023-09-05 | 2023-09-05 | Operation and maintenance method and system for pollution treatment equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116862081A true CN116862081A (en) | 2023-10-10 |
| CN116862081B CN116862081B (en) | 2023-11-21 |
Family
ID=88225334
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311135408.5A Active CN116862081B (en) | 2023-09-05 | 2023-09-05 | Operation and maintenance method and system for pollution treatment equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116862081B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117236572A (en) * | 2023-11-14 | 2023-12-15 | 深圳市共安实业发展有限公司 | Method and system for evaluating performance of dry powder extinguishing equipment based on data analysis |
| CN117708552A (en) * | 2024-02-06 | 2024-03-15 | 华能江苏综合能源服务有限公司 | Power station operation data real-time monitoring method based on edge calculation |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107480895A (en) * | 2017-08-19 | 2017-12-15 | 中国标准化研究院 | A kind of reliable consumer goods methods of risk assessment based on Bayes enhancing study |
| WO2019237492A1 (en) * | 2018-06-13 | 2019-12-19 | 山东科技大学 | Semi-supervised learning-based abnormal electricity utilization user detection method |
| CN115096627A (en) * | 2022-06-16 | 2022-09-23 | 中南大学 | Method and system for fault diagnosis and operation and maintenance in manufacturing process of hydraulic forming intelligent equipment |
| CN115983710A (en) * | 2023-01-30 | 2023-04-18 | 国网湖南省电力有限公司 | High-proportion new energy access electric power system infrastructure project decision method and system |
| CN116629458A (en) * | 2023-07-24 | 2023-08-22 | 深圳康普盾科技股份有限公司 | Energy storage equipment operation optimization method and system based on data analysis |
-
2023
- 2023-09-05 CN CN202311135408.5A patent/CN116862081B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107480895A (en) * | 2017-08-19 | 2017-12-15 | 中国标准化研究院 | A kind of reliable consumer goods methods of risk assessment based on Bayes enhancing study |
| WO2019237492A1 (en) * | 2018-06-13 | 2019-12-19 | 山东科技大学 | Semi-supervised learning-based abnormal electricity utilization user detection method |
| CN115096627A (en) * | 2022-06-16 | 2022-09-23 | 中南大学 | Method and system for fault diagnosis and operation and maintenance in manufacturing process of hydraulic forming intelligent equipment |
| CN115983710A (en) * | 2023-01-30 | 2023-04-18 | 国网湖南省电力有限公司 | High-proportion new energy access electric power system infrastructure project decision method and system |
| CN116629458A (en) * | 2023-07-24 | 2023-08-22 | 深圳康普盾科技股份有限公司 | Energy storage equipment operation optimization method and system based on data analysis |
Non-Patent Citations (1)
| Title |
|---|
| 连子宽;姚力;刘晟源;余允涛;唐小淇;杨莉;林振智;: "基于t-SNE降维和BIRCH聚类的单相用户相位及表箱辨识", 电力系统自动化, no. 08 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117236572A (en) * | 2023-11-14 | 2023-12-15 | 深圳市共安实业发展有限公司 | Method and system for evaluating performance of dry powder extinguishing equipment based on data analysis |
| CN117236572B (en) * | 2023-11-14 | 2024-03-29 | 深圳市共安实业发展有限公司 | Method and system for evaluating performance of dry powder extinguishing equipment based on data analysis |
| CN117708552A (en) * | 2024-02-06 | 2024-03-15 | 华能江苏综合能源服务有限公司 | Power station operation data real-time monitoring method based on edge calculation |
| CN117708552B (en) * | 2024-02-06 | 2024-05-10 | 华能江苏综合能源服务有限公司 | Power station operation data real-time monitoring method based on edge calculation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116862081B (en) | 2023-11-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116862081B (en) | Operation and maintenance method and system for pollution treatment equipment | |
| CN110703057B (en) | Power equipment partial discharge diagnosis method based on data enhancement and neural network | |
| CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
| AU2019243836A1 (en) | Predicting pipe failure | |
| CN111259947A (en) | Power system fault early warning method and system based on multi-mode learning | |
| CN111614491A (en) | Power monitoring system oriented safety situation assessment index selection method and system | |
| CN109800995A (en) | A kind of grid equipment fault recognition method and system | |
| CN116882790B (en) | Carbon emission equipment management method and system for mine ecological restoration area | |
| CN113705688B (en) | Abnormal electricity consumption behavior detection method and system for power users | |
| CN111984442A (en) | Method and device for detecting abnormality of computer cluster system, and storage medium | |
| CN115204536A (en) | Building equipment fault prediction method, device, equipment and storage medium | |
| CN116720324A (en) | Traction substation key equipment fault early warning method and system based on prediction model | |
| CN116739829A (en) | Big data-based power data analysis method, system and medium | |
| CN114138601A (en) | Service alarm method, device, equipment and storage medium | |
| CN117391727A (en) | Carbon neutralization method and system for negative carbon emission | |
| CN116132103A (en) | Network security situation monitoring method and device, electronic equipment and storage medium | |
| CN113449966B (en) | Gypsum board equipment inspection method and system | |
| CN116910635A (en) | Pressure regulator fault diagnosis method and device based on federal learning and expansion convolution | |
| CN113807462A (en) | AI-based network equipment fault reason positioning method and system | |
| CN115689320A (en) | Health management method and device for base station operation and computer readable storage medium | |
| CN115237606B (en) | Edge calculation control system | |
| CN115270140B (en) | Software security vulnerability management method and system | |
| CN117688501A (en) | Error correction method for air quality prediction system | |
| CN116821829A (en) | Transformer fault analysis method and device based on association rule analysis | |
| CN117376160A (en) | Analysis method of communication maintenance decision data based on state information |
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 |