CN113015120B - Pollution control monitoring system and method based on neural network - Google Patents
Pollution control monitoring system and method based on neural network Download PDFInfo
- Publication number
- CN113015120B CN113015120B CN202110117034.9A CN202110117034A CN113015120B CN 113015120 B CN113015120 B CN 113015120B CN 202110117034 A CN202110117034 A CN 202110117034A CN 113015120 B CN113015120 B CN 113015120B
- Authority
- CN
- China
- Prior art keywords
- pollution control
- pollution
- neural network
- monitoring
- parameters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 168
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 108
- 238000000034 method Methods 0.000 title claims description 13
- 238000003745 diagnosis Methods 0.000 claims abstract description 35
- 238000001514 detection method Methods 0.000 claims abstract description 21
- 238000013135 deep learning Methods 0.000 claims abstract description 7
- 238000004891 communication Methods 0.000 claims description 16
- 238000004519 manufacturing process Methods 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 6
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 238000011478 gradient descent method Methods 0.000 claims description 4
- 239000013307 optical fiber Substances 0.000 claims description 4
- 125000004122 cyclic group Chemical group 0.000 claims 2
- 238000005065 mining Methods 0.000 claims 2
- 238000013459 approach Methods 0.000 claims 1
- 238000012549 training Methods 0.000 claims 1
- 238000002203 pretreatment Methods 0.000 abstract 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000003912 environmental pollution Methods 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000010865 sewage Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/06—Protocols specially adapted for file transfer, e.g. file transfer protocol [FTP]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Feedback Control In General (AREA)
Abstract
The application provides a pollution control monitoring system based on a neural network, which comprises the steps of capturing monitoring parameters of all sensors through a graph capturer and forming a graph neural network structure, acquiring pollution indexes of all monitoring points of the whole pollution control area and/or specific loads and margins of pollution control equipment through the graph neural network by a graph neural network processor, then establishing a pollution detection model through a structural type circulating neural network according to the pollution indexes and/or the specific loads and margins by the pollution control processor, finally establishing a pollution diagnosis model through a deep confidence neural network by a pollution control diagnostor, dynamically adjusting and accurately diagnosing the pollution control capacity of the whole pollution control area, feeding back to a pollution control decision platform through a main control module, and further making pre-judgment and pre-treatment plans by the main control module, so that the problem that the traditional pollution control monitoring system does not have deep learning based on big data is solved, and real-time and comprehensive environment pollution monitoring and pre-warning are provided for the pre-judgment and selection of the pollution control decision platform.
Description
Technical Field
The application relates to the field of pollution control monitoring, in particular to a pollution control monitoring system and method based on a neural network.
Background
At present, the national pollution control equipment is gradually increased year by year, the operation and maintenance of the existing pollution control equipment mainly adopts a mode of combining equipment detection and manual monitoring, equipment and/or sensors are required to detect that pollution indexes exceed standards and then report to the police and upload, and then corresponding equipment and areas are manually interfered, so that deep learning based on big data is not formed, and then a pre-judging and processing plan is made, so that real-time and comprehensive environmental pollution monitoring and pre-warning are provided, the pollution control decision platform is used for carrying out the research, judgment and selection of the plan, and a comfortable living environment is provided for people. Thus, there is an urgent need for a pollution control monitoring system and method based on neural networks.
Disclosure of Invention
The application aims to provide a pollution control monitoring system and method based on a neural network, which are used for solving the problems that the existing pollution control monitoring system mainly adopts a mode of combining equipment detection and manual monitoring, equipment and/or sensors are required to detect pollution indexes, alarm and upload after exceeding standards, and then human intervention is performed on corresponding equipment and areas, so that deep learning based on big data is not formed, and then prejudgment and treatment plans are made, so that real-time and comprehensive environmental pollution monitoring and early warning are provided, the pollution control decision platform is used for carrying out the research, judgment and selection of the plans, and a comfortable living environment is provided for people.
In order to solve the technical problems, the application is realized as follows:
a neural network-based pollution control monitoring system, comprising: a monitoring terminal and a pollution control decision platform;
the monitoring terminal collects monitoring parameters of each monitoring point arranged in the pollution control area through the wired and/or wireless transceiver module, sends the monitoring parameters to the main control module and the memory, and sends the monitoring parameters to the pollution control decision platform through the wired and/or wireless transceiver module;
the pollution control decision platform comprises a wired and/or wireless transceiver module, a main control module, a memory, a graphic capturer, a graphic neural network processor, a pollution detector and a pollution control diagnostic device which are sequentially connected, wherein the main control module of the pollution control decision platform is respectively connected with the graphic capturer, the graphic neural network processor, the pollution detector and the pollution control diagnostic device;
the pollution control decision platform receives the monitoring parameters of the monitoring points sent by the monitoring terminal through the wired and/or wireless transceiver module, sends the monitoring parameters to the main control module and the memory of the pollution control decision platform, performs pollution early warning on each monitoring point in the pollution control area based on the neural network through the monitoring parameters, and performs pre-judgment diagnosis on pollution control equipment in the pollution control area;
the graphic capturer captures monitoring parameters of all sensors of each monitoring point in the pollution control area and forms a graphic neural network structure based on the sensor nodes, and the output end of the graphic capturer is connected with the input end of the graphic neural network processor;
the image neural network processor is used for excavating the intrinsic relation among characteristic parameters at different positions of each monitoring point in the pollution control area through the image neural network, and excavating the hidden layer relation of the characteristic parameters through an undirected image structure in the image neural network, so that the pollution index of each monitoring point in the pollution control area and/or the specific load and margin of pollution control equipment are obtained, the running environment of the whole pollution control area is effectively analyzed, and the output end of the image neural network processor is connected with the input end of the pollution detector;
the pollution detector establishes a pollution detection model of the whole pollution control area through a structural type circulating neural network according to the pollution index and/or specific load and margin so as to fully excavate time sequence characteristics among data, the established pollution detection model provides a basis for a pollution control diagnosis model, and the output end of the pollution detector is connected with the input end of the pollution control diagnosis device;
the pollution control diagnostor establishes a pollution diagnosis model through a deep confidence neural network, dynamically adjusts and accurately diagnoses the pollution control capacity of the whole pollution control area, and feeds back dynamic adjustment and diagnosis results to a pollution control decision platform through a main control module.
A pollution control monitoring method based on a neural network comprises the following steps:
101. the monitoring terminal collects monitoring parameters of each monitoring point arranged in the pollution control area through the wired and/or wireless transceiver module, sends the monitoring parameters to the main control module and the memory, and sends the monitoring parameters to the pollution control decision platform through the wired and/or wireless transceiver module;
102. the pollution control decision platform receives the monitoring parameters of the monitoring points sent by the monitoring terminal through the wired and/or wireless transceiver module, and sends the monitoring parameters to the main control module and the memory of the pollution control decision platform;
103. the graphic acquirer of the pollution control decision platform acquires monitoring parameters of all sensors of each monitoring point in a pollution control area and forms a graphic neural network structure based on sensor nodes, and the output end of the graphic acquirer is connected with the input end of the graphic neural network processor;
104. the graphic neural network processor of the pollution control decision platform is used for excavating the inherent relation among the characteristic parameters of different positions of each monitoring point in the pollution control area through the graphic neural network, and excavating the hidden layer relation of the characteristic parameters by utilizing an undirected graphic structure in the graphic neural network, so that the pollution index of each monitoring point in the pollution control area and/or the specific load and margin of pollution control equipment are obtained, the running environment of the whole pollution control area is effectively analyzed, and the output end of the graphic neural network processor is connected with the input end of the pollution detector;
105. the pollution detector of the pollution control decision platform establishes a pollution detection model of the whole pollution control area through a structural type circulating neural network according to the pollution index and/or specific load and margin so as to fully mine time sequence characteristics among data, the established pollution detection model provides a basis for a pollution control diagnosis model, and the output end of the pollution detector is connected with the input end of the pollution control diagnostic device;
106. a pollution diagnosis device of a pollution control decision platform establishes a pollution diagnosis model through a deep confidence neural network, dynamically adjusts and accurately diagnoses the pollution control capacity of the whole pollution control area, and feeds back dynamic adjustment and diagnosis results to the pollution control decision platform through a main control module.
Compared with the prior art, the technical scheme of the application comprises the steps of forming a monitoring early warning network of the whole pollution control area by arranging a sensor-monitoring terminal-pollution control decision platform, carrying out mathematical modeling on the pollution indexes of all monitoring points of the whole pollution control area and/or specific load and margin data of pollution control equipment by a neural network on the basis, specifically, capturing the monitoring parameters of all sensors of all monitoring points in the whole pollution control area by a graph capturer and forming a graph neural network structure based on sensor nodes, digging an internal relation among the monitoring parameters of different positions of the whole pollution control area by a graph neural network processor, obtaining the specific load and margin of the pollution indexes of all monitoring points of the whole pollution control area and/or specific load and margin of the pollution control equipment, then, establishing a pollution detection model of the whole pollution control area by a structural type circulating neural network by the pollution detector according to the pollution indexes and/or specific load and margin, optimizing the model parameters by a group intelligent optimization algorithm, finally, establishing a pollution diagnosis model by the pollution control diagnostic diagnostician by the deep confidence neural network, carrying out dynamic adjustment and the pollution control capacity of the whole pollution control area and carrying out the pollution control area and the pollution control equipment based on the basis of the corresponding dynamic adjustment and the real-time control module, and carrying out the artificial intervention on the basis of the pollution control model and the condition, and the condition is completely provided by the fact that the pollution control module is combined with the prior art has no real-time requirement and the corresponding to the prior art by the prior art, so that the pollution control decision platform can conduct the study, judgment and selection of the plan and provide a comfortable living environment for the masses.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort to a person of ordinary skill in the art.
Fig. 1 is a pollution control monitoring system based on a neural network according to an embodiment of the present application.
Fig. 2 is a schematic diagram of a pollution control monitoring method based on a neural network according to an embodiment of the present application.
Description of the embodiments
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
As shown in fig. 1, an embodiment of the present application provides a pollution control monitoring system based on a neural network, including: a monitoring terminal 1 and a pollution control decision platform 2;
the monitoring terminal 1 collects monitoring parameters of each monitoring point arranged in the pollution control area through the wired and/or wireless transceiver module 1-1, sends the monitoring parameters to the main control module 1-2 and the memory 1-3, and sends the monitoring parameters to the pollution control decision platform 2 through the wired and/or wireless transceiver module 1-4;
the pollution control decision platform 2 comprises a wired and/or wireless transceiver module 2-1, a main control module 2-2 and a memory 2-3, and further comprises a graphic acquirer 2-4, a graphic neural network processor 2-5, a pollution detector 2-6 and a pollution control diagnostic device 2-7 which are sequentially connected, wherein the main control module 2-2 of the pollution control decision platform 2 is respectively connected with the graphic acquirer 2-4, the graphic neural network processor 2-5, the pollution detector 2-6 and the pollution control diagnostic device 2-7;
the pollution control decision platform 2 receives monitoring parameters of monitoring points sent by the monitoring terminal 1 through the wired and/or wireless transceiver module 2-1, sends the monitoring parameters to the main control module 2-2 and the memory 2-3 of the pollution control decision platform 2, performs pollution early warning on each monitoring point in a pollution control area based on a neural network through the monitoring parameters, and performs pre-judgment diagnosis on pollution control equipment in the pollution control area;
the graphic acquirer 2-4 acquires monitoring parameters of all sensors of each monitoring point in the pollution control area and forms a graphic neural network structure based on sensor nodes, and the output end of the graphic acquirer is connected with the input end of the graphic neural network processor;
the graphic neural network processor 2-5 is used for excavating the inherent relation between the characteristic parameters of different positions of each monitoring point in the pollution control area through the graphic neural network, and excavating the hidden layer relation of the characteristic parameters through an undirected graphic structure in the graphic neural network, so that the pollution index of each monitoring point in the pollution control area and/or the specific load and margin of pollution control equipment are obtained, the running environment of the whole pollution control area is effectively analyzed, and the output end of the graphic neural network processor is connected with the input end of the pollution detector;
the pollution detector 2-6 establishes a pollution detection model of the whole pollution control area through a structural type circulating neural network according to the pollution index and/or specific load and margin so as to fully excavate time sequence characteristics among data, and the established pollution detection model provides basis for a pollution control diagnosis model and an input end of the pollution control diagnosis device connected with an output end of the pollution detector;
the pollution control diagnostic device 2-7 establishes a pollution diagnosis model through a deep confidence neural network, dynamically adjusts and accurately diagnoses the pollution control capacity of the whole pollution control area, and feeds back the dynamic adjustment and diagnosis results to the pollution control decision platform 2 through the main control module 2-2.
Preferably, the monitoring terminal 1 collects the monitoring parameters set at the monitoring points and sends the monitoring parameters to the pollution control decision platform 2, the pollution control decision platform 2 automatically decides how to adjust the operation conditions of the production facilities and the treatment facilities in the area, pollution control and emission conditions, pollution source stop and limit and peak-shifting production conditions and the like according to the deep learning of the three-layer neural network, and gives the manager of the pollution control decision platform 2 the study and selection of various plans, and provides the operation path of manual intervention and intervention while the pollution control decision platform 2 has deeply learned and automatically decided.
Preferably, the monitoring parameters of the monitoring points can be collected through a sensor, and can also be directly read by a connecting instrument in a working line of the equipment, wherein the monitoring parameters include, but are not limited to, working states of pollution control equipment of pollution discharge enterprises, including parameters such as current, voltage, power, electric quantity, temperature, throughput, treatment margin and the like, and also include air quality, water quality, flow, valve opening and the like of a pollution discharge outlet, and further include water quality, flow, liquid level of a sewage treatment plant, running conditions of equipment in a factory and the like.
Preferably, the pollution detector establishes a pollution detection model of the whole pollution treatment area through a structural type circulating neural network according to the pollution index and/or specific load and margin, optimizes model parameters through a group intelligent optimization algorithm, thereby rapidly obtaining an optimal solution of the model, fully excavating time sequence characteristics among data, recording past and present monitoring parameters of each monitoring point in time sequence, providing basis for predicting the future of the pollution treatment diagnosis model, and providing an input end of the pollution treatment diagnosis device connected with an output end of the pollution detector.
Preferably, the pollution control diagnostic device adopts a BP idea deep confidence neural network, performs tuning through back propagation, and aims at finding the optimal weight, wherein a back propagation algorithm adopts a back error propagation algorithm of a minimum mean square error criterion to update parameters of the whole network, a cost function is obtained, and then a gradient descent method is adopted to update the weight and bias parameters of the network.
Preferably, the monitoring terminal sends the monitoring parameters to the base station or the gateway through a wired communication mode such as optical fiber communication or other wireless communication modes such as LORA, 2/3/4/5G communication and the like, and then the base station or the gateway sends the monitoring parameters to the pollution control decision platform.
Preferably, the monitoring parameters are processed by the monitoring terminal in addition to being placed on the pollution control decision platform, and accordingly the operation load of the monitoring terminal can be increased.
As shown in fig. 2, an embodiment of the present application provides a pollution control monitoring method based on a neural network, which includes the steps of:
101. the monitoring terminal collects monitoring parameters of each monitoring point arranged in the pollution control area through the wired and/or wireless transceiver module, sends the monitoring parameters to the main control module and the memory, and sends the monitoring parameters to the pollution control decision platform through the wired and/or wireless transceiver module;
102. the pollution control decision platform receives the monitoring parameters of the monitoring points sent by the monitoring terminal through the wired and/or wireless transceiver module, and sends the monitoring parameters to the main control module and the memory of the pollution control decision platform;
103. the graphic acquirer of the pollution control decision platform acquires monitoring parameters of all sensors of each monitoring point in a pollution control area and forms a graphic neural network structure based on sensor nodes, and the output end of the graphic acquirer is connected with the input end of the graphic neural network processor;
104. the graphic neural network processor of the pollution control decision platform is used for excavating the inherent relation among the characteristic parameters of different positions of each monitoring point in the pollution control area through the graphic neural network, and excavating the hidden layer relation of the characteristic parameters by utilizing an undirected graphic structure in the graphic neural network, so that the pollution index of each monitoring point in the pollution control area and/or the specific load and margin of pollution control equipment are obtained, the running environment of the whole pollution control area is effectively analyzed, and the output end of the graphic neural network processor is connected with the input end of the pollution detector;
105. the pollution detector of the pollution control decision platform establishes a pollution detection model of the whole pollution control area through a structural type circulating neural network according to the pollution index and/or specific load and margin so as to fully mine time sequence characteristics among data, the established pollution detection model provides a basis for a pollution control diagnosis model, and the output end of the pollution detector is connected with the input end of the pollution control diagnostic device;
106. a pollution diagnosis device of a pollution control decision platform establishes a pollution diagnosis model through a deep confidence neural network, dynamically adjusts and accurately diagnoses the pollution control capacity of the whole pollution control area, and feeds back dynamic adjustment and diagnosis results to the pollution control decision platform through a main control module.
Preferably, in step 107, the pollution control decision platform automatically decides how to adjust the operation conditions of the production facilities and the treatment facilities, the pollution treatment and emission conditions, the pollution source stop and limit and peak-shifting production conditions and other information in the area according to the deep learning of the three-layer neural network, and gives the manager of the pollution control decision platform the decision and the selection of multiple plans, and provides the operation path of manual intervention and intervention while the pollution control decision platform has deeply learned and automatically decided.
Preferably, the monitoring parameters of the monitoring points in step 101 may be collected by a sensor, or may be directly read by a connection instrument in a working line of the equipment, where the monitoring parameters include, but are not limited to, working states of pollution control equipment of a pollution discharge enterprise, including parameters such as current, voltage, power, electric quantity, temperature, throughput, treatment margin, and the like, and also include air quality, water quality, flow, valve opening of a pollution discharge outlet, and also include water quality, flow, liquid level of a sewage treatment plant, running conditions of equipment in a factory, and the like.
Preferably, in step 105, the pollution detector establishes a pollution detection model of the whole pollution control area through a structural type circulating neural network according to the pollution index and/or specific load and margin, optimizes model parameters through a group intelligent optimization algorithm, thereby rapidly obtaining an optimal solution of the model, fully excavating time sequence characteristics among data, recording past and present monitoring parameters of each monitoring point in time sequence, and providing basis for predicting the future of the pollution control diagnosis model.
Preferably, in step 106, the pollution control diagnostic apparatus adopts a deep confidence neural network of BP idea, performs tuning through back propagation, and aims at finding an optimal weight, wherein a back propagation algorithm adopts a back error propagation algorithm of a minimum mean square error criterion to update parameters of the whole network, calculate a cost function, and then adopts a gradient descent method to update weight and bias parameters of the network.
Preferably, in step 101, the monitoring terminal sends the monitoring parameters to the base station or the gateway through a wired communication mode such as optical fiber communication or other wireless communication modes such as LORA, 2/3/4/5G communication and the like, and then the base station or the gateway sends the monitoring parameters to the pollution control decision platform.
Compared with the prior art, the technical scheme of the application comprises the steps of forming a monitoring early warning network of the whole pollution control area by arranging a sensor-monitoring terminal-pollution control decision platform, carrying out mathematical modeling on the pollution indexes of all monitoring points of the whole pollution control area and/or specific load and margin data of pollution control equipment by a neural network on the basis, specifically, capturing the monitoring parameters of all sensors of all monitoring points in the whole pollution control area by a graph capturer and forming a graph neural network structure based on sensor nodes, digging an internal relation among the monitoring parameters of different positions of the whole pollution control area by a graph neural network processor, obtaining the specific load and margin of the pollution indexes of all monitoring points of the whole pollution control area and/or specific load and margin of the pollution control equipment, then, establishing a pollution detection model of the whole pollution control area by a structural type circulating neural network by the pollution detector according to the pollution indexes and/or specific load and margin, optimizing the model parameters by a group intelligent optimization algorithm, finally, establishing a pollution diagnosis model by the pollution control diagnostic diagnostician by the deep confidence neural network, carrying out dynamic adjustment and the pollution control capacity of the whole pollution control area and carrying out the pollution control area and the pollution control equipment based on the basis of the corresponding dynamic adjustment and the real-time control module, and carrying out the artificial intervention on the basis of the pollution control model and the condition, and the condition is completely provided by the fact that the pollution control module is combined with the prior art has no real-time requirement and the corresponding to the prior art by the prior art, so that the pollution control decision platform can conduct the study, judgment and selection of the plan and provide a comfortable living environment for the masses.
The embodiments of the present application have been described above with reference to the accompanying drawings, but the present application is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present application and the scope of the claims, which are to be protected by the present application.
Claims (10)
1. A pollution control monitoring system based on a neural network, comprising: a monitoring terminal and a pollution control decision platform;
the monitoring terminal collects monitoring parameters of each monitoring point arranged in the pollution control area through the wired and/or wireless transceiver module, sends the monitoring parameters to the main control module and the memory, and sends the monitoring parameters to the pollution control decision platform through the wired and/or wireless transceiver module;
the pollution control decision platform comprises a wired and/or wireless transceiver module, a main control module, a memory, a graphic capturer, a graphic neural network processor, a pollution detector and a pollution control diagnostic device which are sequentially connected, wherein the main control module of the pollution control decision platform is respectively connected with the graphic capturer, the graphic neural network processor, the pollution detector and the pollution control diagnostic device;
the pollution control decision platform receives the monitoring parameters of the monitoring points sent by the monitoring terminal through the wired and/or wireless transceiver module, sends the monitoring parameters to the main control module and the memory of the pollution control decision platform, performs pollution early warning on each monitoring point in the pollution control area based on the neural network through the monitoring parameters, and performs pre-judgment diagnosis on pollution control equipment in the pollution control area;
the graphic capturer captures monitoring parameters of all sensors of each monitoring point in the pollution control area and forms a graphic neural network structure based on the sensor nodes, and the output end of the graphic capturer is connected with the input end of the graphic neural network processor;
the image neural network processor is used for excavating the intrinsic relation among characteristic parameters at different positions of each monitoring point in the pollution control area through the image neural network, and excavating the hidden layer relation of the characteristic parameters through an undirected image structure in the image neural network, so that the pollution index of each monitoring point in the pollution control area and/or the specific load and margin of pollution control equipment are obtained, the running environment of the whole pollution control area is effectively analyzed, and the output end of the image neural network processor is connected with the input end of the pollution detector;
the pollution detector establishes a pollution detection model of the whole pollution control area through a structural type circulating neural network according to the pollution index and/or specific load and margin so as to fully excavate time sequence characteristics among data, the established pollution detection model provides a basis for a pollution control diagnosis model, and the output end of the pollution detector is connected with the input end of the pollution control diagnosis device;
the pollution control diagnostor establishes a pollution diagnosis model through a deep confidence neural network, dynamically adjusts and accurately diagnoses the pollution control capacity of the whole pollution control area, and feeds back dynamic adjustment and diagnosis results to a pollution control decision platform through a main control module.
2. The pollution control monitoring system based on the neural network according to claim 1, wherein the monitoring terminal collects the monitoring parameters set at the monitoring points and sends the monitoring parameters to the pollution control decision platform, the pollution control decision platform automatically decides how to adjust the operation conditions, pollution control and emission conditions, pollution source stop production and peak-shifting production conditions of the production facilities and the pollution sources in the area according to the deep learning of the graphic neural network, the structural type circulating neural network and the deep confidence neural network, and gives the manager of the pollution control decision platform the study, judgment and selection of various plans, and provides the operation approach of manual intervention and intervention while the pollution control decision platform has deeply learned and automatically decided.
3. The pollution control monitoring system based on the neural network according to claim 1, wherein the pollution detector establishes a pollution detection model of the whole pollution control area through the structural type circulating neural network according to the pollution index and/or specific load and margin, optimizes model parameters through a group intelligent optimization algorithm, thereby rapidly obtaining an optimal solution of the model, fully mining time sequence characteristics among data, recording past and present monitoring parameters of each monitoring point in time sequence, and providing basis for predicting the future of the pollution control diagnosis model.
4. The pollution control monitoring system based on the neural network according to claim 1, wherein the pollution control diagnostic device adopts a deep belief neural network of BP idea, performs tuning through back propagation, and aims at finding the optimal weight, wherein a back propagation algorithm adopts a back error propagation algorithm of a minimum mean square error criterion to update parameters of the whole network, calculates a cost function, and then adopts a gradient descent method to update weight and bias parameters of the network.
5. The pollution control monitoring system based on the neural network according to claim 1, wherein the monitoring terminal sends the monitoring parameters to the base station or the gateway through an optical fiber communication wired communication mode or a LORA (local area network), 2/3/4/5G communication and other wireless communication modes, and then the monitoring parameters are sent to the pollution control decision platform through the base station or the gateway.
6. The pollution control monitoring method based on the neural network is characterized by comprising the following steps of:
101. the monitoring terminal collects monitoring parameters of each monitoring point arranged in the pollution control area through the wired and/or wireless transceiver module, sends the monitoring parameters to the main control module and the memory, and sends the monitoring parameters to the pollution control decision platform through the wired and/or wireless transceiver module;
102. the pollution control decision platform receives the monitoring parameters of the monitoring points sent by the monitoring terminal through the wired and/or wireless transceiver module, and sends the monitoring parameters to the main control module and the memory of the pollution control decision platform;
103. the graphic acquirer of the pollution control decision platform acquires monitoring parameters of all sensors of each monitoring point in a pollution control area and forms a graphic neural network structure based on sensor nodes, and the output end of the graphic acquirer is connected with the input end of the graphic neural network processor;
104. the graphic neural network processor of the pollution control decision platform is used for excavating the inherent relation among the characteristic parameters of different positions of each monitoring point in the pollution control area through the graphic neural network, and excavating the hidden layer relation of the characteristic parameters by utilizing an undirected graphic structure in the graphic neural network, so that the pollution index of each monitoring point in the pollution control area and/or the specific load and margin of pollution control equipment are obtained, the running environment of the whole pollution control area is effectively analyzed, and the output end of the graphic neural network processor is connected with the input end of the pollution detector;
105. the pollution detector of the pollution control decision platform establishes a pollution detection model of the whole pollution control area through a structural type circulating neural network according to the pollution index and/or specific load and margin so as to fully mine time sequence characteristics among data, the established pollution detection model provides a basis for a pollution control diagnosis model, and the output end of the pollution detector is connected with the input end of the pollution control diagnostic device;
106. a pollution diagnosis device of a pollution control decision platform establishes a pollution diagnosis model through a deep confidence neural network, dynamically adjusts and accurately diagnoses the pollution control capacity of the whole pollution control area, and feeds back dynamic adjustment and diagnosis results to the pollution control decision platform through a main control module.
7. The method of claim 6, wherein the step 107, the pollution control decision platform, based on the deep learning of the graphic neural network, the structural type cyclic neural network and the deep confidence neural network, automatically decides how to adjust the operation conditions, pollution control and emission conditions, pollution source stop and peak-shifting production condition information of the production facilities and the treatment facilities in the area, and gives the manager of the pollution control decision platform the decision and selection of various plans, and provides the operation path of manual intervention and intervention while the pollution control decision platform has already deeply learned and automatically decided.
8. The pollution control monitoring method based on the neural network according to claim 6, wherein the pollution detector establishes a pollution detection model of the whole pollution control area through the structural type cyclic neural network according to the pollution index and/or specific load and margin, optimizes model parameters through a group intelligent optimization algorithm, thereby rapidly obtaining an optimal solution of the model, fully mining time sequence characteristics among data, recording past and present monitoring parameters of each monitoring point in time sequence, and providing basis for predicting future of the pollution control diagnosis model.
9. The method of claim 6, wherein the step 106, the pollution control diagnostic apparatus uses a deep belief neural network based on BP concept, performs tuning by back propagation, and the training is to find the best weight, wherein the back propagation algorithm uses a back error propagation algorithm based on a minimum mean square error criterion to update the parameters of the whole network, calculate the cost function, and then uses a gradient descent method to update the weight and bias parameters of the network.
10. The pollution control monitoring method based on the neural network according to claim 9, wherein in step 101, the monitoring terminal sends the monitoring parameters to the base station or the gateway through an optical fiber communication wired communication mode or a LORA (local area network), 2/3/4/5G communication and other wireless communication modes, and then the base station or the gateway sends the monitoring parameters to the pollution control decision platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110117034.9A CN113015120B (en) | 2021-01-28 | 2021-01-28 | Pollution control monitoring system and method based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110117034.9A CN113015120B (en) | 2021-01-28 | 2021-01-28 | Pollution control monitoring system and method based on neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113015120A CN113015120A (en) | 2021-06-22 |
| CN113015120B true CN113015120B (en) | 2023-10-13 |
Family
ID=76384915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110117034.9A Active CN113015120B (en) | 2021-01-28 | 2021-01-28 | Pollution control monitoring system and method based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113015120B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114170756A (en) * | 2021-11-10 | 2022-03-11 | 三明学院 | Fire smoke recognizer, method and device thereof, and readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106779418A (en) * | 2016-12-20 | 2017-05-31 | 河海大学常州校区 | Water contamination accident Intelligent Decision-making Method based on neutral net and evidence theory |
| CN107741738A (en) * | 2017-10-20 | 2018-02-27 | 重庆华绿环保科技发展有限责任公司 | A kind of sewage disposal process monitoring intelligent early warning cloud system and sewage disposal monitoring and pre-alarming method |
| CN111414694A (en) * | 2020-03-19 | 2020-07-14 | 天津中德应用技术大学 | Sewage monitoring system based on FCM and BP algorithm and establishment method thereof |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107525907B (en) * | 2017-10-16 | 2019-12-31 | 中国环境科学研究院 | Multi-objective optimization method for underground water pollution monitoring network |
| CN109133351A (en) * | 2018-08-29 | 2019-01-04 | 北京工业大学 | Membrane bioreactor-MBR fouling membrane intelligent early-warning method |
-
2021
- 2021-01-28 CN CN202110117034.9A patent/CN113015120B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106779418A (en) * | 2016-12-20 | 2017-05-31 | 河海大学常州校区 | Water contamination accident Intelligent Decision-making Method based on neutral net and evidence theory |
| CN107741738A (en) * | 2017-10-20 | 2018-02-27 | 重庆华绿环保科技发展有限责任公司 | A kind of sewage disposal process monitoring intelligent early warning cloud system and sewage disposal monitoring and pre-alarming method |
| CN111414694A (en) * | 2020-03-19 | 2020-07-14 | 天津中德应用技术大学 | Sewage monitoring system based on FCM and BP algorithm and establishment method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113015120A (en) | 2021-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107831285B (en) | A kind of dystrophication monitoring system and method based on Internet of Things | |
| CN104408562B (en) | A kind of photovoltaic system generating efficiency comprehensive estimation method based on BP neural network | |
| CN108171259A (en) | A kind of wisdom tip water quality monitoring system and method based on NB-IoT | |
| CN111722540A (en) | Energy Internet digital twin simulation system and method | |
| CN109657003A (en) | A method of hardware data is directly accessed big data platform | |
| CN112772384B (en) | Agricultural water irrigation system and method based on convolutional neural network | |
| CN105956788A (en) | Dynamic management control method for cost of power transmission and transformation project | |
| CN114019831B (en) | Water resource monitoring internet of things platform | |
| CN113015120B (en) | Pollution control monitoring system and method based on neural network | |
| CN116545954A (en) | Communication gateway data transmission method and system based on Internet of things | |
| CN116308304A (en) | New energy intelligent operation and maintenance method and system based on meta learning concept drift detection | |
| CN101237357B (en) | Online failure detection method for industrial wireless sensor network | |
| CN117014471A (en) | Engineering thing networking safety monitoring system based on artificial intelligence | |
| CN110570628A (en) | Power transmission line pole tower geological disaster monitoring, early warning and analyzing system and using method | |
| CN116796633A (en) | Power grid monitoring model correction method based on digital twin technology | |
| CN116668473A (en) | Edge recognition method, system, equipment and medium for agricultural abnormal data | |
| CN116365713A (en) | Photovoltaic power station cluster monitoring method and system | |
| CN112526945B (en) | Full-process monitoring and early warning system with feedback and closed-loop control functions | |
| CN115640980A (en) | Power grid engineering cost dynamic management system based on target control | |
| CN114708718A (en) | Wind generating set temperature cluster control method, device, equipment and medium | |
| CN113741278A (en) | Vacuum station data acquisition, monitoring and analysis system based on cloud platform | |
| Qin | Data Monitoring Platform for Submarine Cable Tunnel Operation Based on Data Mining | |
| CN115434878B (en) | Wind generating set temperature cluster control method, device, equipment and medium | |
| CN216977986U (en) | Online corrosion monitoring and intelligent decision-making system for offshore wind power plant equipment | |
| CN117890553B (en) | Hydrologic water resource monitoring system |
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 |