CN116340427B - Method for environmental protection data early warning system - Google Patents
Method for environmental protection data early warning system Download PDFInfo
- Publication number
- CN116340427B CN116340427B CN202310453105.1A CN202310453105A CN116340427B CN 116340427 B CN116340427 B CN 116340427B CN 202310453105 A CN202310453105 A CN 202310453105A CN 116340427 B CN116340427 B CN 116340427B
- Authority
- CN
- China
- Prior art keywords
- data
- early warning
- environmental protection
- evaluation
- environment
- 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
- 230000007613 environmental effect Effects 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012544 monitoring process Methods 0.000 claims abstract description 45
- 238000001514 detection method Methods 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 9
- 230000003993 interaction Effects 0.000 claims abstract description 4
- 238000011156 evaluation Methods 0.000 claims description 47
- 238000013528 artificial neural network Methods 0.000 claims description 19
- 239000013598 vector Substances 0.000 claims description 18
- 125000004122 cyclic group Chemical group 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000005516 engineering process Methods 0.000 claims description 13
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 230000000306 recurrent effect Effects 0.000 claims description 10
- 230000004913 activation Effects 0.000 claims description 9
- 238000003062 neural network model Methods 0.000 claims description 6
- 230000002194 synthesizing effect Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 4
- 238000012854 evaluation process Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 238000004806 packaging method and process Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 239000002689 soil Substances 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000036541 health Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Classifications
-
- 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
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- 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
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/258—Data format conversion from or to a database
-
- 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
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- 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
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
Abstract
The invention discloses a method for an environmental protection data early warning system, which relates to the field of environmental protection treatment and comprises a front early warning system and a rear early warning system, wherein the front early warning system and the rear early warning system carry out data interaction through an internet interface, the front early warning system comprises an environmental protection data processing module, a primary early warning module and an environmental protection data uploading module, the environmental protection data processing module comprises environmental protection data classification and data format unification, the primary early warning module comprises a threshold monitoring system and an early warning device, and the environmental protection data uploading module comprises uploading information classification and primary early warning notification; the post-early warning system comprises a data monitoring system module, an environment-friendly data blockchain and an intelligent contract chain code module, wherein the data monitoring system module comprises adjacent detection node weighting monitoring, historical data weighting monitoring and data packet authentication uplink, and the intelligent contract chain code module comprises early warning mode selection.
Description
Technical Field
The invention relates to the field of environmental protection treatment, in particular to a method for an environmental protection data early warning system.
Background
Environmental protection treatment is a major research topic for maintaining human health and ecological system balance, and solves a plurality of environmental problems in human society production and life. However, the environmental system has the characteristics of high dimensionality, multiple variables, intricate relationships among factors and the like, and has critical significance in scientifically early warning the change of the future environmental conditions by digging valuable information from complex and diverse environmental protection data.
The early warning of environmental protection data at the present stage is usually carried out through data analysis and modeling, and environmental protection data such as the trend of environmental change, the emission amount of pollutants, the occurrence probability of natural disasters and the like are predicted through methods such as establishing a mathematical model, a machine learning model and the like. However, due to differences in environmental monitoring equipment, monitoring methods and the like, data quality and timeliness often have certain limitations. The environmental protection data acquisition and early warning work also face a plurality of challenges and difficulties, including the problems of accuracy of monitoring data, natural factor and human factor limitation, unsmooth data circulation and the like. Environmental protection treatment is a major research topic for maintaining human health and ecological system balance, and can solve a plurality of environmental problems in human society production and life. However, the environmental system has the characteristics of high dimensionality, multiple variables, intricate relationships among factors and the like, and has critical significance in scientifically early warning the change of the future environmental conditions by digging valuable information from complex and diverse environmental protection data.
In the process of data acquisition, timeliness, authenticity and validity of data are difficult to ensure, and data analysis and early warning model establishment outside data acquisition are also difficult. The environmental protection data early warning needs to be subjected to data analysis and modeling, a certain professional technology and tool support are needed, and different types of environmental protection data can need to use different analysis and modeling methods. Therefore, the difficulty of building a comprehensive environment-friendly data early warning system by the prior means is great.
Accordingly, there is a need to provide a method for an environmental data alert system that addresses the above-described issues.
Disclosure of Invention
The invention aims to provide a method for an environment-friendly data early warning system, which realizes comprehensive detection early warning of air, soil, moisture and various environment-friendly data types, can more comprehensively and three-dimensionally perform early warning work, and adopts a blockchain technology to greatly avoid human interference, thereby improving the robustness of the early warning system, ensuring the safety and reliability of data by a local server and a double verification mechanism stored on a chain, and enhancing the supervision effect by sharing the data on the chain.
In order to achieve the above purpose, the invention provides a method for an environmental protection data early warning system, the early warning system comprises a front early warning system and a rear early warning system, the front early warning system and the rear early warning system conduct data interaction through an internet interface, the front early warning system comprises an environmental protection data processing module, a primary early warning module and an environmental protection data uploading module, and the rear early warning system comprises a data monitoring system module, an environmental protection data block chain and an intelligent contract chain code module.
The early warning method comprises a front early warning method and a rear early warning method, wherein the rear early warning method comprises the following steps:
s901: performing data monitoring, performing weighting monitoring on adjacent detection nodes and historical data weighting monitoring, determining data and classification acquired by different nodes according to weight parameters, and meanwhile, performing data packaging and uplink on the data; in step S901, adjacent detection node weighting monitoring and historical data weighting monitoring respectively perform reliability evaluation of space angle and reliability evaluation of time angle on the environmental protection data packet, and the specific method of evaluation is as follows:
s911: the same type of environment-friendly data type obtained by detecting the nodes with similar time stamps is used for constructing an evaluation set：/>For evaluating collections, +.>，/>The same environmental protection data detected by other nodes in the same layer;
s912: determining a factor weight for each detection node data as an evaluation factorDetermining importance orders of factors in weighting monitoring of adjacent detection nodes and weighting monitoring of historical data, and establishing a weight set +.>The weight set satisfies->；
S913: determining an evaluation set of reliability evaluations of environmental data, in the formula />Is->Is (are) judged by the level result of the evaluation>,/>For the number of grades, the evaluation set V prescribes a grade range of the evaluation result;
s914: building a relation matrix of environment-friendly data credibility, and constructing a relation matrix from U to UCalculating a relation matrix R from U to V:
；
in the formula ,is the factor->With->Degree of (1)>，/>For->The individual elements are comprehensively evaluated to obtain a +.>Go->The relation matrix of the columns comprises all information obtained in the evaluation process of the factor set U by the evaluation set V;
s915: synthesizing a comprehensive reliability evaluation matrix B, and synthesizing a weight set W and R of each evaluated object to obtain a reliability comprehensive evaluation vectorThe calculation method is as follows:
；
；
wherein ,for the comprehensive evaluation result corresponding to each evaluation factor, ">"is a fuzzy operator;
s916: and analyzing the comprehensive evaluation vector, and selecting a final judgment result, wherein the expression is as follows:the unreliable data returns to re-detection, and the trusted data is authenticated and then is uplink;
s902: the encryption automation of the data is carried out by adopting a block chain technology, and the data early warning model selection is carried out by utilizing an intelligent contract chain; in step S902, the environmental protection data detection node directly uploads relevant information to the blockchain network through the unified interface to participate in the consensus process, and the intelligent contract chain adopts the cyclic neural network to make early warning prediction, and the cyclic neural network prediction method is as follows:representing the input layer of the recurrent neural network,hidden layer representing recurrent neural network, +.>An output layer representing a recurrent neural network;
s921: hiding output of layer at history timeAnd input of the current time ∈ ->Information coaction to obtain hidden layer input +.>As a memory state throughout the entire network model;
s922: transmitting from front to back according to the time sequence of hidden layers of the cyclic neural network model, obtaining an output layer result of the last layer, wherein hidden layer latent vectors are expressed as follows:
；
s923: hidden layer latent vectorVia an activation function->Then is the hidden layer->Memory of the sample at time t +.>The results were: />；
The output layer latent vector is expressed as:；
s924: output layer latent vectorVia an activation function->Followed by +.>，/>，； wherein ,/> and />Are all activation functions, U, V, WRespectively inputting, outputting and hiding layer circulating weights;
s925: decomposing the time sequence by using a cyclic neural network model; establishing connection between neurons of the same hidden layer of the cyclic neural network, obtaining environmental protection data prediction data, and performing early warning work according to the data and a set standard after the intelligent contract chain code obtains the prediction data;
s926: early warning triggering, wherein early warning signals are packed into data packets containing time and place and are uploaded to a block chain;
s903: early warning models for different contracts and different blockchain technologies are trained.
Preferably, the environmental protection data processing module comprises environmental protection data classification and data format unification, the primary early warning module comprises a threshold monitoring system and an early warning device, and the environmental protection data uploading module comprises uploading information classification and primary early warning notification; the data monitoring system module comprises adjacent detection node weighting monitoring, historical data weighting monitoring and data packet authentication uplink, the environment-friendly data blockchain comprises a plurality of blocks, and the intelligent contract chain code module comprises early warning mode selection, early warning model parameter determination, on-chain prediction deduction and prediction result uploading.
Preferably, the pre-warning method comprises the following steps:
s801: acquiring environment-friendly data type items, environment-friendly data standardized values, detection time stamps and detection location information parameters in the environment, and classifying the environment-friendly data;
s802: performing preliminary format unification on the acquired data;
s803: the unified data is input to the input end of the front early warning system, the building of a simulink circuit level model is completed on the edge computing equipment, the data is subjected to threshold screening, and the non-conforming data is screened and recorded;
s804: uploading the abnormal data and the abnormal sensing equipment detected by the early-stage primary early-warning module to a data server for remarking, and uploading the collected environmental protection data and the data packet of the early-stage primary early-warning result through an Internet interface.
Therefore, the method for the environmental protection data early warning system has the following beneficial effects;
(1) The invention realizes comprehensive detection and early warning of air, soil, moisture and various environmental protection data types, and performs early warning work more comprehensively and more three-dimensionally.
(2) The invention uses the block chain technology, can avoid human interference to a great extent, and improves the robustness of the early warning system.
(3) The invention ensures the safety and reliability of the data ensured by the local server and the double verification mechanism stored on the chain, and the sharing of the data on the chain also strengthens the supervision effect.
(4) The invention adopts the primary early warning module for completing the simulink circuit level model on the edge computing equipment, has the capability of timely processing abnormal data, occupies small data space, and realizes the lighter early warning design.
(5) The abnormal data and the abnormal sensing equipment detected by the primary early warning module are uploaded to the data server for remarking so as to be checked and analyzed by a subsequent engineer, and on the other hand, the normal data are uploaded to the server for regular storage, so that data support is provided for subsequent early warning.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
FIG. 1 is an overall block diagram of a method for an environmental protection data pre-warning system of the present invention;
FIG. 2 is a flow chart of a pre-warning method of a method for an environmental protection data warning system of the present invention;
FIG. 3 is a flowchart of an intelligent contract chain code module for a method for an environmental protection data pre-warning system of the present invention;
FIG. 4 is a diagram of a recurrent neural network in a post-warning method of a method for an environmental protection data warning system of the present invention;
FIG. 5 is a block diagram of a pre-warning system of a method for an environmental data warning system of the present invention;
FIG. 6 is a diagram of a post-warning system architecture for a method of an environmental protection data warning system of the present invention;
Detailed Description
The technical scheme of the invention is further described below through the attached drawings and the embodiments.
Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
Examples
In this embodiment, as shown in fig. 1-6, a method for an environmental protection data early warning system, where the early warning system includes a front early warning system and a rear early warning system, the front early warning system and the rear early warning system perform data interaction through an internet interface, the front early warning system includes an environmental protection data processing module, a primary early warning module and an environmental protection data uploading module, the environmental protection data processing module includes environmental protection data classification and data format unification, the primary early warning module includes a threshold monitoring system and an early warning device, and the environmental protection data uploading module includes uploading information classification and primary early warning notification; the post-early warning system comprises a data monitoring system module, an environment-friendly data blockchain and an intelligent contract chain code module, wherein the data monitoring system module comprises adjacent detection node weighting monitoring, historical data weighting monitoring and data packet authentication uplink, the environment-friendly data blockchain comprises a plurality of blocks, and the intelligent contract chain code module comprises early warning mode selection, early warning model parameter determination, on-chain prediction deduction and prediction result uploading.
The early warning method comprises a front early warning method and a rear early warning method.
The pre-warning method comprises the following steps:
s801: and acquiring environment-friendly data type items, environment-friendly data standardized values, detection time stamps and detection location information parameters in the environment, and classifying the environment-friendly data.
S802: and carrying out preliminary format unification on the acquired data.
S803: the unified data are input to the input end of the front early warning system, the building of the simulink circuit level model is completed on the edge computing equipment, the data are subjected to threshold screening, and the data which do not accord with the threshold screening are screened and recorded.
S804: uploading the abnormal data and the abnormal sensing equipment detected by the early-stage primary early-warning module to a data server for remarking, and uploading the collected environmental protection data and the data packet of the early-stage primary early-warning result through an Internet interface.
The post-warning method comprises the following steps:
s901: and performing data monitoring, performing weighting monitoring on adjacent detection nodes and historical data weighting monitoring, determining data and classification acquired by different nodes according to weight parameters, and meanwhile, performing data packaging and uplink on the data. In step S901, adjacent detection node weighting monitoring and historical data weighting monitoring respectively perform reliability evaluation of space angle and reliability evaluation of time angle on the environmental protection data packet, and the specific method of evaluation is as follows:
s911: the same environmental protection data type detected by other detection nodes with similar time stamps is used for constructing an evaluation set：/>For evaluating collections, +.>，/>The same environmental protection data detected by other detection nodes in the same layer are obtained.
S912: determining a factor weight for each detection node data as an evaluation factorDetermining importance orders of factors in weighting monitoring of adjacent detection nodes and weighting monitoring of historical data, and establishing a weight set +.>The weight set satisfies->。
S913: determining an evaluation set of reliability evaluations of environmental data, in the formula />Is->Is (are) judged by the level result of the evaluation>,/>For the number of ranks, the comment set V specifies the rank range of the evaluation result.
S914: building a relation matrix of environment-friendly data credibility, and constructing a relation matrix from U to UCalculating a relation matrix R from U to V:
；
in the formula ,is the factor->With->Degree of (1)>，/>For->The individual elements are comprehensively evaluated to obtain a +.>Go->The relation matrix of the columns comprises all information obtained in the evaluation process of the factor set U by the evaluation set V.
S915: synthesizing a comprehensive reliability evaluation matrix B, and synthesizing a weight set W and R of each evaluated object to obtain a reliability comprehensive evaluation vectorThe calculation method is as follows:
；
；
wherein ,for the comprehensive evaluation result corresponding to each evaluation factor, ">"is a blurring operator. S916: and analyzing the comprehensive evaluation vector, and selecting a final judgment result, wherein the expression is as follows: />The unreliable data is returned to be re-detected, and the trusted data is authenticated and then is uplink.
S902: and (3) carrying out confidentiality and automation on data by adopting a block chain technology, and carrying out data early warning model selection by utilizing an intelligent contract chain. In step S902, the environmental protection data detection node directly uploads relevant information to the blockchain network through the unified interface to participate in the consensus process, and the intelligent contract chain adopts the cyclic neural network to make early warning prediction, and the cyclic neural network prediction method is as follows:representing the input layer of the recurrent neural network,hidden layer representing recurrent neural network, +.>Representing the output layer of the recurrent neural network.
S921: hiding output of layer at history timeAnd input of the current time ∈ ->Information coaction to obtain hidden layer input +.>The memory state is used as a memory state to penetrate through the whole network model.
S922: transmitting from front to back according to the time sequence of hidden layers of the cyclic neural network model, obtaining an output layer result of the last layer, wherein hidden layer latent vectors are expressed as follows:
。
s923: hidden layer latent vectorVia an activation function->Then is the hidden layer->Memory of the sample at time t +.>The results were: />；
The output layer latent vector is expressed as:。
s924: output layer latent vectorVia an activation function->Followed by +.>，/>，； wherein ,/> and />Are activation functions, U, V, W are weights for the input, output and hidden layer loops, respectively.
S925: decomposing the time sequence by using a cyclic neural network model; and establishing connection between neurons of the same hidden layer of the cyclic neural network, obtaining environmental protection data prediction data, and performing early warning work according to the data and a set standard after the intelligent contract chain code obtains the prediction data.
S926: and (5) early warning triggering, wherein early warning signals are packaged into data packets containing time and place and are uploaded to the blockchain.
S903: early warning models for different contracts and different blockchain technologies are trained.
Working principle: and constructing a set of environment-friendly data early warning system comprising front early warning automatic control and rear early warning block chain environment-friendly data from the measured environment-friendly data, and providing method and system support for carrying out environment-friendly data early warning work on the basis of certain data. The preliminary screening of the instant data is realized through the pre-early warning, abnormal data is filtered or screened and early warning is carried out, so that problems can be found after a large amount of data is processed, and the real-time performance is effectively provided. After effective data is obtained from the early warning, the effective data is stored, the privacy and the safety of environment-friendly data are considered, an improved blockchain technology is adopted, a multi-level segmentation early warning mode is completed through the technology, so that the safety is improved, a new method is provided for data early warning, the blockchain technology and edge calculation are effectively fused, real-time collection, comparison and monitoring of multi-point position edge calculation data can be achieved, and an improved blockchain early warning algorithm is designed for carrying out current and future all-round early warning on the existing data.
Therefore, the method for the environmental protection data early warning system provided by the invention is used for realizing comprehensive detection early warning of air, soil, moisture and various environmental protection data types, can perform early warning work more comprehensively and stereoscopically, and greatly avoids human interference by using a blockchain technology, improves the robustness of the early warning system, ensures the safety and reliability of data by a local server and a double verification mechanism stored on a chain, and enhances the supervision effect by sharing the data on the chain.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention and not for limiting it, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that: the technical scheme of the invention can be modified or replaced by the same, and the modified technical scheme cannot deviate from the spirit and scope of the technical scheme of the invention.
Claims (2)
1. A method for an environmental protection data pre-warning system, characterized by: the early warning system comprises a front early warning system and a rear early warning system, wherein the front early warning system and the rear early warning system carry out data interaction through an internet interface, the front early warning system comprises an environment-friendly data processing module, a primary early warning module and an environment-friendly data uploading module, and the rear early warning system comprises a data monitoring system module, an environment-friendly data blockchain and an intelligent contract chain code module;
the environment-friendly data processing module comprises environment-friendly data classification and data format unification, the primary early warning module comprises a threshold monitoring system and an early warning device, and the environment-friendly data uploading module comprises uploading information classification and primary early warning notification; the data monitoring system module comprises adjacent detection node weighting monitoring, historical data weighting monitoring and data packet authentication uplink, the environment-friendly data blockchain comprises a plurality of blocks, and the intelligent contract chain code module comprises early warning mode selection, early warning model parameter determination, on-chain prediction deduction and prediction result uploading;
the early warning method comprises a front early warning method and a rear early warning method;
the post-warning method comprises the following steps:
s901: performing data monitoring, performing weighting monitoring on adjacent detection nodes and historical data weighting monitoring, evaluating the credibility of the data of the node, and meanwhile, performing data packaging and uplink on the data; in step S901, adjacent detection node weighting monitoring and historical data weighting monitoring respectively perform reliability evaluation of space angle and reliability evaluation of time angle on the environmental protection data packet, and the specific method of evaluation is as follows:
s911: with similar time stampsThe same type of environment-friendly data type is detected by the detection node of (1) to construct an evaluation set：/>For evaluating collections, +.>，/>The same environmental protection data detected by other detection nodes in the same layer;
s912: determining a factor weight for each detection node data as an evaluation factorDetermining importance orders of factors in weighting monitoring of adjacent detection nodes and weighting monitoring of historical data, and establishing a weight set +.>The weight set satisfies；
S913: determining an evaluation set of reliability evaluations of environmental data, in the formula />Is->Is (are) judged by the level result of the evaluation>,/>For the number of grades, the evaluation set V prescribes a grade range of the evaluation result;
s914: building a relation matrix of environment-friendly data credibility, and constructing a relation matrix from U to UCalculating a relation matrix R from U to V:
；
in the formula ,is the factor->With->Degree of (1)>，/>For->The individual elements are comprehensively evaluated to obtain a +.>Go->The relation matrix of the columns comprises all information obtained in the evaluation process of the factor set U by the evaluation set V;
s915: synthesizing a comprehensive reliability evaluation matrix B, and synthesizing a weight set W and R of each evaluated object to obtain a reliability comprehensive evaluation vectorThe calculation method is as follows:
；
；
wherein ,for the comprehensive evaluation result corresponding to each evaluation factor, ">"is a fuzzy operator;
s916: and analyzing the comprehensive evaluation vector, and selecting a final judgment result, wherein the expression is as follows:the unreliable data returns to re-detection, and the trusted data is authenticated and then is uplink;
s902: the encryption automation of the data is carried out by adopting a block chain technology, and the data early warning model selection is carried out by utilizing an intelligent contract chain; in step S902, the environmental protection data detection node directly uploads relevant information to the blockchain network through the unified interface to participate in the consensus process, and the intelligent contract chain adopts the cyclic neural network to make early warning prediction, and the cyclic neural network prediction method is as follows:input layer representing a recurrent neural network, +.>Hidden layer representing recurrent neural network, +.>An output layer representing a recurrent neural network;
s921: hiding output of layer at history timeAnd input of the current time ∈ ->Information coaction to obtain hidden layer input +.>As a memory state throughout the entire network model;
s922: transmitting from front to back according to the time sequence of hidden layers of the cyclic neural network model, obtaining an output layer result of the last layer, wherein hidden layer latent vectors are expressed as follows:
；
s923: hidden layer latent vectorVia an activation function->Then is the hidden layer->Memory of the sample at time t +.>The results were: />；
The output layer latent vector is expressed as:；
s924: output layer latent vectorVia an activation function->Followed by +.>，/>，； wherein ,/> and />Are activation functions, U, V, W are weights of input, output and hidden layer circulation respectively;
s925: decomposing the time sequence by using a cyclic neural network model; establishing connection between neurons of the same hidden layer of the cyclic neural network, obtaining environmental protection data prediction data, and performing early warning work according to the data and a set standard after the intelligent contract chain code obtains the prediction data;
s926: early warning triggering, wherein early warning signals are packed into data packets containing time and place and are uploaded to a block chain;
s903: early warning models for different contracts and different blockchain technologies are trained.
2. The method for an environmental protection data alert system of claim 1, wherein: the pre-warning method comprises the following steps:
s801: acquiring environment-friendly data type items, environment-friendly data standardized values, detection time stamps and detection location information parameters in the environment, and classifying the environment-friendly data;
s802: performing preliminary format unification on the acquired data;
s803: the unified data is input to the input end of the front early warning system, the building of a simulink circuit level model is completed on the edge computing equipment, the data is subjected to threshold screening, and the non-conforming data is screened and recorded;
s804: uploading the abnormal data and the abnormal sensing equipment detected by the early-stage primary early-warning module to a data server for remarking, and uploading the collected environmental protection data and the data packet of the early-stage primary early-warning result through an Internet interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310453105.1A CN116340427B (en) | 2023-04-25 | 2023-04-25 | Method for environmental protection data early warning system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310453105.1A CN116340427B (en) | 2023-04-25 | 2023-04-25 | Method for environmental protection data early warning system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116340427A CN116340427A (en) | 2023-06-27 |
| CN116340427B true CN116340427B (en) | 2023-10-13 |
Family
ID=86891356
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310453105.1A Active CN116340427B (en) | 2023-04-25 | 2023-04-25 | Method for environmental protection data early warning system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116340427B (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400310A (en) * | 2013-08-08 | 2013-11-20 | 华北电力大学（保定） | Method for evaluating power distribution network electrical equipment state based on historical data trend prediction |
| CN107274297A (en) * | 2017-06-14 | 2017-10-20 | 贵州中北斗科技有限公司 | A kind of soil crop-planting suitability assessment method |
| CN109446812A (en) * | 2018-05-09 | 2019-03-08 | 国家计算机网络与信息安全管理中心 | A kind of embedded system firmware safety analytical method and system |
| CN109685366A (en) * | 2018-12-24 | 2019-04-26 | 中国人民解放军32181部队 | Equipment health state evaluation method based on mutation data |
| KR20200002337A (en) * | 2018-06-29 | 2020-01-08 | 한전케이디엔주식회사 | Fault diagnosis and automatic recovery system based on data sharing |
| CN110929915A (en) * | 2019-10-14 | 2020-03-27 | 武汉烽火众智数字技术有限责任公司 | Intelligent early warning model establishing method and device for alarm situation occurrence area and storage medium |
| CN112070379A (en) * | 2020-08-28 | 2020-12-11 | 上海电机学院 | Little electric wire netting risk monitoring early warning system |
| CN113034857A (en) * | 2021-03-15 | 2021-06-25 | 天津科技大学 | Urban natural disaster monitoring emergency management scheduling platform based on block chain |
| CN113344470A (en) * | 2021-08-02 | 2021-09-03 | 山东炎黄工业设计有限公司 | Intelligent power supply system management method based on block chain |
| CN113434902A (en) * | 2021-06-30 | 2021-09-24 | 华中科技大学 | Construction safety monitoring management system and method based on block chain |
| CN113674509A (en) * | 2021-10-21 | 2021-11-19 | 北京博华信智科技股份有限公司 | Edge node disaster monitoring and early warning system and method based on block chain |
| CN113987070A (en) * | 2021-10-09 | 2022-01-28 | 重庆电子工程职业学院 | Geological disaster risk identification and early warning system based on block chain |
| CN114519923A (en) * | 2021-11-24 | 2022-05-20 | 新疆天池能源有限责任公司 | Intelligent diagnosis and early warning method and system for power plant |
| CN114548749A (en) * | 2022-02-19 | 2022-05-27 | 河海大学 | Soil heavy metal pollution early warning system |
| CN115119280A (en) * | 2022-05-20 | 2022-09-27 | 中国人民解放军空军工程大学 | FANETs safe routing method based on trust mechanism |
| CN115168490A (en) * | 2022-07-01 | 2022-10-11 | 中山大学 | Agricultural non-point source pollution source tracing and early warning system based on block chain |
-
2023
- 2023-04-25 CN CN202310453105.1A patent/CN116340427B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400310A (en) * | 2013-08-08 | 2013-11-20 | 华北电力大学（保定） | Method for evaluating power distribution network electrical equipment state based on historical data trend prediction |
| CN107274297A (en) * | 2017-06-14 | 2017-10-20 | 贵州中北斗科技有限公司 | A kind of soil crop-planting suitability assessment method |
| CN109446812A (en) * | 2018-05-09 | 2019-03-08 | 国家计算机网络与信息安全管理中心 | A kind of embedded system firmware safety analytical method and system |
| KR20200002337A (en) * | 2018-06-29 | 2020-01-08 | 한전케이디엔주식회사 | Fault diagnosis and automatic recovery system based on data sharing |
| CN109685366A (en) * | 2018-12-24 | 2019-04-26 | 中国人民解放军32181部队 | Equipment health state evaluation method based on mutation data |
| CN110929915A (en) * | 2019-10-14 | 2020-03-27 | 武汉烽火众智数字技术有限责任公司 | Intelligent early warning model establishing method and device for alarm situation occurrence area and storage medium |
| CN112070379A (en) * | 2020-08-28 | 2020-12-11 | 上海电机学院 | Little electric wire netting risk monitoring early warning system |
| CN113034857A (en) * | 2021-03-15 | 2021-06-25 | 天津科技大学 | Urban natural disaster monitoring emergency management scheduling platform based on block chain |
| CN113434902A (en) * | 2021-06-30 | 2021-09-24 | 华中科技大学 | Construction safety monitoring management system and method based on block chain |
| CN113344470A (en) * | 2021-08-02 | 2021-09-03 | 山东炎黄工业设计有限公司 | Intelligent power supply system management method based on block chain |
| CN113987070A (en) * | 2021-10-09 | 2022-01-28 | 重庆电子工程职业学院 | Geological disaster risk identification and early warning system based on block chain |
| CN113674509A (en) * | 2021-10-21 | 2021-11-19 | 北京博华信智科技股份有限公司 | Edge node disaster monitoring and early warning system and method based on block chain |
| CN114519923A (en) * | 2021-11-24 | 2022-05-20 | 新疆天池能源有限责任公司 | Intelligent diagnosis and early warning method and system for power plant |
| CN114548749A (en) * | 2022-02-19 | 2022-05-27 | 河海大学 | Soil heavy metal pollution early warning system |
| CN115119280A (en) * | 2022-05-20 | 2022-09-27 | 中国人民解放军空军工程大学 | FANETs safe routing method based on trust mechanism |
| CN115168490A (en) * | 2022-07-01 | 2022-10-11 | 中山大学 | Agricultural non-point source pollution source tracing and early warning system based on block chain |
Non-Patent Citations (2)
| Title |
|---|
| 基于区块链和5G物联网的溯源及异常数据预警系统;艾学瑛;;电子设计工程(第10期);全文 * |
| 基于区块链的传染病监测与预警技术;欧阳丽炜;袁勇;郑心湖;张俊;王飞跃;;智能科学与技术学报(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116340427A (en) | 2023-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Weerakody et al. | A review of irregular time series data handling with gated recurrent neural networks | |
| KR102101974B1 (en) | Anomaly detection | |
| TWI776310B (en) | Method for defining distance metrics and method for training a recurrent artificial neural network | |
| CN112987675B (en) | Method, device, computer equipment and medium for anomaly detection | |
| CN112637132B (en) | Network anomaly detection method and device, electronic equipment and storage medium | |
| TWI776309B (en) | Recurrent artificial neural network, method implemented by a recurrent artificial neural network system, and neural network device | |
| Wickramasinghe et al. | Explainable unsupervised machine learning for cyber-physical systems | |
| JP2021504792A (en) | Systems for shallow circuits as quantum classifiers, computer implementation methods and computer programs | |
| Du et al. | NIDS-CNNLSTM: Network intrusion detection classification model based on deep learning | |
| VS | Multi Label Deep Learning classification approach for False Data Injection Attacks in Smart Grid. | |
| CN113343587A (en) | Flow abnormity detection method for electric power industrial control network | |
| CN114826947B (en) | Flow matrix recovery prediction method and system based on automatic encoder | |
| CN114448657B (en) | Distribution communication network security situation awareness and abnormal intrusion detection method | |
| Suwadi et al. | An optimized approach for predicting water quality features based on machine learning | |
| CN116340427B (en) | Method for environmental protection data early warning system | |
| US20060093203A1 (en) | Attribute threshold evaluation scheme | |
| CN110874601B (en) | Method for identifying running state of equipment, state identification model training method and device | |
| CN112529025A (en) | Data processing method and device | |
| CN116451081A (en) | Data drift detection method, device, terminal and storage medium | |
| Abdullahi et al. | Deep Learning Model for Cybersecurity Attack Detection in Cyber-Physical Systems | |
| KR102320707B1 (en) | Method for classifiying facility fault of facility monitoring system | |
| CN112433952B (en) | Method, system, device and medium for testing fairness of deep neural network model | |
| Bütepage et al. | Gaussian process encoders: Vaes with reliable latent-space uncertainty | |
| KR20220120427A (en) | Method and apparatus for tracking object | |
| Vijay | Detection of plant diseases in tomato leaves: with focus on providing explainability and evaluating user trust |
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 |