CN114049134A - Pollution source online monitoring data counterfeiting identification method - Google Patents
Pollution source online monitoring data counterfeiting identification method Download PDFInfo
- Publication number
- CN114049134A CN114049134A CN202111318179.1A CN202111318179A CN114049134A CN 114049134 A CN114049134 A CN 114049134A CN 202111318179 A CN202111318179 A CN 202111318179A CN 114049134 A CN114049134 A CN 114049134A
- Authority
- CN
- China
- Prior art keywords
- pollution source
- online monitoring
- monitoring data
- score
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 110
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000011156 evaluation Methods 0.000 claims abstract description 90
- 238000013528 artificial neural network Methods 0.000 claims abstract description 27
- 239000010865 sewage Substances 0.000 claims abstract description 19
- 238000001514 detection method Methods 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims description 34
- 238000007689 inspection Methods 0.000 claims description 15
- 239000000779 smoke Substances 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 9
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 7
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 claims description 7
- 229910052698 phosphorus Inorganic materials 0.000 claims description 7
- 239000011574 phosphorus Substances 0.000 claims description 7
- 238000013459 approach Methods 0.000 claims description 6
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 6
- 239000001301 oxygen Substances 0.000 claims description 6
- 229910052760 oxygen Inorganic materials 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 6
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 239000003546 flue gas Substances 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 239000002912 waste gas Substances 0.000 abstract description 4
- 239000002351 wastewater Substances 0.000 abstract description 4
- 230000008901 benefit Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 16
- 230000007613 environmental effect Effects 0.000 description 13
- 210000002569 neuron Anatomy 0.000 description 13
- 238000004364 calculation method Methods 0.000 description 6
- 230000005284 excitation Effects 0.000 description 5
- 239000000428 dust Substances 0.000 description 4
- 238000013461 design Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B19/00—Alarms responsive to two or more different undesired or abnormal conditions, e.g. burglary and fire, abnormal temperature and abnormal rate of flow
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Educational Administration (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for identifying false pollution source online monitoring data, which comprises the following steps: collecting historical online monitoring data of a pollution source, and constructing a BP neural network prediction model based on a pollution source score evaluation index and a pollution source score; collecting data of various score evaluation indexes of a pollution source sewage outlet in real time; calculating by combining preset weights of various score evaluation indexes to obtain the actual pollution source score at the current moment; inputting various collected score evaluation index data into a BP neural network prediction model to obtain a predicted pollution source score at the current moment; and comparing and analyzing the actual pollution source value and the predicted pollution source value to identify whether the online monitoring data is counterfeit or not. Has the advantages that: the real-time identification and judgment of whether the pollution source online detection data are counterfeit or not can be realized, so that the online monitoring service can be further perfected and optimized, and the supervision of the waste water and waste gas emission of enterprises can be effectively realized.
Description
Technical Field
The invention relates to the technical field of pollution source online monitoring, in particular to a method for identifying false pollution source online monitoring data.
Background
In recent years, with the higher and higher requirements of the country on the environmental quality, the desire of common people for the ecological environment with good twinkling of stars and white clouds is more and more urgent, various law enforcement forces are increased by environmental protection departments at all levels, the quality of environmental data is further improved and grasped by the technical means, and the emission condition of each enterprise is faithfully reflected by the environmental online monitoring data. The pollution source online monitoring is an important informatization means for ecological environment supervision, and various monitoring factors (such as wastewater and waste gas monitoring factors including pH, ammonia nitrogen, COD, total phosphorus, smoke dust, smoke temperature and the like) sensors are installed and deployed at a pollution source discharge port, monitoring data are collected, converged and integrated in a unified mode through lower software, and are synchronously pushed to various levels of environment-friendly online monitoring platforms in real time, and the purpose of managing and controlling the pollution source from the source is achieved by combining with card swiping pollution discharge.
However, in order to pursue economic benefits, some pollution emission enterprises currently perform counterfeiting on online monitoring data in many ways to avoid real-time supervision of an online pollution source monitoring network which is built by an environmental protection department, and counterfeiting methods are diversified, which brings great challenges to environment law enforcement work of the environmental protection department. In the case of online data counterfeiting published by the environmental protection department in the past, the pollution sources account for more than 70% of the total amount by modifying software means such as automatic monitoring equipment parameters of the pollution sources, and the real acquisition of the enterprise emission condition is seriously influenced. Therefore, the invention provides a method for identifying false pollution source online monitoring data.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides a method for identifying false pollution source online monitoring data, which aims to overcome the technical problems in the prior related art.
Therefore, the invention adopts the following specific technical scheme:
a method for identifying the counterfeiting of online monitoring data of a pollution source comprises the following steps:
s1, collecting historical online monitoring data of the pollution source, and constructing a BP neural network prediction model based on a pollution source score evaluation index and a pollution source score;
s2, collecting data of various score evaluation indexes of a pollution source sewage outlet in real time by using a preset monitoring sensor;
s3, calculating by utilizing the collected various score evaluation index data and combining preset weights of various score evaluation indexes to obtain the actual pollution source score at the current moment;
s4, inputting the collected various score evaluation index data into a BP neural network prediction model to obtain the predicted pollution source score at the current moment;
and S5, comparing and analyzing the actual pollution source value and the predicted pollution source value, and identifying whether the online monitoring data is counterfeit or not by using the comparison and analysis result.
Further, the step of collecting historical online monitoring data of the pollution sources in S1, and constructing a BP neural network prediction model based on the pollution source score evaluation index and the pollution source score includes the following steps:
s11, collecting historical online monitoring data of the pollution source, and grouping the obtained historical online monitoring data according to a time sequence;
s12, constructing a pollution source score evaluation index system based on the online monitoring data by using the acquired historical online monitoring data;
s13, giving different preset weights to different score evaluation indexes, and obtaining the pollution source score of each group of historical online monitoring data by utilizing the weighted summation of each evaluation index;
s14, constructing a BP neural network prediction model based on the pollution source score evaluation index and the pollution source score.
Further, the grouping processing of the acquired historical online monitoring data in the S11 according to the time sequence includes the following steps:
and sequencing the acquired historical online monitoring data according to a time sequence to obtain a plurality of groups of historical online monitoring data, and clearing the obviously abnormal data in each group of sequenced historical online monitoring data.
Further, the score evaluation indexes in S12 include pH, ammonia nitrogen content, chemical oxygen demand, total phosphorus content, smoke content, and flue gas temperature.
Further, the step of assigning different preset weights to different score evaluation indexes in S13, and obtaining the score of each group of historical online monitoring data by using the weighted sum of the evaluation indexes further includes the following steps:
and constructing a relation table corresponding to the pollution source value and the value evaluation index based on the value evaluation index and the pollution source value in each group of historical online monitoring data.
Further, the step of constructing the BP neural network prediction model based on the pollution source score evaluation index and the pollution source score in S14 includes the following steps:
s141, dividing a plurality of groups of historical online monitoring data with pollution source scores into a training set and a testing set;
and S142, constructing a BP neural network prediction model based on the pollution source score evaluation index and the pollution source score, and respectively training and testing the model by using the training set and the testing set in the S141.
Further, the training of the model in S142 further includes the following steps:
for the condition of insufficient training, the training effect is achieved by increasing nodes in the network or increasing the training period of the network;
for the over-fitting condition, the training period is reduced or controlled, and the training on the network is stopped before the inflection point appears in the data, so that the training effect is achieved.
Further, the step of collecting data of various score evaluation indexes of the pollution source sewage draining exit in real time by using a preset monitoring sensor in the step S2 further includes the steps of:
acquiring video data of a sewage draining exit in real time by using a preset video acquisition device, and judging whether a person approaches the sewage draining exit;
acquiring video data of a station house in real time by using a preset video acquisition device, and judging whether an illegal person intrudes;
when detecting that someone approaches the sewage outlet or illegal personnel intrude the station, the voice alarm is carried out, and the site inspection personnel is informed to carry out site inspection in time.
Further, the calculation formula of the actual pollution source score in S3 is as follows:
y＝a1x1+a2x2+a3x3+a4x4+...+anxn；
wherein x is1、x2、x3、x4…xnRepresenting different score evaluation indices, a1、a2、a3、a4…anRepresents the weight of each evaluation index, and a1+a2+a3+a4+…+an＝1。
Further, the step of comparing and analyzing the actual pollution source score and the predicted pollution source score in S5, and identifying whether the online monitoring data is counterfeit or not by using the comparison and analysis result includes the following steps:
s51, respectively obtaining the actual pollution source value and the predicted pollution source value, judging whether the actual pollution source value and the predicted pollution source value are the same, if the actual pollution source value and the predicted pollution source value are the same, executing S52, and if the actual pollution source value and the predicted pollution source value are different, sending out early warning and informing field inspectors to carry out field inspection;
s52, acquiring various types of value evaluation index data of the pollution source sewage outlet collected in real time, and verifying the various types of value evaluation index data collected in real time by using a relation table corresponding to the pollution source values and the value evaluation indexes;
s53, judging whether the various score evaluation index data collected in real time are consistent with data in a relation table corresponding to the pollution source score and the score evaluation index, if so, judging that the online monitoring data are not fake, and if not, executing S54;
s54, judging whether various score evaluation index data collected in real time are larger than a preset threshold value or smaller than the detection limit of a preset monitoring sensor, if so, sending out an early warning and informing field inspectors to carry out field inspection, and if not, executing S55;
s55, respectively carrying out variance processing on various score evaluation index data collected in a preset time period and judging whether the variance is zero, if so, sending out an early warning and informing field inspectors to carry out field inspection, and if not, judging that the online monitoring data is not fake.
The invention has the beneficial effects that: the model can output the corresponding predicted pollution source value according to the value evaluation index parameter acquired in real time by utilizing the historical online monitoring data, and the predicted pollution source value is compared and analyzed with the actual pollution source value obtained by actual calculation, so that the real-time identification and judgment on whether the pollution source online detection data is counterfeit can be realized, the online monitoring service can be further perfected and optimized, the waste water and waste gas emission of enterprises can be effectively monitored, the cheating prevention early warning and decision auxiliary analysis on the online monitoring data of the environmental protection information can be realized, the powerful monitoring of online monitoring by an environmental protection department can be effectively improved, and the intelligent environmental protection can be realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for identifying forgery of online monitoring data of a pollution source according to an embodiment of the invention.
Detailed Description
For further explanation of the various embodiments, the drawings which form a part of the disclosure and which are incorporated in and constitute a part of this specification, illustrate embodiments and, together with the description, serve to explain the principles of operation of the embodiments, and to enable others of ordinary skill in the art to understand the various embodiments and advantages of the invention, and, by reference to these figures, reference is made to the accompanying drawings, which are not to scale and wherein like reference numerals generally refer to like elements.
According to the embodiment of the invention, a method for identifying false pollution source online monitoring data is provided.
Referring to the drawings and the detailed description, the invention will be further explained, as shown in fig. 1, according to an embodiment of the invention, a method for identifying the counterfeit of online monitoring data of a pollution source includes the following steps:
s1, collecting historical online monitoring data of the pollution source, and constructing a BP neural network prediction model based on a pollution source score evaluation index and a pollution source score;
the step of collecting historical online monitoring data of the pollution sources in the step of S1, and constructing a BP neural network prediction model based on the pollution source score evaluation indexes and the pollution source scores comprises the following steps:
s11, collecting historical online monitoring data of the pollution source, and grouping the obtained historical online monitoring data according to a time sequence;
specifically, each group of historical online monitoring data comprises data of evaluation indexes of the grading values of pH, ammonia nitrogen content, chemical oxygen demand, total phosphorus content, smoke dust content, smoke temperature and the like;
the step of grouping the acquired historical online monitoring data in the time sequence in S11 includes the following steps:
and sequencing the acquired historical online monitoring data according to a time sequence to obtain a plurality of groups of historical online monitoring data, and clearing the obviously abnormal data in each group of sequenced historical online monitoring data.
S12, constructing a pollution source score evaluation index system based on the online monitoring data by using the acquired historical online monitoring data;
specifically, the score evaluation indexes in S12 include pH, ammonia nitrogen content, chemical oxygen demand, total phosphorus content, smoke content, flue gas temperature, and the like.
S13, giving different preset weights to different score evaluation indexes, and obtaining the pollution source score of each group of historical online monitoring data by utilizing the weighted summation of each evaluation index;
specifically, the preset weight is trained through a 5-layer fully-connected neural network, and the variable difference is obtained by rounding one by one.
In addition, the step of giving different preset weights to different score evaluation indexes in S13, and obtaining the score of each group of historical online monitoring data by using the weighted sum of the evaluation indexes further includes the following steps:
and constructing a relation table corresponding to the pollution source value and the value evaluation index based on the value evaluation index and the pollution source value in each group of historical online monitoring data.
S14, constructing a BP neural network prediction model based on the pollution source score evaluation index and the pollution source score.
Specifically, the step of constructing the BP neural network prediction model based on the pollution source score evaluation index and the pollution source score in S14 includes the following steps:
s141, dividing a plurality of groups of historical online monitoring data with pollution source scores into a training set and a testing set;
and S142, constructing a BP neural network prediction model based on the pollution source score evaluation index and the pollution source score, and respectively training and testing the model by using the training set and the testing set in the S141.
Among them, the BP Network (Back-ProPagation Network) is also called as a Back ProPagation neural Network,through the training of sample data, the network weight and the threshold are continuously corrected to enable the error function to descend along the direction of negative gradient, and the expected output is approached. The neural network model is widely applied and is mainly used for function approximation, model identification and classification, data compression, time series prediction and the like. The BP network consists of an input layer, a hidden layer and an output layer, the hidden layer can have one layer or a plurality of layers, the network selects an S-shaped transfer function,
by back propagation error function:
wherein, TiTo a desired output, OiFor the calculation output of the network, the weight value and the threshold value of the network are continuously adjusted to make the error function E extremely small.
Specifically, the BP neural network prediction model in this embodiment is designed as follows:
design of input and output layers: the model takes various influence parameters (including data of score evaluation indexes such as pH, ammonia nitrogen content, chemical oxygen demand, total phosphorus content, smoke dust content and flue gas temperature) of each group of data as input, and takes the pollution source score of each group of historical online monitoring data as output.
Hidden layer design: research shows that a neural network with a hidden layer can approximate a nonlinear function with any precision as long as hidden nodes are enough. Therefore, in this embodiment, a three-layer multi-input single-output BP network with a hidden layer is used to build a prediction model. In the network design process, the determination of the number of hidden layer neurons is very important. The number of hidden layer neurons is too large, so that the network calculation amount is increased, and the overfitting problem is easy to generate; if the number of the neurons is too small, the network performance is affected and the expected effect cannot be achieved. The number of hidden layer neurons in the network has a direct link to the complexity of the real problem, the number of neurons in the input and output layers, and the setting of the expected error. At present, there is no clear formula for determining the number of neurons in the hidden layer, and only some empirical formulas are used, and the final determination of the number of neurons still needs to be determined according to experience and multiple experiments. In this embodiment, the following empirical formula is referred to for the problem of selecting the number of hidden layer neurons:
wherein n is the number of neurons in the input layer, m is the number of neurons in the output layer, and a is a constant between [1 and 10 ].
Selection of an excitation function: BP neural networks typically employ Sigmoid differentiable functions and linear functions as the excitation function of the network. This example selects the S-type tangent function tansig as the excitation function for hidden layer neurons. And because the output of the network is normalized to the range of [ -1,1], the prediction model selects the S-shaped logarithmic function tansig as the excitation function of the neuron of the output layer.
And (3) realizing the model: the prediction selects a neural network tool kit in MATLAB to train the network, and the concrete implementation steps of the prediction model are as follows:
training sample data is input into a network after being normalized, excitation functions of a hidden layer and an output layer of the network are set to be tan sig and logsig functions respectively, the network training function is thingdx, the network performance function is mse, and the number of hidden layer neurons is initially set to be 2. And setting network parameters. The number of network iterations epochs is 5000, the expected error goal is 0.00000001, and the learning rate lr is 0.01. And after the parameters are set, starting to train the network. The network completes learning after 24 iterations of learning to the desired error. After the network training is finished, the prediction data of the pollution source score can be obtained only by inputting various influence parameters into the network.
In addition, the training of the model in S142 further includes the following steps:
for the condition of insufficient training, the training effect is achieved by increasing nodes in the network or increasing the training period of the network;
for the over-fitting condition, the training period is reduced or controlled, and the training on the network is stopped before the inflection point appears in the data, so that the training effect is achieved.
S2, collecting data of various score evaluation indexes of a pollution source sewage outlet in real time by using a preset monitoring sensor;
wherein, the step of collecting data of various score evaluation indexes of the sewage outlet of the pollution source in real time by using a preset monitoring sensor in the step S2 further comprises the following steps:
acquiring video data of a sewage draining exit in real time by using a preset video acquisition device, and judging whether a person approaches the sewage draining exit;
acquiring video data of a station house in real time by using a preset video acquisition device, and judging whether an illegal person intrudes;
when detecting that someone approaches the sewage outlet or illegal personnel intrude the station, the voice alarm is carried out, and the site inspection personnel is informed to carry out site inspection in time.
S3, calculating by utilizing the collected various score evaluation index data and combining preset weights of various score evaluation indexes to obtain the actual pollution source score at the current moment;
wherein, the calculation formula of the actual pollution source score in S3 is as follows:
y＝a1x1+a2x2+a3x3+a4x4+...+anxn；
wherein x is1、x2、x3、x4…xnShowing different score evaluation indexes (including pH, ammonia nitrogen content, chemical oxygen demand, total phosphorus content, smoke dust content, smoke temperature and the like), a1、a2、a3、a4…anRepresents the weight of each evaluation index, and a1+a2+a3+a4+…+an＝1，a1、a2、a3、a4…anThe value range of (a) is greater than 0 and less than or equal to 1.
S4, inputting the collected various score evaluation index data into a BP neural network prediction model to obtain the predicted pollution source score at the current moment;
and S5, comparing and analyzing the actual pollution source value and the predicted pollution source value, and identifying whether the online monitoring data is counterfeit or not by using the comparison and analysis result.
In S5, comparing and analyzing the actual pollution source score and the predicted pollution source score, and identifying whether the online monitoring data is counterfeit by using the comparison and analysis result includes the following steps:
s51, respectively obtaining the actual pollution source value and the predicted pollution source value, judging whether the actual pollution source value and the predicted pollution source value are the same, if the actual pollution source value and the predicted pollution source value are the same, executing S52, and if the actual pollution source value and the predicted pollution source value are different, sending out early warning and informing field inspectors to carry out field inspection;
s52, acquiring various types of value evaluation index data of the pollution source sewage outlet collected in real time, and verifying the various types of value evaluation index data collected in real time by using a relation table corresponding to the pollution source values and the value evaluation indexes;
s53, judging whether the various score evaluation index data collected in real time are consistent with data in a relation table corresponding to the pollution source score and the score evaluation index, if so, judging that the online monitoring data are not fake, and if not, executing S54;
s54, judging whether various score evaluation index data collected in real time are larger than a preset threshold value or smaller than the detection limit of a preset monitoring sensor, if so, sending out an early warning and informing field inspectors to carry out field inspection, and if not, executing S55;
s55, respectively carrying out variance processing on various score evaluation index data collected in a preset time period and judging whether the variance is zero, if so, sending out an early warning and informing field inspectors to carry out field inspection, and if not, judging that the online monitoring data is not fake.
Because normal instrument monitoring data necessarily has certain volatility, the abnormal data is identified by utilizing the characteristic and detecting whether the data is constant in nearly three hours or not. Since the data variance can characterize the volatility of the data, it can be identified whether the data is constant by calculating the variance of the monitored data for approximately three hours.
In conclusion, by means of the technical scheme of the invention, the historical online monitoring data is utilized to construct the BP neural network prediction model based on the pollution source score evaluation index and the pollution source score, so that the model can output the corresponding predicted pollution source value according to the value evaluation index parameter collected in real time, and the predicted pollution source value and the actual pollution source value obtained by actual calculation are adopted for comparison and analysis, therefore, real-time identification and judgment on whether the pollution source online detection data is counterfeit can be realized, so that the online monitoring system can further perfect and optimize online monitoring service, effectively realize supervision on waste water and waste gas emission of enterprises, realize cheating prevention early warning and decision-making auxiliary analysis on the online monitoring data of environmental protection information, effectively improve powerful monitoring of online monitoring by environmental protection departments, and realize intelligent environmental protection.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A method for identifying false pollution source online monitoring data is characterized by comprising the following steps:
s1, collecting historical online monitoring data of the pollution source, and constructing a BP neural network prediction model based on a pollution source score evaluation index and a pollution source score;
s2, collecting data of various score evaluation indexes of a pollution source sewage outlet in real time by using a preset monitoring sensor;
s3, calculating by utilizing the collected various score evaluation index data and combining preset weights of various score evaluation indexes to obtain the actual pollution source score at the current moment;
s4, inputting the collected various score evaluation index data into a BP neural network prediction model to obtain the predicted pollution source score at the current moment;
and S5, comparing and analyzing the actual pollution source value and the predicted pollution source value, and identifying whether the online monitoring data is counterfeit or not by using the comparison and analysis result.
2. The method for identifying the false positives of the online monitoring data of the pollution sources according to claim 1, wherein the step of collecting historical online monitoring data of the pollution sources in the step S1 and constructing a BP neural network prediction model based on the pollution source score evaluation index and the pollution source score comprises the following steps:
s11, collecting historical online monitoring data of the pollution source, and grouping the obtained historical online monitoring data according to a time sequence;
s12, constructing a pollution source score evaluation index system based on the online monitoring data by using the acquired historical online monitoring data;
s13, giving different preset weights to different score evaluation indexes, and obtaining the pollution source score of each group of historical online monitoring data by utilizing the weighted summation of each evaluation index;
s14, constructing a BP neural network prediction model based on the pollution source score evaluation index and the pollution source score.
3. The method for identifying the false positive of the online monitoring data of the pollution source as claimed in claim 2, wherein the step of grouping the acquired historical online monitoring data in the step S11 according to the time sequence comprises the steps of:
and sequencing the acquired historical online monitoring data according to a time sequence to obtain a plurality of groups of historical online monitoring data, and clearing the obviously abnormal data in each group of sequenced historical online monitoring data.
4. The method for identifying the false positive of the online monitoring data of the pollution source as claimed in claim 2, wherein the score evaluation indexes in the S12 include pH, ammonia nitrogen content, chemical oxygen demand, total phosphorus content, smoke content and flue gas temperature.
5. The method for identifying the false positives of the online monitoring data of the pollution sources according to claim 2, wherein the step S13 is performed by assigning different preset weights to different score evaluation indexes, and obtaining the score of each set of historical online monitoring data by using the weighted sum of the evaluation indexes further comprises the steps of:
and constructing a relation table corresponding to the pollution source value and the value evaluation index based on the value evaluation index and the pollution source value in each group of historical online monitoring data.
6. The method for identifying the false positives of the pollution source online monitoring data according to claim 2, wherein the step of constructing the BP neural network prediction model based on the pollution source score evaluation index and the pollution source score in the step S14 includes the following steps:
s141, dividing a plurality of groups of historical online monitoring data with pollution source scores into a training set and a testing set;
and S142, constructing a BP neural network prediction model based on the pollution source score evaluation index and the pollution source score, and respectively training and testing the model by using the training set and the testing set in the S141.
7. The method for identifying the false positives of the pollution source online monitoring data according to claim 6, wherein the training of the model in the step S142 further comprises the steps of:
for the condition of insufficient training, the training effect is achieved by increasing nodes in the network or increasing the training period of the network;
for the over-fitting condition, the training period is reduced or controlled, and the training on the network is stopped before the inflection point appears in the data, so that the training effect is achieved.
8. The method for identifying the false positive of the on-line monitoring data of the pollution source as claimed in claim 1, wherein the step of collecting the data of various score evaluation indexes of the sewage outlet of the pollution source in real time by using a preset monitoring sensor in the step S2 further comprises the following steps:
acquiring video data of a sewage draining exit in real time by using a preset video acquisition device, and judging whether a person approaches the sewage draining exit;
acquiring video data of a station house in real time by using a preset video acquisition device, and judging whether an illegal person intrudes;
when detecting that someone approaches the sewage outlet or illegal personnel intrude the station, the voice alarm is carried out, and the site inspection personnel is informed to carry out site inspection in time.
9. The method for identifying the falsification of the online pollution source monitoring data according to claim 1, wherein the actual pollution source score in the step S3 is calculated by the following formula:
y＝a1x1+a2x2+a3x3+a4x4+...+anxn；
wherein x is1、x2、x3、x4…xnRepresenting different score evaluation indices, a1、a2、a3、a4…anRepresents the weight of each evaluation index, and a1+a2+a3+a4+…+an＝1。
10. The method for identifying the counterfeiting of the online monitoring data of the pollution source according to claim 5, wherein the step of comparing and analyzing the actual pollution source score and the predicted pollution source score in the step S5, and identifying whether the online monitoring data is the counterfeiting by using the comparison and analysis result comprises the following steps:
s51, respectively obtaining the actual pollution source value and the predicted pollution source value, judging whether the actual pollution source value and the predicted pollution source value are the same, if the actual pollution source value and the predicted pollution source value are the same, executing S52, and if the actual pollution source value and the predicted pollution source value are different, sending out early warning and informing field inspectors to carry out field inspection;
s52, acquiring various types of value evaluation index data of the pollution source sewage outlet collected in real time, and verifying the various types of value evaluation index data collected in real time by using a relation table corresponding to the pollution source values and the value evaluation indexes;
s53, judging whether the various score evaluation index data collected in real time are consistent with data in a relation table corresponding to the pollution source score and the score evaluation index, if so, judging that the online monitoring data are not fake, and if not, executing S54;
s54, judging whether various score evaluation index data collected in real time are larger than a preset threshold value or smaller than the detection limit of a preset monitoring sensor, if so, sending out an early warning and informing field inspectors to carry out field inspection, and if not, executing S55;
s55, respectively carrying out variance processing on various score evaluation index data collected in a preset time period and judging whether the variance is zero, if so, sending out an early warning and informing field inspectors to carry out field inspection, and if not, judging that the online monitoring data is not fake.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111318179.1A CN114049134A (en) | 2021-11-09 | 2021-11-09 | Pollution source online monitoring data counterfeiting identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111318179.1A CN114049134A (en) | 2021-11-09 | 2021-11-09 | Pollution source online monitoring data counterfeiting identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114049134A true CN114049134A (en) | 2022-02-15 |
Family
ID=80207575
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111318179.1A Pending CN114049134A (en) | 2021-11-09 | 2021-11-09 | Pollution source online monitoring data counterfeiting identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114049134A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116589078A (en) * | 2023-07-19 | 2023-08-15 | 莒县环境监测站 | Intelligent sewage treatment control method and system based on data fusion |
| CN117235624A (en) * | 2023-09-22 | 2023-12-15 | 中节能天融科技有限公司 | Emission data falsification detection method, device and system and storage medium |
| CN117992441A (en) * | 2024-02-07 | 2024-05-07 | 广州翌拓软件开发有限公司 | Data processing method and system for synchronous auditing |
-
2021
- 2021-11-09 CN CN202111318179.1A patent/CN114049134A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116589078A (en) * | 2023-07-19 | 2023-08-15 | 莒县环境监测站 | Intelligent sewage treatment control method and system based on data fusion |
| CN116589078B (en) * | 2023-07-19 | 2023-09-26 | 莒县环境监测站 | Intelligent sewage treatment control method and system based on data fusion |
| CN117235624A (en) * | 2023-09-22 | 2023-12-15 | 中节能天融科技有限公司 | Emission data falsification detection method, device and system and storage medium |
| CN117235624B (en) * | 2023-09-22 | 2024-05-07 | 中节能数字科技有限公司 | Emission data falsification detection method, device and system and storage medium |
| CN117992441A (en) * | 2024-02-07 | 2024-05-07 | 广州翌拓软件开发有限公司 | Data processing method and system for synchronous auditing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114049134A (en) | Pollution source online monitoring data counterfeiting identification method | |
| CN112101790B (en) | Water body monitoring video and data linkage early warning method and system | |
| CN110046743B (en) | Public building energy consumption prediction method and system based on GA-ANN | |
| WO2021174971A1 (en) | Water environment risk prediction and early warning method | |
| CN110245880A (en) | A kind of pollution sources on-line monitoring data cheating recognition methods | |
| CN109784752A (en) | A kind of reservoir area of Three Gorges water eutrophication risk assessment early warning system and its analysis method | |
| CN110636066B (en) | Network security threat situation assessment method based on unsupervised generative reasoning | |
| CN103971133B (en) | The automatic identifying method of the Surface Defects in Steel Plate of case-based reasioning | |
| CN109034140A (en) | Industrial control network abnormal signal detection method based on deep learning structure | |
| CN111489046A (en) | Regional food safety evaluation model based on supply chain and BP neural network | |
| CN114422184A (en) | Network security attack type and threat level prediction method based on machine learning | |
| CN111191855B (en) | Water quality abnormal event identification and early warning method based on pipe network multi-element water quality time sequence data | |
| CN114169424A (en) | Discharge capacity prediction method based on k nearest neighbor regression algorithm and electricity utilization data | |
| CN116307103A (en) | Traffic accident prediction method based on hard parameter sharing multitask learning | |
| CN117170221A (en) | Artificial intelligence control system for sewage treatment | |
| CN115470850A (en) | Water quality abnormal event recognition early warning method based on pipe network water quality time-space data | |
| CN116952654B (en) | Environment monitoring and early warning system for administrative supervision | |
| CN113591078A (en) | Industrial control intrusion detection system and method based on convolutional neural network architecture optimization | |
| CN117115637A (en) | Water quality monitoring and early warning method and system based on big data technology | |
| CN117495091A (en) | Intelligent ship navigation risk evaluation method based on entropy-TOPSIS-coupling coordination model | |
| CN116823047A (en) | Lake eutrophication evaluation method based on Monte Carlo-variable fuzzy set | |
| CN111325286B (en) | Intelligent identification method for flood control system effect-showing project based on random forest | |
| CN116028803A (en) | Unbalancing method based on sensitive attribute rebalancing | |
| CN115062851A (en) | Pollution discharge abnormity monitoring method and system based on multi-algorithm fusion | |
| CN115277159A (en) | Industrial Internet security situation assessment method based on improved random forest |
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 |