CN113298422B - Pollution source enterprise illegal production monitoring method based on electricity consumption data - Google Patents
Pollution source enterprise illegal production monitoring method based on electricity consumption data Download PDFInfo
- Publication number
- CN113298422B CN113298422B CN202110668541.1A CN202110668541A CN113298422B CN 113298422 B CN113298422 B CN 113298422B CN 202110668541 A CN202110668541 A CN 202110668541A CN 113298422 B CN113298422 B CN 113298422B
- Authority
- CN
- China
- Prior art keywords
- enterprise
- production
- equipment
- phase
- decision tree
- 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
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 76
- 238000012544 monitoring process Methods 0.000 title claims abstract description 42
- 230000005611 electricity Effects 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000003066 decision tree Methods 0.000 claims abstract description 34
- 238000012549 training Methods 0.000 claims abstract description 16
- 230000007613 environmental effect Effects 0.000 claims description 29
- 230000006399 behavior Effects 0.000 claims description 18
- 238000012216 screening Methods 0.000 claims description 5
- 238000013480 data collection Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 239000010754 BS 2869 Class F Substances 0.000 claims description 2
- 238000009434 installation Methods 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 9
- 239000003344 environmental pollutant Substances 0.000 description 8
- 231100000719 pollutant Toxicity 0.000 description 8
- 238000004891 communication Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012545 processing 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063114—Status monitoring or status determination for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a pollution source enterprise illegal production monitoring method based on electricity consumption data, which belongs to the technical field of energy monitoring and early warning, and comprises the steps of installing electricity consumption information acquisition equipment at an electricity consumption bus of a pollution source enterprise, and acquiring electricity consumption data of the total load of the enterprise; analyzing the importance degree of different load characteristics on classification based on a decision tree algorithm, and then selecting the load characteristics with higher importance degree in the process for subsequent training of a simplified model; training a decision tree classifier by using the load characteristics with higher importance degree screened in the last step and taking the combination of the on-off states of the enterprise production equipment and the enterprise environment-friendly equipment in the historical period as a label; and inputting the new multidimensional monitoring data into the trained classifier, and identifying the production behavior state of the polluted enterprise. According to the invention, the production behavior of the pollution source enterprise can be monitored only by arranging the power utilization information acquisition device at the power utilization bus of the enterprise, so that the quantity and the installation cost of the power utilization monitoring equipment are greatly reduced.
Description
Technical Field
The invention relates to a pollution source enterprise illegal production monitoring method based on electricity consumption data, and belongs to the technical field of energy monitoring and early warning.
Background
With the development of society, people pay more and more attention to the improvement of environmental quality, the control on pollutant emission in relevant regulations is very strict, but only a few large-scale enterprises with organized emission incorporate automatic monitoring, and most small and medium-sized enterprises lack a supervision means.
Because the number of enterprises is large, the types of industries are large, the process is complicated, a large amount of manpower, material resources and financial resources are consumed in the traditional mode for judging different types of pollution sources, and the production behaviors of the pollution source enterprises can be intuitively reflected by the power utilization data of the pollution source enterprises. At present, the electricity utilization information acquisition technology can acquire and store information such as voltage, current, voltage unbalance degree, total harmonic distortion rate and the like, a data basis is provided for monitoring production behaviors of pollution source enterprises, and powerful support is provided for environmental protection supervision work of related departments. To enterprise's environmental protection supervision, the environmental protection supervision platform based on power consumption data can carry out incessant power consumption control to blowdown and pollution treatment equipment, judges the start-stop time point, can carry out the blowdown and treat pollution linkage control, realizes no dead angle control, has compensatied the painful point that manual detection pollutant discharged.
However, the existing environmental monitoring scheme based on electricity consumption data analysis needs to install monitoring equipment on pollution treatment equipment, start and stop of the pollution treatment equipment are directly monitored, and whether illegal production behaviors exist in pollution source enterprises is further judged by combining the start and stop conditions of production equipment.
The invention discloses a regional industrial gaseous pollutant monitoring method and system disclosed in Chinese patent with publication number CN110849421A, which comprises a monitoring center, at least one electrical parameter detection module, a communication module and a pollutant detection module; the monitoring center is communicated with the communication module and the pollutant detection module, and the electric parameter detection module is electrically connected with the communication module. The method comprises the steps of monitoring the operation electrical parameters of the production equipment and the pollutant discharge amount, uploading the detection data to a monitoring center, and processing the received data by the monitoring center to obtain the distribution condition of the regional industrial gaseous pollutants.
Above-mentioned reference example needs to carry out the monitoring of power consumption to all production line equipment in workshop and environmental protection equipment, if production equipment or environmental protection equipment are in a large number, not only with high costs, arrange the trouble moreover, and can only learn regional industry gaseous pollutant's distribution situation, can't report to the police to the enterprise of violating the regulations, consequently need improve urgently.
Disclosure of Invention
In order to overcome the defects that the existing environment-friendly detection scheme based on power consumption data analysis needs more monitoring equipment to be installed and the installation cost is high, the invention designs a pollution source enterprise illegal production monitoring method based on power consumption data.
In order to achieve the purpose, the invention adopts the following technical scheme:
a pollution source enterprise illegal production monitoring method based on electricity consumption data is characterized by comprising the following steps: the method comprises the following steps:
a1: installing an intelligent monitoring terminal for acquiring enterprise electricity utilization information at an enterprise electricity utilization bus;
a2: the method comprises the steps that an intelligent monitoring terminal obtains enterprise electricity utilization data in a period of time as load characteristics and obtains start-stop state data of the environment-friendly equipment in corresponding time;
a3: setting a three-phase apparent power threshold, acquiring total load three-phase apparent power of an enterprise in corresponding time through load characteristics, and judging the start-stop state of production equipment according to whether the total load three-phase apparent power of the enterprise exceeds the threshold or not;
a4: whether an enterprise breaks the production behavior in the corresponding time is obtained according to the start-stop state data of the environment-friendly equipment and the start-stop state of the production equipment; the load characteristics are used as a sample, whether an enterprise has illegal production behavior within corresponding time is used as an attribute label of the sample, a plurality of samples are collected as an initial sample set, a decision tree algorithm and the initial sample set are used for carrying out primary training to obtain a simplified classifier model, and a plurality of load characteristics close to a root node are screened from a decision tree of the simplified classifier model to be used as secondary training samples;
a5: training the simplified classifier model again by using the secondary training sample and the corresponding attribute label to obtain a trained separator;
a6: and inputting the real-time enterprise electricity utilization data acquired by the intelligent monitoring terminal into the trained classifier, and judging whether the enterprises have illegal production behaviors or not in the corresponding time period.
Further, the enterprise power consumption information collected by the intelligent monitoring terminal in the step A1 includes: each phase voltage, each phase current, each phase power, each harmonic voltage, each harmonic current, a total harmonic voltage distortion rate, a total harmonic current distortion rate, voltage deviation, voltage unbalance and power factors, wherein each phase power comprises each phase active power, each phase reactive power and each phase apparent power.
Further, in the step A3, judging the start-stop state of the production equipment according to whether the total load three-phase apparent power of the enterprise exceeds the threshold specifically includes judging that the production equipment is in the start state when the total load three-phase apparent power of the enterprise exceeds the set threshold, and otherwise judging that the production equipment is in the stop state.
Further, the step A4 specifically includes setting a data collection set as S, where S includes a load characteristic X and a sample attribute tag of each sample, where the load characteristic X is the enterprise electricity consumption data acquired by the intelligent monitoring terminal in the step A2, where the sample attribute tag is set to three different values Fi (i =1,2, 3), and F1, F2, and F3 respectively represent three different production scenarios, that is, no environmental protection equipment is started in the production process, and that is, environmental protection equipment is started and production is stopped in the production process;
if the number of the categories Fi is Fi |, and the number of the samples in S is S |, the entropy of S is defined as:
wherein Pi is the probability that any sample belongs to Fi, and is recorded as:
the data in S is divided according to the load characteristics X, if the load characteristics X have m different classes, the S is divided into m subsets { S1, S2, \8230;, sm }, and after the load characteristics X are used for dividing the sample set S, the entropy of the subset Si of the S is weighted and calculated, and the formula is as follows:
the information gain obtained under the load characteristic X is:
Gain(S,X)=Entropy(S)-Entropy X (S)
and finally, screening the characteristics X' of a plurality of nodes from top to bottom from the decision tree according to the requirement for the next step of simplifying the model.
Further, the step A5 specifically includes using the load characteristic X' screened in the step A4 as an input quantity of the decision tree algorithm, and using a combination of start-stop states of the production equipment of the enterprise and the environmental protection equipment of the enterprise in a historical period as an attribute label of the algorithm, and retraining the simplified decision tree classifier.
Further, the step A6 specifically includes inputting the real-time enterprise power consumption information acquired by the intelligent monitoring terminal into the decision tree classifier trained in the step A5, and if the judgment result is that the production behavior state of the environmental protection equipment is not started in the production process, performing environmental protection abnormity alarm, and performing field verification and management by a manager.
Compared with the prior art, the invention has the following characteristics and beneficial effects:
1. according to the invention, the intelligent detection terminal is arranged at the enterprise power utilization bus to acquire the enterprise power utilization information of the enterprise and the start-stop state data of the environmental protection equipment, the decision tree is constructed by using a decision tree algorithm to train the classifier model, and then the enterprise power utilization information subsequently monitored by the intelligent detection terminal is input into the trained classifier, so that whether the enterprise violates the rules or not can be judged.
2. The invention trains the classifier by a decision tree method, calculates the information gain of all possible characteristics from the root node to the node, selects the characteristic with the maximum information gain as the characteristic of the node, establishes different values of the characteristic on the child nodes, namely trains the multi-classification classifier, can directly select the production behavior state of 'no environmental protection equipment started in the production process' which is focused on, and is efficient and rapid.
3. The invention simplifies the index quantity used in the process of training the model by adopting the decision tree algorithm, and screens from top to bottom from the decision tree when selecting the node characteristics in the training process.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The present invention will be described in more detail with reference to examples.
As shown in fig. 1, the method for monitoring illegal production of pollution source enterprises based on electricity consumption data of the embodiment includes the following steps:
a1: installing an intelligent monitoring terminal for acquiring enterprise electricity utilization information at an enterprise electricity utilization bus;
a2: the intelligent monitoring terminal acquires enterprise electricity utilization data in a period of time as load characteristics and acquires start-stop state data of the environment-friendly equipment in corresponding time, the time scale of data acquired by the intelligent electricity utilization monitoring terminal is in the minute level, 1min, 3min and 5min are commonly used, and the frequency of acquiring the data is higher than the acquisition frequency of acquiring electricity utilization information in the existing monitoring scheme by 15 min;
a3: setting a three-phase apparent power threshold, acquiring the total load three-phase apparent power of an enterprise within corresponding time through load characteristics, and judging the start-stop state of production equipment according to whether the total load three-phase apparent power of the enterprise exceeds the threshold or not;
a4: whether the enterprises have illegal production behaviors within the corresponding time is obtained according to the start-stop state data of the environment-friendly equipment and the start-stop state of the production equipment; taking the load characteristics as a sample, taking whether an enterprise has illegal production behaviors within corresponding time as an attribute label of the sample, collecting a plurality of samples as an initial sample set, carrying out primary training by using a decision tree algorithm and the initial sample set to obtain a simplified classifier model, and screening a plurality of load characteristics close to a root node from a decision tree of the simplified classifier model to be used as secondary training samples;
the decision tree is a basic algorithm in machine learning, the core of the decision tree algorithm is to apply information gain criterion selection characteristics on each node of the decision tree and recursively construct the decision tree, and the specific method is as follows: calculating the information gains of all possible characteristics from the root node to the node, selecting the characteristic with the maximum information gain as the characteristic of the node, and establishing the characteristic in the child nodes according to different values of the characteristic; then recursively calling the above method for the nodes to construct a decision tree; stopping until the information gains of all the characteristics are very small or no characteristics can be selected, and obtaining a final decision tree;
a5: training the simplified classifier model again by using the secondary training sample and the corresponding attribute label to obtain a trained separator;
a6: and inputting the real-time enterprise electricity utilization data acquired by the intelligent monitoring terminal into the trained classifier, and judging whether the enterprise has an illegal production behavior in the corresponding time period.
Particularly, the production behavior state of the enterprise is divided into the following states by combining the start-stop state data of the environmental protection equipment in the step A2 and the start-stop state of the production equipment in the step A3: environmental protection equipment is not started in the production process, and the environmental protection equipment is started and the production is stopped in the production process.
Further, the enterprise power consumption information collected by the intelligent monitoring terminal in the step A1 includes: each phase voltage, each phase current, each phase power, each harmonic voltage, each harmonic current, total harmonic voltage distortion rate, total harmonic current distortion rate, voltage deviation, voltage unbalance and power factors, wherein each phase power comprises each phase active power, each phase reactive power and each phase apparent power, and each phase apparent power is monitoring data for judging the start-stop state of the production equipment in the step A3.
Further, in the step A3, judging the start-stop state of the production equipment according to whether the total load three-phase apparent power of the enterprise exceeds the threshold specifically includes judging that the production equipment is in the start state when the total load three-phase apparent power of the enterprise exceeds the set threshold, and otherwise judging that the production equipment is in the stop state.
Further, the step A4 specifically includes setting a data collection set as S, where S includes a load characteristic X and a sample attribute tag of each sample, where the load characteristic X is enterprise electricity consumption data acquired by the intelligent monitoring terminal in the step A2, and the sample attribute tag is set as three different values F i (i=1,2,3),F 1 、F 2 And F 3 Respectively representing three different production scenes of not starting environmental protection equipment in the production process, starting the environmental protection equipment in the production process and stopping the production;
setting class F i Is | F i If the number of samples in S is | S |, the entropy of S is defined as:
wherein, P i Is that any sample belongs to F i The probability of (d) is noted as:
the data in S is divided according to load characteristics X, the load characteristics X have m different classes, and then S is divided into m subsets { S 1 ,S 2 ,…,S m Dividing the sample set S by the load characteristic X, and then dividing the subset S of S i The entropy of (a) is weighted, and the formula is as follows:
in information theory, entropy (Entropy) is a measure of uncertainty of a random variable, i.e., the larger the Entropy, the larger the uncertainty of the random variable;
the information gain obtained under the load characteristic X is:
Gain(S,X)=Entropy(S)-Entropy X (S)
the information gain refers to the change of the information entropy before and after the sample set S is divided, and is the split measurement standard of the sample set S, and the obtained information gain is larger, and the classification capability of the sample set S is stronger; the ID3 algorithm of the decision tree is equivalent to the selection of a probability model by using a maximum likelihood method;
finally, screening the characteristics X' of a plurality of nodes from top to bottom from the decision tree for the next simplified model to use according to the requirement;
and B, in the decision tree obtained in the step A4, the more the characteristics of the nodes close to the root node are, the higher the importance degree is, and the characteristics X' of a certain number of nodes are selected from the decision tree from top to bottom according to requirements for being used by a simplified model in the next step.
Further, the step A5 specifically includes using the load characteristics X' screened in the step A4 as input quantities of the decision tree algorithm, and using a combination of start-stop states of the production equipment of the enterprise and the environmental protection equipment of the enterprise in a historical period (i.e., the environmental protection equipment is not started in the production process/the environmental protection equipment is started in the production process/the production is stopped) as an attribute label of the algorithm, and retraining the simplified decision tree classifier.
Particularly, the production behavior state predicted and judged by the logistic regression classifier may have some errors with the actual state, the effect evaluation mainly adopts Accuracy (Accuracy) as an evaluation index, and samples with the predicted classification of the classifier being consistent with the real classification are recorded as True, and samples with the predicted classification of the classifier being inconsistent with the real classification are recorded as False;
the accuracy represents the ratio of the correct classification number of the model to the total number of samples, and is calculated as follows:
further, the step A6 specifically includes inputting the real-time enterprise power consumption information acquired by the intelligent monitoring terminal into the decision tree classifier trained in the step A5, and if the judgment result is that the production behavior state of the environmental protection equipment is not started in the production process, performing environmental protection abnormity alarm, and performing field verification and management by a manager.
It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Claims (2)
1. A pollution source enterprise illegal production monitoring method based on electricity consumption data is characterized by comprising the following steps: the method comprises the following steps:
a1: installing an intelligent monitoring terminal for acquiring enterprise electricity utilization information at an enterprise electricity utilization bus;
a2: the method comprises the steps that an intelligent monitoring terminal obtains enterprise electricity utilization data in a period of time as load characteristics and obtains start-stop state data of the environment-friendly equipment in corresponding time;
a3: setting a three-phase apparent power threshold, acquiring the total load three-phase apparent power of an enterprise within corresponding time through load characteristics, and judging the start-stop state of production equipment according to whether the total load three-phase apparent power of the enterprise exceeds the threshold or not;
a4: whether an enterprise breaks the production behavior in the corresponding time is obtained according to the start-stop state data of the environment-friendly equipment and the start-stop state of the production equipment; taking the load characteristics as a sample, taking whether an enterprise has illegal production behaviors within corresponding time as an attribute label of the sample, collecting a plurality of samples as an initial sample set, carrying out primary training by using a decision tree algorithm and the initial sample set to obtain a simplified classifier model, and screening a plurality of load characteristics close to a root node from a decision tree of the simplified classifier model to be used as secondary training samples;
a5: training the simplified classifier model again by using the secondary training sample and the corresponding attribute label to obtain a trained classifier;
a6: inputting real-time enterprise electricity utilization data acquired by an intelligent monitoring terminal into a trained classifier, and judging whether the enterprise has an illegal production behavior at a corresponding time period;
step A3, judging the starting and stopping state of the production equipment according to whether the total load three-phase apparent power of the enterprise exceeds a threshold value specifically comprises the steps of judging that the production equipment is in a starting state when the total load three-phase apparent power of the enterprise exceeds the set threshold value, and otherwise, judging that the production equipment is in a stopping state;
step A4 specifically includes setting a data collection set as S, wherein the S includes a load characteristic X and a sample attribute label of each sample, the load characteristic X is the enterprise electricity utilization data acquired by the intelligent monitoring terminal in step A2, and the sample attribute label is set to three different values F i ( i = 1, 2, 3),F 1 、F 2 And F 3 Respectively representing three different production scenes of not starting environmental protection equipment in the production process, starting the environmental protection equipment in the production process and stopping the production; setting class F i Is | F i If the number of samples in S is | S |, the entropy of S is defined as:
wherein Pi is any sample belonging to F i The probability of (d) is noted as:
the data in S is divided according to load characteristics X, the load characteristics X have m different classes, and then S is divided into m subsets { S 1 , S 2 ,…,S m Dividing the sample set S by the load characteristic X, and then dividing the subset S of S i The entropy of (a) is weighted, and the formula is as follows:
the information gain obtained under the load characteristic X is:
finally, screening out the characteristics X' of a plurality of nodes from top to bottom from the decision tree for the next step of model simplification according to the requirement;
step A5 specifically comprises the steps of utilizing the load characteristics X' screened in the step A4 as input quantity of a decision tree algorithm, utilizing the combination of the starting and stopping states of the production equipment of the enterprise and the environmental protection equipment of the enterprise in the historical period as attribute labels of the algorithm, and retraining a simplified decision tree classifier;
step A6 specifically comprises the steps of inputting the real-time enterprise electricity utilization information acquired by the intelligent monitoring terminal into the decision tree classifier trained in step A5, and if the judgment result is that the production behavior state of the environmental protection equipment is not started in the production process, carrying out environmental protection abnormity alarm, and carrying out field verification and management by a manager.
2. The monitoring method for illegal production of pollution source enterprises based on electricity consumption data as claimed in claim 1, characterized in that: the enterprise power consumption information collected by the intelligent monitoring terminal in the step A1 comprises the following steps: each phase voltage, each phase current, each phase power, each harmonic voltage, each harmonic current, the total distortion rate of the harmonic voltage, the total distortion rate of the harmonic current, voltage deviation, voltage unbalance and power factors, wherein each phase power comprises each phase active power, each phase reactive power and each phase apparent power.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110668541.1A CN113298422B (en) | 2021-06-16 | 2021-06-16 | Pollution source enterprise illegal production monitoring method based on electricity consumption data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110668541.1A CN113298422B (en) | 2021-06-16 | 2021-06-16 | Pollution source enterprise illegal production monitoring method based on electricity consumption data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113298422A CN113298422A (en) | 2021-08-24 |
CN113298422B true CN113298422B (en) | 2023-01-31 |
Family
ID=77328487
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110668541.1A Active CN113298422B (en) | 2021-06-16 | 2021-06-16 | Pollution source enterprise illegal production monitoring method based on electricity consumption data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113298422B (en) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113762619B (en) * | 2021-09-08 | 2023-07-28 | 国家电网有限公司 | Distribution Internet of things user load identification method, system, equipment and storage medium |
CN113988711A (en) * | 2021-11-22 | 2022-01-28 | 国网江苏省电力有限公司连云港供电分公司 | Power consumption data-based monitoring method for stopping or limiting production of sewage disposal enterprises in control state |
CN114118580B (en) * | 2021-11-29 | 2023-04-07 | 国网山东省电力公司东营供电公司 | Yellow river basin pollution source monitoring and early warning method based on electric power-environmental protection data fusion analysis |
CN115291006A (en) * | 2022-07-21 | 2022-11-04 | 福州大学 | Method for identifying environmental protection working condition abnormity of polluted enterprise based on electricity utilization data |
CN115908082A (en) * | 2023-01-06 | 2023-04-04 | 佰聆数据股份有限公司 | Enterprise pollution discharge monitoring method and device based on electricity utilization characteristic indexes |
CN117455124B (en) * | 2023-12-25 | 2024-03-08 | 杭州烛微智能科技有限责任公司 | Environment-friendly equipment monitoring method, system, medium and electronic equipment for enterprises |
CN117649061B (en) * | 2024-01-30 | 2024-04-26 | 山东达斯特信息技术有限公司 | Multi-node networking electricity analysis method and system for environmental protection monitoring |
Family Cites Families (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7233931B2 (en) * | 2003-12-26 | 2007-06-19 | Lee Shih-Jong J | Feature regulation for hierarchical decision learning |
CN105260628B (en) * | 2014-06-03 | 2019-01-11 | 腾讯科技(深圳)有限公司 | Classifier training method and apparatus, auth method and system |
CN104766158A (en) * | 2015-03-18 | 2015-07-08 | 福建望诚电子有限公司 | Environment protection full-process monitoring system |
US20170083920A1 (en) * | 2015-09-21 | 2017-03-23 | Fair Isaac Corporation | Hybrid method of decision tree and clustering technology |
CN107704070B (en) * | 2017-09-30 | 2020-01-14 | Oppo广东移动通信有限公司 | Application cleaning method and device, storage medium and electronic equipment |
CN108011367B (en) * | 2017-12-04 | 2020-12-18 | 贵州电网有限责任公司电力科学研究院 | Power load characteristic mining method based on depth decision tree algorithm |
CN108960586B (en) * | 2018-06-14 | 2021-06-11 | 华中科技大学 | Non-invasive load identification method adaptive to scene change |
CN109492667A (en) * | 2018-10-08 | 2019-03-19 | 国网天津市电力公司电力科学研究院 | A kind of feature selecting discrimination method for non-intrusive electrical load monitoring |
CN209150722U (en) * | 2018-11-28 | 2019-07-23 | 李�瑞 | A kind of control system of environmental protection equipment power supply ability production equipment power supply |
CN109684295B (en) * | 2018-12-04 | 2021-10-22 | 河北申科电力股份有限公司 | Environment-friendly equipment running state analysis method, device and system |
CN111077865B (en) * | 2019-12-25 | 2021-05-25 | 江苏三希科技股份有限公司 | Pollution source enterprise environment-friendly production load monitoring system and method |
CN111523794B (en) * | 2020-04-21 | 2020-11-24 | 国网四川省电力公司电力科学研究院 | Environment-friendly management and control measure response studying and judging method based on power utilization characteristics of pollution emission enterprises |
CN111428821A (en) * | 2020-05-18 | 2020-07-17 | 江苏电力信息技术有限公司 | Asset classification method based on decision tree |
CN111783827A (en) * | 2020-05-27 | 2020-10-16 | 中能瑞通(北京)科技有限公司 | Enterprise user classification method and device based on load data |
CN112184090B (en) * | 2020-11-30 | 2021-03-16 | 广东浩迪创新科技有限公司 | Standard electricity utilization feature library establishing method, environment-friendly monitoring method, system and monitor |
CN112787401B (en) * | 2021-01-15 | 2022-05-13 | 浙江容大电力工程有限公司 | Environment-friendly monitoring system and monitoring method based on electric power big data |
CN112686473B (en) * | 2021-01-22 | 2023-12-08 | 国网江苏省电力有限公司营销服务中心 | Power consumption prediction method and prediction system based on classification algorithm |
CN112907929A (en) * | 2021-01-29 | 2021-06-04 | 汇智道晟(舟山)科技有限公司 | Environment-friendly monitoring system and method based on electricity utilization information |
-
2021
- 2021-06-16 CN CN202110668541.1A patent/CN113298422B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN113298422A (en) | 2021-08-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113298422B (en) | Pollution source enterprise illegal production monitoring method based on electricity consumption data | |
CN110097297B (en) | Multi-dimensional electricity stealing situation intelligent sensing method, system, equipment and medium | |
CN111241154A (en) | Storage battery fault early warning method and system based on big data | |
CN105424395A (en) | Method and device for determining equipment fault | |
CN110929918A (en) | 10kV feeder line fault prediction method based on CNN and LightGBM | |
CN101833324B (en) | Intelligent fault diagnosis system in tread extrusion process and diagnosis method thereof | |
CN108304567B (en) | Method and system for identifying working condition mode and classifying data of high-voltage transformer | |
CN110687473B (en) | Fault positioning method and system for relay protection test of intelligent substation | |
CN112464995A (en) | Power grid distribution transformer fault diagnosis method and system based on decision tree algorithm | |
CN110580492A (en) | Track circuit fault precursor discovery method based on small fluctuation detection | |
CN105488118A (en) | Electrical equipment fault information display method and device | |
CN111506635A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive naive Bayes algorithm | |
CN111582338A (en) | Method and system for evaluating running state of electric vehicle charging facility | |
CN115222303A (en) | Industry risk data analysis method and system based on big data and storage medium | |
CN113379005B (en) | Intelligent energy management system and method for power grid power equipment | |
CN117353315B (en) | Device for controlling power generation voltage based on transient fluctuation of photovoltaic and wind power generation voltage | |
CN110807174B (en) | Effluent analysis and abnormity identification method for sewage plant group based on statistical distribution | |
CN112803587A (en) | Intelligent inspection method for state of automatic equipment based on diagnosis decision library | |
CN117113135A (en) | Carbon emission anomaly monitoring and analyzing system capable of sorting and classifying anomaly data | |
CN117216713A (en) | Fault delimiting method, device, electronic equipment and storage medium | |
CN116205528A (en) | Illegal construction identification method and system based on construction site power data | |
CN115908082A (en) | Enterprise pollution discharge monitoring method and device based on electricity utilization characteristic indexes | |
CN113191170B (en) | Public facility two-dimensional code damage inspection effectiveness prediction method and system | |
CN114626433A (en) | Fault prediction and classification method, device and system for intelligent electric energy meter | |
CN112561230A (en) | Environment-friendly equipment state monitoring method based on electrical characteristics |
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 |