CN114049033B - Pollution discharge enterprise monitoring method based on electricity consumption data distribution - Google Patents
Pollution discharge enterprise monitoring method based on electricity consumption data distribution Download PDFInfo
- Publication number
- CN114049033B CN114049033B CN202111389019.6A CN202111389019A CN114049033B CN 114049033 B CN114049033 B CN 114049033B CN 202111389019 A CN202111389019 A CN 202111389019A CN 114049033 B CN114049033 B CN 114049033B
- Authority
- CN
- China
- Prior art keywords
- enterprise
- enterprises
- abnormal
- sewage
- suspected
- 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
- 230000005611 electricity Effects 0.000 title claims abstract description 73
- 238000012544 monitoring process Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000002159 abnormal effect Effects 0.000 claims abstract description 82
- 239000010865 sewage Substances 0.000 claims abstract description 75
- 238000012216 screening Methods 0.000 claims abstract description 18
- 238000004519 manufacturing process Methods 0.000 claims description 14
- 230000007613 environmental effect Effects 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims 1
- 238000012795 verification Methods 0.000 abstract description 5
- 230000007123 defense Effects 0.000 description 5
- 238000001514 detection method Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000009435 building construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012850 discrimination method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005067 remediation Methods 0.000 description 1
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N silicon dioxide Inorganic materials O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
-
- 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
-
- 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)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a pollution discharge enterprise monitoring method based on electricity consumption data distribution, which comprises the steps of screening pollution discharge enterprises to be monitored: daily electricity consumption data of a sewage enterprise to be monitored in an observation time period are obtained, and the average value and standard deviation of the electricity consumption data are obtained; setting a first interval by adopting a normal distributed 3 sigma principle, and screening a first suspected pollution discharge abnormal enterprise list; grouping all sewage enterprises to be monitored according to industries, and calculating the average value and standard deviation of current daily electricity data for each group of enterprises day by day; setting a second interval by adopting a normal distributed 3 sigma principle, and screening a second suspected pollution discharge abnormal enterprise list; and carrying out cross verification on the first suspected abnormal sewage disposal enterprise list and the second suspected abnormal sewage disposal enterprise list to obtain a final suspected abnormal sewage disposal enterprise list. The application adopts electricity consumption data, realizes pollution discharge enterprise monitoring based on double intervals and multiple thresholds, and can reflect the pollution discharge condition of the enterprise more objectively.
Description
Technical Field
The invention belongs to the technical field of monitoring of pollution discharge conditions of enterprises, and relates to a pollution discharge enterprise monitoring method based on electricity consumption data distribution.
Background
Monitoring of a sewage disposal enterprise is a very important task for environmental remediation. At present, monitoring means for pollution discharge conditions of enterprises can be classified into people defense and technical defense.
The civil air defense is mainly used for carrying out inspection supervision through environmental departments or receiving social reporting clues to carry out investigation; on the one hand, the mode makes the workload of the environmental department larger, and on the other hand, the discovery of abnormal pollution discharge has a certain contingency.
The technical protection is mainly realized by introducing a sensor capable of monitoring in real time into sewage equipment or a sewage outlet, and an environmental department can monitor whether sewage is abnormal or not in an enterprise in real time through remote monitoring or data backtracking. The technical protection method increases the monitoring cost because extra devices are needed to build a system, and enterprises or governments are required to bear extra cost.
In addition, technical defense and civil air defense processes also have the condition that abnormal blowdown behaviors are hidden, and blowdown enterprises can steal and arrange through bypassing monitoring equipment to feed back inaccurate data.
In summary, the existing pollution discharge monitoring technology for enterprises generally has the disadvantages of high labor cost, heavy enterprise burden, distortion of monitoring data and the like.
Disclosure of Invention
In order to solve the defects in the prior art, the application provides a pollution discharge enterprise monitoring method based on electricity consumption data distribution, which does not need to add extra facilities, and has good credibility in view of the actual and effective characteristics of the electricity consumption data.
In order to achieve the above object, the present invention adopts the following technical scheme:
a pollution discharge enterprise monitoring method based on electricity consumption data distribution comprises the following steps:
step 1: screening sewage enterprises to be monitored:
Step 2: daily electricity consumption data of each sewage enterprise to be monitored in an observation time period are obtained, and the average value and standard deviation of the daily electricity consumption data in the time period are calculated;
Step 3: setting a first interval by adopting a normal distributed 3 sigma principle based on the average value and the standard deviation in the step 2, and screening a first suspected pollution discharge abnormal enterprise list by adopting the first interval;
step 4: grouping all the sewage enterprises to be monitored according to industries, and calculating the average value and standard deviation of the current daily electricity data for each group of enterprises day by day based on the daily electricity data obtained in the step 2;
step5: setting a second interval by adopting a normal distributed 3 sigma principle based on the average value and the standard deviation in the step 4, and screening a second suspected pollution discharge abnormal enterprise list by adopting the second interval;
step 6: and carrying out cross verification on the first suspected abnormal sewage disposal enterprise list and the second suspected abnormal sewage disposal enterprise list to obtain a final suspected abnormal sewage disposal enterprise list.
The invention further comprises the following preferable schemes:
Preferably, in step 1, enterprises closely related to power consumption in enterprise production are screened out as the sewage enterprises to be monitored through a sewage enterprise list provided by an environmental department.
Preferably, in step 1, enterprises with power proportion exceeding 80% in the energy structure are screened to consider that the enterprise production is closely related to the power consumption by measuring the relationship between the enterprise production and the power consumption in the energy structure, and the enterprises are used as sewage enterprises to be monitored.
Preferably, step 3 specifically includes:
Step 3.1: setting a first interval by using a3 sigma principle of normal distribution, taking an average value plus 3 times of standard deviation as an interval upper limit and taking an average value minus 3 times of standard deviation as an interval lower limit;
Step 3.2: for each sewage enterprise to be monitored, when the electricity consumption of a certain day in the observation time period falls outside a first interval, the electricity consumption of the day is considered to exceed a conventional random fluctuation mode, and the abnormal situation is considered;
Step 3.3: counting the number of days when abnormal conditions occur in each sewage enterprise to be monitored in the observation time period;
Step 3.4: sequencing the days of abnormal conditions of all the sewage enterprises to be monitored from high to low, and setting a threshold value n which is an integer smaller than the number of the sewage enterprises to be monitored and larger than zero;
And taking the enterprises arranged in the first n positions as suspected sewage abnormal enterprises, and obtaining a first suspected sewage abnormal enterprise list.
Preferably, in step 4, all the sewage enterprises to be monitored are grouped according to industries, and the obtained industry groups comprise power supply, building industry, environmental management and woven clothing manufacturing.
Preferably, step 5 specifically includes:
Step 5.1: the 3 sigma principle is applied, the average value of the current day power consumption of the group is added and subtracted by 3 times of standard deviation in groups, and the standard deviation is respectively used as the upper limit and the lower limit of the section, so that a second section of each group is obtained;
step 5.2: when the daily electricity value of the enterprise in each group is outside the second interval of the group, the daily electricity value is regarded as an abnormal condition;
Step 5.3: counting the days of abnormal conditions of each enterprise to be monitored in an observation time period;
step 5.4: and for all enterprises to be monitored, sorting the days of abnormal conditions of the groups according to the sequence from high to low, setting a threshold value for each group, and taking the enterprises positioned at the front threshold value in all groups as suspected abnormal sewage enterprises to obtain a second suspected abnormal sewage enterprise list.
Preferably, in step 5.4, the threshold is set on a 30% basis for each group on the days of the observation period.
Preferably, step 6 specifically includes:
Step 6.1: taking the daily electricity data of the first suspected abnormal sewage discharge enterprise list and the second suspected abnormal sewage discharge enterprise list as two groups of samples, and respectively calculating the distribution characteristic indexes of the two groups of enterprise lists;
Step 6.2: respectively calculating the distribution index centers of the two groups of enterprise lists to obtain a first center value and a second center value;
Step 6.3: respectively calculating Euclidean distances between all enterprise electricity distribution characteristic indexes in the first suspected pollution discharge abnormal enterprise list and the first central value and the second central value, comparing the Euclidean distances between the indexes and the first central value and the second central value, and screening and recording the rest enterprises in the first group;
Step 6.4: comparing the Euclidean distance between the power distribution characteristic indexes of all enterprises in the second suspected pollution discharge abnormal enterprise list and the first central value and the Euclidean distance between the power distribution characteristic indexes and the second central value, and screening and recording the rest enterprises in the second group;
step 6.5: and merging the enterprises left in the first group and the enterprises left in the second group to obtain a suspected pollution discharge abnormal enterprise list.
Preferably, the distribution characteristic index in step 6.1 includes a mean x1, a variance x2, a skewness coefficient x3, and a kurtosis coefficient x4 of the electricity data in the observation period.
Preferably, the distribution index center in step 6.2 is an average value of the characteristic indexes of each group.
The application has the beneficial effects that:
The invention realizes the monitoring of the sewage enterprises based on double intervals and multiple thresholds, firstly, the power consumption data and the characteristics of all sewage enterprises to be monitored are adopted to carry out preliminary detection to obtain preliminary suspected abnormal sewage enterprises, secondly, the power consumption data and the characteristics of sewage enterprises in different industries are respectively analyzed according to industry division to carry out refined detection, and finally, the two detection results are subjected to cross verification to screen the final suspected abnormal sewage enterprises, thereby being beneficial to improving the detection precision, and meanwhile, the invention has outstanding advantages in improving the detection accuracy.
The invention directly utilizes the existing power grid facilities, is more convenient and economical, and can be used for pollution discharge monitoring under the condition that the production behavior of pollution discharge enterprises has close relation with electricity consumption;
The invention adopts the enterprise electricity data to carry out pollution discharge monitoring based on the non-tamperable characteristic of the electricity data, can more objectively reflect the production condition of the pollution discharge enterprise, and can further infer the pollution discharge condition of the enterprise by using a statistical analysis method.
Drawings
FIG. 1 is a flow chart of a pollution discharge enterprise monitoring method based on electricity consumption data distribution;
FIG. 2 is an example of electricity usage data in an embodiment of the present invention;
FIG. 3 is an example of anomaly analysis of electricity usage data in an embodiment of the present invention;
FIG. 4 is an example of days of abnormal conditions of each sewage disposal enterprise in the observation period according to the embodiment of the present invention;
FIG. 5 is an example of observing businesses in a group of housing construction industries in an embodiment of the invention;
FIG. 6 is a graph showing the results of a regional analysis of six enterprise electricity usage outside 3 sigma of the mean value of the building construction industry in an embodiment of the present invention;
fig. 7 is a graph showing statistics of areas where six enterprise electricity usage amounts are outside 3σ of the mean value of the building industry in an embodiment of the present invention.
Detailed Description
The application is further described below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present application, and are not intended to limit the scope of the present application.
As shown in fig. 1, the pollution discharge enterprise monitoring method based on electricity consumption data distribution of the invention comprises the following steps:
step 1: screening sewage enterprises to be monitored:
in the specific implementation, enterprises closely related to the power consumption in enterprise production are screened out as enterprises to be monitored and discharged through a key pollution discharge enterprise list provided by an environmental department;
Through the relation closeness of the power proportion and the power consumption of the enterprise in the energy structure, enterprises with the power proportion exceeding 80% in the energy structure are screened to consider that the enterprise production and the power consumption are closely related, and the enterprise is used as a pollution discharge enterprise to be monitored.
Step 2: daily electricity consumption data of each sewage enterprise to be monitored in an observation time period are obtained, and the average value and standard deviation of the daily electricity consumption data in the time period are calculated;
For example: 92 pieces of electricity consumption data of the Jiangsu balance quartz Co., ltd.) were obtained from 5 months, 1 month, 7 months and 30 days in 2020, and an example of the observed values of the electricity consumption data is shown in FIG. 2.
Step 3: based on the average value and standard deviation in the step 2, setting a first interval by adopting a normal distributed 3 sigma principle, and screening a first suspected pollution discharge abnormal enterprise list by adopting a first area, wherein the method specifically comprises the following steps:
Step 3.1: setting a first interval by using a3 sigma principle of normal distribution, taking an average value plus 3 times of standard deviation as an interval upper limit and taking an average value minus 3 times of standard deviation as an interval lower limit;
Step 3.2: for each sewage enterprise to be monitored, when the electricity consumption of a certain day in the observation time period in the step 2 is outside the first area, the electricity consumption of the day is considered to exceed a conventional random fluctuation mode, and the electricity consumption is regarded as an outlier and is regarded as an abnormal condition;
Step 3.3: counting the number of days when abnormal conditions occur in each sewage enterprise to be monitored in the observation time period;
Step 3.4: sequencing the days of abnormal conditions of all the sewage enterprises to be monitored from high to low, and setting a threshold value n which is an integer smaller than the number of the sewage enterprises to be monitored and larger than zero;
And taking the enterprises arranged in the first n positions as suspected sewage abnormal enterprises, and obtaining a first suspected sewage abnormal enterprise list.
For 92 pieces of electricity consumption data of the embodiment, the average value and standard deviation of the calculated samples are 309301.09 and 14540.19 respectively, and the electricity consumption data value of a certain day is out of the interval 309301.09 +/-3× 14540.19, so that the pollution discharge enterprise can be considered to be abnormal, and further, the pollution discharge enterprise can be represented by a box graph shown in fig. 3 generated by an SAS.
The occurrence of three circles in fig. 3 indicates the occurrence of three abnormal conditions, that is, three of 92 pieces of electricity consumption data are abnormal.
Further, for all sewage enterprises to be monitored, analyzing the days of abnormal conditions in the daily electricity data of 31 days from 5 months 1 to 7 months 2020 to form a box-packed diagram as shown in fig. 4.
The dots in fig. 4 represent the number of days of the abnormal situation of each sewage disposal company during the observation period.
And sorting the days of which the abnormality occurs to all enterprises from high to low, and selecting the first n enterprises to be listed in a first abnormal enterprise list.
Wherein the value of n can be determined according to actual needs.
Step 4: grouping all the sewage enterprises to be monitored according to industries, and calculating the average value and standard deviation of the current daily electricity data for each group of enterprises day by day based on the daily electricity data obtained in the step 2;
The industry classification is carried out according to national energy agency formulated standard (NB/T33030-2018 national economy industry electricity utilization classification), so as to form, for example: industry groups of power supply, building industry, environmental management, woven garment manufacturing, and the like.
For example: the housing construction industry group includes 114 observation enterprises, an example of which is shown in fig. 5:
Step 5: based on the average value and standard deviation in the step 4, setting a second interval by adopting a normal distributed 3 sigma principle, and screening a second suspected pollution discharge abnormal enterprise list by adopting a second area, wherein the method specifically comprises the following steps:
Step 5.1: the 3 sigma principle is applied, the average value of the current day power consumption of the group is added and subtracted by 3 times of standard deviation in groups, and the standard deviation is respectively used as the upper limit and the lower limit of the section, so that a second section of each group is obtained;
Step 5.2: when the daily electricity consumption value of the enterprise in each group is outside the second interval of the group, taking the daily electricity consumption of the enterprise as an outlier, and taking the daily electricity consumption of the enterprise as an abnormal condition;
Step 5.3: counting the days of abnormal conditions of each enterprise to be monitored in the observation time period in the step 2;
step 5.4: and for all enterprises to be monitored, sorting the days of abnormal conditions of the groups according to the sequence from high to low, setting a threshold value for each group, and taking the enterprises positioned at the front threshold value in all groups as suspected abnormal sewage enterprises to obtain a second suspected abnormal sewage enterprise list.
The distribution of electricity consumption data is analyzed for 114 enterprises day by day, for example, 5 months and 1 day are taken as an example, and the enterprise electricity consumption distribution is shown in fig. 6.
From fig. 6, it can be seen that there are six areas where the enterprise electricity usage is outside 3σ of the mean value of the building industry, which is considered an abnormal situation.
The results of the daily statistics shown in fig. 7 can be analyzed for 5 months 2 days, 5 months 3 days, and 7 months 31 days in order.
Counting the abnormal days in each enterprise observation period (31 days of 1-7 months in 5 months in 2020) in the industry group, calculating the ratio of the days to the days in the observation period, setting a threshold value (generally taking the value as 30%, adjusting according to actual demands, hopefully reducing a little of suspected list enterprises, improving the ratio, otherwise reducing the ratio), taking the enterprises exceeding the threshold value as suspected pollution discharge abnormal enterprises, and obtaining a second suspected abnormal enterprise list.
Step 6: and carrying out cross verification on the first suspected abnormal sewage disposal enterprise list and the second suspected abnormal sewage disposal enterprise list to obtain a final suspected abnormal sewage disposal enterprise list.
Specifically, for electricity consumption data in the observation period of the sewage disposal enterprises in the two lists, constructing characteristic indexes of distribution of each enterprise: the mean value (x 1), the variance (x 2), the skewness coefficient (x 3) and the kurtosis coefficient (x 4), and then a cross discrimination method is used for obtaining a final suspected abnormal pollution discharge list. The method specifically comprises the following steps:
Step 6.1: taking the daily electricity data of the first suspected abnormal sewage discharge enterprise list and the second suspected abnormal sewage discharge enterprise list as two groups of samples, and respectively calculating the distribution characteristic indexes of the two groups of enterprise lists;
step 6.2: respectively calculating the distribution index centers of two groups of enterprise lists to obtain a first center value and a second center value (namely, the average value of x1-x4, wherein each group has a center and comprises the average value of four indexes, namely, the average value of each of x1-x4 in the group of data);
The first center value is:
C1＝(m1,m2,m3,m4)；
The second center value is:
C2＝(n1,n2,n3,n4)；
m i and n i represent the average of the indices x i in the first and second groups, respectively;
step 6.3: the Euclidean distance between all enterprise electricity distribution characteristic indexes in the first suspected pollution discharge abnormal enterprise list and the first central value and the Euclidean distance between the indexes and the second central value are calculated respectively, and the rest enterprises in the first group are screened and recorded, specifically:
To be used for Representing the power consumption distribution characteristic index of the ith enterprise in the first group,
Indicating Euclidean distance from the power consumption distribution characteristic index of the ith enterprise to the first center;
Indicating the euclidean distance from the ith enterprise electricity distribution index to the second center.
When (when)At this time, the ith business is removed from the first group, and otherwise remains in the first group.
Repeating the judging process for all sewage enterprises in the first group, and recording the rest enterprises in the first group;
Step 6.4: and comparing Euclidean distances between all enterprise electricity distribution characteristic indexes in the second suspected pollution discharge abnormal enterprise list and the first central value and the second central value, and screening and recording the rest enterprises in the second group, wherein the Euclidean distances between the indexes and the first central value and the second central value are specific:
To be used for Representing the power consumption distribution characteristic index of the ith enterprise in the first group,
Indicating Euclidean distance from the power consumption distribution index of the ith enterprise to the first center;
Indicating the euclidean distance from the ith enterprise electricity distribution index to the second center.
When (when)When the ith business is removed from the second group, the ith business is otherwise kept in the second group.
Repeating the judging process for all sewage enterprises in the second group, and recording the rest enterprises in the second group;
step 6.5: and merging the enterprises left in the first group and the enterprises left in the second group to obtain a suspected pollution discharge abnormal enterprise list.
The invention has now been found out by the architecture number analysis platform in the national network system, and enterprises with extremely changed electricity consumption can be found out well. The invention can be used for finding out enterprises which have extreme deviation between the previous production mode and the same line at universities. Such suspected anomalies are also reasonable for a sewage disposal enterprise. The environmental department performs anomaly investigation according to the provided suspected anomaly list, so that the efficiency and the accuracy of verification can be effectively improved.
While the applicant has described and illustrated the embodiments of the present invention in detail with reference to the drawings, it should be understood by those skilled in the art that the above embodiments are only preferred embodiments of the present invention, and the detailed description is only for the purpose of helping the reader to better understand the spirit of the present invention, and not to limit the scope of the present invention, but any improvements or modifications based on the spirit of the present invention should fall within the scope of the present invention.
Claims (4)
1. A pollution discharge enterprise monitoring method based on electricity consumption data distribution is characterized in that:
The method comprises the following steps:
step 1: screening sewage enterprises to be monitored: screening enterprises closely related to power consumption in enterprise production as enterprises to be monitored by a pollution discharge enterprise list provided by an environmental department;
Step 2: daily electricity consumption data of each sewage enterprise to be monitored in an observation time period are obtained, and the average value and standard deviation of the daily electricity consumption data in the time period are calculated;
Step 3: based on the average value and standard deviation in the step 2, setting a first interval by adopting a normal distributed 3 sigma principle, and screening a first suspected pollution discharge abnormal enterprise list by adopting the first interval, wherein the method specifically comprises the following steps:
Step 3.1: setting a first interval by using a3 sigma principle of normal distribution, taking an average value plus 3 times of standard deviation as an interval upper limit and taking an average value minus 3 times of standard deviation as an interval lower limit;
Step 3.2: for each sewage enterprise to be monitored, when the electricity consumption of a certain day in the observation time period falls outside a first interval, the electricity consumption of the day is considered to exceed a conventional random fluctuation mode, and the abnormal situation is considered;
Step 3.3: counting the number of days when abnormal conditions occur in each sewage enterprise to be monitored in the observation time period;
Step 3.4: sequencing the days of abnormal conditions of all the sewage enterprises to be monitored from high to low, and setting a threshold value n which is an integer smaller than the number of the sewage enterprises to be monitored and larger than zero;
taking the enterprises ranked in the first n positions as suspected sewage abnormal enterprises, and obtaining a first suspected sewage abnormal enterprise list;
step 4: grouping all the sewage enterprises to be monitored according to industries, and calculating the average value and standard deviation of the current daily electricity data for each group of enterprises day by day based on the daily electricity data obtained in the step 2;
step 5: based on the average value and standard deviation in the step 4, setting a second interval by adopting a normal distributed 3 sigma principle, and screening a second suspected pollution discharge abnormal enterprise list by adopting the second interval, wherein the method specifically comprises the following steps:
Step 5.1: the 3 sigma principle is applied, the average value of the current day power consumption of the group is added and subtracted by 3 times of standard deviation in groups, and the standard deviation is respectively used as the upper limit and the lower limit of the section, so that a second section of each group is obtained;
step 5.2: when the daily electricity value of the enterprise in each group is outside the second interval of the group, the daily electricity value is regarded as an abnormal condition;
Step 5.3: counting the days of abnormal conditions of each enterprise to be monitored in an observation time period;
step 5.4: for all enterprises to be monitored, sorting the days of abnormal conditions in groups according to the sequence from high to low, setting a threshold value for each group, and taking the enterprises positioned at the front threshold value in all groups as suspected abnormal sewage enterprises to obtain a second suspected abnormal sewage enterprise list;
step 6: cross-verifying the first suspected abnormal sewage discharge enterprise list and the second suspected abnormal sewage discharge enterprise list to obtain a final suspected abnormal sewage discharge enterprise list, which specifically comprises the following steps:
Step 6.1: taking daily electricity data of the first suspected abnormal sewage discharge enterprise list and the second suspected abnormal sewage discharge enterprise list as two groups of samples, and respectively calculating distribution characteristic indexes of the two groups of enterprise lists, wherein the distribution characteristic indexes comprise the mean value, variance, skewness coefficient and kurtosis coefficient of the electricity data in an observation period;
Step 6.2: respectively calculating distribution index centers of two groups of enterprise lists to obtain a first central value and a second central value, wherein the distribution index centers are average values of each group of distribution characteristic indexes;
Step 6.3: respectively calculating Euclidean distances between all enterprise electricity distribution characteristic indexes in the first suspected pollution discharge abnormal enterprise list and the first central value and the second central value, comparing the Euclidean distances between the indexes and the first central value and the second central value, and screening and recording the rest enterprises in the first group;
Step 6.4: comparing the Euclidean distance between the power distribution characteristic indexes of all enterprises in the second suspected pollution discharge abnormal enterprise list and the first central value and the Euclidean distance between the power distribution characteristic indexes and the second central value, and screening and recording the rest enterprises in the second group;
step 6.5: and merging the enterprises left in the first group and the enterprises left in the second group to obtain a suspected pollution discharge abnormal enterprise list.
2. The pollution discharge enterprise monitoring method based on electricity data distribution according to claim 1, wherein:
In step 1, enterprises with power proportion exceeding 80% in the energy structure are screened to consider that the enterprise production is closely related to the power consumption through the relation closeness of the power proportion measurement enterprise production and the power consumption in the energy structure, and the enterprises are used as sewage enterprises to be monitored.
3. The pollution discharge enterprise monitoring method based on electricity data distribution according to claim 1, wherein:
In step 4, all sewage enterprises to be monitored are grouped according to industries, and the obtained industry groups comprise power supply, house construction industry, environmental management and woven clothing manufacturing.
4. The pollution discharge enterprise monitoring method based on electricity data distribution according to claim 1, wherein:
In step 5.4, the threshold was set on a 30% basis for each group on the days of the observation period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111389019.6A CN114049033B (en) | 2021-11-22 | 2021-11-22 | Pollution discharge enterprise monitoring method based on electricity consumption data distribution |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111389019.6A CN114049033B (en) | 2021-11-22 | 2021-11-22 | Pollution discharge enterprise monitoring method based on electricity consumption data distribution |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114049033A CN114049033A (en) | 2022-02-15 |
| CN114049033B true CN114049033B (en) | 2024-06-07 |
Family
ID=80210386
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111389019.6A Active CN114049033B (en) | 2021-11-22 | 2021-11-22 | Pollution discharge enterprise monitoring method based on electricity consumption data distribution |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114049033B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115879726B (en) * | 2022-12-23 | 2023-10-31 | 中国环境科学研究院 | Enterprise production condition and emission monitoring method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488867A (en) * | 2013-07-16 | 2014-01-01 | 深圳市航天泰瑞捷电子有限公司 | Method for automatically screening abnormal electricity consumption user |
| CN103646351A (en) * | 2013-11-08 | 2014-03-19 | 安徽科蓝智能技术有限公司 | Detection method for discriminating stealing event based on metering variations in electricity, water and gas |
| CN108510006A (en) * | 2018-04-08 | 2018-09-07 | 重庆邮电大学 | A kind of analysis of business electrical amount and prediction technique based on data mining |
| CN109490651A (en) * | 2017-09-13 | 2019-03-19 | 广州小兵过河信息科技有限公司 | A kind of real-time pollution discharge monitoring system and its method |
| CN110928254A (en) * | 2019-11-13 | 2020-03-27 | 江苏三希科技股份有限公司 | Environment-friendly monitoring method and system for operation of pollution control equipment produced by pollution discharge enterprise |
| CN110990393A (en) * | 2019-12-17 | 2020-04-10 | 清华苏州环境创新研究院 | Big data identification method for abnormal data behaviors of industry enterprises |
| CN112307435A (en) * | 2020-10-30 | 2021-02-02 | 三峡大学 | Method for judging and screening abnormal electricity consumption based on fuzzy clustering and trend |
| CN112612824A (en) * | 2020-12-15 | 2021-04-06 | 重庆梅安森科技股份有限公司 | Water supply pipe network abnormal data detection method based on big data |
| CN113495912A (en) * | 2021-07-05 | 2021-10-12 | 晟至技术有限公司 | Scattered pollution enterprise accurate prevention and control monitoring method and system based on electric power data |
-
2021
- 2021-11-22 CN CN202111389019.6A patent/CN114049033B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488867A (en) * | 2013-07-16 | 2014-01-01 | 深圳市航天泰瑞捷电子有限公司 | Method for automatically screening abnormal electricity consumption user |
| CN103646351A (en) * | 2013-11-08 | 2014-03-19 | 安徽科蓝智能技术有限公司 | Detection method for discriminating stealing event based on metering variations in electricity, water and gas |
| CN109490651A (en) * | 2017-09-13 | 2019-03-19 | 广州小兵过河信息科技有限公司 | A kind of real-time pollution discharge monitoring system and its method |
| CN108510006A (en) * | 2018-04-08 | 2018-09-07 | 重庆邮电大学 | A kind of analysis of business electrical amount and prediction technique based on data mining |
| CN110928254A (en) * | 2019-11-13 | 2020-03-27 | 江苏三希科技股份有限公司 | Environment-friendly monitoring method and system for operation of pollution control equipment produced by pollution discharge enterprise |
| CN110990393A (en) * | 2019-12-17 | 2020-04-10 | 清华苏州环境创新研究院 | Big data identification method for abnormal data behaviors of industry enterprises |
| CN112307435A (en) * | 2020-10-30 | 2021-02-02 | 三峡大学 | Method for judging and screening abnormal electricity consumption based on fuzzy clustering and trend |
| CN112612824A (en) * | 2020-12-15 | 2021-04-06 | 重庆梅安森科技股份有限公司 | Water supply pipe network abnormal data detection method based on big data |
| CN113495912A (en) * | 2021-07-05 | 2021-10-12 | 晟至技术有限公司 | Scattered pollution enterprise accurate prevention and control monitoring method and system based on electric power data |
Non-Patent Citations (1)
| Title |
|---|
| 环保用电监控***初探;苗刚松;马雪梅;;现代信息科技(第07期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114049033A (en) | 2022-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110824270B (en) | Electricity stealing user identification method and device combining transformer area line loss and abnormal events | |
| CN110689279B (en) | Analysis method for potential safety hazards of residential electricity | |
| CN109948877B (en) | Power consumption anomaly accurate analysis method based on anomaly event combination | |
| CN110927654B (en) | Batch running state evaluation method for intelligent electric energy meters | |
| CN108898311A (en) | A kind of data quality checking method towards intelligent distribution network repairing dispatching platform | |
| CN110119755A (en) | Electricity method for detecting abnormality based on Ensemble learning model | |
| CN116073372A (en) | Intelligent electricity utilization-based safety monitoring management system and method | |
| CN112863134A (en) | Intelligent diagnosis system and method for rural sewage treatment facility abnormal operation | |
| CN113221931B (en) | Electricity stealing prevention intelligent identification method based on electricity utilization information acquisition big data analysis | |
| CN105303331A (en) | Transformer repair risk decision-making method | |
| CN213750303U (en) | Electric energy metering abnormity diagnosis system based on electricity consumption information acquisition system | |
| CN114049033B (en) | Pollution discharge enterprise monitoring method based on electricity consumption data distribution | |
| CN111582568A (en) | Electric power data-based enterprise rework prediction method during spring festival | |
| CN116882946B (en) | Intelligent management system and method based on power generation enterprise data | |
| CN114169424A (en) | Discharge capacity prediction method based on k nearest neighbor regression algorithm and electricity utilization data | |
| CN111177128B (en) | Metering big data batch processing method and system based on improved outlier detection algorithm | |
| CN115018384A (en) | Building site security risk assessment method and system | |
| CN110426996B (en) | Environmental pollution monitoring method based on big data and artificial intelligence | |
| CN114371438B (en) | Measuring equipment misalignment judgment method based on Internet of things | |
| CN111612019A (en) | Method for identifying and analyzing fault abnormality of intelligent electric meter based on big data model | |
| CN112036725A (en) | Electric energy meter fault identification method | |
| CN109409629B (en) | Acquisition terminal manufacturer evaluation method based on multi-attribute decision model | |
| CN109035062A (en) | A kind of client's electricity charge anomaly analysis and tactful application system | |
| CN116167659B (en) | Carbon market carbon emission data quality evaluation method | |
| CN105678386B (en) | Method for determining the time availability of a wind energy plant |
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 |