CN113792988B - Enterprise online monitoring data anomaly identification method - Google Patents
Enterprise online monitoring data anomaly identification method Download PDFInfo
- Publication number
- CN113792988B CN113792988B CN202110974638.5A CN202110974638A CN113792988B CN 113792988 B CN113792988 B CN 113792988B CN 202110974638 A CN202110974638 A CN 202110974638A CN 113792988 B CN113792988 B CN 113792988B
- Authority
- CN
- China
- Prior art keywords
- production
- enterprise
- data
- abnormal
- electricity consumption
- 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
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000012544 monitoring process Methods 0.000 title claims abstract description 43
- 238000004519 manufacturing process Methods 0.000 claims abstract description 181
- 230000005611 electricity Effects 0.000 claims abstract description 99
- 230000002159 abnormal effect Effects 0.000 claims abstract description 97
- 230000000694 effects Effects 0.000 claims abstract description 44
- 230000008859 change Effects 0.000 claims abstract description 19
- 238000001514 detection method Methods 0.000 claims abstract description 7
- 238000010219 correlation analysis Methods 0.000 claims abstract description 6
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 239000003344 environmental pollutant Substances 0.000 claims description 49
- 231100000719 pollutant Toxicity 0.000 claims description 49
- 230000008569 process Effects 0.000 claims description 26
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 19
- 239000001301 oxygen Substances 0.000 claims description 19
- 229910052760 oxygen Inorganic materials 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 15
- 230000005856 abnormality Effects 0.000 claims description 14
- 239000013598 vector Substances 0.000 claims description 13
- 239000002912 waste gas Substances 0.000 claims description 11
- 239000007789 gas Substances 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 4
- 239000000356 contaminant Substances 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000005452 bending Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 125000004122 cyclic group Chemical group 0.000 claims description 2
- 238000007599 discharging Methods 0.000 claims description 2
- 230000007812 deficiency Effects 0.000 claims 1
- 230000001360 synchronised effect Effects 0.000 claims 1
- 230000009467 reduction Effects 0.000 abstract description 4
- 238000003912 environmental pollution Methods 0.000 description 3
- 239000000779 smoke Substances 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 1
- 101150087426 Gnal gene Proteins 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009960 carding Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 239000003546 flue gas Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000011160 research 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
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
An enterprise online monitoring data anomaly identification method comprises the following steps: 1) Acquiring enterprise online data and sub-meter electricity metering data, and preprocessing to obtain enterprise activity data; 2) Generating a self-adaptive sliding window, and performing high-value detection on enterprise activity data in the window to obtain a high-low value sequence; 3) Carrying out correlation analysis on the high-low value sequence data obtained in the step 2 to obtain correlation results among the data; 4) Calling corresponding judgment logic according to the corresponding enterprise abnormal characteristics; 5) And judging the abnormal situation and type of the enterprise activity. The electric quantity data is introduced, so that the monitoring data are mutually evidence, and the reliability of the identification result is improved; the self-adaptive sliding window is generated, the recognition capability of abnormally high values is improved, and the result accuracy is improved; establishing judgment logic for online data anomaly identification; the method realizes the identification of the implementation condition of the production reduction and limit measures of enterprises, the change condition of the real emission amount and the abnormal operation of production and treatment facilities for the first time.
Description
Technical Field
The invention relates to the field of environmental pollution early warning, in particular to an enterprise online monitoring data anomaly identification method.
Background
The exhaust gas monitoring of industrial enterprises mainly comprises monitoring of flue gas, namely exhaust gas and process exhaust gas discharged by industrial boilers and kilns. Based on the on-line data and the electricity consumption data of the industrial enterprises, the pollutant emission characteristics of various industries, production and treatment processes are analyzed, the abnormal characteristics of the on-line data of the industrial enterprises are fully excavated, the production emission rules of the industrial enterprises are summarized, the environment monitoring behaviors can be effectively standardized, and pollution problems can be timely found.
However, the current process of finding out environmental pollution problems based on massive monitoring data requires a great deal of manpower and time, has high technical level and experience dependence on researchers, has low efficiency of the whole application process, has poor timeliness and is limited by the technical level, and the environment management is difficult to effectively support. The method provides support for scientifically supervising the atmospheric pollution emission of industrial enterprises and effectively improving the regional air quality, and needs a method capable of efficiently and rapidly identifying the abnormal monitoring data of the industrial enterprises.
Many data processing methods have been developed for this industry, such as CN110245880a entitled: a pollution source online monitoring data cheating identification method and CN110990393A are named as follows: the method is mainly characterized in that the method is used for carrying out statistics and analysis on online monitoring data, is only used for identifying fake monitoring data, does not relate to the problem of environmental pollution, and has certain limitation on identification function.
Disclosure of Invention
In order to solve the problems, the invention mainly aims to provide an enterprise online monitoring data anomaly identification method.
In order to solve the problems, the invention provides an enterprise online monitoring data anomaly identification method, which comprises the following steps:
1) Acquiring enterprise pollutant parameter data and electricity consumption parameter data, and preprocessing to obtain enterprise activity data: accessing contaminant parameter data and electricity consumption parameter data of an enterprise, and storing by using datatab l e; the steps may include:
(1) Longitudinally processing pollutant parameter data and electricity consumption parameter data to obtain pollutant parameters such as exhaust emission (m 3), smoke concentration (mg/m 3)、SO2 concentration (mg/m 3), NOx concentration (mg/m 3), electricity consumption of production facilities, electricity consumption of treatment facilities, and basic information parameters such as enterprise names, outlet names, production facilities names, exhaust treatment facility names, monitoring time, monitoring point names, and the like;
(2) Matching the processed pollutant parameter data with electricity consumption parameter data, and screening out the gas-related enterprises to be monitored and the corresponding information: the name of the discharge port, the electricity consumption of the production facility and the electricity consumption of the treatment facility;
(3) The enterprise online data are transversely processed, enterprise discharge ports with serious enterprise pollutant parameter data loss and corresponding discharge amount are screened out, enterprise discharge ports with too little continuous hour data are removed, and enough data enter in the early stage of a sliding window in the second step;
(4) Performing cubic spline interpolation on the data of the enterprise and the corresponding missing discharge pollutant parameters after the cleaning in the steps: forming a smooth curve passing through a series of shape value points, and obtaining a curve function set by solving a three bending moment equation set;
(5) And forming pollutant parameter time series activity data corresponding to different discharge ports of different enterprises, and producing facility electricity consumption and processing facility electricity consumption time series activity data matched with the discharge ports.
2) Generating a self-adaptive sliding window, and performing high-value detection on enterprise activity data in the window to obtain a high-low value sequence;
Wherein, the adaptive sliding window method identifies high values: the method is characterized in that the window size and the threshold variable setting are adjusted according to different data types of different enterprises and by combining the generation process characteristics and the data change rules shown in daily production activities, the effective identification characteristic high value is determined, and the sliding window of the characteristics is set up according to different enterprise types;
3) Carrying out correlation analysis on the high-low value sequence data obtained in the step 2 to obtain correlation results among the data;
4) Calling corresponding judgment logic according to the corresponding enterprise abnormal characteristics;
In this step, it is preferable that: the method comprises the steps of analyzing pollutant parameter information such as pollutant concentration, exhaust emission, oxygen content and the like of an enterprise online monitoring system, classifying changes of electricity consumption of production facilities of an electricity metering system, electricity consumption of treatment facilities and the like, carding logic relations among the above parameters and corresponding abnormal characteristics of the enterprise in the production and production stopping processes of the enterprise, and obtaining a judgment logic library of the abnormal characteristics of the enterprise. Calling corresponding judgment logic according to the abnormal characteristics of the enterprise;
according to the production and production stopping states marked by the online monitoring system, enterprise activity data are divided into two types, namely production logic and production stopping logic, the production logic is called to judge when the enterprise activity data are in the production state, and the production stopping logic is called to judge when the enterprise activity data are in the production stopping state;
5) And judging the abnormal situation and the abnormal type of the enterprise activity.
Preferably, the steps of judging the abnormal situation and type of the enterprise activity are as follows:
Based on the obtained activity data such as the enterprise pollutant parameters and the electricity consumption parameters, the judgment logic of the enterprise abnormal characteristics is called to analyze whether the enterprise activity is abnormal or not, and the abnormal types (abnormal rise A, abnormal rise B, abnormal production A, abnormal production B and abnormal production stopping) are judged.
(1) Abnormal elevation a (data false): the pollutant concentration is not in accordance with the logic of the exhaust emission, the electricity consumption of the production facilities, the electricity consumption of the treatment facilities and the like.
(2) Abnormal elevation B: the treatment measures do not match the production load;
Production abnormality: the data representing the production load is not matched, namely the discharge amount of the waste gas of enterprises is inconsistent with the electricity consumption of production facilities.
(3) Production anomaly a: the exhaust emission is abnormally low.
(4) Production anomaly B: the exhaust emission is abnormally high.
(5) Abnormal production stopping:
If the parameters such as oxygen content, pollutant concentration, exhaust emission, electricity consumption of production facilities and the like in the production stopping process are not in accordance with any conditions of the normal production stopping condition, judging that the production stopping is abnormal.
The beneficial effects of the invention are that the technical scheme has the following advantages:
1. On the basis of pollutant parameters, electricity consumption parameters are introduced, so that monitoring data of two relatively independent systems are mutually evidence, and the reliability of the identification result is improved;
2. The self-adaptive sliding window is generated to carry out high-value detection on enterprise activity data in the window, so that the recognition capability of abnormal high values is improved, and the result accuracy is improved;
3. Based on case research, summarizing abnormal discharge behaviors of enterprises, refining manual judgment experience, and establishing judgment logic for online data abnormal recognition;
4. The method realizes the identification of the implementation condition of the production reduction and limit measures of enterprises, the change condition of the real emission amount and the abnormal operation of production and treatment facilities for the first time.
Drawings
FIG. 1 is a flowchart of an abnormality identification method for online monitoring data of an enterprise according to the present invention.
Fig. 2 is a schematic diagram of a smooth curve formed by Cub I C SP L I NE I NTE rpo l at i on performed on the cleaned enterprise and the data corresponding to the missing discharge heavy point parameters.
Detailed Description
The technical scheme of the invention is further specifically described below through examples and with reference to the accompanying drawings.
The concept and the related technical characteristic data mainly comprise:
The data source is enterprise activity data and comprises pollutant parameters, state parameters, electricity consumption parameters and basic information parameters. The pollutant parameters include, but are not limited to, exhaust emission (m 3), smoke concentration (mg/m 3)、SO2 concentration (mg/m 3), NOx concentration (mg/m 3), TVOC (ppm), state parameters including, but not limited to, temperature, pressure, flow rate, oxygen content, humidity of the smoke, production/shutdown state of the production facility, production/shutdown state of the exhaust treatment facility, electricity consumption parameters, electricity consumption of the production facility, electricity consumption of the treatment facility, basic information parameters, enterprise name, outlet name, production facility name, name of the exhaust treatment facility, monitoring point name, and monitoring time.
Anomaly identification algorithm: acquiring enterprise activity data through online data acquisition and preprocessing based on pollutant parameters and state parameters of enterprise online data, power consumption of production facilities, power consumption of processing facilities and other power consumption parameters; performing high-value detection on enterprise activity data by using a self-adaptive sliding window algorithm to obtain a high-low value sequence; carrying out correlation analysis on the high-low value sequences to obtain correlation results among the data; and calling corresponding judgment logic according to the corresponding abnormal characteristics of the enterprises, and judging whether the enterprises have abnormal emission conditions according to the production process and the treatment process characteristics of different industries.
The function is as follows: identifying enterprise data counterfeiting, pushing the enterprise data counterfeiting to an environment management department, and assisting law enforcement supervision; identifying the implementation situation of the yield reduction measures, pushing the implementation situation to an environment management department, and assisting law enforcement supervision; the emission amount change is found, and the source of the pollution of the air quality is traced; the abnormal facilities are found and pushed to enterprises, so that the process optimization and the maintenance of the enterprises are assisted, and the energy conservation and emission reduction of the enterprises are supported.
Referring to fig. 1, a flowchart of an enterprise online monitoring data anomaly identification method according to the present invention mainly includes the steps of:
1) Starting;
2) Accessing enterprise online data and sub-meter electricity metering data, and preprocessing to obtain enterprise activity data;
3) Generating a self-adaptive sliding window, and performing high-value detection on enterprise activity data in the window to obtain a high-low value sequence;
4) Performing correlation analysis on the high-low value sequence data to obtain a correlation result;
5) Calling corresponding judgment logic according to the corresponding enterprise abnormal characteristics;
6) Judging whether enterprise activity data belong to abnormality or not, and giving an abnormality class;
7) And (5) ending.
The following examples are illustrative of the invention and are not intended to limit the scope of the invention.
In this embodiment, the method for identifying the abnormality of the online data of the enterprise comprises the following specific steps:
1. accessing enterprise online data and sub-meter electricity metering data, and preprocessing to obtain enterprise activity data:
accessing enterprise online data and sub-meter electricity metering data, and storing by using datatab l e:
(1) Longitudinally processing enterprise online data to obtain pollutant parameters such as SO 2 monitoring concentration data, NOx monitoring concentration data, exhaust emission and the like which change along with the hour, and corresponding basic information parameters such as enterprise names, exhaust names, monitoring time, oxygen content, whether to stop running and the like; and longitudinally processing the meter-dividing electricity metering data to obtain electricity consumption parameters such as production facilities and processing facilities power and basic information parameters such as enterprise names, facility types, monitoring point names, acquisition time and the like.
(2) And matching the processed enterprise online data with the sub-meter electricity metering data, and screening out corresponding information such as the gas-related enterprises to be monitored, the corresponding discharging ports, the electricity consumption of production facilities, the electricity consumption of processing facilities and the like.
(3) Transversely processing enterprise online data
And (3) screening out enterprise discharge ports with serious pollutant parameters (SO 2 or NOx and exhaust emission) and corresponding emission amounts (more than 80% of pollutant parameter hour data are lost), and removing enterprise discharge ports with too little continuous hour data (removing enterprise discharge ports with too few lines, such as enterprise discharge ports with the line number less than 100), SO that enough data can enter in the early stage of a sliding window in the second step.
(4) And (3) performing Cub I C SP L I NE I nterpo l at i on (cubic spline interpolation) on the data of the enterprise and the corresponding missing discharge pollutant parameters after the cleaning in the steps: and obtaining a smooth curve passing through a series of shape value points, and then obtaining a curve function set by solving a three bending moment equation set.
And after the interpolation is completed, forming pollutant parameter time series activity data corresponding to different discharge ports of different enterprises, and producing facilities and processing facilities matched with the discharge ports with electric power time series activity data.
2. Generating a self-adaptive sliding window, carrying out high-value detection on enterprise activity data in the window to obtain a high-low value sequence,
The adaptive sliding window method identifies high values: the method is characterized in that the window size and the threshold variable setting are adjusted according to different data types of different enterprises and by combining the generation process characteristics and the data change rules shown in daily production activities, the effective identification characteristic high value is determined. A sliding window of features is set up for different enterprise types.
The activity data in the step 1 is calculated in a sliding window: let the initial sliding window size be n (the characteristic case that the sliding window size needs to be set to match the active data vector), let the signal vector s i gnal s=0, … … 0 (length is the active data vector length L), let the initial sliding window size variable n, the threshold variable th resho L d, the peak clipping variable i nf L uence, let the active data vector F I L TEREDY =y (1), … … y (n) in the sliding window need to calculate the arithmetic mean value in the current window:
standard deviation within the current window:
The absolute value of the difference between the first data y (n+i) outside the current window (i=1 … … L-n) and the mean of the active data in the current sliding window:
d i ff(n+i)＝|y(n+i)-avgFi lter(n)| (3)
size of data vector fluctuation in window:
f l uctuate(n)＝thresho l d*stdF i lter(n) (4)
If diff (n+i) > f l uctuate and y (n+i) > AVGF I LTER (n) are satisfied, let the signal value of the n+i-th data be 1 (peak signal), if d iff (n+i) > f l uctuate and y (n+i) < AVGF I LTER (n) at this time, let the signal value of the n+i-th data be-1 (trough signal), peak clipping and assignment are performed on the F I L TEREDY (n+i) variable after the above procedure:
fi lteredY(n+i)＝influence*y(n+i)+(1-influence)*fi lteredY(n)(5)
if diff (n+i) < f l uctuate is satisfied, the signal value of the n+i-th data is set to 0 (wave flat signal), and F I L TEREDY (n+i) is assigned to y (n+i):
fi l teredY(n+i)＝y(n+i) (6)
and (3) cyclic calculation: the window is moved back by one unit data as a whole, and the values of (1) to (6) of the new window are calculated to obtain the signal value of the next data until the calculation of the data vector of the length L is completed and the final signal vector s igna L s is obtained.
3. And (3) carrying out correlation analysis on the high-low value sequence data obtained in the step (2) to obtain correlation results among the data.
4. According to the corresponding abnormal characteristics of the enterprise, invoking corresponding judgment logic,
The method comprises the steps of analyzing the actually measured concentration of pollutants, the exhaust emission and the oxygen content of an enterprise online monitoring system, classifying the change conditions of electricity consumption of a production facility, the electricity consumption of a processing facility and other electricity consumption parameters of a meter electricity metering system, combing the logic relation among the above parameters and the corresponding abnormal characteristics of the enterprise in the production and production stopping process, and obtaining a judgment logic library of the abnormal characteristics of the enterprise. And calling corresponding judgment logic according to the abnormal characteristics of the enterprise.
And according to the production and production stopping states marked by the online monitoring system, enterprise activity data are divided into two types, namely production logic and production stopping logic, the production logic is called to judge when the enterprise activity data are in the production state, and the production stopping logic is called to judge when the enterprise activity data are in the production stopping state.
(1) Enterprise production logic determination:
The first step: and judging whether the change trend of the hour data of the electricity consumption and the exhaust emission of the enterprise production facility changes synchronously (ascending/unchanged/descending), if not, namely, the change of the two factors representing the production load, namely, the exhaust emission and the facility electricity consumption, is inconsistent, and judging that the production logic of the enterprise is not met. If the synchronization is performed, the second step is entered.
And a second step of: and judging whether the change trend of the electricity consumption and the exhaust emission of the treatment facility changes synchronously, if so, judging that the electricity consumption and the exhaust emission meet the production emission logic of enterprises, and if not, judging that the electricity consumption and the exhaust emission logic do not meet the production emission logic.
And a third step of: and (5) judging the abnormal emission type by analyzing the change relation among the parameters, and entering the steps (1) - (4).
(2) And (3) judging the enterprise production stopping logic:
The first step: when the oxygen content is 19.5% -22.0%, the pollutant concentration is far lower than the normal production emission (< average of 20% of historical production), the exhaust emission is 0 or far lower than the normal production emission (< average of 20% of historical production), the electricity consumption for production is 0 or far lower than the normal electricity consumption level (< average of 20% of historical production), and the normal production is judged to be stopped.
And a second step of: if any condition which does not accord with the normal production stopping appears in the production stopping process, the abnormal production stopping is judged. Note that: the process of stopping or starting up is carried out 5 hours before stopping production and 5 hours before ending, and the fluctuation (higher parameters) of the oxygen content, the exhaust emission and the pollutant concentration is reduced or increased is caused, so that the method belongs to the normal condition.
And a third step of: and (5) judging the type of abnormal production stopping by analyzing the data change conditions of the oxygen content, the pollutant concentration, the exhaust emission and the electricity consumption of the production facilities, and entering a step (5).
5. Judging the abnormal condition and type of the enterprise activity,
Based on the obtained enterprise online data, power consumption and other activity data, invoking judgment logic of enterprise abnormal characteristics to analyze whether enterprise activities are abnormal, and judging the abnormal types (abnormal rise A, abnormal rise B, abnormal production A, abnormal production B and abnormal production stopping).
(1) Abnormal elevation a (data false): the pollutant concentration is not in accordance with the logic of the exhaust emission, the electricity consumption of the production facilities, the electricity consumption of the treatment facilities and the like.
① And when the waste gas emission amount of the enterprise and the electricity consumption data of the production facilities are unchanged, the electricity consumption of the treatment facilities is increased, the concentration of pollutants is increased, and the abnormal increase A is judged.
② And when the waste gas emission of enterprises and the electricity consumption data of production facilities are reduced, the electricity consumption of the treatment facilities is unchanged, the concentration of pollutants is increased, and the abnormal increase A is judged.
(2) Abnormal elevation B: the treatment measures do not match the production load.
① When the waste gas emission amount of the enterprise is increased, the electricity consumption of the production facility is increased, but the electricity consumption of the treatment facility is unchanged or reduced, so that the concentration of pollutants is increased, and the abnormal increase B is judged.
② And when the waste gas emission amount of the enterprise and the electricity consumption of the production facility are unchanged, the electricity consumption of the treatment facility is reduced, the concentration of pollutants is increased, and the abnormal increase B is judged.
Production abnormality: the data representing the production load is not matched, namely the discharge amount of the waste gas of enterprises is inconsistent with the electricity consumption of production facilities.
(3) Production anomaly a: the exhaust emission is abnormally low.
① When the electricity consumption of the enterprise production facility is increased, the exhaust emission is unchanged or reduced, and the production abnormality A is judged.
② And when the electricity consumption of the enterprise production facilities is unchanged, the exhaust emission is reduced, and the production abnormality A is judged.
(4) Production anomaly B: the exhaust emission is abnormally high.
① And when the electricity consumption of the enterprise production facilities is unchanged and the exhaust emission is increased, judging that the production is abnormal B.
② And when the electricity consumption of the enterprise production facility is reduced and the exhaust emission is increased or unchanged, judging that the production is abnormal B.
(5) Abnormal production stopping:
If the parameters such as oxygen content, pollutant concentration, exhaust emission, electricity consumption of production facilities and the like in the production stopping process are not in accordance with any conditions of the normal production stopping condition, judging that the production stopping is abnormal.
① Abnormal production shutdown-abnormal oxygen content
And in the process of stopping production, the oxygen content is unchanged or is lower than 19.5%, and the abnormal oxygen content is judged.
② Abnormal production shutdown-abnormal contaminant concentration
And in the production stopping process, the concentration of the pollutants is unchanged or higher than the normal production emission, and the abnormal concentration of the pollutants is judged.
③ Abnormal production stoppage-abnormal exhaust emission
In the production stopping process, the exhaust emission is unchanged or higher than the normal production emission, and the exhaust emission is judged to be abnormal.
④ Abnormal production stoppage-abnormal electricity consumption
In the production stopping process, the electricity consumption of the production facilities is unchanged or higher than the normal production emission, and the electricity consumption is judged to be abnormal.
In addition: the process of stopping or starting up is carried out 5 hours before stopping production and 5 hours before ending, and the fluctuation (higher parameters) of the oxygen content, the exhaust emission and the pollutant concentration is reduced or increased is caused, so that the method belongs to the normal condition.
The above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the specific embodiments of the present invention without departing from the spirit and scope of the present invention, and all modifications and equivalents are intended to be included in the scope of the claims of the present invention.
Claims (7)
1. An enterprise online monitoring data anomaly identification method is characterized by comprising the following steps:
1) Acquiring enterprise online data and sub-meter electricity metering data, and preprocessing to obtain enterprise activity data;
It comprises:
(1) Longitudinally processing enterprise online data to obtain enterprise online pollutant parameters changing along with the hour and enterprise online basic information parameters corresponding to the enterprise online pollutant parameters; longitudinally processing the sub-meter electricity metering data to obtain sub-meter electricity metering electricity consumption parameters and corresponding sub-meter electricity metering basic information parameters;
(2) Matching the processed enterprise online data with the sub-meter electricity metering data, and screening out the air-related enterprises to be monitored and the corresponding information: discharging port, electricity consumption of production facilities and electricity consumption of treatment facilities;
(3) The enterprise online data are transversely processed, enterprise discharge ports with serious enterprise online pollutant parameter deficiency and corresponding discharge amount are screened out, enterprise discharge ports with too few continuous hours of data are removed, and enough data enter in the early stage of a sliding window in the second step;
(4) Performing cubic spline interpolation on the data of the online main parameter missing of the enterprise and the corresponding outlet enterprise after the cleaning in the steps: forming a smooth curve passing through a series of shape value points, and obtaining a curve function set by solving a three bending moment equation set;
(5) Forming key parameter time series activity data corresponding to different discharge ports of different enterprises, and producing facilities and processing facilities matched with the discharge ports by using the key parameter time series activity data;
2) Generating a self-adaptive sliding window, and performing high-value detection on enterprise activity data in the window to obtain a high-low value sequence;
3) Performing correlation analysis on the high-low value sequence data obtained in the step 2) to obtain correlation results among the data;
4) Calling corresponding judgment logic according to the corresponding enterprise abnormal characteristics;
5) And judging the abnormal situation and the abnormal type of the enterprise activity.
2. The method for identifying abnormality of online monitoring data of an enterprise according to claim 1, wherein the online contaminant parameters of the enterprise include SO 2 monitoring concentration data, NOx monitoring concentration data and exhaust emission, and the online basic information parameters of the enterprise include: the enterprise name, the outlet name, the monitoring time, the oxygen content and whether the operation is stopped or not which correspond to the online pollutant parameters of the enterprise; the sub-meter electricity metering and consumption parameters comprise production facility and processing facility power, and the sub-meter electricity metering and consumption basic information parameters comprise enterprise names, facility types, monitoring point names and acquisition time.
3. The method for identifying the abnormality of the online monitoring data of the enterprise according to claim 1, wherein the method comprises the following steps: in the step 2), a self-adaptive sliding window method is adopted to identify high values: according to different data types of different enterprises, the window size and the threshold variable setting are adjusted by combining the generation process characteristics and the data change rules shown in daily production activities, the effective identification characteristic high value is determined, and the sliding window of the characteristics is established according to different enterprise types.
4. The method for identifying the abnormality of the online monitoring data of the enterprise according to claim 1, wherein the specific steps of the step 2) are as follows:
The activity data in the step 1 is calculated in a sliding window: let the initial sliding window size be n, let the signal vectors signal=0, … … 0, length be the active data vector length L, let the initial sliding window size variable n, threshold variable threshold, peak clipping variable index, let the active data vector FILTEREDY =y (1), … … y (n) in the sliding window, need to calculate the arithmetic mean in the current window:
standard deviation within the current window:
The absolute value of the difference between the first data y (n+i) outside the current window, i= … … L-n and the mean of the active data in the current sliding window:
diff(n+i)＝|y(n+i)-avgFilter(n)|(3)
size of data vector fluctuation in window:
fluctuate(n)＝threshold*stdFilter(n)(4)
If diff (n+i) > fluctuate and y (n+i) > AVGFILTER (N) are satisfied, the signal value of the n+i data is set to 1, namely, the peak signal, if diff (n+i) > fluctuate and y (n+i) < AVGFILTER (N) are set at this time, the signal value of the n+i data is set to-1, namely, the trough signal, the FILTEREDY (n+i) variable is subjected to peak clipping and assignment after the above process:
filteredY(n+i)＝influence*y(n+i)+(1-influence)*filteredY(n)(5)
If diff (n+i) < fluctuate is satisfied, the signal value of the n+i-th data is set to 0, that is, the wave level signal, and FILTEREDY (n+i) is assigned as y (n+i):
filteredY(n+i)＝y(n+i)(6)
And (3) cyclic calculation: and moving the whole window backwards by one unit data, and calculating the values of (1) to (6) of the new window to obtain the signal value of the next data until the calculation of the data vector with the length of L is completed and the final signal vector is obtained.
5. The method for identifying anomalies in online monitoring data of an enterprise according to any one of claims 1-4, wherein the determining logic in step 4):
the method comprises the steps of analyzing enterprise online pollutant parameters of an enterprise online monitoring system, combing logic relations among the parameters and corresponding abnormal characteristics of an enterprise in the production and production stopping processes of the enterprise according to the change condition of the sub-meter electricity consumption parameters of the sub-meter electricity consumption system, obtaining a judgment logic library of the abnormal characteristics of the enterprise, and calling corresponding judgment logic according to the abnormal characteristics of the enterprise;
And according to the production and production stopping states marked by the online monitoring system, enterprise activity data are divided into two types, namely production logic and production stopping logic, the production logic is called to judge when the enterprise activity data are in the production state, and the production stopping logic is called to judge when the enterprise activity data are in the production stopping state.
6. The method for identifying anomalies in online monitoring data of an enterprise according to claim 5, wherein in step 5), the anomaly types include: abnormal elevation A, abnormal elevation B, abnormal production A, abnormal production B, and abnormal production stopping;
Wherein:
(1) Abnormal elevation a: the pollutant concentration is logically different from the exhaust emission, the electricity consumption of the production facility and the electricity consumption of the treatment facility,
① When the waste gas emission of enterprises and the electricity consumption data of production facilities are unchanged, the electricity consumption of the treatment facilities is increased, the concentration of pollutants is increased, the abnormal increase A is judged,
② When the waste gas emission of enterprises and the electricity consumption data of production facilities are reduced, the electricity consumption of the treatment facilities is unchanged, the concentration of pollutants is increased, and the abnormal increase A is judged;
(2) Abnormal elevation B: the processing measures do not match the production load,
① When the waste gas emission of enterprises is increased, the electricity consumption of production facilities is increased, but the electricity consumption of treatment facilities is unchanged or reduced, the concentration of pollutants is increased, the abnormal increase B is judged,
② When the waste gas emission of enterprises and the electricity consumption of production facilities are unchanged, the electricity consumption of treatment facilities is reduced, the concentration of pollutants is increased, and the abnormal increase B is judged;
(3) Production anomaly a: the exhaust gas emission amount is abnormally low and is discharged,
① When the electricity consumption of the enterprise production facility is increased, the exhaust emission is unchanged or reduced, the production abnormality A is judged,
② When the electricity consumption of the enterprise production facilities is unchanged and the exhaust emission is reduced, judging that the production is abnormal A;
(4) Production anomaly B: the exhaust gas emission amount is abnormally high and is discharged,
① When the electricity consumption of the enterprise production facilities is unchanged and the exhaust emission is increased, judging that the production is abnormal B,
② When the electricity consumption of the enterprise production facility is reduced and the exhaust emission is increased or unchanged, judging that the production is abnormal B;
(5) Abnormal production stopping:
① Abnormal production shutdown-abnormal oxygen content
In the process of stopping production, the oxygen content is unchanged or lower than 19.5 percent, the oxygen content is judged to be abnormal,
② Abnormal production shutdown-abnormal contaminant concentration
In the production stopping process, the concentration of the pollutant is unchanged or higher than the normal production emission, the pollutant concentration is judged to be abnormal,
③ Abnormal production stoppage-abnormal exhaust emission
In the production stopping process, the exhaust emission is unchanged or higher than the normal production emission, the exhaust emission is judged to be abnormal,
④ Abnormal production stoppage-abnormal electricity consumption
In the production stopping process, the electricity consumption of the production facilities is unchanged or higher than the normal production emission, and the electricity consumption is judged to be abnormal.
7. The method for identifying the abnormality of the online monitoring data of the enterprise according to claim 6, wherein the method comprises the following steps:
The production logic judging step is as follows:
the first step: judging whether the change trend of the hour data of the electricity consumption and the exhaust emission of the enterprise production facility changes synchronously or not: if the two factors of the waste gas emission quantity representing the production load and the facility electricity consumption change are not consistent, judging that the two factors do not accord with the production logic of an enterprise, and if the two factors are synchronous, entering a second step;
and a second step of: judging whether the change trend of the electricity consumption and the exhaust emission of the treatment facility changes synchronously, if so, judging that the electricity consumption and the exhaust emission meet the production emission logic of enterprises, and if not, judging that the electricity consumption and the exhaust emission logic do not meet the production emission logic;
and a third step of: judging the abnormal emission type by analyzing the change relation among the parameters, and entering the steps (1) - (4) in the step (5);
The production stopping logic judging steps are as follows:
the first step: when the oxygen content is 19.5% -22.0%, the pollutant concentration is far lower than the normal production emission: < average production 20%, exhaust emissions 0 or far lower than normal production emissions: < average of historical production 20% or production power usage is 0 or far below normal power usage level: < 20% of the historical production on average, judging that the production is stopped normally;
and a second step of: if any condition which does not accord with normal production stopping appears in the production stopping process, judging that the production stopping is abnormal;
And a third step of: determining the type of the production stopping abnormality by analyzing the data change conditions of the oxygen content, the pollutant concentration, the exhaust emission and the electricity consumption of the production facility, and proceeding to (5) in the step 5).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110974638.5A CN113792988B (en) | 2021-08-24 | 2021-08-24 | Enterprise online monitoring data anomaly identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110974638.5A CN113792988B (en) | 2021-08-24 | 2021-08-24 | Enterprise online monitoring data anomaly identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113792988A CN113792988A (en) | 2021-12-14 |
| CN113792988B true CN113792988B (en) | 2024-07-12 |
Family
ID=78876360
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110974638.5A Active CN113792988B (en) | 2021-08-24 | 2021-08-24 | Enterprise online monitoring data anomaly identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113792988B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114723262A (en) * | 2022-03-31 | 2022-07-08 | 山东省济南生态环境监测中心 | Emission reduction accounting and control method for industrial enterprise during emergency response period of heavy pollution weather |
| CN114693166A (en) * | 2022-04-22 | 2022-07-01 | 北京中科三清环境技术有限公司 | Method and device for monitoring execution condition of emergency emission reduction measure on line and electronic equipment |
| CN115238753B (en) * | 2022-09-21 | 2022-12-06 | 西南交通大学 | Self-adaptive SHM data cleaning method based on local outlier factor |
| CN115689396B (en) * | 2022-12-30 | 2023-08-08 | 天津友美环保科技有限公司 | Pollutant emission control method, device, equipment and medium |
| CN117237165B (en) * | 2023-09-22 | 2024-05-07 | 中节能数字科技有限公司 | Method for detecting fake data |
| CN117609928B (en) * | 2024-01-23 | 2024-04-05 | 华北电力科学研究院有限责任公司 | Pollutant emission amount anomaly identification method and device based on power data |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889088A (en) * | 2019-11-04 | 2020-03-17 | 国网浙江省电力有限公司信息通信分公司 | Enterprise pollution discharge supervision method assisted by electric model |
| CN111191881A (en) * | 2019-12-13 | 2020-05-22 | 大唐东北电力试验研究院有限公司 | Thermal power generating unit industrial equipment state monitoring method based on big data |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101478776B (en) * | 2009-01-23 | 2011-12-21 | 北京交通大学 | Method of railway wireless environment path loss index estimation |
| CN104571050B (en) * | 2015-01-13 | 2017-09-26 | 国网上海市电力公司 | Industrial enterprise's pollutant emission monitoring method based on high frequency electric data |
| CN106126391A (en) * | 2016-06-28 | 2016-11-16 | 北京百度网讯科技有限公司 | System monitoring method and apparatus |
| CN108876181B (en) * | 2018-06-30 | 2023-07-18 | 中碳汇资产运营(深圳)有限公司 | Intelligent enterprise pollutant emission monitoring method and system |
| CN108921440B (en) * | 2018-07-11 | 2022-08-05 | 平安科技（深圳）有限公司 | Pollutant abnormity monitoring method, system, computer equipment and storage medium |
| CN110008565B (en) * | 2019-03-28 | 2020-12-11 | 浙江大学 | Industrial process abnormal working condition prediction method based on operation parameter correlation analysis |
| CN110414045B (en) * | 2019-06-18 | 2023-08-11 | 东华大学 | Short-term wind speed prediction method based on VMD-GRU |
| CN111275307B (en) * | 2020-01-16 | 2023-09-05 | 生态环境部华南环境科学研究所 | Quality control method for high-frequency continuous observation data of automatic online station for water quality |
| CN211628078U (en) * | 2020-04-15 | 2020-10-02 | 江苏安科瑞电器制造有限公司 | Environmental control process monitoring system |
| CN112101969B (en) * | 2020-09-27 | 2024-04-02 | 西安交通大学 | Environment-friendly data fake detection method based on time sequence sliding window discrete coefficient |
| CN112508267B (en) * | 2020-12-04 | 2024-08-09 | 国网湖南省电力有限公司 | Distribution transformer area load prediction method and system based on artificial intelligence |
| CN112862605B (en) * | 2021-04-26 | 2022-06-24 | 广东浩迪智云技术有限公司 | Enterprise operation abnormity prompting method and system based on electricity consumption data |
-
2021
- 2021-08-24 CN CN202110974638.5A patent/CN113792988B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889088A (en) * | 2019-11-04 | 2020-03-17 | 国网浙江省电力有限公司信息通信分公司 | Enterprise pollution discharge supervision method assisted by electric model |
| CN111191881A (en) * | 2019-12-13 | 2020-05-22 | 大唐东北电力试验研究院有限公司 | Thermal power generating unit industrial equipment state monitoring method based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113792988A (en) | 2021-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113792988B (en) | Enterprise online monitoring data anomaly identification method | |
| CN110889088A (en) | Enterprise pollution discharge supervision method assisted by electric model | |
| CN110094251B (en) | SCR catalyst performance degradation analysis method based on time-interval multi-model modeling | |
| CN113988711B (en) | Pollution discharge enterprise stop or limit production monitoring method based on electricity consumption data in control state | |
| CN109064048B (en) | Wastewater discharge source rapid investigation method and system based on wastewater treatment process analysis | |
| CN112184090B (en) | Standard electricity utilization feature library establishing method, environment-friendly monitoring method, system and monitor | |
| CN114757380B (en) | Fault early warning system and method for thermal power plant, electronic equipment and storage medium | |
| CN112287988A (en) | Method for identifying water pollution source online monitoring data abnormity | |
| CN109614526A (en) | Environmental monitoring data fraud means recognition methods based on higher-dimension abnormality detection model | |
| CN112465239B (en) | Desulfurization system operation optimization method based on improved PSO-FCM algorithm | |
| CN112001511A (en) | Equipment reliability and dynamic risk evaluation method, system and equipment based on data mining | |
| CN111289697A (en) | CEMS running state monitoring and data false identification method and system | |
| CN115062851B (en) | Pollution discharge abnormality monitoring method and system based on multi-algorithm fusion | |
| CN117420283A (en) | Integrated multi-channel water quality monitoring method and system | |
| CN112906738A (en) | Water quality detection and treatment method | |
| CN115717590A (en) | Intelligent abnormity detection method for compressor and related device | |
| CN116805065B (en) | Intelligent management method for monitoring data of coal powder heating furnace burner | |
| CN115879726A (en) | Method for mutually optimizing and screening power consumption and emission data of enterprise | |
| CN104750144B (en) | Method of early warning operating condition of equipment | |
| CN116363843A (en) | Laboratory equipment early warning system | |
| CN116184955A (en) | Operation threshold setting method, monitoring method and monitoring system | |
| CN111624985B (en) | Gas turbine control system sensor fault diagnosis method | |
| CN112580838A (en) | Management method and system for operation and maintenance of environmental protection equipment, computer storage medium and terminal | |
| CN113986892A (en) | Coal consumption prediction and data cleaning method and system for thermal power generating unit | |
| 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 |