CN115752590A - Enterprise pollutant emission monitoring method based on electric power data - Google Patents
Enterprise pollutant emission monitoring method based on electric power data Download PDFInfo
- Publication number
- CN115752590A CN115752590A CN202211523428.5A CN202211523428A CN115752590A CN 115752590 A CN115752590 A CN 115752590A CN 202211523428 A CN202211523428 A CN 202211523428A CN 115752590 A CN115752590 A CN 115752590A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- environmental protection
- data
- power data
- electric power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 29
- 239000003344 environmental pollutant Substances 0.000 title claims abstract description 11
- 231100000719 pollutant Toxicity 0.000 title claims abstract description 11
- 238000004519 manufacturing process Methods 0.000 claims abstract description 51
- 230000007613 environmental effect Effects 0.000 claims abstract description 46
- 238000009434 installation Methods 0.000 claims abstract description 6
- 230000035772 mutation Effects 0.000 claims description 19
- 230000008859 change Effects 0.000 claims description 13
- 238000012706 support-vector machine Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000013145 classification model Methods 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 238000012806 monitoring device Methods 0.000 abstract description 4
- 239000000126 substance Substances 0.000 abstract description 3
- 238000010219 correlation analysis Methods 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 16
- 238000011161 development Methods 0.000 description 4
- 230000005611 electricity Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000010865 sewage Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an enterprise pollutant emission monitoring method based on electric power data, which is different from the traditional emission tail end chemical substance content detection and equipment-by-equipment installation electric power monitoring devices. Analyzing the three-phase total active power by variable point identification in a non-invasive summary chart monitoring mode to obtain the production working condition of an enterprise; the enterprise environmental protection working conditions are obtained by carrying out correlation analysis on the enterprise production working conditions and the environmental protection equipment working conditions, and real-time monitoring and intelligent identification of enterprise environmental protection abnormity are realized.
Description
Technical Field
The invention belongs to the technical field of enterprise pollutant emission monitoring, and particularly relates to an enterprise pollutant emission monitoring method based on electric power data.
Background
The ecological environment protection and the economic development are closely related and complement each other. Ecological civilization is built, green development is promoted, and the continuous progress along the sustainable development road can be realized. The enterprise production pollution is the largest environmental pollution source in the world at present, so that the pollution emission control and the environmental monitoring of pollution source enterprises are one of the most important contents in the ecological civilization construction work.
With the continuous development of the electric power monitoring technology, the electric power data analysis is combined with the production behavior monitoring of pollution source enterprises, and a new direction is provided for environmental protection monitoring.
The traditional environmental protection monitoring work is mainly to arrange various sensors at the tail end of each production link and judge whether the enterprises violate pollution discharge through physical or chemical detection of emissions at the tail end of a production line. At present, an environment-friendly monitoring scheme based on electricity consumption data analysis is almost invasive load monitoring, and monitoring equipment is required to be installed on sewage production and sewage treatment equipment. The start and stop of the pollution treatment equipment are directly monitored, and whether illegal production behaviors exist in the pollution source enterprise or not is judged by combining the start and stop conditions of the production equipment.
To traditional environmental protection monitoring work, the surrounding environment of the position of pollution control equipment is dirty and poor, sensor work is easily disturbed by external environment, produces the deviation and even became invalid, and monitoring real-time is poor, and the phenomenon that enterprise "has the inspection, just controls pollution" appears easily, and because various enterprises and trade, its production process is complicated various, does not have unified law and can be sought, and the mode of different grade type pollution sources can consume a large amount of manpower, materials and financial resources in the tradition. The existing environment-friendly monitoring scheme based on the electricity consumption data is almost intrusive load monitoring, when the number of pollution control devices needing monitoring is large, the number of monitoring devices is increased, the environment-friendly monitoring cost is increased, and enterprises are difficult to accept.
Disclosure of Invention
Aiming at the defects and shortcomings in the prior art, the method starts from a pollution source, does not consider various pollution sources, starts from the working states of environment-friendly equipment and production equipment to carry out environment-friendly monitoring, and has continuity and real-time performance; the problems of many monitoring devices, high economic cost and large installation manpower and material resources are solved.
The invention provides a pollution discharge enterprise environment-friendly working condition monitoring and abnormality recognition method based on electric power data, which is different from the traditional method for detecting the content of chemical substances at the tail end of discharge and installing an electric power monitoring device one by one. Analyzing the three-phase total active power by variable point identification in a non-invasive summary chart monitoring mode to obtain the production working condition of an enterprise; the enterprise environmental protection working condition is obtained by carrying out correlation analysis on the enterprise production working condition and the environmental protection equipment working condition, and real-time monitoring and intelligent identification of enterprise environmental protection abnormity are realized, and the method is innovative as follows:
(1) The method for non-invasive monitoring of the production working condition of the enterprise is provided, and the working condition of production equipment of the enterprise can be identified;
(2) The big data technology is utilized to extract the correlation characteristics of the electricity consumption data and the working conditions of the enterprise, so that the monitoring of the production working conditions of the enterprise and the identification of the environment-friendly working condition abnormity are realized, and data support is provided for an environment-friendly department;
(3) And aiming at the pollution control law characteristics of different enterprises in different industries, relevant models or parameters are adjusted, and the perception accuracy is improved.
The design scheme specifically comprises the following steps:
an enterprise pollutant emission monitoring method based on electric power data is characterized by comprising the following steps:
s1, installing an electric power data acquisition device at an electric power inlet line of a polluted enterprise to acquire electric power data of the enterprise; at environmental protection equipment inlet wire department installation electric power terminal of enterprise, monitoring environmental protection equipment opens and stops the operating mode:
the data collected by the electric power data collection device at the electric power inlet line comprises basic electric data, electric energy quality monitoring data and the working condition of environment-friendly equipment; the basic electrical data comprise effective values of each phase voltage and/or current, each phase power and total power;
the electric energy quality data comprises a 1-31 th harmonic current root mean square value and a current total harmonic distortion rate, a 1-31 th harmonic voltage and voltage total harmonic distortion rate, a 0.5-10.5 th inter-harmonic voltage content rate, a three-phase voltage unbalance, a positive sequence, a negative sequence, a zero sequence current, a voltage, each phase voltage deviation and a frequency;
step S2: carrying out variable point identification on three-phase total active power data in the electric power data to obtain the production working condition of an enterprise;
and step S3: combining the starting and stopping states of the enterprise production equipment and the enterprise pollution treatment equipment in the historical period according to the environmental protection rule by using the enterprise production working condition obtained in the step S2 to obtain the enterprise environmental protection working condition;
the specific environmental protection rule is as follows: if the production equipment is normally produced and the environmental protection equipment is started simultaneously, the environmental protection working condition is normal; if the production equipment is normally produced, but the environmental protection equipment is closed at the moment, the production equipment is regarded as abnormal, wherein the environmental protection working condition is regarded as normal when the production equipment is closed;
and step S4: taking enterprise environment-friendly working conditions obtained historically as labels, taking historical power quality monitoring data as input, and training by using an SVM (support vector machine) method to obtain a classifier model;
step S5: and (4) inputting the newly obtained power data into the model obtained in the step (S4), identifying the abnormal condition of the environmental protection working condition of the polluted enterprise, and giving an alarm.
Further, in step S2, after the variable point identification, the specific steps of obtaining the production conditions of the enterprise are as follows:
step S201: for time sequence three-phase total active power data P = (P) 1 ,...,p n ) Assuming the presence of ω mutation points t = (τ) 1 ,...,τ ω ) The position of each mutation point is an integer between 1 and n, and defines tau 0 =0,τ ω+1 =n;
Step S202: omega mutation points t = (tau) 1 ,...,τ ω ) Time sequence three-phase total active power data P = (P) 1 ,...,p n ) Dividing the sequence into omega +1 subsequences, wherein the ith segment is expressed as: p i =(p τi-1 +1,...,p i );
Step S203: converting a multi-change point monitoring problem into a minimum objective function F (n) to solve:
wherein, C (P) i ) Representing the cost function calculated by the ith sub-sequence; beta f (omega) is an additional penalty item optimized by the objective function and used for balancing the number of the calculated mutation points and reducing the phenomenon of excessive or insufficient mutation points, beta is a penalty factor, and f (omega) is a penalty function which increases along with the increase of the number of the mutation points;
step S204: let the penalty term F (ω) = ω +1, then the iterative equation for F (n) is found as follows:
converting the problem of solving the global optimal solution in the step S203 into a process of continuously searching a previous change point;
step S205: setting an initial value F (0) = -beta, circularly calculating in 1-n, taking the minimum time point meeting the objective function as a new variable point, and continuously iterating to solve all the catastrophe points;
step S206: in each searching process, removing data indexes which cannot become variable points, and reducing the calculated amount; the following judgment conditions were introduced: it is assumed that for data time points t, s, l (t < s < l), there is a constant K that satisfies C (p) t+1 ,...,p s )+C(p s+1 ,…,p l )+K≤C(p t+1 ,…,p l ) When F (t) + C (p) t+1 ,...,p s ) If F(s) is satisfied, t is considered to be the last change point before l, and is excluded;
step S207: using the last iterated change point T = (tau) 1 ,...,τ n ) Dividing each time sequence three-phase power data into n +1 subsections, respectively calculating the average value in each subsection to obtain
Step S208: respectively comparing the average values of two adjacent subsegments, and assuming the ith average value asThe next mean value isIf it isThen the change point τ is considered i To tau i+1 The enterprise is in production, otherwise, the enterprise is considered to stop production; so as to obtain the production working condition of the enterprise.
Further, in step S4, the training step of the SVM classification model specifically includes:
step S401: suppose there is n-dimensional power data x i {x 1 ,x 2 ,…,x n And the corresponding environmental protection condition label is y i ∈{-1,1};
Step S402: selecting a penalty function C larger than 0, constructing and solving a convex quadratic programming problem:
Step S404: by w in step S403 * And b * Obtaining a classification decision function: y is i =sign(w * ·x i +b * ) (ii) a Based on the function, input power data x i Obtaining the final environment-friendly working condition label y i 。
Compared with the prior art, the invention and the preferred scheme thereof adopt the electricity utilization data to monitor the environmental protection of enterprises, and have strong real-time and good accuracy; by adopting a non-invasive monitoring scheme, the system has low economic cost, simple installation and small influence on the production of enterprises.
The beneficial effects are at least as follows:
(1) A method for detecting a change point is provided, which can identify the working condition of production equipment of an enterprise.
(2) An enterprise pollutant emission monitoring method based on electric power data at an electric power inlet line of a polluted enterprise is established.
By adopting the algorithm and the model, the monitoring of the production working condition of the enterprise and the identification of the environmental protection working condition abnormity are realized, and data support is provided for an environmental protection department.
Drawings
FIG. 1 is a schematic flow chart of an embodiment of the present invention;
fig. 2 is a schematic view of an installation position of the electric power data acquisition device according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It will be understood that, as used herein, the terms "first," "second," and the like may be used herein to describe various elements, but these elements should not be limited by these terms unless otherwise specified. These terms are only used to distinguish one element from another. For example, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script, without departing from the scope of the present application.
As shown in fig. 1 and fig. 2, the method for monitoring pollutant emissions of an enterprise based on electric power data provided in this embodiment specifically includes the following steps:
step S1, firstly, installing an electric power data acquisition device at an electric power incoming line of a polluted enterprise, and acquiring electric power data of the enterprise; install simple and easy power terminal in enterprise environmental protection equipment inlet wire department, the start-stop operating mode of monitoring environmental protection equipment.
The data collected by the electric power data collection device at the electric power inlet line comprises basic electric data, electric energy quality monitoring data and the working condition of the environment-friendly equipment. The basic electrical data includes the effective value of each phase voltage (current), each phase power and total power (active, reactive, apparent).
The power quality data comprises a 1-31 th harmonic current root mean square value and a current total harmonic distortion rate, a 1-31 th harmonic voltage and voltage total harmonic distortion rate, a 0.5-10.5 th inter-harmonic voltage content, a three-phase voltage unbalance, a positive sequence, a negative sequence, a zero sequence current, a voltage, each phase voltage deviation and a frequency. Data acquisition was performed every 3min, yielding a total of 480 data points 24 hours a day.
Step S2: and carrying out variable point identification on the three-phase total active power data in the electric power data to obtain the production working condition of the enterprise.
And step S3: and (3) combining the starting and stopping states of the enterprise production equipment and the enterprise pollution control equipment in the historical period to obtain the environment-friendly working condition of the enterprise according to the environment-friendly rule by using the enterprise production working condition obtained in the step (S2).
The specific environmental protection rule is as follows: if the production equipment is normally produced and the environmental protection equipment is started simultaneously, the environmental protection working condition is normal; if the production equipment is normally produced, but the environmental protection equipment is closed at the moment, the production equipment is regarded as abnormal, wherein the environmental protection working condition is regarded as normal when the production equipment is closed.
And step S4: and (3) taking the enterprise environment-friendly working condition obtained historically as a label, taking historical power quality monitoring data as input, and training by using an SVM (support vector machine) method to obtain a classifier model.
Step S5: and (4) inputting the newly obtained power data into the model obtained in the step (S4), identifying the abnormal condition of the environmental protection working condition of the polluted enterprise, and giving an alarm in time.
Further, in step S2, after the variable point identification, the step of obtaining the production condition of the enterprise is:
step S201: for time sequence three-phase total active power data P = (P) 1 ,...,p n ) Assuming the presence of ω mutation points t = (τ) 1 ,...,τ ω ) The position of each mutation point is an integer between 1 and n, and defines tau 0 =0,τ ω+1 =n;
Step S202: omega mutation points t = (tau) 1 ,...,τ ω ) Time sequence three-phase total active power data P = (P) 1 ,...,p n ) Dividing the sequence into omega +1 subsequences, wherein the ith segment can be expressed as:
step S203: converting the multi-change point monitoring problem into a minimum objective function F (n) to solve:
wherein, C (P) i ) Representing the cost function calculated by the ith sub-sequence; beta f (omega) is an additional penalty item optimized by the objective function and used for balancing the number of the calculated mutation points and reducing the phenomenon of excessive or insufficient mutation points, beta is a penalty factor, and f (omega) is a penalty function which increases along with the increase of the number of the mutation points.
Step S204: let the penalty term F (ω) = ω +1, then the iterative equation for F (n) is found as follows:
and (4) converting the problem of solving the global optimal solution in the step (S203) into a process of continuously searching a previous change point.
Step S205: setting an initial value F (0) = -beta, circularly calculating in 1 to n, taking the time point meeting the minimum target function as a new variable point, and continuously and iteratively solving all the catastrophe points.
Step S206: in each searching process, data indexes which cannot become the variable points are removed, and the calculation amount is reduced. The following judgment conditions were introduced: suppose that for data time points t, s, l (t < s < l), there is a constant K that satisfies C (p) t+1 ,…,p s )+C(p s+1 ,…,p l )+K≤C(p t+1 ,…,p l ) When F (t) + C (p) t+1 ,...,p s ) If + K.ltoreq.F(s) is satisfied, t is considered to be the last change point before l, and this is excluded.
Step S207: using the last iterated change point T = (tau) 1 ,...,τ n ) Dividing each time sequence three-phase power data into n +1 subsections, respectively calculating the average value in each subsection to obtain
Step S208: respectively comparing the average values of two adjacent subsegments, and assuming the ith average value asThe next mean value isIf it isThen the change point tau is considered i To tau i+1 And if the production is in progress, the enterprise is considered to stop producing. Thus, the production working condition of an enterprise is obtained.
Further, in step S4, the training step of the SVM classification model is:
step S401: falseIs provided with n-dimensional power data x i {x 1 ,x 2 ,…,x n H and the corresponding environmental protection operating mode label is y i ∈{-1,1}。
Step S402: selecting a penalty function C > 0, constructing and solving a convex quadratic programming problem:
Step S404: by w in the previous step * And b * Obtaining a classification decision function: y is i =sign(w * ·x i +b * ). Based on the function, input power data x i Obtaining the final environment-friendly working condition label y i 。
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of steps in various embodiments may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least a portion of sub-steps or stages of other steps.
Those skilled in the art will appreciate that all or part of the processes in the methods for implementing the embodiments may be implemented by hardware that is related to instructions of a computer program, and the computer program may be stored in a non-volatile computer-readable storage medium, and when executed, the computer program may include processes such as those of the embodiments of the methods. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only show several embodiments of the present invention, and the description thereof is specific and detailed, but not to be construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
The present invention is not limited to the above preferred embodiments, and any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (3)
1. An enterprise pollutant emission monitoring method based on electric power data is characterized by comprising the following steps:
s1, installing an electric power data acquisition device at an electric power inlet line of a pollution enterprise to acquire electric power data of the enterprise; at environmental protection equipment inlet wire department installation electric power terminal of enterprise, monitoring environmental protection equipment opens and stops the operating mode:
the data acquired by the electric power data acquisition device at the electric power inlet line comprises basic electric data, electric energy quality monitoring data and the working condition of environmental protection equipment; the basic electrical data comprise effective values of each phase voltage and/or current, each phase power and total power;
the power quality data comprises a 1-31 harmonic current root mean square value and a current total harmonic distortion rate, a 1-31 harmonic voltage and voltage total harmonic distortion rate, a 0.5-10.5 inter-harmonic voltage content rate, a three-phase voltage unbalance degree, a positive sequence, a negative sequence, a zero sequence current, a voltage, each phase voltage deviation and a frequency;
step S2: carrying out variable point identification on three-phase total active power data in the electric power data to obtain the production working condition of an enterprise;
and step S3: combining the starting and stopping states of the enterprise production equipment and the enterprise pollution control equipment in the historical period according to the environmental protection rule by using the enterprise production working condition obtained in the step S2 to obtain the enterprise environmental protection working condition;
the specific environmental protection rule is as follows: if the production equipment is normally produced and the environmental protection equipment is started simultaneously, the environmental protection working condition is normal; if the production equipment is normally produced, but the environmental protection equipment is closed at the moment, the production equipment is regarded as abnormal, wherein the environmental protection working condition is regarded as normal when the production equipment is closed;
and step S4: taking the enterprise environmental protection working conditions obtained historically as labels, taking historical power quality monitoring data as input, and training by an SVM (support vector machine) method to obtain a classifier model;
step S5: and (4) inputting the newly obtained power data into the model obtained in the step (S4), identifying the abnormal condition of the environmental protection working condition of the polluted enterprise, and giving an alarm.
2. The method of claim 1 for monitoring enterprise pollutant emissions based on power data, characterized by:
in the step S2, after the variable point identification, the specific steps of obtaining the production working condition of the enterprise are as follows:
step S201: for time sequence three-phase total active power data P = (P) 1 ,...,p n ) Assuming the presence of ω mutation points t = (τ) 1 ,...,τ ω ) The position of each mutation point is an integer between 1 and n, and defines tau 0 =0,τ ω+1 =n;
Step S202: omega mutation points t = (tau) 1 ,...,τ ω ) Time sequence three-phase total active power data P = (P) 1 ,...,p n ) Dividing the sequence into omega +1 subsequences, wherein the ith segment is expressed as:
step S203: converting the multi-change point monitoring problem into a minimum objective function F (n) to solve:
wherein, C (P) i ) Representing the cost function calculated by the ith sub-sequence; beta f (omega) is an additional penalty term optimized by the objective function and used for balancing the number of the calculated mutation points and reducing the phenomenon that the number of the mutation points is too much or too little, beta is a penalty factor, and f (omega) is a penalty function which is increased along with the increase of the number of the mutation points;
step S204: let the penalty term F (ω) = ω +1, then the iterative equation for F (n) is found as follows:
converting the problem of solving the global optimal solution in the step S203 into a process of continuously searching a previous change point;
step S205: setting an initial value F (0) = -beta, circularly calculating in 1-n, taking the minimum time point meeting the target function as a new variable point, and continuously iterating to solve all the mutation points;
step S206: in each searching process, removing data indexes which cannot become variable points, and reducing the calculated amount; the following judgment conditions were introduced: it is assumed that for data time points t, s, l (t < s < l), there is a constant K that satisfies C (p) t+1 ,...,p s )+C(p s+1 ,...,p l )+K≤C(p t+1 ,...,p l ) When F (t) + C (p) t+1 ,...,p s ) If + K ≦ F(s) holds, t is considered to be the last change point before l, and is excluded;
step S207: using the last iterated change point T = (tau) 1 ,...,τ n ) Dividing each time sequence three-phase power data into n +1 subsections, respectively calculating the average value in each subsection to obtain
Step S208: respectively comparing the average values of two adjacent subsegments, and assuming the ith average value asThe next mean value isIf it isThen the change point τ is considered i To tau i+1 If the enterprise is in production, otherwise, the enterprise is considered to stop production; so as to obtain the production working condition of the enterprise.
3. The method for monitoring enterprise pollutant emissions based on electric power data according to claim 1, characterized in that:
in step S4, the training of the SVM classification model specifically includes:
step S401: suppose there is n-dimensional power data x i {x 1 ,x 2 ,…,x n And the corresponding environmental protection condition label is y i ∈{-1,1};
Step S402: selecting a penalty function C larger than 0, constructing and solving a convex quadratic programming problem:
Step S404: by w in step S403 * And b * Obtaining a classification decision function: y is i =sign(w * ·x i +b * );
Based on the function, input power data x i Obtaining the final environment-friendly working condition label y i 。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211523428.5A CN115752590A (en) | 2022-11-30 | 2022-11-30 | Enterprise pollutant emission monitoring method based on electric power data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211523428.5A CN115752590A (en) | 2022-11-30 | 2022-11-30 | Enterprise pollutant emission monitoring method based on electric power data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115752590A true CN115752590A (en) | 2023-03-07 |
Family
ID=85341583
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211523428.5A Pending CN115752590A (en) | 2022-11-30 | 2022-11-30 | Enterprise pollutant emission monitoring method based on electric power data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115752590A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117236971A (en) * | 2023-09-21 | 2023-12-15 | 中节能天融科技有限公司 | Multi-working condition emission data fake detection method, device and system and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170184393A1 (en) * | 2015-12-24 | 2017-06-29 | University Of Electronic Science And Technology Of China | Method for identifying air pollution sources based on aerosol retrieval and glowworm swarm algorithm |
CN113762607A (en) * | 2021-08-26 | 2021-12-07 | 甘肃同兴智能科技发展有限责任公司 | Prediction method for carbon emission of power grid enterprise |
CN115291006A (en) * | 2022-07-21 | 2022-11-04 | 福州大学 | Method for identifying environmental protection working condition abnormity of polluted enterprise based on electricity utilization data |
-
2022
- 2022-11-30 CN CN202211523428.5A patent/CN115752590A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170184393A1 (en) * | 2015-12-24 | 2017-06-29 | University Of Electronic Science And Technology Of China | Method for identifying air pollution sources based on aerosol retrieval and glowworm swarm algorithm |
CN113762607A (en) * | 2021-08-26 | 2021-12-07 | 甘肃同兴智能科技发展有限责任公司 | Prediction method for carbon emission of power grid enterprise |
CN115291006A (en) * | 2022-07-21 | 2022-11-04 | 福州大学 | Method for identifying environmental protection working condition abnormity of polluted enterprise based on electricity utilization data |
Non-Patent Citations (1)
Title |
---|
靳旦;唐伟;: "基于组合支持向量回归的排污企业生产识别", 四川电力技术, no. 03, 20 June 2020 (2020-06-20) * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117236971A (en) * | 2023-09-21 | 2023-12-15 | 中节能天融科技有限公司 | Multi-working condition emission data fake detection method, device and system and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Li et al. | Classification of energy consumption in buildings with outlier detection | |
Liu et al. | A data mining-based framework for the identification of daily electricity usage patterns and anomaly detection in building electricity consumption data | |
CN110750524A (en) | Method and system for determining fault characteristics of active power distribution network | |
CN107944622A (en) | Wind power forecasting method based on continuous time cluster | |
Junior et al. | Optimized hybrid ensemble learning approaches applied to very short-term load forecasting | |
Niu et al. | Lebesgue sampling based deep belief network for lithium-ion battery diagnosis and prognosis | |
CN115752590A (en) | Enterprise pollutant emission monitoring method based on electric power data | |
Liang et al. | Develop load shape dictionary through efficient clustering based on elastic dissimilarity measure | |
CN112836720A (en) | Building operation and maintenance equipment abnormity diagnosis method and system and computer readable storage medium | |
CN114511181A (en) | Water pollution environment-friendly calibration method and device based on power grid and tax data fusion | |
CN113283502A (en) | Clustering-based equipment state threshold determining method and device | |
Putra et al. | Modeling of high uncertainty photovoltaic generation in quasi dynamic power flow on distribution systems: A case study in Java Island, Indonesia | |
CN113516162A (en) | OCSVM and K-means algorithm based industrial control system flow abnormity detection method and system | |
Sun et al. | Research on anomaly pattern detection in hydrological time series | |
CN112256735B (en) | Power consumption monitoring method and device, computer equipment and storage medium | |
CN111476316B (en) | Method and system for clustering mean value of power load characteristic data based on cloud computing | |
Li et al. | VRLA battery fault prediction for data center based on random forest model and feature enhancement method | |
Mirnaghi et al. | Application of data mining in understanding the charging patterns of the hot water tank in a residential building: a case study | |
Raymand et al. | Machine learning-based estimation of buildings' characteristics employing electrical and chilled water consumption data: Pipeline optimization | |
Liu et al. | Review of outlier detection algorithms based on grain storage temperature data | |
CN118011223B (en) | Fault diagnosis method and system for electric power energy storage system | |
Wen et al. | Charge Time Prediction Model of Power Battery based on Random Forest algorithm | |
Jiang et al. | Incremental electricity consumer behavior learning using smart meter data | |
Shen et al. | Interpretable interval prediction-based outlier-adaptive day-ahead electricity price forecasting involving cross-market features | |
Peng et al. | Multistate Reliability Analysis of Solid Oxide Fuel Cells Using Automatic Spectral Clustering and Neighborhood Rough Sets |
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 |