CN117312888B - Data integration processing method and system for fixed pollution source - Google Patents
Data integration processing method and system for fixed pollution source Download PDFInfo
- Publication number
- CN117312888B CN117312888B CN202311594849.1A CN202311594849A CN117312888B CN 117312888 B CN117312888 B CN 117312888B CN 202311594849 A CN202311594849 A CN 202311594849A CN 117312888 B CN117312888 B CN 117312888B
- Authority
- CN
- China
- Prior art keywords
- emission
- pollution
- discharge unit
- pollution discharge
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000010354 integration Effects 0.000 title claims abstract description 27
- 238000003672 processing method Methods 0.000 title claims abstract description 18
- 239000003344 environmental pollutant Substances 0.000 claims abstract description 99
- 231100000719 pollutant Toxicity 0.000 claims abstract description 99
- 238000012549 training Methods 0.000 claims abstract description 70
- 238000012544 monitoring process Methods 0.000 claims abstract description 50
- 238000009826 distribution Methods 0.000 claims abstract description 46
- 238000004458 analytical method Methods 0.000 claims abstract description 30
- 230000002159 abnormal effect Effects 0.000 claims abstract description 26
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 15
- 238000000034 method Methods 0.000 claims description 40
- 230000015654 memory Effects 0.000 claims description 16
- 238000013480 data collection Methods 0.000 claims description 15
- 239000010865 sewage Substances 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000011109 contamination Methods 0.000 claims 1
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 description 10
- 229910000831 Steel Inorganic materials 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 239000010959 steel Substances 0.000 description 5
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 description 4
- 239000000356 contaminant Substances 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 229910021529 ammonia Inorganic materials 0.000 description 2
- 230000003190 augmentative effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- 239000002910 solid waste Substances 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 239000002912 waste gas Substances 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 239000002351 wastewater Substances 0.000 description 2
- 239000004568 cement Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009713 electroplating Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- 150000002739 metals Chemical class 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000002893 slag Substances 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 239000004753 textile Substances 0.000 description 1
- 238000003911 water pollution Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0003—Composite materials
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- 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
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Chemical & Material Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Food Science & Technology (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Medicinal Chemistry (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a data integration processing method and a system for a fixed pollution source, which relate to the technical field of pollution source data integration, and are characterized in that by collecting pollution monitoring distribution data and collecting historical emission training data of each pollution discharge unit in each emission period, a discharge quantity prediction model set is trained for each emission period of each pollution discharge unit, the pollution discharge unit is divided into a plurality of similar pollution discharge unit sets, for each similar pollution discharge unit set, all similar pollution discharge units in the pollution discharge unit set are further divided into a plurality of similar cluster pollution discharge unit sets by using a clustering algorithm based on the historical emission training data, real-time emission data of each pollution discharge unit is collected, a discharge quantity predicted value is obtained, and after a predicted time step, a pollution discharge abnormal analysis result is generated; the efficiency of locating the cause of abnormal pollutant discharge is improved.
Description
Technical Field
The invention relates to the technical field of pollution source data integration, in particular to a data integration processing method and system for a fixed pollution source.
Background
Enterprises and institutions serve as a fixed pollution source, and refer to units which continuously or intermittently discharge pollutants into the environment during production and operation activities. They include various factories, mines, power plants, hospitals, schools, etc., covering almost all economic sectors and industries. Enterprises and institutions are one of the main sources of pollutant emissions. It is counted that about 80% of industrial contaminants and 70% of domestic contaminants are emitted by enterprises and institutions. The pollutants mainly comprise waste gas, waste water, solid waste and the like, wherein the waste gas mainly comes from industries of thermal power generation, steel, chemical industry, cement and the like, the waste water mainly comes from industries of food, textile, paper making, electroplating and the like, and the solid waste mainly comes from industries of mining, metallurgy, chemical industry, electronics and the like.
The pollutant emission of enterprises and institutions has serious influence on the environment. On the one hand, pollutant emission can lead to air quality reduction, water pollution is aggravated, and soil quality is reduced, so that human health and life quality are affected. On the other hand, pollutant discharge can also destroy the balance of the ecological system, so that the biodiversity is reduced, the function of the ecological system is reduced, and the stability and development of the whole ecological system are affected.
At present, the monitoring of pollutant discharge amounts of various enterprises and institutions is independent, namely, independent data monitoring is respectively carried out on various pollution sources, and early warning or notification modification is carried out when the discharge amounts are abnormal, however, under most conditions, certain pollutant discharge exceeding is not the individual behavior of one enterprise and institution, but a large-scale group effect exists, so that a method is also needed for carrying out data integration on the pollution discharge behaviors of all enterprises and institutions so as to find out the internal group effect, and further find out and stop pollution discharge mess in the industry more timely;
therefore, the invention provides a data integration processing method and system for a fixed pollution source.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, the invention provides a data integration processing method and system for a fixed pollution source, which improves the efficiency of locating the cause of abnormal pollutant discharge.
In order to achieve the above object, embodiment 1 of the present invention provides a data integration processing method for a fixed pollution source, including the following steps:
step one: collecting pollution discharge unit data, and generating pollution monitoring distribution data for each pollution discharge unit based on the pollution discharge unit data;
step two: dividing each day into a plurality of emission periods, and collecting historical emission training data of each pollution discharge unit based on pollution monitoring distribution data in each emission period;
step three: training a set of emission prediction models for each emission cycle of each emission unit based on the historical emission training data;
step four: dividing the pollution discharge units into a plurality of similar pollution discharge unit sets based on pollution monitoring distribution data, and further dividing all similar pollution discharge units into a plurality of similar cluster pollution discharge unit sets based on historical emission training data for each similar pollution discharge unit set by using a clustering algorithm;
step five: collecting real-time emission data of each pollution discharge unit, and obtaining an emission quantity predicted value after a preset predicted time step based on the real-time emission data and an emission quantity predicted model set;
step six: generating a pollution emission anomaly analysis result based on the real-time emission data, emission predicted values of each pollution emission unit and the same cluster pollution emission unit set at the moment after the predicted time step;
The pollution monitoring distribution data is generated for each pollution discharge unit in the following way:
collecting the types of pollutants generated when different product types are produced, and taking the types of pollutants as the types of pollutants to be monitored of the product types;
according to the pollutant types to be monitored of each pollution discharge unit, installing a corresponding emission sensor of each pollutant type for a pollution discharge point of each pollution discharge unit;
the pollution monitoring distribution data comprise all pollutant types to be monitored of each pollution discharge unit;
the mode for collecting the historical emission training data of each pollution discharge unit is as follows:
several days were selected as the sample collection period, in each discharge cycle of each day of the sample collection period:
for each pollution discharge unit, using a discharge sensor corresponding to each pollutant type to be monitored in pollution monitoring distribution data to acquire the discharge of pollutants corresponding to each unit duration in real time;
sequencing the emission of various pollutant types to be monitored acquired in the emission period according to a time sequence to obtain an emission time sequence of the various pollutant types to be monitored;
normalizing the emission time sequence;
for the emission period of the pollution discharge unit per day in a sample collection time period, the emission time sequence of all pollutant types to be monitored forms historical emission training data;
The method for training a discharge quantity prediction model set for each discharge period of each pollution discharge unit comprises the following steps:
for each emission cycle of each emission unit, the type of pollutant to be monitored:
presetting a predicted time step, a sliding step and a sliding window length, converting an emission time sequence corresponding to the pollutant type to be monitored into a plurality of training samples by using a sliding window method, taking each group of training samples as input of an emission prediction model, taking the emission time sequence of the predicted time step in the future as output of the emission prediction model, taking the emission sequence in the predicted time step in the future of each training sample as a prediction target, and training the emission prediction model;
the mode of dividing the sewage disposal unit into a plurality of similar sewage disposal unit sets is as follows:
grouping all the pollution discharge units according to grouping conditions with the same pollutant types to be monitored, and combining the same group of pollution discharge units into a similar pollution discharge unit set;
the clustering algorithm is further divided into a plurality of identical-cluster pollution discharge unit sets by the following steps:
For each emission unit in each collection of like emission units:
calculating the average emission value of each pollutant type to be monitored of the pollution discharge unit in each emission period;
the emission average value is calculated in the following way:
counting the average value of emission time series of each pollutant type to be monitored of the pollution discharge unit in each emission period of each day;
in the sample collection time period, taking the average value of the discharge amounts of all pollutant types to be monitored as a discharge amount average value;
sequencing the discharge amount average value according to the time sequence of the discharge period for each pollutant type to be monitored of the pollution discharge unit to obtain a discharge amount average value sequence;
normalizing the emission average value sequence;
for the pollution discharge unit, merging the emission average value sequences of the pollutant types to be monitored to obtain a clustering vector;
presetting the number K of cluster clusters;
for each collection of like blowdown units:
taking a clustering vector of each pollution discharge unit in the similar pollution discharge unit set as a data point;
using a clustering algorithm to all data points in the similar pollution discharge unit set to obtain K clustering clusters;
Each cluster corresponds to a same-cluster pollution discharge unit set, and the pollution discharge units in each same-cluster pollution discharge unit set are pollution discharge units corresponding to data points in the same cluster;
the mode for collecting the real-time emission data of each pollution discharge unit is as follows:
collecting, by respective emission sensors, emission time series of respective types of pollutants to be monitored of respective pollution discharge units at the beginning of each emission cycle;
normalizing the emission period and the collected emission time sequence to obtain real-time emission data;
the method for obtaining the predicted emission value after the preset predicted time step based on the real-time emission data and the emission prediction model set is as follows:
for each contaminant type to be monitored:
taking a subsequence in the length of the nearest sliding window in a corresponding emission time sequence in the real-time emission data as input of an emission prediction model to obtain an emission sequence in a prediction time step output by the emission prediction model;
taking the last element in the output emission sequence as an emission predicted value;
the method for generating the analysis result of the abnormal pollutant discharge comprises the following steps:
the number of the pollution discharge unit is marked as i, each pollutant type to be monitored of the ith pollution discharge unit is marked as Im, and the number of the pollutant types to be monitored of the ith pollution discharge unit is marked as Im;
Marking an emissions prediction value of an im-th pollutant type to be monitored as pim, and marking the actual emissions collected after a predicted time step as rim;
marking the same cluster pollution discharge unit set where the ith pollution unit is positioned as Ti;
calculating a predicted deviation value xim of the type of the im pollutant to be monitored, wherein the calculation formula of the predicted deviation value xim is as follows:；
calculating a predicted deviation value average value Wi of the ith pollution unit, wherein the calculation formula of the predicted deviation value average value Wi is as follows；
If the average Wi of the predicted deviation values of any pollution unit is larger than a preset first deviation value threshold, generating a corresponding abnormal analysis result of pollution emission for the average Wi of the predicted deviation values of any pollution unit;
the method for generating the corresponding analysis result of the abnormal pollutant emission comprises the following steps:
calculating the average value of the average values of the predicted deviation values of all the pollution discharge units in the same-cluster pollution discharge unit set Ti as a same-cluster deviation average value KTi;
if the difference value between the predicted deviation value average Wi and the same cluster deviation average KTi is smaller than or equal to a preset second deviation threshold value, carrying out emission early warning on all pollution discharge units in the same cluster pollution discharge unit set Ti;
and if the difference value between the predicted deviation value average Wi and the same cluster deviation average KTi is larger than a preset second deviation threshold value, carrying out emission early warning on the pollution discharge unit.
According to embodiment 2 of the invention, a data integration processing system for a fixed pollution source is provided, which comprises a pollution monitoring distribution data collection module, a historical emission data collection module, an emission prediction model training module, a pollution discharge unit clustering module and an emission anomaly analysis result generation module; wherein, each module is electrically connected;
the pollution monitoring distribution data collection module is used for collecting pollution discharge unit data, generating pollution monitoring distribution data for each pollution discharge unit based on the pollution discharge unit data, and sending the pollution monitoring distribution data to the historical emission data collection module and the pollution discharge unit clustering module;
the historical emission data collection module is used for dividing each day into a plurality of emission periods, collecting historical emission training data of each pollution discharge unit based on pollution monitoring distribution data in each emission period, and sending all the historical emission training data to the emission quantity prediction model training module and the pollution discharge unit clustering module;
the emission prediction model training module is used for training an emission prediction model set for each emission period of each pollution discharge unit based on historical emission training data and sending the emission prediction model set to the emission anomaly analysis result generation module;
The pollution discharge unit clustering module is used for dividing the pollution discharge units into a plurality of similar pollution discharge unit sets based on pollution monitoring distribution data, further dividing all the similar pollution discharge units into a plurality of same-cluster pollution discharge unit sets based on historical emission training data, and sending the same-cluster pollution discharge unit sets to the emission anomaly analysis result generation module;
the emission anomaly analysis result generation module is used for collecting real-time emission data of each pollution discharge unit, obtaining emission quantity predicted values after a preset predicted time step based on the real-time emission data and the emission quantity predicted model set, and generating a pollution emission anomaly analysis result based on the real-time emission data, the emission quantity predicted values of each pollution discharge unit and the same-cluster pollution discharge unit set after the predicted time step.
An electronic device according to embodiment 3 of the present invention includes: a processor and a memory, wherein the memory stores a computer program for the processor to call;
the processor executes the data integration processing method of the fixed pollution source based on the augmented reality technology by calling the computer program stored in the memory.
A computer-readable storage medium according to embodiment 4 of the present invention has stored thereon a computer program that is erasable;
when the computer program runs on the computer equipment, the computer equipment is caused to execute the data integration processing method of the fixed pollution source based on the augmented reality technology.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, pollution monitoring distribution data are generated for each pollution discharge unit by collecting the pollution discharge unit data, the pollution monitoring distribution data are generated for each pollution discharge unit, each day is divided into a plurality of discharge periods, in each discharge period, the historical discharge training data of each pollution discharge unit are collected based on the pollution monitoring distribution data, a discharge quantity prediction model set is trained for each discharge period of each pollution discharge unit based on the historical discharge training data, the pollution discharge unit is divided into a plurality of similar pollution discharge unit sets based on the pollution monitoring distribution data, for each similar pollution discharge unit set, all similar pollution discharge units in the similar pollution discharge unit sets are further divided into a plurality of same-cluster pollution discharge unit sets based on the historical discharge training data by using a clustering algorithm, real-time discharge data of each pollution discharge unit are collected, a preset predicted value of the discharge quantity after a predicted time step is obtained based on the real-time discharge data and the predicted value of each pollution discharge unit and the same-cluster pollution discharge unit set, and a pollution discharge abnormality analysis result is generated after the predicted time step is performed; by integrating the same-cluster pollution discharge unit sets with similar discharge properties for each pollution discharge unit, when any one pollution discharge unit is abnormal, the pollution discharge amount condition of the same-cluster pollution discharge unit set can be extendably investigated, so that the reasons of the abnormal pollution discharge amount can be rapidly analyzed, for example, the pollution discharge unit is independent abnormal, or the problem of abnormal pollution discharge units in batches caused by raw material problems, production line problems, time arrangement problems, large demand increase and the like is solved, and the efficiency of positioning the reasons of the abnormal pollutant discharge is improved.
Drawings
FIG. 1 is a flow chart of a data integration processing method of a fixed pollution source in embodiment 1 of the present invention;
FIG. 2 is a block diagram showing the connection relationship of the data integration processing system for fixing a pollution source according to embodiment 2 of the present invention;
fig. 3 is a schematic structural diagram of an electronic device in embodiment 3 of the present invention;
fig. 4 is a schematic diagram of a computer-readable storage medium according to embodiment 4 of the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1: as shown in fig. 1, a data integration processing method of a fixed pollution source includes the following steps:
step one: collecting pollution discharge unit data, and generating pollution monitoring distribution data for each pollution discharge unit based on the pollution discharge unit data;
step two: dividing each day into a plurality of emission periods, and collecting historical emission training data of each pollution discharge unit based on pollution monitoring distribution data in each emission period;
Step three: training a set of emission prediction models for each emission cycle of each emission unit based on the historical emission training data;
step four: dividing the pollution discharge units into a plurality of similar pollution discharge unit sets based on pollution monitoring distribution data, and further dividing all similar pollution discharge units into a plurality of similar cluster pollution discharge unit sets based on historical emission training data for each similar pollution discharge unit set by using a clustering algorithm;
step five: collecting real-time emission data of each pollution discharge unit, and obtaining an emission quantity predicted value after a preset predicted time step based on the real-time emission data and an emission quantity predicted model set;
step six: generating a pollution emission anomaly analysis result based on the real-time emission data, emission predicted values of each pollution emission unit and the same cluster pollution emission unit set at the moment after the predicted time step;
the method for collecting the sewage unit data comprises the following steps:
collecting the product types produced by each sewage disposal unit, and taking the product types of each sewage disposal unit as sewage disposal unit data;
it is understood that the pollution discharge unit refers to units and individuals which discharge pollutants to the environment, including enterprises and public institutions, individual industry and merchants and other organizations and individuals, wherein the maximum ratio of the discharged pollutants is the enterprises and public institutions, and the pollution monitoring is convenient because the positions of the enterprises and public institutions are fixed, and the pollution discharge unit and the fixed pollution source in the invention represent the enterprises and public institutions;
The enterprises and institutions generally produce products due to the requirement of factories, so that waste is generated, and the type of the pollutants is related to the type of the products produced by the sewage disposal units; for example, pollutants produced by steel plants include smoke, sulfur dioxide, ammonia, waste residues, etc., and therefore, the types of pollutants that need to be monitored by different enterprises and institutions are different;
further, the method for generating pollution monitoring distribution data for each pollution discharge unit based on the pollution discharge unit data is as follows:
collecting the types of pollutants generated when different product types are produced, and taking the types of pollutants as the types of pollutants to be monitored of the product types;
according to the pollutant types to be monitored of each pollution discharge unit, installing a corresponding emission sensor of each pollutant type for a pollution discharge point of each pollution discharge unit; for example, for the spot discharge of a steel mill, emission sensors to be installed include, but are not limited to, sulfur dioxide sensors, smoke concentration sensors, ammonia sensors, emission sensors corresponding to various harmful metals in slag, etc.;
the pollution monitoring distribution data comprise all pollutant types to be monitored of each pollution discharge unit;
In a preferred embodiment, the method of dividing the day into a plurality of discharge periods may be dividing the day into equal periods according to a preset discharge period duration; the preset discharge period duration may be set according to actual experience, for example, 1,2,3 hours, etc.;
in another preferred embodiment, the division of the daily into several discharge cycles may also be according to the working time, for example, division of the discharge cycles is performed at 8 to 12 am and 2 to 6 pm;
further, the method for collecting the historical emission training data of each pollution discharge unit based on the pollution monitoring distribution data is as follows:
several days were selected as the sample collection period, in each discharge cycle of each day of the sample collection period:
for each pollution discharge unit, using a discharge sensor corresponding to each pollutant type to be monitored in pollution monitoring distribution data to acquire the discharge of pollutants corresponding to each unit duration in real time; preferably, the unit time is a unit time length preset according to experience, and specifically, the unit time length can be every minute, every 5 minutes, every ten minutes or the like;
sequencing the emission of various pollutant types to be monitored acquired in the emission period according to a time sequence to obtain an emission time sequence of the various pollutant types to be monitored;
Normalizing the emission time sequence;
for the emission period of the pollution discharge unit per day in a sample collection time period, the emission time sequence of all pollutant types to be monitored forms historical emission training data;
further, the method for training a set of emission prediction models for each emission cycle of each emission unit based on the historical emission training data is as follows:
for each emission cycle of each emission unit, the type of pollutant to be monitored:
presetting a predicted time step, a sliding step and a sliding window length, converting an emission time sequence corresponding to the pollutant type to be monitored into a plurality of training samples by using a sliding window method, taking each group of training samples as input of an emission prediction model, taking the emission time sequence of the predicted time step in the future as output of the emission prediction model, taking the emission sequence in the predicted time step in the future of each training sample as a prediction target, and training the emission prediction model; generating an emission prediction model for predicting the emission of the type of pollutant to be monitored in a future prediction market; preferably, the emission prediction model is an RNN neural network model;
It should be noted that, the sliding window method is used as a conventional technical means of a cyclic neural network model or a time sequence prediction model, and the invention is not described in principle here; but for the purpose of facilitating the implementation of the invention, the invention provides the following examples regarding sliding window methods:
assuming we want to train a time prediction model with history data 1,2,3,4,5,6, set the prediction time step to 1, the sliding step to 1 and the sliding window length to 3; then 3 sets of training data and corresponding predicted target data are generated: [1,2,3], [2,3,4] and [3,4,5] are used as training data, and [4], [5] and [6] are respectively used as prediction targets;
further, the method for dividing the pollution discharge unit into a plurality of similar pollution discharge unit sets based on the pollution monitoring distribution data comprises the following steps:
grouping all the pollution discharge units according to grouping conditions with the same pollutant types to be monitored, and combining the same group of pollution discharge units into a similar pollution discharge unit set; namely, the pollution discharge units in each similar pollution discharge unit set have the same pollutant type to be monitored, so that pollutant discharge is integrated according to the discharge type, and enterprises and public institutions with the same discharge type are referred to each other;
Further, the method for further dividing the historical emission training data into a plurality of identical-cluster pollution discharge unit sets by using a clustering algorithm is as follows:
for each emission unit in each collection of like emission units:
calculating the average emission value of each pollutant type to be monitored of the pollution discharge unit in each emission period;
the emission average value is calculated in the following way:
counting the average value of emission time series of each pollutant type to be monitored of the pollution discharge unit in each emission period of each day; for example, counting the average value of the sulfur dioxide emission of a certain steel plant in the sample collection time period between 8 and 9 am;
in the sample collection time period, taking the average value of the discharge amounts of all pollutant types to be monitored as a discharge amount average value;
sequencing the discharge amount average value according to the time sequence of the discharge period for each pollutant type to be monitored of the pollution discharge unit to obtain a discharge amount average value sequence; for example, the average of sulfur dioxide emissions is ordered in the order of 0 point to 1 point, 1 point to 2 points;
normalizing the emission average value sequence; it can be understood that after normalization treatment, each emission average sequence will not have the difference of emission, so that the variation trend of emission can be better reflected, for example, the emission average sequence of sulfur dioxide in a certain steel plant can be [1,0.8,0.9,1.5], which reflects the emission trend;
For the pollution discharge unit, merging the emission average value sequences of the pollutant types to be monitored to obtain a clustering vector;
presetting the number K of cluster clusters;
for each collection of like blowdown units:
taking a clustering vector of each pollution discharge unit in the similar pollution discharge unit set as a data point;
using a clustering algorithm to all data points in the similar pollution discharge unit set to obtain K clustering clusters; specifically, the clustering algorithm can be a K-means or FCM algorithm;
each cluster corresponds to a same-cluster pollution discharge unit set, and the pollution discharge units in each same-cluster pollution discharge unit set are pollution discharge units corresponding to data points in the same cluster; it will be appreciated that the pollution units in each cluster will have similar industrial properties, e.g. similar products, similar production lines, similar pollutant discharge time fluctuations, thereby providing further reference value for the monitoring of the pollutants for the respective pollution units;
further, the manner of collecting the real-time emission data of each pollution discharge unit is as follows:
collecting, by respective emission sensors, emission time series of respective types of pollutants to be monitored of respective pollution discharge units at the beginning of each emission cycle;
Normalizing the emission period and the collected emission time sequence to obtain real-time emission data;
further, the method for obtaining the predicted emission value after the preset predicted time step based on the real-time emission data and the emission prediction model set is as follows:
for each contaminant type to be monitored:
taking a subsequence in the length of the nearest sliding window in a corresponding emission time sequence in the real-time emission data as input of an emission prediction model to obtain an emission sequence in a prediction time step output by the emission prediction model;
taking the last element in the output emission sequence as an emission predicted value;
further, the method for generating the analysis result of abnormal pollutant discharge comprises the following steps:
the number of the pollution discharge unit is marked as i, each pollutant type to be monitored of the ith pollution discharge unit is marked as Im, and the number of the pollutant types to be monitored of the ith pollution discharge unit is marked as Im;
marking an emissions prediction value of an im-th pollutant type to be monitored as pim, and marking the actual emissions collected after a predicted time step as rim;
marking the same cluster pollution discharge unit set where the ith pollution unit is positioned as Ti;
Calculating a predicted deviation value xim of the type of the im pollutant to be monitored, wherein the calculation formula of the predicted deviation value xim is as follows:；
calculating a predicted deviation value average value Wi of the ith pollution unit, wherein the calculation formula of the predicted deviation value average value Wi is as follows；
If the average Wi of the predicted deviation values of any pollution unit is larger than a preset first deviation value threshold, generating a corresponding abnormal analysis result of pollution emission for the average Wi of the predicted deviation values of any pollution unit;
specifically, the method for generating the corresponding analysis result of abnormal pollutant emission is as follows:
calculating the average value of the average values of the predicted deviation values of all the pollution discharge units in the same-cluster pollution discharge unit set Ti as a same-cluster deviation average value KTi;
if the difference value between the predicted deviation value average Wi and the same-cluster deviation average KTi is smaller than or equal to a preset second deviation threshold value, judging that the pollution discharge amount of the same-cluster pollution discharge unit set Ti is abnormal, and carrying out emission early warning on all pollution discharge units in the same-cluster pollution discharge unit set Ti;
if the difference value between the predicted deviation value average Wi and the same cluster deviation average KTi is larger than a preset second deviation threshold value, judging that the discharge amount of the pollution discharge unit is abnormal, and carrying out discharge early warning on the pollution discharge unit;
it can be understood that by integrating the same-cluster pollution discharge unit sets with similar emission properties for each pollution discharge unit, when any one pollution discharge unit has abnormal pollution discharge amount, the pollution discharge amount condition of the same-cluster pollution discharge unit set can be extendably investigated, so that the cause of abnormal pollution discharge amount can be rapidly analyzed, for example, the independent abnormal condition of the pollution discharge unit or the problem of abnormal pollution discharge units in batches caused by raw material problems, production line problems, time arrangement problems, large increase of the demand and the like can be solved, and the efficiency of locating the cause of abnormal pollutant discharge is improved.
Example 2: as shown in FIG. 2, the data integration processing system of the fixed pollution source comprises a pollution monitoring distribution data collection module, a historical emission data collection module, an emission quantity prediction model training module, a pollution discharge unit clustering module and an emission abnormal analysis result generation module; wherein, each module is electrically connected;
the pollution monitoring distribution data collection module is mainly used for collecting pollution discharge unit data, generating pollution monitoring distribution data for each pollution discharge unit based on the pollution discharge unit data, and sending the pollution monitoring distribution data to the historical emission data collection module and the pollution discharge unit clustering module;
the historical emission data collection module is mainly used for dividing each day into a plurality of emission periods, collecting historical emission training data of each pollution discharge unit based on pollution monitoring distribution data in each emission period, and sending all the historical emission training data to the emission quantity prediction model training module and the pollution discharge unit clustering module;
the emission prediction model training module is mainly used for training an emission prediction model set for each emission period of each pollution discharge unit based on historical emission training data, and sending the emission prediction model set to the emission anomaly analysis result generation module;
The pollution discharge unit clustering module is mainly used for dividing a pollution discharge unit into a plurality of similar pollution discharge unit sets based on pollution monitoring distribution data, for each similar pollution discharge unit set, further dividing all similar pollution discharge units into a plurality of same-cluster pollution discharge unit sets based on historical emission training data by using a clustering algorithm, and sending the same-cluster pollution discharge unit sets to the emission anomaly analysis result generation module;
the emission anomaly analysis result generation module is mainly used for collecting real-time emission data of each pollution discharge unit, obtaining emission predicted values after a preset predicted time step based on the real-time emission data and an emission prediction model set, and generating pollution emission anomaly analysis results based on the real-time emission data, the emission predicted values of each pollution discharge unit and the same-cluster pollution discharge unit set after the predicted time step.
Example 3: fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 3, an electronic device 100 is also provided according to yet another aspect of the present application. The electronic device 100 may include one or more processors and one or more memories. Wherein the memory has stored therein computer readable code which, when executed by the one or more processors, can perform the data integration processing method of the stationary pollution source as described above.
The method or system according to embodiments of the present application may also be implemented by means of the architecture of the electronic device shown in fig. 3. As shown in fig. 3, the electronic device 100 may include a bus 101, one or more CPUs 102, a Read Only Memory (ROM) 103, a Random Access Memory (RAM) 104, a communication port 105 connected to a network, an input/output component 106, a hard disk 107, and the like. A storage device in the electronic device 100, such as the ROM103 or the hard disk 107, may store the data integration processing method of the fixed pollution source provided herein. The data integration processing method of the fixed pollution source may, for example, include the following steps: step one: collecting pollution discharge unit data, and generating pollution monitoring distribution data for each pollution discharge unit based on the pollution discharge unit data; step two: dividing each day into a plurality of emission periods, and collecting historical emission training data of each pollution discharge unit based on pollution monitoring distribution data in each emission period; step three: training a set of emission prediction models for each emission cycle of each emission unit based on the historical emission training data; step four: dividing the pollution discharge units into a plurality of similar pollution discharge unit sets based on pollution monitoring distribution data, and further dividing all similar pollution discharge units into a plurality of similar cluster pollution discharge unit sets based on historical emission training data for each similar pollution discharge unit set by using a clustering algorithm; step five: collecting real-time emission data of each pollution discharge unit, and obtaining an emission quantity predicted value after a preset predicted time step based on the real-time emission data and an emission quantity predicted model set; step six: and after the predicted time step, generating a pollution discharge abnormality analysis result based on the real-time discharge data, the discharge quantity predicted value of each pollution discharge unit and the same cluster pollution discharge unit set.
Further, the electronic device 100 may also include a user interface 108. Of course, the architecture shown in fig. 3 is merely exemplary, and one or more components of the electronic device shown in fig. 3 may be omitted as may be practical in implementing different devices.
Example 4: fig. 4 is a schematic structural diagram of a computer readable storage medium according to an embodiment of the present application. As shown in fig. 4, is a computer-readable storage medium 200 according to one embodiment of the present application. The computer-readable storage medium 200 has stored thereon computer-readable instructions. The method of data integration processing of a stationary source of pollution according to embodiments of the present application described with reference to the above figures may be performed when the computer readable instructions are executed by a processor. Computer-readable storage medium 200 includes, but is not limited to, for example, volatile memory and/or nonvolatile memory. Volatile memory can include, for example, random Access Memory (RAM), cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like.
In addition, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, the present application provides a non-transitory machine-readable storage medium storing machine-readable instructions executable by a processor to perform instructions corresponding to the method steps provided herein, which when executed by a Central Processing Unit (CPU), perform the functions defined above in the methods of the present application.
The methods and apparatus, devices, and apparatus of the present application may be implemented in numerous ways. For example, the methods and apparatus, devices of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, firmware. The above-described sequence of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the sequence specifically described above unless specifically stated otherwise. Furthermore, in some embodiments, the present application may also be implemented as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present application. Thus, the present application also covers a recording medium storing a program for executing the method according to the present application.
In addition, in the foregoing technical solutions provided in the embodiments of the present application, parts consistent with implementation principles of corresponding technical solutions in the prior art are not described in detail, so that redundant descriptions are avoided.
The purpose, technical scheme and beneficial effects of the invention are further described in detail in the detailed description. It is to be understood that the above description is only of specific embodiments of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The above preset parameters or preset thresholds are set by those skilled in the art according to actual conditions or are obtained by mass data simulation.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (8)
1. The data integration processing method of the fixed pollution source is characterized by comprising the following steps of:
step one: collecting pollution discharge unit data, and generating pollution monitoring distribution data for each pollution discharge unit based on the pollution discharge unit data;
step two: dividing each day into a plurality of emission periods, and collecting historical emission training data of each pollution discharge unit based on pollution monitoring distribution data in each emission period;
step three: training a set of emission prediction models for each emission cycle of each emission unit based on the historical emission training data;
step four: dividing the pollution discharge units into a plurality of similar pollution discharge unit sets based on pollution monitoring distribution data, and further dividing all similar pollution discharge units into a plurality of similar cluster pollution discharge unit sets based on historical emission training data for each similar pollution discharge unit set by using a clustering algorithm;
Step five: collecting real-time emission data of each pollution discharge unit, and obtaining an emission quantity predicted value after a preset predicted time step based on the real-time emission data and an emission quantity predicted model set;
step six: generating a pollution emission anomaly analysis result based on the real-time emission data, emission predicted values of each pollution emission unit and the same cluster pollution emission unit set at the moment after the predicted time step;
the pollution monitoring distribution data is generated for each pollution discharge unit in the following way:
collecting the types of pollutants generated when different product types are produced, and taking the types of pollutants as the types of pollutants to be monitored of the product types;
according to the pollutant types to be monitored of each pollution discharge unit, installing a corresponding emission sensor of each pollutant type for a pollution discharge point of each pollution discharge unit;
the pollution monitoring distribution data comprise all pollutant types to be monitored of each pollution discharge unit;
the generation mode of the analysis result of the abnormal pollutant discharge is as follows:
the number of the pollution discharge unit is marked as i, each pollutant type to be monitored of the ith pollution discharge unit is marked as Im, and the number of the pollutant types to be monitored of the ith pollution discharge unit is marked as Im;
Marking an emissions prediction value of an im-th pollutant type to be monitored as pim, and marking the actual emissions collected after a predicted time step as rim;
marking the same cluster pollution discharge unit set where the ith pollution unit is positioned as Ti;
calculating a predicted deviation value xim of the type of the im pollutant to be monitored, wherein the calculation formula of the predicted deviation value xim is as follows:；
calculating a predicted deviation value average value Wi of the ith pollution unit, wherein the calculation formula of the predicted deviation value average value Wi is as follows ；
If the average Wi of the predicted deviation values of any pollution unit is larger than a preset first deviation value threshold, generating a corresponding abnormal analysis result of pollution emission for the average Wi of the predicted deviation values of any pollution unit;
the method for generating the corresponding analysis result of the abnormal pollutant emission comprises the following steps:
calculating the average value of the average values of the predicted deviation values of all the pollution discharge units in the same-cluster pollution discharge unit set Ti as a same-cluster deviation average value KTi;
if the difference value between the predicted deviation value average Wi and the same cluster deviation average KTi is smaller than or equal to a preset second deviation threshold value, carrying out emission early warning on all pollution discharge units in the same cluster pollution discharge unit set Ti;
and if the difference value between the predicted deviation value average Wi and the same cluster deviation average KTi is larger than a preset second deviation threshold value, carrying out emission early warning on the pollution discharge unit.
2. The method for integrating data of a fixed pollution source according to claim 1, wherein the means for collecting historical emission training data of each pollution discharge unit is as follows:
several days were selected as the sample collection period, in each discharge cycle of each day of the sample collection period:
for each pollution discharge unit, using a discharge sensor corresponding to each pollutant type to be monitored in pollution monitoring distribution data to acquire the discharge of pollutants corresponding to each unit duration in real time;
sequencing the emission of various pollutant types to be monitored acquired in the emission period according to a time sequence to obtain an emission time sequence of the various pollutant types to be monitored;
normalizing the emission time sequence;
for the emission cycle of the pollution discharge unit per day during a sample collection period, a time series of emissions for all pollutant types to be monitored constitutes historical emission training data.
3. The method for data integration processing of a stationary pollution source according to claim 2, wherein the training of a set of emission prediction models for each emission cycle of each pollution discharge unit is performed by:
For each emission cycle of each emission unit, the type of pollutant to be monitored:
presetting a predicted time step, a sliding step and a sliding window length, converting an emission time sequence corresponding to the pollutant type to be monitored into a plurality of training samples by using a sliding window method, taking each group of training samples as input of an emission prediction model, taking the emission time sequence of the predicted time step in the future as output of the emission prediction model, taking the emission sequence in the predicted time step in the future of each training sample as a prediction target, and training the emission prediction model;
the mode of dividing the sewage disposal unit into a plurality of similar sewage disposal unit sets is as follows:
grouping all the pollution discharge units according to grouping conditions with the same pollutant types to be monitored, and combining the same group of pollution discharge units into a same type of pollution discharge unit set.
4. The method for integrating and processing data of a fixed pollution source according to claim 3, wherein the method for further dividing the fixed pollution source into a plurality of identical-cluster pollution discharge unit sets by using a clustering algorithm is as follows:
For each emission unit in each collection of like emission units:
calculating the average emission value of each pollutant type to be monitored of the pollution discharge unit in each emission period;
sequencing the discharge amount average value according to the time sequence of the discharge period for each pollutant type to be monitored of the pollution discharge unit to obtain a discharge amount average value sequence;
normalizing the emission average value sequence;
for the pollution discharge unit, merging the emission average value sequences of the pollutant types to be monitored to obtain a clustering vector;
presetting the number K of cluster clusters;
for each collection of like blowdown units:
taking a clustering vector of each pollution discharge unit in the similar pollution discharge unit set as a data point;
and using a clustering algorithm for all data points in the similar pollution discharge unit set to obtain K clustering clusters.
5. The method for integrating data of a fixed pollution source according to claim 4, wherein the emission average is calculated by:
counting the average value of emission time series of each pollutant type to be monitored of the pollution discharge unit in each emission period of each day;
and in the statistical sample collection time period, taking the average value of the discharge amounts of the various pollutant types to be monitored as a discharge amount average value.
6. A data integration processing system of a fixed pollution source, which is realized based on the data integration processing method of the fixed pollution source according to any one of claims 1 to 5, and is characterized by comprising a pollution monitoring distribution data collection module, a historical emission data collection module, an emission quantity prediction model training module, a pollution discharge unit clustering module and an emission anomaly analysis result generation module; wherein, each module is electrically connected;
the pollution monitoring distribution data collection module is used for collecting pollution discharge unit data, generating pollution monitoring distribution data for each pollution discharge unit based on the pollution discharge unit data, and sending the pollution monitoring distribution data to the historical emission data collection module and the pollution discharge unit clustering module;
the historical emission data collection module is used for dividing each day into a plurality of emission periods, collecting historical emission training data of each pollution discharge unit based on pollution monitoring distribution data in each emission period, and sending all the historical emission training data to the emission quantity prediction model training module and the pollution discharge unit clustering module;
the emission prediction model training module is used for training an emission prediction model set for each emission period of each pollution discharge unit based on historical emission training data and sending the emission prediction model set to the emission anomaly analysis result generation module;
The pollution discharge unit clustering module is used for dividing the pollution discharge units into a plurality of similar pollution discharge unit sets based on pollution monitoring distribution data, further dividing all the similar pollution discharge units into a plurality of same-cluster pollution discharge unit sets based on historical emission training data, and sending the same-cluster pollution discharge unit sets to the emission anomaly analysis result generation module;
the emission anomaly analysis result generation module is used for collecting real-time emission data of each pollution discharge unit, obtaining emission quantity predicted values after a preset predicted time step based on the real-time emission data and the emission quantity predicted model set, and generating a pollution emission anomaly analysis result based on the real-time emission data, the emission quantity predicted values of each pollution discharge unit and the same-cluster pollution discharge unit set after the predicted time step.
7. An electronic device, comprising: a processor and a memory, wherein:
the memory stores a computer program which can be called by the processor;
the processor executes the data integration processing method of the stationary contamination source according to any one of claims 1 to 5 in the background by calling a computer program stored in the memory.
8. A computer readable storage medium having stored thereon a computer program that is erasable;
the computer program, when run on a computer device, causes the computer device to perform the data integration processing method of a stationary pollution source as claimed in any one of claims 1 to 5 in the background.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311594849.1A CN117312888B (en) | 2023-11-28 | 2023-11-28 | Data integration processing method and system for fixed pollution source |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311594849.1A CN117312888B (en) | 2023-11-28 | 2023-11-28 | Data integration processing method and system for fixed pollution source |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117312888A CN117312888A (en) | 2023-12-29 |
| CN117312888B true CN117312888B (en) | 2024-02-06 |
Family
ID=89255504
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311594849.1A Active CN117312888B (en) | 2023-11-28 | 2023-11-28 | Data integration processing method and system for fixed pollution source |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117312888B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101843879B1 (en) * | 2017-06-26 | 2018-03-30 | 한국환경공단 | System for detecting abnormality data, method thereof and computer recordable medium storing the method |
| CN113777236A (en) * | 2021-09-08 | 2021-12-10 | 中科三清科技有限公司 | Air quality monitoring method and device based on emission source |
| CN115689396A (en) * | 2022-12-30 | 2023-02-03 | 天津友美环保科技有限公司 | Pollutant discharge control method, device, equipment and medium |
| CN116626233A (en) * | 2023-05-08 | 2023-08-22 | 河北先河环保科技股份有限公司 | Air pollution tracing method based on multi-source data fusion, terminal and storage medium |
| CN116681187A (en) * | 2023-08-03 | 2023-09-01 | 北京滴普科技有限公司 | Enterprise carbon quota prediction method based on enterprise operation data |
| CN116720667A (en) * | 2023-08-10 | 2023-09-08 | 碳阻迹（北京）科技有限公司 | Intelligent enterprise carbon data management and control method and system based on big data analysis |
| CN117057668A (en) * | 2023-09-12 | 2023-11-14 | 河北工程大学 | Industrial pollutant emission prediction method based on deep learning model |
-
2023
- 2023-11-28 CN CN202311594849.1A patent/CN117312888B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101843879B1 (en) * | 2017-06-26 | 2018-03-30 | 한국환경공단 | System for detecting abnormality data, method thereof and computer recordable medium storing the method |
| CN113777236A (en) * | 2021-09-08 | 2021-12-10 | 中科三清科技有限公司 | Air quality monitoring method and device based on emission source |
| CN115689396A (en) * | 2022-12-30 | 2023-02-03 | 天津友美环保科技有限公司 | Pollutant discharge control method, device, equipment and medium |
| CN116626233A (en) * | 2023-05-08 | 2023-08-22 | 河北先河环保科技股份有限公司 | Air pollution tracing method based on multi-source data fusion, terminal and storage medium |
| CN116681187A (en) * | 2023-08-03 | 2023-09-01 | 北京滴普科技有限公司 | Enterprise carbon quota prediction method based on enterprise operation data |
| CN116720667A (en) * | 2023-08-10 | 2023-09-08 | 碳阻迹（北京）科技有限公司 | Intelligent enterprise carbon data management and control method and system based on big data analysis |
| CN117057668A (en) * | 2023-09-12 | 2023-11-14 | 河北工程大学 | Industrial pollutant emission prediction method based on deep learning model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117312888A (en) | 2023-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11156997B2 (en) | Systems and methods for artificial intelligence-based maintenance of an air conditioning system | |
| JP4762088B2 (en) | Process abnormality diagnosis device | |
| Marti-Puig et al. | Effects of the pre-processing algorithms in fault diagnosis of wind turbines | |
| US20210157310A1 (en) | System and method for forecasting industrial machine failures | |
| CN116975378B (en) | Equipment environment monitoring method and system based on big data | |
| EP4035008A2 (en) | Method and system for diagnosing anomaly in a manufacturing plant | |
| JP6756425B2 (en) | Energy saving diagnostic program | |
| CN116151621A (en) | Atmospheric pollution treatment risk detection system based on data analysis | |
| JP7273202B2 (en) | Method and system for performance optimization of flue gas desulfurization (FGD) units | |
| Vasilaki et al. | Data-driven versus conventional N2O EF quantification methods in wastewater; how can we quantify reliable annual EFs? | |
| CN115860427A (en) | Enterprise full-life-cycle carbon asset management system | |
| CN117312888B (en) | Data integration processing method and system for fixed pollution source | |
| CN117217419B (en) | Method and system for monitoring full life cycle carbon emission of industrial production | |
| CN112686433B (en) | Method, device, equipment and storage medium for predicting express quantity | |
| CN116843085B (en) | Freshwater fish growth monitoring method, device, equipment and storage medium | |
| CN116629642A (en) | Carbon emission assessment method, device and equipment | |
| CN116448234A (en) | Power transformer running state voiceprint monitoring method and system | |
| CN115342937A (en) | Temperature anomaly detection method and device | |
| CN105809304B (en) | Method for analyzing correlation of production operation parameters of power plant and pollution control facility | |
| Peruzzo et al. | Pattern-based feature extraction for fault detection in quality relevant process control | |
| CN111476433A (en) | Data analysis-based flue gas emission prediction method and system | |
| CN117035230B (en) | Sewage treatment equipment running state evaluation method based on big data analysis | |
| ul Hasan et al. | Malicious odor item identification using an electronic nose based on support vector machine classification | |
| WO2023175711A1 (en) | Plant structure corrosion prediction device, inference device, machine-learning device, information prediction device, plant structure corrosion prediction method, inference method, machine-learning method, and information prediction method | |
| Ruiz et al. | Advanced Machine Learning Techniques for Corrosion Rate Estimation and Prediction in Industrial Cooling Water Pipelines |
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 |