CN116589078A - Intelligent sewage treatment control method and system based on data fusion - Google Patents
Intelligent sewage treatment control method and system based on data fusion Download PDFInfo
- Publication number
- CN116589078A CN116589078A CN202310882447.5A CN202310882447A CN116589078A CN 116589078 A CN116589078 A CN 116589078A CN 202310882447 A CN202310882447 A CN 202310882447A CN 116589078 A CN116589078 A CN 116589078A
- Authority
- CN
- China
- Prior art keywords
- sewage
- variable
- real
- target
- time
- 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.)
- Granted
Links
- 239000010865 sewage Substances 0.000 title claims abstract description 318
- 238000000034 method Methods 0.000 title claims abstract description 56
- 230000004927 fusion Effects 0.000 title claims abstract description 23
- 238000012544 monitoring process Methods 0.000 claims abstract description 37
- 230000008569 process Effects 0.000 claims abstract description 24
- 238000010219 correlation analysis Methods 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims description 37
- 230000001364 causal effect Effects 0.000 claims description 26
- 239000003344 environmental pollutant Substances 0.000 claims description 25
- 231100000719 pollutant Toxicity 0.000 claims description 25
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 25
- 238000010586 diagram Methods 0.000 claims description 16
- 238000007689 inspection Methods 0.000 claims description 16
- 238000005070 sampling Methods 0.000 claims description 14
- 238000004519 manufacturing process Methods 0.000 claims description 13
- 239000000356 contaminant Substances 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 9
- 230000001419 dependent effect Effects 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 239000002351 wastewater Substances 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 5
- 238000005192 partition Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 238000005065 mining Methods 0.000 claims description 4
- 238000004065 wastewater treatment Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 7
- 238000004364 calculation method Methods 0.000 abstract 1
- 230000000875 corresponding effect Effects 0.000 description 30
- 238000004140 cleaning Methods 0.000 description 15
- 230000005856 abnormality Effects 0.000 description 9
- 230000008859 change Effects 0.000 description 8
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 description 5
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 5
- 239000001301 oxygen Substances 0.000 description 5
- 229910052760 oxygen Inorganic materials 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000012806 monitoring device Methods 0.000 description 4
- 239000000126 substance Substances 0.000 description 4
- 238000005259 measurement Methods 0.000 description 3
- 238000013480 data collection Methods 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004806 packaging method and process Methods 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 238000004062 sedimentation Methods 0.000 description 2
- 238000011166 aliquoting Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000010842 industrial wastewater Substances 0.000 description 1
- 230000007786 learning performance Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 238000003918 potentiometric titration Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000010802 sludge Substances 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F1/00—Treatment of water, waste water, or sewage
- C02F1/008—Control or steering systems not provided for elsewhere in subclass C02F
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F3/00—Biological treatment of water, waste water, or sewage
- C02F3/006—Regulation methods for biological treatment
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/001—Upstream control, i.e. monitoring for predictive control
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/02—Temperature
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/04—Oxidation reduction potential [ORP]
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/06—Controlling or monitoring parameters in water treatment pH
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/08—Chemical Oxygen Demand [COD]; Biological Oxygen Demand [BOD]
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/11—Turbidity
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/14—NH3-N
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/22—O2
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/40—Liquid flow rate
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/42—Liquid level
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Economics (AREA)
- Organic Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Hydrology & Water Resources (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Biodiversity & Conservation Biology (AREA)
- Microbiology (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Activated Sludge Processes (AREA)
Abstract
The application discloses an intelligent control method and system for sewage treatment based on data fusion, belonging to the field of intelligent control, wherein the method comprises the following steps: collecting historical pollution discharge records and real-time monitoring data of a target pollution discharge source, establishing a target pollution discharge database, and obtaining a target independent variable set through correlation analysis; judging whether the real-time variable belongs to a target independent variable set, if so, obtaining first real-time predicted sewage variable information through a prediction model; detecting the real-time sewage discharge of a target pollution source to obtain real-time target sewage variable information; performing union calculation on the first real-time predicted sewage variable information and the real-time target sewage variable information to obtain target sewage information to be treated; and generating a sewage treatment scheme according to the target sewage information to be treated, so as to realize intelligent control. The application solves the technical problem that the sewage treatment is difficult to be efficiently and accurately carried out in the prior art, and achieves the technical effect of realizing the automatic monitoring and the optimal control of the whole sewage treatment process based on data fusion.
Description
Technical Field
The application relates to the field of intelligent control, in particular to an intelligent sewage treatment control method and system based on data fusion.
Background
With the development of society and the improvement of living standard, the discharge amount of various industrial and domestic sewage is continuously increased, and serious threat is brought to water supply environment and human health. However, the existing sewage treatment system mainly depends on manual monitoring and determining operation parameters of sewage treatment equipment according to experience judgment, and efficient and accurate sewage treatment control is difficult to realize. Particularly, for industrial wastewater with large discharge amount and complex pollutant types, manual monitoring and control cannot meet the requirements of high frequency and quick response.
Disclosure of Invention
The application provides an intelligent control method and system for sewage treatment based on data fusion, and aims to solve the technical problem that in the prior art, sewage treatment is difficult to be performed efficiently and accurately.
In view of the above problems, the application provides an intelligent sewage treatment control method and system based on data fusion.
In a first aspect of the disclosure, an intelligent control method for sewage treatment based on data fusion is provided, and the method comprises the following steps: collecting historical pollution discharge record data of a target pollution discharge source and constructing a target pollution discharge database, wherein the target pollution discharge database refers to a historical pollution discharge time sequence with a pollution source variable identifier and a sewage variable identifier; performing correlation analysis on the pollution source variable and the sewage variable by using a target pollution discharge database to obtain an analysis result, and screening to obtain a target independent variable set based on the analysis result; dynamically monitoring a target pollution discharge source through a first sub-layout in the sub-sampling module to obtain real-time target pollution discharge variable information, wherein the real-time target pollution discharge variable information comprises a plurality of real-time variable data of a plurality of real-time variables; judging whether the real-time variables belong to a target independent variable set or not, if so, analyzing the real-time variable data through an analysis module to obtain first real-time predicted sewage variable information; dynamically detecting real-time discharged sewage of a target sewage source through a second sub-block in the sub-sampling module to obtain real-time target sewage variable information; performing union operation on the first real-time predicted sewage variable information and the real-time target sewage variable information to obtain target sewage information to be treated; the main control module generates a sewage treatment scheme based on the target sewage information to be treated, and treats the sewage discharged in real time according to the sewage treatment scheme.
In another aspect of the disclosure, an intelligent control system for sewage treatment based on data fusion is provided, the system comprising: the historical data acquisition module is used for acquiring historical pollution discharge record data of the target pollution discharge source and constructing a target pollution discharge database, wherein the target pollution discharge database refers to a historical pollution discharge time sequence with a pollution source variable identifier and a sewage variable identifier; the target independent variable set module is used for carrying out correlation analysis on the pollution source variable and the sewage variable by utilizing the target pollution discharge database to obtain an analysis result, and screening the analysis result to obtain a target independent variable set; the real-time pollution discharge information module is used for dynamically monitoring the target pollution discharge source through a first sub-layout in the sub-mining module to obtain real-time target pollution discharge variable information, wherein the real-time target pollution discharge variable information comprises a plurality of real-time variable data of a plurality of real-time variables; the sewage predicting variable module is used for judging whether the real-time variables belong to the target independent variable set or not, and if so, analyzing the real-time variable data through the analyzing module to obtain first real-time predicted sewage variable information; the sewage dynamic detection module is used for dynamically detecting the real-time discharged sewage of the target sewage source through the second sub-layout in the sub-sampling module to obtain real-time target sewage variable information; the information union operation module is used for performing union operation on the first real-time predicted sewage variable information and the real-time target sewage variable information to obtain target sewage information to be treated; the treatment scheme generation module is used for generating a sewage treatment scheme based on the target sewage information to be treated by the main control module and treating the sewage discharged in real time according to the sewage treatment scheme.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
because the historical pollution discharge record and real-time monitoring data of the target pollution discharge source are firstly collected, a target pollution discharge database is established, and a target independent variable set is obtained through correlation analysis; then, judging whether the real-time variable belongs to a target independent variable set, and if so, obtaining first real-time predicted sewage variable information through a prediction model; meanwhile, detecting the real-time sewage discharge of the target pollution source to obtain real-time target sewage variable information; then, carrying out union computation on the first real-time predicted sewage variable information and the real-time target sewage variable information to obtain target sewage information to be treated; finally, a sewage treatment scheme is generated according to the target sewage information to be treated, so that the technical scheme of intelligent control is realized, the technical problem that the sewage treatment is difficult to be efficiently and accurately carried out in the prior art is solved, and the technical effect of realizing automatic monitoring and optimal control of the whole sewage treatment process based on data fusion is achieved.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
FIG. 1 is a schematic diagram of a possible flow chart of an intelligent control method for sewage treatment based on data fusion according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a possible flow for obtaining a target independent variable set in a data fusion-based intelligent control method for sewage treatment according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a possible flow for adjusting a target independent variable set in an intelligent control method for sewage treatment based on data fusion according to an embodiment of the present application;
fig. 4 is a schematic diagram of a possible structure of an intelligent sewage treatment control system based on data fusion according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a historical data acquisition module 11, a target independent variable set module 12, a real-time pollution discharge information module 13, a predicted sewage variable module 14, a sewage dynamic detection module 15, an information union operation module 16 and a treatment scheme generation module 17.
Detailed Description
The technical scheme provided by the application has the following overall thought:
the embodiment of the application provides an intelligent sewage treatment control method and system based on data fusion. Firstly, historical data and real-time data are collected, a database is established, and a variable set is screened through correlation analysis, so that a foundation is provided for follow-up monitoring prediction and intelligent control. Then, judging real-time variables by utilizing a variable set, and if the real-time variables belong to the variable set, obtaining first real-time predicted sewage variable information through model prediction; and detecting and obtaining real-time target sewage variable information. And then, integrating the first real-time predicted sewage variable information with the real-time target sewage variable information by adopting a data fusion method to obtain accurate target sewage information to be treated. Finally, according to the target sewage information to be treated, the main control module generates a sewage treatment scheme in real time, so as to realize the optimal control of the sewage treatment process.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Embodiment one:
as shown in fig. 1, the embodiment of the application provides an intelligent control method for sewage treatment based on data fusion, which is applied to an intelligent control system for sewage treatment, wherein the intelligent control system for sewage treatment comprises a sub-sampling module, an analysis module and a main control module.
Specifically, the sub-sampling module is used for dynamically monitoring real-time variable information and real-time discharged sewage information of a target sewage source, comprises a first sub-section and a second sub-section, and is in communication connection with the multi-parameter water quality sensor to acquire dynamic real-time data. The first sub-block is used for monitoring real-time target pollution discharge variable information, such as production process variation; the second sub-section is used for monitoring real-time target sewage variable information, such as the type and the content of pollutants in sewage. The analysis module is used for analyzing the real-time variable data and obtaining first real-time predicted sewage variable information. The analysis module comprises a trained sewage prediction model, and can be obtained by training historical sewage discharge time sequence data. The sewage prediction model is established by adopting a neural network and is used for predicting sewage variables corresponding to the real-time variable data. The main control module generates a customized sewage treatment scheme based on the target sewage information to be treated and controls the real-time sewage treatment process.
The intelligent control method for sewage treatment comprises the following steps:
step S100: collecting historical pollution discharge record data of a target pollution discharge source and constructing a target pollution discharge database, wherein the target pollution discharge database refers to a historical pollution discharge time sequence with a pollution source variable identifier and a sewage variable identifier;
specifically, the target sewage source refers to a waste water source to be controlled and treated, such as a sewage treatment system of a municipal domestic sewage treatment plant, a waste water discharge system of an industrial enterprise, and the like. First, a target sewage source data collection range and content are determined. The historical pollution discharge record data of the target pollution discharge source comprises two aspects of data of pollution source variable identification and sewage variable identification. The pollution source variable marks generate sewage data such as production process variation, water and electricity consumption data and the like, and the sewage variable marks are specific data of the sewage itself such as the pH value, COD, ammonia nitrogen and the concentration of various pollutants of the sewage. And secondly, searching historical file data such as an environment monitoring report, an environment-friendly self-checking report, a production daily report and a production record of a target pollution discharge source, and extracting pollution source variable and sewage variable data related to sewage discharge from the historical file data.
And then, organizing the collected historical record data according to time sequence to form a complete target pollution discharge database comprising pollution source variables and sewage variables, recording sewage discharge characteristics of the target pollution discharge sources in different historical periods, and providing data support for subsequent analysis and prediction model training. Then, on the basis of the target pollution discharge database, the corresponding relation between the pollution source variable and the sewage variable is analyzed. For example, if a change in a process corresponds to a change in the concentration of a contaminant in the wastewater, a relationship between the process variable and the concentration of a contaminant variable is established, reflecting the inherent correlation between the variables, providing a basis for the analysis of the variables and the establishment of a predictive model.
Step S200: performing correlation analysis on the pollution source variable and the sewage variable by using the target pollution discharge database to obtain an analysis result, and screening to obtain a target independent variable set based on the analysis result;
specifically, firstly, respectively extracting pollution source variables related to production process change and equipment operation parameters and sewage variable data related to pH value, chemical oxygen demand and ammonia nitrogen concentration; secondly, calculating pearson correlation coefficients between each pollution source variable and each sewage variable, judging whether strong correlation exists between the variables, wherein the range of the pearson correlation coefficients is between-1 and 1, and the larger the absolute value is, the stronger the correlation is; then, taking the measured value of each pollution source variable as an x-axis, taking the measured value of the corresponding sewage variable as a y-axis, drawing a scatter diagram, observing whether clear correspondence exists between the variables by the scatter diagram, and judging the relativity between the variables; then, a pollution source variable with a high correlation with a plurality of sewage variables, such as pearson correlation coefficient not less than 0.7, is selected as a candidate independent variable. And then, in the candidate independent variables, checking whether the pearson correlation coefficient is more than or equal to 0.9 in high correlation among the variables, if so, removing some variables to avoid multiple collinearity, and finally determining that the variables which are highly correlated with the sewage variable and have no multiple collinearity form a target independent variable set.
Step S300: dynamically monitoring the target pollution discharge source through a first sub-layout in the sub-mining module to obtain real-time target pollution discharge variable information, wherein the real-time target pollution discharge variable information comprises a plurality of real-time variable data of a plurality of real-time variables;
specifically, a first sub-layout in the sub-sampling module is used for monitoring real-time target pollution discharge variable information. The real-time target blowdown variable information includes variables in the target independent variable set, and other variables related to production process or equipment parameters. Firstly, determining a specific monitoring method of each monitoring variable, such as installing an on-line monitoring device, such as a flowmeter, a liquid level meter and a thermometer, on a related pipeline and equipment of a target pollution discharge source, and detecting the flow, the liquid level and the temperature in a field pipeline; the camera is used for monitoring the operation of equipment in a certain process; and a communication interface with the PLC or the DCS is arranged for collecting process parameters of the PLC or the DCS system and the like. And through each monitoring device arranged on the target sewage source, data information such as flow, temperature, pressure, video images and the like is acquired in real time and transmitted to a first sub-layout of the sub-acquisition module in a wired or wireless mode in real time, so that real-time target sewage variable information is obtained.
Step S400: judging whether the real-time variables belong to the target independent variable set or not, if so, analyzing the real-time variable data through the analysis module to obtain first real-time predicted sewage variable information;
specifically, firstly, a plurality of variable data obtained by real-time monitoring are extracted, and the data are obtained by real-time monitoring of a first sub-section of the sub-sampling module and comprise a plurality of real-time variables. Then traversing the real-time variables, extracting the real-time variables one by one, searching in the target independent variable set, and if all the real-time variables exist in the target independent variable set, making the real-time variables belong to the target independent variable set.
The analysis module is used for analyzing the real-time variable data to obtain first real-time predicted sewage variable information, and the module comprises a sewage prediction model trained by utilizing the historical sewage discharge time sequence data and the neural network and is used for predicting sewage variables corresponding to the real-time variable data. When the real-time variables belong to the target independent variable set, the analysis module analyzes the real-time variables, and inputs the real-time variables into the sewage prediction model to obtain first real-time predicted sewage variable information.
The first real-time predicted sewage variable information refers to real-time sewage variable information which is predicted by an analysis module through a prediction model by utilizing real-time collected target sewage variable information, and comprises pollutant types, pollutant concentrations, PH values, water quality parameters, sewage flow and the like, and provides basis for the follow-up generation of a sewage treatment scheme, so that the accurate control of real-time discharged sewage is realized.
Step S500: dynamically detecting the real-time discharged sewage of the target sewage source through a second sub-layout in the sub-mining module to obtain real-time target sewage variable information;
specifically, first, monitoring parameters such as pH, chemical oxygen demand, ammonia nitrogen, and other major contaminant parameters are determined; the monitoring method is determined, such as pH value measurement by using a potentiometric titration method, ammonia nitrogen measurement by using an ion selective electrode, chemical oxygen demand measurement by using an ultraviolet spectrophotometer, and the like. Then, water quality monitoring devices corresponding to the monitoring parameters are deployed at the tail ends of the real-time sewage discharge pipelines or the treatment devices, each device carries out online monitoring, and monitoring results are transmitted to the second sub-section in real time. The second sub-block receives monitoring results transmitted by each water quality monitoring device in real time, such as pH value, ammonia nitrogen concentration, chemical oxygen demand and the like, and stores the monitoring results in a database in real time to form a real-time target sewage database. And then, checking and comparing the received monitoring results of the parameters, and identifying and eliminating data exceeding a normal range or obvious abnormality so as to avoid interference to subsequent analysis and processing. And then, extracting information such as pH value, main pollutant types, concentration and the like from a real-time target sewage database to form real-time target sewage variable information, and providing basis for the follow-up determination of sewage treatment schemes.
Step S600: performing union operation on the first real-time predicted sewage variable information and the real-time target sewage variable information to obtain target sewage information to be treated;
specifically, the first real-time predicted sewage variable information is real-time sewage variable information obtained by prediction using a real-time target independent variable as an input through a prediction model. The real-time target sewage variable information is actual real-time sewage variable information obtained through real-time monitoring of the second sub-edition. The two information are mutually supplemented, so that the singleness of the information is avoided, and the accuracy and the completeness of the information are improved.
Firstly, judging whether the first real-time predicted sewage variable information corresponds to a variable in the real-time target sewage variable information, and extracting the strain amount. For example, if the first real-time predicted wastewater variable information includes COD, BOD, NH-N and the real-time target wastewater variable information includes COD, BOD, TP, the corresponding variables COD and BOD can be extracted. And then, setting a difference threshold for each variable, and when the difference value of the corresponding variable exceeds the difference threshold, respectively calculating the values of the corresponding variable in the two sets of information, and taking the higher value as the value of the variable in the target sewage information to be treated. For example, if the COD value in the first real-time predicted sewage variable information is 1000mg/L and the COD value in the real-time target sewage variable information is 800mg/L, the COD value in the target sewage to be treated is 1000mg/L. And when the difference value of the corresponding variable does not exceed the difference value threshold, taking any variable in the difference value as the variable in the target sewage information to be treated. For example, if the NH3-N value in the first real-time predicted sewage variable information is 20mg/L, the NH3-N value in the target sewage to be treated is 20mg/L, and if the TP value in the real-time target sewage variable information is 0.5mg/L, the TP value in the target sewage to be treated is 0.5mg/L. Thereby obtaining the target sewage information to be treated.
Step S700: the main control module generates a sewage treatment scheme based on the target sewage information to be treated, and treats the real-time discharged sewage according to the sewage treatment scheme.
Specifically, the main control module firstly determines a sewage treatment scheme according to the pollutant types and the proportion of the pollutant types in the target sewage information to be treated. For example, if the target sewage to be treated shows that the content of COD and BOD in the sewage is higher, the main control module determines to adopt a biochemical treatment scheme; if the target sewage to be treated shows that the content of suspended matters in the sewage is higher, the main control module determines to adopt a turbidity removal scheme. The main control module is provided with a plurality of preset sewage treatment schemes, and the optimal scheme can be dynamically selected according to the target sewage information to be treated.
And then, the main control module sends a treatment instruction to the treatment equipment according to the selected sewage treatment scheme, and controls and adjusts the treatment equipment to treat the sewage discharged in real time. For example, if a biochemical treatment scheme is selected, the main control module controls and regulates the activated sludge tank and the sedimentation tank, and biochemical oxidation is performed on sewage, and then sedimentation and turbidity removal are performed; if the turbidity removing scheme is selected, the main control module increases dosage and dosing in the turbidity removing tank, controls the rotating speed of the reverse flow mixer and the like, and enhances the turbidity removing effect.
In the treatment process, the main control module continuously monitors the working state of the treatment equipment and the treatment effect of sewage. If the treatment effect is found to be poor, the main control module timely adjusts the sewage treatment scheme or corrects the working parameters of the treatment equipment, so that the sewage treatment can achieve the expected effect.
Further, the embodiment of the application further comprises:
step S110: extracting first historical blowdown data in the historical blowdown record data at a first period;
wherein the first historical blowdown data comprises first pollution source variable information and first sewage variable information;
the first pollution source variable information refers to variation information of a first pollution source production process;
wherein the first wastewater variable information includes a first contaminant species and a first contaminant content;
step S120: and constructing the historical pollution discharge time sequence according to a first corresponding relation among the first period, the first pollution source variable information, the first pollutant type and the first pollutant content.
Specifically, the first historical blowdown data includes first pollution source variable information and first sewage variable information. The first pollution source variable information refers to the production process of the first pollution source in the first period and the change information of related parameters. For example, if the first pollution source is a food manufacturing company, the first pollution source variable information is the cleaning process of the newly added packaging bottles in the first period, and the parameter information such as the number of the cleaning bottles, the unit water consumption and the like in the cleaning process; the first sewage variable information includes a first contaminant species and a first contaminant content emitted by the first source of contaminants during the first period, such as, for example, COD of 1000mg/L, BOD of 600mg/L, etc.
And then, according to the corresponding relation among the first pollution source variable information, the first pollutant type and the first pollutant content in the first period, constructing a historical pollution discharge time sequence. For example, the number of cleaning bottles is 200 per batch, the unit water consumption is 20 tons per batch, the COD value of the corresponding first pollutant is 1000mg/L, the BOD value is 600mg/L, and the corresponding relation is added to the historical sewage discharge time sequence.
The first pollution source production process change information, related parameters and corresponding sewage discharge information are systematically extracted from the historical pollution discharge record data, a historical pollution discharge time sequence is built according to the first pollution source production process change information, related parameters and corresponding sewage discharge information, and data support is provided for correlation analysis and target independent variable set determination.
Further, as shown in fig. 2, the embodiment of the present application further includes:
step S310: taking the first pollution source variable information in the first corresponding relation as an independent variable and the first pollutant type and the first pollutant content as dependent variables;
step S320: drawing a scatter diagram according to the mapping relation between the independent variable and the dependent variable;
step S330: extracting a first scatter plot of a first process index parameter from the scatter plot;
step S340: reading a preset meshing scheme, and meshing the first scatter diagram according to the preset meshing scheme to obtain a first partition result;
Step S350: calculating a first maximum mutual information value of a first zone in the first zone result, and comparing to obtain a first maximum information coefficient;
step S360: and if the first maximum information coefficient meets a preset coefficient threshold value, adding the first process index parameter to the target independent variable set.
Specifically, in order to obtain the target independent variable set through screening, correlation analysis is performed on the first corresponding relation. First, the first pollution source variable information in the first correspondence is used as an independent variable, and the first pollutant type and the first pollutant content are used as dependent variables. Then, a scatter diagram is drawn according to the mapping relation between the independent variable and the dependent variable. For example, the independent variable is the number of cleaning bottles, the dependent variable is the COD value, and a scatter diagram of the number of cleaning bottles versus the COD value can be drawn. Then, a first scattergram of the first process index parameter is extracted from the scattergrams. For example, a scattergram of the parameter of the number of cleaning bottles is extracted from the number of cleaning bottles-COD value scattergram.
Then, in order to grid-divide the first scattergram, a predetermined meshing scheme is read. For example, the predetermined meshing scheme is a 5*5 aliquoting scheme. Then, the first scatter diagram is grid-divided according to the scheme, and a first partition result is obtained, for example, the scatter diagram is divided into 25 cells. Next, a first maximum mutual information value of the first area in the first partition result, for example, the maximum mutual information value of the cell (1, 1) is 0.8, and is compared with a predetermined threshold value of 0.7, so as to obtain a first maximum information coefficient of 0.8/0.7=1.14. If the first maximum information coefficient meets a predetermined coefficient threshold, e.g., greater than 1, a corresponding parameter, such as the number of bottles purged, is added to the target set of arguments. And through comprehensive systematic correlation detection and screening of the first corresponding relation, a target independent variable set is finally determined, and a basis is provided for follow-up monitoring analysis and real-time control.
Further, as shown in fig. 3, the embodiment of the present application further includes:
step S361: sequentially taking each target independent variable in the target independent variable set as a conditional variable;
step S362: performing causal inspection on the condition variable based on the Grangel causal inspection principle to obtain an inspection result;
step S363: and adjusting the target independent variable set according to the test result.
Specifically, to further refine the target set of independent variables, causal verification is performed on the variables therein. And sequentially taking each target independent variable in the target independent variable set as a conditional variable to carry out causal inspection. For example, the target independent variable set contains two variables, namely the number of cleaning bottles and the water consumption, and the number of cleaning bottles is firstly used as a condition variable for causal inspection, and then the water consumption is used as the condition variable for causal inspection.
Then, firstly determining a condition variable X and a result variable Y, wherein the condition variable X is the number of cleaning bottles, and the result variable Y is the COD value; collecting historical monitoring data of the condition variable X and the result variable Y, such as the number of cleaning bottles and COD value from 2017, 1 to 2018, 12; checking abnormal time of the condition variable X, for example, the number of the cleaning bottles in 5 months in 2017 shows a trend of abrupt increase, and determining the abnormal time; checking the performance of the result variable Y after the determined abnormal moment of the condition variable X, for example checking the COD value after 5 months in 2017, if the COD value also shows sudden increase after 5 months in 2017, the abnormality of X is prior to the abnormality of Y; if the test result meets the condition that the X abnormality precedes the Y abnormality, judging that a causal relationship exists between the condition variable X and the result variable Y; otherwise, judging that the causal relationship between the two is not obvious; then, further calculating the time difference between the abnormality of the condition variable X and the abnormality of the result variable Y to judge the strength of the causal relationship between the condition variable X and the result variable Y, wherein the shorter the time difference is, the stronger the causal relationship is; the judgment results are summarized, and as a result of causal examination between the condition variable X and the result variable Y, for example, there is a strong causal relationship between X (number of cleaned bottles) and Y (COD value), and the time difference between X abnormality and Y abnormality is 2 days. And repeatedly checking other condition variables to obtain a final checking result.
Then, reading a causal test result, and judging the causal relation between each variable in the target independent variable set and the result variable, for example, a strong causal relation exists between the variable 1 (the number of cleaning bottles) and the result variable (COD value); the causal relationship between the variable 2 (water consumption) and the result variable (COD value) is not obvious, etc. If the causal relationship between a variable and an outcome variable is strong or exists, the variable is retained; if the causal relationship is not obvious, the variable is removed from the target set of independent variables, e.g., variable 1 (number of bottles washed) is retained in the target set of independent variables, and variable 2 (water usage) is removed from the target set of independent variables. If causal relation exists between the rejected variables and other result variables, the rejected variables are reserved as independent variables of the other result variables; if there is no causal relationship with all the result variables, the variables are completely rejected.
The condition variable is subjected to causal inspection based on the Granges causal inspection principle, the target independent variable set is adjusted according to the inspection result, and key independent variable support is provided for subsequent monitoring analysis and control.
Further, the embodiment of the application further comprises:
Step S410: constructing a data set by utilizing the historical pollution discharge time sequence;
step S420: and performing supervised learning, training and checking on the data set based on a neural network principle to obtain a sewage prediction model, and storing the sewage prediction model into the analysis module.
Specifically, in order to realize real-time prediction of a target pollution discharge source, a sewage prediction model is constructed. The historical sewage discharge time sequence comprises the corresponding relation between pollution source variable information and corresponding sewage variable information of the target sewage discharge source in different periods. Based on the method, pollution source variables in a plurality of periods can be extracted as input variables, and corresponding sewage variables are taken as output variables to form a data set.
And based on the neural network principle, performing supervised learning, training and inspection on the data set to obtain a sewage prediction model. The supervised learning process adopts a BP neural network, inputs pollution source variables extracted from a data set, and learns a mapping relation between the two through training of the network; the training process continuously adjusts the network weight and the threshold value, reduces the training error and optimizes the network learning performance; and in the checking process, a part of data in the data set is used for checking the trained network, the prediction performance of the trained network is estimated, if the checking result is poor, the weight is required to be re-adjusted for retraining, and finally, a sewage prediction model with good performance can be obtained, and then, the sewage prediction model is stored in an analysis module for predicting sewage information in real time.
By constructing the sewage prediction model, the real-time sewage discharge condition of the target sewage discharge source can be accurately predicted, key information is provided for the main control module, and a targeted treatment scheme is generated, so that the initiative of pollution control is improved, and the pollution loss is reduced to the greatest extent.
Further, the embodiment of the application further comprises:
step S430: if at least one real-time variable in the plurality of real-time variables does not belong to the target independent variable set, marking the real-time variable as a variable to be evaluated;
step S440: removing the variables to be evaluated in the real-time variables to obtain variables to be predicted, and matching the variable data to be predicted of the variables to be predicted;
step S450: analyzing the variable data to be predicted through the sewage prediction model to obtain second real-time predicted sewage variable information;
step S460: acquiring sewage variable deviation between the second real-time predicted sewage variable information and the real-time target sewage variable information;
step S470: and establishing a second corresponding relation between the sewage variable deviation and the variable to be evaluated, and adding the second corresponding relation to the historical sewage discharge time sequence.
Specifically, in order to accurately predict the real-time pollution discharge condition in the target pollution discharge source, the sewage prediction model is upgraded. Firstly, judging whether at least one real-time variable in a plurality of real-time variables does not belong to a target independent variable set, and if so, recording the real-time variable as a variable to be evaluated. And then eliminating the variables to be evaluated in the real-time variables to obtain the variables to be predicted and the data thereof. And analyzing the variable data to be predicted through the sewage prediction model to obtain second real-time predicted sewage variable information. And meanwhile, obtaining the sewage variable deviation between the second real-time predicted sewage variable information and the real-time target sewage variable information, wherein for example, the predicted value of COD is 1000mg/L, the actual measured value is 1080mg/L, and the sewage variable deviation of COD is 80mg/L. Then, a second corresponding relation between the sewage variable deviation and the variable to be evaluated is established, for example, the sewage variable deviation COD is 80mg/L, and the cleaning quantity of the packaging bottles of the variable to be evaluated is increased by 10%. And adding the second corresponding relation to the historical pollution discharge time sequence.
By updating and upgrading the sewage prediction model according to actual variables, the function of the sewage prediction model is played to the greatest extent, high-precision real-time pollution discharge monitoring and early warning are realized, key information is provided for the main control module, targeted early warning and treatment are implemented, and environmental loss is reduced.
Further, the embodiment of the application further comprises:
step S510: the second sub-block is in communication connection with the multi-parameter water quality sensor.
Specifically, the second sub-block is in communication connection with the multi-parameter water quality sensor to obtain real-time water quality parameter information. The second sub-section establishes communication connection with a multi-parameter water quality sensor arranged in a sewage pipe network or a treatment facility through a wireless communication module or a wired interface. The multi-parameter water quality sensor can detect a plurality of parameters in water quality, such as pH value, dissolved oxygen, conductivity, turbidity, COD, BOD and the like. Through communication connection, the second sub-block can read all water quality parameter information acquired by the multi-parameter water quality sensor in real time, and then the obtained real-time water quality parameter information can be provided for the main control module for finding abnormal change of sewage quality through analyzing the change trend of the water quality parameter, taking countermeasures in time, intervening the working state of sewage treatment equipment, introducing specialized treatment process, enabling the water quality parameter to be quickly recovered to be normal, and avoiding further expansion of pollution loss.
In summary, the intelligent control method for sewage treatment based on data fusion provided by the embodiment of the application has the following technical effects:
collecting historical pollution discharge record data of a target pollution discharge source and constructing a target pollution discharge database, wherein the target pollution discharge database refers to a historical pollution discharge time sequence with a pollution source variable identifier and a sewage variable identifier, and a data base is provided for subsequent sewage analysis and construction of a prediction model; performing correlation analysis on pollution source variables and sewage variables by using a target pollution discharge database to obtain analysis results, screening to obtain a target independent variable set based on the analysis results, and providing an acquisition direction for collecting sewage prediction information and real-time information; dynamically monitoring a target sewage source through a first sub-layout in the sub-sampling module to obtain real-time target sewage variable information, wherein the real-time target sewage variable information comprises a plurality of real-time variable data of a plurality of real-time variables, and a data basis is provided for obtaining target sewage information to be processed; judging whether the real-time variables belong to a target independent variable set or not, if so, analyzing the real-time variable data through an analysis module to obtain first real-time predicted sewage variable information, and obtaining predicted related information of sewage; dynamically detecting real-time discharged sewage of a target sewage source through a second sub-layout in the sub-sampling module, and providing a data basis for obtaining the information of the target sewage to be treated; performing union operation on the first real-time predicted sewage variable information and the real-time target sewage variable information to obtain target sewage information to be treated, and providing support for a targeted sewage treatment scheme; the main control module generates a sewage treatment scheme based on target sewage information to be treated, and treats the sewage discharged in real time according to the sewage treatment scheme, so that the automatic monitoring and optimal control of the whole sewage treatment process are realized based on data fusion.
Embodiment two:
based on the same inventive concept as the intelligent control method for sewage treatment based on data fusion in the foregoing embodiment, as shown in fig. 4, an embodiment of the present application provides an intelligent control system for sewage treatment based on data fusion, which includes:
the historical data acquisition module 11 is used for acquiring historical pollution discharge record data of a target pollution discharge source and constructing a target pollution discharge database, wherein the target pollution discharge database refers to a historical pollution discharge time sequence with a pollution source variable identifier and a sewage variable identifier;
a target independent variable set module 12, configured to perform correlation analysis on the pollution source variable and the sewage variable by using the target pollution discharge database, obtain an analysis result, and screen to obtain a target independent variable set based on the analysis result;
the real-time pollution discharge information module 13 is configured to dynamically monitor the target pollution discharge source through a first sub-layout in the sub-sampling module to obtain real-time target pollution discharge variable information, where the real-time target pollution discharge variable information includes a plurality of real-time variable data of a plurality of real-time variables;
the predicted sewage variable module 14 is configured to determine whether the multiple real-time variables all belong to the target independent variable set, and if so, analyze the multiple real-time variable data through the analysis module to obtain first real-time predicted sewage variable information;
The sewage dynamic detection module 15 is used for dynamically detecting the real-time discharged sewage of the target sewage source through the second sub-layout in the sub-sampling module to obtain real-time target sewage variable information;
the information union operation module 16 is configured to perform union operation on the first real-time predicted sewage variable information and the real-time target sewage variable information to obtain target sewage information to be treated;
and the treatment scheme generating module 17 is used for generating a sewage treatment scheme by the main control module based on the target sewage information to be treated and treating the real-time discharged sewage according to the sewage treatment scheme.
Further, the historical data collection module 11 includes the following steps:
extracting first historical blowdown data in the historical blowdown record data at a first period;
wherein the first historical blowdown data comprises first pollution source variable information and first sewage variable information;
the first pollution source variable information refers to variation information of a first pollution source production process;
wherein the first wastewater variable information includes a first contaminant species and a first contaminant content;
and constructing the historical pollution discharge time sequence according to a first corresponding relation among the first period, the first pollution source variable information, the first pollutant type and the first pollutant content.
Further, the real-time blowdown information module 13 includes the following steps:
taking the first pollution source variable information in the first corresponding relation as an independent variable and the first pollutant type and the first pollutant content as dependent variables;
drawing a scatter diagram according to the mapping relation between the independent variable and the dependent variable;
extracting a first scatter plot of a first process index parameter from the scatter plot;
reading a preset meshing scheme, and meshing the first scatter diagram according to the preset meshing scheme to obtain a first partition result;
calculating a first maximum mutual information value of a first zone in the first zone result, and comparing to obtain a first maximum information coefficient;
and if the first maximum information coefficient meets a preset coefficient threshold value, adding the first process index parameter to the target independent variable set.
Further, the real-time pollution discharge information module 13 further includes the following steps:
sequentially taking each target independent variable in the target independent variable set as a conditional variable;
performing causal inspection on the condition variable based on the Grangel causal inspection principle to obtain an inspection result;
and adjusting the target independent variable set according to the test result.
Further, the predicted sewage variable module 14 includes the following execution steps:
constructing a data set by utilizing the historical pollution discharge time sequence;
and performing supervised learning, training and checking on the data set based on a neural network principle to obtain a sewage prediction model, and storing the sewage prediction model into the analysis module.
Further, the predicted sewage variable module 14 further includes the following execution steps:
if at least one real-time variable in the plurality of real-time variables does not belong to the target independent variable set, marking the real-time variable as a variable to be evaluated;
removing the variables to be evaluated in the real-time variables to obtain variables to be predicted, and matching the variable data to be predicted of the variables to be predicted;
analyzing the variable data to be predicted through the sewage prediction model to obtain second real-time predicted sewage variable information;
acquiring sewage variable deviation between the second real-time predicted sewage variable information and the real-time target sewage variable information;
and establishing a second corresponding relation between the sewage variable deviation and the variable to be evaluated, and adding the second corresponding relation to the historical sewage discharge time sequence.
Further, the sewage dynamic detection module 15 includes the following:
The second sub-block is in communication connection with the multi-parameter water quality sensor.
Any of the steps of the methods described above may be stored as computer instructions or programs in a non-limiting computer memory and may be called by a non-limiting computer processor to identify any method for implementing an embodiment of the present application, without unnecessary limitations.
Further, the first or second element may not only represent a sequential relationship, but may also represent a particular concept, and/or may be selected individually or in whole among a plurality of elements. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (8)
1. The intelligent control method for sewage treatment based on data fusion is characterized by comprising the following steps:
collecting historical pollution discharge record data of a target pollution discharge source and constructing a target pollution discharge database, wherein the target pollution discharge database refers to a historical pollution discharge time sequence with a pollution source variable identifier and a sewage variable identifier;
Performing correlation analysis on the pollution source variable and the sewage variable by using the target pollution discharge database to obtain an analysis result, and screening to obtain a target independent variable set based on the analysis result;
dynamically monitoring the target pollution discharge source through a first sub-layout in the sub-sampling module to obtain real-time target pollution discharge variable information, wherein the real-time target pollution discharge variable information comprises a plurality of real-time variable data of a plurality of real-time variables;
judging whether the real-time variables belong to the target independent variable set or not, if so, analyzing the real-time variable data through an analysis module to obtain first real-time predicted sewage variable information;
dynamically detecting the real-time discharged sewage of the target sewage source through a second sub-layout in the sub-mining module to obtain real-time target sewage variable information;
performing union operation on the first real-time predicted sewage variable information and the real-time target sewage variable information to obtain target sewage information to be treated;
the main control module generates a sewage treatment scheme based on the target sewage information to be treated, and treats the real-time discharged sewage according to the sewage treatment scheme.
2. The intelligent control method for sewage treatment according to claim 1, wherein the step of collecting the historical sewage record data of the target sewage source and constructing the target sewage database comprises the steps of:
extracting first historical blowdown data in the historical blowdown record data at a first period;
wherein the first historical blowdown data comprises first pollution source variable information and first sewage variable information;
the first pollution source variable information refers to variation information of a first pollution source production process;
wherein the first wastewater variable information includes a first contaminant species and a first contaminant content;
and constructing the historical pollution discharge time sequence according to a first corresponding relation among the first period, the first pollution source variable information, the first pollutant type and the first pollutant content.
3. The intelligent control method for sewage treatment according to claim 2, wherein the screening to obtain the target independent variable set based on the analysis result comprises:
taking the first pollution source variable information in the first corresponding relation as an independent variable and the first pollutant type and the first pollutant content as dependent variables;
Drawing a scatter diagram according to the mapping relation between the independent variable and the dependent variable;
extracting a first scatter plot of a first process index parameter from the scatter plot;
reading a preset meshing scheme, and meshing the first scatter diagram according to the preset meshing scheme to obtain a first partition result;
calculating a first maximum mutual information value of a first zone in the first zone result, and comparing to obtain a first maximum information coefficient;
and if the first maximum information coefficient meets a preset coefficient threshold value, adding the first process index parameter to the target independent variable set.
4. The intelligent control method for wastewater treatment according to claim 3, wherein said adding the first process index parameter to the target independent variable set further comprises:
sequentially taking each target independent variable in the target independent variable set as a conditional variable;
performing causal inspection on the condition variable based on the Grangel causal inspection principle to obtain an inspection result;
and adjusting the target independent variable set according to the test result.
5. The intelligent control method for sewage treatment according to claim 1, wherein before the analyzing the plurality of real-time variable data by the analyzing module to obtain the first real-time predicted sewage variable information, the method comprises:
Constructing a data set by utilizing the historical pollution discharge time sequence;
and performing supervised learning, training and checking on the data set based on a neural network principle to obtain a sewage prediction model, and storing the sewage prediction model into the analysis module.
6. The intelligent control method for sewage treatment according to claim 5, further comprising, after said determining whether said plurality of real-time variables all belong to said target independent variable set:
if at least one real-time variable in the plurality of real-time variables does not belong to the target independent variable set, marking the real-time variable as a variable to be evaluated;
removing the variables to be evaluated in the real-time variables to obtain variables to be predicted, and matching the variable data to be predicted of the variables to be predicted;
analyzing the variable data to be predicted through the sewage prediction model to obtain second real-time predicted sewage variable information;
acquiring sewage variable deviation between the second real-time predicted sewage variable information and the real-time target sewage variable information;
and establishing a second corresponding relation between the sewage variable deviation and the variable to be evaluated, and adding the second corresponding relation to the historical sewage discharge time sequence.
7. The intelligent control method for sewage treatment according to claim 1, wherein the second sub-block is in communication connection with a multiparameter water quality sensor.
8. The intelligent control system for sewage treatment based on data fusion, which is used for implementing the intelligent control method for sewage treatment based on data fusion according to any one of claims 1 to 7, and comprises the following steps:
the system comprises a historical data acquisition module, a target pollution discharge database and a sewage variable identification module, wherein the historical data acquisition module is used for acquiring historical pollution discharge record data of a target pollution discharge source and constructing the target pollution discharge database, and the target pollution discharge database refers to a historical pollution discharge time sequence with the pollution source variable identification and the sewage variable identification;
the target independent variable set module is used for carrying out correlation analysis on the pollution source variable and the sewage variable by utilizing the target pollution discharge database to obtain an analysis result, and screening the analysis result to obtain a target independent variable set;
the real-time pollution discharge information module is used for dynamically monitoring the target pollution discharge source through a first sub-layout in the sub-sampling module to obtain real-time target pollution discharge variable information, wherein the real-time target pollution discharge variable information comprises a plurality of real-time variable data of a plurality of real-time variables;
The predicted sewage variable module is used for judging whether the plurality of real-time variables belong to the target independent variable set or not, and if so, analyzing the plurality of real-time variable data through the analysis module to obtain first real-time predicted sewage variable information;
the sewage dynamic detection module is used for dynamically detecting the real-time discharged sewage of the target sewage source through a second sub-layout in the sub-sampling module to obtain real-time target sewage variable information;
the information union operation module is used for performing union operation on the first real-time predicted sewage variable information and the real-time target sewage variable information to obtain target sewage information to be treated;
the treatment scheme generation module is used for generating a sewage treatment scheme based on the target sewage information to be treated by the main control module and treating the real-time discharged sewage according to the sewage treatment scheme.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310882447.5A CN116589078B (en) | 2023-07-19 | 2023-07-19 | Intelligent sewage treatment control method and system based on data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310882447.5A CN116589078B (en) | 2023-07-19 | 2023-07-19 | Intelligent sewage treatment control method and system based on data fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116589078A true CN116589078A (en) | 2023-08-15 |
| CN116589078B CN116589078B (en) | 2023-09-26 |
Family
ID=87606626
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310882447.5A Active CN116589078B (en) | 2023-07-19 | 2023-07-19 | Intelligent sewage treatment control method and system based on data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116589078B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117111450A (en) * | 2023-10-19 | 2023-11-24 | 中国标准化研究院 | Intelligent control method and system for environmental pollution treatment equipment |
| CN118092349A (en) * | 2024-02-28 | 2024-05-28 | 中国市政工程西南设计研究总院有限公司 | Sewage treatment plant operation system and control method |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130204831A1 (en) * | 2011-11-04 | 2013-08-08 | David N. Reshef | Identifying associations in data |
| CN106779165A (en) * | 2016-11-21 | 2017-05-31 | 山东大学 | Power system environment dispatching method based on urban air-quality Predicting Technique |
| CN111461167A (en) * | 2020-03-02 | 2020-07-28 | 平安国际智慧城市科技股份有限公司 | Pollution source positioning method, device, equipment and storage medium based on big data |
| CN112308273A (en) * | 2019-07-31 | 2021-02-02 | 中国石油化工股份有限公司 | Memory, petrochemical enterprise pollution discharge management method, device and equipment |
| CN112651553A (en) * | 2020-12-24 | 2021-04-13 | 航天科工网络信息发展有限公司 | Urban atmospheric pollution early warning supervision and decision analysis method |
| CN113608477A (en) * | 2021-08-06 | 2021-11-05 | 张佳 | Integration sewage management and control platform |
| CN114049134A (en) * | 2021-11-09 | 2022-02-15 | 重庆商勤科技有限公司 | Pollution source online monitoring data counterfeiting identification method |
| CN115276006A (en) * | 2022-09-26 | 2022-11-01 | 江苏永鼎股份有限公司 | Load prediction method and system for power integration system |
| CN115578015A (en) * | 2022-12-07 | 2023-01-06 | 华南理工大学 | Sewage treatment overall process supervision method and system based on Internet of things and storage medium |
| CN116089218A (en) * | 2023-02-10 | 2023-05-09 | 杭州谐云科技有限公司 | Dynamic baseline alarm method and system based on Kubernetes historical data and trend analysis |
| WO2023123779A1 (en) * | 2021-12-30 | 2023-07-06 | 无锡雪浪数制科技有限公司 | Dynamic system identification-based product quality prediction method and device for rectification column |
| CN116451035A (en) * | 2023-04-25 | 2023-07-18 | 国网安徽省电力有限公司电力科学研究院 | Data characteristic engineering processing method for improving distributed photovoltaic prediction precision |
-
2023
- 2023-07-19 CN CN202310882447.5A patent/CN116589078B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130204831A1 (en) * | 2011-11-04 | 2013-08-08 | David N. Reshef | Identifying associations in data |
| CN106779165A (en) * | 2016-11-21 | 2017-05-31 | 山东大学 | Power system environment dispatching method based on urban air-quality Predicting Technique |
| CN112308273A (en) * | 2019-07-31 | 2021-02-02 | 中国石油化工股份有限公司 | Memory, petrochemical enterprise pollution discharge management method, device and equipment |
| CN111461167A (en) * | 2020-03-02 | 2020-07-28 | 平安国际智慧城市科技股份有限公司 | Pollution source positioning method, device, equipment and storage medium based on big data |
| CN112651553A (en) * | 2020-12-24 | 2021-04-13 | 航天科工网络信息发展有限公司 | Urban atmospheric pollution early warning supervision and decision analysis method |
| CN113608477A (en) * | 2021-08-06 | 2021-11-05 | 张佳 | Integration sewage management and control platform |
| CN114049134A (en) * | 2021-11-09 | 2022-02-15 | 重庆商勤科技有限公司 | Pollution source online monitoring data counterfeiting identification method |
| WO2023123779A1 (en) * | 2021-12-30 | 2023-07-06 | 无锡雪浪数制科技有限公司 | Dynamic system identification-based product quality prediction method and device for rectification column |
| CN115276006A (en) * | 2022-09-26 | 2022-11-01 | 江苏永鼎股份有限公司 | Load prediction method and system for power integration system |
| CN115578015A (en) * | 2022-12-07 | 2023-01-06 | 华南理工大学 | Sewage treatment overall process supervision method and system based on Internet of things and storage medium |
| CN116089218A (en) * | 2023-02-10 | 2023-05-09 | 杭州谐云科技有限公司 | Dynamic baseline alarm method and system based on Kubernetes historical data and trend analysis |
| CN116451035A (en) * | 2023-04-25 | 2023-07-18 | 国网安徽省电力有限公司电力科学研究院 | Data characteristic engineering processing method for improving distributed photovoltaic prediction precision |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117111450A (en) * | 2023-10-19 | 2023-11-24 | 中国标准化研究院 | Intelligent control method and system for environmental pollution treatment equipment |
| CN117111450B (en) * | 2023-10-19 | 2023-12-22 | 中国标准化研究院 | Intelligent control method and system for environmental pollution treatment equipment |
| CN118092349A (en) * | 2024-02-28 | 2024-05-28 | 中国市政工程西南设计研究总院有限公司 | Sewage treatment plant operation system and control method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116589078B (en) | 2023-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116589078B (en) | Intelligent sewage treatment control method and system based on data fusion | |
| CN114297954B (en) | Big data intelligent analysis digital control platform based on sewage treatment plant | |
| Regmi et al. | The future of WRRF modelling–outlook and challenges | |
| Yel et al. | Prediction of primary treatment effluent parameters by Fuzzy Inference System (FIS) approach | |
| CN112591820B (en) | Industrial wastewater sorting and recycling system based on automatic control | |
| CN112417765B (en) | Sewage treatment process fault detection method based on improved teacher-student network model | |
| CN118071177B (en) | Sewage treatment simulation regulation and control method and system | |
| CN117170221A (en) | Artificial intelligence control system for sewage treatment | |
| CN118445581B (en) | Sewage treatment process monitoring system and method based on data identification | |
| Bonastre et al. | In-line chemical analysis of wastewater: present and future trends | |
| CN117892094A (en) | Sewage operation and maintenance platform big data analysis system | |
| CN118350510A (en) | Rainwater utilization method based on multistage purification technology of rainwater collection system | |
| CN117964023A (en) | Sewage treatment control system based on artificial intelligence algorithm control | |
| CN113838542A (en) | Intelligent prediction method and system for chemical oxygen demand | |
| CN117196883A (en) | Sewage treatment decision optimization method and system based on artificial intelligence | |
| CN114149076B (en) | Intelligent debugging system of anaerobic ammonia oxidation sewage treatment system | |
| CN114971164B (en) | Artificial intelligence-based method and system for detecting abnormality of sludge treatment equipment | |
| CN114693493A (en) | IoT-based polluted river water ecological restoration system | |
| CN111007220B (en) | Method for agile monitoring of water quality of live pig breeding sewage | |
| Chi et al. | Wastewater treatment sensor fault detection using RBF neural network with set membership estimation | |
| CN118471388B (en) | Ship sewage treatment analysis system and method based on data identification | |
| Wärff | Operational digital twins for water resource recovery facilities–Rationale, components, and case studies | |
| Juuso et al. | Intelligent analysers and dynamic simulation in a biological water treatment process | |
| CN118619505A (en) | Automatic sludge treatment method, device, computer equipment and storage medium | |
| CN117870034B (en) | Control method, device and system for environmental parameters of clean room |
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 |