CN113687040A - Decision tree algorithm-based water plant real-time dosing quantity prediction method, device and medium - Google Patents
Decision tree algorithm-based water plant real-time dosing quantity prediction method, device and medium Download PDFInfo
- Publication number
- CN113687040A CN113687040A CN202110857782.0A CN202110857782A CN113687040A CN 113687040 A CN113687040 A CN 113687040A CN 202110857782 A CN202110857782 A CN 202110857782A CN 113687040 A CN113687040 A CN 113687040A
- Authority
- CN
- China
- Prior art keywords
- real
- time
- data
- prediction
- dosing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 218
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 46
- 238000003066 decision tree Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 37
- 239000000701 coagulant Substances 0.000 claims abstract description 121
- 238000012549 training Methods 0.000 claims abstract description 89
- 238000012360 testing method Methods 0.000 claims abstract description 51
- 238000007781 pre-processing Methods 0.000 claims abstract description 15
- 238000004590 computer program Methods 0.000 claims description 17
- 239000008394 flocculating agent Substances 0.000 claims description 14
- 238000012937 correction Methods 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 4
- 230000006872 improvement Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000015271 coagulation Effects 0.000 description 2
- 238000005345 coagulation Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000016615 flocculation Effects 0.000 description 2
- 238000005189 flocculation Methods 0.000 description 2
- 235000021110 pickles Nutrition 0.000 description 2
- 238000001556 precipitation Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000003651 drinking water Substances 0.000 description 1
- 235000020188 drinking water Nutrition 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- 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
- G01N33/18—Water
-
- 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
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Biology (AREA)
- Economics (AREA)
- Biochemistry (AREA)
- Marketing (AREA)
- Immunology (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Analytical Chemistry (AREA)
- Medicinal Chemistry (AREA)
- Entrepreneurship & Innovation (AREA)
- Pathology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Food Science & Technology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Separation Of Suspended Particles By Flocculating Agents (AREA)
Abstract
The invention discloses a method, a device and a medium for predicting the real-time dosing quantity of a water plant based on a decision tree algorithm, wherein the method comprises the following steps: acquiring historical dosing data of a water plant; preprocessing historical dosing data to obtain training data and testing data; inputting training data into a water plant real-time dosing quantity prediction model, and training the prediction model to obtain a trained dosing quantity prediction model; inputting the test data into a trained dosing quantity prediction model, and verifying the prediction precision of the dosing quantity prediction model; and acquiring real-time raw water data, inputting the real-time raw water data into a trained dosing quantity prediction model, setting the target effluent turbidity, and outputting predicted values of the flocculant dosage and the coagulant aid dosage by the dosing quantity prediction model. The method carries out real-time prediction analysis on historical dosing data based on a decision tree algorithm so as to accurately predict the real-time dosing amount, thereby scientifically allocating the dosing amount and reducing the cost of water treatment of a water plant on the premise of ensuring the stability of the effluent quality.
Description
Technical Field
The invention relates to the technical field of water treatment, in particular to a method, a device and a medium for predicting the real-time dosing quantity of a water plant based on a decision tree algorithm.
Background
The water supply system is an important aspect of modern city construction, and turbidity is an important index in drinking water quality specification and is directly related to the quality of water quality. The dosing flocculation precipitation is an important process in the water treatment process of a water works, and the effect of the dosing flocculation precipitation directly influences the subsequent process and the water quality of the water works. Coagulation is a key technology in water plant technology, directly influences the water production quality of a water plant, and an important factor influencing the coagulation effect is the addition amount of coagulant dosage.
The energy consumption and the medicine consumption in the operation of a water plant have great influence on the cost of water treatment, and under the condition of the traditional process, the dosage is usually set manually according to the experience of operation managers, so that the fluctuation of the turbidity of the effluent is large; or the dosage is too large, which leads to the increase of the cost of water treatment.
Disclosure of Invention
The technical problem to be solved by the embodiment of the invention is to provide a method, a device and a medium for predicting the real-time dosing quantity of a water plant based on a decision tree algorithm.
In order to achieve the above object, an embodiment of the present invention provides a method for predicting a real-time dosing amount of a water plant based on a decision tree algorithm, including:
acquiring historical dosing data of a water plant, wherein the dosing data comprises dosing time, real-time raw water flow, raw water turbidity, raw water temperature, raw water pH value, flocculant dosage, coagulant aid dosage and effluent turbidity;
preprocessing the historical dosing data to obtain sample data, and randomly dividing the sample data into training data and testing data according to a preset proportion;
inputting the training data into a water plant real-time dosing quantity prediction model, and training the real-time dosing quantity prediction model to obtain a trained real-time dosing quantity prediction model; the real-time dosing quantity prediction model adopts an XGboost gradient lifting algorithm, and comprises a flocculating agent prediction regression device, a coagulant aid prediction regression device and a water outlet turbidity prediction regression device;
inputting the test data into a trained real-time dosing quantity prediction model, and verifying the prediction precision of the real-time dosing quantity prediction model;
acquiring real-time raw water data, inputting the real-time raw water data into a trained real-time dosing quantity prediction model, setting the target effluent turbidity, and outputting a predicted value of the flocculant dosage and a predicted value of the coagulant aid dosage by the real-time dosing quantity prediction model.
As an improvement of the above scheme, the preprocessing the historical administration data to obtain sample data, and randomly dividing the sample data into training data and test data according to a preset proportion specifically includes:
performing data cleaning on the historical administration data to remove invalid data, incomplete data and abnormal data;
integrating the washed historical dosing data to obtain sample data;
and randomly dividing the sample data into training data and testing data according to a preset proportion.
As an improvement of the above scheme, the inputting of the training data into the real-time dosing quantity prediction model of the water plant, and the training of the real-time dosing quantity prediction model to obtain the trained real-time dosing quantity prediction model specifically include:
inputting the training data into a water plant real-time dosage prediction model;
training the flocculant prediction regression device according to the dosing time, the real-time raw water flow, the raw water turbidity, the raw water temperature, the raw water pH value, the flocculant using amount and the effluent turbidity in the training data to obtain a trained flocculant prediction regression device;
training the coagulant aid prediction regressor according to the dosing time, the real-time raw water flow, the raw water turbidity, the raw water temperature, the raw water pH value, the coagulant aid consumption and the effluent turbidity in the training data to obtain a trained coagulant aid prediction regressor;
training the effluent turbidity prediction regressor according to the dosing time, the real-time raw water flow, the raw water turbidity, the raw water temperature, the raw water pH value, the flocculant using amount, the coagulant aid using amount and the effluent turbidity in the training data to obtain a trained effluent turbidity prediction regressor;
and integrating the trained flocculant prediction regressor, coagulant aid prediction regressor and effluent turbidity prediction regressor to obtain a trained real-time dosing amount prediction model.
As an improvement of the above scheme, the inputting the test data into a trained real-time dosing quantity prediction model, and verifying the prediction accuracy of the real-time dosing quantity prediction model specifically includes:
inputting the test data into a trained flocculant prediction regression device and a trained coagulant aid prediction regression device to obtain a predicted value of the dosage of the flocculant and a predicted value of the dosage of the coagulant aid;
inputting the predicted value of the flocculant dosage and the predicted value of the coagulant aid dosage into a trained effluent turbidity prediction regression device to obtain the predicted value of the effluent turbidity;
calculating to obtain a prediction deviation value of the flocculant using amount according to the flocculant using amount in the test data and the predicted value of the flocculant using amount;
calculating a prediction deviation value of the coagulant aid dosage according to the coagulant aid dosage in the test data and the prediction value of the coagulant aid dosage;
calculating to obtain a prediction deviation value of the effluent turbidity according to the effluent turbidity in the test data and the predicted value of the effluent turbidity;
and judging the prediction precision of the real-time dosing prediction model according to the prediction deviation value of the flocculant using amount, the prediction deviation value of the coagulant aid using amount and the prediction deviation value of the effluent turbidity.
As an improvement of the above scheme, the obtaining of the real-time raw water data, inputting the real-time raw water data into a trained real-time dosing prediction model, and setting the target effluent turbidity, wherein after the real-time dosing prediction model outputs a predicted value of the flocculant dosage and a predicted value of the coagulant aid dosage, the method further comprises the following steps:
acquiring the actual effluent turbidity after the chemical dosing of the water plant by adopting the predicted value of the flocculant dosage and the predicted value of the coagulant aid dosage;
and correcting the real-time dosing amount prediction model according to the predicted value of the flocculant dosage, the predicted value of the coagulant aid dosage and the actual effluent turbidity.
As an improvement of the above scheme, the correcting the real-time dosing amount prediction model according to the predicted value of the flocculant dosage, the predicted value of the coagulant aid dosage and the actual effluent turbidity specifically comprises:
adding the predicted value of the flocculant dosage, the predicted value of the coagulant aid dosage and the actual effluent turbidity into historical dosing data, and then training the real-time dosing quantity prediction model to realize correction of the real-time dosing quantity prediction model.
As an improvement of the above scheme, the correcting the real-time dosing amount prediction model according to the predicted value of the flocculant dosage, the predicted value of the coagulant aid dosage and the actual effluent turbidity specifically comprises:
inputting the predicted value of the flocculant dosage, the predicted value of the coagulant aid dosage and the actual effluent turbidity into a flocculant prediction regression device, a coagulant aid prediction regression device and an effluent turbidity prediction regression device, and training the flocculant prediction regression device, the coagulant aid prediction regression device and the effluent turbidity prediction regression device to realize correction of the real-time dosing quantity prediction model.
The embodiment of the invention also provides a device for predicting the real-time dosage of a water plant based on a decision tree algorithm, which comprises:
the system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for acquiring historical dosing data of a water plant, and the dosing data comprises dosing time, real-time raw water flow, raw water turbidity, raw water temperature, raw water PH value, flocculating agent dosage, coagulant aid dosage and effluent turbidity;
the preprocessing module is used for preprocessing the historical dosing data to obtain sample data, and randomly dividing the sample data into training data and test data according to a preset proportion;
the training module is used for inputting the training data into a water plant real-time dosing quantity prediction model, training the real-time dosing quantity prediction model and obtaining a trained real-time dosing quantity prediction model; the real-time dosing quantity prediction model adopts an XGboost gradient lifting algorithm, and comprises a flocculating agent prediction regression device, a coagulant aid prediction regression device and a water outlet turbidity prediction regression device;
the verification module is used for inputting the test data into a trained real-time dosing quantity prediction model and verifying the prediction precision of the real-time dosing quantity prediction model;
and the prediction module is used for acquiring real-time raw water data, inputting the real-time raw water data into a trained real-time dosing amount prediction model, and setting the target effluent turbidity, so that the real-time dosing amount prediction model outputs a predicted value of the flocculant using amount and a predicted value of the coagulant aid using amount.
The embodiment of the invention also provides terminal equipment which comprises a processor, a memory and a computer program which is stored in the memory and is configured to be executed by the processor, wherein when the processor executes the computer program, the water plant real-time dosage prediction method based on the decision tree algorithm is realized.
The embodiment of the invention also provides a computer-readable storage medium, which comprises a stored computer program, wherein when the computer program runs, the device where the computer-readable storage medium is located is controlled to execute any one of the decision tree algorithm-based water plant real-time dosing quantity prediction methods.
Compared with the prior art, the method, the device and the medium for predicting the real-time dosing quantity of the water plant based on the decision tree algorithm have the advantages that: obtaining historical dosing data of a water plant, wherein the dosing data comprises dosing time, real-time raw water flow, raw water turbidity, raw water temperature, raw water pH value, flocculating agent dosage, coagulant aid dosage and effluent turbidity; preprocessing the historical dosing data to obtain sample data, and randomly dividing the sample data into training data and testing data according to a preset proportion; inputting the training data into a water plant real-time dosing quantity prediction model, and training the real-time dosing quantity prediction model to obtain a trained real-time dosing quantity prediction model; the real-time dosing quantity prediction model adopts an XGboost gradient lifting algorithm, and comprises a flocculating agent prediction regression device, a coagulant aid prediction regression device and a water outlet turbidity prediction regression device; inputting the test data into a trained real-time dosing quantity prediction model, and verifying the prediction precision of the real-time dosing quantity prediction model; acquiring real-time raw water data, inputting the real-time raw water data into a trained real-time dosing quantity prediction model, setting the target effluent turbidity, and outputting a predicted value of the flocculant dosage and a predicted value of the coagulant aid dosage by the real-time dosing quantity prediction model. The embodiment of the invention carries out real-time prediction analysis on historical dosing data based on a decision tree algorithm so as to accurately predict the real-time dosing amount, thereby scientifically allocating the dosing amount and reducing the water treatment cost of a water plant on the premise of ensuring the stable water quality of effluent.
Drawings
FIG. 1 is a schematic flow chart of a method for predicting the real-time dosage of a water plant based on a decision tree algorithm according to a preferred embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a preferred embodiment of a device for predicting the real-time dosage of a water plant based on a decision tree algorithm according to the present invention;
fig. 3 is a schematic structural diagram of a preferred embodiment of a terminal device provided in the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for predicting a real-time dosage of a water plant based on a decision tree algorithm according to a preferred embodiment of the present invention. The method for predicting the real-time dosing quantity of the water plant based on the decision tree algorithm comprises the following steps:
s1, obtaining historical dosing data of the water plant, wherein the dosing data comprises dosing time, real-time raw water flow, raw water turbidity, raw water temperature, raw water PH value, flocculating agent dosage, coagulant aid dosage and effluent turbidity;
s2, preprocessing the historical dosing data to obtain sample data, and randomly dividing the sample data into training data and test data according to a preset proportion;
s3, inputting the training data into a water plant real-time dosing quantity prediction model, and training the real-time dosing quantity prediction model to obtain a trained real-time dosing quantity prediction model; the real-time dosing quantity prediction model adopts an XGboost gradient lifting algorithm, and comprises a flocculating agent prediction regression device, a coagulant aid prediction regression device and a water outlet turbidity prediction regression device;
s4, inputting the test data into a trained real-time dosing quantity prediction model, and verifying the prediction precision of the real-time dosing quantity prediction model;
and S5, acquiring real-time raw water data, inputting the real-time raw water data into a trained real-time dosing amount prediction model, and setting the target effluent turbidity, wherein the real-time dosing amount prediction model outputs a predicted value of the usage amount of the flocculating agent and a predicted value of the usage amount of the coagulant aid.
It should be noted that, in this embodiment, a machine learning function library of an xgboost (extreme Gradient boosting) Gradient boosting algorithm is used for training. The MSE mean square error is adopted in the regression problem, and the number of machine learners is set to be 65 at the same time for improving the accuracy.
The embodiment carries out real-time prediction analysis on historical dosing data based on a decision tree algorithm so as to accurately predict the real-time dosing amount, thereby scientifically allocating the dosing amount and reducing the water treatment cost of a water plant on the premise of ensuring the stability of the effluent quality.
In another preferred embodiment, the S2, preprocessing the historical administration data to obtain sample data, and randomly dividing the sample data into training data and test data according to a preset proportion, specifically including:
s201, performing data cleaning on the historical administration data, and removing invalid data, incomplete data and abnormal data;
s202, integrating the washed historical dosing data to obtain sample data;
and S203, randomly dividing the sample data into training data and testing data according to a preset proportion.
For example, the dosing data from 2017 to 2019 of a water plant are obtained, and the dosing data comprise dosing time, real-time raw water flow, raw water turbidity, raw water temperature, raw water PH, flocculant dosage, coagulant aid dosage and effluent turbidity. After invalid data, incomplete data and abnormal data in the administration data from 2017 to 2019 are removed, the remaining administration data are integrated to obtain sample data, and the sample data are randomly divided into training data and test data according to a preset proportion.
It should be noted that, in the present embodiment, the preset ratio may be set according to actual situations, and in general, the ratio of the training data to the test data is preferably 8:2 or 7: 3.
In a further preferred embodiment, the S3, inputting the training data into the water plant real-time dosing quantity prediction model, and training the real-time dosing quantity prediction model to obtain a trained real-time dosing quantity prediction model, specifically includes:
s301, inputting the training data into a water plant real-time dosing quantity prediction model;
s302, training the flocculant prediction regressor according to the dosing time, the real-time raw water flow, the raw water turbidity, the raw water temperature, the raw water PH value, the flocculant using amount and the effluent turbidity in the training data to obtain a trained flocculant prediction regressor;
s303, training the coagulant aid prediction regression device according to the dosing time, the real-time raw water flow, the raw water turbidity, the raw water temperature, the raw water PH value, the coagulant aid consumption and the effluent turbidity in the training data to obtain a trained coagulant aid prediction regression device;
s304, training the effluent turbidity prediction regressor according to the dosing time, the real-time raw water flow, the raw water turbidity, the raw water temperature, the raw water PH value, the flocculant using amount, the coagulant aid using amount and the effluent turbidity in the training data to obtain the trained effluent turbidity prediction regressor;
s305, integrating the trained flocculant prediction regression device, coagulant aid prediction regression device and effluent turbidity prediction regression device to obtain a trained real-time dosing amount prediction model.
Specifically, training data is input into a water plant real-time dosage prediction model; training the flocculant prediction regressor according to the dosing time, the real-time raw water flow, the raw water turbidity, the raw water temperature, the raw water pH value, the flocculant using amount and the effluent turbidity in the training data to obtain a trained flocculant prediction regressor which is stored as a pac. Training the coagulant aid prediction regressor according to the dosing time, the real-time raw water flow, the raw water turbidity, the raw water temperature, the raw water pH value, the coagulant aid consumption and the effluent turbidity in the training data to obtain a trained coagulant aid prediction regressor which is stored as a pam.pick file; training the effluent turbidity prediction regressor according to the dosing time, the real-time raw water flow, the raw water turbidity, the raw water temperature, the raw water pH value, the flocculant using amount, the coagulant aid using amount and the effluent turbidity in the training data to obtain a trained effluent turbidity prediction regressor which is stored as a turbidicity. And integrating the trained flocculant prediction regressor, coagulant aid prediction regressor and effluent turbidity prediction regressor to obtain a trained real-time dosing amount prediction model.
In a further preferred embodiment, the step S4 of inputting the test data into a trained real-time dosing quantity prediction model, and verifying the prediction accuracy of the real-time dosing quantity prediction model specifically includes:
s401, inputting the test data into a trained flocculant prediction regression device and a trained coagulant aid prediction regression device to obtain a predicted value of the dosage of the flocculant and a predicted value of the dosage of the coagulant aid;
s402, inputting the predicted value of the flocculant dosage and the predicted value of the coagulant aid dosage into a trained effluent turbidity prediction regression device to obtain the predicted value of the effluent turbidity;
s403, calculating to obtain a prediction deviation value of the flocculant using amount according to the flocculant using amount in the test data and the predicted value of the flocculant using amount;
s404, calculating a prediction deviation value of the coagulant aid amount according to the coagulant aid amount in the test data and the prediction value of the coagulant aid amount;
s405, calculating to obtain a prediction deviation value of the effluent turbidity according to the effluent turbidity in the test data and the prediction value of the effluent turbidity;
and S406, judging the prediction precision of the real-time dosing quantity prediction model according to the prediction deviation value of the flocculant using quantity, the prediction deviation value of the coagulant aid using quantity and the prediction deviation value of the effluent turbidity.
Specifically, test data are input into a trained flocculant prediction regression pac.pickle and a trained coagulant aid prediction regression pam.pickle to obtain a predicted value of the flocculant dosage and a predicted value of the coagulant aid dosage; and inputting the predicted value of the flocculant dosage and the predicted value of the coagulant aid dosage into a trained effluent turbidity prediction regression device to obtain the predicted value of the effluent turbidity.
Predicting the amount of flocculant according to the amount of flocculant in the test data and the amount of flocculantCalculating to obtain a prediction deviation value of the flocculant dosage; calculating a prediction deviation value of the coagulant aid dosage according to the coagulant aid dosage in the test data and the prediction value of the coagulant aid dosage; and calculating to obtain a prediction deviation value of the effluent turbidity according to the effluent turbidity in the test data and the predicted value of the effluent turbidity. Wherein, the specific calculation formula of the deviation value is
Wherein D represents a prediction bias value, X1Indicates the predicted value, X2Representing values in the test data.
The smaller the prediction deviation value, the higher the prediction accuracy. In this embodiment, in order to improve the prediction accuracy of the real-time dosing prediction model, the minimum unit of the raw water temperature and the raw water PH value is preferably 0.01, and the minimum unit of the raw water turbidity and the effluent turbidity is preferably 0.1.
In a further preferred embodiment, the step S5 of obtaining real-time raw water data, inputting the real-time raw water data into a trained real-time dosing prediction model, and setting a target effluent turbidity, wherein the real-time dosing prediction model outputs a predicted value of flocculant usage and a predicted value of coagulant aid usage, and further includes:
s6, acquiring the actual effluent turbidity after the chemical dosing of the water plant by adopting the predicted value of the flocculant dosage and the predicted value of the coagulant aid dosage;
and S7, correcting the real-time dosing amount prediction model according to the predicted value of the flocculant dosage, the predicted value of the coagulant aid dosage and the actual effluent turbidity.
Preferably, in step S7, the correcting the real-time dosing amount prediction model according to the predicted value of the flocculant usage amount, the predicted value of the coagulant aid usage amount, and the actual effluent turbidity includes:
adding the predicted value of the flocculant dosage, the predicted value of the coagulant aid dosage and the actual effluent turbidity into historical dosing data, and then training the real-time dosing quantity prediction model to realize correction of the real-time dosing quantity prediction model.
Specifically, in the present embodiment, a full-scale method is adopted, the predicted value of the flocculant usage, the predicted value of the coagulant aid usage, and the actual effluent turbidity are added to the historical dosing data, the dosing is performed once according to S1 to S5, and each dosing application is performed once again, and the above cycle is repeated, so as to correct the real-time dosing prediction model.
Preferably, in step S7, the correcting the real-time dosing amount prediction model according to the predicted value of the flocculant usage amount, the predicted value of the coagulant aid usage amount, and the actual effluent turbidity includes:
inputting the predicted value of the flocculant dosage, the predicted value of the coagulant aid dosage and the actual effluent turbidity into a flocculant prediction regression device, a coagulant aid prediction regression device and an effluent turbidity prediction regression device, and training the flocculant prediction regression device, the coagulant aid prediction regression device and the effluent turbidity prediction regression device to realize correction of the real-time dosing quantity prediction model.
Specifically, in the embodiment, an incremental method is adopted, the predicted value of the flocculant use amount, the predicted value of the coagulant aid use amount and the actual effluent turbidity are input into a flocculant prediction regression pac. And executing S4-S5 again, and executing the application once again for each administration, and circulating the steps so as to realize the correction of the real-time dosage prediction model.
Correspondingly, the invention also provides a device for predicting the real-time dosage of the water plant based on the decision tree algorithm, which can realize all the processes of the method for predicting the real-time dosage of the water plant based on the decision tree algorithm in the embodiment.
Referring to fig. 2, fig. 2 is a schematic structural diagram of a device for predicting the real-time dosage of a water plant based on a decision tree algorithm according to a preferred embodiment of the present invention. The device for predicting the real-time dosing quantity of the water plant based on the decision tree algorithm comprises:
the obtaining module 201 is configured to obtain historical dosing data of a water plant, where the dosing data includes dosing time, real-time raw water flow, raw water turbidity, raw water temperature, raw water PH value, flocculant dosage, coagulant aid dosage, and effluent turbidity;
the preprocessing module 202 is configured to preprocess the historical dosing data to obtain sample data, and randomly divide the sample data into training data and test data according to a preset proportion;
the training module 203 is used for inputting the training data into a water plant real-time dosing quantity prediction model, training the real-time dosing quantity prediction model and obtaining a trained real-time dosing quantity prediction model; the real-time dosing quantity prediction model adopts an XGboost gradient lifting algorithm, and comprises a flocculating agent prediction regression device, a coagulant aid prediction regression device and a water outlet turbidity prediction regression device;
the verification module 204 is used for inputting the test data into a trained real-time dosing quantity prediction model and verifying the prediction precision of the real-time dosing quantity prediction model;
the prediction module 205 is configured to obtain real-time raw water data, input the real-time raw water data into a trained real-time dosing amount prediction model, and set a target effluent turbidity, where the real-time dosing amount prediction model outputs a prediction value of a flocculant usage amount and a prediction value of a coagulant aid usage amount.
Preferably, the preprocessing module 202 is specifically configured to:
performing data cleaning on the historical administration data to remove invalid data, incomplete data and abnormal data;
integrating the washed historical dosing data to obtain sample data;
and randomly dividing the sample data into training data and testing data according to a preset proportion.
Preferably, the training module 203 is specifically configured to:
inputting the training data into a water plant real-time dosage prediction model;
training the flocculant prediction regression device according to the dosing time, the real-time raw water flow, the raw water turbidity, the raw water temperature, the raw water pH value, the flocculant using amount and the effluent turbidity in the training data to obtain a trained flocculant prediction regression device;
training the coagulant aid prediction regressor according to the dosing time, the real-time raw water flow, the raw water turbidity, the raw water temperature, the raw water pH value, the coagulant aid consumption and the effluent turbidity in the training data to obtain a trained coagulant aid prediction regressor;
training the effluent turbidity prediction regressor according to the dosing time, the real-time raw water flow, the raw water turbidity, the raw water temperature, the raw water pH value, the flocculant using amount, the coagulant aid using amount and the effluent turbidity in the training data to obtain a trained effluent turbidity prediction regressor;
and integrating the trained flocculant prediction regressor, coagulant aid prediction regressor and effluent turbidity prediction regressor to obtain a trained real-time dosing amount prediction model.
Preferably, the verification module 204 is specifically configured to:
inputting the test data into a trained flocculant prediction regression device and a trained coagulant aid prediction regression device to obtain a predicted value of the dosage of the flocculant and a predicted value of the dosage of the coagulant aid;
inputting the predicted value of the flocculant dosage and the predicted value of the coagulant aid dosage into a trained effluent turbidity prediction regression device to obtain the predicted value of the effluent turbidity;
calculating to obtain a prediction deviation value of the flocculant using amount according to the flocculant using amount in the test data and the predicted value of the flocculant using amount;
calculating a prediction deviation value of the coagulant aid dosage according to the coagulant aid dosage in the test data and the prediction value of the coagulant aid dosage;
calculating to obtain a prediction deviation value of the effluent turbidity according to the effluent turbidity in the test data and the predicted value of the effluent turbidity;
and judging the prediction precision of the real-time dosing prediction model according to the prediction deviation value of the flocculant using amount, the prediction deviation value of the coagulant aid using amount and the prediction deviation value of the effluent turbidity.
Preferably, the apparatus further comprises:
an actual effluent turbidity obtaining module 206, configured to obtain an actual effluent turbidity after dosing is performed on the water plant by using the predicted value of the flocculant usage and the predicted value of the coagulant aid usage;
and the correcting module 207 is used for correcting the real-time dosing amount predicting model according to the predicted value of the flocculant using amount, the predicted value of the coagulant aid using amount and the actual effluent turbidity.
Preferably, the corrective module 207 is specifically configured to:
adding the predicted value of the flocculant dosage, the predicted value of the coagulant aid dosage and the actual effluent turbidity into historical dosing data, and then training the real-time dosing quantity prediction model to realize correction of the real-time dosing quantity prediction model.
Preferably, the corrective module 207 is specifically configured to:
inputting the predicted value of the flocculant dosage, the predicted value of the coagulant aid dosage and the actual effluent turbidity into a flocculant prediction regression device, a coagulant aid prediction regression device and an effluent turbidity prediction regression device, and training the flocculant prediction regression device, the coagulant aid prediction regression device and the effluent turbidity prediction regression device to realize correction of the real-time dosing quantity prediction model.
In a specific implementation, the working principle, the control flow and the realized technical effect of the decision tree algorithm-based water plant real-time dosing quantity prediction device provided by the embodiment of the invention are the same as those of the decision tree algorithm-based water plant real-time dosing quantity prediction method in the embodiment, and are not described herein again.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a terminal device according to a preferred embodiment of the present invention. The terminal device comprises a processor 301, a memory 302 and a computer program stored in the memory 302 and configured to be executed by the processor 301, wherein the processor 301 implements the decision tree algorithm-based water plant real-time dosing quantity prediction method according to any one of the embodiments when executing the computer program.
Preferably, the computer program may be divided into one or more modules/units (e.g., computer program 1, computer program 2, … …) that are stored in the memory 302 and executed by the processor 301 to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used for describing the execution process of the computer program in the terminal device.
The Processor 301 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, etc., the general purpose Processor may be a microprocessor, or the Processor 301 may be any conventional Processor, the Processor 301 is a control center of the terminal device, and various interfaces and lines are used to connect various parts of the terminal device.
The memory 302 mainly includes a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function, and the like, and the data storage area may store related data and the like. In addition, the memory 302 may be a high speed random access memory, a non-volatile memory such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), and the like, or the memory 302 may be other volatile solid state memory devices.
It should be noted that the terminal device may include, but is not limited to, a processor and a memory, and those skilled in the art will understand that the structural diagram of fig. 3 is only an example of the terminal device and does not constitute a limitation of the terminal device, and may include more or less components than those shown, or combine some components, or different components.
The embodiment of the invention also provides a computer-readable storage medium, which comprises a stored computer program, wherein when the computer program runs, the device where the computer-readable storage medium is located is controlled to execute the method for predicting the real-time dosage of the water plant based on the decision tree algorithm in any embodiment.
The embodiment of the invention provides a method, a device and a medium for predicting the real-time dosing quantity of a water plant based on a decision tree algorithm, wherein historical dosing data of the water plant are obtained, wherein the dosing data comprise dosing time, real-time raw water flow, raw water turbidity, raw water temperature, raw water PH value, flocculating agent dosage, coagulant aid dosage and effluent turbidity; preprocessing the historical dosing data to obtain sample data, and randomly dividing the sample data into training data and testing data according to a preset proportion; inputting the training data into a water plant real-time dosing quantity prediction model, and training the real-time dosing quantity prediction model to obtain a trained real-time dosing quantity prediction model; the real-time dosing quantity prediction model adopts an XGboost gradient lifting algorithm, and comprises a flocculating agent prediction regression device, a coagulant aid prediction regression device and a water outlet turbidity prediction regression device; inputting the test data into a trained real-time dosing quantity prediction model, and verifying the prediction precision of the real-time dosing quantity prediction model; acquiring real-time raw water data, inputting the real-time raw water data into a trained real-time dosing quantity prediction model, setting the target effluent turbidity, and outputting a predicted value of the flocculant dosage and a predicted value of the coagulant aid dosage by the real-time dosing quantity prediction model. The embodiment of the invention carries out real-time prediction analysis on historical dosing data based on a decision tree algorithm so as to accurately predict the real-time dosing amount, thereby scientifically allocating the dosing amount and reducing the water treatment cost of a water plant on the premise of ensuring the stable water quality of effluent.
It should be noted that the above-described system embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the system provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (10)
1. A water plant real-time dosing quantity prediction method based on a decision tree algorithm is characterized by comprising the following steps:
acquiring historical dosing data of a water plant, wherein the dosing data comprises dosing time, real-time raw water flow, raw water turbidity, raw water temperature, raw water pH value, flocculant dosage, coagulant aid dosage and effluent turbidity;
preprocessing the historical dosing data to obtain sample data, and randomly dividing the sample data into training data and testing data according to a preset proportion;
inputting the training data into a water plant real-time dosing quantity prediction model, and training the real-time dosing quantity prediction model to obtain a trained real-time dosing quantity prediction model; the real-time dosing quantity prediction model adopts an XGboost gradient lifting algorithm, and comprises a flocculating agent prediction regression device, a coagulant aid prediction regression device and a water outlet turbidity prediction regression device;
inputting the test data into a trained real-time dosing quantity prediction model, and verifying the prediction precision of the real-time dosing quantity prediction model;
acquiring real-time raw water data, inputting the real-time raw water data into a trained real-time dosing quantity prediction model, setting the target effluent turbidity, and outputting a predicted value of the flocculant dosage and a predicted value of the coagulant aid dosage by the real-time dosing quantity prediction model.
2. The method for predicting the real-time dosing quantity of the water plant based on the decision tree algorithm according to claim 1, wherein the step of preprocessing the historical dosing data to obtain sample data, and the step of randomly dividing the sample data into training data and testing data according to a preset proportion comprises the steps of:
performing data cleaning on the historical administration data to remove invalid data, incomplete data and abnormal data;
integrating the washed historical dosing data to obtain sample data;
and randomly dividing the sample data into training data and testing data according to a preset proportion.
3. The method for predicting the real-time dosing quantity of the water plant based on the decision tree algorithm as claimed in claim 1, wherein the training data is input into a real-time dosing quantity prediction model of the water plant, and the real-time dosing quantity prediction model is trained to obtain the trained real-time dosing quantity prediction model, which specifically comprises:
inputting the training data into a water plant real-time dosage prediction model;
training the flocculant prediction regression device according to the dosing time, the real-time raw water flow, the raw water turbidity, the raw water temperature, the raw water pH value, the flocculant using amount and the effluent turbidity in the training data to obtain a trained flocculant prediction regression device;
training the coagulant aid prediction regressor according to the dosing time, the real-time raw water flow, the raw water turbidity, the raw water temperature, the raw water pH value, the coagulant aid consumption and the effluent turbidity in the training data to obtain a trained coagulant aid prediction regressor;
training the effluent turbidity prediction regressor according to the dosing time, the real-time raw water flow, the raw water turbidity, the raw water temperature, the raw water pH value, the flocculant using amount, the coagulant aid using amount and the effluent turbidity in the training data to obtain a trained effluent turbidity prediction regressor;
and integrating the trained flocculant prediction regressor, coagulant aid prediction regressor and effluent turbidity prediction regressor to obtain a trained real-time dosing amount prediction model.
4. The decision tree algorithm-based water plant real-time dosing quantity prediction method of claim 3, wherein the step of inputting the test data into a trained real-time dosing quantity prediction model and verifying the prediction accuracy of the real-time dosing quantity prediction model specifically comprises the steps of:
inputting the test data into a trained flocculant prediction regression device and a trained coagulant aid prediction regression device to obtain a predicted value of the dosage of the flocculant and a predicted value of the dosage of the coagulant aid;
inputting the predicted value of the flocculant dosage and the predicted value of the coagulant aid dosage into a trained effluent turbidity prediction regression device to obtain the predicted value of the effluent turbidity;
calculating to obtain a prediction deviation value of the flocculant using amount according to the flocculant using amount in the test data and the predicted value of the flocculant using amount;
calculating a prediction deviation value of the coagulant aid dosage according to the coagulant aid dosage in the test data and the prediction value of the coagulant aid dosage;
calculating to obtain a prediction deviation value of the effluent turbidity according to the effluent turbidity in the test data and the predicted value of the effluent turbidity;
and judging the prediction precision of the real-time dosing prediction model according to the prediction deviation value of the flocculant using amount, the prediction deviation value of the coagulant aid using amount and the prediction deviation value of the effluent turbidity.
5. The method for predicting the real-time dosing quantity of the water plant based on the decision tree algorithm as claimed in claim 1, wherein the steps of obtaining real-time raw water data, inputting the real-time raw water data into a trained real-time dosing quantity prediction model, setting the target effluent turbidity, and outputting the predicted value of the flocculant dosage and the predicted value of the coagulant aid dosage by the real-time dosing quantity prediction model further comprise:
acquiring the actual effluent turbidity after the chemical dosing of the water plant by adopting the predicted value of the flocculant dosage and the predicted value of the coagulant aid dosage;
and correcting the real-time dosing amount prediction model according to the predicted value of the flocculant dosage, the predicted value of the coagulant aid dosage and the actual effluent turbidity.
6. The method for predicting the real-time dosing quantity of the water plant based on the decision tree algorithm as claimed in claim 5, wherein the correction of the real-time dosing quantity prediction model according to the predicted value of the flocculant dosage, the predicted value of the coagulant aid dosage and the actual effluent turbidity is specifically as follows:
adding the predicted value of the flocculant dosage, the predicted value of the coagulant aid dosage and the actual effluent turbidity into historical dosing data, and then training the real-time dosing quantity prediction model to realize correction of the real-time dosing quantity prediction model.
7. The method for predicting the real-time dosing quantity of the water plant based on the decision tree algorithm as claimed in claim 5, wherein the correction of the real-time dosing quantity prediction model according to the predicted value of the flocculant dosage, the predicted value of the coagulant aid dosage and the actual effluent turbidity is specifically as follows:
inputting the predicted value of the flocculant dosage, the predicted value of the coagulant aid dosage and the actual effluent turbidity into a flocculant prediction regression device, a coagulant aid prediction regression device and an effluent turbidity prediction regression device, and training the flocculant prediction regression device, the coagulant aid prediction regression device and the effluent turbidity prediction regression device to realize correction of the real-time dosing quantity prediction model.
8. A water plant real-time dosing quantity predicting device based on a decision tree algorithm, which is characterized in that,
the system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for acquiring historical dosing data of a water plant, and the dosing data comprises dosing time, real-time raw water flow, raw water turbidity, raw water temperature, raw water PH value, flocculating agent dosage, coagulant aid dosage and effluent turbidity;
the preprocessing module is used for preprocessing the historical dosing data to obtain sample data, and randomly dividing the sample data into training data and test data according to a preset proportion;
the training module is used for inputting the training data into a water plant real-time dosing quantity prediction model, training the real-time dosing quantity prediction model and obtaining a trained real-time dosing quantity prediction model; the real-time dosing quantity prediction model adopts an XGboost gradient lifting algorithm, and comprises a flocculating agent prediction regression device, a coagulant aid prediction regression device and a water outlet turbidity prediction regression device;
the verification module is used for inputting the test data into a trained real-time dosing quantity prediction model and verifying the prediction precision of the real-time dosing quantity prediction model;
and the prediction module is used for acquiring real-time raw water data, inputting the real-time raw water data into a trained real-time dosing amount prediction model, and setting the target effluent turbidity, so that the real-time dosing amount prediction model outputs a predicted value of the flocculant using amount and a predicted value of the coagulant aid using amount.
9. A terminal device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the decision tree algorithm-based water plant real-time dosage prediction method according to any one of claims 1 to 7.
10. A computer-readable storage medium, comprising a stored computer program, wherein when the computer program runs, the computer-readable storage medium controls a device to execute the method for predicting the real-time dosage of a water plant based on a decision tree algorithm according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110857782.0A CN113687040A (en) | 2021-07-28 | 2021-07-28 | Decision tree algorithm-based water plant real-time dosing quantity prediction method, device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110857782.0A CN113687040A (en) | 2021-07-28 | 2021-07-28 | Decision tree algorithm-based water plant real-time dosing quantity prediction method, device and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113687040A true CN113687040A (en) | 2021-11-23 |
Family
ID=78578121
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110857782.0A Pending CN113687040A (en) | 2021-07-28 | 2021-07-28 | Decision tree algorithm-based water plant real-time dosing quantity prediction method, device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113687040A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114563988A (en) * | 2022-01-26 | 2022-05-31 | 浙江中控信息产业股份有限公司 | Water plant intelligent PAC adding method and system based on random forest algorithm |
| CN114626642A (en) * | 2022-05-16 | 2022-06-14 | 武汉华信数据系统有限公司 | Dosing system control method and device, storage medium and electronic equipment |
| CN114781249A (en) * | 2022-04-07 | 2022-07-22 | 浙江浙能台州第二发电有限责任公司 | High-density clarification tank dosage prediction and control method based on multidimensional scoring model |
| CN114906913A (en) * | 2022-05-31 | 2022-08-16 | 上海环保（集团）有限公司 | Chemical phosphorus removal accurate dosing system and device based on intelligent learning |
| CN115108595A (en) * | 2022-06-27 | 2022-09-27 | 重庆远通电子技术开发有限公司 | Intelligent water purifying agent adding method based on machine learning |
| CN115375009A (en) * | 2022-07-28 | 2022-11-22 | 上海城市水资源开发利用国家工程中心有限公司 | Method for establishing coagulation intelligent monitoring linkage system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111718028A (en) * | 2020-06-24 | 2020-09-29 | 南京邮电大学 | Intelligent modeling method for coagulant addition of water treatment plant based on big data analysis |
| CN111966053A (en) * | 2020-07-09 | 2020-11-20 | 上海威派格智慧水务股份有限公司 | Intelligent flocculant decision making system |
| CN112216354A (en) * | 2020-09-17 | 2021-01-12 | 江苏集萃工业过程模拟与优化研究所有限公司 | Intelligent dosing system and method based on CFD numerical simulation and machine learning |
-
2021
- 2021-07-28 CN CN202110857782.0A patent/CN113687040A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111718028A (en) * | 2020-06-24 | 2020-09-29 | 南京邮电大学 | Intelligent modeling method for coagulant addition of water treatment plant based on big data analysis |
| CN111966053A (en) * | 2020-07-09 | 2020-11-20 | 上海威派格智慧水务股份有限公司 | Intelligent flocculant decision making system |
| CN112216354A (en) * | 2020-09-17 | 2021-01-12 | 江苏集萃工业过程模拟与优化研究所有限公司 | Intelligent dosing system and method based on CFD numerical simulation and machine learning |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114563988A (en) * | 2022-01-26 | 2022-05-31 | 浙江中控信息产业股份有限公司 | Water plant intelligent PAC adding method and system based on random forest algorithm |
| CN114781249A (en) * | 2022-04-07 | 2022-07-22 | 浙江浙能台州第二发电有限责任公司 | High-density clarification tank dosage prediction and control method based on multidimensional scoring model |
| CN114626642A (en) * | 2022-05-16 | 2022-06-14 | 武汉华信数据系统有限公司 | Dosing system control method and device, storage medium and electronic equipment |
| CN114626642B (en) * | 2022-05-16 | 2022-09-06 | 武汉华信数据系统有限公司 | Dosing system control method and device, storage medium and electronic equipment |
| CN114906913A (en) * | 2022-05-31 | 2022-08-16 | 上海环保（集团）有限公司 | Chemical phosphorus removal accurate dosing system and device based on intelligent learning |
| CN114906913B (en) * | 2022-05-31 | 2023-08-22 | 上海环保（集团）有限公司 | Intelligent learning-based chemical dephosphorization accurate dosing system and device |
| CN115108595A (en) * | 2022-06-27 | 2022-09-27 | 重庆远通电子技术开发有限公司 | Intelligent water purifying agent adding method based on machine learning |
| CN115375009A (en) * | 2022-07-28 | 2022-11-22 | 上海城市水资源开发利用国家工程中心有限公司 | Method for establishing coagulation intelligent monitoring linkage system |
| CN115375009B (en) * | 2022-07-28 | 2023-09-22 | 上海城市水资源开发利用国家工程中心有限公司 | Method for establishing intelligent monitoring linkage system for coagulation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113687040A (en) | Decision tree algorithm-based water plant real-time dosing quantity prediction method, device and medium | |
| KR101889510B1 (en) | Method of estimating coagulant injection rate in water treatment using deep neural network | |
| CN111768038A (en) | Pollutant monitoring method and device, terminal equipment and storage medium | |
| CN112132700A (en) | Formula decision method for regulating and controlling water quality | |
| CN112700050B (en) | Method and system for predicting ultra-short-term 1 st point power of photovoltaic power station | |
| CN109887253B (en) | Correlation analysis method for petrochemical device alarm | |
| CN105320112A (en) | Production control support apparatus and production control support method | |
| CN114442686B (en) | Dissolved oxygen concentration control method, dissolved oxygen concentration control device, electronic equipment and storage medium | |
| CN115784331A (en) | Coagulating sedimentation control method, device, equipment and storage medium | |
| CN112433914B (en) | Method and system for obtaining parallel computing task progress | |
| CN115270861A (en) | Product composition data monitoring method and device, electronic equipment and storage medium | |
| CN115409362A (en) | Method for planning control concentration of regional pollutants, electronic equipment and storage medium | |
| JP7471209B2 (en) | Information processing device, prediction method, water treatment system, and prediction program | |
| CN113582309A (en) | Method and device for determining coagulant adding amount | |
| CN113569935B (en) | Softening and dosing method, system and equipment based on SVM and principal component contribution graph | |
| CN112632469A (en) | Method and device for detecting abnormity of business transaction data and computer equipment | |
| CN111950778A (en) | Hardware development workload estimation method, device, terminal and storage medium | |
| CN117079742A (en) | Method and device for treating fluorine-containing wastewater, electronic equipment and storage medium | |
| CN117073806B (en) | Sewage treatment ectopic monitoring method and system based on artificial intelligence | |
| CN115796472B (en) | Energy metering processing method and device, electronic equipment and readable storage medium | |
| CN117350601B (en) | Water quality prediction method and device, electronic equipment and storage medium | |
| CN109344369B (en) | Certificate making method based on original value verification and terminal equipment | |
| CN115076128B (en) | Water pump water flow measurement method, device, equipment and storage medium | |
| CN117379978B (en) | Ultrafiltration membrane pool operation method and device, electronic equipment and readable storage medium | |
| CN114368844B (en) | Data monitoring method and device for high-salinity mine water treatment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211123 |