CN109961186A - Desulphurization system operating parameter prediction technique based on decision tree and BP neural network - Google Patents
Desulphurization system operating parameter prediction technique based on decision tree and BP neural network Download PDFInfo
- Publication number
- CN109961186A CN109961186A CN201910223673.6A CN201910223673A CN109961186A CN 109961186 A CN109961186 A CN 109961186A CN 201910223673 A CN201910223673 A CN 201910223673A CN 109961186 A CN109961186 A CN 109961186A
- Authority
- CN
- China
- Prior art keywords
- operating parameter
- prediction
- parameter prediction
- data
- decision tree
- 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
- 238000003066 decision tree Methods 0.000 title claims abstract description 47
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 23
- 238000012360 testing method Methods 0.000 claims abstract description 7
- 238000004140 cleaning Methods 0.000 claims abstract description 4
- 238000011156 evaluation Methods 0.000 claims abstract description 4
- 239000002002 slurry Substances 0.000 claims description 12
- 238000013138 pruning Methods 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 230000005856 abnormality Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 238000005201 scrubbing Methods 0.000 claims description 3
- 210000004218 nerve net Anatomy 0.000 claims description 2
- 238000012795 verification Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000006477 desulfuration reaction Methods 0.000 description 4
- 230000023556 desulfurization Effects 0.000 description 4
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 2
- 240000002853 Nelumbo nucifera Species 0.000 description 2
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 1
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 description 1
- 239000005864 Sulphur Substances 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 239000003546 flue gas Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 239000003607 modifier Substances 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 229920001228 polyisocyanate Polymers 0.000 description 1
- 239000005056 polyisocyanate Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000010977 unit operation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—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
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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"
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Tourism & Hospitality (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Feedback Control In General (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The desulphurization system operating parameter prediction technique based on decision tree and BP neural network that the invention discloses a kind of, comprising: step 1, desulphurization system operation data is cleared up；Step 2, to the partial data in the operation data after cleaning as training sample set, remainder data is as test sample collection, and the data concentrated to training sample are normalized；Step 3, it is concentrated from training sample and selects suitable characteristic variable, the input variable as operating parameter prediction model；Step 4, the output variable for determining operating parameter prediction model is established operating parameter prediction model using BP neural network and traditional decision-tree, and is predicted using operating parameter prediction model；Step 5, evaluation analysis is carried out to the result of prediction, verifies the validity of prediction.Beneficial effects of the present invention: it is with good performance, study convergence rate and prediction accuracy are improved, prediction task can be completed well.
Description
Technical field
The present invention relates to desulphurization system technical field, in particular to a kind of based on decision tree and BP neural network
Desulphurization system operating parameter prediction technique.
Background technique
In thermal power plant, the desulfurization to flue gas is an essential link.Desulphurization system is in the process of running
A large amount of operation data is generated, these data contain value abundant for excavating.And current many desulphurization systems are still and lean on
Operations staff is by rule of thumb adjusted stock volume and slurry circulating pump, the disadvantage is that adjust not in time, not precisely.With increasingly
A set of desulfurization intelligence control system that can precisely adjust is badly in need of in stringent environmental requirement, power station.This system being precisely controlled
It need to establish on the basis of data-driven modeling, therefore carrying out deep learning to the historical data of desulphurization system is both wanting for environmental protection
Asking is also the requirement for improving power station desulfurization economy.
Neural network is since nineteen forties come out in various controls, signal processing, pattern-recognition, finance card
All various aspects such as certificate, optimization calculating are all widely applied, and wherein neural network is because it is in classification problem and regression problem
It is with good performance, it is widely used in data variation trend prediction, however traditional BP neural network model convergence rate is slow,
Prediction effect is not especially good.
Summary of the invention
To solve the above problems, the purpose of the present invention is to provide a kind of desulfurization system based on decision tree and BP neural network
System operating parameter prediction technique, it is with good performance, study convergence rate and prediction accuracy are improved, can be completed well
Prediction task.
The desulphurization system operating parameter prediction technique based on decision tree and BP neural network that the present invention provides a kind of, packet
It includes:
Step 1, data scrubbing, rejecting abnormalities data are carried out to thermo-power station desulphurization system operation data；
Step 2, to the partial data in operation data healthy after cleaning as training sample set, remainder data is as survey
Sample set is tried, and the sample data concentrated to training sample is normalized；
Step 3, decision tree is generated by training sample set, and uses and obtains new sample data in real time as test sample concentration
Data check Decision Tree Construction in the preliminary observation that generates, the branch that will affect forecasting accuracy wipes out, and selection is suitable
Characteristic variable, obtain the input variable of operating parameter prediction model, the work of stock volume, circulating pump including slurries system is negative
Lotus, outlet SO2Four variable elements of concentration and slurry pH value；
Step 4, with the outlet SO of subsequent time2Output variable of the concentration as operating parameter prediction model, using BP mind
Operating parameter prediction model is established through network and decision tree, and using operating parameter prediction model to the outlet SO of subsequent time2
Concentration is predicted；
Step 5, evaluation analysis is carried out to the result of prediction, verifies the validity of prediction.
It is further improved as of the invention, in step 1, measurement parameter exceeded for concentration of emission be not in normal range (NR)
Interior and mutation data point, which needs to identify, to be rejected.
It is further improved as of the invention, in step 3, decision tree uses the beta pruning of CART tree algorithm.
It is further improved as of the invention, in step 4, BP neural network chooses the three-layer network of a hidden layer, hidden
Logistic activation primitive is used containing layer, output layer uses linear activation primitive, and training method uses BP algorithm.
It is further improved as of the invention, in step 5, when analyzing verifying, needs to measure three parameters: anticipation trend
Accuracy, prediction error and square root mean square error.
Improved as of the invention further, the accuracy of anticipation trend be predicted value twice in succession is obtained variation tendency with
The variation tendency of actual value compares, if change direction is consistent, trend prediction is correct, otherwise prediction error.
The invention has the benefit that
Extract input parameter of the optimal characteristic variable as BP neural network by decision tree, make up BP neural network without
Method effectively determines the defect of input parameter.After increasing traditional decision-tree, the precision of prediction of prediction model is significantly improved, decision tree
After introducing can effective exclusive PCR noise, make to predict that stability is improved significantly, estimated performance is significantly promoted, and restrains effect
More preferably, it predicts more accurate.
Detailed description of the invention
Fig. 1 is that a kind of desulphurization system operating parameter based on decision tree and BP neural network described in the embodiment of the present invention is pre-
The schematic diagram of survey method；
Fig. 2 is the desulphurization system operating parameter prediction output schematic diagram using BP neural network；
Fig. 3 is the error using desulphurization system operating parameter the prediction output and desired output of BP neural network；
Fig. 4 is the present invention is based on the desulphurization system operating parameter of decision tree and BP neural network prediction output and using BP mind
The contrast schematic diagram of desulphurization system operating parameter prediction output through network；
Fig. 5 is invention based on the desulphurization system operating parameter of decision tree and BP neural network prediction output and desired output
Error and the contrast schematic diagram of desulphurization system operating parameter prediction output and the error of desired output using BP neural network.
Specific embodiment
The present invention is described in further detail below by specific embodiment and in conjunction with attached drawing.
A kind of desulphurization system operating parameter prediction side based on decision tree and BP neural network described in the embodiment of the present invention
Method, as shown in Figure 1, using the stock volume of slurries system, the workload of circulating pump, the outlet SO of preceding 20s-40s2Concentration and slurry
Outlet SO of the combination of four variable elements of liquid pH value to subsequent time2Concentration and slurry pH value are predicted.It specifically includes:
Step 1, data scrubbing, rejecting abnormalities data are carried out to thermo-power station desulphurization system operation data.For concentration of emission
Exceeded, measurement parameter does not need to identify with the data point of mutation in the normal range to be rejected.
Step 2, training sample set is used as to 11000 groups in 12000 groups of data unit operations healthy after cleaning, remaining
1000 groups of data are as test sample collection, and the sample data concentrated to training sample is normalized.
Step 3, decision tree is generated by training sample set, and uses and obtains new sample data in real time as test sample concentration
Data check Decision Tree Construction in the preliminary observation that generates, the branch that will affect forecasting accuracy wipes out, and selection is suitable
Characteristic variable, obtain the input variable of operating parameter prediction model, the work of stock volume, circulating pump including slurries system is negative
Lotus, 20s-40s outlet SO2Four variable elements of concentration and slurry pH value.
Generally comprise many variables in training sample, influence of some of them variable to prediction output be unrelated or very little, becomes
When measuring excessive, a possibility that neural network is difficult to work normally, also will increase over-fitting will lead to, therefore, it is necessary in BP nerve
Before network training, variable is simplified according to prediction output, suitable characteristic variable is selected, determines the input of BP neural network
Parameter.The present invention extracts input parameter of the optimal characteristic variable as BP neural network by decision tree, makes up BP nerve net
Network can not effectively determine the defect of input parameter.
Decision tree network is a kind of simple form of Directed Graph Model with specified conditions probability distribution.In general,
Decision tree can be played the state s being considered as with binary set by we, and wherein each element of state is influenced by its ancestors.
The most common structure of decision tree network is divided into the structure of many layers, wherein crude sampling by a series of multiple hidden layers into
Row, then ultimately generates visible layer.Decision tree construction can be carried out in two steps: the first step, the generation of decision tree: by training sample
Collection generates the process of decision tree.Second step, the beta pruning of decision tree: the beta pruning of decision tree be to the decision tree generated on last stage into
Performing check, correction and modified process, the data check decision for mainly using new sample data set to concentrate as test data
The preliminary rule generated in tree generating process wipes out those branches for influencing forecasting accuracy.Decision tree uses in the present invention
CART tree algorithm beta pruning.The pruning algorithms of CART tree may be summarized to be two steps, and the first step is to generate various cut from original decision tree
The decision tree of branch effect, second is that the predictive ability after beta pruning is examined with cross validation, selects extensive predictive ability best
Beta pruning after number as final CART tree.
Step 4, with the outlet SO of subsequent time2Output variable of the concentration as operating parameter prediction model, using BP mind
Operating parameter prediction model is established through network and decision tree, and subsequent time is gone out using actual operating parameter prediction model
Mouth SO2Concentration is predicted.
The decision tree is the decision tree after step 3 branch is wiped out, and that is to say the slurry finally determined using the decision tree of step 3
The stock volume of liquid system, the workload of circulating pump, 20s-40s outlet SO2Concentration and slurry pH value as input variable, under
The outlet SO at one moment2Output variable of the concentration as operating parameter prediction model, establishes operating parameter based on BP neural network
Prediction model.
BP neural network (error backward propagation method), be it is a kind of by error backpropagation algorithm training multilayer before
Present neural network.The basic studies rule of BP neural network is constantly to adjust network by backpropagation using gradient descent method
Weight and threshold value, keep the error sum of squares of network minimum.BP neural network model topology structure include input layer (input),
Hidden layer (hidden layer) and output layer (output layer).
BP neural network of the invention chooses the three-layer network of a hidden layer, and input layer number is 4, output layer section
Point number is 1, and hidden layer node number is 4~13, and hidden layer uses logistic activation primitive, and output layer is swashed using linear
Function living, cost function are mean square error, and training method uses BP algorithm.
The training method of BP neural network is as follows: given input variable is transmitted to hidden layer from input layer, hidden layer passes through
Result is transmitted to output layer by weight and activation primitive, and the result of output layer is compared with desired output result, when practical defeated
When there is error with desired output out, then feedback modifiers reversely are carried out to neural network weight, is preset most until error amount reaches
Small error.
Training process is related to some important variables choices, such as learning efficiency, every time interior loop iteration step number, instruction
Practicing terminates how judgment criteria determines, influences the iteration step length for seeking optimal value every time, and initial value value is 0.1, to improve journey
Sequence speed of searching optimization, as training carries out, when Step wise approximation optimal solution, is recycled every time according to error judgment standard, if this time comparing last time
Error increases, and learning efficiency takes half value, reduces step-length, prevents from missing optimal solution.
In the forecast period of model, the mode of one-step prediction is selected, i.e., every time after output predicted value y (t+1), to y (t+
2) it is needed when being predicted using actual observed value as input, to avoid the inaccurate influence to predicting later of single prediction.
Step 5, evaluation analysis is carried out to the result of prediction, verifies the validity of prediction.
In order to which the performance of more fully valuation prediction models needs to measure mould from three angles after prediction model training
Type is for short-term SO2The validity of the prediction of concentration: accuracy, prediction error and the square root mean square error of anticipation trend.In advance
The accuracy of survey trend is that the variation tendency that predicted value twice in succession is obtained variation tendency and actual value compares, if variation side
To consistent, then trend prediction is correct, otherwise prediction error.
Fig. 2 shows using between the desulphurization system operating parameter prediction output of common BP neural network and true measurement
Some points that can not be overlapped, prediction accuracy be not high.Fig. 3 shows the desulphurization system operating parameter using common BP neural network
The curve amplitude of the error of prediction output and desired output is larger, and the fluctuation up and down 0 is very big, and there are also many errors are very big
Point, convergence effect is not especially good.Fig. 4 shows that the present invention is based on the desulphurization system operating parameter of decision tree and BP neural network is pre-
Survey output can be preferably overlapped with true measurement, and use neural network desulphurization system operating parameter prediction output in the presence of compared with
Polyisocyanate value point, there is the point that can not be much overlapped with true measurement.Fig. 5 shows invention based on the de- of decision tree and BP neural network
The error of sulphur system operational parameters prediction output and desired output is smaller in 0 fluctuation up and down, can restrain well, and uses mind
The error of desulphurization system operating parameter prediction output and desired output through network is very big in 0 fluctuation up and down, and relative error is very
Greatly, it can not restrain well.Comparison diagram 5 show that of the invention run based on the desulphurization system of decision tree and BP neural network is joined
Number prediction technique, after increasing traditional decision-tree, the precision of prediction of prediction model is significantly improved, and can be seen by the amplitude of curve
Out, after decision tree introduces can effective exclusive PCR noise, be that prediction stability is improved significantly, estimated performance significantly mentions
It rises, convergence effect is more preferable, predicts more accurate.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (6)
1. a kind of desulphurization system operating parameter prediction technique based on decision tree and BP neural network characterized by comprising
Step 1, data scrubbing, rejecting abnormalities data are carried out to thermo-power station desulphurization system operation data；
Step 2, to the partial data in operation data healthy after cleaning as training sample set, remainder data is as test specimens
This collection, and the sample data concentrated to training sample is normalized；
Step 3, decision tree is generated by training sample set, and uses and obtains the number that new sample data is concentrated as test sample in real time
According to the preliminary observation generated in verification Decision Tree Construction, the branch that will affect forecasting accuracy is wiped out, and is selected suitable special
Variable is levied, the input variable of operating parameter prediction model is obtained, the workload of stock volume, circulating pump including slurries system,
Export SO2Four variable elements of concentration and slurry pH value；
Step 4, with the outlet SO of subsequent time2Output variable of the concentration as operating parameter prediction model, using BP neural network
Operating parameter prediction model is established with decision tree, and using operating parameter prediction model to the outlet SO of subsequent time2Concentration into
Row prediction；
Step 5, evaluation analysis is carried out to the result of prediction, verifies the validity of prediction.
2. desulphurization system operating parameter prediction technique according to claim 1, which is characterized in that in step 1, for discharge
Concentration over-standard, measurement parameter do not need to identify with the data point of mutation in the normal range to be rejected.
3. desulphurization system operating parameter prediction technique according to claim 1, which is characterized in that in step 3, decision tree is adopted
With CART tree algorithm beta pruning.
4. desulphurization system operating parameter prediction technique according to claim 1, which is characterized in that in step 4, BP nerve net
Network chooses the three-layer network of a hidden layer, and hidden layer uses logistic activation primitive, and output layer uses linear activation primitive,
Training method uses innovatory algorithm.
5. desulphurization system operating parameter prediction technique according to claim 1, which is characterized in that in step 5, tested in analysis
When card, need to measure three parameters: accuracy, prediction error and the square root mean square error of anticipation trend.
6. desulphurization system operating parameter prediction technique according to claim 5, which is characterized in that the accuracy of anticipation trend
It is that the variation tendency that predicted value twice in succession is obtained variation tendency and actual value compares, if change direction is consistent, trend
Prediction is correct, otherwise prediction error.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910223673.6A CN109961186A (en) | 2019-03-22 | 2019-03-22 | Desulphurization system operating parameter prediction technique based on decision tree and BP neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910223673.6A CN109961186A (en) | 2019-03-22 | 2019-03-22 | Desulphurization system operating parameter prediction technique based on decision tree and BP neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109961186A true CN109961186A (en) | 2019-07-02 |
Family
ID=67024752
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910223673.6A Pending CN109961186A (en) | 2019-03-22 | 2019-03-22 | Desulphurization system operating parameter prediction technique based on decision tree and BP neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109961186A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110363347A (en) * | 2019-07-12 | 2019-10-22 | 江苏天长环保科技有限公司 | The method of neural network prediction air quality based on decision tree index |
| CN111013370A (en) * | 2019-11-08 | 2020-04-17 | 中国大唐集团科学技术研究院有限公司火力发电技术研究院 | Wet desulphurization slurry supply amount prediction method based on deep neural network |
| CN111046940A (en) * | 2019-12-06 | 2020-04-21 | 中车长春轨道客车股份有限公司 | Vehicle door fault diagnosis method based on decision tree and neural network |
| CN111199307A (en) * | 2019-12-03 | 2020-05-26 | 上海集成电路研发中心有限公司 | Production line production state prediction method and system based on decision tree |
| CN111310788A (en) * | 2020-01-15 | 2020-06-19 | 广东奥博信息产业股份有限公司 | Water body pH value prediction method based on parameter optimization |
| CN111562541A (en) * | 2020-05-31 | 2020-08-21 | 宁夏隆基宁光仪表股份有限公司 | Software platform for realizing electric energy meter detection data management by applying CART algorithm |
| CN112488286A (en) * | 2019-11-22 | 2021-03-12 | 大唐环境产业集团股份有限公司 | MBR membrane pollution online monitoring method and system |
| CN112579847A (en) * | 2019-09-30 | 2021-03-30 | 北京国双科技有限公司 | Method and device for processing production data, storage medium and electronic equipment |
| CN112906967A (en) * | 2021-02-24 | 2021-06-04 | 大唐环境产业集团股份有限公司 | Desulfurization system slurry circulating pump performance prediction method and device |
| CN112926765A (en) * | 2021-01-22 | 2021-06-08 | 湖南大唐先一科技有限公司 | Desulfurization system operation optimization method and information physical fusion system |
| CN112943224A (en) * | 2019-12-11 | 2021-06-11 | 中国石油化工股份有限公司 | Method for calculating dynamic liquid level of heavy oil well |
| CN113077041A (en) * | 2020-01-06 | 2021-07-06 | 大唐环境产业集团股份有限公司 | Deep neural network modeling independent variable dimension reduction method based on genetic algorithm |
| CN113780405A (en) * | 2021-09-07 | 2021-12-10 | 科希曼电器有限公司 | Air conditioner parameter regression optimization method based on deep neural network |
| CN114330553A (en) * | 2021-12-29 | 2022-04-12 | 电子科技大学 | Digital acquisition system calibration method based on supervised learning |
| CN117198517A (en) * | 2023-06-27 | 2023-12-08 | 安徽省立医院(中国科学技术大学附属第一医院) | Modeling method of motion reactivity assessment and prediction model based on machine learning |
| CN117674302A (en) * | 2024-02-01 | 2024-03-08 | 浙江省白马湖实验室有限公司 | Combined heat and power load scheduling method based on two-stage integrated learning |
| CN117808506A (en) * | 2023-12-28 | 2024-04-02 | 智诚建筑信息技术(深圳)有限公司 | Analysis method and system for realizing material transaction based on neural network |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109343367A (en) * | 2018-10-26 | 2019-02-15 | 齐鲁工业大学 | A method of based on network response surface flue gas desulfurization |
-
2019
- 2019-03-22 CN CN201910223673.6A patent/CN109961186A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109343367A (en) * | 2018-10-26 | 2019-02-15 | 齐鲁工业大学 | A method of based on network response surface flue gas desulfurization |
Non-Patent Citations (2)
| Title |
|---|
| BINBIN DAN等: ""Research on Multi-BP NN-based Control Model for"", 《DEPARTMENT OF INDUSTRIAL ENGINEERING》 * |
| 梁栋等: ""一种基于决策树和遗传算法-BP神经网络的组合预测模型"", 《中国科技论文》 * |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110363347A (en) * | 2019-07-12 | 2019-10-22 | 江苏天长环保科技有限公司 | The method of neural network prediction air quality based on decision tree index |
| CN110363347B (en) * | 2019-07-12 | 2022-04-15 | 江苏天长环保科技有限公司 | Method for predicting air quality based on neural network of decision tree index |
| CN112579847A (en) * | 2019-09-30 | 2021-03-30 | 北京国双科技有限公司 | Method and device for processing production data, storage medium and electronic equipment |
| CN111013370A (en) * | 2019-11-08 | 2020-04-17 | 中国大唐集团科学技术研究院有限公司火力发电技术研究院 | Wet desulphurization slurry supply amount prediction method based on deep neural network |
| CN112488286B (en) * | 2019-11-22 | 2024-05-28 | 大唐环境产业集团股份有限公司 | On-line monitoring method and system for MBR membrane pollution |
| CN112488286A (en) * | 2019-11-22 | 2021-03-12 | 大唐环境产业集团股份有限公司 | MBR membrane pollution online monitoring method and system |
| CN111199307A (en) * | 2019-12-03 | 2020-05-26 | 上海集成电路研发中心有限公司 | Production line production state prediction method and system based on decision tree |
| CN111046940A (en) * | 2019-12-06 | 2020-04-21 | 中车长春轨道客车股份有限公司 | Vehicle door fault diagnosis method based on decision tree and neural network |
| CN112943224B (en) * | 2019-12-11 | 2023-02-07 | 中国石油化工股份有限公司 | Method for calculating dynamic liquid level of heavy oil well |
| CN112943224A (en) * | 2019-12-11 | 2021-06-11 | 中国石油化工股份有限公司 | Method for calculating dynamic liquid level of heavy oil well |
| CN113077041A (en) * | 2020-01-06 | 2021-07-06 | 大唐环境产业集团股份有限公司 | Deep neural network modeling independent variable dimension reduction method based on genetic algorithm |
| CN111310788B (en) * | 2020-01-15 | 2023-06-09 | 广东奥博信息产业股份有限公司 | Water pH value prediction method based on parameter optimization |
| CN111310788A (en) * | 2020-01-15 | 2020-06-19 | 广东奥博信息产业股份有限公司 | Water body pH value prediction method based on parameter optimization |
| CN111562541A (en) * | 2020-05-31 | 2020-08-21 | 宁夏隆基宁光仪表股份有限公司 | Software platform for realizing electric energy meter detection data management by applying CART algorithm |
| CN111562541B (en) * | 2020-05-31 | 2022-05-24 | 宁夏隆基宁光仪表股份有限公司 | Software platform for realizing electric energy meter detection data management by applying CART algorithm |
| CN112926765A (en) * | 2021-01-22 | 2021-06-08 | 湖南大唐先一科技有限公司 | Desulfurization system operation optimization method and information physical fusion system |
| CN112906967A (en) * | 2021-02-24 | 2021-06-04 | 大唐环境产业集团股份有限公司 | Desulfurization system slurry circulating pump performance prediction method and device |
| CN113780405A (en) * | 2021-09-07 | 2021-12-10 | 科希曼电器有限公司 | Air conditioner parameter regression optimization method based on deep neural network |
| CN114330553B (en) * | 2021-12-29 | 2023-04-07 | 电子科技大学 | Digital acquisition system calibration method based on supervised learning |
| CN114330553A (en) * | 2021-12-29 | 2022-04-12 | 电子科技大学 | Digital acquisition system calibration method based on supervised learning |
| CN117198517A (en) * | 2023-06-27 | 2023-12-08 | 安徽省立医院(中国科学技术大学附属第一医院) | Modeling method of motion reactivity assessment and prediction model based on machine learning |
| CN117198517B (en) * | 2023-06-27 | 2024-04-30 | 安徽省立医院(中国科学技术大学附属第一医院) | Modeling method of motion reactivity assessment and prediction model based on machine learning |
| CN117808506A (en) * | 2023-12-28 | 2024-04-02 | 智诚建筑信息技术(深圳)有限公司 | Analysis method and system for realizing material transaction based on neural network |
| CN117674302A (en) * | 2024-02-01 | 2024-03-08 | 浙江省白马湖实验室有限公司 | Combined heat and power load scheduling method based on two-stage integrated learning |
| CN117674302B (en) * | 2024-02-01 | 2024-05-03 | 浙江省白马湖实验室有限公司 | Combined heat and power load scheduling method based on two-stage integrated learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109961186A (en) | Desulphurization system operating parameter prediction technique based on decision tree and BP neural network | |
| CN109840362B (en) | Multi-objective optimization-based integrated just-in-time learning industrial process soft measurement modeling method | |
| CN108171641B (en) | Rail transit emergency plan evaluation method | |
| CN113591379B (en) | Auxiliary decision-making method for transient stability prevention and emergency coordination control of power system | |
| CN107037306A (en) | Transformer fault dynamic early-warning method based on HMM | |
| CN106447092A (en) | Marine reverse osmosis desalination system performance prediction method based on MEA-BP neural network | |
| US20220261655A1 (en) | Real-time prediction method for engine emission | |
| CN106896219A (en) | The identification of transformer sub-health state and average remaining lifetime method of estimation based on Gases Dissolved in Transformer Oil data | |
| CN111310990A (en) | Improved gray combination model-based track quality prediction method and system | |
| Ning et al. | GA-BP air quality evaluation method based on fuzzy theory. | |
| US20230237316A1 (en) | Forecast method and system of wind power probability density | |
| CN108804800A (en) | Lithium ion battery SOC on-line prediction methods based on echo state network | |
| CN116432123A (en) | Electric energy meter fault early warning method based on CART decision tree algorithm | |
| CN110033181B (en) | Power generation equipment state evaluation method based on self-encoder | |
| CN110851784A (en) | Early warning method for field operation of electric energy meter | |
| CN112418662A (en) | Power distribution network operation reliability analysis method using artificial neural network | |
| CN116662925A (en) | Industrial process soft measurement method based on weighted sparse neural network | |
| CN108363738B (en) | Recommendation method for industrial equipment data analysis algorithm | |
| CN110378045A (en) | A kind of pre- maintaining method of guide precision based on deep learning | |
| CN115828744A (en) | White light LED fault on-line diagnosis and service life prediction method | |
| CN113111588B (en) | NO of gas turbine X Emission concentration prediction method and device | |
| CN114648178A (en) | Operation and maintenance strategy optimization method of electric energy metering device based on DDPG algorithm | |
| Hui et al. | Prediction of safety objective of an enterprise using fuzzy neural network | |
| CN112070399B (en) | Safety risk assessment method and system for large-scale engineering structure | |
| CN104239046A (en) | Software self-adapting method based on HMM (hidden Markov model) and MOEA (multi-objective evolutionary algorithm) |
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: 20190702 |
|
| RJ01 | Rejection of invention patent application after publication |