CN103744293B - Wastewater treatment monitoring method and system based on fuzzy neural network - Google Patents
Wastewater treatment monitoring method and system based on fuzzy neural network Download PDFInfo
- Publication number
- CN103744293B CN103744293B CN201410039249.3A CN201410039249A CN103744293B CN 103744293 B CN103744293 B CN 103744293B CN 201410039249 A CN201410039249 A CN 201410039249A CN 103744293 B CN103744293 B CN 103744293B
- Authority
- CN
- China
- Prior art keywords
- soft
- sensing
- dissolved oxygen
- fuzzy
- anfis
- 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.)
- Expired - Fee Related
Links
Landscapes
- Feedback Control In General (AREA)
- Activated Sludge Processes (AREA)
Abstract
The invention provides a kind of wastewater treatment monitoring method based on fuzzy neural network, the method is on the basis of the parameters such as existing A/O Waste Water Treatments HRT, Aerobic Pond DO and return current ratio of the mixed liquid r are investigated on water outlet COD and ammonia nitrogen influence, the weights of neutral net and threshold value global search are optimized with the genetic algorithm based on real coding using neural network structure algorithm, the BP ANN soft-sensing models and GA ANN soft-sensing models of optimization are built respectively.The dissolved oxygen intelligent Optimal Control System scheme based on soft-sensing model is built on this basis, the data communication of MATLAB and MCGS is realized with reference to OPC technology, dissolved oxygen intelligent Optimal Control System is applied to paper waste A/O process treatment process dissolved oxygen Optimum Regulations, the energy-saving of paper waste A/O waste water treatment engineerings is realized.The present invention can increase substantially the stability of paper industry waste water draining water quality, realize precise control, and reduce chemicals consumption and power consumption in wastewater treatment process.
Description
Technical field
The invention belongs to a kind of technology neck for carrying out comprehensive stability treatment to paper production waste water using intelligence control system
Domain.
Background technology
As country, provinces and cities' environmental protection policy pressure are continued to increase, and each papermaking enterprise itself is for reduction production cost
The need for, while ton paper water consumption constantly declines, draining concentration is improved constantly, and draining water quality constantly deteriorates, variation water quality
Also it is larger, bring severe pressure to sewage disposal.Further, since the kind of each paper mill production is not quite similar, chemical industry used
Raw material is also otherwise varied, and production waiting also respectively has arrangement, therefore causes the influent quality fluctuation of wastewater reuse approach factory larger, enters
Water-carrying capacity, influent COD and chemical feeding quantity etc. are all being continually changing, and material is transmitted, migrated and transformed in affecting processing system
The balance of journey, thus current Waste Water Treatment is all difficult to real steady-state operation, generally there is effluent quality unstable
The problems such as fixed, Frequent Troubles, and wastewater treatment process have complexity, non-linear, time variation, it is uncertain the features such as.
Therefore, in order to improve the reliability and stability of processing system, system operation cost and maintenance cost are reduced, make be
System can realize energy-saving target again while Environmental Technology index is met, in the urgent need to developing a kind of automatic intelligent
Wastewater treatment control method and system.
Neutral net is also known as artificial neural network(Artificial Neural Network, abbreviation ANN or NN)It is with letter
Single non-linear neural is first as processing unit, by connecting and composing extensively with the non-of large-scale distributed parallel processing capability
Linear dynamics system.Soft-sensing model based on neutral net can be under conditions of not possessing object priori, according to right
The input/output data Direct Modeling of elephant(Using auxiliary variable as neutral net input, and leading variable is used as neutral net
Output, the hard measurement of not measurable variable is solved the problems, such as by the study of neutral net), and with stronger on-line correction energy
Power simultaneously can be suitably used for the bioprocess and serious uncertain system of polynary nonlinearity.Divide by structure type, nerve net
Network can substantially be divided into feedforward network and feedback network;More common in hard measurement is backpropagation neural network in feedforward network
Network (BP-ANN) and radial basis function neural network (RBF-ANN).Although neutral net is with arbitrarily approaching Nonlinear Mapping
The function of ability and self study self adaptation, it is also possible to high flexible approach any function with solve complexity nonlinear problem,
Suitable for the analog simulation of Waste Water Treatment.However, the gradient training algorithm used by it is a kind of local search algorithm, hold very much
Easily it is absorbed in local optimum;And there is the shortcomings of testing accuracy is high but precision of prediction is low, and net training time is more long.Therefore, a lot
Researcher is by with powerful global search and the genetic algorithm for optimizing function(Genetic Algorithm, abbreviation GA)For right
The optimization of neutral net, constructs the more excellent genetic neural network of performance (GA-ANN).Genetic algorithm be based on natural selection and
One class of gene genetics principle has the full search algorithm of parallel iteration ability and learning ability.It will " survival of the fittest be fitted
The theory of biologic evolution of person's existence " is introduced into the coded strings population that parameter to be optimized is formed, according to certain fitness value function
And using selection, intersect and variation three genetic operation operators the individuality in population is screened so that fitness value compared with
Excellent individuality is remained, and constitutes new population, and ideal adaptation angle value is continued to optimize in new population, until meeting certain limit
Condition, the final global search optimizing realized in solution space.
In view of the complexity and uncertainty of wastewater treatment, based on the mixed model that genetic algorithm and neutral net are combined
Modeling and simulating to wastewater treatment process studies Worth Expecting.
The content of the invention
The purpose of the present invention is exactly to solve prior art problem, there is provided at a kind of waste water based on fuzzy neural network monitoring
Reason method and system, sewage indices can be online considered using the system, self-organizing, self adaptation and good non-
The Based Intelligent Control of the wastewater treatment of the abilities such as Linear Mapping.
It is that, up to above-mentioned purpose, the technical scheme that the present invention takes is as follows:
A kind of wastewater treatment monitoring method based on fuzzy neural network, its step includes:
(1) process characteristic to A/O Biological Nitrogen Removal Processes is analyzed, from and necessary hardware device is installed,
Design PLC control program and carry out the Project Configuration of industrial control software MCGS, the embedded pulping wastewater treatment of structure automatically controls and is
System;
(2) biological nature and the structure and algorithm of combination neutral net according to A/O Waste Water Treatments, build optimal god
Through Network Soft Sensor Model:Choose hydraulic detention time (HRT), water inlet pH value that A/O Waste Water Treatments can be monitored on-line
(pH), the correlation of four parameters of Aerobic Pond dissolved oxygen (DO) and return current ratio of the mixed liquid (r) and water outlet COD and water outlet ammonia nitrogen,
Build BP-ANN the and ANFIS soft-sensing models of optimization respectively in MATLAB;
(3) global search optimization is carried out to the weights and threshold value of neutral net using the genetic algorithm based on real coding,
Build GA-ANN soft-sensing models;
(4) Adaptive Fuzzy Neural-network technology is incorporated into the GA-ANN soft-sensing model structures of A/O Waste Water Treatments
In building, combining adaptive Fuzzy C-Means Cluster Algorithm, so as to realize the automatic optimal of ANFIS soft-sensing model number of fuzzy rules;
The estimated performance of com-parison and analysis ANFIS soft-sensing models and GA-ANN soft-sensing models, should by the soft-sensing model of best performance
Dissolved oxygen intelligent Optimal Control System for building paper waste A/O handling process;
(5) data communication of MATLAB and MCGS is realized using OPC technology, and the dissolved oxygen intelligent optimization control that will be built
System processed is applied to the dissolved oxygen regulation process in paper waste A/O process treatment process.
Pulping wastewater treatment automatic control system includes the industry based on Windows CE.NET embedded OSs
People's computer, on-line computing model(COD detectors, DO detectors and pH detectors)And for realizing various intelligent control schemes
Executing agency.These executing agencies include intake pump, reflux pump and device etc. air blower, and these devices are received in the present system
IPC is controlled;By controlling the motor used by these devices, the task of regulation flow of inlet water, capacity of returns and aeration rate is completed.Carry out
The design of PLC control program and the configuration work of industrial control software MCGS;The mounting of PLC and ADAM modules is carried out, man-machine behaviour is built
Make platform, the online acquisition of realize intaking A/O technological processes pH value and Inlet and outlet water COD value and to flow of inlet water, mixed liquor
The online regulation and control of capacity of returns and dissolved oxygen.
Effluent quality hard measurement research based on neutral net and genetic neural network:By attempt different transmission functions,
Training algorithm and network structure, seek high performance BP neural network forecast model, are easily trapped into make up BP neural network
The shortcoming of local optimum, introduces the Real Coding Genetic Algorithm with ability of searching optimum to water outlet COD and water outlet ammonia nitrogen
BP-ANN soft-sensing models are optimized.
Effluent quality Research on Soft based on Adaptive Fuzzy Neural-network:It is poly- using adaptive fuzzy C averages
Class algorithm carries out space division to input data, draws the optimal number of fuzzy rules of ANFIS soft-sensing models.Pass through trial and error method again
Determine the membership function of ANFIS soft-sensing models, determine the ANFIS soft-sensing models training step of water outlet COD and water outlet ammonia nitrogen
Number.
Dissolved oxygen intelligent Optimal Control System based on Adaptive Fuzzy Neural-network soft-sensing model:That can monitor on-line
Hydraulic detention time (HRT), water inlet pH value (pH), Aerobic Pond dissolved oxygen (DO) and return current ratio of the mixed liquid (r) four parameters works
For the input quantity of ANFIS models sets up forecast model, it is used to predict and control water outlet COD value.
ANFIS models are chosen as the fuzzy controller in dissolved oxygen intelligent Optimal Control System, for controlling dissolved oxygen
Correction;ANFIS networks are trained using fuzzy rule, corresponding fuzzy rule are formed in online fuzzy rule base
Then, the control to dissolved oxygen content is realized.The data communication of MCGS and MATLAB is realized using OPC technology, is realized in MCGS rings
The operation of dissolved oxygen intelligent Optimal Control System under border.
The present invention is directed to the existing energy-saving demand of A/O Waste Water Treatments, is investigating A/O Waste Water Treatments HRT, good
On the basis of the parameter such as oxygen pond DO and return current ratio of the mixed liquid r is on water outlet COD and ammonia nitrogen influence, using neural network structure algorithm and base
The weights of neutral net and threshold value global search are optimized in the genetic algorithm of real coding, the BP-ANN of optimization is built respectively
Soft-sensing model and GA-ANN soft-sensing models.The dissolved oxygen intelligent optimal control based on soft-sensing model is built on this basis
System schema, the data communication of MATLAB and MCGS is realized with reference to OPC technology, and dissolved oxygen intelligent Optimal Control System is applied to
Paper waste A/O process treatment process dissolved oxygen Optimum Regulations, realize the energy-saving of paper waste A/O waste water treatment engineerings.
After the technology of the present invention is promoted, the stability of paper industry waste water draining water quality can be increased substantially(Estimated fluctuation from
Present 10% is dropped within 2%), precise control is realized, and reduce the chemicals consumption in wastewater treatment process(Estimated drop
It is low by 10% or so)And power consumption(It is estimated to reduce by 5% or so).
Technical scheme is described further with reference to the accompanying drawings and examples:
Brief description of the drawings
Fig. 1 is the monitoring system in waste water processing schematic diagram based on fuzzy neural network of the present invention.
Specific embodiment
As shown in figure 1, wastewater treatment monitoring method and system based on fuzzy neural network of the present invention include:
(1) process characteristic to A/O Biological Nitrogen Removal Processes is analyzed, from and necessary hardware device is installed,
Design PLC control program and carry out the Project Configuration of industrial control software MCGS, the embedded pulping wastewater treatment of structure automatically controls and is
System;
(2) biological nature and the structure and algorithm of combination neutral net according to A/O Waste Water Treatments, build optimal god
Through Network Soft Sensor Model:Choose hydraulic detention time (HRT), water inlet pH value that A/O Waste Water Treatments can be monitored on-line
(pH), the correlation of four parameters of Aerobic Pond dissolved oxygen (DO) and return current ratio of the mixed liquid (r) and water outlet COD and water outlet ammonia nitrogen,
Build BP-ANN the and ANFIS soft-sensing models of optimization respectively in MATLAB;
(3) global search optimization is carried out to the weights and threshold value of neutral net using the genetic algorithm based on real coding,
Build GA-ANN soft-sensing models;
(4) Adaptive Fuzzy Neural-network technology is incorporated into the GA-ANN soft-sensing model structures of A/O Waste Water Treatments
In building, combining adaptive Fuzzy C-Means Cluster Algorithm, so as to realize the automatic optimal of ANFIS soft-sensing model number of fuzzy rules;
The estimated performance of com-parison and analysis ANFIS soft-sensing models and GA-ANN soft-sensing models, should by the soft-sensing model of best performance
Dissolved oxygen intelligent Optimal Control System for building paper waste A/O handling process;
(5) data communication of MATLAB and MCGS is realized using OPC technology, and the dissolved oxygen intelligent optimization control that will be built
System processed is applied to the dissolved oxygen regulation process in paper waste A/O process treatment process.
The structure of pulping wastewater treatment automatic control system:Pulping wastewater treatment automatic control system includes being based on
Personal industry computer, the on-line computing model of Windows CE.NET embedded OSs(COD detectors, DO detectors and
PH detectors)And for realizing the executing agency of various intelligent control schemes.These executing agencies include intake pump, reflux pump
With the device such as air blower, these devices control by IPC in the present system;By controlling the motor used by these devices, complete to adjust
The task of section flow of inlet water, capacity of returns and aeration rate.Carry out the design of PLC control program and the configuration work of industrial control software MCGS
Make;The mounting of PLC and ADAM modules is carried out, human interface is built, intake to A/O technological processes pH value and Inlet and outlet water is realized
The online acquisition of COD value and the online regulation and control to flow of inlet water, mixed-liquor return amount and dissolved oxygen.
Effluent quality hard measurement research based on neutral net and genetic neural network:By attempt different transmission functions,
Training algorithm and network structure, set up high performance BP neural network forecast model, are easily trapped into make up BP neural network
The defect of local optimum, introduces the Real Coding Genetic Algorithm with ability of searching optimum to water outlet COD and water outlet ammonia nitrogen
BP-ANN soft-sensing models are optimized.
Effluent quality Research on Soft based on Adaptive Fuzzy Neural-network:It is poly- using adaptive fuzzy C averages
Class algorithm carries out space division to input data, obtains the optimal number of fuzzy rules of ANFIS soft-sensing models.Pass through trial and error method again
Determine the membership function of ANFIS soft-sensing models, determine the ANFIS soft-sensing models training step of water outlet COD and water outlet ammonia nitrogen
Number.
Dissolved oxygen intelligent Optimal Control System based on Adaptive Fuzzy Neural-network soft-sensing model:That can monitor on-line
Hydraulic detention time (HRT), water inlet pH value (pH), Aerobic Pond dissolved oxygen (DO) and return current ratio of the mixed liquid (r) four parameters works
For the input quantity of ANFIS models sets up forecast model, it is used to predict and control water outlet COD value.
ANFIS models are chosen as the fuzzy controller in dissolved oxygen intelligent Optimal Control System, for controlling dissolved oxygen
Correction;After being trained to ANFIS networks using fuzzy rule, corresponding fuzzy rule are formed in online fuzzy rule base
Then, the control to dissolved oxygen content is realized.The data communication of MCGS and MATLAB is realized using OPC technology, dissolved oxygen intelligent is realized
Operation of the Optimal Control System under MCGS environment.
Claims (2)
1. a kind of wastewater treatment monitoring method based on fuzzy neural network, its step includes:
(1) on the basis of A/O biological denitrification phosphorous removal technique features are analyzed, choose and install necessary hardware device, design PLC controls
Processing procedure sequence simultaneously carries out the Project Configuration of industrial control software MCGS, builds embedded pulping wastewater treatment automatic control system;
(2) biological nature according to A/O Waste Water Treatments and the structure and algorithm that pass through neutral net, build optimal nerve net
Network soft-sensing model:Choose hydraulic detention time (HRT), water inlet pH value (pH), good that A/O Waste Water Treatments can be monitored on-line
Four parameters in oxygen pond dissolved oxygen (DO) and return current ratio of the mixed liquid (r) and water outlet COD and the correlation of water outlet ammonia nitrogen, in MATLAB
The middle BP-ANN and ANFIS soft-sensing models for building optimization respectively;It is described build optimize BP-ANN soft-sensing models be
Refer to by attempting different transmission functions, training algorithm and network structure, seek high performance BP neural network forecast model, introduce
Real Coding Genetic Algorithm with ability of searching optimum carries out excellent to the BP-ANN soft-sensing models of water outlet COD and water outlet ammonia nitrogen
Change;
(3) genetic algorithm based on real coding carries out global search optimization to the weights and threshold value of neutral net, builds GA-
ANN soft-sensing models;
(4) Adaptive Fuzzy Neural-network is introduced into the GA-ANN soft-sensing models of A/O Waste Water Treatments structure, with reference to certainly
Fuzzy C-Means Cluster Algorithm is adapted to, the automatic optimal of ANFIS soft-sensing model number of fuzzy rules is realized;By com-parison and analysis
The estimated performance of ANFIS soft-sensing models and GA-ANN soft-sensing models, the soft-sensing model of best performance is made for structure
The dissolved oxygen intelligent Optimal Control System of paper waste water A/O handling process;Adaptive fuzzy C means clustering algorithms enter to input data
Row space divides, and draws the optimal number of fuzzy rules of ANFIS soft-sensing models, then determine ANFIS hard measurement moulds by trial and error method
The membership function of type, determines the ANFIS soft-sensing model train epochs of water outlet COD and water outlet ammonia nitrogen;
(5) data communication of MATLAB and MCGS is realized using OPC technology, and the dissolved oxygen intelligent optimal control system that will be built
System is applied to the dissolved oxygen regulation in paper waste A/O process treatment process.
2. the wastewater treatment monitoring method of fuzzy neural network is based on as claimed in claim 1, it is characterised in that:Using fuzzy
After rule is trained to ANFIS networks, corresponding fuzzy rule is formd in online fuzzy rule base, choose ANFIS moulds
Type is used as the fuzzy controller in dissolved oxygen intelligent Optimal Control System, the correction for controlling dissolved oxygen.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410039249.3A CN103744293B (en) | 2014-01-27 | 2014-01-27 | Wastewater treatment monitoring method and system based on fuzzy neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410039249.3A CN103744293B (en) | 2014-01-27 | 2014-01-27 | Wastewater treatment monitoring method and system based on fuzzy neural network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103744293A CN103744293A (en) | 2014-04-23 |
CN103744293B true CN103744293B (en) | 2017-06-16 |
Family
ID=50501322
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410039249.3A Expired - Fee Related CN103744293B (en) | 2014-01-27 | 2014-01-27 | Wastewater treatment monitoring method and system based on fuzzy neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103744293B (en) |
Families Citing this family (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105045951A (en) * | 2015-05-27 | 2015-11-11 | 华南理工大学 | Soft-measurement method for volatile fatty acid in effluent of anaerobic wastewater treatment system |
CN106022501A (en) * | 2015-10-13 | 2016-10-12 | 中国水产科学研究院渔业机械仪器研究所 | Freshwater aquaculture water quality prediction system based on meteorological data |
CN105573115B (en) * | 2015-12-09 | 2018-05-11 | 中山大学 | Sewage disposal process energy-conserving and optimizing control method based on quantum genetic algorithm |
CN105446138A (en) * | 2015-12-16 | 2016-03-30 | 中国农业大学 | Water quality adjusting optimizing system and water quality adjusting optimizing method in aquatic organism cultivation environment |
CN105629722B (en) * | 2016-02-23 | 2018-03-16 | 河海大学常州校区 | More pond sewage dynamic allocation methods and system based on fuzzy rule Self Adaptive Control |
CN107664682A (en) * | 2016-07-30 | 2018-02-06 | 复凌科技(上海)有限公司 | A kind of water quality hard measurement Forecasting Methodology of ammonia nitrogen |
CN107664683A (en) * | 2016-07-30 | 2018-02-06 | 复凌科技(上海)有限公司 | A kind of water quality hard measurement Forecasting Methodology of total nitrogen |
US20180121889A1 (en) * | 2016-10-28 | 2018-05-03 | Wipro Limited | Method and system for dynamically managing waste water treatment process for optimizing power consumption |
CN106600509B (en) * | 2016-12-28 | 2020-09-15 | 北京航空航天大学 | Method for analyzing and judging water exchange and pollution discharge behaviors of enterprise based on basic data |
CN106991491B (en) * | 2017-02-21 | 2020-11-13 | 南京邮电大学 | RBF neural network's environmental pollution monitoring system based on genetic algorithm optimization |
CN109507957B (en) * | 2017-09-15 | 2022-04-01 | 进金生实业股份有限公司 | Cloud intelligent power-saving system for water treatment industry |
CN108563118B (en) * | 2018-03-22 | 2020-10-16 | 北京工业大学 | Dissolved oxygen model prediction control method based on self-adaptive fuzzy neural network |
CN109857056A (en) * | 2019-03-08 | 2019-06-07 | 中冶华天南京电气工程技术有限公司 | A kind of Intelligent sewage processing control system |
CN110824915B (en) * | 2019-09-30 | 2022-06-07 | 华南师范大学 | GA-DBN network-based intelligent monitoring method and system for wastewater treatment |
CN110981021B (en) * | 2019-12-23 | 2022-08-05 | 中新国际联合研究院 | Intelligent dosing system and method for advanced wastewater oxidation treatment based on fuzzy BP neural network |
CN112327617B (en) * | 2020-10-21 | 2022-05-03 | 北京工业大学 | Robust optimization control method of aerobic-anoxic-anaerobic reactor |
CN112381138A (en) * | 2020-11-13 | 2021-02-19 | 长春工业大学 | OS-ELM-based complex separation process measurement model establishment method |
CN113087030B (en) * | 2021-03-02 | 2022-08-02 | 天津大学 | Water resource double-circulation feedback control system and method |
CN113031445B (en) * | 2021-03-12 | 2022-09-09 | 北京工业大学 | Mechanism model-based robust multivariable control method for sewage denitrification process |
CN116116181B (en) * | 2023-04-18 | 2023-07-18 | 科扬环境科技有限责任公司 | Model optimization-based waste gas and wastewater treatment method and device |
CN117092908B (en) * | 2023-10-19 | 2024-01-02 | 中国标准化研究院 | Intelligent control method and system for wastewater treatment equipment based on genetic algorithm |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102262147A (en) * | 2011-07-15 | 2011-11-30 | 华南理工大学 | Soft measurement method and system for effluent chemical oxygen demand (COD) of waste water treatment system |
CN202075272U (en) * | 2011-03-30 | 2011-12-14 | 北京中拓百川投资有限公司 | Soft measurement system applied to sewage treatment |
WO2012109900A1 (en) * | 2011-02-14 | 2012-08-23 | 华南理工大学 | Method and system for wastewater treatment based on dissolved oxygen control by fuzzy neural network |
CN102662040A (en) * | 2012-04-20 | 2012-09-12 | 辽宁工程技术大学 | Ammonian online soft measuring method for dynamic modularized nerve network |
CN102854296A (en) * | 2012-08-30 | 2013-01-02 | 北京工业大学 | Sewage-disposal soft measurement method on basis of integrated neural network |
CN103399134A (en) * | 2013-08-20 | 2013-11-20 | 渤海大学 | Sewage COD soft measurement method based on output observer |
-
2014
- 2014-01-27 CN CN201410039249.3A patent/CN103744293B/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012109900A1 (en) * | 2011-02-14 | 2012-08-23 | 华南理工大学 | Method and system for wastewater treatment based on dissolved oxygen control by fuzzy neural network |
CN202075272U (en) * | 2011-03-30 | 2011-12-14 | 北京中拓百川投资有限公司 | Soft measurement system applied to sewage treatment |
CN102262147A (en) * | 2011-07-15 | 2011-11-30 | 华南理工大学 | Soft measurement method and system for effluent chemical oxygen demand (COD) of waste water treatment system |
CN102662040A (en) * | 2012-04-20 | 2012-09-12 | 辽宁工程技术大学 | Ammonian online soft measuring method for dynamic modularized nerve network |
CN102854296A (en) * | 2012-08-30 | 2013-01-02 | 北京工业大学 | Sewage-disposal soft measurement method on basis of integrated neural network |
CN103399134A (en) * | 2013-08-20 | 2013-11-20 | 渤海大学 | Sewage COD soft measurement method based on output observer |
Also Published As
Publication number | Publication date |
---|---|
CN103744293A (en) | 2014-04-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103744293B (en) | Wastewater treatment monitoring method and system based on fuzzy neural network | |
US9747544B2 (en) | Method and system for wastewater treatment based on dissolved oxygen control by fuzzy neural network | |
CN105510546B (en) | A kind of biochemical oxygen demand (BOD) BOD intelligent detecting methods based on self-organizing Recurrent RBF Neural Networks | |
CN105404151B (en) | Sewage disposal process dynamic multi-objective optimization control method | |
Do et al. | A design of higher-level control based genetic algorithms for wastewater treatment plants | |
CN108536106A (en) | A kind of aerating system dissolved oxygen based on Kalman filtering-extreme learning machine regulates and controls method online | |
Yao et al. | Predicting membrane fouling in a high solid AnMBR treating OFMSW leachate through a genetic algorithm and the optimization of a BP neural network model | |
CN113189881A (en) | Multi-objective optimization control method and system for sewage treatment | |
Gheytaspour et al. | Forecasting oxygen demand in treatment plant using artificial neural networks | |
Sulaiman et al. | Modeling anaerobic process for wastewater treatment: new trends and methodologies | |
Yetilmezsoy et al. | Adaptive neuro-fuzzy inference-based modeling of a full-scale expanded granular sludge bed reactor treating corn processing wastewater | |
CN112250246B (en) | Intelligent azo dye wastewater detoxification and advanced treatment method | |
CN106769748B (en) | Intelligent detection system for water permeability of membrane bioreactor-MBR (Membrane bioreactor) | |
Wang et al. | Artificial intelligence algorithm application in wastewater treatment plants: Case study for COD load prediction | |
Fu et al. | Dissolved oxygen control system based on the TS fuzzy neural network | |
Huang et al. | Modeling and optimization of the activated sludge process | |
Huang et al. | Improving nitrogen removal using a fuzzy neural network-based control system in the anoxic/oxic process | |
Swarnalatha | Simulation and Analysis of Ammonium-Based Aeration Control Strategies to Enhance Efficiency in Wastewater Treatment Plant | |
Huang et al. | Modeling of a paper-making wastewater treatment process using a fuzzy neural network | |
Ramesh et al. | Relevance of Artificial Intelligence in Wastewater Management | |
Yordanova et al. | Neuro-fuzzy control for anaerobic wastewater treatment | |
Zhang et al. | Direct adaptive neural network control for wastewater treatment process | |
Luolong et al. | Predicting wastewater sludge recycle performance based on fuzzy neural network | |
Bakht et al. | Hybrid Multi-Stream Deep Learning-Based Nutrient Estimation Framework in Biological Wastewater Treatement | |
Juuso | Hybrid models in dynamic simulation of a biological water treatment process |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170616 Termination date: 20180127 |
|
CF01 | Termination of patent right due to non-payment of annual fee |