CN112661259A - Self-adaptive control method and system for aeration process - Google Patents
Self-adaptive control method and system for aeration process Download PDFInfo
- Publication number
- CN112661259A CN112661259A CN202011479871.8A CN202011479871A CN112661259A CN 112661259 A CN112661259 A CN 112661259A CN 202011479871 A CN202011479871 A CN 202011479871A CN 112661259 A CN112661259 A CN 112661259A
- Authority
- CN
- China
- Prior art keywords
- adaptive control
- neural network
- model
- activated sludge
- parameter information
- 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
- 238000000034 method Methods 0.000 title claims abstract description 128
- 230000008569 process Effects 0.000 title claims abstract description 93
- 238000005273 aeration Methods 0.000 title claims abstract description 54
- 239000010802 sludge Substances 0.000 claims abstract description 99
- 238000013528 artificial neural network Methods 0.000 claims abstract description 92
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims abstract description 71
- 229910052760 oxygen Inorganic materials 0.000 claims abstract description 71
- 239000001301 oxygen Substances 0.000 claims abstract description 71
- 239000010865 sewage Substances 0.000 claims abstract description 62
- 230000003044 adaptive effect Effects 0.000 claims description 64
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 38
- 238000004062 sedimentation Methods 0.000 claims description 29
- 239000002245 particle Substances 0.000 claims description 20
- 238000004088 simulation Methods 0.000 claims description 15
- 238000005457 optimization Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000000342 Monte Carlo simulation Methods 0.000 claims description 10
- 230000033228 biological regulation Effects 0.000 claims description 10
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 description 12
- 238000005265 energy consumption Methods 0.000 description 11
- 101100436077 Caenorhabditis elegans asm-1 gene Proteins 0.000 description 10
- 101100204282 Neurospora crassa (strain ATCC 24698 / 74-OR23-1A / CBS 708.71 / DSM 1257 / FGSC 987) Asm-1 gene Proteins 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000005070 sampling Methods 0.000 description 5
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000000813 microbial effect Effects 0.000 description 4
- 244000005700 microbiome Species 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000005538 encapsulation Methods 0.000 description 3
- 230000012010 growth Effects 0.000 description 3
- 230000007062 hydrolysis Effects 0.000 description 3
- 238000006460 hydrolysis reaction Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 241000894006 Bacteria Species 0.000 description 2
- 238000005842 biochemical reaction Methods 0.000 description 2
- 230000031018 biological processes and functions Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 239000003344 environmental pollutant Substances 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 229910052757 nitrogen Inorganic materials 0.000 description 2
- 238000004806 packaging method and process Methods 0.000 description 2
- 231100000719 pollutant Toxicity 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 239000006228 supernatant Substances 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- CKUAXEQHGKSLHN-UHFFFAOYSA-N [C].[N] Chemical compound [C].[N] CKUAXEQHGKSLHN-UHFFFAOYSA-N 0.000 description 1
- 230000001651 autotrophic effect Effects 0.000 description 1
- 239000013043 chemical agent Substances 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- -1 flow rate Substances 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000033001 locomotion Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000007269 microbial metabolism Effects 0.000 description 1
- 239000013586 microbial product Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010992 reflux Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 230000005477 standard model Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000003911 water pollution Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
- Y02W10/00—Technologies for wastewater treatment
- Y02W10/10—Biological treatment of water, waste water, or sewage
Landscapes
- Activated Sludge Processes (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses an aeration process self-adaptive control method and system, which relate to the field of sewage treatment, and comprise the steps of adopting an aerobic pool dissolved oxygen concentration self-adaptive control model to calculate a next-moment aerobic pool dissolved oxygen concentration adjusting target according to the acquired current-moment sewage quality parameter information, activated sludge quality parameter information and air volume information of a blower, and determining the air volume of the blower at the next moment according to the next-moment aerobic pool dissolved oxygen concentration adjusting target; wherein the aerobic tank dissolved oxygen concentration self-adaptive control model is established and determined according to a PSO-BP neural network and an activated sludge model No. 1; the invention can optimize and transform the aeration process of the biological treatment system of the sewage treatment plant, and improve the stability and the utilization efficiency of the biological treatment system.
Description
Technical Field
The invention relates to the field of sewage treatment, in particular to an aeration process self-adaptive control method and system.
Background
The sewage treatment belongs to the energy consumption intensive industry, and the energy consumption mainly comprises chemical agents, electric energy, combustion heat energy and the like. Wherein, the electric energy consumption of the urban sewage treatment plant accounts for about 60-90% of the direct energy consumption of the whole plant. The biological treatment system takes charge of removing main pollutants in the sewage, is a core link of sewage treatment, and the energy consumption required by the operation of the biological treatment system is about 50-70% of the energy consumption required by the whole plant. The aeration process of the biological treatment system of the sewage treatment plant is optimized and modified, the stability and the utilization efficiency of the biological treatment system are improved, and the biological treatment system meets the requirements of effluent standard of the sewage treatment plant and meets the requirements of energy conservation and consumption reduction.
The sewage treatment industry in China is restricted by industrialization and economic development and relatively starts late, and meanwhile, the number of the sewage treatment plants is small and the distribution is uneven, most of the sewage treatment plants still have the defects of backward equipment and technology, high energy consumption, low automation and intelligence degree and the like, and the sewage treatment plants are urgently needed to be amplified, reformed and upgraded. Therefore, in order to reduce energy consumption, reduce sewage treatment cost, improve sewage treatment quality and improve sewage treatment efficiency, the sewage treatment plants in China should be developed towards intellectualization, automation, precision and low energy consumption in the future, wherein the technical research and upgrading modification of the aeration process occupying the main energy consumption and the core part of the sewage treatment plants are more important in the future research and development. Because the direct experiment of the sewage treatment plant has low feasibility and high cost, the simulation control needs to be performed through modeling so as to provide a theoretical basis for the actual experiment. However, the aeration process involves biological reaction, mud water backflow and other processes, and the modeling has many influencing factors and is complex, so that the modeling has certain difficulty. In addition, the current domestic aeration process is mainly controlled by manual PID regulation control or manual experience control, the control accuracy is low, and the aeration process control has the characteristics of uncertainty, nonlinearity, time-varying property, time lag, great inertia and the like. Therefore, the fine control of the aeration process is not only a key problem in sewage treatment but also a difficult problem.
Disclosure of Invention
The invention aims to provide an aeration process self-adaptive control method and system aiming at the defects of the prior art, which are used for optimizing and modifying the aeration process of a biological treatment system of a sewage treatment plant and improving the stability and the utilization efficiency of the biological treatment system.
In order to achieve the purpose, the invention provides the following scheme:
an adaptive control method for an aeration process comprises the following steps:
acquiring the sewage quality parameter information, the activated sludge quality parameter information and the air volume information of the blower at the current moment;
calculating a dissolved oxygen concentration adjusting target of the aerobic tank at the next moment by adopting an aerobic tank dissolved oxygen concentration self-adaptive control model according to the sewage quality parameter information, the activated sludge quality parameter information and the air volume information of the blower at the current moment;
determining the air output of the blower at the next moment according to the dissolved oxygen concentration regulation target of the aerobic tank at the next moment;
the self-adaptive control model of the dissolved oxygen concentration of the aerobic tank is established and determined according to a PSO-BP neural network and an activated sludge model No. 1.
Optionally, acquiring the sewage quality parameter information, the activated sludge parameter information and the blower air volume information at the current moment specifically comprises:
acquiring sewage quality parameter information in real time by using water quality sensors arranged at a water inlet end, a water outlet end, an aerobic tank and a secondary sedimentation tank; the sewage quality parameter information comprises temperature, COD, ammonia nitrogen, TKN, DO and pH;
acquiring activated sludge mudness parameter information in real time by using online sludge concentration meters arranged in an aerobic tank and a secondary sedimentation tank; the activated sludge argillaceous parameter information is MLSS;
and acquiring air quantity information of the air blower in real time by utilizing an air quantity sensor arranged at an air outlet pipeline opening of the air blower.
Optionally, the determination process of the adaptive control model for the dissolved oxygen concentration of the aerobic tank is as follows:
constructing an activated sludge model No. 1;
taking the dissolved oxygen concentration of an aerobic pool in the aeration process as a control object, taking the activated sludge model No.1 as a platform, and adopting a Monte Carlo method to carry out a simulation experiment on the PSO-BP neural network adaptive control model so as to obtain an optimized PSO-BP neural network adaptive control model; the optimized PSO-BP neural network self-adaptive control model is a self-adaptive control model of the dissolved oxygen concentration of the aerobic pool.
Optionally, the constructing of the activated sludge model No.1 specifically includes:
and constructing an activated sludge model No.1 based on a model process flow based on COST624&682 standards, Simulink in MATLAB or a graphical user interface in MATLAB.
Optionally, the determining process of the PSO-BP neural network adaptive control model is as follows:
determining sample data; the sample data comprises the sewage quality parameter information, the activated sludge quality parameter information and the blower air quantity information at the historical moment;
constructing a BP neural network;
determining initial weights of a hidden layer and an output layer by adopting a particle swarm algorithm;
determining a PID control structure based on the BP neural network according to the initial weights of the BP neural network and the hidden layer and the output layer;
and training the PID control structure based on the BP neural network by adopting the sample data to obtain a PSO-BP neural network self-adaptive control model.
An aeration process adaptive control system comprising:
the information acquisition module is used for acquiring the sewage quality parameter information, the activated sludge quality parameter information and the air volume information of the blower at the current moment;
the aerobic tank dissolved oxygen concentration regulation target calculation module is used for calculating a dissolved oxygen concentration regulation target of the aerobic tank at the next moment by adopting an aerobic tank dissolved oxygen concentration self-adaptive control model according to the sewage quality parameter information, the activated sludge quality parameter information and the air volume information of the blower at the current moment;
the air outlet quantity determining module is used for determining the air outlet quantity of the air blower at the next moment according to the dissolved oxygen concentration adjusting target of the aerobic pool at the next moment;
the self-adaptive control model of the dissolved oxygen concentration of the aerobic tank is established and determined according to a PSO-BP neural network and an activated sludge model No. 1.
Optionally, the information obtaining module specifically includes:
the water quality parameter information acquisition unit is used for acquiring the sewage quality parameter information in real time by using water quality sensors arranged at the water inlet end, the water outlet end, the aerobic tank and the secondary sedimentation tank; the sewage quality parameter information comprises temperature, COD, ammonia nitrogen, TKN, DO and pH;
the sludge parameter information acquisition unit is used for acquiring activated sludge parameter information in real time by using online sludge concentration meters arranged in the aerobic tank and the secondary sedimentation tank; the activated sludge argillaceous parameter information is MLSS;
and the air blower air volume information acquisition unit is used for acquiring air blower air volume information in real time by utilizing an air volume sensor arranged at an air outlet pipeline opening of the air blower.
Optionally, the method further includes: an adaptive control model building module for the dissolved oxygen concentration of the aerobic tank; the adaptive control model building module for the dissolved oxygen concentration of the aerobic tank comprises:
the activated sludge model 1 constructing unit is used for constructing an activated sludge model 1;
the optimization unit is used for carrying out simulation experiments on the PSO-BP neural network adaptive control model by taking the dissolved oxygen concentration of an aerobic pool in the aeration process as a control object and taking the activated sludge model No.1 as a platform and adopting a Monte Carlo method so as to obtain the optimized PSO-BP neural network adaptive control model; the optimized PSO-BP neural network self-adaptive control model is a self-adaptive control model of the dissolved oxygen concentration of the aerobic pool.
Optionally, the activated sludge model No.1 constructing unit specifically includes:
and the activated sludge model No.1 constructing subunit is used for constructing an activated sludge model No.1 based on a model process flow of COST624&682 benchmark, Simulink in MATLAB or a graphical user interface in MATLAB.
Optionally, the optimization unit specifically includes:
a sample data determining subunit, configured to determine sample data; the sample data comprises the sewage quality parameter information, the activated sludge quality parameter information and the blower air quantity information at the historical moment;
the BP neural network construction subunit is used for constructing a BP neural network;
the initial weight calculation subunit is used for determining initial weights of the hidden layer and the output layer by adopting a particle swarm algorithm;
the PID control structure determining subunit is used for determining a PID control structure based on the BP neural network according to the BP neural network and the initial weights of the hidden layer and the output layer;
the PSO-BP neural network adaptive control model determining subunit is used for training the PID control structure based on the BP neural network by adopting the sample data to obtain a PSO-BP neural network adaptive control model;
the optimization subunit is used for carrying out simulation experiments on the PSO-BP neural network adaptive control model by taking the dissolved oxygen concentration of the aerobic tank in the aeration process as a control object and taking the activated sludge model No.1 as a platform and adopting a Monte Carlo method so as to obtain the optimized PSO-BP neural network adaptive control model; the optimized PSO-BP neural network self-adaptive control model is a self-adaptive control model of the dissolved oxygen concentration of the aerobic pool.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention optimizes the design of the controller of the aeration process of the sewage treatment plant, constructs an adaptive control model of the dissolved oxygen concentration of the aerobic tank based on the PSO-BP neural network, increases the intelligent control link of the dissolved oxygen concentration of the aerobic tank, breaks through the limitation of the traditional control by manual experience, and improves the stability and the utilization efficiency of the aeration process.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of the adaptive control method for aeration process according to the present invention;
FIG. 2 is a block diagram of an adaptive control system for an aeration process according to the present invention;
FIG. 3 is a model process flow diagram of COST624&682 benchmark for the present invention;
FIG. 4 is an encapsulation diagram of the components of the processes within the bioreactor according to the present invention;
FIG. 5 is a schematic diagram of the packaging modules for the reaction rate of the process group molecular process, the movement speed of particles in the secondary sedimentation tank, the sludge concentration of each voxel layer and the like in the model of the invention;
FIG. 6 is an overall encapsulation diagram of the activated sludge model No.1 according to the present invention using the A/O process;
FIG. 7 is a schematic structural diagram of a BP neural network according to the present invention;
FIG. 8 is a control structure diagram of the PSO-BP neural network adaptive algorithm of the present invention;
FIG. 9 is a diagram of the aeration process based on the PSO-BP neural network adaptive control of 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.
The invention aims to provide an aeration process self-adaptive control method and system, which are used for optimizing and modifying the aeration process of a biological treatment system of a sewage treatment plant, and improving the stability and the utilization efficiency of the biological treatment system
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Example one
As shown in fig. 1, the present embodiment provides an adaptive control method for an aeration process, including:
step 101: acquiring the sewage quality parameter information, the activated sludge quality parameter information and the air volume information of the blower at the current moment; the method specifically comprises the following steps:
acquiring sewage quality parameter information in real time by using water quality sensors arranged at a water inlet end, a water outlet end, an aerobic tank and a secondary sedimentation tank; the sewage quality parameter information comprises temperature, COD, ammonia nitrogen, TKN, DO and pH.
Acquiring activated sludge mudness parameter information in real time by using online sludge concentration meters arranged in an aerobic tank and a secondary sedimentation tank; the activated sludge argillaceous parameter information is MLSS.
And acquiring air quantity information of the air blower in real time by utilizing an air quantity sensor arranged at an air outlet pipeline opening of the air blower.
Step 102: and calculating the dissolved oxygen concentration adjusting target of the aerobic tank at the next moment by adopting an aerobic tank dissolved oxygen concentration self-adaptive control model according to the sewage quality parameter information, the activated sludge quality parameter information and the air volume information of the blower at the current moment.
The self-adaptive control model of the dissolved oxygen concentration of the aerobic tank is established and determined according to a PSO-BP neural network and an activated sludge model No. 1.
Step 103: and determining the air output of the air blower at the next moment according to the dissolved oxygen concentration regulation target of the aerobic tank at the next moment.
The determination process of the self-adaptive control model for the dissolved oxygen concentration of the aerobic tank comprises the following steps:
constructing an activated sludge model No. 1; the method specifically comprises the following steps: and constructing an activated sludge model No.1 based on a model process flow based on COST624&682 standards, Simulink in MATLAB or a graphical user interface in MATLAB.
Taking the dissolved oxygen concentration of an aerobic pool in the aeration process as a control object, taking the activated sludge model No.1 as a platform, and adopting a Monte Carlo method to carry out a simulation experiment on the PSO-BP neural network adaptive control model so as to obtain an optimized PSO-BP neural network adaptive control model; the optimized PSO-BP neural network self-adaptive control model is a self-adaptive control model of the dissolved oxygen concentration of the aerobic pool.
The PSO-BP neural network adaptive control model determination process comprises the following steps:
determining sample data; the sample data comprises the sewage quality parameter information, the activated sludge quality parameter information and the blower air quantity information at the historical moment.
And constructing the BP neural network.
And determining initial weights of the hidden layer and the output layer by adopting a particle swarm algorithm.
And determining a PID control structure based on the BP neural network according to the initial weights of the BP neural network and the hidden layer and the output layer.
And training the PID control structure based on the BP neural network by adopting the sample data to obtain a PSO-BP neural network self-adaptive control model.
Example two
As shown in fig. 2, the present embodiment provides an adaptive control system for an aeration process, including:
the information acquisition module 201 is used for acquiring the sewage quality parameter information, the activated sludge quality parameter information and the blower air volume information at the current moment; the method specifically comprises the following steps:
the water quality parameter information acquisition unit is used for acquiring the sewage quality parameter information in real time by using water quality sensors arranged at the water inlet end, the water outlet end, the aerobic tank and the secondary sedimentation tank; the sewage quality parameter information comprises temperature, COD, ammonia nitrogen, TKN, DO and pH.
The sludge parameter information acquisition unit is used for acquiring activated sludge parameter information in real time by using online sludge concentration meters arranged in the aerobic tank and the secondary sedimentation tank; the activated sludge argillaceous parameter information is MLSS.
And the air blower air volume information acquisition unit is used for acquiring air blower air volume information in real time by utilizing an air volume sensor arranged at an air outlet pipeline opening of the air blower.
The aerobic tank dissolved oxygen concentration regulation target calculation module 202 is used for calculating a dissolved oxygen concentration regulation target of the aerobic tank at the next moment by adopting an aerobic tank dissolved oxygen concentration self-adaptive control model according to the sewage quality parameter information, the activated sludge quality parameter information and the air volume information of the blower at the current moment; the self-adaptive control model of the dissolved oxygen concentration of the aerobic tank is established and determined according to a PSO-BP neural network and an activated sludge model No. 1.
And the air output determining module 203 is used for determining the air output of the air blower at the next moment according to the dissolved oxygen concentration adjusting target of the aerobic tank at the next moment.
The adaptive control system for the aeration process provided by the embodiment further comprises: an adaptive control model building module for the dissolved oxygen concentration of the aerobic tank; the adaptive control model building module for the dissolved oxygen concentration of the aerobic tank comprises:
and the activated sludge model No.1 constructing unit is used for constructing an activated sludge model No. 1.
The optimization unit is used for carrying out simulation experiments on the PSO-BP neural network adaptive control model by taking the dissolved oxygen concentration of an aerobic pool in the aeration process as a control object and taking the activated sludge model No.1 as a platform and adopting a Monte Carlo method so as to obtain the optimized PSO-BP neural network adaptive control model; the optimized PSO-BP neural network self-adaptive control model is a self-adaptive control model of the dissolved oxygen concentration of the aerobic pool.
The model construction unit for the activated sludge No.1 specifically comprises:
and the activated sludge model No.1 constructing subunit is used for constructing an activated sludge model No.1 based on a model process flow of COST624&682 benchmark, Simulink in MATLAB or a graphical user interface in MATLAB.
The optimization unit specifically includes:
a sample data determining subunit, configured to determine sample data; the sample data comprises the sewage quality parameter information, the activated sludge quality parameter information and the blower air quantity information at the historical moment.
And the BP neural network constructing subunit is used for constructing the BP neural network.
And the initial weight calculation subunit is used for determining the initial weights of the hidden layer and the output layer by adopting a particle swarm algorithm.
And the PID control structure determining subunit is used for determining a PID control structure based on the BP neural network according to the BP neural network and the initial weights of the hidden layer and the output layer.
And the PSO-BP neural network adaptive control model determining subunit is used for training the PID control structure based on the BP neural network by adopting the sample data to obtain a PSO-BP neural network adaptive control model.
The optimization subunit is used for carrying out simulation experiments on the PSO-BP neural network adaptive control model by taking the dissolved oxygen concentration of the aerobic tank in the aeration process as a control object and taking the activated sludge model No.1 as a platform and adopting a Monte Carlo method so as to obtain the optimized PSO-BP neural network adaptive control model; the optimized PSO-BP neural network self-adaptive control model is a self-adaptive control model of the dissolved oxygen concentration of the aerobic pool.
EXAMPLE III
The invention provides a control method of an aeration process based on PSO-BP neural network adaptive control, which comprises the following steps:
step S1: monitoring the sewage quality parameter information and the activated sludge mud parameter information in the water inlet end, the water outlet end, the aerobic tank and the secondary sedimentation tank in real time by using an online sensor; and the air quantity information of the air blower is monitored on line by utilizing an air quantity sensor arranged at the outlet of an air outlet pipeline of the air blower.
Step S2: and a controller arranged in the blower room acquires the sewage quality parameter information, the activated sludge quality parameter information and the blower air volume information of the aeration process, and the variables and the parameters are called as the current system state.
Step S3: the controller calculates the optimal dissolved oxygen concentration regulating target of the aerobic tank under the current system state based on the current system state and the dissolved oxygen concentration self-adaptive control model of the aerobic tank.
Step S4: the controller adjusts the air output of the air blower according to the dissolved oxygen concentration adjusting target of the aerobic tank, and self-adaptive intelligent control is achieved.
In the control method for the aeration process based on the PSO-BP neural network adaptive control provided in this embodiment, the sewage quality parameter information includes temperature, COD, ammonia nitrogen, TKN, DO, pH, and the like, and the activated sludge argillaceous parameter information is MLSS.
In the control method for the aeration process based on the PSO-BP neural network adaptive control provided by this embodiment, the online sensor includes a water quality sensor, a mud quality sensor, and an air volume sensor. The water quality sensor is arranged at a water inlet end, a water outlet end, an aerobic tank and a secondary sedimentation tank, and comprises a flowmeter, an online thermometer, an online liquid level meter, an online pH meter, an online ORP tester, an online DO meter, an online COD meter, an online ammonia nitrogen meter and an online TKN meter; the mud sensors are arranged in the aerobic tank and the secondary sedimentation tank and are online sludge concentration meters; the air quantity sensor is arranged in an air outlet pipeline of the air blower.
In the control method for an aeration process based on PSO-BP neural network adaptive control provided in this embodiment, a method for constructing an adaptive control model for dissolved oxygen concentration in an aerobic tank is specifically described as follows:
in this example, model 1 (Activated Sludge model No.1, ASM1 for short) proposed by the international society for water pollution control and research is used. The ASM1 divides the substance in the sewage into 13 process components according to biological characteristics such as solubility, contained components and the like, divides the system reaction process into 8 sub-processes according to the angles such as microbial metabolism, electron receptors and the like, and adopts a double Monod mode for rate description of each sub-process, so that the model parameter has no space change and is a centralized parameter model.
The ASM1 divides the biological process in the biological reaction tank into 8 sub-processes (including 3 microorganism growth processes, 2 microorganism attenuation processes, 1 ammoniation process and 2 hydrolysis processes), divides the material in the biological reaction tank into 13 process components (including 8 carbon nitrogen substrates, 3 microorganism materials, 1 additional electron acceptor and 1 process alkalinity change), each sub-process has several process components, each process component takes part in several sub-processes, meanwhile, 5 stoichiometric parameters are defined aiming at the metering relation of mutual transformation among the process components in each subprocess, and 14 reaction kinetic parameters (including a half saturation coefficient, a microbial attenuation coefficient, a microbial maximum specific growth rate, correction factors of microbial growth and hydrolysis, and ammoniation and hydrolysis rates) are defined aiming at the reaction of the process components participating in each subprocess.
In this embodiment, based on ASM1, a sub-process reaction rate equation and a single-process component total reaction rate equation are sequentially established, and units of each process component are unified to finally generate a model.
The sewage treatment system is a large nonlinear system affected by large disturbances such as inflow water, flow rate, pollutant load and inflow water components. Optimizing its control strategy by modeling requires overcoming a number of difficulties, such as: large time constant range (several minutes to several days, etc.), complexity of biological reactions, lack of standard evaluation criteria, etc. Therefore, an acceptable process benchmark is needed to establish and test the activated sludge model No. 1.
The activated sludge model No.1 established by the invention is constructed and verified based on a COST624&682 standard model process flow. The COST624&682 benchmark addresses the goals of reducing research COSTs and improving sewage treatment technologies by enhancing understanding of microorganisms in the activated sludge system and enhancing control optimization of the biological treatment process.
The model process flow of COST624&682 benchmark has the following requirements:
a) consists of 5 continuous biochemical tanks (2 anoxic tanks and 3 aerobic tanks, adopting an A/O process) and a secondary sedimentation tank;
b) the biochemical pool 1 and the biochemical pool 2 are anoxic pools without adding air; the biochemical pool 3, the biochemical pool 4 and the biochemical pool 5 are aerobic pools, and the saturated dissolved oxygen concentration in the biochemical pool is 8g/m3The Kla default values are 10/hr, 10/hr and 3.5/hr, respectively, and ASM1 is used asA biochemical reaction process model;
c) the secondary sedimentation tank has no biochemical reaction and is divided into 10 layers, and a sedimentation process model is described by adopting a Takacs double-exponential sedimentation rate equation;
d) mixed liquor circulates from the biochemical tank 5 to the biochemical tank 1, and sludge flows back and circulates from the secondary sedimentation tank to the biochemical tank 1.
e) The physical structure parameters of the biochemical tank and the secondary sedimentation tank, the dynamic parameters, the stoichiometric parameters and the secondary sedimentation tank model parameter values of the ASM1 at 15 ℃, the water inlet value and the water outlet value of the ASM1 at a steady state, the steady state value and the water outlet value of each layer of the secondary sedimentation tank, the water inlet value and the water outlet value of the ASM1 at a dynamic state, and the dynamic value and the water outlet value of each layer of the secondary sedimentation tank are given by the standard. FIG. 3 shows COST624&682 benchmark model process flow chart; wherein each letter of FIG. 3 is interpreted as QinFor the inflow, QrIs the amount of sludge recirculation, QrinIs the internal circulation reflux amount, QfThe water inflow of the secondary sedimentation tank, QeThe discharge amount of supernatant in the secondary sedimentation tank, QwThe discharge amount of the sludge in the secondary sedimentation tank is reduced; zinAs the concentration of the influent component, ZrTo return the concentration of the sludge component, ZrinIs the internal circulating component concentration, ZfIs the concentration of the water inlet component of the secondary sedimentation tank, ZeDischarge supernatant component concentration, ZwFor the discharge sludge component concentration.
In addition, the embodiment also adopts another two more intuitive and concise modeling representations in MATLAB, which are specifically as follows:
the present embodiment uses Simulink in MATLAB to represent modeling more intuitively and concisely. The packaging of each mechanism for operating the Simulink-built activated sludge model No.1 is shown in FIGS. 4-6. The interior of the biological reaction tank model is composed of encapsulation modules of all process components, the concentration change of the process components follows the material conservation principle, and the same process components participate in various reactions. The model built by Simulink is clear and intuitive in structure through intuitive feeling, and the model operation effect can be obtained through the change of the output value of an oscilloscope and the operation process.
The present embodiment also employs a Graphical User Interface (GUI) in MATLAB to more intuitively and succinctly represent modeling. According to the designed functional module, the interface of the simulation system mainly has the functions of input sample selection, sampling step length setting, kinetic parameter setting, stoichiometric parameter setting and drawing of three aerobic tank dissolved oxygen concentration change curves. The interface design comprises controls such as an edit box, a radio button, a coordinate axis box, a static text box and the like. The specific design is as follows:
a) control and sampling parameter settings. And 3 editing frames are used for acquiring parameters such as system sampling step length, sampling control step length, sampling days and the like.
b) A sample selection is input. The 5 radio buttons select the input sample.
c) And (3) drawing a change curve of the dissolved oxygen concentration of the aerobic tanks. The 2 buttons select the program to run and begin drawing curves or clear curves already drawn in the coordinate axis, and the 3 coordinate axis boxes are used to display curves.
d) Initial performance parameter settings. 19 static texts and 19 edit boxes are used to prompt and input the set kinetic and stoichiometric parameters, respectively.
An activated sludge model No.1 interface designed by using a GUI graphical user interface has the functions of parameter setting, input selection, output curve drawing and the like.
In the embodiment, a simulation experiment is performed on the control effect of the PSO-BP neural network adaptive control model by taking the dissolved oxygen concentration of the aerobic tank in the aeration process as a control object and taking the ASM1 as a platform.
Particle Swarm Optimization (PSO) is an evolutionary computing technique that treats each problem solution being optimized as a particle. All the particles are searched in a D-dimensional space, an optimal position is searched, an adaptive value is determined by using the fixness-function to judge the quality of the current position, and meanwhile, the speed, namely the flying direction and the flying distance, are continuously adjusted according to the flying experience of the particles and the fellows. Furthermore, the particle can remember its currently determined optimal position during the search process.
As shown in fig. 7, the present embodiment employs a three-layer BP neural network, which includes 4 input nodes, 5 hidden nodes, and 3 output nodes. j is the input layer, i is the hidden layer, l is the output layer, yr(k) Y (k), e (k),1 is BP nerveAn input of the network; k is a radical ofp,ki,kdAnd outputting the result to the BP neural network.
The control structure of the PSO-BP neural network adaptive control model is shown in FIG. 8. The PID control method based on the BP neural network has the problem of sensitive initial values, namely the selection of the initial weights of the hidden layer and the output layer has great influence on the final operation result of the system. And a large number of repeated experimental tests are usually needed to select a proper initial value, and if the initial value is manually selected and tested and screened, the operation is too heavy and tedious. In the embodiment, the system performs multiple times of initial selection on the initial weight by using a Particle Swarm Optimization (PSO), and selects the initial value with the best comprehensive effect from the recorded results.
The specific learning process is as follows:
a) and calculating the total quantity of the connection weights in the BP neural network, namely the dimension value of the particles in the particle swarm algorithm.
b) Randomly generating a particle population, setting the evolution times, and performing iterative learning according to a particle swarm algorithm;
c) and evaluating the quality, the superiority and the inferiority of the generated individuals by using a mean square error function output by the whole system as a fitness function, and obtaining a BP neural network weight when the mean square error output by the system reaches the minimum by using the strong iterative search capability of a particle swarm algorithm.
The control method for the aeration process based on the PSO-BP neural network adaptive control provided in this embodiment trains an adaptive control model of dissolved oxygen concentration in the aeration process by using the PSO-BP neural network, where the training parameters are as follows: learning rate eta is 0.003, inertia coefficient gamma is 0.003, initial weight is random value, and the stable weight with best operation stability effect is selected by a particle swarm algorithm.
Noise immunity and robustness are important metrics for controlling system performance.
In order to observe and analyze the experimental results conveniently, in this embodiment, the ASM1 is set in a steady-state input state, gaussian white noise with a signal-to-noise ratio of 20 is added to the feedback signals of the aeration tank, and a simulation experiment is performed on the system using the dissolved oxygen concentration adaptive control model of the PSO-BP neural network shown in fig. 9.
In the embodiment, a Monte Carlo method is adopted to test the robust performance of the aeration process of the activated sludge system under the dissolved oxygen concentration self-adaptive control model of the PSO-BP neural network. In order to observe and analyze the experimental result conveniently, the system is in a dynamic input state. For autotrophic bacteria yield coefficient Y in experimental modelAHeterotrophic bacteria yield coefficient YHThe proportion f of inert particles in the microorganismPThe ratio of the nitrogen content in the microbial cells iXBThe nitrogen content ratio i in the microbial productXPAnd respectively selecting parameter perturbation intervals. The parameters are uniformly distributed in a given interval, 50 groups of parameter values are randomly combined, and then the state of the self-adaptive control model is obtained through a simulation experiment when the parameters are randomly combined. Meanwhile, the upper limit value of the parameters is taken, and a simulation experiment is carried out to obtain a self-adaptive control model when the parameters are severe.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (10)
1. An adaptive control method for an aeration process, which is characterized by comprising the following steps:
acquiring the sewage quality parameter information, the activated sludge quality parameter information and the air volume information of the blower at the current moment;
calculating a dissolved oxygen concentration adjusting target of the aerobic tank at the next moment by adopting an aerobic tank dissolved oxygen concentration self-adaptive control model according to the sewage quality parameter information, the activated sludge quality parameter information and the air volume information of the blower at the current moment;
determining the air output of the blower at the next moment according to the dissolved oxygen concentration regulation target of the aerobic tank at the next moment;
the self-adaptive control model of the dissolved oxygen concentration of the aerobic tank is established and determined according to a PSO-BP neural network and an activated sludge model No. 1.
2. An aeration process self-adaptive control method according to claim 1, wherein the acquiring of the sewage quality parameter information, the activated sludge quality parameter information and the blower air volume information at the current time specifically comprises:
acquiring sewage quality parameter information in real time by using water quality sensors arranged at a water inlet end, a water outlet end, an aerobic tank and a secondary sedimentation tank; the sewage quality parameter information comprises temperature, COD, ammonia nitrogen, TKN, DO and pH;
acquiring activated sludge mudness parameter information in real time by using online sludge concentration meters arranged in an aerobic tank and a secondary sedimentation tank; the activated sludge argillaceous parameter information is MLSS;
and acquiring air quantity information of the air blower in real time by utilizing an air quantity sensor arranged at an air outlet pipeline opening of the air blower.
3. An aeration process adaptive control method according to claim 1, wherein the aerobic tank dissolved oxygen concentration adaptive control model is determined by the following steps:
constructing an activated sludge model No. 1;
taking the dissolved oxygen concentration of an aerobic pool in the aeration process as a control object, taking the activated sludge model No.1 as a platform, and adopting a Monte Carlo method to carry out a simulation experiment on the PSO-BP neural network adaptive control model so as to obtain an optimized PSO-BP neural network adaptive control model; the optimized PSO-BP neural network self-adaptive control model is a self-adaptive control model of the dissolved oxygen concentration of the aerobic pool.
4. An aeration process self-adaptive control method according to claim 3, wherein the construction of the activated sludge model No.1 specifically comprises the following steps:
and constructing an activated sludge model No.1 based on a model process flow based on COST624&682 standards, Simulink in MATLAB or a graphical user interface in MATLAB.
5. An aeration process adaptive control method according to claim 3, wherein the PSO-BP neural network adaptive control model is determined by the following steps:
determining sample data; the sample data comprises the sewage quality parameter information, the activated sludge quality parameter information and the blower air quantity information at the historical moment;
constructing a BP neural network;
determining initial weights of a hidden layer and an output layer by adopting a particle swarm algorithm;
determining a PID control structure based on the BP neural network according to the initial weights of the BP neural network and the hidden layer and the output layer;
and training the PID control structure based on the BP neural network by adopting the sample data to obtain a PSO-BP neural network self-adaptive control model.
6. An adaptive control system for aeration processes, comprising:
the information acquisition module is used for acquiring the sewage quality parameter information, the activated sludge quality parameter information and the air volume information of the blower at the current moment;
the aerobic tank dissolved oxygen concentration regulation target calculation module is used for calculating a dissolved oxygen concentration regulation target of the aerobic tank at the next moment by adopting an aerobic tank dissolved oxygen concentration self-adaptive control model according to the sewage quality parameter information, the activated sludge quality parameter information and the air volume information of the blower at the current moment;
the air outlet quantity determining module is used for determining the air outlet quantity of the air blower at the next moment according to the dissolved oxygen concentration adjusting target of the aerobic pool at the next moment;
the self-adaptive control model of the dissolved oxygen concentration of the aerobic tank is established and determined according to a PSO-BP neural network and an activated sludge model No. 1.
7. An adaptive control system for aeration processes according to claim 6, wherein the information acquisition module specifically comprises:
the water quality parameter information acquisition unit is used for acquiring the sewage quality parameter information in real time by using water quality sensors arranged at the water inlet end, the water outlet end, the aerobic tank and the secondary sedimentation tank; the sewage quality parameter information comprises temperature, COD, ammonia nitrogen, TKN, DO and pH;
the sludge parameter information acquisition unit is used for acquiring activated sludge parameter information in real time by using online sludge concentration meters arranged in the aerobic tank and the secondary sedimentation tank; the activated sludge argillaceous parameter information is MLSS;
and the air blower air volume information acquisition unit is used for acquiring air blower air volume information in real time by utilizing an air volume sensor arranged at an air outlet pipeline opening of the air blower.
8. An adaptive control system for an aeration process according to claim 6, characterized by further comprising: an adaptive control model building module for the dissolved oxygen concentration of the aerobic tank; the adaptive control model building module for the dissolved oxygen concentration of the aerobic tank comprises:
the activated sludge model 1 constructing unit is used for constructing an activated sludge model 1;
the optimization unit is used for carrying out simulation experiments on the PSO-BP neural network adaptive control model by taking the dissolved oxygen concentration of an aerobic pool in the aeration process as a control object and taking the activated sludge model No.1 as a platform and adopting a Monte Carlo method so as to obtain the optimized PSO-BP neural network adaptive control model; the optimized PSO-BP neural network self-adaptive control model is a self-adaptive control model of the dissolved oxygen concentration of the aerobic pool.
9. An adaptive control system for an aeration process according to claim 8, wherein the model construction unit No.1 of the activated sludge specifically comprises:
and the activated sludge model No.1 constructing subunit is used for constructing an activated sludge model No.1 based on a model process flow of COST624&682 benchmark, Simulink in MATLAB or a graphical user interface in MATLAB.
10. An adaptive control system for an aeration process according to claim 8, wherein the optimization unit comprises:
a sample data determining subunit, configured to determine sample data; the sample data comprises the sewage quality parameter information, the activated sludge quality parameter information and the blower air quantity information at the historical moment;
the BP neural network construction subunit is used for constructing a BP neural network;
the initial weight calculation subunit is used for determining initial weights of the hidden layer and the output layer by adopting a particle swarm algorithm;
the PID control structure determining subunit is used for determining a PID control structure based on the BP neural network according to the BP neural network and the initial weights of the hidden layer and the output layer;
the PSO-BP neural network adaptive control model determining subunit is used for training the PID control structure based on the BP neural network by adopting the sample data to obtain a PSO-BP neural network adaptive control model;
the optimization subunit is used for carrying out simulation experiments on the PSO-BP neural network adaptive control model by taking the dissolved oxygen concentration of the aerobic tank in the aeration process as a control object and taking the activated sludge model No.1 as a platform and adopting a Monte Carlo method so as to obtain the optimized PSO-BP neural network adaptive control model; the optimized PSO-BP neural network self-adaptive control model is a self-adaptive control model of the dissolved oxygen concentration of the aerobic pool.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011479871.8A CN112661259A (en) | 2020-12-15 | 2020-12-15 | Self-adaptive control method and system for aeration process |
AU2021101438A AU2021101438A4 (en) | 2020-12-15 | 2021-03-20 | Adaptive control method and system for aeration process |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011479871.8A CN112661259A (en) | 2020-12-15 | 2020-12-15 | Self-adaptive control method and system for aeration process |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112661259A true CN112661259A (en) | 2021-04-16 |
Family
ID=75404690
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011479871.8A Pending CN112661259A (en) | 2020-12-15 | 2020-12-15 | Self-adaptive control method and system for aeration process |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN112661259A (en) |
AU (1) | AU2021101438A4 (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113511736A (en) * | 2021-05-18 | 2021-10-19 | 广州中国科学院沈阳自动化研究所分所 | Intelligent aeration method and device for sewage treatment |
CN113609754A (en) * | 2021-07-05 | 2021-11-05 | 上海华高汇元工程服务有限公司 | Air distribution control method for sewage aeration |
CN113830896A (en) * | 2021-09-27 | 2021-12-24 | 湖南工商大学 | Aerobic segment oxygen early warning method, system and equipment based on graph neural network |
CN113979541A (en) * | 2021-11-26 | 2022-01-28 | 昆明理工大学 | A2Intelligent control method for O biological pond process |
CN114314823A (en) * | 2022-02-09 | 2022-04-12 | 南开大学 | Dissolved oxygen control system and method in aeration link |
CN114442686A (en) * | 2022-01-13 | 2022-05-06 | 中国农业大学 | Method and device for controlling dissolved oxygen concentration, electronic device, and storage medium |
CN115385445A (en) * | 2022-09-21 | 2022-11-25 | 南京晓庄学院 | Soft measurement management system for sewage biochemical treatment based on big data |
CN115806344A (en) * | 2022-11-22 | 2023-03-17 | 曲誉环境综合治理有限公司 | ORP control accurate aeration system |
CN116081797A (en) * | 2022-08-25 | 2023-05-09 | 北控水务(中国)投资有限公司 | Dynamic optimization method, device and equipment for full-flow control quantity of sewage treatment plant |
CN116165974A (en) * | 2022-12-14 | 2023-05-26 | 上海市政工程设计研究总院(集团)有限公司 | Aeration control method, system, terminal and medium for sewage treatment process |
CN117252100A (en) * | 2023-09-22 | 2023-12-19 | 安徽理工大学 | Airbag performance optimization method and system based on medicament combustion test |
CN118026321A (en) * | 2024-04-12 | 2024-05-14 | 四川欧美华环境工程有限公司 | Air supply aeration control system for sewage treatment |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113393316B (en) * | 2021-06-10 | 2023-02-03 | 罗嗣扬 | Loan overall process accurate wind control and management system based on massive big data and core algorithm |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108002532A (en) * | 2017-11-15 | 2018-05-08 | 南京普信环保股份有限公司 | Sewage disposal model dynamic checking method based on Internet of Things and big data technology |
CN108563118A (en) * | 2018-03-22 | 2018-09-21 | 北京工业大学 | A kind of dissolved oxygen model predictive control method based on Adaptive Fuzzy Neural-network |
CN109711070A (en) * | 2018-12-29 | 2019-05-03 | 上海海事大学 | A kind of dissolved oxygen concentration optimization method based on activated sludge water process |
CN109879410A (en) * | 2019-03-27 | 2019-06-14 | 上海西派埃智能化系统有限公司 | Sewage treatment aeration control system |
CN110378533A (en) * | 2019-07-22 | 2019-10-25 | 中展环能(北京)技术有限公司 | A kind of intelligence aeration management method based on big data analysis |
CN112062179A (en) * | 2020-08-24 | 2020-12-11 | 华南理工大学 | Dissolved oxygen layered optimization control method for GHG emission reduction in papermaking wastewater treatment |
-
2020
- 2020-12-15 CN CN202011479871.8A patent/CN112661259A/en active Pending
-
2021
- 2021-03-20 AU AU2021101438A patent/AU2021101438A4/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108002532A (en) * | 2017-11-15 | 2018-05-08 | 南京普信环保股份有限公司 | Sewage disposal model dynamic checking method based on Internet of Things and big data technology |
CN108563118A (en) * | 2018-03-22 | 2018-09-21 | 北京工业大学 | A kind of dissolved oxygen model predictive control method based on Adaptive Fuzzy Neural-network |
CN109711070A (en) * | 2018-12-29 | 2019-05-03 | 上海海事大学 | A kind of dissolved oxygen concentration optimization method based on activated sludge water process |
CN109879410A (en) * | 2019-03-27 | 2019-06-14 | 上海西派埃智能化系统有限公司 | Sewage treatment aeration control system |
CN110378533A (en) * | 2019-07-22 | 2019-10-25 | 中展环能(北京)技术有限公司 | A kind of intelligence aeration management method based on big data analysis |
CN112062179A (en) * | 2020-08-24 | 2020-12-11 | 华南理工大学 | Dissolved oxygen layered optimization control method for GHG emission reduction in papermaking wastewater treatment |
Non-Patent Citations (4)
Title |
---|
乔俊飞等: "基于改进粒子群算法的污水处理过程神经网络优化控制", 《智能系统学报》 * |
吴宏鑫等: "《特征建模 理论、方法和应用》", 31 October 2019, 国防工业出版社 * |
潘锦宇: "基于改进神经网络预测的智能污水处理监控系统设计", 《中国优秀博硕士学位论文全文数据库(硕士) 工程科技Ⅰ辑》 * |
王彪龙等: "基于自然选择策略的PSO-BP神经网络的滑坡可靠性评价方法", 《中外公路》 * |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113511736A (en) * | 2021-05-18 | 2021-10-19 | 广州中国科学院沈阳自动化研究所分所 | Intelligent aeration method and device for sewage treatment |
CN113511736B (en) * | 2021-05-18 | 2023-01-13 | 广州中国科学院沈阳自动化研究所分所 | Intelligent aeration method and device for sewage treatment |
CN113609754B (en) * | 2021-07-05 | 2023-08-25 | 上海华高汇元工程服务有限公司 | Air quantity distribution control method for sewage aeration |
CN113609754A (en) * | 2021-07-05 | 2021-11-05 | 上海华高汇元工程服务有限公司 | Air distribution control method for sewage aeration |
CN113830896A (en) * | 2021-09-27 | 2021-12-24 | 湖南工商大学 | Aerobic segment oxygen early warning method, system and equipment based on graph neural network |
CN113830896B (en) * | 2021-09-27 | 2022-12-27 | 湖南工商大学 | Aerobic segment oxygen early warning method, system and equipment based on graph neural network |
CN113979541A (en) * | 2021-11-26 | 2022-01-28 | 昆明理工大学 | A2Intelligent control method for O biological pond process |
CN113979541B (en) * | 2021-11-26 | 2023-11-03 | 昆明理工大学 | A, A 2 Intelligent control method for O biological pool process |
CN114442686A (en) * | 2022-01-13 | 2022-05-06 | 中国农业大学 | Method and device for controlling dissolved oxygen concentration, electronic device, and storage medium |
CN114442686B (en) * | 2022-01-13 | 2024-02-06 | 中国农业大学 | Dissolved oxygen concentration control method, dissolved oxygen concentration control device, electronic equipment and storage medium |
CN114314823A (en) * | 2022-02-09 | 2022-04-12 | 南开大学 | Dissolved oxygen control system and method in aeration link |
CN116081797A (en) * | 2022-08-25 | 2023-05-09 | 北控水务(中国)投资有限公司 | Dynamic optimization method, device and equipment for full-flow control quantity of sewage treatment plant |
CN115385445A (en) * | 2022-09-21 | 2022-11-25 | 南京晓庄学院 | Soft measurement management system for sewage biochemical treatment based on big data |
CN115806344B (en) * | 2022-11-22 | 2023-08-04 | 曲誉环境综合治理有限公司 | ORP (integrated pressure and pressure) control precise aeration system |
CN115806344A (en) * | 2022-11-22 | 2023-03-17 | 曲誉环境综合治理有限公司 | ORP control accurate aeration system |
CN116165974A (en) * | 2022-12-14 | 2023-05-26 | 上海市政工程设计研究总院(集团)有限公司 | Aeration control method, system, terminal and medium for sewage treatment process |
CN117252100A (en) * | 2023-09-22 | 2023-12-19 | 安徽理工大学 | Airbag performance optimization method and system based on medicament combustion test |
CN117252100B (en) * | 2023-09-22 | 2024-05-03 | 安徽理工大学 | Airbag performance optimization method and system based on medicament combustion test |
CN118026321A (en) * | 2024-04-12 | 2024-05-14 | 四川欧美华环境工程有限公司 | Air supply aeration control system for sewage treatment |
Also Published As
Publication number | Publication date |
---|---|
AU2021101438A4 (en) | 2021-05-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112661259A (en) | Self-adaptive control method and system for aeration process | |
CN102122134A (en) | Method and system for wastewater treatment of dissolved oxygen control based on fuzzy neural network | |
CN109857056A (en) | A kind of Intelligent sewage processing control system | |
CN110378533A (en) | A kind of intelligence aeration management method based on big data analysis | |
CN106802563B (en) | A kind of sewage procedure optimization control method based on drosophila optimization and LSSVM | |
Mulas | Modelling and control of activated sludge processes | |
CN109669352A (en) | Oily waste water treatment procedure optimization control method based on adaptive multi-objective particle swarm | |
US11709463B2 (en) | Control method based on adaptive neural network model for dissolved oxygen of aeration system | |
AU2021100130A4 (en) | Intelligent control method and system for sewage treatment aeration based on deep learning | |
CN109711070A (en) | A kind of dissolved oxygen concentration optimization method based on activated sludge water process | |
CN111762958A (en) | Deep well aeration process optimization method and device for sewage treatment plant based on ASM2D model | |
CN114314823B (en) | System and method for controlling dissolved oxygen in aeration link | |
CN116360366B (en) | Sewage treatment process optimization control method | |
Chen et al. | Optimal strategies evaluated by multi-objective optimization method for improving the performance of a novel cycle operating activated sludge process | |
CN106651032A (en) | Method for intelligently controlling ammoxidation process of SBR method by neural network | |
Sotomayor et al. | Software sensor for on-line estimation of the microbial activity in activated sludge systems | |
CN114132980B (en) | Short-range intelligent accurate aeration control method, equipment and system for sewage treatment | |
CN101928064A (en) | Method for simulating paper-making wastewater treatment by activated sludge process | |
CN113087288A (en) | Water treatment control system and method for energy center of manufacturing enterprise | |
CN115959933B (en) | Intelligent control method and system for aerobic composting | |
CN117079730A (en) | A, A 2 Method for establishing full-flow optimized mathematical model of O biological pond process | |
Kapumbe et al. | Modeling and simulation of membrane bioreactor model based on ASM3 for domestic wastewater treatment. | |
Huang et al. | Modeling and optimization of the activated sludge process | |
CN107720975B (en) | Sewage treatment optimization simulation method using ethanol substances as external carbon source | |
CN116165974A (en) | Aeration control method, system, terminal and medium for sewage treatment process |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210416 |