[go: up one dir, main page]

CN115557600B - Artificial neural network intelligent aeration device for biochemical reaction and control method thereof - Google Patents

Artificial neural network intelligent aeration device for biochemical reaction and control method thereof Download PDF

Info

Publication number
CN115557600B
CN115557600B CN202211245104.XA CN202211245104A CN115557600B CN 115557600 B CN115557600 B CN 115557600B CN 202211245104 A CN202211245104 A CN 202211245104A CN 115557600 B CN115557600 B CN 115557600B
Authority
CN
China
Prior art keywords
neural network
input
detector
water quality
quality monitoring
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.)
Active
Application number
CN202211245104.XA
Other languages
Chinese (zh)
Other versions
CN115557600A (en
Inventor
李强林
詹春洪
邱诚
杨华莲
谢雨桐
徐萧月
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chengdu Huicai Environmental Protection Technology Co ltd
Chengdu Univeristy of Technology
Original Assignee
Chengdu Huicai Environmental Protection Technology Co ltd
Chengdu Univeristy of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chengdu Huicai Environmental Protection Technology Co ltd, Chengdu Univeristy of Technology filed Critical Chengdu Huicai Environmental Protection Technology Co ltd
Publication of CN115557600A publication Critical patent/CN115557600A/en
Application granted granted Critical
Publication of CN115557600B publication Critical patent/CN115557600B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F3/00—Biological treatment of water, waste water, or sewage
    • C02F3/02—Aerobic processes
    • C02F3/12—Activated sludge processes
    • C02F3/1236—Particular type of activated sludge installations
    • C02F3/1263—Sequencing batch reactors [SBR]
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F3/00—Biological treatment of water, waste water, or sewage
    • C02F3/02—Aerobic processes
    • C02F3/12—Activated sludge processes
    • C02F3/1236—Particular type of activated sludge installations
    • C02F3/1268—Membrane bioreactor systems
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F7/00—Aeration of stretches of water
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2209/00—Controlling or monitoring parameters in water treatment
    • C02F2209/02—Temperature
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2209/00—Controlling or monitoring parameters in water treatment
    • C02F2209/04—Oxidation reduction potential [ORP]
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2209/00—Controlling or monitoring parameters in water treatment
    • C02F2209/06—Controlling or monitoring parameters in water treatment pH
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2209/00—Controlling or monitoring parameters in water treatment
    • C02F2209/08—Chemical Oxygen Demand [COD]; Biological Oxygen Demand [BOD]
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2209/00—Controlling or monitoring parameters in water treatment
    • C02F2209/40—Liquid flow rate
    • 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

  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Organic Chemistry (AREA)
  • Hydrology & Water Resources (AREA)
  • Environmental & Geological Engineering (AREA)
  • Water Supply & Treatment (AREA)
  • Chemical & Material Sciences (AREA)
  • Microbiology (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Activated Sludge Processes (AREA)

Abstract

The invention discloses an artificial neural network intelligent aeration device for biochemical reaction and a control method thereof, which comprises the steps of deploying a neural network model in a controller, the neural network model is used for adjusting network parameters according to the data acquired by the inlet water quality monitoring assembly and the outlet water quality monitoring assembly, so that the aeration rate can be accurately controlled according to the water quality, the water quantity and the external environment by optimizing the calculation process.

Description

Artificial neural network intelligent aeration device for biochemical reaction and control method thereof
Technical Field
The invention relates to the technical field of sewage treatment, in particular to an artificial neural network intelligent aeration device for biochemical reaction and a control method thereof.
Background
The SBR water treatment process is a sequencing batch activated sludge process, which is also called batch activated sludge process sewage treatment process. The SBR technology is based on a technology of wastewater biological treatment activated sludge method for degrading pollutants such as organic matters, ammonia nitrogen and the like in sewage under aerobic-anoxic-anaerobic conditions by using microorganisms growing in suspension. In order to provide aerobic conditions, aeration is needed in the SBR biochemical reaction tank, and aeration is usually provided in the form of an aerator, and the aeration is stopped in the anoxic-anaerobic stage.
The aeration quantity directly determines the growth activity of aerobic microorganisms, plays an important role in biochemical reaction stages such as degradation of organic matters, nitrification and the like, if the aeration quantity is insufficient, dissolved oxygen in water is insufficient, aerobic bacteria cannot normally survive, so that the activity of sludge is inhibited, the nitrification is insufficient, the chemical oxygen demand of effluent and ammonia nitrogen are out of standard, the quality of effluent water is affected, and if the aeration quantity is excessive, namely the aeration quantity exceeds the oxygen quantity actually required by activated sludge treatment sewage, the activated sludge is oxidized by itself, and bad effects such as sludge aging flocculation decomposition, sludge expansion and the like are caused, and if the excessive aeration has negative effects on the process, the unnecessary energy consumption is increased.
The prior aeration technology cannot be adjusted and optimized according to water quality, water quantity and external environment, so that the aeration quantity is inaccurate.
Disclosure of Invention
Aiming at the defects in the prior art, the artificial neural network intelligent aeration device for biochemical reaction and the control method thereof solve the problem that the existing aeration technology cannot be adjusted and optimized according to water quality, water quantity and external environment, so that the aeration quantity is inaccurate.
In order to achieve the aim of the invention, the technical scheme adopted by the invention is that the artificial neural network intelligent aeration device for biochemical reaction comprises a controller, an aerator, an adjusting tank, an SBR biochemical tank, an MBR membrane separation tank, a water outlet tank, a water inlet quality monitoring component and a water outlet quality monitoring component;
The sewage treatment device comprises an adjusting tank, a water inlet water quality monitoring component, an aeration machine and a controller, wherein the adjusting tank is internally provided with a lifting pump which is used for pumping sewage which is collected into the adjusting tank into the SBR biochemical tank, the SBR biochemical tank is used for carrying out biochemical reaction on the sewage and collecting the sewage after the biochemical reaction into the MBR membrane separation tank, the MBR membrane separation tank is used for carrying out mud-water separation on the sewage after the biochemical reaction to obtain filtered water, the water outlet tank is used for containing the filtered water, the water inlet water quality monitoring component is inserted into the adjusting tank and used for collecting water inlet data and sending the water inlet data to the controller, the water outlet water quality monitoring component is inserted into the SBR biochemical tank and used for collecting water quality data in the aeration process and sending the water quality data to the controller, and the controller is used for controlling the aeration amount of the aeration machine according to the water inlet data and the water quality data.
Further, the inlet water quality monitoring component comprises a flowmeter, a COD detector, a TP detector, a TN detector, a DO detector, a temperature detector and a pH detector, and the outlet water quality monitoring component comprises a COD detector, a TP detector, a TN detector, a DO detector, a sludge concentration detector, a pH detector and an ORP detector.
A control method of an artificial neural network intelligent aeration device for biochemical reaction comprises the following steps:
S1, training a neural network model according to data acquired by a water inlet water quality monitoring assembly and a water outlet water quality monitoring assembly to obtain a primarily trained neural network model;
s2, deploying the primarily trained neural network model in a controller;
s3, acquiring data of the inlet water quality monitoring assembly and the outlet water quality monitoring assembly in real time, inputting the data into a controller, and adjusting network parameters of a primarily trained neural network model;
and S4, calculating the aeration quantity of the aerator according to the adjusted neural network model.
Further, the neural network model in the step S1 comprises an input layer, an implicit layer and an output layer;
the relationship between the input layer and the output layer is:
Wherein Y is the output of the output layer, X k is the kth input quantity of the input layer, K is the quantity of the input quantity, For the actual output corresponding to the kth input, C jk is the radial base center corresponding to the kth input of the jth hidden layer neuron, sigma j is the radial base width of the jth hidden layer neuron, D jk is the weight of the kth input of the jth hidden layer neuron, L is the number of hidden layer neurons, w j is the weight of the jth hidden layer neuron, and N is the number of hidden layer neurons.
Further, the acquiring the radial base center includes the steps of:
a1, calculating the distance between all input quantities to obtain a sample distance set;
a2, selecting a plurality of different sample distances from the sample distance set as initial centers;
a3, calculating the distance from a plurality of input quantities to each initial center;
A4, judging whether the distance is smaller than a distance threshold, if so, adding the input quantity into the corresponding initial center to obtain a plurality of similar sets, otherwise, taking the distance as a new initial center, and jumping to the step A3 until all the input quantity is distributed to the similar sets;
a5, obtaining a radial base center according to all input quantities in the similar set.
The further scheme has the beneficial effects that a plurality of different sample distances are selected from the sample distance set to serve as initial centers, a plurality of initial centers can be obtained, input quantities close to the initial centers are found and are classified into a similar set, the distances among the input quantities in the similar set are lower than a distance threshold, when the input quantities are far away from the existing initial center, namely the distance threshold is not met, the distance is taken as a new initial center, and therefore each input quantity can be classified into the corresponding similar set, and the radial base center can be found in a self-adaptive mode.
Further, the calculation formula of the radial base center in the step A5 is as follows:
Wherein, C jk is the radial base center corresponding to the kth input quantity of the neuron of the jth hidden layer in a similar set, P is the quantity of the input quantity in the similar set, and X k is the kth input quantity of the input layer.
Further, the weight update formula of the jth hidden layer neuron is as follows:
wj i+1＝wj i-△wj i
Wherein w j i+1 is the weight of the jth hidden layer neuron of the (i+1) th iteration, w j i is the weight of the jth hidden layer neuron of the (i) th iteration, and Δw j i is the weight variation of the jth hidden layer neuron of the (i) th iteration.
Further, the formula of the weight change amount Δw j i is:
Wherein, eta is the moving step length, For the gradient mean value estimator of the i-1 th iteration, θ i-1 is the gradient statistical dispersion estimator of the i-1 th iteration, λ i-1 is the attenuation factor of the i-1 th iteration, λ i-2 is the attenuation factor of the i-2 nd iteration,For the gradient mean value estimator of the i-2 th iteration, θ i-2 is the gradient statistical dispersion estimator of the i-2 th iteration, Y i is the output of the output layer of the i-2 th iteration, and ε is a constant.
In summary, the invention has the beneficial effects that the neural network model is deployed in the controller, and the network parameters are adjusted according to the data acquired by the inlet water quality monitoring assembly and the outlet water quality monitoring assembly through the neural network model, so that the invention can optimize the calculation process according to the water quality, the water quantity and the external environment, and accurately control the aeration.
Drawings
FIG. 1 is a schematic diagram of an artificial neural network intelligent aeration device for biochemical reactions;
FIG. 2 is a flow chart of a control method of an artificial neural network intelligent aeration device for biochemical reaction.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and all the inventions which make use of the inventive concept are protected by the spirit and scope of the present invention as defined and defined in the appended claims to those skilled in the art.
As shown in figure 1, the artificial neural network intelligent aeration device for biochemical reaction comprises a controller, an aerator, an adjusting tank, an SBR biochemical tank, an MBR membrane separation tank, a water outlet tank, a water inlet quality monitoring component and a water outlet quality monitoring component;
The sewage treatment device comprises an adjusting tank, a water inlet water quality monitoring component, an aeration machine and a controller, wherein the adjusting tank is internally provided with a lifting pump which is used for pumping sewage which is collected into the adjusting tank into the SBR biochemical tank, the SBR biochemical tank is used for carrying out biochemical reaction on the sewage and collecting the sewage after the biochemical reaction into the MBR membrane separation tank, the MBR membrane separation tank is used for carrying out mud-water separation on the sewage after the biochemical reaction to obtain filtered water, the water outlet tank is used for containing the filtered water, the water inlet water quality monitoring component is inserted into the adjusting tank and used for collecting water inlet data and sending the water inlet data to the controller, the water outlet water quality monitoring component is inserted into the SBR biochemical tank and used for collecting water quality data in the aeration process and sending the water quality data to the controller, and the controller is used for controlling the aeration amount of the aeration machine according to the water inlet data and the water quality data.
The inlet water quality monitoring component comprises a flowmeter, a COD detector, a TP detector, a TN detector, a DO detector, a temperature detector, a pH detector and a sludge concentration detector, and the outlet water quality monitoring component comprises a COD detector, a TP detector, a TN detector, a DO detector, a sludge concentration detector, a pH detector and an ORP detector.
As shown in fig. 2, a control method of an artificial neural network intelligent aeration device for biochemical reaction comprises the following steps:
S1, training a neural network model according to data acquired by a water inlet water quality monitoring assembly and a water outlet water quality monitoring assembly to obtain a primarily trained neural network model;
s2, deploying the primarily trained neural network model in a controller;
s3, acquiring data of the inlet water quality monitoring assembly and the outlet water quality monitoring assembly in real time, inputting the data into a controller, and adjusting network parameters of a primarily trained neural network model;
and S4, calculating the aeration quantity of the aerator according to the adjusted neural network model.
The reference aeration rate of the next operation period is obtained through machine learning by the data collected before and after the biochemical reaction, the stored aeration rate process data are increased along with the increase of the operation time of the system, the aeration rate is more and more accurate and the effluent quality is more stable as the aeration rate data which can be referred to later are given, so that the purposes of intelligence, high efficiency and energy saving are achieved.
In step S1, the data acquired by the inlet water quality monitoring component and the data acquired by the outlet water quality monitoring component are firstly used for preliminarily finding the corresponding relation between the inlet water and the outlet water after aeration of the aerator to obtain a preliminarily trained neural network model, the preliminarily trained neural network model is applied to the biochemical process of the biochemical pool, and in the actual operation process, the network parameters of the neural network model are continuously finely adjusted again through the outlet water data after aeration, which is equivalent to the fact that the neural network model is always trained in the actual operation process, so that the network parameters are changed and adapt to the external environment.
The data collected by the water inlet quality monitoring component is input data of the neural network model, and the actual data of the data collected by the water outlet quality monitoring component after passing through the aerator can be used for adjusting network parameters of the neural network model according to the input data and the actual data.
The neural network model in the step S1 comprises an input layer, an implicit layer and an output layer;
the relationship between the input layer and the output layer is:
Wherein Y is the output of the output layer, X k is the kth input quantity of the input layer, K is the quantity of the input quantity, For the actual output corresponding to the kth input, C jk is the radial base center corresponding to the kth input of the jth hidden layer neuron, sigma j is the radial base width of the jth hidden layer neuron, D jk is the weight of the kth input of the jth hidden layer neuron, L is the number of hidden layer neurons, w j is the weight of the jth hidden layer neuron, and N is the number of hidden layer neurons.
The data of the kth input quantity X k of the input layer is derived from the data collected by the water inlet water quality monitoring component, and the actual output corresponding to the kth input quantity is derived from the data collected by the water outlet water quality monitoring component.
The step of obtaining the radial base center comprises the following steps:
a1, calculating the distance between all input quantities to obtain a sample distance set;
a2, selecting a plurality of different sample distances from the sample distance set as initial centers;
a3, calculating the distance from a plurality of input quantities to each initial center;
A4, judging whether the distance is smaller than a distance threshold, if so, adding the input quantity into the corresponding initial center to obtain a plurality of similar sets, otherwise, taking the distance as a new initial center, and jumping to the step A3 until all the input quantity is distributed to the similar sets;
a5, obtaining a radial base center according to all input quantities in the similar set.
In this embodiment, the types of input include reaction water temperature, sludge concentration, inflow water flow, pH of the regulating tank, COD value, NH3-N value, ORP value and TP value.
The calculation formula of the radial base center in the step A5 is as follows:
Wherein, C jk is the radial base center corresponding to the kth input quantity of the neuron of the jth hidden layer in a similar set, P is the quantity of the input quantity in the similar set, and X k is the kth input quantity of the input layer.
The weight updating formula of the jth hidden layer neuron is as follows:
wj i+1＝wj i-Δwj i
Wherein w j i+1 is the weight of the jth hidden layer neuron of the (i+1) th iteration, w j i is the weight of the jth hidden layer neuron of the (i) th iteration, and Δw j i is the weight variation of the jth hidden layer neuron of the (i) th iteration.
The formula of the weight change amount Δw j i is as follows:
Wherein, eta is the moving step length, For the gradient mean value estimator of the i-1 th iteration, θ i-1 is the gradient statistical dispersion estimator of the i-1 th iteration, λ i-1 is the attenuation factor of the i-1 th iteration, λ i-2 is the attenuation factor of the i-2 nd iteration,For the gradient mean value estimator of the i-2 th iteration, θ i-2 is the gradient statistical dispersion estimator of the i-2 th iteration, Y i is the output of the output layer of the i-2 th iteration, and ε is a constant.
In this embodiment, the relation formula of the input layer and the output layer, the process of acquiring the radial base center, the formula of updating the weights of the hidden layer neurons and the formula of the weight variation are applicable to all training processes of the neural network model of the present invention.

Claims (3)

1.一种生化反应的人工神经网络智能曝气装置的控制方法，其特征在于，所述人工神经网络智能曝气装置包括：控制器、曝气机、调节池、SBR生化池、MBR膜分离池、出水池、进水水质监测组件和出水水质监测组件；1. A control method for an artificial neural network intelligent aeration device for biochemical reaction, characterized in that the artificial neural network intelligent aeration device comprises: a controller, an aerator, a regulating tank, an SBR biochemical tank, an MBR membrane separation tank, an outlet tank, an inlet water quality monitoring component and an outlet water quality monitoring component; 所述调节池中设置提升泵，用于将汇入调节池的污水抽入SBR生化池；所述SBR生化池用于对污水进行生化反应，并将进行生化反应后的污水汇入MBR膜分离池；所述MBR膜分离池用于对进行生化反应后的污水进行泥水分离，得到过滤后的水；所述出水池用于盛装过滤后的水；所述进水水质监测组件插入调节池，用于采集进水数据，并发送至控制器；所述出水水质监测组件插入SBR生化池，用于采集曝气过程的水质数据，并发送至控制器；所述控制器用于根据进水数据和水质数据，对曝气机的曝气量进行控制；所述曝气机用于对SBR生化池输入氧气；A lifting pump is provided in the regulating tank, which is used to pump the sewage introduced into the regulating tank into the SBR biochemical tank; the SBR biochemical tank is used to carry out biochemical reaction on the sewage, and introduce the sewage after the biochemical reaction into the MBR membrane separation tank; the MBR membrane separation tank is used to separate mud and water from the sewage after the biochemical reaction to obtain filtered water; the outlet tank is used to hold the filtered water; the inlet water quality monitoring component is inserted into the regulating tank, which is used to collect inlet water data and send it to the controller; the outlet water quality monitoring component is inserted into the SBR biochemical tank, which is used to collect water quality data of the aeration process and send it to the controller; the controller is used to control the aeration amount of the aerator according to the inlet water data and water quality data; the aerator is used to input oxygen into the SBR biochemical tank; 所述进水水质监测组件包括：流量计、COD检测仪、TP检测仪、TN检测仪、DO检测仪、温度检测仪和pH检测仪；The inlet water quality monitoring components include: a flow meter, a COD detector, a TP detector, a TN detector, a DO detector, a temperature detector and a pH detector; 所述出水水质监测组件包括：COD检测仪、TP检测仪、TN检测仪、DO检测仪、污泥浓度检测仪、pH检测仪和ORP检测仪；The effluent water quality monitoring components include: COD detector, TP detector, TN detector, DO detector, sludge concentration detector, pH detector and ORP detector; 所述控制方法包括以下步骤：The control method comprises the following steps: S1、根据进水水质监测组件和出水水质监测组件采集的数据，对神经网络模型进行训练，得到初步训练的神经网络模型；S1. Training the neural network model according to the data collected by the inlet water quality monitoring component and the outlet water quality monitoring component to obtain a preliminarily trained neural network model; 所述神经网络模型包括：输入层、隐含层和输出层；输入层与输出层的关系为：The neural network model includes: an input layer, a hidden layer and an output layer; the relationship between the input layer and the output layer is: 其中，为输出层的输出，为输入层的第个输入量，为输入量的数量，为为第个输入量对应的实际输出，为第个隐藏层神经元第个输入量对应的径向基中心，为第个隐藏层神经元的径向基宽度；为第个隐藏层神经元第个输入量的权重，为隐藏层神经元的数量，为第个隐藏层神经元的权重，为隐藏层神经元的数量；in, is the output of the output layer, The input layer Input quantity, is the number of input quantities, For the The actual output corresponding to the input quantity is For the Hidden layer neurons The radial basis center corresponding to the input quantity is For the The radial basis width of the hidden layer neurons; For the Hidden layer neurons The weight of the input, is the number of neurons in the hidden layer, For the The weights of the neurons in the hidden layer, is the number of neurons in the hidden layer; 所述第个隐藏层神经元的权重更新公式为：The said The weight update formula of the hidden layer neurons is: 其中，为第次迭代的第个隐藏层神经元的权重，为第次迭代的第个隐藏层神经元的权重，为第次迭代的第个隐藏层神经元的权重变化量；in, For the The iteration The weights of the neurons in the hidden layer, For the The iteration The weights of the neurons in the hidden layer, For the The iteration The weight change of the neurons in the hidden layer; 所述权重变化量的公式为：The weight change The formula is: 其中，为移动步长，为第次迭代的梯度均值估计量，为第次迭代的梯度统计离散度估计量，为第次迭代的衰减因子，为第次迭代的衰减因子，为第次迭代的梯度均值估计量，为第次迭代的梯度统计离散度估计量，为第次迭代的输出层的输出，为常数；in, is the moving step length, For the The gradient mean estimator for the iterations, For the The gradient statistical dispersion estimator for the iteration, For the The decay factor of the iteration, For the The decay factor of the iteration, For the The gradient mean estimator for the iterations, For the The gradient statistical dispersion estimator for the iteration, For the The output of the output layer of the iteration, is a constant; S2、将初步训练的神经网络模型部署在控制器内；S2, deploying the initially trained neural network model in the controller; S3、实时采集进水水质监测组件和出水水质监测组件的数据，并输入控制器内，调整初步训练的神经网络模型的网络参数；S3, collecting data from the inlet water quality monitoring component and the outlet water quality monitoring component in real time, and inputting the data into the controller to adjust the network parameters of the initially trained neural network model; S4、根据调整后的神经网络模型，计算得到曝气机的曝气量。S4. According to the adjusted neural network model, the aeration volume of the aerator is calculated. 2.根据权利要求1所述的生化反应的人工神经网络智能曝气装置的控制方法，其特征在于，获取所述径向基中心包括以下步骤：2. The control method of the artificial neural network intelligent aeration device for biochemical reaction according to claim 1 is characterized in that obtaining the radial basis center comprises the following steps: A1、计算所有输入量之间的距离，得到样本距离集合；A1. Calculate the distances between all input quantities to obtain a sample distance set; A2、从样本距离集合选取多个不同的样本距离作为初始中心；A2. Select multiple different sample distances from the sample distance set as the initial center; A3、计算多个输入量到每个初始中心的距离；A3. Calculate the distances from multiple input quantities to each initial center; A4、判断是否存在距离小于距离阈值，若是，则将输入量加入对应的初始中心，得到多个相似集合，若否，则将该距离作为新的初始中心，并跳转至步骤A3，直到所有输入量均分配到相似集合；A4. Determine whether there is a distance less than the distance threshold. If so, add the input amount to the corresponding initial center to obtain multiple similarity sets. If not, use the distance as the new initial center and jump to step A3 until all input amounts are assigned to similarity sets. A5、根据相似集合中所有输入量，得到径向基中心。A5. Obtain the radial basis center based on all input quantities in the similarity set. 3.根据权利要求2所述的生化反应的人工神经网络智能曝气装置的控制方法，其特征在于，所述步骤A5中径向基中心的计算公式为：3. The control method of the artificial neural network intelligent aeration device for biochemical reaction according to claim 2, characterized in that the calculation formula of the radial basis center in step A5 is: 其中，为一个相似集合中第个隐藏层神经元第个输入量对应的径向基中心，为相似集合中输入量的数量，为输入层的第个输入量。in, For a similar set Hidden layer neurons The radial basis center corresponding to the input quantity is is the number of input quantities in the similarity set, The input layer An input quantity.
CN202211245104.XA 2022-07-26 2022-10-12 Artificial neural network intelligent aeration device for biochemical reaction and control method thereof Active CN115557600B (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN2022108873299 2022-07-26
CN202210887329 2022-07-26

Publications (2)

Publication Number Publication Date
CN115557600A CN115557600A (en) 2023-01-03
CN115557600B true CN115557600B (en) 2024-12-17

Family

ID=84745656

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211245104.XA Active CN115557600B (en) 2022-07-26 2022-10-12 Artificial neural network intelligent aeration device for biochemical reaction and control method thereof

Country Status (1)

Country Link
CN (1) CN115557600B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116863465B (en) * 2023-09-01 2023-12-12 四川省每文环保科技有限公司 Sewage intelligent operation monitoring system
CN117808216B (en) * 2024-03-01 2024-05-07 四川省铁路建设有限公司 Energy saving and emission reduction effect evaluation method for sewage treatment

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103064290A (en) * 2013-01-01 2013-04-24 北京工业大学 Dissolved oxygen model prediction control method based on self-organization radial basis function neural network
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
CN111242380A (en) * 2020-01-17 2020-06-05 中国水利水电科学研究院 A prediction method of lake (library) eutrophication based on artificial intelligence algorithm

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105036334B (en) * 2015-07-27 2017-02-22 北京工业大学 Device and method for treating urban sewage through repeated-water-inlet SBR by fully utilizing carbon source in raw water
CN106295800B (en) * 2016-07-28 2019-03-05 北京工业大学 A kind of water outlet total nitrogen TN intelligent detecting method based on recurrence Self organizing RBF Neural Network

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103064290A (en) * 2013-01-01 2013-04-24 北京工业大学 Dissolved oxygen model prediction control method based on self-organization radial basis function neural network
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
CN111242380A (en) * 2020-01-17 2020-06-05 中国水利水电科学研究院 A prediction method of lake (library) eutrophication based on artificial intelligence algorithm

Also Published As

Publication number Publication date
CN115557600A (en) 2023-01-03

Similar Documents

Publication Publication Date Title
AU2021101438A4 (en) Adaptive control method and system for aeration process
CN115557600B (en) Artificial neural network intelligent aeration device for biochemical reaction and control method thereof
JP5143003B2 (en) Denitrification process and denitrification device
CN108549234A (en) A kind of multiobjective optimization control method based on dynamic variate
CN113104961A (en) Real-time aeration accurate control method based on activated sludge treatment sewage process
CN114671523B (en) Sewage treatment energy-saving method based on predictive control
CN115356930B (en) A multi-objective optimization control system and method in sewage treatment process
CN108569756A (en) A kind of Intellectualized sewage water treatment process control new method（EBIS）
CN113189881A (en) Multi-objective optimization control method and system for sewage treatment
KR20220024245A (en) Integrated control system for sewage treatment plant
CN103792844B (en) A kind of sewage treatment control method based on orderly cluster
CN115981153B (en) Deep learning-based A 2 O process intermittent low-carbon aeration method and control system
CN111484124A (en) Intelligent control and biochemical process intensive method and system for sewage treatment
Baeza et al. In-line fast OUR (oxygen uptake rate) measurements for monitoring and control of WWTP
JP3487092B2 (en) Method of controlling biological water treatment equipment
CN118619445B (en) Prediction method for aeration quantity required for maintaining stable dissolved oxygen of activated sludge system
CN112924646B (en) A BOD Soft Sensing Method Based on Adaptive Pruning Feedforward Small World Neural Network
CN114879496A (en) Data-driven prediction control method for random sampling model in municipal sewage treatment process
CN118838168A (en) Sewage treatment aeration control method and system based on artificial intelligence and mechanism model
Kapumbe et al. Modeling and simulation of membrane bioreactor model based on ASM3 for domestic wastewater treatment.
CN113003692A (en) Case reasoning-based dosing control method for denitrification process of municipal sewage treatment
CN116484584B (en) Intelligent control method of two-stage sewage treatment system
CN113979541A (en) A2Intelligent control method for O biological pond process
Fotso Development of a Dynamic Simulation Model for Equalization Tanks
CN117819702B (en) Module combined type nutrient supply control method in 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
GR01 Patent grant
GR01 Patent grant