CN113033917A - Sewage treatment plant prediction planning operation management method based on peripheral data - Google Patents
Sewage treatment plant prediction planning operation management method based on peripheral data Download PDFInfo
- Publication number
- CN113033917A CN113033917A CN202110420432.8A CN202110420432A CN113033917A CN 113033917 A CN113033917 A CN 113033917A CN 202110420432 A CN202110420432 A CN 202110420432A CN 113033917 A CN113033917 A CN 113033917A
- Authority
- CN
- China
- Prior art keywords
- sewage treatment
- data
- operation management
- neural network
- network model
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Abstract
The invention relates to the technical field of sewage treatment, in particular to a method for predicting, planning and operating and managing a sewage treatment plant based on peripheral data, which comprises the following steps: acquiring the predicted inlet water quality and inlet water quantity of a sewage treatment plant and a set operation management scheme; inputting the predicted water quality and water inflow and the operation management scheme into a pre-trained sewage treatment prediction model, and outputting a corresponding sewage treatment prediction result; inputting the prediction result of sewage treatment into a pre-trained optimization model, optimizing an operation management scheme and correspondingly outputting a new operation management scheme; judging whether the sewage treatment prediction result meets the set expected result: and if so, executing operation management based on the current operation management scheme. The prediction planning operation management method for the sewage treatment plant can achieve standard discharge of effluent water quality and reduce sewage treatment loss, thereby taking both the sewage treatment effect and the energy consumption management effect of the sewage treatment plant into consideration.
Description
Technical Field
The invention relates to the technical field of sewage treatment, in particular to a method for predicting, planning and operating and managing a sewage treatment plant based on peripheral data.
Background
With the rapid development of economy, the urban sewage production capacity is a determining factor for planning the layout of a sewage system, the construction of a matched pipe network and a sewage interception system, the scale of an urban sewage treatment plant and a sewage treatment process. In the design process of the sewage treatment plant, the design water quality and the water inflow often determine the scale of the urban sewage treatment plant, the selection of the process flow, the investment of the project and the operating cost. The actual inlet water quality, the inlet water quantity and the design value of most of the existing urban sewage treatment plants have large difference, and the stable and efficient operation of the urban sewage treatment is seriously influenced.
Therefore, the quality and the inflow of the inlet water of the sewage treatment plant need to be predicted, and a basis is provided for the operation and decision of the sewage treatment plant. For example, chinese patent publication No. CN106200381A discloses a method for controlling the operation of a water plant in stages according to the amount of treated water, which comprises: collecting real-time water inflow data of a sewage treatment plant, calculating the current water inflow chemical oxygen demand, and storing the collected real-time water inflow data, the collected water inflow chemical oxygen demand data and corresponding time points into a database; establishing a data curve for the acquired data by taking the real-time inflow water flow and the inflow water chemical oxygen demand data as vertical coordinates and the time point corresponding to the real-time inflow water flow data as horizontal coordinates, and smoothing and denoising the data curve; establishing a data prediction model for the data subjected to smoothing and denoising by adopting a neural network technology; predicting the data at the selected moment to obtain a predicted value; and controlling the operation of the sewage treatment plant according to the obtained predicted value.
The method for controlling the operation of the water plant in stages in the prior scheme is also a prediction planning operation management method for the sewage treatment plant, and the operation of the sewage treatment plant is controlled by predicting the inflow water quality and the inflow of the sewage treatment plant, so that the aim of ensuring the effluent quality discharge to reach the standard, namely ensuring the sewage treatment effect is fulfilled. However, in practice, before sewage treatment in a sewage treatment plant, a set of operation management scheme needs to be set, and the purpose is to ensure the sewage treatment effect. However, the applicant finds that if the set operation management scheme only aims at ensuring the sewage treatment effect, the problems of excessive chemical agents, excessive aeration and the like easily occur during operation management, and further, a great deal of energy, manpower and material consumption are easily wasted, so that the energy consumption management effect of the sewage treatment plant is poor. Therefore, how to provide a prediction planning operation management method for a sewage treatment plant, which can realize that the effluent quality discharge reaches the standard and can reduce the sewage treatment loss, is a technical problem which needs to be solved urgently.
Disclosure of Invention
Aiming at the defects of the prior art, the technical problems to be solved by the invention are as follows: how to provide a prediction planning operation management method for a sewage treatment plant, which can realize that the effluent quality discharge reaches the standard and can reduce the sewage treatment loss, thereby taking the sewage treatment effect and the energy consumption management effect of the sewage treatment plant into consideration.
In order to solve the technical problems, the invention adopts the following technical scheme:
a sewage treatment plant prediction planning operation management method based on peripheral data comprises the following steps:
s01: acquiring the predicted inlet water quality and inlet water quantity of a sewage treatment plant and a set operation management scheme;
s02: inputting the predicted water quality and water inflow and the operation management scheme into a pre-trained sewage treatment prediction model, and outputting a corresponding sewage treatment prediction result;
s03: inputting the prediction result of sewage treatment into a pre-trained optimization model, optimizing an operation management scheme and correspondingly outputting a new operation management scheme;
s04: judging whether the sewage treatment prediction result meets the set expected result: if yes, executing operation management based on the current operation management scheme; otherwise, return to step S02.
Preferably, in step S01, the inflow water quality and inflow water quantity of the sewage treatment plant are predicted based on the peripheral data; the peripheral data includes any one or more of ambient weather data, demographic data, enterprise data, and economic data.
Preferably, the environmental meteorological data comprises any one or more of rainfall, temperature and relative humidity within a certain period of time in the future; the population data comprises any one or more of the number of the population in the standing city, the number of the population in the standing town, the number of the population in the standing countryside and the number of the population in the floating population; the enterprise data comprises the number of various enterprises and the corresponding sewage production amount; the economic data comprises any one or more of total urban production value, total import and export value, total social consumer retail value, industrial sales value, total industrial production value, urban resident consumption price index, urban food urban resident consumption price index, non-food urban resident consumption price index, urban consumer consumption price index of consumer product, urban consumer consumption price index of food smoke and wine, total industrial production value above scale, urban consumer consumption price index of education culture entertainment and commodity room sales area.
Preferably, in step S01, the peripheral data is input into a pre-trained gray correlation analysis-gating unit neural network model, and the corresponding prediction results of the influent water quality and the influent water amount of the sewage treatment plant are output.
Preferably, the grey correlation analysis-gating cell neural network model is trained by the following steps:
s11: respectively establishing a grey correlation analysis model and a gate control unit neural network model;
s12: connecting an output of the grey correlation analysis model with an input of a gate control unit neural network model to form a grey correlation analysis-gate control unit neural network model;
s13: and training and optimizing the grey correlation analysis-gate control unit neural network model through the set peripheral data training set to obtain the trained grey correlation analysis-gate control unit neural network model.
Preferably, in step S02, the sewage treatment prediction model includes a principal component analysis model, a convolutional neural network model and a long-short term memory neural network model; the principal component analysis model is used for carrying out dimensionality reduction on input data and outputting the data to the convolutional neural network model, the convolutional neural network model is used for constructing a characteristic space of the data and outputting the characteristic space to the long-short term memory neural network model, and the long-short term memory neural network model is used for expressing time sequence characteristics of the data and outputting a corresponding sewage treatment prediction result.
Preferably, the sewage treatment prediction model is trained by the following steps:
s21: respectively establishing a principal component analysis model, a convolutional neural network model and a long-term and short-term memory neural network model;
s22: sequentially connecting the output of the principal component analysis model, the input of the convolutional neural network model, the output of the convolutional neural network model and the input of the long-term and short-term memory neural network model to form a sewage treatment prediction model;
s23: and training and optimizing the sewage treatment prediction model through the set sewage treatment data training set to obtain the trained sewage treatment prediction model.
Preferably, the principal component analysis model is expressed by the following formula:
in the formula: p represents a variable of the factor i after the principal component transformation is considered; x is the number ofi,jA corresponding value representing the ith factor in the j-th year; w is ai,jA corresponding feature vector representing the ith factor in the jth year; 1,2, …, a, j 1,2, …, m;
the convolutional neural network model is represented by the following formula:
relu(x)＝max(0,x)；
pr(t)＝max pooling(pi-1(t))；
in the formula: h isr(t) a feature vector of the r-th layer convolution kernel at the t-th moment; relu (·) denotes a Relu activation function;
a convolution operation representing a convolution kernel; omegar(t) a weight vector representing the r-th layer convolution kernel; p is a radical ofr(t) represents a feature vector of the r-th pool layer at the t-th time instant; maxporoling (·) denotes the pool rules;
the long-short term memory neural network model is represented by the following formula:
ft＝σ[Wf(ht-1,xt)+bf]；
lt＝σ[Wl(ht-1,xt)+bl]；
c′t＝tanh[Wc(ht-1,xt)+bc]；
ct＝ftct-1+ltc′t；
ot＝σ[Wo(ht-1,xt)+bo]；
in the formula: f. oftRepresents the forgetting gate coefficient at time t; ltRepresenting the input gate coefficient at time t; c'tRepresents input data obtained by a tanh function; c. CtRepresents the state of the update unit at time t; otRepresenting the output gate coefficient; h istRepresenting the output data at time t; h ist-1Represents the output data at time t-1; x is the number oftRepresenting input data at time t; c. Ct-1Represents the state of the cells at time t-1; wf(. and b)fA weight function and a deviation respectively representing forgetting gates corresponding to neurons from time t-1 to time t; wl(. and b)lInput gates corresponding to neurons from time t-1 to time t, respectively; wc(. and b)cA weight function and a deviation respectively representing input data corresponding to neurons from time t-1 to time t; wo(. and b)oRepresenting the weight function and the bias, respectively, with the output gates of the neurons from time t-1 to time t.
Preferably, in step S03, the optimization model optimizes the operation management scheme by using any one or more of a genetic algorithm, a particle swarm algorithm, and a fuzzy inference algorithm.
Preferably, the operation management scheme includes any one or more of electric energy consumption, material consumption, equipment operation and personnel allocation.
Compared with the prior art, the prediction planning operation management method for the sewage treatment plant has the following beneficial effects:
according to the invention, a sewage treatment prediction result is generated based on the predicted inlet water quality and inlet water quantity and a set operation management scheme, whether the discharge of the outlet water quality reaches the standard can be judged according to the sewage treatment prediction result, and operation management is executed when the discharge of the outlet water quality reaches the standard, so that the discharge of the outlet water quality reaches the standard, and the sewage treatment effect of a sewage treatment plant can be improved. Meanwhile, the operation management scheme is adjusted and optimized according to the sewage treatment prediction result, the optimal operation management scheme can be obtained in the process of continuously adjusting and optimizing the operation management scheme, and then the operation management is executed according to the optimal operation management scheme, so that the sewage treatment loss can be reduced, and the energy consumption management effect of the sewage treatment plant can be improved. Therefore, the invention can give consideration to both the sewage treatment effect and the energy consumption management effect of the sewage treatment plant.
Drawings
For purposes of promoting a better understanding of the objects, aspects and advantages of the invention, reference will now be made in detail to the present invention as illustrated in the accompanying drawings, in which:
FIG. 1 is a logic diagram of a predictive planning operation management method in an embodiment;
FIG. 2 is a logic block diagram of a gray correlation analysis-gating cell neural network model in an embodiment;
FIG. 3 is a logic block diagram of a prediction model for sewage treatment in an embodiment;
FIG. 4 is a schematic diagram of an interface for predicting traffic in an embodiment;
FIG. 5 is a schematic view of an interface for predicting the quality and quantity of inlet water in the example;
FIGS. 6 and 7 are schematic diagrams of the operation of the optimization model in the embodiment;
FIG. 8 is an interface diagram of the operation management result in the embodiment.
Detailed Description
The following is further detailed by the specific embodiments:
example (b):
the embodiment discloses a method for predicting, planning and operating a sewage treatment plant based on peripheral data.
As shown in fig. 1, a method for predicting, planning and operating a sewage treatment plant based on peripheral data includes the following steps:
s01: and obtaining the predicted inlet water quality and inlet water quantity of the sewage treatment plant and a set operation management scheme. Specifically, the operation management scheme includes any one or more of electric energy consumption, material consumption, equipment operation, and personnel allocation.
S02: inputting the predicted water quality and water inflow and the operation management scheme into a pre-trained sewage treatment prediction model, and outputting a corresponding sewage treatment prediction result.
S03: and inputting the sewage treatment prediction result into a pre-trained optimization model, optimizing the operation management scheme and correspondingly outputting a new operation management scheme. Specifically, the optimization model adopts any one or more algorithms of a genetic algorithm, a particle swarm algorithm and a fuzzy inference algorithm to optimize the operation management scheme.
S04: judging whether the sewage treatment prediction result meets the set expected result: if yes, executing operation management based on the current operation management scheme; otherwise, return to step S02.
According to the invention, a sewage treatment prediction result is generated based on the predicted inlet water quality and inlet water quantity and a set operation management scheme, whether the discharge of the outlet water quality reaches the standard can be judged according to the sewage treatment prediction result, and operation management is executed when the discharge of the outlet water quality reaches the standard, so that the discharge of the outlet water quality reaches the standard, and the sewage treatment effect of a sewage treatment plant can be improved. Meanwhile, the operation management scheme is adjusted and optimized according to the sewage treatment prediction result, the optimal operation management scheme can be obtained in the process of continuously adjusting and optimizing the operation management scheme, and then the operation management is executed according to the optimal operation management scheme, so that the sewage treatment loss can be reduced, and the energy consumption management effect of the sewage treatment plant can be improved. Therefore, the invention can give consideration to both the sewage treatment effect and the energy consumption management effect of the sewage treatment plant.
In the specific implementation process, the inflow water quality and inflow of the sewage treatment plant are predicted based on peripheral data; the peripheral data includes any one or more of ambient weather data, demographic data, business data, and economic data.
Specifically, the environmental meteorological data includes any one or more of rainfall, temperature and relative humidity within a certain period of time in the future; the population data comprises any one or more of the number of the population in the standing city, the number of the population in the standing town, the number of the population in the standing countryside and the number of the population in the floating population; the enterprise data comprises the number of various enterprises and the corresponding sewage production amount; the economic data comprises any one or more of total urban production value, total import and export value, total social consumer retail value, industrial sales value, total industrial value, urban resident consumption price index, urban food resident consumption price index, non-food urban resident consumption price index, urban consumer price index of consumer product, urban consumer price index of food smoke and wine, total industrial value above scale, urban resident consumption price index of education culture entertainment and commodity room sales area. The applicant has also made the following studies in designing the technical solution of the present invention:
rainfall has direct influence to sewage treatment plant's inflow, and when the rainfall increased, the total displacement in city increased, because reasons such as the reposition of redundant personnel of rain and sewage is not thorough, sewer line leaks, the sewage line can be sneaked into to the rainwater, leads to sewage treatment plant's inflow to increase. The influence of temperature on water inflow is reflected in the influence on the activity of microorganisms in the activated sludge, most of the microorganisms in the sewage treatment suitably grow at 15-35 ℃, and in the suitable temperature range, the higher the temperature is, the stronger the activity of the microorganisms is, the better the treatment effect is, otherwise, the lower the temperature is, the poorer the biological activity is; the exceeding range inhibits the growth of microorganisms. Relative humidity (climate characteristics) also has an important influence on water inflow, and the relative humidity directly determines the rainfall condition in a certain season or time period, thereby influencing the water inflow. In the embodiment, rainfall, temperature and relative humidity of the position where the sewage treatment plant is located in real time and in the future 40 days are obtained through a meteorological office website or a national weather network in a certain region.
The population quantity can influence the inflow of sewage treatment plant because population quantity has decided domestic sewage production volume, and then has influenced the inflow. According to the 'Chinese water resource bulletin' of 2019 years, the comprehensive water consumption of China is 431m3, the domestic water consumption (including public water) of urban people is 225L/d, and the domestic water consumption of rural residents is 89L/d; the total domestic sewage production amount is about 80% of water consumption, so that the water inflow amount can be predicted through the population number. The embodiment can consult the number of the population of the living city, the number of the population of the living town and the number of the population of the living countryside in the area through a certain area statistical information network, and then count the number of the visitors who receive the tourist on the holiday of the major festival every year as the number of the floating population through a certain area government official network.
The quantity of enterprises can influence the water inflow of the sewage treatment plant, because the quantity of enterprises directly influences the industrial water consumption, and then influences the water inflow of the sewage treatment plant, and the corresponding water inflow can be predicted by the quantity of various enterprises. In the embodiment, the number of different types of enterprises and corresponding water consumption above the scale are consulted through a regional statistical information network and a water conservancy bureau; then, according to a manual for producing and discharging coefficients, the sewage discharging coefficient (the ratio of the sewage discharging amount to the water consumption) of relevant enterprises is consulted, and the sewage production amount corresponding to various enterprises is determined by a linear analysis method.
According to the method, the inlet water quality and the inlet water quantity of the sewage treatment plant are predicted based on the peripheral data, namely, the peripheral data such as environmental meteorological data, population data, enterprise data, economic data and the like of the position of the sewage treatment plant are fully considered, so that the inlet water quality and the inlet water quantity of the sewage treatment plant can be accurately and effectively predicted, and the sewage management effect of the sewage treatment plant can be assisted to be improved. Meanwhile, the peripheral data of the invention comprise environmental meteorological data, population data, enterprise data and economic data, and the data are the peripheral data most relevant to the inflow water quality and inflow water quantity of the sewage treatment plant, so the prediction accuracy of the inflow water quality and inflow water quantity of the sewage treatment plant can be further improved based on the peripheral data.
In the specific implementation process, peripheral data are input into a pre-trained grey correlation analysis-gating unit neural network model, and corresponding prediction results of the inflow water quality and inflow water quantity of the sewage treatment plant are output. Specifically, with reference to fig. 2, a gray correlation analysis-gating unit neural network model is trained by the following steps:
s11: respectively establishing a grey correlation analysis model and a gate control unit neural network model;
s12: connecting an output of the grey correlation analysis model with an input of a gate control unit neural network model to form a grey correlation analysis-gate control unit neural network model;
s13: and training and optimizing the grey correlation analysis-gate control unit neural network model through the set peripheral data training set to obtain the trained grey correlation analysis-gate control unit neural network model.
The method for establishing the gray correlation analysis model comprises the following steps:
generating a data matrix by the following formula and using the peripheral data training set:
in the formula:
the data processing apparatus is characterized by comprising a data processing unit, a data processing unit and a data processing unit, wherein the data processing unit is used for representing ith peripheral data, and i is 1,2, …;
wherein the content of the first and second substances,
in the formula:
representing the kth peripheral data in the ith peripheral data; γ represents the number of data in each type of peripheral data;
generating a data matrix by the following formula and using the peripheral data training set:
in the formula:
the data processing apparatus is characterized by comprising a data processing unit, a data processing unit and a data processing unit, wherein the data processing unit is used for representing ith peripheral data, and i is 1,2, …;
wherein the content of the first and second substances,
in the formula:
to representThe kth peripheral data in the ith peripheral data; γ represents the number of data in each type of peripheral data;
determining a reference data sequence by the following formula and using a peripheral data training set:
converting the data matrix by the following formula, and constructing a dimensionless data matrix:
s24: the correlation coefficient is calculated by the following formula:
in the formula: deltaα(k) A correlation coefficient representing peripheral data and corresponding reference data; epsilon is a discrimination coefficient, epsilon belongs to (0,1), and data with a correlation coefficient smaller than 0.7 is filtered out.
The built gate control unit neural network model is represented by the following formula:
zt＝σ(Wz·[Xt,ht-1])；
rt＝σ(Wr·[Xt,ht-1])；
in the formula: z is a radical oftRepresents an update gate; r istRepresents a reset gate; xtRepresenting a current input; h ist-1Representing the hidden layer output at time t-1;
a summary representing the input and past hidden states; h istHidden layer output representing time t; wz、Wr、WhEach represents a trainable parameter matrix; []Representing that the two vectors are connected; denotes the matrix product.
According to the invention, the inflow water quality and inflow of the sewage treatment plant can be accurately and effectively predicted based on the gray correlation analysis-gate control unit neural network model (GRA-GRU model), and the sewage management effect of the sewage treatment plant can be improved in an auxiliary manner. Meanwhile, the model is established and trained in the above way, the grey correlation analysis-gate control unit neural network model with extremely high accuracy can be obtained, and the prediction accuracy of the inlet water quality and the inlet water quantity of the sewage treatment plant can also be improved.
In a specific implementation process, as shown in fig. 3, the sewage treatment prediction model (PCA-CNN-LSTM model) includes a principal component analysis model, a convolutional neural network model, and a long-short term memory neural network model; the principal component analysis model is used for carrying out dimensionality reduction on input data and outputting the data to the convolutional neural network model, the convolutional neural network model is used for constructing a characteristic space of the data and outputting the characteristic space to the long-short term memory neural network model, and the long-short term memory neural network model is used for expressing time sequence characteristics of the data and outputting a corresponding sewage treatment prediction result.
In the specific implementation process, the sewage treatment prediction model is trained through the following steps:
s21: respectively establishing a principal component analysis model, a convolutional neural network model and a long-term and short-term memory neural network model;
s22: sequentially connecting the output of the principal component analysis model, the input of the convolutional neural network model, the output of the convolutional neural network model and the input of the long-term and short-term memory neural network model to form a sewage treatment prediction model;
s23: and training and optimizing the sewage treatment prediction model through the set sewage treatment data training set to obtain the trained sewage treatment prediction model.
Specifically, the principal component analysis model is expressed by the following formula:
in the formula: p represents a variable of the factor i after the principal component transformation is considered; x is the number ofi,jA corresponding value representing the ith factor in the j-th year; w is ai,jA corresponding feature vector representing the ith factor in the jth year; 1,2, …, a, j 1,2, …, m;
the convolutional neural network model is represented by the following formula:
relu(x)＝max(0,x)；
pr(t)＝max pooling(pi-1(t))；
in the formula: h isr(t) a feature vector of the r-th layer convolution kernel at the t-th moment; relu (·) denotes a Relu activation function;
a convolution operation representing a convolution kernel; omegar(t) a weight vector representing the r-th layer convolution kernel; p is a radical ofr(t) represents a feature vector of the r-th pool layer at the t-th time instant; maxporoling (·) denotes the pool rules;
the long-short term memory neural network model is represented by the following formula:
ft＝σ[Wf(ht-1,xt)+bf]；
lt＝σ[Wl(ht-1,xt)+bl]；
c′t＝tanh[Wc(ht-1,xt)+bc]；
ct＝ftct-1+ltc′t；
ot＝σ[Wo(ht-1,xt)+bo]；
in the formula: f. oftRepresents the forgetting gate coefficient at time t; ltRepresenting the input gate coefficient at time t; c'tRepresents input data obtained by a tanh function; c. CtRepresents the state of the update unit at time t; otRepresenting the output gate coefficient; h istRepresenting the output data at time t; h ist-1Represents the output data at time t-1; x is the number oftRepresenting input data at time t; c. Ct-1Represents the state of the cells at time t-1; wf(. and b)fA weight function and a deviation respectively representing forgetting gates corresponding to neurons from time t-1 to time t; wl(. and b)lInput gates corresponding to neurons from time t-1 to time t, respectively; wc(. and b)cA weight function and a deviation respectively representing input data corresponding to neurons from time t-1 to time t; wo(. and b)oRepresenting the weight function and the bias, respectively, with the output gates of the neurons from time t-1 to time t.
According to the invention, the sewage treatment prediction result can be accurately and effectively obtained based on the sewage treatment prediction model (PCA-CNN-LSTM model), the sewage management effect of a sewage treatment plant can be helped to be improved, and the operation management scheme can be better optimized. Meanwhile, the model is established and trained in the above way, a sewage treatment prediction model (PCA-CNN-LSTM model) with extremely high accuracy can be obtained, and the prediction accuracy of the water inflow of the sewage treatment plant can be improved.
In order to verify the feasibility of the prediction planning operation management method for the sewage treatment plant, the following tests are performed in this embodiment by taking a certain sewage treatment plant in a certain market as an example:
environmental meteorological data, population data, enterprise data and economic data of the coverage area of the sewage treatment plant in the city are collected, the data are input into a grey correlation analysis-gate control unit neural network model to predict the service volume, the inflow water quality and the inflow, the prediction interface of the service volume is shown in figure 4, and the prediction interface of the inflow water quality and the inflow is shown in figure 5.
And (3) constructing a mapping relation from data to results by using a sewage treatment prediction model (PCA-CNN-LSTM model), inputting the predicted water quality and water inflow and a set operation management scheme (internal daily data) into the sewage treatment prediction model, and outputting a corresponding sewage treatment prediction result.
And inputting the sewage treatment prediction result into a pre-trained optimization model, optimizing the operation management scheme and correspondingly outputting a new operation management scheme. The COD value of the experiment is taken as an example, and the optimization process is shown in figures 6 and 7.
And judging whether the sewage treatment prediction result meets the set expected result (the expected result is the first-class A standard of pollutant discharge standard of the urban sewage treatment plant), and executing operation management based on the current operation management scheme, wherein the result of the operation management is shown in figure 8.
The comparison of the results of the operation management and the actual results is as follows:
1) actual results for a month: the total electricity consumption is: 539250 kW.h, the daily average power consumption is: 17395 kW.h.
Results of the operation management: the daily power consumption is 15520 kW.h, and the daily energy consumption is saved by 10.78%.
2) Actual results for a month: the actual total amount of liquid chlorine is as follows: 10319kg, daily average dosage: 332.87 kg.
Results of the operation management: the daily average dosage of the liquid chlorine is 300kg, and the daily energy consumption is saved by 9.87%.
3) Actual results in a month: the actual total amount of aluminum salt is: 29330kg, the daily average dosage is: 946.13 kg.
The result of the operation management after optimization is as follows: the daily average dosage of the aluminum salt is 930kg, and the daily energy consumption is saved by 1.70 percent.
Therefore, the loss can be reduced extremely well by adopting the prediction planning operation management method for the sewage treatment plant, so that the prediction planning operation management method for the sewage treatment plant is feasible.
The foregoing is merely an example of the present invention, and common general knowledge in the field of known specific structures and characteristics is not described herein in any greater extent than that known in the art at the filing date or prior to the priority date of the application, so that those skilled in the art can now appreciate that all of the above-described techniques in this field and have the ability to apply routine experimentation before this date can be combined with one or more of the present teachings to complete and implement the present invention, and that certain typical known structures or known methods do not pose any impediments to the implementation of the present invention by those skilled in the art. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.
Claims (10)
1. A sewage treatment plant prediction planning operation management method based on peripheral data is characterized by comprising the following steps:
s01: acquiring the predicted inlet water quality and inlet water quantity of a sewage treatment plant and a set operation management scheme;
s02: inputting the predicted water quality and water inflow and the operation management scheme into a pre-trained sewage treatment prediction model, and outputting a corresponding sewage treatment prediction result;
s03: inputting the prediction result of sewage treatment into a pre-trained optimization model, optimizing an operation management scheme and correspondingly outputting a new operation management scheme;
s04: judging whether the sewage treatment prediction result meets the set expected result: if yes, executing operation management based on the current operation management scheme; otherwise, return to step S02.
2. The method for forecasting planned operation and management of a sewage treatment plant based on peripheral data as claimed in claim 1, wherein in step S01, the quality and quantity of inlet water of the sewage treatment plant are forecasted based on the peripheral data; the peripheral data includes any one or more of ambient weather data, demographic data, enterprise data, and economic data.
3. The peripheral data-based plant predictive planning operation management method of sewage treatment plants according to claim 2, characterized in that: the environmental meteorological data comprises any one or more of rainfall, temperature and relative humidity within a certain period of time in the future; the population data comprises any one or more of the number of the population in the standing city, the number of the population in the standing town, the number of the population in the standing countryside and the number of the population in the floating population; the enterprise data comprises the number of various enterprises and the corresponding sewage production amount; the economic data comprises any one or more of total urban production value, total import and export value, total social consumer retail value, industrial sales value, total industrial production value, urban resident consumption price index, urban food urban resident consumption price index, non-food urban resident consumption price index, urban consumer consumption price index of consumer product, urban consumer consumption price index of food smoke and wine, total industrial production value above scale, urban consumer consumption price index of education culture entertainment and commodity room sales area.
4. The method as claimed in claim 2, wherein the peripheral data are inputted into a pre-trained grey correlation analysis-gating unit neural network model in step S01, and the corresponding prediction results of the quality and quantity of inlet water of the sewage treatment plant are outputted.
5. The peripheral data based prediction planning operation management method for a sewage treatment plant according to claim 4, characterized in that the grey correlation analysis-gating unit neural network model is trained by the following steps:
s11: respectively establishing a grey correlation analysis model and a gate control unit neural network model;
s12: connecting an output of the grey correlation analysis model with an input of a gate control unit neural network model to form a grey correlation analysis-gate control unit neural network model;
s13: and training and optimizing the grey correlation analysis-gate control unit neural network model through the set peripheral data training set to obtain the trained grey correlation analysis-gate control unit neural network model.
6. The peripheral data-based prediction planning operation management method for sewage treatment plants according to claim 1, wherein in step S02, the sewage treatment prediction model comprises a principal component analysis model, a convolutional neural network model and a long-short term memory neural network model; the principal component analysis model is used for carrying out dimensionality reduction on input data and outputting the data to the convolutional neural network model, the convolutional neural network model is used for constructing a characteristic space of the data and outputting the characteristic space to the long-short term memory neural network model, and the long-short term memory neural network model is used for expressing time sequence characteristics of the data and outputting a corresponding sewage treatment prediction result.
7. The peripheral data based plant predictive planning operation management method of claim 6, wherein the plant predictive model is trained by:
s21: respectively establishing a principal component analysis model, a convolutional neural network model and a long-term and short-term memory neural network model;
s22: sequentially connecting the output of the principal component analysis model, the input of the convolutional neural network model, the output of the convolutional neural network model and the input of the long-term and short-term memory neural network model to form a sewage treatment prediction model;
s23: and training and optimizing the sewage treatment prediction model through the set sewage treatment data training set to obtain the trained sewage treatment prediction model.
8. The peripheral data-based plant predictive planning operation management method of sewage treatment plants according to claim 7, characterized in that:
the principal component analysis model is expressed by the following formula:
in the formula: p represents a variable of the factor i after the principal component transformation is considered; x is the number ofi,jA corresponding value representing the ith factor in the j-th year; w is ai,jA corresponding feature vector representing the ith factor in the jth year; 1,2, …, a, j 1,2, …, m;
the convolutional neural network model is represented by the following formula:
relu(x)＝max(0,x)；
pr(t)＝maxpooling(pi-1(t))；
in the formula: h isr(t) a feature vector of the r-th layer convolution kernel at the t-th moment; relu (·) denotes a Relu activation function;
a convolution operation representing a convolution kernel; omegar(t) a weight vector representing the r-th layer convolution kernel; p is a radical ofr(t) represents a feature vector of the r-th pool layer at the t-th time instant; maxporoling (·) denotes the pool rules;
the long-short term memory neural network model is represented by the following formula:
ft＝σ[Wf(ht-1,xt)+bf]；
lt＝σ[Wl(ht-1,xt)+bl]；
c′t＝tanh[Wc(ht-1,xt)+bc]；
ct＝ftct-1+ltc′t；
ot＝σ[Wo(ht-1,xt)+bo]；
in the formula: f. oftRepresents the forgetting gate coefficient at time t; ltRepresenting the input gate coefficient at time t; c'tRepresents input data obtained by a tanh function; c. CtRepresents the state of the update unit at time t; otRepresenting the output gate coefficient; h istRepresenting the output data at time t; h ist-1Represents the output data at time t-1; x is the number oftRepresenting input data at time t; c. Ct-1Represents the state of the cells at time t-1; wf(. and b)fA weight function and a deviation respectively representing forgetting gates corresponding to neurons from time t-1 to time t; wl(. and b)lInput gates corresponding to neurons from time t-1 to time t, respectively; wc(. and b)cA weight function and a deviation respectively representing input data corresponding to neurons from time t-1 to time t; wo(. and b)oRepresenting the weight function and the bias, respectively, with the output gates of the neurons from time t-1 to time t.
9. The peripheral data-based prediction planning operation management method for sewage treatment plants according to claim 1, wherein in step S03, the optimization model optimizes the operation management scheme by using any one or more of genetic algorithm, particle swarm algorithm and fuzzy inference algorithm.
10. The peripheral data-based plant predictive planning operation management method of sewage treatment plants according to claim 1, characterized in that: the operation management scheme includes any one or more of electric energy consumption, material consumption, equipment operation and personnel allocation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110420432.8A CN113033917B (en) | 2021-04-19 | 2021-04-19 | Sewage treatment plant prediction planning operation management method based on peripheral data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110420432.8A CN113033917B (en) | 2021-04-19 | 2021-04-19 | Sewage treatment plant prediction planning operation management method based on peripheral data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113033917A true CN113033917A (en) | 2021-06-25 |
| CN113033917B CN113033917B (en) | 2022-04-12 |
Family
ID=76457918
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110420432.8A Active CN113033917B (en) | 2021-04-19 | 2021-04-19 | Sewage treatment plant prediction planning operation management method based on peripheral data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113033917B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113479999A (en) * | 2021-07-29 | 2021-10-08 | 中建智能技术有限公司 | Sewage data processing method and device and computer equipment |
| CN114149076A (en) * | 2021-12-21 | 2022-03-08 | 浙江沃乐环境科技有限公司 | Intelligent debugging system of anaerobic ammonia oxidation sewage treatment system |
| CN114417622A (en) * | 2022-01-24 | 2022-04-29 | 大唐融合通信股份有限公司 | Sewage treatment method, device, equipment and system |
| CN114626642A (en) * | 2022-05-16 | 2022-06-14 | 武汉华信数据系统有限公司 | Dosing system control method and device, storage medium and electronic equipment |
| CN115981153A (en) * | 2022-12-30 | 2023-04-18 | 浙江问源环保科技股份有限公司 | Deep learning based A 2 O process intermittent low-carbon aeration method and control system |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006095440A (en) * | 2004-09-29 | 2006-04-13 | Toshiba Corp | Operation management system in sewage treatment plant |
| JP2007002474A (en) * | 2005-06-22 | 2007-01-11 | Mitsubishi Electric Corp | Integrated operation management method for sewage treatment plant |
| CN102681498A (en) * | 2011-03-15 | 2012-09-19 | 中国科学院沈阳自动化研究所 | Sewage treatment process optimizing operation method |
| CN103605859A (en) * | 2013-11-28 | 2014-02-26 | 浙江工业大学 | Optimum design method for secondary sedimentation tank of sewage treatment work |
| WO2015147349A1 (en) * | 2014-03-26 | 2015-10-01 | 부산대학교 산학협력단 | Integrated operation management device for plurality of sewage treatment plants sharing same discharge water system and method thereof |
| CN106200381A (en) * | 2016-07-27 | 2016-12-07 | 华电水务工程有限公司 | A kind of according to processing the method that water yield control by stages water factory runs |
| CN108640276A (en) * | 2018-04-17 | 2018-10-12 | 东南大学 | A kind of sewage treatment plant AAO process optimization operation methods based on WEST models |
| CN109508811A (en) * | 2018-09-30 | 2019-03-22 | 中冶华天工程技术有限公司 | Parameter prediction method is discharged based on principal component analysis and the sewage treatment of shot and long term memory network |
| CN109933027A (en) * | 2019-02-28 | 2019-06-25 | 重庆工商大学 | Sewage management platform based on factory's group's monitoring water quality and modelling management |
| CN109976187A (en) * | 2019-02-28 | 2019-07-05 | 重庆工商大学 | The sewage management platform for being optimized based on biochemical wastewater treatment and being finely aerated |
| CN110188946A (en) * | 2019-05-29 | 2019-08-30 | 剑科云智(深圳)科技有限公司 | A kind of prediction technique and sewage forecasting system of wastewater parameters |
| CN110245881A (en) * | 2019-07-16 | 2019-09-17 | 重庆邮电大学 | A kind of water quality prediction method and system of the sewage treatment based on machine learning |
| 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 |
| CN111027776A (en) * | 2019-12-13 | 2020-04-17 | 北京华展汇元信息技术有限公司 | Sewage treatment water quality prediction method based on improved long-short term memory LSTM neural network |
| CN111221306A (en) * | 2020-01-17 | 2020-06-02 | 石化盈科信息技术有限责任公司 | Method for predicting key indexes of sewage system |
| CN111291937A (en) * | 2020-02-25 | 2020-06-16 | 合肥学院 | Method for predicting quality of treated sewage based on combination of support vector classification and GRU neural network |
| CN111553468A (en) * | 2020-05-15 | 2020-08-18 | 南京大学 | Method for accurately predicting effluent quality of sewage treatment plant |
| CN111667098A (en) * | 2020-05-14 | 2020-09-15 | 湖北工业大学 | Wind power station output power prediction method based on multi-model combination optimization |
| CN111693667A (en) * | 2020-05-06 | 2020-09-22 | 杭州电子科技大学 | Water quality detection system and method based on gated recursive array |
| CN111858715A (en) * | 2020-07-24 | 2020-10-30 | 青岛洪锦智慧能源技术有限公司 | Sewage treatment plant water inlet quality prediction method based on data mining |
-
2021
- 2021-04-19 CN CN202110420432.8A patent/CN113033917B/en active Active
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006095440A (en) * | 2004-09-29 | 2006-04-13 | Toshiba Corp | Operation management system in sewage treatment plant |
| JP2007002474A (en) * | 2005-06-22 | 2007-01-11 | Mitsubishi Electric Corp | Integrated operation management method for sewage treatment plant |
| CN102681498A (en) * | 2011-03-15 | 2012-09-19 | 中国科学院沈阳自动化研究所 | Sewage treatment process optimizing operation method |
| CN103605859A (en) * | 2013-11-28 | 2014-02-26 | 浙江工业大学 | Optimum design method for secondary sedimentation tank of sewage treatment work |
| WO2015147349A1 (en) * | 2014-03-26 | 2015-10-01 | 부산대학교 산학협력단 | Integrated operation management device for plurality of sewage treatment plants sharing same discharge water system and method thereof |
| CN106200381A (en) * | 2016-07-27 | 2016-12-07 | 华电水务工程有限公司 | A kind of according to processing the method that water yield control by stages water factory runs |
| CN108640276A (en) * | 2018-04-17 | 2018-10-12 | 东南大学 | A kind of sewage treatment plant AAO process optimization operation methods based on WEST models |
| CN109508811A (en) * | 2018-09-30 | 2019-03-22 | 中冶华天工程技术有限公司 | Parameter prediction method is discharged based on principal component analysis and the sewage treatment of shot and long term memory network |
| CN109933027A (en) * | 2019-02-28 | 2019-06-25 | 重庆工商大学 | Sewage management platform based on factory's group's monitoring water quality and modelling management |
| CN109976187A (en) * | 2019-02-28 | 2019-07-05 | 重庆工商大学 | The sewage management platform for being optimized based on biochemical wastewater treatment and being finely aerated |
| CN110188946A (en) * | 2019-05-29 | 2019-08-30 | 剑科云智(深圳)科技有限公司 | A kind of prediction technique and sewage forecasting system of wastewater parameters |
| CN110245881A (en) * | 2019-07-16 | 2019-09-17 | 重庆邮电大学 | A kind of water quality prediction method and system of the sewage treatment based on machine learning |
| 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 |
| CN111027776A (en) * | 2019-12-13 | 2020-04-17 | 北京华展汇元信息技术有限公司 | Sewage treatment water quality prediction method based on improved long-short term memory LSTM neural network |
| CN111221306A (en) * | 2020-01-17 | 2020-06-02 | 石化盈科信息技术有限责任公司 | Method for predicting key indexes of sewage system |
| CN111291937A (en) * | 2020-02-25 | 2020-06-16 | 合肥学院 | Method for predicting quality of treated sewage based on combination of support vector classification and GRU neural network |
| CN111693667A (en) * | 2020-05-06 | 2020-09-22 | 杭州电子科技大学 | Water quality detection system and method based on gated recursive array |
| CN111667098A (en) * | 2020-05-14 | 2020-09-15 | 湖北工业大学 | Wind power station output power prediction method based on multi-model combination optimization |
| CN111553468A (en) * | 2020-05-15 | 2020-08-18 | 南京大学 | Method for accurately predicting effluent quality of sewage treatment plant |
| CN111858715A (en) * | 2020-07-24 | 2020-10-30 | 青岛洪锦智慧能源技术有限公司 | Sewage treatment plant water inlet quality prediction method based on data mining |
Non-Patent Citations (8)
| Title |
|---|
| LOUZADAVALORY,J. P.等: "Combining Genetic Algorithms with a Water Quality Model to Determine Efficiencies of Sewage Treatment Systems in Watersheds", 《JOURNAL OF ENVIRONMENTAL ENGINEERING》 * |
| MOZAFAR ANSARI等: "Optimized fuzzy inference system to enhance prediction accuracy for influent characteristics of a sewage treatment plant", 《SCIENCE OF THE TOTAL ENVIRONMENT》 * |
| 刘开第等: "污水处理厂运行管理效果评价模型", 《中国给水排水》 * |
| 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", 《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》 * |
| 米莎等: "基于BP神经网络的污水处理厂进水水质预测模型", 《给水排水》 * |
| 钟百鸿等: "基于综合灰关联序模型的残差门控循环神经网络位标器零部件选配", 《中国机械工程》 * |
| 马腾飞: "污水处理厂运行管理问题反思与优化途径", 《工程技术研究》 * |
| 鲁明: "基于PCA-GA-BP模型对污水BOD的预测", 《湖北汽车工业学院学报》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113479999A (en) * | 2021-07-29 | 2021-10-08 | 中建智能技术有限公司 | Sewage data processing method and device and computer equipment |
| CN113479999B (en) * | 2021-07-29 | 2022-09-13 | 中建智能技术有限公司 | Sewage data processing method and device and computer equipment |
| CN114149076A (en) * | 2021-12-21 | 2022-03-08 | 浙江沃乐环境科技有限公司 | Intelligent debugging system of anaerobic ammonia oxidation sewage treatment system |
| CN114149076B (en) * | 2021-12-21 | 2022-07-19 | 浙江沃乐环境科技有限公司 | Intelligent debugging system of anaerobic ammonia oxidation sewage treatment system |
| CN114417622A (en) * | 2022-01-24 | 2022-04-29 | 大唐融合通信股份有限公司 | Sewage treatment method, device, equipment and system |
| CN114417622B (en) * | 2022-01-24 | 2023-09-01 | 大唐融合通信股份有限公司 | Sewage treatment method, device, equipment and system |
| CN114626642A (en) * | 2022-05-16 | 2022-06-14 | 武汉华信数据系统有限公司 | Dosing system control method and device, storage medium and electronic equipment |
| CN115981153A (en) * | 2022-12-30 | 2023-04-18 | 浙江问源环保科技股份有限公司 | Deep learning based A 2 O process intermittent low-carbon aeration method and control system |
| CN115981153B (en) * | 2022-12-30 | 2023-08-04 | 浙江问源环保科技股份有限公司 | Deep learning-based A 2 O process intermittent low-carbon aeration method and control system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113033917B (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113033917B (en) | Sewage treatment plant prediction planning operation management method based on peripheral data | |
| Işık et al. | Artificial neural networks and adaptive neuro-fuzzy inference systems approaches to forecast the meteorological data for HVAC: the case of cities for Turkey | |
| CN105069525B (en) | Round-the-clock 96 Day Load Curve Forecastings and optimization update the system | |
| Cinar et al. | Development of future energy scenarios with intelligent algorithms: case of hydro in Turkey | |
| Piltan et al. | Energy demand forecasting in Iranian metal industry using linear and nonlinear models based on evolutionary algorithms | |
| Dun et al. | Short-term air quality prediction based on fractional grey linear regression and support vector machine | |
| CN110222888A (en) | A kind of per day Methods of electric load forecasting based on BP neural network | |
| Kalogirou | Artificial neural networks and genetic algorithms in energy applications in buildings | |
| CN111652425A (en) | River water quality prediction method based on rough set and long and short term memory network | |
| CN108694473A (en) | Building energy consumption prediction technique based on RBF neural | |
| Zhang et al. | A novel method based on FTS with both GA-FCM and multifactor BPNN for stock forecasting | |
| CN108280998A (en) | Short-time Traffic Flow Forecasting Methods based on historical data dynamic select | |
| Wang et al. | A full-view management method based on artificial neural networks for energy and material-savings in wastewater treatment plants | |
| CN114970362A (en) | Power grid load scheduling prediction method and system under multi-energy structure | |
| Pai | Hybrid ellipsoidal fuzzy systems in forecasting regional electricity loads | |
| Li et al. | A method of rainfall runoff forecasting based on deep convolution neural networks | |
| Abba et al. | Neuro-fuzzy ensemble techniques for the prediction of turbidity in water treatment plant | |
| CN110837929A (en) | Least square support vector machine electricity utilization prediction method based on adaptive genetic algorithm | |
| Salles et al. | Dynamic setpoint optimization using metaheuristic algorithms for wastewater treatment plants | |
| CN109408896B (en) | Multi-element intelligent real-time monitoring method for anaerobic sewage treatment gas production | |
| Huang et al. | Wind prediction based on improved bp artificial neural network in wind farm | |
| CN112949948B (en) | Integrated learning method and system for electric vehicle power conversion demand interval prediction in time-sharing mode | |
| CN111401638B (en) | Spatial load prediction method based on extreme learning machine and load density index method | |
| Eseye et al. | Efficient feature selection strategy for accurate electricity demand forecasting | |
| CN113988352A (en) | Sewage treatment plant water inflow prediction method based on peripheral data |
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 |