Sewage pump station control method and device based on combined regulation of pollution reduction and carbon reduction

Abstract

The invention relates to the technical field of sewage treatment, and discloses a sewage pump station control method and device based on pollution reduction and carbon reduction combined adjustment. Preprocessing the multi-dimensional data of the pump station to delete abnormal data; constructing a target function according to minimum carbon emission and maximum pollution discharge capacity of the pump station, and establishing target constraint conditions in combination with factors such as operation time, electric quantity and water level of the pump station; searching a parameter solution of pump station operation according to a star-graffiti optimization algorithm; according to the searched parameter solution of the pump station operation, predicting the carbon emission and pollution discharge capacity by using a carbon emission and pollution discharge capacity prediction model; and when the comprehensive fitness function value of the carbon emission and pollution discharge capacity is greater than a preset threshold value or the number of iterations is greater than a preset number of iterations, outputting an optimal parameter solution of pump station operation as an optimal control strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage treatment, and in particular to a sewage pump station control method and device based on combined regulation of pollution reduction and carbon reduction. Background Art

[0002] With the acceleration of my country's urbanization process, the amount of urban sewage discharge has increased year by year. As an important part of the drainage system, sewage pumping stations play a key role in the sewage transportation process. However, the large amount of carbon emissions generated during the operation of sewage pumping stations has become one of the important sources of greenhouse gases. It is estimated that by 2030, the total greenhouse gas emissions of the sewage treatment industry will reach 365 million tons of carbon dioxide equivalent, accounting for 2.95% of the total greenhouse gas emissions in the country. Among all aspects of sewage treatment, carbon emissions during the operation and maintenance stage of pumping stations account for as much as 62.57%. In addition, the operating energy consumption cost of pumping stations accounts for about 30% to 40% of the total cost of urban drainage systems, which poses a severe challenge to the dual control of operating costs and environmental impacts.

[0003] At present, the operation and management of urban sewage pumping stations mainly rely on manual experience scheduling, lacking scientific data support and optimization mechanisms. Although some sewage pumping stations are equipped with water monitoring equipment and drainage scheduling models, they mainly aim to optimize water quantity and water quality discharge, and have not yet formed a systematic carbon reduction scheduling mechanism. In addition, the pumps and motors of some traditional pumping stations are aging, with low energy efficiency levels, and the pipe network characteristics are not well matched with the pump working conditions, further exacerbating energy waste and environmental pollution. Summary of the invention

[0004] In view of this, the present application provides a method for controlling an urban sewage pumping station based on combined regulation of pollution reduction and carbon reduction, which solves the technical problem that the operation and management of urban sewage pumping stations in the prior art mainly rely on manual experience scheduling and lack of scientific data support and optimization mechanism.

[0005] According to a first aspect of the present application, a method for controlling an urban sewage pumping station based on combined regulation of pollution reduction and carbon reduction is provided, comprising:

[0006] Acquire multi-dimensional data of the pump station, wherein the multi-dimensional data of the pump station includes weather conditions, rainfall, pump station water level monitoring data, pump station flow monitoring data, pump station water quality monitoring data and pump station power monitoring data;

[0007] Preprocess the multi-dimensional data of the pumping station to remove abnormal data;

[0008] The objective function is constructed based on the minimum carbon emission and maximum sewage discharge capacity of the pumping station, and the target constraint conditions are established in combination with factors such as the pumping station operation time, electricity, and water level. Among them, the minimum carbon emission objective function of the pumping station is f1=minC=min(E×G×t1), and the maximum sewage discharge capacity objective function is f2=maxQ=max(S×a×t1). The target constraint condition is 0≤Q1=l×w×h+p×t0≤Q max , E is electricity consumption, G is carbon emission factor, t1 is pump station operation time, S is pump station flow, a is water quality data, l is water level, w is width, h is length, p is rainfall, t0 is rainfall duration;

[0009] Search for parameter solutions for pump station operation based on the Nudibranch optimization algorithm;

[0010] According to the searched parameter solutions of the pump station operation, the carbon emission and sewage discharge capacity prediction model is used to predict the carbon emission and sewage discharge capacity;

[0011] Determine whether the comprehensive fitness function value of the predicted carbon emission and pollution discharge capacity is less than the preset threshold. When the comprehensive fitness function value of carbon emission and pollution discharge capacity is greater than the preset threshold or the number of iterations is greater than the preset number of iterations, output the optimal parameter solution for the operation of the pump station as the optimal control strategy, otherwise continue to perform the optimization iterative calculation of the Nutcracker optimization algorithm.

[0012] According to a second aspect of the present application, a control device for an urban sewage pump station based on combined regulation of pollution reduction and carbon reduction is provided, comprising:

[0013] A data acquisition module is used to acquire multi-dimensional data of the pump station, wherein the multi-dimensional data of the pump station includes weather conditions, rainfall, pump station water level monitoring data, pump station flow monitoring data, pump station water quality monitoring data and pump station power monitoring data;

[0014] A preprocessing module is used to preprocess the multi-dimensional data of the pumping station to delete abnormal data;

[0015] The initialization module is used to construct the objective function based on the minimum carbon emission and maximum sewage discharge capacity of the pumping station, and to establish the objective constraint conditions based on the pumping station operation time, electricity, water level and other factors. Among them, the minimum objective function of carbon emission of the pumping station is f1=minC=min(E×G×t1), the maximum objective function of sewage discharge capacity is f2=maxQ=max(S×a×t1), and the objective constraint conditions are 0≤Q1=l×w×h+p×t0≤Q max , E is electricity consumption, G is carbon emission factor, t1 is pump station operation time, S is pump station flow, a is water quality data, l is water level, w is width, h is length, p is rainfall, t0 is rainfall duration;

[0016] Parameter optimization module, used to search for parameter solutions for pump station operation based on the Nudibranch optimization algorithm;

[0017] A prediction module is used to predict carbon emission and sewage discharge capacity according to the searched parameter solutions of the pump station operation and by using the carbon emission and sewage discharge capacity prediction model;

[0018] The output module is used to determine whether the comprehensive fitness function value of the predicted carbon emission and pollution discharge capacity is less than the preset threshold. When the comprehensive fitness function value of the carbon emission and pollution discharge capacity is greater than the preset threshold or the number of iterations is greater than the preset number of iterations, the optimal parameter solution for the operation of the pump station is output as the optimal control strategy, otherwise the optimization iterative calculation of the Nutcracker optimization algorithm continues.

[0019] According to the third aspect of the present application, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned urban sewage pumping station control method based on combined regulation of pollution reduction and carbon reduction are implemented.

[0020] According to the fourth aspect of the present application, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the urban sewage pumping station control method based on combined regulation of pollution reduction and carbon reduction are implemented.

[0021] Through the above-mentioned technical scheme, the present application provides a method, device, and equipment for controlling urban sewage pumping stations based on joint regulation of pollution reduction and carbon reduction, which obtains multi-dimensional data of the pumping station; pre-processes the multi-dimensional data of the pumping station to delete abnormal data; constructs an objective function based on the minimum carbon emissions and maximum sewage discharge capacity of the pumping station, and establishes target constraints based on factors such as the pumping station operation time, electricity, and water level; searches for parameter solutions for the operation of the pumping station according to the Nutcracker optimization algorithm; predicts carbon emissions and sewage discharge capacity using a carbon emission and sewage discharge capacity prediction model based on the searched parameter solutions for the operation of the pumping station; when the comprehensive fitness function value of carbon emissions and sewage discharge capacity is greater than a preset threshold or the number of iterations is greater than the preset number of iterations, outputs the optimal parameter solution for the operation of the pumping station as the optimal control strategy.

[0022] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application and to implement it in accordance with the contents of the specification, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0024] Figure 1 A schematic diagram of an application scenario of a method for controlling a municipal sewage pump station based on combined regulation of pollution reduction and carbon reduction provided in an embodiment of the present application is shown;

[0025] Figure 2 A flow chart of a method for controlling a municipal sewage pumping station based on combined regulation of pollution reduction and carbon reduction provided in an embodiment of the present application is shown;

[0026] Figure 3 A flow chart of the method for training the emission and discharge capacity prediction model provided in the embodiments of the present application is shown;

[0027] Figure 4 A schematic diagram of the method flow of the optimized Nudibranch optimization algorithm provided in an embodiment of the present application is shown;

[0028] Figure 5 A structural schematic diagram of a city sewage pump station control device based on combined regulation of pollution reduction and carbon reduction provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0029] The specific implementation of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0030] An urban sewage pump station control method based on pollution reduction and carbon reduction combined regulation provided by an embodiment of the present invention can be applied to Figure 1 In the scenario of the urban sewage pumping station shown in the figure, the sewage pumping station automation system consists of an industrial computer and a field control system. The field control system includes an inlet control subsystem and an outlet control subsystem. The inlet control subsystem and the outlet control subsystem are both composed of liquid level sensors and actuators. The industrial computer and the inlet control subsystem are connected to the outlet control subsystem through a field bus, realizing the automation of the whole process control from sewage collection, treatment to discharge. A joint regulation based on pollution reduction and carbon reduction is executed through the industrial computer (model training) or the field control system (edge ​​computing can be used for model deployment, localized analysis and decision-making, and the control actuator executes the pump station control strategy). The invention discloses a control method for an urban sewage pumping station, which comprises the following steps: obtaining multi-dimensional data of the pumping station; pre-processing the multi-dimensional data of the pumping station to delete abnormal data; constructing an objective function according to the minimum carbon emission and maximum sewage discharge capacity of the pumping station, and establishing target constraints in combination with factors such as the operation time, power consumption, and water level of the pumping station; searching for parameter solutions for the operation of the pumping station according to the Nudibranch optimization algorithm; predicting the carbon emission and sewage discharge capacity according to the searched parameter solutions for the operation of the pumping station using a carbon emission and sewage discharge capacity prediction model; and outputting the optimal parameter solution for the operation of the pumping station as the optimal control strategy when the comprehensive fitness function value of the carbon emission and sewage discharge capacity is greater than a preset threshold or the number of iterations is greater than a preset number of iterations.

[0031] The present invention is described in detail below through specific embodiments.

[0032] Embodiment 1:

[0033] like Figure 2 As shown, a method for controlling a municipal sewage pump station based on combined regulation of pollution reduction and carbon reduction is provided in an embodiment of the present invention, comprising:

[0034] Step 201, obtaining multi-dimensional data of a pumping station;

[0035] Among them, the multi-dimensional data of the pumping station includes weather conditions, rainfall, pumping station water level monitoring data, pumping station flow monitoring data, pumping station water quality monitoring data and pumping station power monitoring data;

[0036] Step 202: pre-process the multi-dimensional data of the pumping station to delete abnormal data;

[0037] Wherein, step 202 specifically includes:

[0038] Step 202-1, performing integrity check and null value processing on the multi-dimensional data of the pump station;

[0039] Step 202-2, detecting and cleaning abnormal values ​​of multi-dimensional data of pumping stations;

[0040] Step 202-3: Standardize the multi-dimensional data of the pumping station.

[0041] Step 203: construct an objective function based on the minimum carbon emission and maximum sewage discharge capacity of the pump station, and establish objective constraints based on factors such as the pump station operation time, electricity, and water level;

[0042] Among them, the minimum objective function of carbon emission of the pumping station is f1=minC=min(E×G×t1), the maximum objective function of sewage discharge capacity is f2=maxQ=max(S×a×t1), and the objective constraint condition is 0≤Q1=l×w×h+p×t0≤Q max , E is electricity consumption, G is carbon emission factor, t1 is pump station operation time, S is pump station flow, a is water quality data, l is water level, w is width, h is length, p is rainfall, t0 is rainfall duration;

[0043] Step 204, searching for a parameter solution for pump station operation according to the Nudibranch optimization algorithm;

[0044] Among them, before step 204, it is necessary to set various parameters of the Nutcracker optimization algorithm, and the initialization parameters include the upper and lower limits of the parameters [X min ,X max ], maximum number of iterations T max , population size N, population dimension D, first stage search probability P a1 , the second stage search probability Pa2 .

[0045] Step 205: predicting carbon emission and sewage discharge capacity using a carbon emission and sewage discharge capacity prediction model according to the searched parameter solution of the pump station operation;

[0046] Step 206: determine whether the predicted comprehensive fitness function value of carbon emissions and pollution discharge capacity is less than a preset threshold;

[0047] Among them, the comprehensive fitness function value is Among them, C(θ) is the current carbon emission value, Q(θ) is the current pollution discharge capacity, and C min is the optimal reference value of carbon emissions, Q max It is the optimal reference value for sewage discharge capacity.

[0048] Step 207: When the comprehensive fitness function value of carbon emission and pollution discharge capacity is greater than the preset threshold or the number of iterations is greater than the preset number of iterations, the optimal parameter solution for the operation of the pump station is output as the optimal control strategy, otherwise, it is adjusted to step 204 to continue the optimization iterative calculation of the Nutcracker optimization algorithm.

[0049] The optimal control strategy includes the pump station start and stop time strategy and pump speed adjustment strategy. The output optimal control strategy is, for example, the start and stop time points are 06:00-22:00 every day, and the sewage discharge capacity is 1500m 3 / h, carbon emissions and pollution discharge capacity are balanced and improved simultaneously during the optimization process.

[0050] A method, device, and equipment for controlling a city sewage pump station based on combined regulation of pollution reduction and carbon reduction is provided in a first embodiment of the present invention. The method, device, and equipment obtain multidimensional data of the pump station; preprocess the multidimensional data of the pump station to delete abnormal data; construct an objective function based on the minimum carbon emission and maximum sewage discharge capacity of the pump station, and establish target constraints based on factors such as the pump station operation time, electricity, and water level; search for parameter solutions for the operation of the pump station according to the Nutcracker optimization algorithm; predict carbon emissions and sewage discharge capacity using a carbon emission and sewage discharge capacity prediction model based on the searched parameter solutions for the operation of the pump station; when the comprehensive fitness function value of carbon emissions and sewage discharge capacity is greater than a preset threshold or the number of iterations is greater than a preset number of iterations, output the optimal parameter solution for the operation of the pump station as the optimal control strategy.

[0051] Embodiment 2:

[0052] Based on Example 1 of the present invention, a step of training the emission and discharge capacity prediction model is added before step 205, such as Figure 3 As shown, including:

[0053] Step 301, obtaining historical multidimensional data of a pumping station as a sample data set;

[0054] Step 302: define the feature number of input data, select an appropriate number of neurons, set the transfer function of the hidden layer to the logsig function, and set the transfer function of the output layer to the purelin function;

[0055] Step 303: Input the sample data set from the input layer into the carbon emission and pollution discharge capacity prediction model, perform nonlinear mapping through the logsig activation function in the hidden layer, and use the linear function purelin to generate the prediction result;

[0056] Step 304: Compare the prediction result with the target data and calculate the mean square error (MSE);

[0057] Step 305: Use the Levenberg-Marquardt algorithm to perform error back propagation, and adjust the weight and threshold of the model according to the mean square error MSE.

[0058] The second embodiment of the present invention can adapt to environmental changes and fluctuations in operating conditions through continuous learning and adjustment, and maintain the stability and reliability of prediction. The use of the Levenberg-Marquardt algorithm improves the robustness of the model, enabling it to quickly adjust in the face of data changes.

[0059] Embodiment three:

[0060] In order to improve the global optimization ability of the algorithm, improve convergence performance, enhance robustness and generalization ability, based on the dual population mechanism of reinforcement learning, the parameter solution of the Nutcracker optimization algorithm in step 204 for searching the pump station operation is optimized and improved, such as Figure 4 As shown, including:

[0061] Step 401, initializing the Q table in the Q-learning algorithm, in which the value of each state-action pair is stored, and its initial value is zero;

[0062] Among them, in addition to setting the initialization parameters of the nutcracker optimization algorithm, initializing the random position of the nutcracker population, setting the initial Q-table of Q-learning, the initial value is 0, Q-table (Q-table) is a data structure in reinforcement learning (RL), which is used to store the expected utility or value of an agent taking a specific action in a specific state. The Q-table is one of the central concepts of Q-learning. It records the estimated value of the cumulative reward under each state-action pair. These values ​​are usually called Q-values. The basic components of the Q-table include state: the environment or situation in which the agent is located. Action: the possible behavior that the agent can take in this state. Q-value: represents the expected return of taking a specific action in a given state. The higher the Q-value, the better the long-term benefit of taking the action in this state.

[0063] Step 402: sort the population in ascending order according to the fitness value, and assign the top 50% of the fitness ranking to the development population for local search and deep optimization; the remaining individuals are assigned to the exploration population to perform a global search in the solution space to find potential new solutions;

[0064] Step 403: adjust the current position of each individual in the exploration population according to the population mean and the positions of other individuals, introduce random disturbances, and search for potential new solutions;

[0065] Among them, the position update formula is x i ' ,j =x m,j +ε·(x A,j -x B,j )+μ·(r1 2 ·U j -L j ), where x m,j is the population mean, A, B are randomly selected individuals, ε, μ, r1, U j ,L j is the control parameter.

[0066] Step 404: For each individual in the development population, the Q-learning reinforcement learning algorithm is used to adjust the individual position.

[0067] Among them, the state encoding is the local diversity change rate in, is the individual diversity measure in the current iteration, It is a measure of individual diversity in the previous generation. The local diversity change rate is used to measure the spatial distribution and diversity level of the population, indicating whether the current search process is concentrated in the local area to avoid falling into the local optimal solution. The fitness change rate is in, is the current fitness value, is the fitness value of the previous round, and the fitness change rate is used to measure the quality change of the current solution, indicating the convergence speed of the search process and the degree of optimization of the objective function. Through the encoding and joint use of these two parameters, the algorithm can dynamically perceive the search state, adjust the search behavior in the development population, and improve the local search accuracy and convergence speed. This mechanism effectively combines the Nutcracker optimization algorithm with the reinforcement learning algorithm, improving the comprehensive performance of global optimization and local development.

[0068] The action selection strategy is to use the SoftMax function to select the storage and recovery strategy. Among them, π q (s t ,a j ) is the action selection probability, in state s t Next select action a j The probability of executing action a in this state j The possibility, Q(s t ,a j ) is the Q value indicating that in state s t Next, perform action a j The expected cumulative reward value that can be obtained is the core parameter of the Q-learning algorithm, s t The current state represents the current environmental state, which is generally encoded by a combination of features such as the fitness change rate and the local diversity change rate. j For action j in state s t The available actions include “store current position” and “restore to the best historical solution” and other strategic operations. n is the size of the action space, the number of different strategies available, and represents the dimension of the action space.

[0069] The storage policy is in, The updated individual position represents the position vector of individual i in the next iteration (round t+1), The current individual position represents the position vector of individual i in the current iteration (round t), μ is the step size that controls the current solution to approach the optimal solution, which is used to balance the search intensity and accuracy, and x best is the position of the individual with the best fitness found in the current population, which is used as the reference target point. λ is a random number used to introduce disturbances to avoid premature convergence. It is a random number between 0 and 1, which is used to enhance search diversity. A ,xB The positions of two different individuals randomly selected from the population serve as reference points for generating random differences.

[0070] The recovery strategy is in, The updated individual position represents the position vector of individual i in the next iteration (round t+1); RP i,1 Alternative position 1 is the first alternative position in the recovery strategy, which is a potential better position found by individual i in local search or historical records; RP i,2 The second alternative position in the strategy for restoring alternative position 2 is the alternative solution found by individual i in another search path or other strategy; f(RP i,1 ) is the fitness value of the first candidate position, indicating the candidate position RP i,1 Evaluation result in the fitness function; f(RP i,2 ) is the fitness value of the second candidate position, indicating the candidate position RP i,2 Evaluation result in the fitness function; f(x i ) is the current individual fitness value, which represents the fitness value of individual i in the current solution space position and is one of the decision bases.

[0071] Reward and Q table update, where the reward is Among them, R is the reward value, which represents the immediate reward obtained by individual i after performing the current action, and measures the effectiveness of the action in improving fitness; The fitness value for the next round represents the fitness function value of individual i after the updated position;

[0072] The current fitness value represents the fitness function value of individual i at the current position.

[0073] The Q table is updated to Q(s t ,a t )←Q(s t ,a t )+α·[R+γ·max(Q(s t+1 ,a))-Q(s t ,a t )], where is the current Q value indicating the current state s t Next select action a t The expected cumulative reward; α is the learning rate that controls the amplitude of Q value update, ranging from 0<α≤1. The larger the value, the more sensitive it is to the update of new information; R is the immediate reward, which means that in the current state s t Execute action a tThe immediate reward obtained after the decision is made; γ is the discount factor that measures the impact of future rewards on current decisions, ranging from 0≤γ≤1. The larger the value, the more attention is paid to long-term returns; max(Q(s t+1 ,a)) is the future optimal Q value, indicating that in the next state s t+1 The maximum Q value of all possible actions a represents the optimal return expectation in the future; a t The current state indicates that in the current state s t The action selected next may be storage, recovery, or other strategic behavior; t+1 The next state represents the execution of action a t After that, the system transfers to the new environment state.

[0074] Embodiment 3 of the present invention proposes a dual-population mechanism based on reinforcement learning, which divides the original population into exploration sub-populations and utilization sub-populations according to the fitness values ​​of individuals to better balance the global exploration and local development capabilities. An improved foraging strategy based on randomized oppositional learning is designed for the exploration sub-population to enhance diversity. Q-learning is used as an adaptive selector to optimally adjust the behavior of the utilization sub-population in different problems. The state is encoded using the fitness value of the individual and the relative change of local diversity, and the action is selected according to the Q table value to dynamically optimize the benefits at different stages. Reinforcement learning is combined with the Star Crow optimization algorithm, and the exploration and utilization strategies are dynamically selected through RL to improve the global optimization capability of the algorithm.

[0075] Further, as Figures 2 to 4 The specific implementation of the method, in an embodiment of the present invention, provides a control device for an urban sewage pump station based on the combined regulation of pollution reduction and carbon reduction, such as Figure 5 As shown, the device comprises:

[0076] The data acquisition module 510 is used to acquire multi-dimensional data of the pump station, wherein the multi-dimensional data of the pump station includes weather conditions, rainfall, pump station water level monitoring data, pump station flow monitoring data, pump station water quality monitoring data and pump station power monitoring data;

[0077] A preprocessing module 520 is used to preprocess the multi-dimensional data of the pump station to delete abnormal data;

[0078] Initialization module 530 is used to construct an objective function based on the minimum carbon emission and maximum sewage discharge capacity of the pumping station, and to establish target constraints based on factors such as the pumping station operation time, electricity, and water level. The minimum objective function of the pumping station carbon emission is f1=minC=min(E×G×t1), and the maximum objective function of sewage discharge capacity is f2=maxQ=max(S×a×t1). The target constraint is 0≤Q1=l×w×h+p×t0≤Q max, E is electricity consumption, G is carbon emission factor, t1 is pump station operation time, S is pump station flow, a is water quality data, l is water level, w is width, h is length, p is rainfall, t0 is rainfall duration;

[0079] A parameter optimization module 540, for searching for a parameter solution for pump station operation according to a Nutcracker optimization algorithm;

[0080] A prediction module 550 is used to predict the carbon emission and sewage discharge capacity according to the searched parameter solution of the pump station operation and using the carbon emission and sewage discharge capacity prediction model;

[0081] Output module 560 is used to determine whether the comprehensive fitness function value of the predicted carbon emission and pollution discharge capacity is less than a preset threshold. When the comprehensive fitness function value of the carbon emission and pollution discharge capacity is greater than the preset threshold or the number of iterations is greater than the preset number of iterations, the optimal parameter solution for the operation of the pump station is output as the optimal control strategy, otherwise the optimization iterative calculation of the Nutcracker optimization algorithm continues.

[0082] In an embodiment of the present invention, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of implementing a method for controlling an urban sewage pump station based on combined regulation of pollution reduction and carbon reduction include:

[0083] Acquire multi-dimensional data of the pump station, wherein the multi-dimensional data of the pump station includes weather conditions, rainfall, pump station water level monitoring data, pump station flow monitoring data, pump station water quality monitoring data and pump station power monitoring data;

[0084] Preprocess the multi-dimensional data of the pumping station to remove abnormal data;

[0085] The objective function is constructed based on the minimum carbon emission and maximum sewage discharge capacity of the pumping station, and the target constraint conditions are established in combination with factors such as the pumping station operation time, electricity, and water level. Among them, the minimum carbon emission objective function of the pumping station is f1=minC=min(E×G×t1), and the maximum sewage discharge capacity objective function is f2=maxQ=max(S×a×t1). The target constraint condition is 0≤Q1=l×w×h+p×t0≤Q max , E is electricity consumption, G is carbon emission factor, t1 is pump station operation time, S is pump station flow, a is water quality data, l is water level, w is width, h is length, p is rainfall, t0 is rainfall duration;

[0086] Search for parameter solutions for pump station operation based on the Nudibranch optimization algorithm;

[0087] According to the searched parameter solutions of the pump station operation, the carbon emission and sewage discharge capacity prediction model is used to predict the carbon emission and sewage discharge capacity;

[0088] Determine whether the comprehensive fitness function value of the predicted carbon emission and pollution discharge capacity is less than the preset threshold. When the comprehensive fitness function value of carbon emission and pollution discharge capacity is greater than the preset threshold or the number of iterations is greater than the preset number of iterations, output the optimal parameter solution for the operation of the pump station as the optimal control strategy, otherwise continue to perform the optimization iterative calculation of the Nutcracker optimization algorithm.

[0089] In an embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0090] Acquire multi-dimensional data of the pump station, wherein the multi-dimensional data of the pump station includes weather conditions, rainfall, pump station water level monitoring data, pump station flow monitoring data, pump station water quality monitoring data and pump station power monitoring data;

[0091] Preprocess the multi-dimensional data of the pumping station to remove abnormal data;

[0092] The objective function is constructed based on the minimum carbon emission and maximum sewage discharge capacity of the pumping station, and the objective constraints are established by combining the pumping station operation time, power, water level and other factors. Among them, the objective function for the minimum carbon emission of the pumping station is, the objective function for the maximum sewage discharge capacity is, and the objective constraints are, E is the power consumption, G is the carbon emission factor, is the pumping station operation time, S is the pumping station flow, a is the water quality data, l is the water level, w is the width, h is the length, p is the rainfall, and t0 is the rainfall duration;

[0093] Search for parameter solutions for pump station operation based on the Nudibranch optimization algorithm;

[0094] According to the searched parameter solutions of the pump station operation, the carbon emission and sewage discharge capacity prediction model is used to predict the carbon emission and sewage discharge capacity;

[0095] Determine whether the comprehensive fitness function value of the predicted carbon emission and pollution discharge capacity is less than the preset threshold. When the comprehensive fitness function value of carbon emission and pollution discharge capacity is greater than the preset threshold or the number of iterations is greater than the preset number of iterations, output the optimal parameter solution for the operation of the pump station as the optimal control strategy, otherwise continue to perform the optimization iterative calculation of the Nutcracker optimization algorithm.

[0096] It should be noted that, in the above embodiments, only the urban sewage treatment pump station is used as an example to illustrate the principles and implementation steps of the embodiments of the present invention, and no specific limitation is made to the actual application scenarios. For example, the technical solution of the present invention can also be applied to metering fault prediction of other power grid-related instruments. For the functions or steps that can be implemented by the computer-readable storage medium or computer device, please refer to the aforementioned method embodiments. To avoid repetition, they will not be described one by one here.

[0097] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0098] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0099] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for controlling a municipal sewage pumping station based on combined regulation of pollution reduction and carbon reduction, characterized in that: include: Acquire multi-dimensional data of the pump station, wherein the multi-dimensional data of the pump station includes weather conditions, rainfall, pump station water level monitoring data, pump station flow monitoring data, pump station water quality monitoring data and pump station power monitoring data; Preprocessing the multi-dimensional data of the pump station to delete abnormal data; The objective function is constructed based on the minimum carbon emission and maximum sewage discharge capacity of the pumping station, and the target constraint conditions are established in combination with factors such as the pumping station operation time, electricity, and water level. Among them, the minimum objective function of carbon emission of the pumping station is f1=minC=min(E×G×t1), and the maximum objective function of sewage discharge capacity is f2=maxQ=max(S×a×t1). The target constraint condition is 0≤Q1=l×w×h+p×t0≤Q max , E is electricity consumption, G is carbon emission factor, t1 is pump station operation time, S is pump station flow, a is water quality data, l is water level, w is width, h is length, p is rainfall, t0 is rainfall duration; Search for parameter solutions for pump station operation based on the Nudibranch optimization algorithm; According to the searched parameter solutions of the pump station operation, the carbon emission and sewage discharge capacity prediction model is used to predict the carbon emission and sewage discharge capacity; Determine whether the comprehensive fitness function value of the predicted carbon emission and pollution discharge capacity is less than the preset threshold. When the comprehensive fitness function value of carbon emission and pollution discharge capacity is greater than the preset threshold or the number of iterations is greater than the preset number of iterations, output the optimal parameter solution for the operation of the pump station as the optimal control strategy, otherwise continue to perform the optimization iterative calculation of the Nutcracker optimization algorithm.

2. The urban sewage pump station control method based on pollution reduction and carbon reduction combined regulation according to claim 1 is characterized in that: The step of preprocessing the multidimensional data of the pump station to delete abnormal data includes: Performing integrity check and null value processing on the multi-dimensional data of the pump station; Detecting and cleaning abnormal values ​​of the multi-dimensional data of the pump station; The multi-dimensional data of the pumping station is standardized.

3. The urban sewage pump station control method based on pollution reduction and carbon reduction combined regulation according to claim 1 is characterized in that: Before the step of searching the parameter solution of the pump station operation according to the Nutcracker optimization algorithm and predicting the carbon emission and sewage discharge capacity using the carbon emission and sewage discharge capacity prediction model, the step of training the emission and sewage discharge capacity prediction model includes: Obtain historical multidimensional data of the pumping station as a sample data set; Define the feature number of input data, select the appropriate number of neurons, set the transfer function of the hidden layer to the logsig function, and set the transfer function of the output layer to the purelin function; Input the sample data set from the input layer into the carbon emission and pollution discharge capacity prediction model, perform nonlinear mapping through the logsig activation function in the hidden layer, and use the linear function purelin to generate the prediction result; Compare the prediction result with the target data and calculate the mean square error (MSE); The Levenberg-Marquardt algorithm is used for error back propagation, and the weights and thresholds of the model are adjusted according to the mean square error (MSE).

4. The urban sewage pump station control method based on pollution reduction and carbon reduction combined regulation according to claim 1 is characterized in that: Before the step of searching for the parameter solution of the pump station operation according to the Nutcracker optimization algorithm and predicting the carbon emission and sewage discharge capacity by using the artificial neural network model, the method includes: The initialization parameters required for the iteration of the Nutcracker optimization algorithm are preset, wherein the initialization parameters include the upper and lower limits of the parameters [X min ,X max ], maximum number of iterations T max , population size N, population dimension D, first stage search probability P a1 , the second stage search probability P a2 .

5. The urban sewage pump station control method based on pollution reduction and carbon reduction combined regulation according to claim 1 is characterized in that: The Nutcracker optimization algorithm is used to search for parameter solutions for pump station operation, including: Initialize the Q-table in the Q-learning algorithm, which stores the value of each state-action pair, and its initial value is zero; The population is sorted in ascending order according to the fitness value, and the top 50% of the fitness rankings are assigned to the development population for local search and deep optimization; the remaining individuals are assigned to the exploration population to perform a global search in the solution space to find potential new solutions; The current position of each individual in the exploration population is adjusted according to the population mean and the positions of other individuals, random disturbances are introduced, and potential new solutions are sought; For each individual in the development population, a Q-learning reinforcement learning algorithm is used to adjust the individual position.

6. The urban sewage pump station control method based on pollution reduction and carbon reduction combined regulation according to claim 1 is characterized in that: The comprehensive fitness function value is Among them, C(θ) is the current carbon emission value, Q(θ) is the current pollution discharge capacity, and C min is the optimal reference value of carbon emissions, Q max It is the optimal reference value for sewage discharge capacity.

7. The urban sewage pump station control method based on pollution reduction and carbon reduction combined regulation according to claim 1 is characterized in that: The optimal control strategy includes a pump station start and stop time strategy and a pump speed adjustment strategy.

8. A control device for an urban sewage pumping station based on combined regulation of pollution reduction and carbon reduction, characterized in that: include: A data acquisition module is used to acquire multi-dimensional data of a pump station, wherein the multi-dimensional data of a pump station includes weather conditions, rainfall, water level monitoring data of a pump station, flow monitoring data of a pump station, water quality monitoring data of a pump station, and power monitoring data of a pump station; A preprocessing module, used for preprocessing the multi-dimensional data of the pumping station to delete abnormal data; The initialization module is used to construct the objective function based on the minimum carbon emission and maximum sewage discharge capacity of the pumping station, and to establish the objective constraint conditions based on the pumping station operation time, electricity, water level and other factors. Among them, the minimum objective function of carbon emission of the pumping station is f1=minC=min(E×G×t1), the maximum objective function of sewage discharge capacity is f2=maxQ=max(S×a×t1), and the objective constraint conditions are 0≤Q1=l×w×h+p×t0≤Q max , E is electricity consumption, G is carbon emission factor, t1 is pump station operation time, S is pump station flow, a is water quality data, l is water level, w is width, h is length, p is rainfall, t0 is rainfall duration; Parameter optimization module, used to search for parameter solutions for pump station operation based on the Nudibranch optimization algorithm; A prediction module is used to predict carbon emission and sewage discharge capacity according to the searched parameter solutions of the pump station operation and by using the carbon emission and sewage discharge capacity prediction model; The output module is used to determine whether the comprehensive fitness function value of the predicted carbon emission and pollution discharge capacity is less than the preset threshold. When the comprehensive fitness function value of the carbon emission and pollution discharge capacity is greater than the preset threshold or the number of iterations is greater than the preset number of iterations, the optimal parameter solution for the operation of the pump station is output as the optimal control strategy, otherwise the optimization iterative calculation of the Nutcracker optimization algorithm continues.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the urban sewage pumping station control method based on the combined regulation of pollution reduction and carbon reduction as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the steps of the urban sewage pumping station control method based on the combined regulation of pollution reduction and carbon reduction as described in any one of claims 1 to 7 are implemented.

Images