Whole-flow intelligent regulation and control method and device for sewage treatment and medium

Abstract

The invention discloses a full-flow intelligent regulation and control method and equipment for sewage treatment and a medium, and relates to the technical field of sewage treatment. The method comprises the following steps: acquiring basic data of a sewage treatment plant to be regulated and controlled, and constructing a corresponding sewage treatment model based on the basic data; based on the sewage treatment model, determining input parameters and output indexes in the sewage treatment process; respectively disturbing each input parameter by utilizing a preset global sensitivity analysis method, determining key input parameters of which the sensitivity indexes are greater than a preset threshold value, and constructing a lag disturbance model of each key input parameter; monitoring data in the sewage treatment process are collected in real time, and real-time lag effluent quality prediction is carried out according to the monitoring data and the lag disturbance model; and judging whether the real-time lagging water quality prediction data exceeds an effluent water quality limit value or not, and performing control parameter dynamic optimization and regulation on the sewage treatment model based on a preset multi-target optimization algorithm under the condition that the real-time lagging water quality prediction data exceeds the effluent water quality limit value.

Description

Technical Field

[0001] The present application relates to the technical field of sewage treatment, and in particular to a method, equipment and medium for intelligent control of the entire sewage treatment process. Background Art

[0002] Traditional sewage treatment methods mostly rely on manual experience and fixed process parameters, making it difficult to achieve precise control and optimization of the sewage treatment process. At the same time, since the sewage treatment process involves multiple complex biochemical reactions and physical processes, the mutual influence and hysteresis effect between the various parameters make it difficult to predict and control the sewage treatment effect.

[0003] In order to solve the above problems, many model-based intelligent control methods have emerged in recent years. These methods establish mathematical models of the sewage treatment process and use real-time monitoring data and advanced algorithms to calibrate and optimize the models to achieve precise control and optimization of the sewage treatment process. However, the existing intelligent control methods still have some shortcomings.

[0004] First, the existing model building process often ignores the sensitivity analysis of the impact of input parameters on effluent water quality. In the sewage treatment process, different parameters have different degrees of influence on effluent water quality, and slight changes in some key parameters may lead to significant fluctuations in effluent water quality. Therefore, conducting sensitivity analysis on input parameters and identifying key parameters are important prerequisites for achieving precise control of the sewage treatment process.

[0005] Secondly, existing intelligent control methods often ignore the lag effect between parameter disturbance and effluent water quality changes. Since the biochemical reactions and physical processes in the sewage treatment process have a certain time delay, parameter changes are often not immediately reflected in the effluent water quality. Therefore, when establishing the model and performing control, it is necessary to consider the lag time between parameter disturbance and effluent water quality changes to improve the prediction accuracy of the model and the control effect. Summary of the invention

[0006] The embodiments of the present application provide a method, device and medium for intelligent control of the entire process of sewage treatment, which are used to solve the following technical problems: how to accurately predict water quality changes in real time, optimize control parameters and control the sewage treatment process in real time.

[0007] In a first aspect, an embodiment of the present application provides a method for intelligent control of the entire process of sewage treatment, the method comprising: obtaining basic data of a sewage treatment plant to be regulated, and constructing a corresponding sewage treatment model based on the basic data; wherein the basic data comprises: process data and equipment data; based on the sewage treatment model, determining the input parameters affecting the effluent water quality in the sewage treatment process and the output indicators for evaluating the sewage treatment effect; using a preset global sensitivity analysis method to perturb each input parameter respectively, so as to determine the key input parameters whose sensitivity index is greater than a preset threshold value based on the fluctuation of each output indicator, and construct a hysteresis perturbation model for each key input parameter; deploying sensors at the process detection nodes corresponding to each key input parameter to collect monitoring data in the sewage treatment process in real time, and performing real-time lagging effluent water quality prediction based on the monitoring data and the hysteresis perturbation model; judging whether the real-time lagging water quality prediction data exceeds the effluent water quality limit, and if it exceeds the limit, dynamically optimizing and regulating the control parameters of the sewage treatment model based on a preset multi-objective optimization algorithm.

[0008] In one implementation of the present application, each input parameter is perturbed respectively using a preset global sensitivity analysis method to determine the key input parameters whose sensitivity index is greater than a preset threshold value based on the fluctuation of each output indicator, specifically including: defining the perturbation interval of each input parameter, and generating a perturbation sequence of each input parameter using a preset random sequence generation algorithm; inputting the perturbation values ​​in the perturbation sequence of each input parameter into the sewage treatment model in sequence for perturbation to obtain a perturbation output indicator; based on the perturbation output indicator, performing sensitivity calculation on each input parameter using a preset global sensitivity calculation formula, and comparing the calculated sensitivity index with the preset threshold value to determine the key input parameters whose sensitivity is greater than the preset threshold value among each input parameter.

[0009] In one implementation of the present application, the global sensitivity calculation formula is expressed by the following formula:

[0010] in, For the The sensitivity index of the input parameters, is the global sensitivity disturbance change constant, M is the number of input parameters, For the The input parameters correspond to the initialization parameter values, For the The first in the disturbance sequence corresponding to the input parameter The disturbance value, For the The mean of all disturbance values ​​in the disturbance sequence corresponding to the input parameters, is the number of perturbation values ​​in the perturbation sequence corresponding to each input parameter.

[0011] In one implementation of the present application, a lag disturbance model for each key input parameter is constructed, specifically including: performing data statistical analysis on the disturbance output index to identify the lag time between the disturbance of each key input parameter and the change in effluent water quality; initializing the order of the ARMA model to be applied, and using the disturbance sequence of each key input parameter and the corresponding disturbance output index as the input and output data of the model, estimating the model parameters by the least squares method to obtain the corresponding initial lag disturbance model; based on the lag time of each key input parameter and the corresponding sensitivity index, adjusting the parameters of the corresponding initial lag disturbance model to obtain the lag disturbance model of each key input parameter.

[0012] In one implementation of the present application, based on the lag time of each key input parameter and the corresponding sensitivity index, the parameters of the corresponding initial lag disturbance model are adjusted, specifically including: matching the lag time of each key input parameter with the corresponding preset order correction table to determine the order correction value corresponding to the lag time of each key input parameter, and correcting the order of the corresponding initial lag disturbance model based on the order correction value; and substituting the sensitivity index of each key input parameter into a preset weighted constant linear calculation formula to determine the parameter weighted constant of the corresponding initial lag disturbance model, so as to perform weighted calculation on the parameters of the corresponding initial lag disturbance model based on the parameter weighted constant.

[0013] In one implementation of the present application, the weighted constant linear calculation formula is expressed by the following formula:

[0014] in, is the parameter weighting constant of the initial hysteresis disturbance model corresponding to the i-th key input parameter, is the sensitivity index of the i-th key input parameter, a , b , c is the preset weighted constant calculation coefficient, and n is the nonlinear adjustment factor used to adjust the influence of the sensitivity index on the weighted constant.

[0015] In one implementation of the present application, real-time lagged effluent water quality prediction is performed based on monitoring data and a lagged disturbance model, specifically including: inputting the monitoring data corresponding to each key input parameter into the corresponding lagged disturbance model to determine the single lagged water quality prediction data corresponding to each key input parameter; based on the process detection node corresponding to each key input parameter, determining the historical contribution index corresponding to each single lagged water quality prediction data, and using the historical contribution index as the weight of each single lagged water quality prediction data, and calculating the real-time lagged water quality prediction data by weighted average.

[0016] In one implementation of the present application, a multi-objective optimization algorithm is constructed based on a multi-objective particle swarm optimization algorithm; based on a preset multi-objective optimization algorithm, the control parameters of the sewage treatment model are dynamically optimized and regulated, specifically including: taking real-time lagged water quality prediction data and the control parameters of the current sewage treatment model as input, and performing iterative calculations through a multi-objective optimization algorithm; when the iterative calculation reaches a preset convergence condition, outputting a control parameter combination, and applying it to the sewage treatment model to achieve real-time regulation of the sewage treatment process.

[0017] In the second aspect, an embodiment of the present application also provides an intelligent control device for the entire process of sewage treatment, characterized in that the device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by at least one processor, and the instructions are executed by at least one processor so that at least one processor can execute a method for intelligent control of the entire process of sewage treatment such as any one of the above.

[0018] On the third aspect, the embodiments of the present application also provide a non-volatile computer storage medium for intelligent control of the entire sewage treatment process, storing computer executable instructions, characterized in that when the computer executable instructions are executed, a method for intelligent control of the entire sewage treatment process such as any of the above is implemented.

[0019] The embodiments of the present application provide a method, device and medium for intelligent control of the whole process of sewage treatment, which have the following beneficial effects: 1. Significantly improve sewage treatment efficiency: This application uses a global sensitivity analysis method to accurately identify the key input parameters that have the greatest impact on effluent water quality, and constructs a hysteresis perturbation model for these parameters. This technical solution not only simplifies the control complexity, but also significantly improves the pertinence and efficiency of the sewage treatment process. By real-time control of these key parameters, the present invention enables the sewage treatment system to quickly respond to water quality changes and optimize the treatment process, thereby greatly improving treatment efficiency.

[0020] 2. Effectively reduce energy consumption costs: This application uses a multi-objective optimization algorithm to dynamically optimize the control parameters of the sewage treatment model while ensuring that the effluent quality meets the standards. By adjusting the control parameters in real time, this application minimizes energy consumption and effectively reduces the operating costs of the sewage treatment plant. In addition, through intelligent regulation, this application also avoids unnecessary energy waste and further improves energy utilization efficiency.

[0021] 3. Enhance the stability and reliability of system operation: This application achieves precise control of the sewage treatment process by real-time monitoring of the dynamic changes of key input parameters and combining the hysteresis perturbation model to predict water quality. This technical solution can promptly detect and respond to abnormal situations such as sudden changes in water quality and equipment failures to ensure the stable operation of the sewage treatment system. At the same time, the introduction of the hysteresis perturbation model also makes the system's prediction of water quality changes more accurate, further enhancing the reliability of the system.

[0022] 4. Optimize effluent water quality and ensure environmental safety: Through precise control and real-time monitoring of key input parameters, this application can ensure that the effluent water quality always remains within the set limits, or even reaches higher water quality standards, which helps to protect the water environment, improve the quality of water resources, and avoid environmental safety problems caused by substandard effluent water quality. 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: Figure 1 A flow chart of a method for intelligent control of the entire sewage treatment process provided in an embodiment of the present application; Figure 2 A schematic diagram of the internal structure of an intelligent control device for the entire sewage treatment process provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0025] The embodiments of the present application provide a method, device and medium for intelligent control of the entire process of sewage treatment, which are used to solve the following technical problems: how to accurately predict water quality changes in real time, optimize control parameters and control the sewage treatment process in real time.

[0026] The technical solution proposed in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0027] Figure 1 A flow chart of a method for intelligently controlling the entire process of sewage treatment provided in an embodiment of the present application. Figure 1As shown, the embodiment of the present application provides a method for intelligent control of the whole process of sewage treatment, which specifically includes the following steps: Step 101: Obtain basic data of the sewage treatment plant to be regulated, and build a corresponding sewage treatment model based on the basic data.

[0028] It should be noted that the basic data of the embodiments of the present application include: process data, equipment data, etc.

[0029] In one embodiment, process data includes various parameters in the sewage treatment process, such as influent flow, water quality indicators (such as COD, BOD, ammonia nitrogen, total phosphorus, etc.), operating parameters of each treatment unit (such as aeration volume, return volume, sludge age, etc.), etc. Equipment data includes performance parameters, operating status and historical maintenance records of various equipment in the sewage treatment plant. In actual operation, these data can be obtained through the automated control system of the sewage treatment plant, online monitoring instruments, and manual sampling and analysis.

[0030] In one embodiment, based on the basic data obtained, a sewage treatment model is constructed using mathematical modeling and simulation technology. The model should be able to simulate the actual operation of the sewage treatment plant, including the treatment effect of each treatment unit, the conversion process of pollutants, and economic indicators such as energy consumption and material consumption. It should be noted that when establishing the model, it is necessary to select a suitable mathematical model based on the process characteristics and data availability of the sewage treatment plant. Commonly used models include activated sludge models (such as ASM series), biofilm models, and data-driven machine learning models. In an embodiment of the present application, the ASM model is preferably used as the basic framework, and the model is optimized and corrected in combination with a machine learning algorithm. After the model is constructed, the initial parameters of the model need to be set according to the basic data. These parameters include, but are not limited to, the reaction rate constants, kinetic parameters, and equipment performance parameters of each treatment unit. The setting of the parameters should reflect the actual operation of the sewage treatment plant as much as possible.

[0031] Step 102: Based on the sewage treatment model, determine the input parameters that affect the effluent quality during the sewage treatment process and the output indicators used to evaluate the sewage treatment effect.

[0032] In one embodiment, the sewage treatment model constructed in step 101 is used to further determine key input parameters that affect effluent water quality and output indicators for evaluating sewage treatment effects.

[0033] Among them, input parameters refer to various factors that can affect the quality of effluent during sewage treatment. Through the analysis of various variables in the model, for example, the following key input parameters can be determined: Influent flow rate: The size of the influent flow rate directly affects the treatment load and treatment effect of the sewage treatment plant. Too large a flow rate may lead to insufficient treatment and affect the effluent quality; too small a flow rate may reduce the treatment efficiency and increase the operating cost; Water quality indicators: including COD (chemical oxygen demand), BOD (biochemical oxygen demand), ammonia nitrogen, total phosphorus, etc. These indicators directly reflect the concentration and type of pollutants in sewage and are key factors affecting the quality of effluent; Aeration volume: The size of the aeration volume directly affects the activity of aerobic microorganisms, thereby affecting the degradation of organic matter and the nitrification reaction, and has an important impact on the quality of effluent; Backflow volume: The control of internal and external backflow volumes is crucial to the denitrification and phosphorus removal process. Reasonable backflow volume can improve treatment efficiency and improve effluent quality. Output indicators are key parameters used to evaluate the effect of sewage treatment and can directly reflect the quality of water. Based on the sewage treatment model and actual needs, for example, the following output indicators can be determined: effluent COD: effluent COD is one of the important indicators for measuring the effect of sewage treatment, which reflects the degree of removal of organic matter in sewage; effluent ammonia nitrogen: ammonia nitrogen is one of the common pollutants in sewage, and its removal effect directly reflects the denitrification capacity of the sewage treatment plant; effluent total phosphorus: total phosphorus is one of the important parameters for measuring the effect of sewage treatment, and is of great significance for preventing eutrophication of water bodies; energy consumption: energy consumption is an important indicator for measuring the economy of the sewage treatment process, including electricity consumption, drug consumption, etc.

[0034] Step 103: Use a preset global sensitivity analysis method to perturb each input parameter respectively, so as to determine the key input parameters whose sensitivity index is greater than a preset threshold based on the fluctuation of each output indicator, and construct a hysteresis perturbation model for each key input parameter.

[0035] In one embodiment of the present application, after determining the input parameters and output indicators, each input parameter is first perturbed separately using a preset global sensitivity analysis method to determine the key input parameters whose sensitivity index is greater than a preset threshold based on the fluctuation of each output indicator.

[0036] Specifically, the disturbance interval of each input parameter is defined, and a disturbance sequence of each input parameter is generated using a preset random sequence generation algorithm; the disturbance values ​​in the disturbance sequence of each input parameter are input into the sewage treatment model in turn for disturbance to obtain a disturbance output index; based on the disturbance output index, a sensitivity calculation formula is used to perform sensitivity calculation on each input parameter, and the calculated sensitivity index is compared with a preset threshold value to determine the key input parameters whose sensitivity is greater than the preset threshold value among the input parameters.

[0037] In one embodiment of the present application, the global sensitivity calculation formula is expressed by the following formula:

[0038] in, For the The sensitivity index of the input parameters, is the global sensitivity disturbance change constant, M is the number of input parameters, For the The input parameters correspond to the initialization parameter values, For the The first in the disturbance sequence corresponding to the input parameter The disturbance value, For the The mean of all disturbance values ​​in the disturbance sequence corresponding to the input parameters, is the number of perturbation values ​​in the perturbation sequence corresponding to each input parameter.

[0039] Furthermore, a hysteresis disturbance model of each key input parameter is constructed.

[0040] Specifically, a statistical analysis of the disturbance output indicators is performed to identify the lag time between the disturbance of each key input parameter and the change of effluent water quality; the order of the ARMA model to be applied is initialized, and the disturbance sequence of each key input parameter and the corresponding disturbance output indicator are used as the input and output data of the model. The model parameters are estimated by the least squares method to obtain the corresponding initial lag disturbance model; based on the lag time of each key input parameter and the corresponding sensitivity index, the parameters of the corresponding initial lag disturbance model are adjusted to obtain the lag disturbance model of each key input parameter.

[0041] Among them, based on the lag time of each key input parameter and the corresponding sensitivity index, the parameters of the corresponding initial lag disturbance model are adjusted, specifically including: matching the lag time of each key input parameter with the corresponding preset order correction table to determine the order correction value corresponding to the lag time of each key input parameter, and correcting the order of the corresponding initial lag disturbance model based on the order correction value; and substituting the sensitivity index of each key input parameter into the preset weighted constant linear calculation formula to determine the parameter weighted constant of the corresponding initial lag disturbance model, so as to perform weighted calculation on the parameters of the corresponding initial lag disturbance model based on the parameter weighted constant.

[0042] In one embodiment of the present application, the weighted constant linear calculation formula is expressed by the following formula:

[0043] in, is the parameter weighting constant of the initial hysteresis disturbance model corresponding to the i-th key input parameter, is the sensitivity index of the i-th key input parameter, a , b , c is the preset weighted constant calculation coefficient, and n is the nonlinear adjustment factor used to adjust the influence of the sensitivity index on the weighted constant.

[0044] Step 104: deploy sensors at the process detection nodes corresponding to the key input parameters to collect monitoring data in the sewage treatment process in real time, and make real-time delayed effluent water quality prediction based on the monitoring data and the delayed disturbance model.

[0045] In one embodiment of the present application, after constructing the hysteresis disturbance model of each key input parameter, sensors are deployed on the process detection nodes corresponding to each key input parameter to collect monitoring data in the sewage treatment process in real time.

[0046] In one embodiment, when deploying sensors for process detection nodes corresponding to each key input parameter, it is necessary to select appropriate sensor types (such as flow meters, pressure sensors, dissolved oxygen sensors, etc.) according to the characteristics of the process detection nodes and monitoring requirements to ensure that the sensors have sufficient accuracy and stability to meet the monitoring requirements. Then, install the sensors on the selected process detection nodes and perform necessary calibration and debugging. Finally, build a data acquisition system and connect the output signals of each sensor to the data acquisition module. Through the data acquisition system, the monitoring data of each key input parameter can be obtained in real time and transmitted to the central control unit for processing and analysis.

[0047] Furthermore, real-time delayed effluent water quality prediction is performed based on monitoring data and delayed disturbance model.

[0048] Specifically, the monitoring data corresponding to each key input parameter is input into the corresponding lag disturbance model to determine the single lag water quality prediction data corresponding to each key input parameter; based on the process detection node corresponding to each key input parameter, the historical contribution index corresponding to each single lag water quality prediction data is determined, and the historical contribution index is used as the weight of each single lag water quality prediction data, and the real-time lag water quality prediction data is calculated by weighted average.

[0049] It should be noted that the historical contribution index reflects the actual impact of each key input parameter on the change of effluent water quality in the past. This index can be obtained through statistical analysis of historical data. It takes into account factors such as the frequency and amplitude of changes in each parameter and the significance of the impact on effluent water quality.

[0050] Step 105: determine whether the real-time lagged water quality prediction data exceeds the effluent water quality limit, and if it exceeds the limit, dynamically optimize and adjust the control parameters of the sewage treatment model based on a preset multi-objective optimization algorithm.

[0051] In one embodiment of the present application, after obtaining the real-time lagged water quality prediction data, it is determined whether the real-time lagged water quality prediction data exceeds the effluent water quality limit, and if it exceeds the limit, the control parameters of the sewage treatment model are dynamically optimized and regulated based on a preset multi-objective optimization algorithm. Among them, the multi-objective optimization algorithm in the embodiment of the present application is constructed based on the multi-objective particle swarm optimization algorithm.

[0052] Specifically, the real-time lagged water quality prediction data and the control parameters of the current sewage treatment model are taken as input, and iterative calculations are performed through a multi-objective optimization algorithm. When the iterative calculation reaches the preset convergence conditions, the control parameter combination is output and applied to the sewage treatment model to achieve real-time regulation of the sewage treatment process.

[0053] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, the embodiment of this application also provides an intelligent control device for the whole process of sewage treatment, whose structure is as follows: Figure 2 shown.

[0054] Figure 2 This is a schematic diagram of the internal structure of a full-process intelligent control device for sewage treatment provided in an embodiment of the present application. Figure 2 As shown, the device includes: at least one processor 201; and, a memory 202 communicatively connected to the at least one processor; The memory 202 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 201 to enable at least one processor 201 to: Obtain the basic data of the sewage treatment plant to be regulated, and build a corresponding sewage treatment model based on the basic data; the basic data includes: process data and equipment data; Based on the sewage treatment model, determine the input parameters that affect the effluent quality during sewage treatment and the output indicators used to evaluate the sewage treatment effect; Use the preset global sensitivity analysis method to perturb each input parameter respectively, so as to determine the key input parameters whose sensitivity index is greater than the preset threshold value based on the fluctuation of each output indicator, and construct the hysteresis perturbation model of each key input parameter; Sensors are deployed at the process detection nodes corresponding to each key input parameter to collect monitoring data in the sewage treatment process in real time, and real-time delayed effluent water quality prediction is performed based on the monitoring data and delayed disturbance model; Determine whether the real-time lagged water quality prediction data exceeds the effluent water quality limit, and if it exceeds the limit, dynamically optimize and adjust the control parameters of the sewage treatment model based on the preset multi-objective optimization algorithm.

[0055] Some embodiments of the present application provide corresponding Figure 1 A non-volatile computer storage medium for intelligent control of the entire process of sewage treatment, storing computer executable instructions, wherein the computer executable instructions are set as: Obtain the basic data of the sewage treatment plant to be regulated, and build a corresponding sewage treatment model based on the basic data; the basic data includes: process data and equipment data; Based on the sewage treatment model, determine the input parameters that affect the effluent quality during the sewage treatment process and the output indicators used to evaluate the sewage treatment effect; Use the preset global sensitivity analysis method to perturb each input parameter respectively, so as to determine the key input parameters whose sensitivity index is greater than the preset threshold value based on the fluctuation of each output indicator, and construct the hysteresis perturbation model of each key input parameter; Sensors are deployed at the process detection nodes corresponding to each key input parameter to collect monitoring data in the sewage treatment process in real time, and real-time delayed effluent water quality prediction is performed based on the monitoring data and delayed disturbance model; Determine whether the real-time lagged water quality prediction data exceeds the effluent water quality limit, and if it exceeds the limit, dynamically optimize and adjust the control parameters of the sewage treatment model based on the preset multi-objective optimization algorithm.

[0056] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0057] The system and medium provided in the embodiments of the present application correspond one-to-one to the method. Therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0058] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0059] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0060] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0061] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0062] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0063] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0064] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0065] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0066] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for intelligent control of the entire process of sewage treatment, characterized in that: The method comprises: Obtaining basic data of the sewage treatment plant to be regulated, and building a corresponding sewage treatment model based on the basic data; wherein the basic data includes: process data and equipment data; Based on the sewage treatment model, determine the input parameters that affect the effluent quality during the sewage treatment process and the output indicators used to evaluate the sewage treatment effect; Use the preset global sensitivity analysis method to perturb each input parameter respectively, so as to determine the key input parameters whose sensitivity index is greater than the preset threshold value based on the fluctuation of each output indicator, and construct the hysteresis perturbation model of each key input parameter; Deploy sensors at process detection nodes corresponding to each key input parameter to collect monitoring data in the sewage treatment process in real time, and perform real-time delayed effluent water quality prediction based on the monitoring data and the delayed disturbance model; Determine whether the real-time lagged water quality prediction data exceeds the effluent water quality limit, and if it exceeds the limit, dynamically optimize and regulate the control parameters of the sewage treatment model based on a preset multi-objective optimization algorithm.

2. According to claim 1, a method for intelligent control of the whole process of sewage treatment is characterized in that: The preset global sensitivity analysis method is used to perturb each input parameter respectively, so as to determine the key input parameters whose sensitivity index is greater than the preset threshold based on the fluctuation of each output indicator, including: Define the disturbance interval of each input parameter, and use the preset random sequence generation algorithm to generate the disturbance sequence of each input parameter; Inputting the disturbance values ​​in the disturbance sequence of each input parameter into the sewage treatment model in sequence for disturbance, so as to obtain a disturbance output index; Based on the disturbance output index, a preset global sensitivity calculation formula is used to perform sensitivity calculation on each input parameter, and the calculated sensitivity index is compared with the preset threshold value to determine the key input parameter whose sensitivity is greater than the preset threshold value among the input parameters.

3. The method for intelligent control of the whole process of sewage treatment according to claim 2 is characterized in that: The global sensitivity calculation formula is expressed by the following formula: in, For the The sensitivity index of the input parameters, is the global sensitivity disturbance change constant, M is the number of input parameters, For the The input parameters correspond to the initialization parameter values, For the The first in the disturbance sequence corresponding to the input parameter The disturbance value, For the The mean of all disturbance values ​​in the disturbance sequence corresponding to the input parameters, is the number of perturbation values ​​in the perturbation sequence corresponding to each input parameter.

4. The method for intelligent control of the whole process of sewage treatment according to claim 2 is characterized in that: Construct the hysteresis disturbance model of each key input parameter, including: Performing statistical analysis on the disturbance output index to identify the lag time between the disturbance of each key input parameter and the change of effluent water quality; Initialize the order of the ARMA model to be applied, and use the disturbance sequence of each key input parameter and the corresponding disturbance output index as the input and output data of the model, estimate the model parameters by the least squares method to obtain the corresponding initial lag disturbance model; Based on the lag time of each key input parameter and the corresponding sensitivity index, the parameters of the corresponding initial lag disturbance model are adjusted to obtain the lag disturbance model of each key input parameter.

5. The method for intelligent control of the whole process of sewage treatment according to claim 4 is characterized in that: Based on the lag time and corresponding sensitivity index of each key input parameter, the parameters of the corresponding initial lag disturbance model are adjusted, including: Matching the lag time of each key input parameter with the corresponding preset order correction table to determine the order correction value corresponding to the lag time of each key input parameter, and correcting the order of the corresponding initial lag disturbance model based on the order correction value; and, The sensitivity index of each key input parameter is substituted into a preset weighted constant linear calculation formula to determine the parameter weighted constant of the corresponding initial hysteresis disturbance model, so as to perform weighted calculation on the parameters of the corresponding initial hysteresis disturbance model based on the parameter weighted constant.

6. A method for intelligent control of the whole process of sewage treatment according to claim 5, characterized in that: The linear calculation formula of the weighted constant is expressed as follows: in, is the parameter weighting constant of the initial hysteresis disturbance model corresponding to the i-th key input parameter, is the sensitivity index of the i-th key input parameter, a , b , c is the preset weighted constant calculation coefficient, and n is the nonlinear adjustment factor used to adjust the influence of the sensitivity index on the weighted constant.

7. The method for intelligent control of the whole process of sewage treatment according to claim 1 is characterized in that: The real-time delayed effluent water quality prediction is performed according to the monitoring data and the delayed disturbance model, specifically including: Input the monitoring data corresponding to each key input parameter into the corresponding hysteresis disturbance model to determine the single hysteresis water quality prediction data corresponding to each key input parameter; Based on the process detection nodes corresponding to each key input parameter, the historical contribution index corresponding to each single lagged water quality prediction data is determined, and the historical contribution index is used as the weight of each single lagged water quality prediction data to calculate the real-time lagged water quality prediction data by weighted average.

8. The method for intelligent control of the whole process of sewage treatment according to claim 1 is characterized in that: The multi-objective optimization algorithm is constructed based on the multi-objective particle swarm optimization algorithm; Based on the preset multi-objective optimization algorithm, the control parameters of the sewage treatment model are dynamically optimized and regulated, specifically including: The real-time lagged water quality prediction data and the control parameters of the current sewage treatment model are used as input to perform iterative calculations through a multi-objective optimization algorithm; When the iterative calculation reaches the preset convergence condition, the control parameter combination is output and applied to the sewage treatment model to achieve real-time regulation of the sewage treatment process.

9. An intelligent control device for the whole process of sewage treatment, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; In which, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a method for intelligent control of the entire process of sewage treatment as described in any one of claims 1-8.

10. A non-volatile computer storage medium for intelligent control of the entire sewage treatment process, storing computer executable instructions, characterized in that: When the computer executable instructions are executed, a method for intelligent control of the entire sewage treatment process as described in any one of claims 1 to 8 is implemented.

Images