A water treatment agent dosing control method and control system

Abstract

The present application relates to the field of water treatment technology, and is a dosing control scheme, specifically to a dosing control method and control system for water treatment agents. By predicting the water quality of the incoming water, water quality data about the water to be treated is obtained, and the water quality data is used as a key parameter to obtain the corresponding predicted amount of agent dosage, and based on this predicted amount and the changes in the water body target data and the water quality during the dosing process, the feedback control weight and the feedforward control weight are determined, and the feedback control weight and the feedforward control weight are combined to obtain the dosing control amount. The control method provided in the embodiment of the present application can achieve accurate determination of the control amount based on the water quality and the overall environmental changes of the water treatment system. Compared with the single control logic in the prior art, it increases the accuracy of the overall control and can solve the problems of complex water treatment systems and inaccurate environmental control.

Description

Technical Field

[0001] The present application relates to the field of water treatment technology, and is a dosing control scheme, specifically to a dosing control method and control system for water treatment agents. Background Art

[0002] While automated control technology has become widespread in the industrial sector, research on automated control of the dosing process in sewage treatment plants is still limited. Existing technologies primarily focus on implementing dosing through empirical formulas. This low level of automated dosing results in energy waste and hinders further improvements in sewage treatment plants. Summary of the Invention

[0003] To address the above technical issues, this application provides a water treatment agent dosing control method and control system. By collecting multiple physical and chemical data of the incoming water and determining the water quality information of the water body to be treated, the amount of agent added is precisely controlled based on the water quality information and the key indicators of the current water body being treated. To achieve the above objectives, the technical solutions adopted in the embodiments of the present invention are as follows:

[0004] In a first aspect, a method for controlling the dosing of water treatment agents is provided, which is applied to a water treatment system. The water treatment system includes at least one biological pool and a dosing pump. The biological pool is connected to a water inlet pipe, and multiple sensors are provided in the water inlet pipe and the biological pool. The multiple sensors are used to obtain multiple physical and chemical data and target indicator data. The method includes: based on the physical and chemical data of the water to be treated to be fed into the biological pool, online water quality detection is performed according to the physical and chemical data to obtain water quality data about the water to be treated; the physical and chemical data include conductivity, pH value, flow rate, temperature, ammonia content and suspended solids. any one or more of the solid amount, the water quality data includes any one or more of the dissolved chemical oxygen demand, phosphate content and carbon-nitrogen ratio; determining the predicted dosage of the agent based on the multiple water quality data and target index data; determining the initial frequency of the dosing pump based on the predicted dosage of the agent, and determining the error value between the real-time target index data and the set index data, determining the feedback frequency of the dosing pump through the error value, determining the target frequency based on the initial frequency and the feedback frequency, and controlling the dosing pump to dosing based on the target frequency; the real-time target index data is obtained based on the gradient time.

[0005] In some specific implementations, the obtained conductivity, pH value, temperature, flow rate, and suspended solids amount are weightedly summed with corresponding weights to obtain the dissolved chemical oxygen demand.

[0006] In some specific implementations, the obtained conductivity, pH value, temperature, flow rate, suspended solids content, ammonia content, and dissolved chemical oxygen demand are weightedly summed with corresponding weights to obtain the phosphate content.

[0007] In some specific implementations, the obtained conductivity, pH value, temperature, flow rate, suspended solids content, and phosphate content are weightedly summed with corresponding weights to obtain the carbon-nitrogen ratio.

[0008] In some specific implementations, determining the predicted dosage of the agent based on the multiple water quality data and the target indicator data includes: determining the weight values corresponding to the multiple water quality data based on the type of the target indicator data, updating the water quality data based on the weight values, and inputting the updated multiple water quality data and the target indicator data into the trained convergent agent prediction model to obtain the predicted dosage of the agent.

[0009] In some specific implementations, the drug prediction model is a feedforward neural network model constructed by an input layer, a hidden layer, and an output layer, and the weight value between the hidden layer and the output layer and the center width vector of the Gaussian basis function are optimized by a genetic algorithm, and the initial network structure and parameters are adjusted based on the optimized parameters, and training is performed until convergence based on the adjusted drug prediction model.

[0010] In some specific implementations, the gradient time is a time setting in which the sampling interval time gradually decreases, and real-time target indicator data of the water body is obtained based on the sampling interval time.

[0011] In some specific implementations, the initial frequency of the dosing pump is determined based on the dosing pump flow rate and the liquid volume of the dosing pump, and the dosing pump flow rate is determined based on the drug concentration, the predicted drug dosage, and the flow rate.

[0012] In some specific implementations, determining the target frequency based on the initial frequency and the feedback frequency includes: combining the initial frequency and the feedback frequency by a combined weight of the initial frequency and the feedback frequency; the combined weight is determined based on the change in water quality data per unit time and real-time target indicator data.

[0013] In a second aspect, a dosing control system is provided, which is applied to a water treatment system, wherein the water treatment system includes at least one biological pool and a dosing pump, the biological pool is connected to a water inlet pipe, and a plurality of sensors are provided in the water inlet pipe and the biological pool; the control system is electrically connected to the plurality of sensors and the dosing pump, controls the plurality of sensors and the dosing pump, and obtains a plurality of physical and chemical data and target index data collected by the plurality of sensors; the control system includes: a data processing device for performing online water quality detection based on the physical and chemical data to obtain water quality data about the water to be treated; a prediction device for determining a predicted dosage of the agent based on the plurality of water quality data and target index data; a control output device for obtaining an initial frequency and a feedback frequency, and determining a target frequency based on the initial frequency and the feedback frequency, and using the target frequency as a control output.

[0014] In the technical solution provided by the embodiment of the present application, the water quality data of the water to be treated is obtained by predicting the water quality of the incoming water, and the water quality data is used as a key parameter to obtain the corresponding predicted amount of the drug to be dosed. Based on this predicted amount and the changes in the water body target data and the changes in the water quality during the dosing process, the feedback control weight and the feedforward control weight are determined, and the feedback control weight and the feedforward control weight are combined to obtain the control amount for dosing. The control method provided by the embodiment of the present application can accurately determine the control amount based on the water quality and the overall environmental changes of the water treatment system. Compared with the single control logic in the prior art, it increases the accuracy of the overall control and can solve the problems of complex water treatment systems and inaccurate environmental control. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0016] The methods, systems, and / or programs in the accompanying drawings will be further described according to exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments, wherein example numerals represent similar structures in the various views of the drawings.

[0017] Figure 1 It is a schematic diagram of the structure of the water treatment system provided in the embodiment of the present application.

[0018] Figure 2 This is a flow chart of the dosing control method provided in an embodiment of the present application.

[0019] Figure 3It is a schematic diagram of the control system structure provided in an embodiment of the present application.

[0020] Figure 4 This is a schematic diagram of the terminal device structure provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to better understand the above technical solution, the technical solution of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0022] In the following detailed description, numerous specific details are set forth by way of example in order to provide a thorough understanding of the relevant teachings. However, it will be apparent to one skilled in the art that the present application can be practiced without these details. In other instances, well-known methods, procedures, systems, compositions, and / or circuits have been described at a relatively high level, without detail, to avoid unnecessarily obscuring aspects of the present application.

[0023] Flowcharts are used in this application to illustrate the execution processes performed by the system according to the embodiments of the present application. It should be clearly understood that the execution processes of the flowcharts may not be executed in sequence. Instead, these execution processes may be executed in reverse order or simultaneously. In addition, at least one additional execution process may be added to the flowchart. One or more execution processes may be deleted from the flowchart.

[0024] Before further explaining the embodiments of the present invention in detail, the nouns and terms involved in the embodiments of the present invention are explained. The nouns and terms involved in the embodiments of the present invention are subject to the following interpretations.

[0025] (1) In response to, it is used to indicate the conditions or states on which the executed operations depend. When the dependent conditions or states are met, one or more operations executed may be in real time or with a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations executed are executed.

[0026] (2) Based on, used to indicate the conditions or states on which the executed operations depend. When the dependent conditions or states are met, one or more operations executed may be in real time or with a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations executed are executed.

[0027] The embodiment of the present application provides a drug dosing control system applied to a water treatment system, for accurately controlling the amount of drug required to be added during the water treatment process.

[0028] Generally speaking, the sewage treatment process is divided into three stages. The first stage primarily utilizes physical methods to remove insoluble solids from the sewage. Methods such as sedimentation, filtration, flotation, and centrifugation are used to remove suspended solids and other substances such as floating oil through screen filtration, settling, and centrifugation. The second stage typically uses biological treatment methods. After secondary treatment, some residual substances, such as nitrogen, phosphorus, and difficult-to-degrade soluble compounds and pathogens, remain. After secondary treatment, sewage does not meet higher discharge standards. Direct discharge could pollute rivers with weaker dilution capacity and cannot be used for tap water or industrial water replenishment. Tertiary treatment further removes pollutants not removed by secondary treatment, such as difficult-to-degrade organic and inorganic pollutants, nitrogen, and phosphorus. Based on secondary treatment, chemical, physical, and chemical methods are used to further treat these remaining pollutants. While tertiary treatment consumes significant resources, it effectively utilizes water resources. Hazardous substances, such as harmful bacteria, may still be present in sewage after tertiary treatment. Ultraviolet disinfection and ozone disinfection can kill these harmful bacteria and prevent the discharged sewage from contaminating clean water sources.

[0029] The water treatment system of the embodiment of the present application is a secondary or tertiary process of the above treatment. For details about this water treatment system, please refer to Figure 1 The water treatment system 100 includes at least one biological pool, which is used to implement the aforementioned secondary or tertiary treatment process. The secondary biological pool is preferably selected as the target biological pool in this embodiment. Of course, in other embodiments, the water treatment system may have other multi-stage structures, and the biological pool may be any biological pool in any of the other multi-stage structures that requires dosing treatment.

[0030] The biological pool is equipped with a dosing pump 110 for dosing the biological pool. The biological pool is connected to an external water source via an inlet pipe, and the external water source is drained into the biological pool via the inlet pipe. The dosing process of the dosing pump is a key link in the water treatment process. The content of the added drug determines the water treatment effect. When the added drug content is too low, the required water treatment results cannot be achieved. When the added drug content is too high, not only will it cause waste of drugs, but it will also cause biological and chemical changes in the original water body, thereby reducing the effect of water treatment. Therefore, how to achieve precise control of the amount of drug added is a key technology in current water treatment technology.

[0031] In existing technology, water quality control relies on manual adjustments to the dosage of chemicals, often relying on the experience of technicians. Technicians take samples and observe the water quality indicators of the raw water after the chemicals are added, combining historical dosage data and personal experience to determine the appropriate dosage. They can also statistically analyze historical production data to develop a comparison table comparing water quality and chemical consumption, and then determine the dosage based on actual conditions. This method relies heavily on the judgment and control of experienced technicians, resulting in high labor costs and the risk of chemical waste. With the advancement of automation, automated control methods are now being adopted in some water treatment scenarios to achieve precise drug dosing. Generally, existing automated dosing methods employ a dynamic adjustment process, monitoring specific sampling points in real time. The actual values detected are compared with pre-set target values to determine the deviation between the two. Based on this deviation, the corresponding control output is calculated to achieve precise adjustment of the drug dosage. For this method, after the drug is added, the water body needs to go through a more complicated treatment process and the lag time corresponding to this process is relatively long. When the water quality or flow rate changes significantly, this control method cannot adjust the dosage of the drug in time. Although this method solves the problem of inaccurate control of drug dosage based on manual experience, its control accuracy needs to be improved during actual use.

[0032] In view of the above technical background, in order to solve the problem of inaccurate control of drug dosage in the prior art, the embodiment of the present application is further configured with a dosing control system 120 in the above water treatment system for accurately controlling the dosage. Specifically, for the added dosing control system, multiple sensors 130 are respectively provided in the water inlet pipe and the biological pool in the water treatment system, which are respectively used to obtain multiple physical and chemical data and target indicator data, and transmit the above data to the dosing control system as the input source of the dosing control system. The dosing control method is configured in the dosing control system to determine the real-time dosage of the current water treatment system and the frequency corresponding to the dosing pump, and this frequency is sent to the dosing pump to realize dosing control.

[0033] It is worth noting that sewage treatment is a complex process involving multiple aspects, including physical, biological and chemical reactions. This complexity is mainly reflected in several aspects: First, these reactions are usually nonlinear, which makes it difficult to establish an accurate model. Second, there are many uncertainties, such as fluctuations in influent water quality and changes in the operating status of treatment equipment, which increase the challenge of establishing an accurate model. Third, the operating status of the sewage treatment system changes over time, including fluctuations in influent water quality and aging maintenance of treatment equipment, which makes it impossible for static models to accurately describe the dynamic behavior of the system. In addition, there is a certain time lag in the sewage treatment process, which makes real-time monitoring and control more difficult.

[0034] In summary, in order to achieve accurate dosing control, the control model of the control system provided in this embodiment needs to take the influent water quality data as an important input indicator, and also needs to take the changes in the water body during the process as the key disturbance factor in the overall control process.

[0035] Therefore, the sensors in the water inlet pipe and the bio-tank in this embodiment are configured differently, and the data collected is also different. The sensor in the water inlet pipe collects water quality data related to the incoming water, while the sensor in the bio-tank collects water data within the bio-tank that indicates whether discharge standards have been met. This means that, in this embodiment, water quality information is determined before drug administration and the dosage is determined based on this water quality information. During the drug administration process, water data from the bio-tank is collected to determine whether discharge standards have been met. This water data and water quality information are linearly combined to determine the dosage adjustment, which is then adjusted.

[0036] In another embodiment, the specific process of the dosing control method provided in this embodiment can be referred to. Figure 2 , including the following steps:

[0037] Step S21 . Based on the acquired physicochemical data of the water to be treated to enter the biological pool, online water quality testing is performed according to the physicochemical data to obtain water quality data about the water to be treated.

[0038] In general, for the automated control process, the key parameters of the current environment are collected, and the compensation amount is determined based on the difference between the key parameters and the key parameters corresponding to the control target, and the change in the control amount is determined based on the compensation amount. In a single environment, because the disturbance factors are low, the changes in the system are linear or close to linear, so the changes in the system can be inferred based on the changes in the key parameters. However, in the water treatment scenario, the changes in the key parameters in the water body are affected by multiple factors, and the changes in the influencing factors cannot be inferred. If the control parameters of the system are inferred based solely on the changes in the key parameters, it will cause problems such as inaccurate system control and high latency.

[0039] Therefore, in order to improve the accuracy of drug dosing control in this embodiment, it is necessary to obtain the water quality information of the current water body to be treated, and introduce the water quality information into the subsequent reasoning process, thereby improving the accuracy of obtaining control parameters.

[0040] Specifically, the physical and chemical data include any one or more of conductivity, pH value, flow rate, temperature, ammonia content and suspended solids; the water quality data include any one or more of dissolved chemical oxygen demand, phosphate content and carbon-nitrogen ratio.

[0041] Among them, online measurement of the chemical oxygen demand (COD) of the water body is very important. However, in actual operation, the neglect of online detection of the dissolved chemical oxygen demand (SCOD) of the water body leads to the failure to fully utilize the COD in the raw water, thereby affecting the accuracy of subsequent chemical addition. The phosphate quality index in the influent water body is an important indicator that needs to be monitored during operation. Reasonable and accurate estimation of the influent phosphate concentration not only facilitates managers to understand the influent water quality status in a timely manner, but also helps to evaluate the biodegradability of the wastewater. The influent carbon-nitrogen ratio (C / N) is a key parameter that affects the addition of chemicals in the wastewater treatment denitrification process. It has a direct impact on the dosing strategy through multiple dimensions such as microbial metabolic needs, denitrification efficiency and economy. Different influent sources have different carbon-nitrogen ratios in the water body, so it is necessary to test the carbon-nitrogen ratio in the influent water body to determine the specific content in the water body.

[0042] Existing methods for detecting these water quality data require manual sampling, filtration, and chemical analysis of the water, or the use of a TP online analyzer, if using online analysis methods. However, this process typically takes 15-30 minutes, making it difficult to meet the requirements for real-time monitoring of SCOD, phosphate content, and carbon-nitrogen ratio in incoming water using existing detection methods.

[0043] In this embodiment, a detection model is established by means of multiple linear regression to determine the above water quality data, and online detection is implemented based on the detection model.

[0044] Specifically, the SCOD detection is performed by weighted summing the collected conductivity, pH value, temperature, flow rate, and suspended solids content with corresponding weights to obtain the final result. The weights corresponding to the above-mentioned physical and chemical data are obtained based on linear regression during the training process of the detection model. In one embodiment, the training method obtains multiple sets of the above-mentioned physical and chemical data, classifies the multiple sets of data into training samples and calibration samples, uses multiple linear regression analysis, and fits the results to obtain a multiple linear regression model corresponding to SCOD, which is expressed based on the following formula: SCOD = flow rate * 0.0271 + pH * 6.4424 + conductivity * 0.0091 + temperature * 1.7274 + suspended solids content * 0.1339 - 95.603.

[0045] Similarly, the results of phosphate content and carbon-nitrogen ratio are also obtained by constructing corresponding detection models based on multiple linear regression, and the weight values corresponding to the physical and chemical data are configured in this detection model. But the difference is that the physical and chemical data between phosphate content and carbon-nitrogen ratio and between SCOD are different. Among them, the physical and chemical data input into the multiple linear regression detection model for phosphate content include conductivity, pH value, temperature, flow rate, suspended solids and ammonia content; and, in the detection of phosphate content, dissolved chemical oxygen demand is also required as a reference variable. For the multiple linear regression detection model of phosphate, it is expressed based on the following formula: PO 3- 4==10.1583-0.0094*SCOD+0.0003*flow-2.2928*pH+0.0027*conductivity+0.1888*temperature-0.0028*suspended solids+0.0593*ammonia content. For the carbon-nitrogen ratio, the physical and chemical data input into the two multivariate linear regression detection models include conductivity, pH value, temperature, flow rate and suspended solids. In addition, phosphate needs to be used as a reference variable in the detection of carbon-nitrogen ratio content. For the multi-source linear regression detection model of carbon-nitrogen ratio, it is based on the following formula: C / N=12.4843+0.0007*flow+7.7775*pH-0.0048*conductivity+0.0314∗suspended solids-0.4178*temperature-11.0004*PO 3- 4.

[0046] Step S22: Determine the predicted dosage of the drug based on the plurality of water quality data and target indicator data.

[0047] In this embodiment, multiple water quality data sets are acquired in step S21. However, in water treatment scenarios, different treatment processes and objectives vary across different treatment stages, and different types of water quality data have different impacts, leading to different requirements for the dosage of the drug. Therefore, it is necessary to optimize the water quality data based on different water treatment requirements to obtain the final predicted dosage of the drug.

[0048] Specifically, in this embodiment, it is necessary to determine the weight values corresponding to multiple water quality data according to the type of target indicator data, and update the water quality data according to the weight values, and use the updated multiple water quality data and target indicator data as input to determine the predicted dosage of the agent.

[0049] In one embodiment, the determination of the predicted dosage of the drug is obtained by adopting a drug prediction model. Among them, the drug prediction model is a feedforward neural network model constructed by an input layer, a hidden layer and an output layer. Regarding the processing process of the feedforward neural network model, the updated dissolved chemical oxygen demand, phosphate content, carbon-nitrogen ratio and target index data are transmitted to the input layer, the above data are normalized in the input layer, the features are scaled to the [0,1] interval, and the Gaussian kernel function is used as the dimensional activation function to map the input layer to a series of radial basis functions of the hidden layer to obtain nonlinear features, and the nonlinear features are converted to output features by the weights in the network. Among them, the output feature is the predicted value of the drug dosage, that is, the predicted drug dosage.

[0050] The accuracy of the prediction results of the neural network model is achieved by optimizing the key parameters of the model. In order to improve the prediction accuracy of the neural network model in this embodiment, a genetic algorithm is used as an optimization method.

[0051] Specifically, the two parameters, the initial Gaussian basis function width vector and the weight value between the hidden layer and the output layer, are converted into corresponding binary mixed codes through binary coding. The converted binary codes are then XORed vertically to obtain new numerical values to generate special binary codes. The fitness of the generated special binary codes is calculated based on the fitness function, and the fitness is determined based on whether the fitness meets the population requirements or the iteration limit. If the population requirements or the iteration limit are met, the current parameters are the optimal parameters. If the above conditions are not met, the roulette wheel method is used to retain the individuals corresponding to the parameters with the highest fitness. Parameter crossover is performed on the selected individuals to generate new parameter combinations. The new parameter combinations are amplified by setting random probabilities to adjust the Gaussian basis function width vector and the weight value between the hidden layer and the output layer. The amplified new parameter combinations are iterated until the above termination conditions are met and the optimal parameter combination is output as the target parameter. The neural network model is optimized based on this target parameter.

[0052] A genetic algorithm is used to generate new parameter combinations by crossover of individual parameters. Specifically, after initial selection via the roulette wheel method, the parent generation begins generating new offspring through initial adaptive crossover and mutation. The adaptive crossover and mutation probabilities continuously change with the fitness of the offspring in the population, resulting in the initial crossover probability, mutation probability, and new offspring crossover probability. Two mutant offspring individuals are obtained by randomly selecting two parents from the optimized parent population and performing crossover selection and mutation selection. The fitness of the mutant offspring chromosomes is compared with that of the parent chromosomes. If the offspring's fitness is better than that of the parent, the offspring and parent are replaced and incorporated into population P to form a new population for repeated iterative evolution. Crossover and mutation generate two daughter chromosomes. Each individual in the population can be used as an independent computational unit to perform parallel computational optimization during the crossover and mutation processes, achieving multi-objective parallel optimization, thereby shortening the search process and obtaining the optimal individual.

[0053] Step S23. Determine the initial frequency of the dosing pump based on the predicted dosage of the drug, and determine the error value between the real-time target index data and the set index data, determine the feedback frequency of the dosing pump through the error value, determine the target frequency based on the initial frequency and the feedback frequency, and control the dosing pump to dosing based on the target frequency.

[0054] In this embodiment, the real-time target indicator data is acquired based on the gradient time, wherein the gradient time is a time setting in which the sampling interval time gradually decreases.

[0055] Specifically, the sampling interval refers to the time interval for the sensor to send back data. In addition, it is worth noting that the setting for the gradient time is set during a complete water treatment process. A complete water treatment process means that the volume of the currently treated water body is the water storage volume of the biological pool, that is, the volume of the water body treated can be determined by the outlet flow rate and time, with the first water inflow as the node; the start of drug administration can also be used as the node to determine the volume of water body treated during the drug administration process. The reason for this setting is that with the change of the dosage and time of the drug input, the change of the target indicator data in the water body intensifies. In order to ensure the accuracy of control, the sampling frequency of the target indicator data based on the intensified change should be increased.

[0056] In this embodiment, a feedforward controller and a feedback controller are combined to control drug administration.

[0057] Specifically, the feedforward controller receives the predicted dosage amount obtained in step S22 as input, which determines the initial frequency of the dosing pump. The feedback controller receives the error between the real-time target indicator data collected based on the gradient time and the set indicator data, and determines the feedback frequency of the dosing pump based on this error. Finally, the initial frequency and the feedback frequency are linearly combined to obtain the target frequency, which is then used to control the dosing pump to deliver the dosage.

[0058] The initial frequency of the dosing pump is determined based on the dosing pump flow rate and the liquid volume of the dosing pump, and is calculated based on the following formula: ,in is the flow rate of the dosing pump, and C is the volume of the agent per stroke; the flow rate of the dosing pump is determined based on the agent concentration, the predicted amount of the agent and the flow rate, and is calculated based on the following formula: ; Where y is the predicted dosage of the drug, is the influent water flow rate, and D is the reagent concentration.

[0059] In one embodiment, the input to the feedback controller can be the error between the real-time target index data and the set index data. The controller can be constructed based on a PID controller. The controller updates the proportional coefficient, integral time, and differential time based on the error value to obtain a corresponding control variable. This control variable is the feedback frequency of the dosing pump. The set index data refers to data that meets the drainage requirements.

[0060] It is worth noting that the disturbances caused by different water qualities in the overall dosing system are also different, and the reaction time of the processing process is also different. It takes a certain time lag from the generation of the disturbance to the formation of obvious deviations, which makes it difficult for the feedback controller to respond quickly. Therefore, in this embodiment, feedforward control and feedback control are combined, and the weight of feedback control is adjusted according to the changes in water quality to quickly respond to the interference caused by changes in water quality. Specifically, when the water quality changes significantly, the weight of feedback control is reduced and the weight of feedforward control is increased; when the water quality is relatively stable, the feedforward weight is reduced and the feedback weight is increased to ensure that the effluent water quality is more stable.

[0061] Among them, the linear combination of feedforward control and feedback control is expressed based on the following formula: ;Where w is the target frequency, a is the weight coefficient, v is the feedforward output frequency, and u is the feedback output frequency.

[0062] In one possible implementation, the weight coefficient is adjusted based on the change in water quality data, and the adjustment method is expressed based on the following formula: ,in and are the dissolved chemical oxygen demand at the current moment and the previous moment respectively, and are the phosphate content at the current moment and the previous moment respectively, and are the carbon-nitrogen ratios at the current moment and the previous moment, respectively; k, l, and m are adjustment coefficients, which are 0.05 / 0.02 and 0.03, respectively, in this embodiment.

[0063] The embodiment of the present application provides a method for controlling the dosing of water treatment agents, which predicts the water quality of the incoming water to obtain water quality data about the water to be treated, and uses the water quality data as a key parameter to obtain the corresponding predicted amount of agent to be added, and determines the feedback control weight and feedforward control weight based on the predicted amount and the changes in the water body target data and water quality during the dosing process, and combines the feedback control weight and feedforward control weight to obtain the control amount for dosing. The control method provided in the embodiment of the present application can accurately determine the control amount based on the water quality and the overall environmental changes of the water treatment system, which increases the accuracy of the overall control compared to the single control logic in the prior art, and can solve the problems of complex water treatment systems and inaccurate environmental control.

[0064] In another embodiment, see Figure 3 The dosing control system 120 in this embodiment includes:

[0065] A data processing device 121 is used to perform online water quality testing based on the physical and chemical data to obtain water quality data about the water to be treated;

[0066] Prediction device 122, used for determining the predicted dosage of the agent based on the plurality of water quality data and target indicator data;

[0067] The control output device 123 is used to obtain an initial frequency and a feedback frequency, and determine a target frequency based on the initial frequency and the feedback frequency, and use the target frequency as a control output.

[0068] See Figure 4The above method can also be integrated into the provided terminal device 400. In view of the fact that the device may have relatively large differences due to different configurations or performance, it can include one or more processors 401 and memory 402. The memory 402 can store one or more applications or data. Among them, the memory 402 can be a temporary storage or a persistent storage. The application stored in the memory 402 can include one or more modules (not shown in the figure), each of which can include a series of computer-executable instructions in the terminal device. Furthermore, the processor 401 can be configured to communicate with the memory 402, and the terminal device can execute the series of computer-executable instructions in the memory 402. The terminal device can also include one or more power supplies 403, one or more wired / wireless network interfaces 404, one or more input / output interfaces 405, one or more keyboards 406, etc.

[0069] In a specific embodiment, the terminal device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions in the terminal device, and the one or more programs are configured to be executed by one or more processors, including computer-executable instructions for performing the following:

[0070] Based on the acquired physicochemical data of the water to be treated that is to enter the biological pool, online water quality testing is performed according to the physicochemical data to obtain water quality data about the water to be treated;

[0071] Determining a predicted dosage of the agent based on the plurality of water quality data and target indicator data;

[0072] The initial frequency of the dosing pump is determined based on the predicted dosage of the medicine, and the error value between the real-time target index data and the set index data is determined. The feedback frequency of the dosing pump is determined by the error value. The target frequency is determined based on the initial frequency and the feedback frequency. The dosing pump is controlled to perform dosing based on the target frequency.

[0073] The following is a detailed introduction to the various components of the processor:

[0074] In this embodiment, the processor is an application specific integrated circuit (ASIC), or is configured to implement one or more integrated circuits of the embodiments of the present application, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (FPGAs).

[0075] Optionally, the processor can execute various functions by running or executing the software program stored in the memory and calling the data stored in the memory, such as executing the above Figure 2 The method shown.

[0076] In a specific implementation, as an embodiment, the processor may include one or more microprocessors.

[0077] The memory is used to store the software program for executing the solution of the present application, and the execution is controlled by the processor. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0078] Alternatively, the memory may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, a random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and capable of being accessed by a computer, but is not limited thereto. The memory may be integrated with the processor or exist independently and be coupled to the processing unit through the processor's interface circuit, and this is not specifically limited in the embodiments of the present application.

[0079] It should be noted that the structure of the processor shown in this embodiment does not constitute a limitation on the device. The actual device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0080] In addition, the technical effects of the processor can refer to the technical effects of the method described in the above method embodiment, and will not be repeated here.

[0081] It should be understood that the processor in the embodiments of the present application may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0082] In this application, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0083] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0084] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0085] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0086] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0087] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0088] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0089] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0090] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for controlling the dosing of water treatment agents, characterized in that: Applied to a water treatment system, the water treatment system includes at least one biological pool and a dosing pump, the biological pool is connected to a water inlet pipe, and multiple sensors are provided in the water inlet pipe and the biological pool, the multiple sensors are used to obtain multiple physical and chemical data and target indicator data; the method includes: Based on the acquired physicochemical data of the water to be treated to be introduced into the biological pool, online water quality testing is performed according to the physicochemical data to obtain water quality data about the water to be treated; the physicochemical data includes any one or more of conductivity, pH value, flow rate, temperature, ammonia content, and suspended solids content; the water quality data includes dissolved chemical oxygen demand, phosphate content, and carbon-nitrogen ratio; the water quality data is determined by establishing a detection model through a multivariate linear regression method, and online detection is performed based on the detection model; Determining a predicted dosage of a drug based on the plurality of water quality data and the target indicator data, comprising: determining weight values corresponding to the plurality of water quality data based on the type of the target indicator data, updating the water quality data based on the weight values, and inputting the updated plurality of water quality data and the target indicator data into a drug prediction model trained to convergence to obtain the predicted dosage of the drug, wherein the drug prediction model is a feedforward neural network model constructed by an input layer, a hidden layer, and an output layer; Determining the initial frequency of the dosing pump based on the predicted dosage of the medicine, determining an error value between real-time target index data and set index data, determining a feedback frequency of the dosing pump based on the error value, determining a target frequency based on the initial frequency and the feedback frequency, and controlling the dosing pump to dosing based on the target frequency, including: combining the initial frequency and the feedback frequency using a combined weight of the initial frequency and the feedback frequency, wherein the combined weight is expressed based on the following formula: ,in and are the dissolved chemical oxygen demand at the current moment and the previous moment respectively, and are the phosphate content at the current moment and the previous moment respectively, and are the carbon-nitrogen ratios at the current moment and the previous moment respectively, k, l and m are adjustment coefficients respectively; the real-time target index data is obtained based on the gradient time.

2. The water treatment agent dosing control method according to claim 1, characterized in that: The obtained conductivity, pH value, temperature, flow rate and suspended solid amount are weightedly summed with corresponding weights to obtain the dissolved chemical oxygen demand.

3. The water treatment agent dosing control method according to claim 2, characterized in that: The obtained conductivity, pH value, temperature, flow rate, suspended solids content, ammonia content and dissolved chemical oxygen demand are weightedly summed with corresponding weights to obtain the phosphate content.

4. The water treatment agent dosing control method according to claim 3, characterized in that: The obtained conductivity, pH value, temperature, flow rate, suspended solids content and phosphate content are weightedly summed with corresponding weights to obtain the carbon-nitrogen ratio.

5. The water treatment agent dosing control method according to claim 1, characterized in that: The weight values between the hidden layer and the output layer and the center width vector of the Gaussian basis function are optimized by genetic algorithm, and the initial network structure and parameters are adjusted based on the optimized parameters, and the adjusted drug prediction model is trained until convergence.

6. The water treatment agent dosing control method according to claim 1, characterized in that: The gradient time is a time setting in which the sampling interval time gradually decreases, and real-time target indicator data of the water body is obtained based on the sampling interval time.

7. The water treatment agent dosing control method according to claim 1, characterized in that: The initial frequency of the dosing pump is determined based on the dosing pump flow rate and the liquid volume of the dosing pump, and the dosing pump flow rate is determined based on the drug concentration, the predicted drug dosage, and the flow rate.

8. A dosing control system, characterized in that: Applicable to a water treatment system, the water treatment system includes at least one biological pool and a dosing pump, the biological pool is connected to a water inlet pipe, and multiple sensors are provided in the water inlet pipe and the biological pool; the control system is electrically connected to the multiple sensors and the dosing pump, controls the multiple sensors and the dosing pump, and obtains multiple physical and chemical data and target indicator data collected by the multiple sensors, and executes the water treatment agent dosing control method according to any one of claims 1 to 7, the control system comprising: A data processing device, configured to perform online water quality testing based on the physical and chemical data to obtain water quality data on the water to be treated; A prediction device, configured to determine a predicted dosage of a pharmaceutical agent based on the plurality of water quality data and target indicator data; The control output device is used to obtain an initial frequency and a feedback frequency, and determine a target frequency based on the initial frequency and the feedback frequency, and use the target frequency as a control output.

Images