Method, system and equipment for controlling sludge in activated sludge process

Abstract

The invention relates to a sludge control method, system and equipment for an activated sludge process, and the method comprises the steps: monitoring the state fluctuation of observation data, and judging whether a control parameter needs to be regulated or controlled according to a stable threshold value; if the observation data exceed a stable threshold range, responding to the state fluctuation of the observation data through an algorithm model, dynamically regulating and controlling the sludge reflux ratio, evaluating control parameters, and outputting model evaluation indexes; the control parameters are analyzed based on the model evaluation indexes, optimal control distribution is determined, then the control reference parameters are updated, and the sludge reflux ratio is recalculated; and if the observation data is within the stable threshold range, maintaining the dynamically regulated control parameters so as to carry out steady-state regulation. According to the invention, through the combination of multi-dimensional data monitoring, real-time monitoring and early warning, dynamic regulation and steady state control, efficient, stable and low-cost operation of the sewage plant is ensured, and powerful technical support is provided for optimization control of the sewage plant.

Description

Technical Field

[0001] The present invention relates to the technical field of water treatment, and in particular to a method, system and equipment for controlling sludge in an activated sludge process. Background Art

[0002] In the current sewage treatment process, the control of return sludge has been realized by remote operation, which is a technical advancement and improves the convenience and efficiency of the treatment process. However, in terms of quantity control, the existing technical methods still mainly rely on manual experience adjustment, or operate according to a preset fixed amount. Although this method is simple and easy to implement, it has obvious disadvantages.

[0003] Since the water quality and quantity of the sewage treatment plant's influent change in real time with time and seasons, this dynamic change places higher demands on the precise control of the sludge return volume. It is difficult to respond to these real-time changes in a timely and accurate manner simply by relying on manual experience. Especially in the case of sudden changes in sewage load, if the relevant parameters are not adjusted in time, it may lead to production safety accidents, which is a risk that cannot be ignored.

[0004] In addition, completely relying on manual parameter adjustment not only increases the labor intensity of operators, but also requires operators to have a high level of professional skills. This, to a certain extent, limits the automation and intelligence level of the sewage treatment process, and also increases labor costs and safety risks.

[0005] Therefore, the existing sludge return flow control methods have obvious deficiencies in real-time, safety and automation, and are in urgent need of improvement. Summary of the invention

[0006] 1. Technical issues to be resolved

[0007] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides a method, system and equipment for controlling sludge in an activated sludge process, which solves the technical problems that the existing sludge return flow control method has obvious deficiencies in real-time performance, safety and automation.

[0008] (II) Technical solution

[0009] In order to achieve the above object, the main technical solutions adopted by the present invention include:

[0010] In a first aspect, an embodiment of the present invention provides a method for controlling sludge in an activated sludge process, comprising:

[0011] Receive and process input observation data of multiple dimensions of sewage treatment plants;

[0012] Continuously monitor the state fluctuations of observation data in each dimension, and determine whether the currently configured control parameters need to be adjusted based on the pre-adapted stability threshold;

[0013] If the observed data exceeds the pre-adapted stable threshold range, the built-in algorithm model responds to the state fluctuation of the observed data, dynamically adjusts the sludge return ratio, and evaluates the currently configured control parameters in combination with the actual working conditions, and outputs the model evaluation indicators;

[0014] Based on the model evaluation indicators, the control parameters are analyzed regularly or in real time to determine the optimal control distribution, the control benchmark parameters of the model are updated according to the optimal control distribution, and the sludge return ratio is recalculated and optimized;

[0015] If the observed data is within the pre-adapted stable threshold range, the control parameters after the previous round of dynamic regulation are maintained, and the frequency converter is automatically controlled by setting the return flow of the return sludge pump to perform steady-state regulation.

[0016] Optionally, continuously monitoring the state fluctuations of the observation data in each dimension and judging whether the currently configured control parameters need to be adjusted according to the pre-adapted stability threshold value include:

[0017] Conduct statistical analysis on the observation data of each dimension of continuous monitoring, and calculate the mean square error data of the observation data of each dimension including time, day, week and month;

[0018] For each observation data, one or more stability thresholds are preset according to the data characteristics and system control requirements;

[0019] By comparing the calculated mean square error data with the preset stability threshold, the result of the state fluctuation analysis is output;

[0020] Based on the results of the state fluctuation analysis, determine whether the control parameters of the current configuration need to be adjusted;

[0021] If there is at least one mean square error data exceeding the corresponding stability threshold, the dynamic control mechanism is triggered.

[0022] Optionally, if the observed data exceeds the pre-adapted stable threshold range, the built-in algorithm model responds to the state fluctuation of the observed data, dynamically adjusts the sludge return ratio, and evaluates the currently configured control parameters in combination with the actual working conditions. The output model evaluation indicators include:

[0023] If any monitored observation data exceeds the preset corresponding stability threshold range, the built-in algorithm model should be immediately triggered to perform data fitting to respond to the state fluctuation of the observation data;

[0024] Analyze and summarize the acquired historical data to obtain the input range of the influencing factors involved in fitting, and determine the influence of the input range of the influencing factors involved in fitting on the sludge return ratio by statistical method;

[0025] The algorithm model and the influencing factors involved in fitting are used to construct a fitting model with sludge return ratio as the independent variable for prediction;

[0026] According to the input range of the influencing factors involved in fitting, uniform distribution data sampling is performed to obtain valid sample data, which is then brought into the fitting model for fitting calculation to obtain the values ​​of various influencing coefficients;

[0027] The data states of other samples not involved in the calculation are brought into the fitting for regression iteration, the errors are calculated and the distribution statistics are performed, and the marginal samples are eliminated. The optimized values ​​of the influence coefficients are obtained according to the influence degree of each factor involved in the fitting, and then the calibrated fitting model is obtained.

[0028] The sludge return ratio is dynamically regulated based on the calibrated model. During the dynamic regulation of the sludge return ratio, the current configured control parameters are evaluated in combination with the actual working conditions, and the model evaluation indicators are output.

[0029] Optionally, it includes: when the effective sample data is less than the set threshold, introducing at least one of the project's empirical control data, empirical status and human intervention item data, and bringing them into the fitting model for fitting calculation to reduce the error of actual regulation.

[0030] Optionally,

[0031] The fitted model is:

[0032] R=K 1 *T+K 2 *MLSS+K 3 *SVI+K 4 *SV+K 5 *PH+...K n *G+M;

[0033] Among them, K 1 ~K n is the value of each influencing coefficient, T is temperature, MLSS is the real-time sludge concentration state of the biochemical pool, SV is the sludge settling ratio, SVI is the sludge volume, PH is the pH value in the biochemical pool, G is the index affecting system stability, and M is the calibration constant;

[0034] The model evaluation indicators are:

[0035]

[0036] Among them, TargetMLSS is the target setting value of the biochemical pool, and k is the number of interval sampling observations.

[0037] Optionally, based on the model evaluation index, the control parameters are analyzed regularly or in real time to determine the optimal control distribution, the control benchmark parameters of the model are updated according to the optimal control distribution, and the sludge return ratio is recalculated and optimized, including:

[0038] Record and process the dynamic control data including model evaluation indicators and corresponding control parameters generated by each dynamic control;

[0039] According to the pre-defined model evaluation optimal state threshold, statistical analysis is performed on the recorded dynamic control data in real time or regularly to dynamically evaluate the distribution of the model control effect range in the current scenario;

[0040] From the distribution of the model control effect range in the current scenario, select the data that shows the best control effect as the source data for fitting model calibration, which is used to recalibrate and update the K in the fitting model. 1 ~K n coefficient;

[0041] According to the calibrated K 1 ~K n coefficient, update the control benchmark parameters of the model, and recalculate the sludge return ratio;

[0042] The updated control benchmark parameters and the recalculated more optimal sludge return ratio are deployed in the fitting model.

[0043] Optionally, if the observed data is within the pre-adapted stable threshold range, the control parameters after the previous round of dynamic regulation are maintained, and the frequency converter is automatically controlled by setting the return flow of the return sludge pump to perform steady-state regulation, including:

[0044] If the observed data is within the pre-adapted stable threshold range, the control parameters including the sludge return ratio set after the previous round of dynamic regulation are maintained unchanged;

[0045] According to the maintained control parameters, the return flow rate of the return sludge pump is set to ensure that the set return flow rate matches the current steady-state control requirements;

[0046] Enable the frequency converter associated with the return sludge pump, and automatically control the frequency converter to adjust based on the set return flow rate to maintain the stable operation of the return sludge system;

[0047] During the steady-state control process, the observed data is continuously monitored, and when the observed data changes and exceeds the stable threshold range, the corresponding dynamic control mechanism is triggered.

[0048] In a second aspect, the present invention provides a control system for activated sludge process sludge, comprising:

[0049] An input processing module is used to receive and process input observation data of multiple dimensions of the sewage treatment plant;

[0050] The stable observation module is used to continuously monitor the state fluctuations of the observation data in each dimension, and determine whether the currently configured control parameters need to be adjusted based on the pre-adapted stable threshold;

[0051] The dynamic control module is used to respond to the state fluctuation of the observed data through the built-in algorithm model if the observed data exceeds the pre-adapted stable threshold range, dynamically control the sludge return ratio, evaluate the currently configured control parameters in combination with the actual working conditions, and output the model evaluation index;

[0052] Model calibration module, used to analyze control parameters regularly or in real time based on model evaluation indicators, determine the optimal control distribution, update the control benchmark parameters of the model according to the optimal control distribution, and recalculate and optimize the sludge return ratio;

[0053] The stable control module is used to maintain the control parameters after the previous round of dynamic control if the observed data is within the pre-adapted stable threshold range, and automatically control the frequency converter by setting the return flow of the return sludge pump to perform steady-state control.

[0054] In a third aspect, the present invention provides a control device for activated sludge process sludge, comprising:

[0055] A PLC controller, used to execute the method as described above;

[0056] The SCADA system is connected to the PLC controller and is equipped with a production monitoring interface for receiving and displaying data from the PLC controller to achieve remote monitoring and control of the production process;

[0057] The IO component is connected to the field acquisition component, field processing equipment and PLC controller respectively, and is used to collect field instrument data and transmit it back to the PLC controller, monitor the equipment operation status and upload it to the PLC controller, and receive the control instructions of the PLC to control the start and stop of the equipment;

[0058] The field collection component is connected to the IO component and deployed at the sewage treatment site to collect various field instrument data and equipment operating status and upload them to the IO component.

[0059] Optionally, the on-site collection component includes:

[0060] The water inlet flow meter is installed at the water inlet of the sewage treatment plant to detect the water inlet flow of the whole plant in real time;

[0061] The SS instrument at the water inlet is installed at the water inlet of the sewage treatment plant to detect the concentration of suspended solids in the water in real time;

[0062] The aerobic end MLSS meter is installed at the aerobic end of the biochemical pool to detect the sludge concentration of the aerobic end water body;

[0063] The pH meter is set at the aerobic end of the biochemical pool to detect the pH value in the pool;

[0064] A temperature meter is installed in the biochemical pool to monitor the water temperature in the pool in real time;

[0065] The secondary sedimentation tank mud level meter is installed in the secondary sedimentation tank to detect the mud thickness of the secondary sedimentation tank;

[0066] The sludge pump room liquid level meter is installed in the sludge pump room and is used to detect the liquid level in the sludge pump room;

[0067] The MLSS meter in the sludge pump room is installed in the sludge pump room to detect the concentration of the return sludge;

[0068] The return sludge pipeline flow meter is installed on the return sludge pipeline from the sludge pump room to the biochemical tank to detect the flow of return sludge in real time;

[0069] The outlet flow meter is installed at the outlet of the sewage treatment plant to detect the outlet flow of the entire plant in real time;

[0070] The SS instrument at the outlet is installed at the outlet to detect the concentration of suspended matter in the outlet water in real time.

[0071] (III) Beneficial effects

[0072] The beneficial effects of the present invention are:

[0073] First, the present invention can receive and process observation data of multiple dimensions of the sewage treatment plant, so as to fully understand the operating status of the sewage treatment plant. Through continuous monitoring of these data, the system can timely detect state fluctuations in various dimensions, providing an accurate information basis for subsequent regulation.

[0074] Secondly, the present invention uses a preset stability threshold to determine whether the currently configured control parameters need to be adjusted. When the observed data exceeds the stability threshold range, the system will respond quickly and dynamically adjust the sludge return ratio through the built-in algorithm model. This dynamic control mechanism enables the system to be flexibly adjusted according to actual conditions, ensuring the rationality of the amount of activated sludge in the biological reactor, thereby promoting the stable and efficient operation of the system.

[0075] In addition, the present invention also evaluates the currently configured control parameters in combination with the actual working conditions and outputs the model evaluation index. This function enables the system to self-evaluate its control effect, providing an important reference for subsequent parameter optimization.

[0076] Furthermore, the present invention analyzes the control parameters based on the model evaluation index, determines the optimal control distribution, and updates the control reference parameters of the model according to this distribution. By recalculating and optimizing the sludge return ratio, the system can continuously iterate and converge, achieving more accurate control as it is used. This statistically based control iterative convergence method significantly improves the control accuracy and adaptability of the system.

[0077] Finally, when the observed data is within the stable threshold range, the present invention can maintain the control parameters after the previous round of dynamic regulation, and automatically control the frequency converter by setting the return flow of the return sludge pump for steady-state regulation. This steady-state regulation method not only reduces the operating cost, but also provides technical support for the optimization control of the sewage treatment plant.

[0078] In summary, the present invention ensures the efficient and stable operation of the sewage treatment plant by combining multi-dimensional data monitoring, real-time monitoring and early warning, dynamic regulation and steady-state control, while reducing operating costs, providing strong technical support for the optimization control of the sewage treatment plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 A flow chart of return sludge control provided by an embodiment of the present invention;

[0080] Figure 2 A schematic flow chart of a method for controlling sludge in an activated sludge process according to an embodiment of the present invention;

[0081] Figure 3 A schematic diagram of a specific flow chart of step S2 of the method for controlling sludge in an activated sludge process according to an embodiment of the present invention;

[0082] Figure 4 A specific flow chart of step S3 of the method for controlling sludge in an activated sludge process provided by an embodiment of the present invention;

[0083] Figure 5 A specific flow chart of step S4 of the method for controlling sludge in an activated sludge process provided by an embodiment of the present invention;

[0084] Figure 6 A schematic diagram of dynamic calibration of a method for controlling sludge in an activated sludge process provided by an embodiment of the present invention;

[0085] Figure 7 A specific flow chart of step S5 of the method for controlling sludge in an activated sludge process provided by an embodiment of the present invention;

[0086] Figure 8 A diagram of the sludge control system architecture provided by an embodiment of the present invention;

[0087] Fig. 9 A general process flow chart of activated sludge process sludge control provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0088] In order to better explain the present invention and facilitate understanding, the present invention is described in detail below through specific implementation modes in conjunction with the accompanying drawings.

[0089] Prior to this, in order to facilitate understanding of the technical solution provided by the present invention, some concepts are first introduced below.

[0090] Activated sludge: Activated sludge is a kind of sludge-like flocculent, which is formed by the reproduction of aerobic microorganisms after a certain period of time when air is continuously introduced into wastewater. It is inhabited by microorganisms mainly composed of floccules, which have a strong ability to adsorb and oxidize organic matter. Activated sludge can be divided into aerobic activated sludge and anaerobic granular activated sludge. Activated sludge is usually used for aerobic biological treatment of sewage and wastewater. It can remove soluble and colloidal biodegradable organic matter from sewage, as well as suspended solids and other substances that can be adsorbed by activated sludge. It can also remove part of phosphorus and nitrogen. It has the characteristics of wide adaptability to water quality and quantity, flexible and diverse operation modes, and good controllability.

[0091] Return sludge: Return sludge refers to the sludge concentrated by the secondary sedimentation tank in the biochemical pool. The purpose of return sludge is to maintain a certain concentration of suspended solids in the biochemical pool, that is, to maintain a certain concentration of microorganisms.

[0092] like Figure 1 and Figure 2As shown, an activated sludge process sludge control method proposed in an embodiment of the present invention includes: receiving and processing observation data of multiple dimensions of a sewage treatment plant input; continuously monitoring the state fluctuations of the observation data of each dimension, and judging whether it is necessary to adjust the currently configured control parameters according to a pre-adapted stable threshold; if the observation data exceeds the pre-adapted stable threshold range, responding to the state fluctuations of the observation data through a built-in algorithm model, dynamically adjusting the sludge return ratio, and evaluating the currently configured control parameters in combination with the actual working conditions, and outputting a model evaluation index; based on the model evaluation index, regularly or in real time analyzing the control parameters, determining the optimal control distribution, updating the control reference parameters of the model according to the optimal control distribution, and recalculating and optimizing the sludge return ratio; if the observation data is within the pre-adapted stable threshold range, maintaining the control parameters after the previous round of dynamic regulation, and automatically controlling the frequency converter by setting the return flow of the return sludge pump to perform steady-state regulation.

[0093] First, the present invention can receive and process observation data of multiple dimensions of the sewage treatment plant, so as to fully understand the operating status of the sewage treatment plant. Through continuous monitoring of these data, the system can timely detect state fluctuations in various dimensions, providing an accurate information basis for subsequent regulation.

[0094] Secondly, the present invention uses a preset stability threshold to determine whether the currently configured control parameters need to be adjusted. When the observed data exceeds the stability threshold range, the system will respond quickly and dynamically adjust the sludge return ratio through the built-in algorithm model. This dynamic control mechanism enables the system to be flexibly adjusted according to actual conditions, ensuring the rationality of the amount of activated sludge in the biological reactor, thereby promoting the stable and efficient operation of the system.

[0095] In addition, the present invention also evaluates the currently configured control parameters in combination with the actual working conditions and outputs the model evaluation index. This function enables the system to self-evaluate its control effect, providing an important reference for subsequent parameter optimization.

[0096] Furthermore, the present invention analyzes the control parameters based on the model evaluation index, determines the optimal control distribution, and updates the control reference parameters of the model according to this distribution. By recalculating and optimizing the sludge return ratio, the system can continuously iterate and converge, achieving more accurate control as it is used. This statistically based control iterative convergence method significantly improves the control accuracy and adaptability of the system.

[0097] Finally, when the observed data is within the stable threshold range, the present invention can maintain the control parameters after the previous round of dynamic regulation, and automatically control the frequency converter by setting the return flow of the return sludge pump for steady-state regulation. This steady-state regulation method not only reduces the operating cost, but also provides technical support for the optimization control of the sewage treatment plant.

[0098] In summary, the present invention ensures the efficient and stable operation of the sewage treatment plant by combining multi-dimensional data monitoring, real-time monitoring and early warning, dynamic regulation and steady-state control, while reducing operating costs, providing strong technical support for the optimization control of the sewage treatment plant.

[0099] In order to better understand the above technical solution, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a clearer and more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0100] Specifically, an embodiment of the present invention provides a method for controlling sludge in an activated sludge process, comprising:

[0101] S1. Receive and process input observation data of multiple dimensions of sewage treatment plants.

[0102] During the operation of the sewage treatment plant, it is necessary to receive and process observation data of multiple key dimensions. These data not only cover core indicators such as the water volume of the biochemical pool, MLSS (real-time sludge concentration status of the biochemical pool), temperature and pH value, but may also include other parameters closely related to sewage treatment efficiency and environmental impact. The system collects these data in real time and conducts accurate analysis and processing to ensure the stability and optimization performance of the sewage treatment plant operation.

[0103] Specifically, monitoring the amount of water entering the biochemical pool helps the system to grasp the treatment load in real time so as to adjust the treatment strategy; the observation of MLSS is directly related to the sludge activity and treatment effect, and is an important indicator for evaluating the health status of the biological treatment process; the monitoring of temperature and pH value is essential for maintaining a suitable growth environment for microorganisms during the biological treatment process. By integrating these multi-dimensional observation data, the operating status of the sewage plant can be more comprehensively evaluated, potential problems can be discovered in a timely manner, and corresponding control measures can be taken to achieve efficient, stable and sustainable development of sewage treatment.

[0104] S2. Continuously monitor the state fluctuations of the observation data in each dimension, and determine whether the control parameters of the current configuration need to be adjusted based on the pre-adapted stability threshold.

[0105] By observing the state fluctuations of each observation, evaluate whether the system control state needs to be recalibrated to ensure the accuracy and real-time performance of the system control; when the overall state of the system does not change much, switch to steady-state control to avoid frequent control changes of the equipment, which is more friendly to the life of the on-site equipment.

[0106] Furthermore, if Figure 3 As shown, step S2 includes:

[0107] S21. Perform statistical analysis on the observation data of each dimension of continuous monitoring, and calculate the mean square error data of the observation data of each dimension including time, day, week and month.

[0108] S22. For each observation data, one or more stability thresholds are preset according to data characteristics and system control requirements.

[0109] S23. Output the result of the state fluctuation analysis by comparing the calculated mean square error data with a preset stability threshold.

[0110] S24. Based on the result of the state fluctuation analysis, determine whether the control parameters of the current configuration need to be adjusted.

[0111] S25. If there is at least one mean square error data exceeding the corresponding stability threshold, the dynamic control mechanism is triggered.

[0112] In a specific embodiment, in order to evaluate the stability of the operation of the sewage treatment plant, a steady-state observation mean square error calculation method is used. This method is not only applicable to the observation of water inflow and SS, but also to other observation factors, such as temperature, pH, etc. The specific calculation method is to first calculate the mean square error of each observation dimension, and then judge the stability of the dimension according to the size of the mean square error.

[0113] In addition, different stability thresholds are adapted for each observation dimension. When the mean square error of a dimension exceeds its corresponding stability threshold, the dimension is judged to be in an unstable state. At this time, the dynamic control mechanism will be triggered to quickly calibrate the control parameters to ensure the stable operation of the sewage plant. In this way, real-time monitoring and dynamic adjustment of each key dimension of the sewage plant can be achieved, thereby ensuring the efficiency and quality of sewage treatment.

[0114] Among them, the steady-state observation mean square error σ 进水水量 The calculation method is as follows, and the evaluation method of observation data such as MLSS, temperature and pH is similar:

[0115] in

[0116] Among them, x i is the influent volume, n is the sampling times, is the average value of the inlet flow rate of n samples.

[0117] For the steady-state observation mean square error σ 进水水量 , adapting the stability threshold, the evaluation method of observation data such as MLSS, temperature and pH value is similar:

[0118]

[0119] In the formula, σ th The preset stable threshold of the inlet water volume is used to evaluate the stability status of the current system.

[0120] S3. If the observed data exceeds the pre-adapted stable threshold range, the built-in algorithm model responds to the state fluctuation of the observed data, dynamically adjusts the sludge return ratio, and evaluates the currently configured control parameters in combination with the actual working conditions, and outputs the model evaluation index. In this step, the system is accurately and stably controlled by quickly responding to input fluctuations, and the system control state is quickly adjusted through rapid system state evaluation calculation.

[0121] Furthermore, if Figure 4 As shown, step S3 includes:

[0122] S31. If any monitored observation data exceeds the corresponding preset stability threshold range, the built-in algorithm model should be immediately triggered to perform data fitting to respond to the state fluctuation of the observation data.

[0123] S32. Analyze and summarize the acquired historical data to obtain the input range of the influencing factors involved in fitting, and determine the influence of the input range of the influencing factors involved in fitting on the sludge return ratio by statistical method.

[0124] S33. Utilize the algorithm model and the influencing factors involved in fitting to construct a fitting model with the sludge return ratio as the predicted independent variable.

[0125] S34. According to the input range of the influencing factors involved in the fitting, uniform distribution data sampling is performed to obtain valid sample data, and the data is brought into the fitting model for fitting calculation to obtain the values ​​of various influencing coefficients.

[0126] S35. Bring the data states of other samples that are not involved in the calculation into the fitting process for regression iteration, calculate the error and make distribution statistics, and remove marginal samples. Iterate successively according to the degree of influence of each influencing factor involved in the fitting, and obtain the optimized values ​​of each influencing coefficient, and then obtain a calibrated fitting model.

[0127] S36. Dynamically adjust the sludge return ratio based on the calibrated model. At the same time, during the dynamic adjustment of the sludge return ratio, the currently configured control parameters are evaluated in combination with the actual working conditions, and the model evaluation index is output.

[0128] In a specific embodiment, dynamic regulation focuses on the reasonable control of the sludge return ratio. In this embodiment, the PLSR model method is used to calculate and infer the return ratio, and then the actual working condition performance is combined to evaluate the control accuracy of the current control system, so as to promote the system to complete online real-time calibration and correction.

[0129] The model controls the sludge return ratio, takes the sludge return ratio as the predicted independent variable, and uses temperature, MLSS, SVI, SV, pH, etc. as key influencing indicators to construct the PLSR fitting model, and performs the following steps to obtain the model coefficients;

[0130] (1) Sorting out the input range of influencing factors: This can be obtained from the summary of on-site historical records, such as the distribution range and stable fluctuation range of MLSS in the biochemical pool;

[0131] (2) Sort out the influence of the factors: This means that the influence of the existing input factors involved in the fitting on R is confirmed by statistical methods to ensure the accuracy of the model influence coefficient calibration to the greatest extent; for example, through R 2 To count the degree of correlation, and then do horizontal sorting in different dimensions;

[0132] (3) Calibration data sample sampling: Based on the input range of 1, uniformly distributed data sampling is performed to ensure that the data sample coverage involved in model calibration and subsequent model regression verification is good enough to avoid the model results being too biased and performing poorly in special cases;

[0133] (4) Calculation of the influence input coefficient of influencing factors: According to the valid sample data, the model formula is substituted and fitted to obtain the values ​​of each influence coefficient as the model feature representation;

[0134] (5) Model coefficient regression verification: Since the above model is obtained through several sets of valid sample state adjustment, it is necessary to verify and regress the model accuracy. That is, bring in other sample data states that are not involved in the calculation to perform regression iteration, calculate the error, perform distribution statistics, and remove marginal samples; according to the importance of each influencing factor, iterate repeatedly according to this method to obtain the actual control parameters, which are finally used to guide the setting of the reflux ratio R;

[0135] The final fitting model is:

[0136] R=K 1 *T+K 2 *MLSS+K 3 *SVI+K 4 *SV+K 5 *PH+...K n *G+M;

[0137] Among them, K 1 ~K nare the values ​​of various influencing coefficients, T is temperature, MLSS is the real-time sludge concentration state of the biochemical pool, SV is the settling ratio of sludge, SVI is the sludge volume, PH is the pH value in the biochemical pool, G is an index affecting system stability, which is used to characterize the important indicators affecting system stability, such as influent water volume, influent SS, return sludge concentration, etc., and M is a calibration constant; the common main influencing factors include the above-mentioned temperature, MLSS, SV, PH, SVI, etc., which are added or deleted according to actual working conditions; but the initial state parameters need to obtain historical production data for calibration.

[0138] The settling ratio (SV) of sludge was determined using the national standard method;

[0139] Sludge volume index (SVI) is expressed as the volume occupied by 1g of dry sludge after 30 minutes of sedimentation:

[0140]

[0141] And the model evaluation index obtained is:

[0142]

[0143] Among them, MLSS is the real-time sludge concentration state of the biochemical pool, Target MLSS is the target setting value of the biochemical pool, and k is the number of interval sampling observations. Generally, after a sewage treatment plant makes some adjustments to the return ratio, the effect is often not immediately apparent and takes a certain amount of time to be reflected. This system uses k as the number of interval sampling observations, with a default definition of one observation every 10 minutes and continuous observation for 8 hours; the model evaluation index P Loss It can be defined as the MLSS value of the biochemical pool. The lower it is, the more accurate the model control state is.

[0144] It is worth mentioning that in order to ensure the stability of automatic adjustment of working conditions, when the effective sample data is less than the set threshold, at least one of the project empirical control data, empirical state and human intervention item data is introduced and brought into the fitting model for fitting calculation to reduce the error of actual regulation. Human intervention can be performed if the environment changes greatly.

[0145] In particular, when manual intervention is used to check the mud level in the secondary sedimentation tank, it should be controlled within the following range:

[0146] (1) The normal mud layer in the secondary sedimentation tank should be controlled at 0.3-0.9m, but not more than 1 / 3 of the mud level.

[0147] (2) The reflux ratio should not change by more than 5% of the preset value.

[0148] (3) The reflux flow rate does not exceed 10% of the preset value.

[0149] S4. Based on the model evaluation indicators, the control parameters are analyzed regularly or in real time to determine the optimal control distribution, the control benchmark parameters of the model are updated according to the optimal control distribution, and the sludge return ratio is recalculated and optimized.

[0150] In step S4, the control parameters under the optimal control distribution are analyzed through the model evaluation index, the corresponding model control benchmark parameters are updated, and a better reflux ratio R is recalculated, so that the model can perform more effectively during use.

[0151] Furthermore, if Figure 5 As shown, step S4 includes:

[0152] S41, recording and processing the dynamic control data including the model evaluation index and the corresponding control parameters generated by each dynamic control.

[0153] S42. According to the pre-defined model evaluation optimal state threshold, statistical analysis is performed on the recorded dynamic control data in real time or regularly to dynamically evaluate the distribution range of the model control effect in the current scenario.

[0154] S43, from the distribution of the model control effect range in the current scenario, select the data showing the best control effect as the source data for calibration of the fitting model, for recalibration and updating the K in the fitting model 1 ~K n coefficient.

[0155] S44, according to the calibrated K 1 ~K n coefficient, update the control benchmark parameters of the model, and recalculate the sludge return ratio.

[0156] S45. The updated control benchmark parameters and the recalculated more optimal sludge return ratio are deployed in the fitting model.

[0157] In a specific embodiment, reference Figure 6 The specific implementation method of dynamic calibration is as follows: in the industrial control process, each control state adjustment needs to be recorded in the historical data statistics, including all model effect evaluations and corresponding model control parameters, etc.; define the model evaluation optimal state threshold, calculate the dynamic calibration based on the model evaluation statistics, and evaluate the reasonable control effect range distribution of the corresponding scenario; select the best stage performance data as the source data for model calibration, that is, recalibrate and update K 1 ~K n coefficient; update the corresponding model control benchmark parameters and recalculate to obtain a better reflux ratio R.

[0158] S5. If the observed data is within the pre-adapted stable threshold range, the control parameters after the previous round of dynamic regulation are maintained, and the frequency converter is automatically controlled by setting the return flow of the return sludge pump to perform steady-state regulation.

[0159] Furthermore, if Figure 7 As shown, step S5 includes:

[0160] S51. If the observed data is within the pre-adapted stable threshold range, the control parameters including the sludge return ratio set after the previous round of dynamic regulation are maintained unchanged.

[0161] S52. According to the maintained control parameters, the return flow rate of the return sludge pump is set to ensure that the set return flow rate matches the current steady-state control demand.

[0162] S53, enabling the frequency converter associated with the return sludge pump, and automatically controlling the frequency converter to adjust based on the set return flow rate to maintain a stable operating state of the return sludge system.

[0163] S54. During the steady-state control process, the observed data is continuously monitored, and when the observed data changes and exceeds the stable threshold range, the corresponding dynamic control mechanism is triggered.

[0164] In a specific embodiment, the overall state of the return sludge system is stable at this time, and no excessive regulation is required, maintaining the return ratio R configuration after the previous dynamic calibration. Conventional constant flow control can meet the demand, and the inverter is automatically adjusted by setting the return flow of the return sludge pump. As shown in the following formula:

[0165] QR*RSSS=(Q+QR)*MLSS;

[0166] In the formula, RSSS is the return sludge concentration, QR is the return flow rate, and Q is the influent flow rate. On the other hand, an embodiment of the present invention provides a control system for activated sludge process sludge, including:

[0167] The input processing module is used to receive and process the input observation data of the sewage treatment plant in multiple dimensions.

[0168] The stable observation module is used to continuously monitor the state fluctuations of the observation data in each dimension, and determine whether the control parameters of the current configuration need to be adjusted based on the pre-adapted stable threshold.

[0169] The dynamic control module is used to respond to the state fluctuation of the observed data through the built-in algorithm model when the observed data exceeds the pre-adapted stable threshold range, dynamically control the sludge return ratio, evaluate the currently configured control parameters in combination with the actual working conditions, and output the model evaluation indicators.

[0170] The model calibration module is used to analyze the control parameters regularly or in real time based on the model evaluation indicators, determine the optimal control distribution, update the control benchmark parameters of the model according to the optimal control distribution, and recalculate and optimize the sludge return ratio.

[0171] The stable control module is used to maintain the control parameters after the previous round of dynamic control if the observed data is within the pre-adapted stable threshold range, and automatically control the frequency converter by setting the return flow of the return sludge pump to perform steady-state control.

[0172] Furthermore, an embodiment of the present invention provides a control device for activated sludge process sludge, including: a PLC controller for executing the method described above. A SCADA system, connected to the PLC controller, is configured with a production monitoring interface for receiving and displaying data from the PLC controller to achieve remote monitoring and control of the production process. An IO component, connected to a field acquisition component, a field processing device, and a PLC controller, respectively, is used to collect field instrument data and transmit it back to the PLC controller, monitor the equipment operating status and upload it to the PLC controller, and receive control instructions from the PLC to control the start and stop of the equipment. The field acquisition component is connected to the IO component and deployed at the sewage treatment site to collect a variety of field instrument data and equipment operating status and upload them to the IO component.

[0173] It is important to understand that the sludge in the biochemical pool flows with the sewage from the biochemical pool to the secondary sedimentation tank along with the hydraulic flow of the water treatment process. The sludge in the sewage flows into the sludge pump room after sedimentation in the secondary sedimentation tank and the action of the sludge scraper. The normal operation of the biochemical pool requires a certain sludge concentration to be maintained, so part of the sludge flowing into the sludge pump room needs to be returned to the biochemical pool.

[0174] A return sludge pump is installed in the sludge pump room. The return sludge pump is controlled by a frequency converter. Through the adjustment of the frequency converter, the pump can run according to the set flow rate. However, when the liquid level LT in the sludge pump room is lower than the operating level of the pump, the pump should stop running.

[0175] refer to Figure 8 The activated sludge process sludge control device provided in the embodiment of the present invention takes the PLC controller as the core, realizes the collection of field instrument data, equipment operation status and equipment start and stop control through the IO module, realizes the precise control of return sludge through the development of logic operation program, transmits the process data to the SCADA system through the industrial Ethernet protocol, develops the production monitoring interface in the SCADA system, and realizes the remote monitoring and control of the production process.

[0176] In general, the activated sludge process sludge control device provided by the embodiment of the present invention realizes accurate control and efficient management of sludge in the sewage treatment process through the synergistic effect of the PLC controller, SCADA system, IO components and field collection components. This not only improves the efficiency and quality of sewage treatment, but also makes positive contributions to environmental protection and sustainable development.

[0177] Furthermore, the on-site data collection components include: an inlet flow meter, which is set at the inlet of the sewage treatment plant and is used to detect the inlet flow of the whole plant in real time; an inlet SS meter, which is set at the inlet and is used to detect the suspended solids concentration in the inlet in real time; an aerobic MLSS meter, which is set at the aerobic end of the biochemical tank and is used to detect the sludge concentration of the aerobic end water body; a pH meter, which is set at the aerobic end of the biochemical tank and is used to detect the pH value in the tank; a temperature meter, which is set in the biochemical tank and is used to monitor the water temperature in the tank in real time; and a secondary sedimentation tank mud level meter, which is set in the secondary sedimentation tank. Used to detect the mud thickness in the secondary sedimentation tank; the sludge pump room level meter is installed in the sludge pump room to detect the liquid level in the sludge pump room; the sludge pump room MLSS meter is installed in the sludge pump room to detect the concentration of the return sludge; the return sludge pipeline flow meter is installed on the return sludge pipeline from the sludge pump room to the biochemical tank to detect the flow of the return sludge in real time; the outlet end flow meter is installed at the outlet end of the sewage treatment plant to detect the outlet flow of the entire plant in real time; the outlet end SS meter is installed at the outlet end to detect the concentration of suspended matter in the outlet water in real time.

[0178] Furthermore, the detection instruments used in the present invention are commonly used and mature products on the market. All instrument signals are connected to the above-mentioned PLC controller through the PLC IO module. Fig. 9 The general process shown in the figure, the instrument access point of the present invention is as follows Figure 8 As shown, the functions are described as follows:

[0179] (1) At the inlet end of the sewage treatment plant: flow meters and SS instruments are installed to detect the real-time inlet flow rate and inlet suspended solids concentration of the entire plant;

[0180] (2) At the aerobic end of the biochemical pool: an MLSS meter is set up to detect the sludge concentration in the aerobic end water body; a pH meter is set up to detect the pH in the pool; a temperature meter is set up to detect the temperature in the pool;

[0181] (3) In the secondary sedimentation tank: a mud level meter is installed to detect the mud thickness in the secondary sedimentation tank;

[0182] (4) In the sludge pump room: a liquid level meter and MLSS instrument are installed to detect the liquid level and return sludge concentration in the sludge pump room;

[0183] (5) On the return sludge pipeline from the sludge pump room to the biochemical tank: a flow meter is installed to detect the return sludge flow rate;

[0184] (6) At the outlet of the sewage treatment plant: flow meters and SS instruments are installed to detect the real-time effluent flow and effluent suspended solids concentration of the entire plant.

[0185] In summary, the embodiments of the present invention provide a method, system and equipment for controlling sludge in an activated sludge process. The present invention realizes precise regulation of the sludge return ratio through advanced calculation and control strategies, thereby ensuring a reasonable amount of activated sludge in the biological reaction tank and promoting stable and efficient operation of the system.

[0186] First, the present invention adopts a return ratio derivation and calculation method based on the PLSR model, which can comprehensively consider the main factors affecting the sludge return ratio and ensure that the setting of the return ratio is more scientific and reasonable.

[0187] Secondly, the present invention introduces a dynamic evaluation method for reflux ratio control. This method is based on the historical actual control distribution and confirms the optimal control parameters from a statistical perspective. This method is not only more reliable and accurate, but also can continuously optimize future control strategies based on past control effects.

[0188] In addition, the present invention also has a dynamic calibration function for the reflux ratio. By analyzing the performance of historical control data and combining the system self-evaluation mechanism, the model can achieve self-iterative optimization. This feature reduces the system's requirements for the initial control state and can gradually achieve control convergence during actual use, making it more accurate the more it is used.

[0189] The present invention can also adjust the sludge return volume in real time according to changes in operating conditions, such as fluctuations in the quality and quantity of the influent, changes in the sludge settling performance, etc. This flexibility ensures the rationality of the amount of activated sludge in the biological reaction tank, thereby maintaining the stable operation of the system and the efficient treatment effect.

[0190] In the case of little fluctuation in influent water quality and influent volume, the present invention can also reduce operating costs through steady-state control, providing strong technical support for the optimization control of sewage treatment plants. In particular, its self-evaluation and statistically based control iteration convergence functions enable the performance of the control system to be continuously improved during use, achieving a more accurate control effect with more use.

[0191] Since the system / device described in the above embodiments of the present invention is a system / device used to implement the method of the above embodiments of the present invention, a person skilled in the art can understand the specific structure and deformation of the system / device based on the method described in the above embodiments of the present invention, and thus will not be described in detail here. All systems / devices used in the method of the above embodiments of the present invention belong to the scope of protection of the present invention.

[0192] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take 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 code.

[0193] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions.

[0194] It should be noted that in the claims, any reference numerals placed between brackets shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention may be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In the claims enumerating several means, several of these means may be embodied by the same hardware. The use of the words first, second, third, etc., is for convenience of expression only and does not indicate any order. These words may be understood as part of the component name.

[0195] In addition, it should be noted that, in the description of this specification, the description of the terms "one embodiment", "some embodiments", "embodiment", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0196] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments after knowing the basic creative concept. Therefore, the claims should be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0197] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention should also include these modifications and variations.

Claims

1. A method for controlling sludge in an activated sludge process, characterized in that: include: Receive and process input observation data of multiple dimensions of sewage treatment plants; Continuously monitor the state fluctuations of observation data in each dimension, and determine whether the currently configured control parameters need to be adjusted based on the pre-adapted stability threshold; If the observed data exceeds the pre-adapted stable threshold range, the built-in algorithm model responds to the state fluctuation of the observed data, dynamically adjusts the sludge return ratio, and evaluates the currently configured control parameters in combination with the actual working conditions, and outputs the model evaluation indicators; Based on the model evaluation indicators, the control parameters are analyzed regularly or in real time to determine the optimal control distribution, the control benchmark parameters of the model are updated according to the optimal control distribution, and the sludge return ratio is recalculated and optimized; If the observed data is within the pre-adapted stable threshold range, the control parameters after the previous round of dynamic regulation are maintained, and the frequency converter is automatically controlled by setting the return flow of the return sludge pump to perform steady-state regulation.

2. The method for controlling activated sludge process sludge according to claim 1, characterized in that: Continuously monitor the state fluctuations of observation data in various dimensions, and determine whether the currently configured control parameters need to be adjusted based on the pre-adapted stability thresholds, including: Conduct statistical analysis on the observation data of each dimension of continuous monitoring, and calculate the mean square error data of the observation data of each dimension including time, day, week and month; For each observation data, one or more stability thresholds are preset according to the data characteristics and system control requirements; By comparing the calculated mean square error data with the preset stability threshold, the result of the state fluctuation analysis is output; Based on the results of the state fluctuation analysis, determine whether the control parameters of the current configuration need to be adjusted; If there is at least one mean square error data exceeding the corresponding stability threshold, the dynamic control mechanism is triggered.

3. The method for controlling activated sludge process sludge according to claim 1, characterized in that: If the observed data exceeds the pre-adapted stable threshold range, the built-in algorithm model responds to the state fluctuation of the observed data, dynamically adjusts the sludge return ratio, and evaluates the currently configured control parameters in combination with the actual working conditions. The output model evaluation indicators include: If any monitored observation data exceeds the preset corresponding stability threshold range, the built-in algorithm model should be immediately triggered to perform data fitting to respond to the state fluctuation of the observation data; Analyze and summarize the acquired historical data to obtain the input range of the influencing factors involved in fitting, and determine the influence of the input range of the influencing factors involved in fitting on the sludge return ratio by statistical method; The algorithm model and the influencing factors involved in fitting are used to construct a fitting model with sludge return ratio as the independent variable for prediction; According to the input range of the influencing factors involved in fitting, uniform distribution data sampling is performed to obtain valid sample data, which is then brought into the fitting model for fitting calculation to obtain the values ​​of various influencing coefficients; The data states of other samples not involved in the calculation are brought into the fitting for regression iteration, the errors are calculated and the distribution statistics are performed, and the marginal samples are eliminated. The optimized values ​​of the influence coefficients are obtained according to the influence degree of each factor involved in the fitting, and then the calibrated fitting model is obtained. The sludge return ratio is dynamically regulated based on the calibrated model. During the dynamic regulation of the sludge return ratio, the current configured control parameters are evaluated in combination with the actual working conditions, and the model evaluation indicators are output.

4. The method for controlling activated sludge process sludge according to claim 3, characterized in that: include: When the effective sample data is less than the set threshold, at least one of the project's empirical control data, empirical status, and human intervention item data is introduced and brought into the fitting model for fitting calculation to reduce the error of actual regulation.

5. The method for controlling activated sludge process sludge according to claim 3, characterized in that: The fitted model is: R=K1*T+K2*MLSS+K3*SVI+K4*SV+K5*PH+...K n *G+M; Among them, K1~K n is the value of each influencing coefficient, T is temperature, MLSS is the real-time sludge concentration state of the biochemical pool, SV is the sludge settling ratio, SVI is the sludge volume, PH is the pH value in the biochemical pool, G is the index affecting system stability, and M is the calibration constant; The model evaluation indicators are: Among them, Target MLSS is the target setting value of the biochemical pool, and k is the number of interval sampling observations.

6. The method for controlling activated sludge process sludge according to claim 5, characterized in that: Based on the model evaluation indicators, the control parameters are analyzed regularly or in real time to determine the optimal control distribution, the control benchmark parameters of the model are updated according to the optimal control distribution, and the sludge return ratio is recalculated and optimized, including: Record and process the dynamic control data including model evaluation indicators and corresponding control parameters generated by each dynamic control; According to the pre-defined model evaluation optimal state threshold, statistical analysis is performed on the recorded dynamic control data in real time or regularly to dynamically evaluate the distribution of the model control effect range in the current scenario; From the distribution of the model control effect range in the current scenario, select the data that shows the best control effect as the source data for fitting model calibration, which is used to recalibrate and update K1~K in the fitting model. n coefficient; According to the calibrated K1~K n coefficient, update the control benchmark parameters of the model, and recalculate the sludge return ratio; The updated control benchmark parameters and the recalculated more optimal sludge return ratio are deployed in the fitting model.

7. The method for controlling activated sludge process sludge according to claim 1, characterized in that: If the observed data is within the pre-adapted stable threshold range, the control parameters after the previous round of dynamic regulation are maintained, and the inverter is automatically controlled by setting the return flow of the return sludge pump to perform steady-state regulation, including: If the observed data is within the pre-adapted stable threshold range, the control parameters including the sludge return ratio set after the previous round of dynamic regulation are maintained unchanged; According to the maintained control parameters, the return flow rate of the return sludge pump is set to ensure that the set return flow rate matches the current steady-state control requirements; Enable the frequency converter associated with the return sludge pump, and automatically control the frequency converter to adjust based on the set return flow rate to maintain the stable operation of the return sludge system; During the steady-state control process, the observed data is continuously monitored, and when the observed data changes and exceeds the stable threshold range, the corresponding dynamic control mechanism is triggered.

8. A control system for activated sludge process sludge, characterized in that: include: An input processing module is used to receive and process input observation data of multiple dimensions of the sewage treatment plant; The stable observation module is used to continuously monitor the state fluctuations of the observation data in each dimension, and determine whether the currently configured control parameters need to be adjusted based on the pre-adapted stable threshold; The dynamic control module is used to respond to the state fluctuation of the observed data through the built-in algorithm model if the observed data exceeds the pre-adapted stable threshold range, dynamically control the sludge return ratio, evaluate the currently configured control parameters in combination with the actual working conditions, and output the model evaluation index; Model calibration module, used to analyze control parameters regularly or in real time based on model evaluation indicators, determine the optimal control distribution, update the control benchmark parameters of the model according to the optimal control distribution, and recalculate and optimize the sludge return ratio; The stable control module is used to maintain the control parameters after the previous round of dynamic control if the observed data is within the pre-adapted stable threshold range, and automatically control the frequency converter by setting the return flow of the return sludge pump to perform steady-state control.

9. An activated sludge process sludge control device, characterized in that: include: A PLC controller, used to execute the method according to any one of claims 1 to 7; The SCADA system is connected to the PLC controller and is equipped with a production monitoring interface for receiving and displaying data from the PLC controller to achieve remote monitoring and control of the production process; The IO component is connected to the field acquisition component, field processing equipment and PLC controller respectively, and is used to collect field instrument data and transmit it back to the PLC controller, monitor the equipment operation status and upload it to the PLC controller, and receive the control instructions of the PLC to control the start and stop of the equipment; The field collection component is connected to the IO component and deployed at the sewage treatment site to collect various field instrument data and equipment operating status and upload them to the IO component.

10. The activated sludge process sludge control device according to claim 9, characterized in that: The on-site collection components include: The water inlet flow meter is installed at the water inlet of the sewage treatment plant to detect the water inlet flow of the whole plant in real time; The SS instrument at the water inlet is installed at the water inlet of the sewage treatment plant to detect the concentration of suspended solids in the water in real time; The aerobic end MLSS meter is installed at the aerobic end of the biochemical pool to detect the sludge concentration of the aerobic end water body; The pH meter is set at the aerobic end of the biochemical pool to detect the pH value in the pool; A temperature meter is installed in the biochemical pool to monitor the water temperature in the pool in real time; The secondary sedimentation tank mud level meter is installed in the secondary sedimentation tank to detect the mud thickness of the secondary sedimentation tank; The sludge pump room liquid level meter is installed in the sludge pump room and is used to detect the liquid level in the sludge pump room; The MLSS meter in the sludge pump room is installed in the sludge pump room to detect the concentration of the return sludge; The return sludge pipeline flow meter is installed on the return sludge pipeline from the sludge pump room to the biochemical tank to detect the return sludge flow in real time; The outlet flow meter is installed at the outlet of the sewage treatment plant to detect the outlet flow of the entire plant in real time; The SS instrument at the outlet is installed at the outlet to detect the concentration of suspended matter in the outlet water in real time.

Images