Autonomous adjustment method and system for desulfurization wastewater dosing device of thermal power plant

Abstract

The invention provides an autonomous adjustment method and system for a thermal power plant desulfurization wastewater dosing device, and the method comprises the steps: collecting multiple parameters such as flow, pH value, heavy metal ion and suspended matter concentration in real time through on-line monitoring instruments arranged at a water inlet end, a reaction unit and a water outlet end; constructing and continuously updating a dynamic mathematical model based on historical data and a reaction mechanism; a control system integrating intelligent algorithms such as a neural network and fuzzy control is utilized, and optimal dosing parameters are calculated in combination with the model and real-time data; a dosing pump or a valve is driven to execute precise dosing; and finally, closed-loop optimization is formed through effluent quality feedback. According to the invention, automatic, accurate and self-adaptive adjustment of the dosing device is realized, the defects that a traditional mode depends on manpower and response lags behind are overcome, stable and standard discharge of desulfurization wastewater is effectively guaranteed, meanwhile, medicament consumption and operation cost are remarkably reduced, and the automation level and the capability of coping with working condition fluctuation of the system are improved.

Description

Technical Field

[0001] This invention relates to the field of industrial wastewater treatment technology, and in particular to an autonomous adjustment method and system for a chemical dosing device for desulfurization wastewater in thermal power plants. Background Technology

[0002] In the production process of thermal power plants, wet desulfurization technology is widely used, which generates a large amount of desulfurization wastewater with complex composition and large fluctuations. This wastewater contains high concentrations of suspended solids, heavy metal ions (such as mercury, cadmium, lead, etc.), and supersaturated sulfites and sulfates. If not treated properly, it will cause serious environmental pollution.

[0003] Currently, the chemical dosing treatment of desulfurization wastewater in thermal power plants generally suffers from low automation and reliance on manual experience. Operators typically set dosing parameters (such as the type and dosage of chemicals) based on fixed procedures or periodic water quality test results. However, the quality and quantity of desulfurization wastewater are affected by various factors such as coal quality, boiler load, and desulfurization system operating conditions, resulting in significant real-time fluctuations. Fixed dosing patterns or delayed manual adjustments are insufficient to adapt to these dynamic changes, often leading to overdosing or underdosing. Overdosing not only wastes chemicals and increases operating costs but may also introduce new pollutants; underdosing results in substandard wastewater treatment, environmental pollution after discharge, and even equipment problems such as scaling and blockage in the system.

[0004] While existing technologies have attempted to introduce automatic control, they mostly rely on simple feedback control based on single parameters such as pH or turbidity. This lacks overall optimization for multi-parameter, nonlinear, and large-hysteresis systems, failing to achieve precise, economical, and adaptive dosing control. Therefore, there is an urgent need in this field for an autonomous adjustment method and system capable of real-time sensing of water quality changes, intelligent decision-making, and precise execution. Summary of the Invention

[0005] The purpose of this invention is to provide an autonomous adjustment method and system for a chemical dosing device for desulfurization wastewater in thermal power plants. Through real-time monitoring, intelligent modeling, algorithm decision-making, and feedback optimization, the dosing device can be automatically, accurately, and adaptively adjusted to ensure stable discharge of desulfurization wastewater while minimizing chemical consumption and operating costs.

[0006] According to one objective of the present invention, the present invention provides an autonomous adjustment method for a chemical dosing device for desulfurization wastewater in a thermal power plant, comprising the following steps: Step S1: Real-time monitoring of multiple parameters: Online monitoring instruments are installed at the inlet, reaction unit and outlet of the desulfurization wastewater treatment system to collect water quality parameters in real time, including wastewater flow rate, pH value, concentration of at least one heavy metal ion and concentration of suspended solids. Step S2: Dynamic Model Construction and Update: Based on historical operating data, wastewater treatment process principles and chemical reaction kinetics, a dynamic mathematical model describing the quantitative relationship between water quality parameters and dosing parameters is constructed, and the model is continuously optimized and updated using real-time monitoring data; Step S3: Intelligent Algorithm Decision: The real-time collected water quality parameters are input into the control system integrated with the intelligent algorithm. The intelligent algorithm combines the dynamic model and the preset treatment target to calculate the optimal dosing parameters under the current operating conditions. Step S4: Automatic adjustment execution: The control system generates control commands based on the optimal dosing parameters to drive the actuators of the dosing device to adjust the actual dosing amount; Step S5: Feedback Optimization: Monitor the water quality at the outlet in real time, and feed the water quality data back to the control system for comparison with the preset standard; if the standard is not met, the control system is triggered to readjust the dosing parameters.

[0007] Furthermore, in step S1, the online monitoring instruments include at least an electromagnetic flowmeter, a pH online monitor, a heavy metal ion online monitor, and a suspended solids concentration detector; the collected data is transmitted to the control system in real time via RS485 or industrial Ethernet communication.

[0008] Furthermore, in step S2, the specific process of constructing the dynamic mathematical model includes: establishing an initial model framework based on chemical mechanisms, and calibrating the initial model framework using historical operating data through data fitting and parameter optimization methods; the continuous optimization and update refers to periodically incorporating new real-time monitoring data and corresponding dosing and effluent data into the training set to perform rolling optimization of the parameters of the dynamic mathematical model.

[0009] Furthermore, in step S3, the intelligent algorithm is a neural network algorithm, a fuzzy control algorithm, or a fusion of both. When a neural network algorithm is used, the neural network is trained using historical operating data, with water quality parameters as input and dosing parameters as output. When a fuzzy control algorithm is used, the deviation of water quality parameters is divided into fuzzy intervals, and a dosing adjustment strategy is formulated based on a preset fuzzy rule base.

[0010] Further, in step S4, the actuating element of the dosing device is a dosing pump or a dosing valve; when the actuating element is a dosing pump, the dosing flow rate is changed by adjusting the motor frequency or stroke of the dosing pump; when the actuating element is a dosing valve, the dosing flow rate is controlled by adjusting the opening of the electric valve.

[0011] Furthermore, step S4 also includes: real-time monitoring of the operating status parameters of the dosing device actuator, including operating pressure and motor current, and alarming or protective shutdown when the parameters are abnormal.

[0012] Furthermore, in step S5, if the effluent water quality does not meet the standards, the control system analyzes the reasons for the exceedance based on the dynamic model and intelligent algorithm, and automatically adjusts the dosing parameters; step S5 also includes: periodically summarizing and analyzing the historical operating data of the system, exploring operating patterns, and periodically optimizing the dynamic model and intelligent algorithm based on the analysis results.

[0013] According to another objective of the present invention, the present invention provides an autonomous adjustment system for a chemical power plant desulfurization wastewater dosing device that implements the above-described method, comprising: The monitoring module includes multiple online monitoring instruments installed at different stations in the desulfurization wastewater treatment system for real-time collection of water quality parameters; The control module is communicatively connected to the monitoring module. It stores a dynamic mathematical model and integrates an intelligent algorithm to receive the water quality parameters and output the optimal dosing parameters through calculation. An execution module, connected to the control module, includes a controlled dosing execution element for receiving control commands and adjusting the dosing amount; The feedback module includes an online water quality monitor installed at the water outlet, used to feed back the water quality data of the effluent to the control module.

[0014] Furthermore, the monitoring module includes an electromagnetic flow meter and an online pH monitor installed in the inlet pipe, an online heavy metal ion monitor and a suspended solids concentration detector installed in the reaction tank, and a comprehensive water quality monitor installed in the outlet pipe; the control module is a programmable logic controller (PLC) or a distributed control system (DCS); the dosing actuator in the execution module is a variable frequency dosing pump or an electric regulating valve.

[0015] Furthermore, it also includes a status monitoring unit for monitoring the working status of the execution module. The status monitoring unit includes a pressure sensor and a current sensor. The monitoring module, control module, execution module and feedback module are connected to each other via fieldbus or industrial Ethernet.

[0016] This invention's technical solution achieves significant benefits by constructing a complete intelligent closed loop encompassing monitoring, modeling, decision-making, execution, and feedback. Through real-time multi-parameter monitoring and dynamic models, it enables precise perception and prediction of complex and variable water quality, ensuring accurate matching of chemical dosage with current operating conditions. This fundamentally solves the problems of lag and mismatch in fixed chemical dosing patterns, significantly improving the compliance rate and stability of effluent quality and effectively reducing environmental pollution risks. Precise decision-making based on intelligent algorithms avoids waste and shortages of chemicals, directly reducing chemical consumption costs and secondary treatment costs due to substandard treatment, resulting in significant economic benefits. Autonomous adjustment throughout the entire process greatly reduces manual intervention, improving system automation and operational efficiency while mitigating risks caused by insufficient personnel experience or operational errors. This solution possesses strong self-learning and adaptive capabilities; its dynamic model and intelligent algorithms continuously optimize based on operating data, effectively addressing drastic changes in water quality and quantity caused by variations in coal consumption and load fluctuations. The system is robust and widely applicable. Attached Figure Description

[0017] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the method according to an embodiment of the present invention; Figure 2 This is a system framework diagram of an embodiment of the present invention; Detailed Implementation The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limiting this invention.

[0020] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified. Furthermore, the terms "installed," "connected," and "linked" should be interpreted broadly; for example, they may refer to a fixed connection, a detachable connection, or an integral connection; they may refer to a mechanical connection or an electrical connection; they may refer to a direct connection or an indirect connection through an intermediate medium; and they may refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0021] Example 1 like Figure 1 As shown, a self-adjustment method for a desulfurization wastewater dosing device in a thermal power plant includes the following steps: Step S1: Real-time monitoring of multiple parameters: Online monitoring instruments are installed at the inlet, reaction unit and outlet of the desulfurization wastewater treatment system to collect water quality parameters in real time, including wastewater flow rate, pH value, concentration of at least one heavy metal ion and concentration of suspended solids. Step S2: Dynamic Model Construction and Update: Based on historical operating data, wastewater treatment process principles and chemical reaction kinetics, a dynamic mathematical model describing the quantitative relationship between water quality parameters and dosing parameters is constructed, and the model is continuously optimized and updated using real-time monitoring data; Step S3: Intelligent Algorithm Decision: The real-time collected water quality parameters are input into the control system integrated with the intelligent algorithm. The intelligent algorithm combines the dynamic model and the preset treatment target to calculate the optimal dosing parameters under the current operating conditions. Step S4: Automatic adjustment execution: The control system generates control commands based on the optimal dosing parameters to drive the actuators of the dosing device to adjust the actual dosing amount; Step S5: Feedback Optimization: Monitor the water quality at the outlet in real time, and feed the water quality data back to the control system for comparison with the preset standard; if the standard is not met, the control system is triggered to readjust the dosing parameters.

[0022] Specifically, in step S1, the online monitoring instruments include at least an electromagnetic flowmeter, a pH online monitor, a heavy metal ion online monitor, and a suspended solids concentration detector. The heavy metal ion online monitor is an atomic absorption spectrometer or an inductively coupled plasma spectrometer. In step S1, the collected data is transmitted to the control system in real time via RS485 or industrial Ethernet communication.

[0023] Specifically, in step S2, the specific process of constructing the dynamic mathematical model includes: establishing an initial model framework based on chemical mechanisms, and calibrating the initial model framework using historical operating data through data fitting and parameter optimization methods; the continuous optimization and update refers to periodically incorporating new real-time monitoring data and corresponding dosing and effluent data into the training set to perform rolling optimization of the parameters of the dynamic mathematical model.

[0024] Specifically, in step S3, the intelligent algorithm is a neural network algorithm, a fuzzy control algorithm, or a fusion of both. When a neural network algorithm is used, the neural network is trained using historical operating data, with water quality parameters as input and dosing parameters as output. When a fuzzy control algorithm is used, the deviation of water quality parameters is divided into fuzzy intervals, and a dosing adjustment strategy is formulated based on a preset fuzzy rule base.

[0025] The preset treatment objectives in step S3 include achieving the required effluent quality and minimizing reagent consumption.

[0026] Specifically, in step S4, the actuating element of the dosing device is a dosing pump or a dosing valve. When the actuating element is a dosing pump, the dosing flow rate is changed by adjusting the motor frequency or stroke of the dosing pump. When the actuating element is a dosing valve, the dosing flow rate is controlled by adjusting the opening degree of the electric valve.

[0027] Step S4 also includes: real-time monitoring of the operating status parameters of the dosing device actuator, including operating pressure and motor current, and alarming or protective shutdown when the parameters are abnormal.

[0028] Specifically, in step S5, if the effluent water quality fails to meet standards, the control system analyzes the causes of the exceedance using the dynamic model and intelligent algorithm, and automatically adjusts the dosing parameters. Step S5 also includes periodically summarizing and analyzing the system's historical operating data to uncover operating patterns, and periodically optimizing the dynamic model and intelligent algorithm based on the analysis results.

[0029] like Figure 2 As shown, an autonomous adjustment system for a desulfurization wastewater dosing device in a thermal power plant, used to implement the above method, includes: The monitoring module includes multiple online monitoring instruments installed at different stations in the desulfurization wastewater treatment system for real-time collection of water quality parameters; The control module is communicatively connected to the monitoring module. It stores a dynamic mathematical model and integrates an intelligent algorithm to receive the water quality parameters and output the optimal dosing parameters through calculation. An execution module, connected to the control module, includes a controlled dosing execution element for receiving control commands and adjusting the dosing amount; The feedback module includes an online water quality monitor installed at the water outlet, used to feed back the water quality data of the effluent to the control module.

[0030] Specifically, the monitoring module includes an electromagnetic flow meter and an online pH monitor installed in the inlet pipe, an online heavy metal ion monitor and a suspended solids concentration detector installed in the reaction tank, and a comprehensive water quality monitor installed in the outlet pipe.

[0031] The control module is a programmable logic controller (PLC) or a distributed control system (DCS).

[0032] The dosing actuator in the execution module is a variable frequency dosing pump or an electric regulating valve.

[0033] The monitoring module, control module, execution module and feedback module are connected via fieldbus or industrial Ethernet.

[0034] Specifically, the system further includes a status monitoring unit for monitoring the working status of the execution module, and the status monitoring unit includes a pressure sensor and a current sensor.

[0035] Example 2 This embodiment is based on Embodiment 1 and provides a method for autonomous adjustment of a chemical dosing device for desulfurization wastewater in a thermal power plant. The process is as follows: Figure 1 As shown: S1: Real-time monitoring of multiple parameters Install online monitoring instruments at the following key locations in the desulfurization wastewater treatment system: Inlet pipe: Install an electromagnetic flow meter and a pH online monitoring instrument to accurately measure instantaneous wastewater flow rate and real-time pH value, respectively.

[0036] Reaction cell: Equipped with an online heavy metal ion monitor, which can be an inductively coupled plasma optical emission spectrometer (ICP-OES) or a specific heavy metal electrode, to periodically (e.g., every 15 minutes) measure Hg. 2+ Cd 2+ Pb 2+ The concentration of target ions was measured. Simultaneously, a suspended matter concentration detector based on the principle of laser scattering was installed.

[0037] Outlet water pipeline: A comprehensive water quality monitoring instrument (such as a HACH SC200 universal controller with multi-parameter probes) is installed to perform final testing on the treated effluent. Monitoring parameters include pH, turbidity (alternating suspended solids), and specific heavy metal ions. All instruments communicate via RS485 interface using the Modbus RTU protocol, uploading the collected data to the central control system in real time.

[0038] S2: Dynamic Model Building and Updating The dynamic mathematical model is the core, and its construction and updating process is as follows: Data collection: Collect data on the entire process of desulfurization wastewater treatment at the power plant over the past 1-2 years, covering different seasons, loads, and coal types, to form a historical database.

[0039] Mechanism modeling: Establishing an initial model framework based on chemical principles. For example: Neutralization model: Calculate the theoretical dosage based on the initial pH of the wastewater, the target pH (usually set to 7-9), and the reaction equation of the neutralizing agent used (such as NaOH, Ca(OH)2).

[0040] Flocculation and sedimentation model: Based on colloid chemistry and flocculation kinetics, establish the functional relationship between suspended solids and heavy metal concentrations and the dosage of flocculants (such as PAC) and coagulants (such as PAM), taking into account the influence of hydraulic conditions (such as G / GT value).

[0041] Data-driven correction: Using historical databases, multivariate nonlinear regression or machine learning methods are employed to fit and calibrate parameters in the mechanistic model (such as reaction rate constant and efficiency coefficient) to make the model output more closely resemble reality.

[0042] Online model update: The control system automatically starts a model update program once a week or once a month, incorporating recent (e.g., the previous week's) real-time monitoring data and corresponding dosing and effluent data into the training set, and fine-tuning the model parameters using a rolling time window to ensure that the model always reflects the current characteristics of the system.

[0043] S3: Intelligent Algorithm Decision Making This embodiment uses a fusion algorithm of neural network (NN) and fuzzy control (FLC).

[0044] Neural Network Module: A three-layer feedforward backpropagation (BP) neural network is employed. Input layer nodes correspond to multiple water quality parameters monitored in S1 (flow rate, pH, heavy metal concentration, ... suspended solids concentration). Output layer nodes correspond to the recommended dosages of various chemicals. The number of hidden layer nodes is determined through trial and error. The network is fully trained using the historical database constructed in S2 (the training objective is to minimize the error between the predicted dosage and the "optimal" dosage), and is then used for online prediction after training.

[0045] Fuzzy Control Module: Serving as a supplement and emergency backup to the Neural Network (NN). Deviations in water quality parameters (such as the difference between the current pH and the target pH, or the ratio of the current heavy metal concentration to the limit) are defined as fuzzy input variables, with their universe of discourse divided into fuzzy sets such as "negative large," "negative small," "zero," "positive small," and "positive large." The adjustment amount of the dosage is defined as a fuzzy output variable. A fuzzy rule base in the form of "IF-THEN" is established, for example: "IF pH deviation is negative large, THEN neutralizer dosage adjustment is positive large." Through fuzzy inference and defuzzification, specific adjustment instructions are output.

[0046] Decision Fusion: During the operation of the control system, the output of the neural network is used as the baseline dosage. At the same time, the fuzzy controller operates in parallel. If the adjustment of its output exceeds a preset threshold, the adjustment is added to the baseline dosage to achieve fast and robust correction.

[0047] S4: Automatic adjustment execution For dosing devices that use metering pumps (such as the ProMinent Gamma / L series), the control system adjusts the pump's stroke frequency via a 4-20mA analog signal or bus communication (such as Profibus-DP), thereby linearly changing the dosing flow rate.

[0048] For dosing pipelines controlled by regulating valves, the control system outputs a signal to the electric actuator (such as AUMA) to precisely adjust the valve opening.

[0049] Meanwhile, a pressure sensor is installed on the outlet pipeline of the dosing pump, and a current sensor is installed in the pump motor circuit. These parameters are monitored in real time. If the operating pressure rises abnormally, it may indicate pipeline blockage, and if the current is abnormal, it may indicate pump jamming. The control system will immediately issue an audible and visual alarm and execute the shutdown protection logic.

[0050] S5: Feedback Optimization Real-time feedback control: Data from the effluent comprehensive monitoring instrument is compared in real time with the "Emission Standard of Air Pollutants for Thermal Power Plants" (GB13223-2011). If a certain indicator (such as Cd) is not specified, the data will be compared with the standard. 2+ If the concentration exceeds the standard for two consecutive sampling cycles, the control system immediately initiates the decision-making process (step S3) to analyze which agent is insufficient or the ratio is imbalanced, and recalculates the dosing parameters for adjustment.

[0051] Periodic Data Mining and Optimization: The control system automatically generates a daily operation report at dawn and initiates a data analysis routine. Through correlation analysis, potential patterns are discovered, such as "under low-load conditions in winter, when burning high-sulfur coal, the PAC dosage needs to be increased by about 5% based on the model's recommended value." These patterns are transformed into empirical rules, used to fine-tune the parameters of the dynamic model or enrich the rule base of fuzzy control, enabling continuous system evolution.

[0052] Example 3 like Figure 2 As shown, this embodiment is based on Embodiments 1 and 2. This embodiment provides a system for implementing the above-mentioned autonomous adjustment method of the desulfurization wastewater dosing device in thermal power plants, which includes: Monitoring module: It consists of the aforementioned electromagnetic flow meter, pH monitor, heavy metal monitor, suspended solids monitor and effluent comprehensive monitor.

[0053] Control module: This is the core processing unit and can be an advanced control station using an industrial-grade PLC (such as the Siemens S7-1500 series) or DCS. It internally stores dynamic mathematical models and runs decision-making programs that integrate intelligent algorithms (such as NN and FLC algorithms).

[0054] The execution module includes a frequency converter-driven dosing pump (for flocculants, neutralizers, etc.) and / or an electrically controlled regulating valve. It receives a 4-20mA control signal from the control module.

[0055] Feedback module: This is essentially handled by the effluent integrated monitoring instrument, whose data is directly connected to the control module.

[0056] All modules are connected via industrial Ethernet or fieldbus to form a complete distributed control system.

[0057] This invention achieves precise matching between chemical dosage and water quality changes through real-time monitoring of multiple parameters and intelligent decision-making, significantly improving the stability and compliance rate of effluent water quality. It avoids the drawbacks of "overdosing" and "underdosing," effectively reducing chemical consumption and secondary treatment costs caused by substandard treatment.

[0058] This invention features fully automated operation, significantly reducing manual intervention, mitigating risks arising from differences in human experience and operational errors, and improving system efficiency. The dynamic model and intelligent algorithms possess self-learning and adaptive capabilities, effectively addressing drastic changes in water quality and quantity caused by variations in coal consumption and load fluctuations, demonstrating strong system robustness. Through continuous feedback and data mining, the system can continuously self-optimize, maintaining optimal operating conditions over the long term.

[0059] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for autonomous adjustment of a chemical dosing device for desulfurization wastewater in a thermal power plant, characterized in that, Includes the following steps: Step S1: Real-time monitoring of multiple parameters: Online monitoring instruments are installed at the inlet, reaction unit and outlet of the desulfurization wastewater treatment system to collect water quality parameters in real time, including wastewater flow rate, pH value, concentration of at least one heavy metal ion and concentration of suspended solids. Step S2: Dynamic Model Construction and Update: Based on historical operating data, wastewater treatment process principles and chemical reaction kinetics, a dynamic mathematical model describing the quantitative relationship between water quality parameters and dosing parameters is constructed, and the model is continuously optimized and updated using real-time monitoring data; Step S3: Intelligent Algorithm Decision: The real-time collected water quality parameters are input into the control system integrated with the intelligent algorithm. The intelligent algorithm combines the dynamic model and the preset treatment target to calculate the optimal dosing parameters under the current operating conditions. Step S4: Automatic adjustment execution: The control system generates control commands based on the optimal dosing parameters to drive the actuators of the dosing device to adjust the actual dosing amount; Step S5: Feedback Optimization: Monitor the water quality at the outlet in real time, and feed the water quality data back to the control system for comparison with the preset standard; if the standard is not met, the control system is triggered to readjust the dosing parameters.

2. The self-adjustment method for the chemical dosing device for desulfurization wastewater in thermal power plants according to claim 1, characterized in that, In step S1, the online monitoring instruments include at least an electromagnetic flow meter, a pH online monitor, a heavy metal ion online monitor, and a suspended solids concentration detector; the collected data is transmitted to the control system in real time via RS485 or industrial Ethernet communication.

3. The self-adjustment method for the chemical dosing device for desulfurization wastewater in thermal power plants according to claim 1, characterized in that, In step S2, the specific process of constructing the dynamic mathematical model includes: establishing an initial model framework based on chemical mechanisms, and calibrating the initial model framework using historical operating data through data fitting and parameter optimization methods; the continuous optimization and update refers to periodically incorporating new real-time monitoring data and corresponding dosing and effluent data into the training set to perform rolling optimization of the parameters of the dynamic mathematical model.

4. The self-adjustment method for the chemical dosing device for desulfurization wastewater in thermal power plants according to claim 1, characterized in that, In step S3, the intelligent algorithm is a neural network algorithm, a fuzzy control algorithm, or a fusion of both. When a neural network algorithm is used, the neural network is trained using historical operating data, with water quality parameters as input and dosing parameters as output. When a fuzzy control algorithm is used, the deviation of water quality parameters is divided into fuzzy intervals, and a dosing adjustment strategy is formulated based on a preset fuzzy rule base.

5. The self-adjustment method for the chemical dosing device for desulfurization wastewater in thermal power plants according to claim 1, characterized in that, In step S4, the actuating element of the dosing device is a dosing pump or a dosing valve; when the actuating element is a dosing pump, the dosing flow rate is changed by adjusting the motor frequency or stroke of the dosing pump; when the actuating element is a dosing valve, the dosing flow rate is controlled by adjusting the opening of the electric valve.

6. The self-adjustment method for the chemical dosing device for desulfurization wastewater in thermal power plants according to claim 5, characterized in that, Step S4 also includes: real-time monitoring of the operating status parameters of the dosing device actuator, including operating pressure and motor current, and alarming or protective shutdown when the parameters are abnormal.

7. The self-adjustment method for the chemical dosing device for desulfurization wastewater in thermal power plants according to claim 1, characterized in that, In step S5, if the effluent water quality does not meet the standards, the control system analyzes the reasons for the exceedance based on the dynamic model and intelligent algorithm, and automatically adjusts the dosing parameters. Step S5 also includes: periodically summarizing and analyzing the historical operating data of the system, exploring operating patterns, and periodically optimizing the dynamic model and intelligent algorithm based on the analysis results.

8. An autonomous adjustment system for a desulfurization wastewater dosing device in a thermal power plant for implementing the method of any one of claims 1-7, characterized in that, include: The monitoring module includes multiple online monitoring instruments installed at different stations in the desulfurization wastewater treatment system for real-time collection of water quality parameters; The control module is communicatively connected to the monitoring module. It stores a dynamic mathematical model and integrates an intelligent algorithm to receive the water quality parameters and output the optimal dosing parameters through calculation. An execution module, connected to the control module, includes a controlled dosing execution element for receiving control commands and adjusting the dosing amount; The feedback module includes an online water quality monitor installed at the water outlet, used to feed back the water quality data of the effluent to the control module.

9. The self-adjusting system for the desulfurization wastewater dosing device in a thermal power plant according to claim 8, characterized in that, The monitoring module includes an electromagnetic flow meter and an online pH monitor installed in the inlet pipe, an online heavy metal ion monitor and a suspended solids concentration detector installed in the reaction tank, and a comprehensive water quality monitor installed in the outlet pipe; the control module is a programmable logic controller (PLC) or a distributed control system (DCS); the dosing actuator in the execution module is a variable frequency dosing pump or an electric regulating valve.

10. The self-adjusting system for the desulfurization wastewater dosing device in a thermal power plant according to claim 8, characterized in that, It also includes a status monitoring unit for monitoring the working status of the execution module. The status monitoring unit includes a pressure sensor and a current sensor. The monitoring module, control module, execution module and feedback module are connected to each other via fieldbus or industrial Ethernet.

Images