Autonomous intelligent adjusting method and system for pH value of desulfurization device of thermal power plant

Abstract

The invention provides a method and a system for autonomously and intelligently adjusting the pH value of a desulfurization device of a thermal power plant. The method comprises the following steps: collecting inlet flue gas parameters, pH values of multiple points in an absorption tower and slurry physical property parameters in real time; transmitting the data to a control system, and dynamically predicting the optimal pH value range required by the current working condition by using a built-in desulfurization reaction model; comparing the actual pH value with a prediction range, generating a desulfurizing agent adding basic instruction, and performing dynamic correction by combining the liquid level and density of the slurry to obtain a final instruction; a high-precision metering pump and a regulating valve are controlled to execute precise adding; meanwhile, the model is self-optimized according to performance index feedback such as desulfurization efficiency and outlet SO2 concentration. Through combination of multi-parameter perception, model prediction feedforward and physical property parameter dynamic correction, the pH value is converted from passive and lagged adjustment to active and accurate intelligent adjustment, the desulfurization efficiency and the system stability are effectively improved, the operation cost is reduced, and environment-friendly up-to-standard emission is ensured.

Description

Technical Field

[0001] This invention relates to the field of flue gas purification technology in thermal power plants, and in particular to an autonomous intelligent adjustment method and system for pH value of desulfurization devices in thermal power plants. Background Technology

[0002] In the limestone-gypsum wet desulfurization process of thermal power plants, the pH value of the slurry in the absorption tower is a key parameter affecting desulfurization efficiency. If the pH value is too high, although the desulfurization efficiency will be improved, it will easily lead to waste of desulfurizing agents (such as limestone), scaling of pipelines, and equipment blockage. If the pH value is too low, the desulfurization reaction rate will decrease, the sulfur dioxide (SO2) absorption will be insufficient, and the SO2 concentration at the outlet will exceed the standard, failing to meet environmental emission requirements.

[0003] Currently, pH adjustment in desulfurization units of thermal power plants mainly relies on two methods: manual experience-based adjustment and simple PID-based customized adjustment. Manual experience-based adjustment involves operators periodically checking pH meter readings and manually adjusting the frequency of the desulfurizing agent supply pump or the valve opening based on experience. This method heavily depends on personal experience, has a slow response time, cannot adapt to rapid changes in flue gas load and SO2 concentration, has poor adjustment accuracy, and is prone to fluctuations in desulfurization efficiency or material waste. Simple PID-based setpoint adjustment involves setting a fixed pH target and using a PID controller to adjust the amount of desulfurizing agent added based on the deviation between the measured pH value and the set value. While this method achieves automation, it is a "post-event adjustment" and a single-loop control, failing to consider the feedforward effects of inlet flue gas parameters (such as SO2 concentration, flue gas volume, and temperature) and the impact of changes in the slurry's own properties (such as density and liquid level) on the reaction environment. When operating conditions fluctuate significantly, PID regulation also suffers from overshoot, oscillation, or slow response, resulting in unsatisfactory control performance.

[0004] Therefore, there is an urgent need in this field for a pH autonomous intelligent regulation scheme that can comprehensively consider multiple influencing factors, has predictive and self-learning capabilities, and can achieve precise feedforward-feedback composite regulation. Summary of the Invention

[0005] The purpose of this invention is to provide an autonomous intelligent adjustment method and system for pH value of desulfurization equipment in thermal power plants, so as to achieve rapid, accurate and stable control of pH value, thereby improving desulfurization efficiency, reducing desulfurizing agent consumption and ensuring long-term stable operation of the unit.

[0006] According to one objective of the present invention, the present invention provides an autonomous intelligent adjustment method for pH value of a desulfurization unit in a thermal power plant, comprising the following steps: S1. Real-time data acquisition of multiple parameters: Real-time acquisition of flue gas parameters at the inlet flue of the desulfurization unit, pH value parameters of the slurry in the absorption tower, and physical property parameters of the slurry. S2. Data Processing and Dynamic Prediction of Target pH Value: The real-time data collected in step S1 is sent to the control system through a data transmission network; based on the real-time data, the control system dynamically calculates the optimal pH value range required to achieve the target desulfurization efficiency under the current operating conditions using a built-in desulfurization reaction model. S3. Intelligent decision-making and dynamic correction of desulfurizer addition: The control system compares the actual average pH value collected in step S1 with the target pH range obtained in step S2, and generates a basic adjustment command for the amount of desulfurizer added based on the comparison result; at the same time, it dynamically corrects the basic adjustment command according to the real-time collected slurry level and slurry density, and generates the final adjustment command. S4. Precise addition and execution of desulfurizing agent: The control system sends the final adjustment command to the desulfurizing agent addition unit, and the desulfurizing agent addition unit precisely adjusts the addition flow rate of the desulfurizing agent according to the command; S5. Closed-loop feedback and model self-optimization: Real-time monitoring of the performance indicators of the desulfurization system and comparison of the performance indicators with the expected values. If the performance indicators continue to deviate from the expectations, the model optimization mechanism is triggered to correct and update the parameters of the desulfurization reaction model using historical operating data.

[0007] Further, in step S1, the flue gas parameters include at least SO2 concentration, flue gas flow rate, and flue gas temperature; the pH value parameter is the pH value measured by pH sensors installed at at least two different height positions inside the absorption tower; the physical property parameters include at least slurry level and slurry density; and the actual average pH value is the arithmetic mean or weighted average of the readings of the at least two pH sensors.

[0008] Furthermore, in step S2, the desulfurization reaction model is a prediction model trained based on the desulfurization chemical reaction mechanism and historical operating data; the input variables of the desulfurization reaction model include at least the inlet SO2 concentration, flue gas flow rate, and flue gas temperature, and the output variable is the recommended target pH range.

[0009] Further, in step S3, the "generating a basic adjustment instruction for the amount of desulfurizer added based on the comparison results" specifically means: using a PID control algorithm, a fuzzy control algorithm, or a fuzzy PID control algorithm to generate the basic adjustment instruction based on the deviation between the actual average pH value and the target pH value range.

[0010] Further, in step S3, the "dynamic correction of the basic adjustment command based on the real-time collected slurry level and slurry density" specifically means: pre-establishing the correction coefficient relationship between slurry level and density and the amount of desulfurizer added, querying the relationship based on the real-time level and density to obtain the correction coefficient, and multiplying the basic adjustment command by the correction coefficient to obtain the final adjustment command.

[0011] Furthermore, in step S4, the desulfurizing agent addition unit includes a high-precision metering pump and a regulating valve, and the addition flow rate of the desulfurizing agent is changed by adjusting the rotation speed of the high-precision metering pump and / or the opening degree of the regulating valve.

[0012] According to another objective of the present invention, the present invention provides an autonomous intelligent regulation system for implementing the above-described method, comprising: The data acquisition module is used to collect flue gas parameters, slurry pH value parameters, and slurry physical property parameters in real time; A data transmission network is used to transmit the data collected by the data acquisition module to the control system in real time. The control system has a built-in data processing unit, a desulfurization reaction model unit, and a decision control unit, and is used to execute the steps of the method as described in any one of claims 1-6; The desulfurizing agent addition unit is used to receive the final adjustment command from the control system and precisely execute the desulfurizing agent addition operation.

[0013] Furthermore, the data acquisition module includes: A flue gas analyzer set installed on the inlet flue of the desulfurization unit is used to monitor SO2 concentration, flue gas flow rate and flue gas temperature; At least two pH sensors are installed at different heights inside the absorption tower; Level and density sensors are installed on the absorption tower.

[0014] Furthermore, the core of the control system is an industrial control computer or a programmable logic controller (PLC); the data processing unit is used to filter and normalize the received data; the desulfurization reaction model unit is used to run a hybrid prediction model based on mechanism and data; and the decision control unit is used to employ a fuzzy PID control algorithm and execute the dynamic correction.

[0015] Furthermore, the desulfurizing agent addition unit includes a high-precision metering pump and a regulating valve; the high-precision metering pump has an accuracy level better than 0.5%; the desulfurizing agent addition flow rate is changed by adjusting the rotation speed of the high-precision metering pump and / or the opening degree of the regulating valve.

[0016] This invention's technical solution completely changes the outdated traditional control mode that relies on manual experience or simple PID setpoints by constructing an autonomous intelligent control method that integrates multi-parameter real-time monitoring, model prediction, intelligent decision-making, and closed-loop self-optimization. By introducing inlet flue gas parameters and combining them with a desulfurization reaction model to dynamically predict the target pH value, it achieves proactive and forward-looking control of operating conditions from a feedforward perspective, significantly overcoming the lag of traditional feedback control and providing a faster response. By comprehensively considering multi-dimensional data such as pH values, slurry levels, and densities at multiple points within the absorption tower and dynamically correcting the control commands, the control strategy better fits the complex reaction environment within the tower, greatly improving the accuracy of pH control and system stability. Through closed-loop feedback and model self-optimization mechanisms, the system possesses continuous learning and adaptability, enabling it to cope with long-term disturbances such as fluctuations in desulfurizing agent quality and equipment performance degradation. This ensures desulfurization efficiency and stable emission compliance while effectively avoiding excessive addition of desulfurizing agent, achieving significant energy savings, reduced consumption, and lower operating costs. 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 method for autonomous intelligent adjustment of pH value in a desulfurization unit of a thermal power plant includes the following steps: Step S1: Real-time data acquisition of multiple parameters: Real-time acquisition of flue gas parameters at the inlet flue of the desulfurization unit, pH value parameters of the slurry in the absorption tower, and physical property parameters of the slurry. Step S2, Data Processing and Dynamic Prediction of Target pH Value: The real-time data collected in step S1 is sent to the control system through a data transmission network; based on the real-time data, the control system dynamically calculates the optimal pH value range required to achieve the target desulfurization efficiency under the current operating conditions using a built-in desulfurization reaction model. Step S3, Intelligent decision-making and dynamic correction of desulfurizer addition: The control system compares the actual average pH value collected in step S1 with the target pH range obtained in step S2, and generates a basic adjustment command for the amount of desulfurizer added based on the comparison result; at the same time, the control system dynamically corrects the basic adjustment command based on the real-time collected slurry level and slurry density, and generates the final adjustment command. Step S4, Precise addition and execution of desulfurizing agent: The control system sends the final adjustment command to the desulfurizing agent addition unit, and the desulfurizing agent addition unit precisely adjusts the addition flow rate of the desulfurizing agent according to the command; Step S5, Closed-loop feedback and model self-optimization: Monitor the performance indicators of the desulfurization system in real time and compare the performance indicators with the expected values. If the performance indicators continue to deviate from the expectations, the model optimization mechanism is triggered to correct and update the parameters of the desulfurization reaction model using historical operating data.

[0022] Specifically, in step S1, the flue gas parameters include at least SO2 concentration, flue gas flow rate, and flue gas temperature; the pH value parameter is the pH value measured by pH sensors installed at at least two different height positions inside the absorption tower, and the actual average pH value is the arithmetic mean or weighted average of the readings of the at least two pH sensors; in step S1, the physical property parameters include at least slurry level and slurry density.

[0023] Specifically, in step S2, the desulfurization reaction model is a prediction model trained based on the desulfurization chemical reaction mechanism and historical operation data. The desulfurization reaction model is one of the following: a neural network model, a support vector machine model, or a random forest model, or a hybrid model of the model and the mechanism model. The input variables of the desulfurization reaction model include at least the inlet SO2 concentration, flue gas flow rate, and flue gas temperature, and the output variable is the recommended target pH range.

[0024] Specifically, in step S3, the "generating a basic adjustment instruction for the amount of desulfurizer added based on the comparison results" specifically means: using a PID control algorithm, a fuzzy control algorithm, or a fuzzy PID control algorithm to generate the basic adjustment instruction based on the deviation between the actual average pH value and the target pH value range.

[0025] In step S3, the step of "dynamically correcting the basic adjustment command based on the real-time collected slurry level and slurry density" specifically involves: establishing a correction coefficient relationship between slurry level and density and the amount of desulfurizer added in advance; querying the relationship based on the real-time level and density to obtain the correction coefficient; and multiplying the basic adjustment command by the correction coefficient to obtain the final adjustment command.

[0026] Specifically, in step S4, the desulfurizing agent addition unit includes a high-precision metering pump and a regulating valve, and the addition flow rate of the desulfurizing agent is changed by adjusting the rotation speed of the high-precision metering pump and / or the opening degree of the regulating valve.

[0027] Specifically, in step S5, the performance indicators include at least the actual desulfurization efficiency and the net flue gas SO2 concentration; the model optimization mechanism is triggered periodically or by a performance indicator deviation event.

[0028] like Figure 2 As shown, an autonomous intelligent regulation system for implementing the above method includes: The data acquisition module is used to collect flue gas parameters, slurry pH value parameters, and slurry physical property parameters in real time; A data transmission network is used to transmit the data collected by the data acquisition module to the control system in real time. The control system has a built-in data processing unit, a desulfurization reaction model unit, and a decision control unit, which are used to execute the steps of the above-mentioned autonomous intelligent adjustment method for pH value of the desulfurization device in thermal power plants. The desulfurizing agent addition unit is used to receive the final adjustment command from the control system and precisely execute the desulfurizing agent addition operation.

[0029] Specifically, the data acquisition module includes: A flue gas analyzer set installed on the inlet flue of the desulfurization unit is used to monitor SO2 concentration, flue gas flow rate and flue gas temperature; At least two pH sensors are installed at different heights inside the absorption tower; Level and density sensors are installed on the absorption tower.

[0030] Specifically, the core of the control system is an industrial control computer or a programmable logic controller (PLC).

[0031] Specifically, the desulfurizing agent addition unit includes a high-precision metering pump and a regulating valve, wherein the high-precision metering pump has an accuracy level better than 0.5%.

[0032] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the above-described method for autonomous intelligent adjustment of pH value in a desulfurization unit of a thermal power plant.

[0033] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method for autonomous intelligent adjustment of pH value in a desulfurization unit of a thermal power plant.

[0034] A desulfurization device for a thermal power plant is equipped with the aforementioned autonomous intelligent regulation system.

[0035] Example 2 This embodiment, based on Embodiment 1, provides a construction strategy for an autonomous intelligent pH adjustment system for a desulfurization unit in a thermal power plant: like Figure 2 As shown, the autonomous intelligent control system of this embodiment is applied to the limestone-gypsum wet desulfurization unit of a 1000MW unit, including: Data acquisition module: A CEMS flue gas analyzer is installed on the inlet flue of the desulfurization unit to measure SO2 concentration in real time (range: 0-5000 mg / m³). 3 ), flue gas flow rate (range: 0-3 million m³) 3 / h) and flue gas temperature (range: 0-150℃).

[0036] Inside the absorption tower, three pH sensors are installed from top to bottom: above the spray layer, in the middle, and at the inlet of the circulating pump. These sensors are used to comprehensively reflect the pH distribution of the slurry (measurement range: 3-7).

[0037] A radar level gauge (measuring range: 0-15m) and an online density meter (measuring range: 1000-1300 kg / m³) are installed on the absorption tower body. 3 ).

[0038] Data transmission network: Industrial Ethernet and Profibus-DP bus are used to transmit the above sensor data to the control system in real time and stably.

[0039] Control system: Utilizing a high-performance industrial control computer as its core, running configuration software and advanced algorithm programs. The system includes: Data processing unit: Performs median filtering and moving average filtering on the received raw data to eliminate spike interference, and normalizes all parameters to the [0,1] interval for easy model processing.

[0040] Desulfurization reaction model unit: This unit's built-in model is a hybrid model based on a BP neural network and a material balance equation. The input layer of the neural network consists of normalized inlet SO2 concentration, flue gas flow rate, and flue gas temperature; the hidden layer has 10 nodes; and the output layer is the recommended target pH value. The material balance equation is used to physically constrain and verify the rationality of the neural network's output.

[0041] Decision control unit: This unit employs a fuzzy PID control algorithm. Its input is pH. avg Compared with the target pH value, the median pH value target The deviation e and the rate of change of deviation ec are output as the basic change in the amount of desulfurizer added. At the same time, the unit has a built-in correction coefficient lookup table based on the slurry level and density. The basic change is multiplied and corrected according to the real-time level and density to generate a control signal (4-20mA) sent to the actuator.

[0042] The desulfurizing agent addition unit includes a diaphragm-type high-precision metering pump (accuracy 0.5%) and an electric regulating valve. The metering pump provides power and basic flow, while the regulating valve performs rapid and fine adjustments. Working together, they receive a 4-20mA signal from the control system to precisely control the addition flow rate of the limestone slurry.

[0043] Example 3 This embodiment, based on Embodiments 1 and 2, provides a method for autonomous intelligent adjustment of pH value in a desulfurization unit of a thermal power plant, such as... Figure 1 As shown, the operation process of this method is as follows: System initialization and model training: In the initial stage of system commissioning, stable operating data of the unit under different loads and coal types are collected, including inlet flue gas parameters, slurry physical property parameters, pH value, and corresponding desulfurization efficiency. This data is used to train the neural network part of the desulfurization reaction model offline until its prediction error is less than 2%. Simultaneously, the control parameters and physical property correction coefficient table of the fuzzy PID controller are initialized.

[0044] Running in real time: The system is powered on, and all sensors begin operating. Assume that at a certain moment, the collected data is: Inlet SO2 concentration = 2500 mg / m³ 3 Flue gas flow rate = 2.2 million m³ 3 / h, flue gas temperature = 120℃, three pH sensor readings are 5.2, 5.1, 5.3 respectively, slurry level = 8.5m, slurry density = 1150 kg / m³ 3 .

[0045] The data is transmitted to the control system via the network. The data processing unit calculates the average pH value. avg =5.2.

[0046] The desulfurization reaction model unit receives the normalized flue gas parameters, calculates them through a neural network, and verifies the material balance to output the target pH range under the current operating conditions as [5.4, 5.6].

[0047] The decision control unit detects pH avg (5.2) <pH target min(5.4), the deviation e is negative. Based on the fuzzy PID rule and the current slurry properties (medium to high liquid level, normal density), it is calculated that the amount of desulfurizing agent needs to be increased by 8% from the current level.

[0048] The instruction (+8%) was sent to the desulfurizer addition unit. The high-precision metering pump and regulating valve worked in tandem to precisely increase the limestone slurry flow rate by 8%.

[0049] Feedback optimization: After increasing the amount of desulfurizing agent, the system continuously monitored the desulfurization efficiency (from 95.5% to 96.8%) and the SO2 concentration in the clean flue gas (from 45 mg / m³). 3 Reduced to 28 mg / m 3 ).

[0050] After one week of operation, it was found that even with the desulfurizing agent dosage maintained at a high level, the desulfurization efficiency slowly decreased to 95.8%. The model optimization mechanism was triggered.

[0051] The control system retrieved and analyzed operating data from the past week. Through data mining, it was discovered that, under similar inlet conditions, the required pH setpoint to achieve the same desulfurization efficiency was 0.1 points higher than the original model prediction. The system determined that this might be due to a slight decrease in the reactivity of the new batch of limestone.

[0052] Therefore, the system automatically fine-tuned the desulfurization reaction model, appropriately increasing the output of the target pH value. Subsequently, the system operated under the new model parameters, and the desulfurization efficiency recovered to over 96.5%.

[0053] Through the implementation of this embodiment, the pH control standard deviation of the desulfurization device in the thermal power plant was reduced from 0.35 under manual control to less than 0.15, the average consumption of limestone slurry was reduced by about 5%, the annual cost savings were significant, and the annual emission compliance rate was 100%.

[0054] This invention integrates multi-dimensional parameters such as flue gas, slurry pH (measured at multiple points), and slurry properties, providing a comprehensive and reliable data foundation for intelligent decision-making and overcoming the limitations and biases of single pH measurement. Employing a fusion model driven by both mechanism and data, it can predict the required pH value in advance based on changes in inlet conditions, achieving a shift from "passive feedback" to "active feedforward," resulting in faster response and more advanced control.

[0055] This invention's control strategy not only considers pH deviation but also introduces dynamic correction of slurry physical properties, making the adjustment more consistent with the actual reaction environment within the tower. Simultaneously, it incorporates closed-loop feedback and a model self-learning mechanism, enabling the system to adapt to long-term disturbances such as changes in desulfurizing agent quality and equipment performance degradation, maintaining optimal control at all times. The use of high-precision metering pumps and regulating valves as actuators ensures accurate addition at low flow rates, avoiding over- or under-adjustment and guaranteeing long-term stable operation of the pH value and the desulfurization system.

[0056] This invention, through precise control, minimizes the excessive addition of desulfurizing agents while ensuring desulfurization efficiency, thereby reducing operating costs (chemical consumption, electricity consumption) and solid waste generation, while ensuring emissions meet standards, thus achieving both economic and environmental benefits.

[0057] 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 intelligent adjustment of pH value in a desulfurization unit of a thermal power plant, characterized in that, Includes the following steps: S1. Real-time data acquisition of multiple parameters: Real-time acquisition of flue gas parameters at the inlet flue of the desulfurization unit, pH value parameters of the slurry in the absorption tower, and physical property parameters of the slurry. S2. Data Processing and Dynamic Prediction of Target pH Value: The real-time data collected in step S1 is sent to the control system through a data transmission network; based on the real-time data, the control system dynamically calculates the optimal pH value range required to achieve the target desulfurization efficiency under the current operating conditions using a built-in desulfurization reaction model. S3. Intelligent decision-making and dynamic correction of desulfurizer addition amount: The control system compares the actual average pH value collected in step S1 with the target pH value range obtained in step S2, and generates a basic adjustment command for the amount of desulfurizer addition based on the comparison result. Simultaneously, based on the real-time collected slurry level and slurry density, the basic adjustment command is dynamically corrected to generate the final adjustment command; S4. Precise addition and execution of desulfurizing agent: The control system sends the final adjustment command to the desulfurizing agent addition unit, and the desulfurizing agent addition unit precisely adjusts the addition flow rate of the desulfurizing agent according to the command; S5. Closed-loop feedback and model self-optimization: Real-time monitoring of the performance indicators of the desulfurization system and comparison of the performance indicators with the expected values. If the performance indicators continue to deviate from the expectations, the model optimization mechanism is triggered to correct and update the parameters of the desulfurization reaction model using historical operating data.

2. The method for autonomous intelligent adjustment of pH value in a desulfurization unit of a thermal power plant according to claim 1, characterized in that, In step S1, the flue gas parameters include at least SO2 concentration, flue gas flow rate, and flue gas temperature; the pH value parameter is the pH value measured by pH sensors installed at at least two different height positions inside the absorption tower; the physical property parameters include at least slurry level and slurry density; and the actual average pH value is the arithmetic mean or weighted average of the readings of the at least two pH sensors.

3. The method for autonomous intelligent adjustment of pH value in a desulfurization unit of a thermal power plant according to claim 1, characterized in that, In step S2, the desulfurization reaction model is a prediction model trained based on the desulfurization chemical reaction mechanism and historical operating data; the input variables of the desulfurization reaction model include at least the inlet SO2 concentration, flue gas flow rate, and flue gas temperature, and the output variable is the recommended target pH range.

4. The method for autonomous intelligent adjustment of pH value in a desulfurization unit of a thermal power plant according to claim 1, characterized in that, In step S3, the "generating a basic adjustment instruction for the amount of desulfurizer added based on the comparison results" specifically means: using a PID control algorithm, a fuzzy control algorithm, or a fuzzy PID control algorithm to generate the basic adjustment instruction based on the deviation between the actual average pH value and the target pH value range.

5. The method for autonomous intelligent adjustment of pH value in a desulfurization unit of a thermal power plant according to claim 1, characterized in that, In step S3, the step of "dynamically correcting the basic adjustment command based on the real-time collected slurry level and slurry density" specifically involves: establishing a correction coefficient relationship between slurry level and density and the amount of desulfurizer added in advance; querying the relationship based on the real-time level and density to obtain the correction coefficient; and multiplying the basic adjustment command by the correction coefficient to obtain the final adjustment command.

6. The method for autonomous intelligent adjustment of pH value in a desulfurization unit of a thermal power plant according to claim 1, characterized in that, In step S4, the desulfurizing agent addition unit includes a high-precision metering pump and a regulating valve. The addition flow rate of the desulfurizing agent is changed by adjusting the rotation speed of the high-precision metering pump and / or the opening degree of the regulating valve.

7. An autonomous intelligent adjustment system for implementing the method of any one of claims 1-6, characterized in that, include: The data acquisition module is used to collect flue gas parameters, slurry pH value parameters, and slurry physical property parameters in real time; A data transmission network is used to transmit the data collected by the data acquisition module to the control system in real time. The control system has a built-in data processing unit, a desulfurization reaction model unit, and a decision control unit, and is used to execute the steps of the method as described in any one of claims 1-6; The desulfurizing agent addition unit is used to receive the final adjustment command from the control system and precisely execute the desulfurizing agent addition operation.

8. The autonomous intelligent adjustment system according to claim 7, characterized in that, The data acquisition module includes: A flue gas analyzer set installed on the inlet flue of the desulfurization unit is used to monitor SO2 concentration, flue gas flow rate and flue gas temperature; At least two pH sensors are installed at different heights inside the absorption tower; Level and density sensors are installed on the absorption tower.

9. The autonomous intelligent adjustment system according to claim 7, characterized in that, The core of the control system is an industrial control computer or a programmable logic controller (PLC); the data processing unit is used to filter and normalize the received data; the desulfurization reaction model unit is used to run a hybrid prediction model based on mechanism and data; and the decision control unit is used to employ a fuzzy PID control algorithm and execute the dynamic correction.

10. The autonomous intelligent adjustment system according to claim 7, characterized in that, The desulfurizing agent addition unit includes a high-precision metering pump and a regulating valve; the high-precision metering pump has an accuracy level better than 0.5%; the addition flow rate of the desulfurizing agent is changed by adjusting the rotation speed of the high-precision metering pump and / or the opening degree of the regulating valve.

Images