Power plant chemical equipment dosing flow control system with fault diagnosis function

Abstract

The invention relates to the technical field of fault diagnosis, and discloses a power plant chemical equipment dosing flow control system with a fault diagnosis function, which is provided with a dosing flow control module, a data acquisition module, a fault diagnosis module and a control module. And state estimation is carried out through a particle filter algorithm based on an input and output relation of a system model and real-time data, and potential faults are identified in time and a control strategy is optimized. And parameters of the dosing flow control system model are continuously updated by using an incremental system identification algorithm, future fault risks are predicted based on deviation, a fault alarm and a control strategy are generated, and the stability and reliability of the system are ensured. A particle filter algorithm and an incremental system identification algorithm are combined, and real-time sensor data are utilized to perform accurate fault diagnosis on the dosing flow control system, so that accurate fault diagnosis and intelligent control adjustment are realized, the dosing flow control accuracy is improved, the influence of equipment faults on system operation is reduced, and the system reliability is improved. The automatic regulation capability of the system is enhanced, the operation efficiency and stability of chemical equipment of a power plant are improved, and finally the accuracy and reliability of the dosing flow are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of fault diagnosis, and in particular to a chemical equipment dosing flow control system for a power plant with a fault diagnosis function. Background Art

[0002] The dosing system is an integral part of a power plant's chemical equipment. Its primary function is to precisely add chemicals based on water treatment needs to regulate water quality, control corrosion, prevent scaling, and ensure safe equipment operation. Precise dosing flow control is crucial for protecting equipment, extending service life, and improving system efficiency in power plant boilers, cooling towers, and circulating water systems. A dosing flow control system adjusts chemical flow through real-time monitoring, ensuring accurate and timely dosing, thereby maintaining optimal equipment operation and preventing malfunctions or damage caused by improper dosing.

[0003] However, in actual applications, existing power plant chemical equipment dosing flow control systems fail to effectively diagnose faults during the dosing process. When a fault occurs, the system fails to detect and handle it in a timely manner, resulting in unstable dosing flow, degraded equipment performance, and even equipment damage, causing additional downtime and maintenance costs for the power plant. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a power plant chemical equipment dosing flow control system with a fault diagnosis function to solve the problem that the current power plant chemical equipment dosing flow control system cannot effectively diagnose equipment faults during the dosing process in actual applications.

[0005] The present invention discloses a dosing flow control system for chemical equipment in a power plant with a fault diagnosis function, the system comprises a dosing flow control module, a data acquisition module, a fault diagnosis module and a control module; wherein,

[0006] The dosing flow control module is used to control the flow of the dosing pump and adjust the amount of the drug output to the chemical equipment based on the flow;

[0007] The data acquisition module is used to collect real-time sensor data related to the dosing flow rate; the sensor data includes dosing flow rate, pressure, and temperature;

[0008] The fault diagnosis module is used to receive the sensor data sent by the data acquisition module, perform fault diagnosis on the dosing flow control system based on the sensor data through a particle filter algorithm and an incremental identification algorithm, and output a diagnosis result;

[0009] The control module is used to generate control instructions according to the diagnosis results and the comprehensive dosing flow data, and adjust the operation of the dosing flow control module based on the control instructions; the comprehensive dosing flow data includes the collected dosing flow value and the dosing flow set value.

[0010] Furthermore, before performing fault diagnosis on the dosing flow control system based on sensor data by using a particle filter algorithm and an incremental identification algorithm, it also includes constructing a dosing flow control system model.

[0011] Furthermore, the process of constructing the dosing flow control system model includes:

[0012] Determine the input-output relationship of the dosing flow control system and establish the physical relationship between the input and output through mathematical modeling; wherein the input includes the control signal, operating conditions and external influencing factors, and the output includes the device response;

[0013] Establishing a mathematical model describing the dynamic behavior of the dosing flow control system according to the device characteristics of the dosing flow control system and the determined input-output relationship, and using the mathematical model as a dosing flow control system model;

[0014] Based on the initial state of the equipment, equipment parameters and environmental conditions, the dosing flow control system model is initialized, and the initial dosing flow control system state estimation value is set.

[0015] Furthermore, the control signal includes a dosing flow setting value, pump speed adjustment, and valve opening adjustment;

[0016] The operating conditions include operating temperature and operating pressure;

[0017] The external influencing factors include fluctuations in power supply voltage, temperature and humidity inside the power plant, and changes in chemical supply;

[0018] The device response includes the output of the flow sensor, the reading of the pressure sensor, the working status of the pump, and the valve opening;

[0019] The equipment characteristics include the performance curve of the pump, the adjustment characteristics of the valve, the pipeline characteristics, and the sensor characteristics.

[0020] Furthermore, the fault diagnosis of the dosing flow control system based on sensor data by using the particle filter algorithm and the incremental identification algorithm includes:

[0021] The particle filter algorithm is used to estimate the state of the dosing flow control system in real time based on the sensor data, and the state estimation is updated. Based on the updated state estimation, it is determined whether there is a fault, and a first determination result is obtained.

[0022] The incremental identification algorithm continuously trains and updates the model parameters of the dosing flow control system based on sensor data, determines the deviation between the actual behavior of the dosing flow control system and the expected behavior, and predicts future failure risks based on the deviation to obtain the first prediction result;

[0023] The first judgment result and the first prediction result are used as the diagnosis result.

[0024] Furthermore, the particle filter algorithm includes the following operations:

[0025] According to the initial state of the dosing flow control system and the constructed dosing flow control system model, a particle set is generated and assigned corresponding initial weights; each particle represents a hypothesis of the dosing flow control system state;

[0026] Determine the system state equation based on the dosing flow control system model, and update the particle weights based on the sensor data and the system state equation;

[0027] Calculate the input-output relationship of the dosing flow control system model and update the particle state based on the calculation results;

[0028] Resample according to the updated particle weights and particle states to generate a new particle set;

[0029] A weighted average operation is performed on the new particle set to obtain the final estimation result of the system state, and based on the final estimation result, it is determined whether the dosing flow control system has a fault.

[0030] Furthermore, the incremental identification algorithm includes the following operations:

[0031] The mathematical model of the dosing flow control system is updated based on the real-time collected sensor data and system input and output data through the incremental identification algorithm;

[0032] Calculate the deviation of system behavior based on the difference between the output of the current dosing flow control system model and the actual measurement data;

[0033] A deviation threshold is set based on the historical behavior pattern of the dosing flow control system and the known normal behavior range. When the calculated system behavior deviation exceeds the deviation threshold, it is considered that the system has a potential fault; and within a preset time period, it is determined whether the deviation gradually increases or persists. If it is judged to be so, the probability of fault occurrence and future risk points are predicted based on historical trends, and a fault risk warning is generated.

[0034] Furthermore, in the process of updating the mathematical model of the dosing flow control system by using the incremental identification algorithm, the recursive least square method is used to adjust the model parameters.

[0035] Furthermore, the control decision module adopts a fault warning strategy and a fault compensation strategy:

[0036] The fault warning strategy includes generating a warning signal when a potential fault is detected and notifying an operator of the warning signal;

[0037] The fault compensation strategy includes generating an alarm signal after a fault is detected, notifying an operator of the alarm signal, and adjusting the operation of the dosing flow control module.

[0038] Furthermore, the control module generates control instructions based on the diagnosis results and the comprehensive dosing flow data, including:

[0039] Identify the fault type based on the diagnosis result, and generate a corresponding corrected dosing flow instruction according to the identified fault type;

[0040] Calculate the correction amount based on the comprehensive dosing flow data;

[0041] The modified dosing flow instruction is modified based on the correction amount to generate a control instruction.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] The present invention is provided with a dosing flow control module, a data acquisition module, a fault diagnosis module and a control module. Based on the monitored dosing flow, pressure, temperature and other sensor data, and based on the input-output relationship and real-time data of the system model, a particle filter algorithm is used to perform state estimation, timely identify potential faults and optimize the control strategy. The incremental system identification algorithm is also used to continuously update the parameters of the dosing flow control system model, predict future fault risks based on deviations, generate fault alarms and control strategies, and ensure the stability and reliability of the system. By combining the particle filter algorithm and the incremental system identification algorithm, the dosing flow control system is accurately diagnosed using real-time sensor data, achieving accurate fault diagnosis and intelligent control adjustment, improving the accuracy of dosing flow control, reducing the impact of equipment failures on system operation, enhancing the system's autonomous adjustment capability, improving the operating efficiency and stability of the power plant's chemical equipment, and ultimately ensuring the accuracy and reliability of the dosing flow. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute part of the economic application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0045] Figure 1 This is a structural schematic diagram of a chemical dosing flow control system for power plant chemical equipment with a fault diagnosis function disclosed in another embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0047] Example 1

[0048] The present invention discloses a power plant chemical equipment dosing flow control system with a fault diagnosis function, please refer to Figure 1 , Figure 1 This is a schematic diagram of a structure of a chemical dosing flow control system for power plant chemical equipment with a fault diagnosis function disclosed in an embodiment of the present invention. The system includes a dosing flow control module, a data acquisition module, a fault diagnosis module, and a control module; wherein,

[0049] The dosing flow control module is used to control the flow of the dosing pump and adjust the amount of medicine output to the chemical equipment based on the flow rate;

[0050] The data acquisition module is used to collect real-time sensor data related to the dosing flow rate, including but not limited to dosing flow rate, pressure, and temperature.

[0051] The fault diagnosis module is used to receive the sensor data sent by the data acquisition module, perform fault diagnosis on the dosing flow control system based on the sensor data through the particle filter algorithm and the incremental identification algorithm, and output the diagnosis results.

[0052] The control module is used to generate control instructions based on the diagnosis results and the comprehensive dosing flow data, and adjust the operation of the dosing flow control module based on the control instructions. The comprehensive dosing flow data includes the collected dosing flow value and the dosing flow set value.

[0053] Furthermore, before performing fault diagnosis on the dosing flow control system based on sensor data by using a particle filter algorithm and an incremental identification algorithm, it also includes constructing a dosing flow control system model.

[0054] The process of building a dosing flow control system model includes:

[0055] Determine the input-output relationship of the dosing flow control system and establish the physical relationship between input and output through mathematical modeling. Inputs include control signals, operating conditions, and external influencing factors, while outputs include device responses.

[0056] Establishing a mathematical model describing the dynamic behavior of the dosing flow control system according to the device characteristics of the dosing flow control system and the determined input-output relationship, and using the mathematical model as a dosing flow control system model;

[0057] Based on the initial state of the equipment, equipment parameters and environmental conditions, the dosing flow control system model is initialized, and the initial dosing flow control system state estimation value is set.

[0058] Specifically, in the embodiments of the present invention, the initial state of a device refers to the state of the device before system startup or a fault occurs. Examples include the initial flow rate of a pump and the initial opening of a valve. Device parameters refer to the physical properties of the device, such as the maximum flow rate of a pump, the opening range of a valve, and the accuracy of a sensor. These parameters are obtained from manufacturer manuals or experimental measurements. Environmental conditions refer to the environmental conditions that affect device performance during operation, such as temperature, humidity, and system load.

[0059] The control signal refers to a specific instruction or target value used to regulate the operation of the dosing flow control system, including but not limited to the dosing flow set value, pump speed adjustment, and valve opening adjustment. Operating conditions refer to the environmental or internal conditions to which the system is subjected during operation, including operating temperature, operating pressure, etc. External influencing factors refer to factors outside the system that may affect the dosing flow control system. They are usually uncontrollable, but still need to be considered in the model to ensure that the system can adapt to different external conditions, including but not limited to power supply voltage fluctuations, temperature and humidity inside the power plant, changes in chemical supply, and equipment aging or wear.

[0060] Equipment response refers to the reaction of the equipment to the input signal in the dosing flow control system. It is mainly measured by the actual output data obtained by the sensor, including but not limited to the output of the flow sensor, the reading of the pressure sensor, the working status of the pump, and the valve opening.

[0061] Device characteristics refer to the basic parameters and operational characteristics of each device in a system. These characteristics affect how the device responds to input signals (such as control signals or operating conditions) and how it performs under different operating conditions. Device characteristics include, but are not limited to, pump performance curves, valve regulation characteristics, piping characteristics, and sensor characteristics.

[0062] Pump performance curves describe the relationship between flow and pressure under different operating conditions. These curves display information such as the pump's maximum flow, maximum head, and efficiency, helping to determine the pump's efficiency and flow control capabilities under different operating conditions. These curves are related to factors such as pump speed and load. For example, the pressure provided by the pump or the pump's operating point at different flow demands.

[0063] A valve's regulating characteristics describe its response when regulating flow, including the relationship between valve opening and flow rate, as well as the valve's regulating accuracy. For example, how a change in valve opening from 0 to 100% affects flow rate, or the valve's ability to adjust over different flow ranges.

[0064] Pipeline characteristics include factors such as the length, diameter, material, and surface smoothness of the pipe, which affect the flow characteristics of the fluid, including flow resistance, friction loss, etc. For example, long pipes and thick pipes may result in greater pressure drop, while short pipes and smooth surfaces may reduce resistance.

[0065] Sensor characteristics refer to the sensor's accuracy, sensitivity, response time, measurement range, and operating conditions. For example, the measurement accuracy of a flow sensor, the response speed of a pressure sensor, and the operating range of a temperature sensor.

[0066] Device characteristics can help understand and predict device behavior under specific operating conditions, ensuring that the system can perform its tasks accurately and efficiently. In a dosing flow control system, by incorporating device characteristics into the mathematical model, it is possible to ensure that the dosing flow and system performance meet the desired targets. Furthermore, these device characteristics are crucial for incremental system identification and particle filter algorithms in fault diagnosis because they form the foundation for modeling, provide essential information about the system's dynamics, and help identify and correct potential faults in the system.

[0067] In an embodiment of the present invention, the dosing flow control system model includes an observation equation, an input-output relationship equation, and a system state equation. Among them, the observation equation is used to link actual observations (such as sensor data) with the system state, indicating how the observation data (such as the real-time flow of the dosing flow sensor) is derived from the internal state of the system (such as the flow regulation state of the pump). The input-output relationship equation is used to describe how the device response is mapped to parameters such as control signals and operating conditions. The system state equation is used to describe the dynamic behavior and state evolution of the system, for example, how the system flow, pressure, etc. change over time and which control inputs affect them.

[0068] Furthermore, the particle filter algorithm and the incremental identification algorithm are used to perform fault diagnosis on the dosing flow control system based on sensor data, including:

[0069] The particle filter algorithm is used to estimate the state of the dosing flow control system in real time based on the sensor data, and the state estimation is updated. Based on the updated state estimation, it is determined whether there is a fault, and a first determination result is obtained.

[0070] The incremental identification algorithm continuously trains and updates the model parameters of the dosing flow control system based on sensor data, determines the deviation between the actual behavior of the dosing flow control system and the expected behavior, and predicts future failure risks based on the deviation to obtain the first prediction result;

[0071] The first judgment result and the first prediction result are used as the diagnosis result.

[0072] In an embodiment of the present invention,

[0073] Furthermore, the particle filter algorithm includes the following operations:

[0074] According to the initial state of the dosing flow control system and the constructed dosing flow control system model, a particle set is generated and assigned corresponding initial weights; each particle represents a hypothesis of the dosing flow control system state;

[0075] Determine the system state equation based on the dosing flow control system model, and update the particle weights based on the sensor data and the system state equation;

[0076] Calculate the input-output relationship of the dosing flow control system model and update the particle state based on the calculation results;

[0077] Resample according to the updated particle weights and particle states to generate a new particle set;

[0078] A weighted average operation is performed on the new particle set to obtain the final estimation result of the system state, and based on the final estimation result, it is determined whether the dosing flow control system has a fault.

[0079] In an embodiment of the present invention, by generating a particle set and assigning an initial weight, each particle represents a possible system state hypothesis. This method can explore the possibility of the system state in a diverse way and continuously update the credibility of these hypotheses based on real-time sensor data. By updating the weights of the particles based on the system model and sensor data, the particle filter algorithm can gradually approach the true state of the system. In addition, performing a resampling operation can focus on those particles that are most likely to represent the actual system state, thereby improving the accuracy of the system state estimation. Through the weighted averaging operation, combined with the different weights of the particle set, an accurate system state estimation result is finally output, which can effectively diagnose whether the system has a fault. The purpose of the present invention performing the above process is to dynamically adjust the estimation results, improve the accuracy and real-time performance of the system diagnosis, and ensure the stability and fault prevention capabilities of the dosing flow control system during operation.

[0080] Furthermore, the incremental identification algorithm includes the following operations:

[0081] The mathematical model of the dosing flow control system is updated based on the real-time collected sensor data and system input and output data through the incremental identification algorithm;

[0082] Deviations in system behavior are calculated based on the difference between the output of the current dosing flow control system model and the actual measurement data.

[0083] A deviation threshold is set based on the historical behavior pattern of the dosing flow control system and the known normal behavior range. When the calculated system behavior deviation exceeds the deviation threshold, it is considered that the system has a potential fault; and within a preset time period, it is determined whether the deviation gradually increases or persists. If it is judged to be so, the probability of fault occurrence and future risk points are predicted based on historical trends, and a fault risk warning is generated.

[0084] Preferably, the weighted average calculation formula in the particle filter algorithm includes:

[0085]

[0086] in, is the final estimated result of the system state at the current moment; w i (t) is the weight of the i-th particle at the current moment; x i (t) is the state of the i-th particle at the current moment; M is the coefficient matrix, which is used to adjust the state value of each particle and represents the weight of the particle state; N is the regularization factor, which is used to ensure that the sum of the weights of all particles is 1, and is used to prevent the weight from being too large or too small.

[0087] The weight update formula is:

[0088]

[0089] Among them, w i (t+1) is the weight of the i-th particle after update; y(t) is the observation value at the current moment; ∑ -1 is the inverse covariance matrix of the observation noise; H is the measurement matrix, which represents the mapping relationship from the system state to the measurement value; α is the dynamic adjustment factor, which aims to allow the weight to be dynamically adjusted according to the changes in the particle state and system noise.

[0090] As a further preferred embodiment, the model parameter formula in the incremental identification algorithm is:

[0091]

[0092] in, is the system model parameter at time t; is the updated system model parameter at time t+1; K is the Kalman gain, which is used to adjust the speed of model parameter update; is the expected observation data based on the model; λ is the time decay factor, which is used to simulate the influence of external factors and adjust the step size of parameter update; t is the current time step.

[0093] Furthermore, in the process of updating the mathematical model of the dosing flow control system by using the incremental identification algorithm, the recursive least square method is used to adjust the model parameters.

[0094] Furthermore, the control decision module adopts fault warning strategy and fault compensation strategy:

[0095] The fault warning strategy includes generating a warning signal when a potential fault is detected and notifying an operator of the warning signal;

[0096] The fault compensation strategy includes generating an alarm signal after detecting a confirmed fault, notifying the operator of the alarm signal, and adjusting the operation of the dosing flow control module.

[0097] Furthermore, the control module generates control instructions based on the diagnosis results and the comprehensive dosing flow data, including:

[0098] Identify the fault type based on the diagnosis result, and generate a corresponding corrected dosing flow instruction according to the identified fault type;

[0099] Calculate the correction amount based on the comprehensive dosing flow data;

[0100] The modified dosing flow instruction is modified based on the correction amount to generate a control instruction.

[0101] Specifically, the control module generates different control strategies based on the classification of different fault types in the diagnostic results, including generating corresponding corrected flow values, pressure values, or adjustment parameters according to different fault types; and performs intelligent optimization and adjustment based on historical data to improve the system response speed and accuracy.

[0102] Finally, it should be noted that the embodiment of the present invention discloses a power plant chemical equipment dosing flow control system with a fault diagnosis function, which discloses only a preferred embodiment of the present invention and is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that it is still possible to modify the technical solutions recorded in the aforementioned embodiments, or to replace some of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A chemical dosing flow control system for power plant chemical equipment with fault diagnosis function, characterized in that: The system includes a dosing flow control module, a data acquisition module, a fault diagnosis module and a control module; wherein, The dosing flow control module is used to control the flow of the dosing pump and adjust the amount of the drug output to the chemical equipment based on the flow; The data acquisition module is used to collect real-time sensor data related to the dosing flow rate; the sensor data includes dosing flow rate, pressure, and temperature; The fault diagnosis module is used to receive the sensor data sent by the data acquisition module, perform fault diagnosis on the dosing flow control system based on the sensor data through a particle filter algorithm and an incremental identification algorithm, and output a diagnosis result; The control module is used to generate control instructions according to the diagnosis results and the comprehensive dosing flow data, and adjust the operation of the dosing flow control module based on the control instructions; the comprehensive dosing flow data includes the collected dosing flow value and the dosing flow set value.

2. The power plant chemical equipment dosing flow control system with fault diagnosis function according to claim 1, characterized in that: Before performing fault diagnosis on the dosing flow control system based on sensor data through particle filtering algorithm and incremental identification algorithm, it also includes building a dosing flow control system model.

3. The power plant chemical equipment dosing flow control system with fault diagnosis function according to claim 2, characterized in that: The process of constructing the dosing flow control system model includes: Determine the input-output relationship of the dosing flow control system and establish the physical relationship between the input and output through mathematical modeling; wherein the input includes the control signal, operating conditions and external influencing factors, and the output includes the device response; Establishing a mathematical model describing the dynamic behavior of the dosing flow control system according to the device characteristics of the dosing flow control system and the determined input-output relationship, and using the mathematical model as a dosing flow control system model; Based on the initial state of the equipment, equipment parameters and environmental conditions, the dosing flow control system model is initialized, and the initial dosing flow control system state estimation value is set.

4. The power plant chemical equipment dosing flow control system with fault diagnosis function according to claim 3, characterized in that: The control signals include dosing flow setting value, pump speed adjustment, and valve opening adjustment; The operating conditions include operating temperature and operating pressure; The external influencing factors include fluctuations in power supply voltage, temperature and humidity inside the power plant, and changes in chemical supply; The device response includes the output of the flow sensor, the reading of the pressure sensor, the working status of the pump, and the valve opening; The equipment characteristics include the performance curve of the pump, the adjustment characteristics of the valve, the pipeline characteristics, and the sensor characteristics.

5. The power plant chemical equipment dosing flow control system with fault diagnosis function according to any one of claims 2 to 4, characterized in that: The fault diagnosis of the dosing flow control system based on sensor data by using a particle filter algorithm and an incremental identification algorithm includes: The particle filter algorithm is used to estimate the state of the dosing flow control system in real time based on the sensor data, and the state estimation is updated. Based on the updated state estimation, it is determined whether there is a fault, and a first determination result is obtained. The incremental identification algorithm continuously trains and updates the model parameters of the dosing flow control system based on sensor data, determines the deviation between the actual behavior of the dosing flow control system and the expected behavior, and predicts future failure risks based on the deviation to obtain the first prediction result; The first judgment result and the first prediction result are used as the diagnosis result.

6. The power plant chemical equipment dosing flow control system with fault diagnosis function according to claim 5, characterized in that: The particle filter algorithm includes the following operations: According to the initial state of the dosing flow control system and the constructed dosing flow control system model, a particle set is generated and assigned corresponding initial weights; each particle represents a hypothesis of the dosing flow control system state; Determine the system state equation based on the dosing flow control system model, and update the particle weights based on the sensor data and the system state equation; Calculate the input-output relationship of the dosing flow control system model and update the particle state based on the calculation results; Resample according to the updated particle weights and particle states to generate a new particle set; A weighted average operation is performed on the new particle set to obtain the final estimation result of the system state, and based on the final estimation result, it is determined whether the dosing flow control system has a fault.

7. The power plant chemical equipment dosing flow control system with fault diagnosis function according to claim 5, characterized in that: The incremental identification algorithm includes the following operations: The mathematical model of the dosing flow control system is updated based on the real-time collected sensor data and system input and output data through the incremental identification algorithm; Calculate the deviation of system behavior based on the difference between the output of the current dosing flow control system model and the actual measurement data; A deviation threshold is set based on the historical behavior pattern of the dosing flow control system and the known normal behavior range. When the calculated system behavior deviation exceeds the deviation threshold, it is considered that the system has a potential fault; and within a preset time period, it is determined whether the deviation gradually increases or persists. If it is judged to be so, the probability of fault occurrence and future risk points are predicted based on historical trends, and a fault risk warning is generated.

8. The power plant chemical equipment dosing flow control system with fault diagnosis function according to claim 7, characterized in that: In the process of updating the mathematical model of the dosing flow control system through the incremental identification algorithm, the recursive least squares method is used to adjust the model parameters.

9. The power plant chemical equipment dosing flow control system with fault diagnosis function according to claim 1, characterized in that: The control decision module adopts fault warning strategy and fault compensation strategy: The fault warning strategy includes generating a warning signal when a potential fault is detected and notifying an operator of the warning signal; The fault compensation strategy includes generating an alarm signal after a fault is detected, notifying an operator of the alarm signal, and adjusting the operation of the dosing flow control module.

10. The power plant chemical equipment dosing flow control system with fault diagnosis function according to claim 1, characterized in that: The control module generates control instructions based on the diagnosis results and the comprehensive dosing flow data, including: Identify the fault type based on the diagnosis result, and generate a corresponding corrected dosing flow instruction according to the identified fault type; Calculate the correction amount based on the comprehensive dosing flow data; The modified dosing flow instruction is modified based on the correction amount to generate a control instruction.

Images