APS-based self-adaptive optimization start-stop control system for coal pulverizing system of thermal power generating unit

Abstract

The invention belongs to the technical field of industrial automation control, and discloses an APS-based self-adaptive optimization start-stop control system for a coal pulverizing system of a thermal power generating unit, and the system comprises an APS instruction analysis module which is used for analyzing an APS start-stop instruction, extracting process constraint parameters of the coal pulverizing system, and generating a start-stop control target and a load adjustment boundary in combination with a boiler operation load; the working condition sensing module is used for extracting working condition interaction factors reflecting coal type, equipment and wind powder interaction by collecting operation working condition data, constructing a state-energy-load three-dimensional mapping relation and forming a physical side state vector; the section division module is used for constructing a control subspace of an energy rheological section of the coal pulverizing system based on the physical side state vector, dividing the control subspace into different energy operation sections, calculating energy release rates of a preset target section and a current section, and generating a start-stop strategy switching signal; the energy utilization efficiency is improved, and the equipment loss is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial automation control, and more particularly, to an adaptive optimization start-stop control system for a coal pulverizing system of a thermal power unit based on APS. BACKGROUND

[0002] The patent with the patent publication number CN112594668A discloses a solution to over-temperature and over-pressure in the start-stop grinding of a thermal power unit. The accumulated powder in the coal mill during the start of the coal pulverizing system is determined to determine the intermediate point temperature rise of the supercritical once-through boiler. Based on the corresponding relationship between the determined intermediate point temperature rise and the feedwater flow, the target feedwater flow corresponding to the feedforward increase of the intermediate point temperature rise during the start-stop grinding is determined. The generated feedwater instruction corresponding to the target feedwater flow is sent to the thermal power unit, so that the thermal power unit increases the target feedwater flow in advance according to the feedwater instruction. The present application increases a part of the water flow in advance based on the accumulated powder in the coal mill, so that the water-coal ratio of the thermal power unit during the start of the grinding will not deviate too much, thereby being able to quickly suppress the change of the intermediate point temperature, reduce the influence on the superheated temperature, make the thermal power unit quickly and stably, improve the automation control level of the unit, enable the thermal power unit to operate safely and stably, and ensure the load response speed of the unit.

[0003] The existing adaptive optimization start-stop control system for a coal pulverizing system of a thermal power unit mainly has the following problems: In the prior art, only the total energy consumption of the system is monitored and adjusted, which leads to an insufficiently fine control strategy and difficulty in effectively adapting to complex working conditions. In complex and changing working conditions, the prior art lacks a flexible control mechanism, which leads to low running efficiency of the coal pulverizing system, and even may cause problems such as overloading operation or inefficient operation of the system. In the existing start-stop control of the coal pulverizing system of a thermal power unit, the start-stop instruction response is usually based on a fixed threshold trigger mechanism or a time sequence strategy set by humans, ignoring the influence of factors such as coal type change, equipment state degradation, and wind-powder coupling disturbance on the energy release path and response rhythm during actual operation. The start-stop command is executed compulsorily once triggered, and the response time cannot be dynamically adjusted, which easily causes energy consumption fluctuations, thermal load shocks, and even induces unstable operation of the boiler. The system lacks quantitative analysis of the energy release behavior of the current operating section and the target section, and the control behavior is blind and lagging. The system is easily affected by the disturbance amplification effect when executing the start-stop operation, which leads to an increase in execution deviation.

[0004] In view of this, the present application proposes an adaptive optimization start-stop control system for a coal pulverizing system of a thermal power unit based on APS to solve the above problems. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art, in order to achieve the above-mentioned purpose, the present application provides the following technical scheme: the adaptive optimization start-stop control system of the coal pulverizing system of the thermal power generating unit based on APS, comprising: An APS instruction analysis module is used for analyzing the APS start-stop instruction, extracting the process constraint parameters of the coal pulverizing system, combining the boiler operation load, generating the start-stop control target and the load adjustment boundary; A working condition sensing module extracts the working condition interaction factors reflecting the coal type, equipment and air-powder interaction by collecting the operation working condition data, constructs the state-energy-load three-dimensional mapping relationship, and forms the physical side state vector; A section division module constructs the control subspace of the energy flow variation interval of the coal pulverizing system based on the physical side state vector, divides it into different energy operation sections, calculates the energy release rate of the preset target section and the current section, and generates the start-stop strategy switching signal; A start-stop correction module combines the dynamic change curve of the APS start-stop instruction and the current equipment health state data, constructs the real-time optimization space of the start-stop strategy parameters, and performs self-iterative correction on the start-stop strategy parameters; An efficiency evaluation module receives the start-stop strategy switching signal, constructs the actuator coupling behavior matrix, identifies the transient coupling path between the multiple source controls, introduces the disturbance suppression mechanism, absorbs the coal quality disturbance and air pressure fluctuation in real time, and evaluates the effect of the start-stop execution process.

[0006] Preferably, the method for obtaining the process constraint parameters comprises: Receiving the structured start-stop instruction issued by APS, performing semantic recognition and analysis on the start-stop instruction, and extracting the process constraint parameters; the process constraint parameters include the minimum air-powder ratio, the maximum start-stop frequency per hour, the priority start-stop grouping of the coal mill, the start-stop response delay time, the upper limit of the coal mill shell temperature and the lower limit of the main steam pressure.

[0007] Preferably, the method for obtaining the start-stop control target and the load adjustment boundary comprises: Analyzing the APS start-stop instruction type, extracting the process constraint parameters of the coal pulverizing system therefrom, combining the current boiler operation load data, constructing a weighted multi-objective optimization function, and finally outputting the start-stop control target; The load adjustment boundary is derived based on the current operation load state of the boiler, and is used to constrain the allowable operation parameter range of the coal pulverizing system during the start-stop process: according to the design parameters of the core equipment of the coal pulverizing system, the initial physical limit load boundary of the equipment is determined; based on the safety operation index in the process constraint parameters, the initial physical limit load boundary is corrected and modified; in combination with the minimum stable combustion powder supply amount and the maximum allowable powder supply amount corresponding to the current boiler operation load, the modified initial physical limit load boundary is subjected to secondary verification, and the final load adjustment boundary is generated.

[0008] Preferably, the method for obtaining the working condition interaction factor comprises: The running working condition data is collected, including coal quality online analysis data, mill running state data and air pressure and air speed data, and is preprocessed through standardization and abnormality elimination. Based on a principal component analysis method, working condition interaction factors reflecting the coupling relationship of coal type characteristics, equipment response behavior and air-powder delivery are extracted. The working condition interaction factors include coal type crushing efficiency factor, air-powder ratio deviation factor and equipment dynamic response factor, and represent the coupling characteristics of the pulverizing system under different running states.

[0009] Preferably, the method for obtaining the physical side state vector comprises: Based on the extracted working condition interaction factors, coal rheological property parameters, equipment health state parameters and gas-solid transport state parameters are further fused to construct a multi-dimensional state vector describing the running characteristics of the pulverizing system. A state-energy mapping model and a state-load mapping model are respectively established based on the multi-dimensional state vector. The energy consumption level required by the unit load is calculated through the state-energy mapping model, the maximum load adjustment capacity of the system under the current working condition is calculated through the state-load mapping model, and the physical side state vector is output.

[0010] Preferably, the method for obtaining the energy running section comprises: According to the equipment running state corresponding to each energy running section, the energy release rate of the energy running section per unit time is calculated. The physical side state vector and the equipment running state are used to construct a control subspace of the energy rheological interval of the pulverizing system, which reflects the change rule and boundary of the system energy under different running conditions. According to the numerical range of the energy release rate, the control subspace of the energy rheological interval of the pulverizing system is divided into different energy running sections.

[0011] Preferably, the method for generating the start-stop strategy switching signal comprises: For the target running section, the target energy release rate is set when the start-stop instruction is issued, guiding the control execution direction. The energy release rate per unit time of the current running section is preset, and the energy release rate difference between the current section and the target section during the running process is calculated. The dynamic delay time function is introduced to calculate the execution delay time of the current start-stop strategy, control the execution rhythm of the start-stop action, and preset the dynamic delay time threshold. When the execution delay time of the current start-stop strategy is greater than or equal to the preset dynamic delay time threshold, it is determined that the execution condition is met, and the start-stop strategy switching signal is generated.

[0012] Preferably, the method for constructing the real-time optimization space comprises: Collect the historical start-stop instruction sequence issued by the APS, extract the feature information of the historical APS start-stop instruction, and form a dynamic change curve of the APS start-stop instruction; obtain the current device health state data, and construct a device health state vector; Based on the dynamic change curve of the APS start-stop instruction and the device health state vector, a real-time optimization space of the start-stop strategy parameter is constructed, and the optimal start-stop strategy parameter combination is selected in the real-time optimization space through a greedy algorithm, so that the start-stop strategy parameter of the current start-stop strategy is self-iteratively corrected.

[0013] Preferably, the identification method of the transient coupling path comprises: Obtain the control input signal and response output data of each actuator in the pulverizing system, construct an actuator coupling behavior matrix according to the response relationship between the input and output of each actuator, normalize the actuator coupling behavior matrix, extract the main coupling path by using an eigenvalue decomposition method, model each actuator as a node and the coupling relationship as an edge, construct a coupling relationship directed graph, and identify the transient coupling path existing in the start-stop switching process.

[0014] Preferably, the method for evaluating the effect of the start-stop execution process comprises: A disturbance suppression mechanism is introduced, which can identify and suppress the unstable influence of coal quality disturbance and air pressure fluctuation on the system in real time during the execution of the start-stop strategy, and evaluate the execution effect of the start-stop; the disturbance suppression mechanism comprises the following steps: collecting coal quality online analysis data, air pressure and wind speed sensing data and mill load data, identifying the mutation behavior characteristics of the coal size, moisture and volatile parameters and the dynamic fluctuation characteristics of the air supply system, and establishing a disturbance source feature vector; A system disturbance transmission model containing control input and disturbance input is constructed, and the influence path of the disturbance on the key output variables of the pulverizing system is extracted; based on the disturbance source feature vector, a disturbance suppression strategy is implemented; The efficiency index of the pulverizing system is quantified by constructing an efficiency score function, and the effect of the start-stop execution process is evaluated.

[0015] Compared with the prior art, the present application has the following advantages: The present application accurately calculates the energy release rate of each energy operation section by constructing a physical side state vector and combining the mill power, coal output rate, and air-powder ratio of the device operating state. By constructing the control subspace of the energy flow variation interval, the system is flexibly divided into multiple energy operation sections according to the real-time energy release rate and different operating states. Each energy operation section has a clear energy release rate boundary and control strategy, ensuring that the system can accurately match the energy demand at different stages and achieve the optimal operating state. By real-time monitoring of the energy release rate and device state, the control target of each section can be flexibly adjusted according to the actual operating conditions, thereby realizing the optimal allocation and use of energy.

[0016] By real-time calculation of the difference between the current energy release rate and the target rate, and introduction of a disturbance intensity factor for normalization processing, the execution delay time of the start-stop control strategy is dynamically adjusted. This mechanism significantly improves the adaptive ability of the control system to operating state fluctuations, making the start-stop operation more flexible and controllable, effectively avoiding control impact and system oscillation caused by too fast response. By setting a dynamic delay time threshold, a start-stop strategy switching signal is only generated when the current energy behavior meets the strategy execution conditions, effectively preventing invalid start-stop or unnecessary adjustment, improving the rationality of control strategy execution and the stability of system operation. It can absorb disturbances caused by coal quality changes, wind pressure fluctuations, and other factors in real time, actively suppress and respond to typical disturbance sources, and enhance the robustness of the system to complex working conditions. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 The figure is a structural schematic diagram of the APS-based adaptive optimization start-stop control system for the coal pulverizing system of a thermal power generating unit of the present application. Figure 2 The figure is a structural schematic diagram of the APS-based adaptive optimization start-stop control system for the coal pulverizing system of a thermal power generating unit of the present application. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0019] Embodiment 1

[0020] Please refer to Figure 1 The present application proposes an APS-based adaptive optimization start-stop control system for the coal pulverizing system of a thermal power generating unit, which further includes: In traditional coal-fired power plant pulverizing systems, the start-stop control of the pulverizing system usually employs a fixed threshold trigger mechanism or a manually set timing strategy. This approach often ignores the impact of actual operating conditions on the system, resulting in a lack of precision in the control strategy and difficulty in responding to complex and dynamic operating environments. Existing control strategies often fail to adapt to changes in coal type, equipment aging, and wind-pulverized coupling disturbances, affecting the energy release path and control response, leading to low system efficiency and even causing the system to overload or run inefficiently.

[0021] Specifically, the existing technology has the following shortcomings: Inaccurate energy consumption monitoring: In traditional systems, only the total energy consumption is monitored and adjusted, without considering the energy release behavior of each subsystem and different energy operating sections. This rough energy regulation method cannot effectively adapt to different operating conditions and accurately control energy flow, resulting in energy waste and reduced system efficiency.

[0022] Lack of flexible control mechanism: In complex and changing operating conditions, traditional start-stop control methods are often based on fixed threshold trigger mechanisms, lacking flexible adjustment space. When coal quality changes, wind-pulverized ratio fluctuations, and equipment state changes occur, the system cannot dynamically adjust the start-stop response time, resulting in delayed or excessive control actions. This rigid control method may cause excessive response or delay, severely affecting the efficiency of the pulverizing system and even adversely affecting boiler operation.

[0023] Unable to cope with disturbances: Since traditional control strategies do not consider the impact of disturbance sources such as coal quality changes and wind pressure fluctuations, start-stop operations are often amplified by external disturbances, causing the system's execution deviation to increase. This control method without disturbance suppression mechanism makes the system less adaptable to complex operating conditions, and may even cause the boiler to run unstable, leading to system failure or performance degradation.

[0024] Insufficient quantitative analysis of energy release behavior: Existing start-stop control systems lack quantitative analysis of the energy release behavior of the pulverizing system, especially for the division of different energy operating sections and dynamic calculation of energy release rate. Traditional systems often cannot clearly identify the switching and transition between different energy sections, resulting in ambiguous goals and basis for start-stop operations, and control behavior is blind and lagging.

[0025] Unable to effectively handle complex operating conditions: Under the influence of factors such as coal type changes, equipment aging, and wind-pulverized coupling disturbances, existing start-stop control strategies often fail to adjust energy release rate and start-stop strategies in real time and accurately, resulting in inefficient system operation and even system overload or low efficiency. Traditional fixed control strategies cannot adapt to changes in energy demand under complex operating conditions, leading to energy waste and system load fluctuations.

[0026] To effectively solve the above problems, the present application proposes an adaptive optimization start-stop control system for a coal pulverizing system of a thermal power unit based on APS, comprising: An APS instruction analysis module is configured to analyze APS start-stop instructions, extract process constraint parameters of the coal pulverizing system, combine the boiler operating load, generate start-stop control targets and load adjustment boundaries, and the like. A working condition sensing module is configured to extract working condition interaction factors reflecting coal types, equipment and air-pulverized coal interaction by collecting operating working condition data, construct a state-energy-load three-dimensional mapping relationship, and form a physical side state vector. A section division module is configured to construct a control subspace of the energy flow variation interval of the coal pulverizing system based on the physical side state vector, divide it into different energy operation sections, calculate the energy release rate of the preset target section and the current section, and generate a start-stop strategy switching signal. A start-stop correction module is configured to combine the dynamic change curve of the APS start-stop instruction and the current equipment health state data, construct a real-time optimization space of the start-stop strategy parameters, and perform self-iterative correction of the start-stop strategy parameters. An efficiency evaluation module is configured to receive the start-stop strategy switching signal, construct an actuator coupling behavior matrix, identify the transient coupling path between multiple source controls, introduce a disturbance suppression mechanism, absorb coal quality disturbances and air pressure fluctuations in real time, and evaluate the effect of the start-stop execution process.

[0027] The method for obtaining the process constraint parameters comprises: Receiving the structured start-stop instruction issued by the APS, performing semantic recognition and analysis on the start-stop instruction, and extracting the process constraint parameters; the start-stop instruction comprises target start-stop states, scheduling target load intervals, effective time periods and process constraint parameters related to the coal pulverizing system; the process constraint parameters comprise minimum air-pulverized coal ratios, maximum start-stop frequencies per hour, priority start-stop grouping of coal mills, start-stop response delay times, upper limits of coal mill shell temperatures and lower limits of main steam pressures.

[0028] The method for obtaining the start-stop control targets and the load adjustment boundaries comprises: Analyzing the APS start-stop instruction type, extracting the process constraint parameters of the coal pulverizing system (such as the upper limit of the coal mill bearing temperature, the lubricating oil pressure threshold, the coal powder fineness requirement and the minimum coal powder flow required for boiler stable combustion, etc.), combining the current boiler operating load data, constructing a weighted multi-objective optimization function with start-up time, energy consumption and load fluctuation (deviation between the actual load of the boiler and the preset target load) as optimization objectives, and finally outputting the start-stop control targets, including time targets (staged completion time, such as reaching the rated output within 10 minutes after the coal mill is started), energy efficiency targets (electricity consumption threshold per unit of coal powder output) and stability targets (coal powder flow fluctuation rate, such as within ±2%); the boiler operating load data comprises the boiler evaporation capacity, the main steam pressure, the reheater outlet temperature and the actual coal consumption. APS command analysis: APS (Automatic Power Generation Control) start and stop commands include the equipment target load and the start and stop phases (e.g., cold start, hot start, normal shutdown, etc.). The command code identifies the current start and stop phase (e.g., "pulverizing system preheating," "pulverizer start sequence," etc.). The load regulation boundary is derived based on the current operating load state of the boiler, and is used to constrain the allowable operating parameter range of the pulverizing system during the start-up and shutdown process: the initial physical limit load boundary of the equipment is determined based on the design parameters of the core equipment of the pulverizing system; the initial physical limit load boundary is shrunk and corrected based on the safe operation indicators in the process constraint parameters; the corrected initial physical limit load boundary is rechecked based on the minimum stable combustion pulverized powder feed rate and the maximum allowable pulverized powder feed rate corresponding to the current operating load of the boiler to generate the final load regulation boundary.

[0029] Methods for obtaining working condition interaction factors include: The operating condition data are collected, including online coal quality analysis data, mill operating status data and wind pressure and speed data. The data are preprocessed by standardization and anomaly elimination. Based on the principal component analysis method, the operating condition interaction factors reflecting the coupling relationship between coal type characteristics, equipment response behavior and air-powder conveying are extracted. The operating condition interaction factors include coal type crushing efficiency factor, air-powder ratio deviation factor and equipment dynamic response factor, which characterize the coupling characteristics of the pulverizing system under different operating conditions.

[0030] Methods for obtaining the physical side state vector include: Based on the extracted operating condition interaction factors, the coal rheological parameters, including pulverized coal particle size, moisture content, and ash content, equipment health parameters, and gas-solid transport state parameters are further integrated. The coal rheological parameters include motor temperature rise margin, current fluctuation rate, and start-stop load ratio. The gas-solid transport state parameters include primary wind speed uniformity, pipeline pressure loss, and air-to-powder ratio deviation. A multidimensional state vector is constructed to describe the operating characteristics of the pulverizing system. Based on this multidimensional state vector, a state-energy mapping model and a state-load mapping model are established. The energy consumption level required for unit load is calculated through the state-energy mapping model, and the maximum load regulation capability of the system under the current working conditions is calculated through the state-load mapping model, and the output forms the physical side state vector.

[0031] Methods for obtaining the energy operation section include: The energy operating segment represents the energy release capacity and efficiency of the pulverizing system per unit time under specific operating conditions. It is the mapping result of the physical state vector in the control subspace. Due to the dynamic changes of factors such as coal type differences, equipment wear, and air-to-pulverizer matching, the system's energy fluctuations exhibit nonlinear and piecewise continuous characteristics, necessitating the extraction of its implicit structure. According to the device operating state corresponding to each energy operating section (such as the coal mill power, the pulverized coal output rate, the air-pulverized coal ratio, etc.), the energy release rate of the energy operating section in unit time is calculated ; The energy release rate is: ; wherein, represents the real-time power consumed by the coal mill at the time point ; represents the pulverized coal output of the coal mill at the time point The pulverization efficiency is the efficiency of effectively pulverizing the pulverized coal into a particle size that meets the preset process requirements. represents the pulverized coal output of the coal mill at the time point The physical side state vector and the device operating state are used to construct a control subspace of the energy flow variation interval of the pulverizing system, which reflects the variation law and boundary of the system energy under different operating conditions. According to the numerical range of the energy release rate, the control subspace of the energy flow variation interval of the pulverizing system is divided into different energy operating sections.

[0032] The energy operating section is defined as: ; wherein, represents the th energy operating section; represents the th energy operating section; represents the lower limit of the energy release rate of the th energy operating section, that is, the minimum value allowed by the energy release rate of the section; represents the index of the energy operating section; represents the total number of energy operating sections; The existing problems in the prior art are solved: in the prior art, only the total energy consumption of the system is monitored and adjusted, and the specific energy release rate of each operating section is not refined, resulting in a control strategy that is not fine enough and is difficult to effectively adapt to complex working conditions. In complex and changing working conditions (such as coal quality changes, load fluctuations, etc.), the prior art lacks a flexible control mechanism, resulting in low operating efficiency of the pulverizing system, and even may cause problems such as overloading operation or inefficient operation of the system.

[0033] ​Advantages over the prior art: By constructing a physical side state vector and combining the mill power, coal output rate, and air-powder ratio, the energy release rate of each energy operation section is accurately calculated. By constructing the control subspace of the energy flow variation interval, the system is flexibly divided into multiple energy operation sections according to the real-time energy release rate and different operation states. Each energy operation section has a clear energy release rate boundary and control strategy, ensuring that the system can accurately match the energy demand at different stages and achieve the optimal operation state. By real-time monitoring of the energy release rate and the device state, the control target of each section can be flexibly adjusted according to the actual operation condition, thereby realizing the optimal allocation and use of energy.

[0034] The method for generating the start-stop strategy switching signal comprises: For the target operation section, the system sets the target energy release rate as when the start-stop instruction is issued, and guides the control execution direction; the preset energy release rate of the current operation section per unit time is ; during the operation process, the energy release rate difference between the current section and the target section is calculated in real time; the energy release rate difference is: ; A dynamic delay time function is introduced to calculate the execution delay time of the current start-stop strategy, and the execution rhythm of the start-stop action is controlled; The dynamic delay time function is: ; wherein, represents the execution delay time of the current start-stop strategy; represents the basic delay time length of the preset start-stop strategy, which refers to the fixed delay time under the disturbance-free or reference state, and is used to ensure the smooth transition of the start-stop action; represents the disturbance intensity factor, which is used to adjust the influence degree of the energy deviation on the delay time; A preset dynamic delay time threshold is set, and when the execution delay time of the current start-stop strategy is greater than or equal to the preset dynamic delay time threshold, it is determined that the execution condition is met, and the start-stop strategy switching signal is generated.

[0035] The problems existing in the prior art are solved: In the existing start-stop control of the coal pulverizing system of a thermal power unit, the start-stop instruction response is usually based on a fixed threshold trigger mechanism or a time sequence strategy set by humans, ignoring the influence of factors such as coal type change, equipment state degradation, and air-powder coupling disturbance on the energy release path and response rhythm. Once the start-stop command is triggered, it is executed compulsorily, and the response time cannot be dynamically adjusted, which easily causes energy consumption fluctuation, thermal load impact, and even induces unstable boiler operation. The system lacks quantitative analysis of the energy release behavior of the current operation section and the target section, and the control behavior is blind and lagging; the system is easily affected by the disturbance amplification effect when executing the start-stop operation, resulting in increased execution deviation.

[0036] The beneficial effects of the prior art: by calculating the difference between the current energy release rate and the target rate in real time, and introducing the disturbance intensity factor for normalization processing, the execution delay time of the start-stop control strategy is dynamically adjusted. This mechanism significantly improves the adaptive ability of the control system to the fluctuation of the operating state, making the start-stop operation more flexible and controllable, effectively avoiding the control impact and system oscillation caused by too fast response. By setting a dynamic delay time threshold, a start-stop strategy switching signal is only generated when the current energy behavior meets the strategy execution condition, effectively preventing invalid start-stop or unnecessary adjustment, improving the rationality of the control strategy execution and the stability of the system operation. It can absorb disturbances caused by factors such as coal quality changes and wind pressure fluctuations in real time, actively suppress and optimize the response to typical disturbance sources, and enhance the robustness of the system to complex working conditions.

[0037] The construction method of the real-time optimization space includes: Collecting the historical start-stop instruction sequence issued by APS, extracting the feature information of the historical APS start-stop instruction, the instruction feature information including the instruction target change trend, change slope, duration and target boundary value, forming the dynamic change curve of the APS start-stop instruction; obtaining the current device health state data, the current device health state data including the health state data of the coal mill, coal feeder, electric actuator and damper device in the pulverizing system, the health state data including current fluctuation, temperature rise, component wear degree and operation stability index, and constructing a device health state vector; Based on the dynamic change curve of the APS start-stop instruction and the device health state vector, a real-time optimization space containing start-stop delay time, target wind-pulverized coal ratio and minimum loading threshold strategy parameters is dynamically generated as the adjustable range of the control parameters; a start-stop strategy parameter combination is selected in the real-time optimization space based on the greedy algorithm, and the start-stop strategy parameters of the current start-stop strategy are iteratively corrected.

[0038] The identification method of the transient coupling path includes: Obtaining the control input signal and response output data of each actuator in the pulverizing system, constructing an actuator coupling behavior matrix according to the response relationship between the input and output of each actuator, which is used to reflect the transient behavior coupling characteristics of the actuator, and the elements in the actuator coupling behavior matrix are the sensitivity values of each control input to the system output response; The actuator coupling behavior matrix is normalized, the eigenvalue decomposition method is used to extract the main coupling path, each actuator is modeled as a node, and the coupling relationship is modeled as an edge, a coupling relationship directed graph is constructed, and the transient coupling path existing in the start-stop switching process is identified.

[0039] It should be noted that during the start-stop process of the pulverizing system, multiple actuators (such as coal mills, coal feeders, dampers, etc.) change their states almost simultaneously. Due to the delay difference between control instructions and physical responses, if the linkage relationship between these actuators is not identified and coordinated: the coal feeder loads in advance, the coal mill has not started, which is easy to cause coal blockage; the damper opening degree changes suddenly but the air-pulverized coal ratio is unbalanced, which may cause unstable combustion; the rapid adjustment of each control channel leads to problems such as wind pressure resonance, power oscillation, etc. Therefore, identifying the coupling path can predict risks before control execution and coordinate the action sequence and rate in advance. The dynamic response characteristics of different devices are different (such as large inertia of the coal mill, fast action of the damper), and if this difference is ignored during the execution of the start-stop switching instruction, it is easy to cause inconsistent control rhythm, and the system appears: asynchronous response: some devices respond too fast or too slow, and the overall system regulation is unbalanced; overshoot or lag: system oscillation, increased lag time. By identifying these transient coupling paths, rhythm coordination, instruction sequencing or beat delay adjustment can be performed to make the start-stop control more stable.

[0040] The method for evaluating the effect of the start-stop execution process includes: A disturbance suppression mechanism is introduced to identify and suppress the unstable influence of coal quality disturbance and wind pressure fluctuation on the system in real time during the execution of the start-stop strategy, and to evaluate the execution effect of the start-stop. The disturbance suppression mechanism includes identifying the mutation behavior characteristics of the coal type particle size, moisture, volatile content parameters and the dynamic fluctuation characteristics of the air supply system by collecting coal quality online analysis data, wind pressure and wind speed sensing data and coal mill load data, and establishing a disturbance source feature vector; A system disturbance transmission model containing control input and disturbance input is constructed to extract the influence path of the disturbance on the key output variables of the pulverizing system (including coal powder concentration, air-pulverized coal ratio, coal mill power, etc.); Based on the disturbance source feature vector, implement the disturbance suppression strategy; Based on the disturbance source feature vector, implement the disturbance suppression strategy, for example, use pre-feeding adjustment to correct the control instruction parameters in advance, add low-pass filtering to the actuator response signal to suppress high-frequency disturbance, and dynamically adjust the minimum load limit of the coal mill and the control boundary of the air-pulverized coal ratio adjustment band according to the disturbance intensity; The performance index of the pulverizing system is quantified by constructing an efficiency score function, and then the effect of the start-stop execution process is evaluated. The performance index includes response time, energy release rate fitting degree, actuator action consistency and system stability index.

[0041] The preset air-pulverized coal ratio threshold is set by the staff based on the analysis results of historical data. The system collects different air-pulverized coal ratios and calculates their average value as a reference. The staff can adjust it according to the actual situation during system operation; Similarly, set the preset dynamic delay time threshold and the minimum load threshold.

[0042] In this embodiment, the physical side state vector is constructed, and the coal mill power, coal powder output rate, and air-powder ratio are combined to accurately calculate the energy release rate of each energy operation section. By constructing the control subspace of the energy flow variation interval, the system is flexibly divided into multiple energy operation sections according to the real-time energy release rate and different operation states. Each energy operation section has a clear energy release rate boundary and control strategy, ensuring that the system can accurately match the energy demand at different stages and achieve the optimal operation state. By real-time monitoring of the energy release rate and the device state, the control target of each section can be flexibly adjusted according to the actual operation condition, thereby realizing the optimal allocation and use of energy.

[0043] By real-time calculation of the difference between the current energy release rate and the target rate, and introduction of the disturbance intensity factor for normalization processing, the execution delay time of the start-stop control strategy is dynamically adjusted. This mechanism significantly improves the adaptive ability of the control system to operation state fluctuations, making the start-stop operation more flexible and controllable, effectively avoiding control impact and system oscillation caused by too fast response. By setting a dynamic delay time threshold, a start-stop strategy switching signal is only generated when the current energy behavior meets the strategy execution condition, effectively preventing invalid start-stop or unnecessary adjustment, improving the execution rationality of the control strategy and the stability of the system operation. It can absorb disturbances caused by coal quality changes, wind pressure fluctuations and other factors in real time, actively suppress and optimize the response to typical disturbance sources, and enhance the robustness of the system to complex working conditions.

[0044] Embodiment 2

[0045] Please refer to Figure 2 The embodiment does not describe some parts in detail, which are described in Embodiment 1. The adaptive optimization start-stop control method for the coal pulverizing system of a thermal power unit based on APS is provided, which includes: S1, analyze the APS start-stop instruction, extract the process constraint parameters of the coal pulverizing system, combine the boiler operation load, generate the start-stop control target and load adjustment boundary; S2, extract the working condition interaction factors reflecting the coal type, equipment, and air-powder interaction by collecting the working condition data, construct the state-energy-load three-dimensional mapping relationship, and form the physical side state vector; S3, based on the physical side state vector, construct the control subspace of the energy flow variation interval of the coal pulverizing system, and divide it into different energy operation sections, calculate the energy release rate of the preset target section and the current section, and generate the start-stop strategy switching signal; S4, combine the dynamic change curve of the APS start-stop instruction and the current equipment health state data to construct the real-time optimization space of the start-stop strategy parameters, and perform self-iterative correction of the start-stop strategy parameters; S5, receiving the start-stop strategy switching signal, constructing the actuator coupling behavior matrix, identifying the transient coupling path between the multi-source control; introducing the disturbance suppression mechanism, absorbing the coal quality disturbance and wind pressure fluctuation in real time, and evaluating the effect of the start-stop execution process.

[0046] Since the electronic device introduced in the embodiment is the electronic device used in the implementation of the APS-based adaptive optimization start-stop control system for the coal pulverizing system of the thermal power generating unit in the embodiment, the specific implementation of the electronic device and its various changes can be understood by those skilled in the art based on the APS-based adaptive optimization start-stop control system for the coal pulverizing system of the thermal power generating unit in the embodiment, so the implementation of the electronic device in the method in the embodiment will not be introduced in detail. As long as the electronic device used in the implementation of the APS-based adaptive optimization start-stop control system for the coal pulverizing system of the thermal power generating unit in the embodiment is implemented by those skilled in the art, it belongs to the scope of protection of the present application.

[0047] The above formulas are dimensionless values, and the formulas are obtained by collecting a large amount of data to simulate the most recent real situation, and the preset parameters and threshold values in the formula are set by those skilled in the art according to the actual situation.

[0048] The above is only the preferred embodiment of the present application, and the protection scope of the present application is not limited to the above-mentioned embodiments, and any technical solution falling within the concept of the present application belongs to the protection scope of the present application. It should be noted that, for ordinary technical operators in the technical field, some improvements and decorations without departing from the principles of the present application are also considered to be within the protection scope of the present application.

Claims

1. The adaptive optimization start-stop control system of the pulverizing system of the thermal power unit based on APS is characterized by: include: The APS instruction parsing module is used to parse the APS start and stop instructions, extract the process constraint parameters of the pulverizing system, and generate the start and stop control targets and load regulation boundaries based on the boiler operating load; The working condition perception module collects operating condition data to extract working condition interaction factors reflecting the interaction between coal type, equipment, and air-powder, constructs a three-dimensional mapping relationship between state, energy, and load, and forms a physical side state vector; The segment division module constructs the control subspace of the energy rheological range of the pulverizing system based on the physical side state vector, divides it into different energy operation segments, calculates the energy release rate of the preset target segment and the current segment, and generates the start-stop strategy switching signal; The start-stop correction module combines the dynamic change curve of the APS start-stop command and the current equipment health status data to build a real-time optimization space for the start-stop strategy parameters and perform self-iterative correction of the start-stop strategy parameters; The performance evaluation module receives the start-stop strategy switching signal, constructs the actuator coupling behavior matrix, and identifies the transient coupling path between multi-source controls; introduces a disturbance suppression mechanism to absorb coal quality disturbances and wind pressure fluctuations in real time, and evaluates the effectiveness of the start-stop execution process.

2. The APS-based adaptive optimization start-stop control system for a thermal power unit pulverizing system according to claim 1 is characterized in that: The method for obtaining the process constraint parameters includes: Receive the structured start and stop instructions issued by APS, perform semantic recognition and analysis on the start and stop instructions, and extract process constraint parameters; process constraint parameters include minimum air-to-powder ratio, maximum number of starts and stops per hour, coal mill priority start and stop grouping, start and stop response delay time, coal mill shell temperature upper limit and main steam pressure lower limit.

3. The APS-based adaptive optimization start-stop control system for a thermal power unit pulverizing system according to claim 2 is characterized in that: The method for obtaining the start-stop control target and the load regulation boundary includes: Analyze the APS start-stop instruction type and extract the process constraint parameters of the pulverizing system from it. Combined with the current operating load data of the boiler, a weighted multi-objective optimization function is constructed to ultimately output the start-stop control target. The load regulation boundary is derived based on the current operating load state of the boiler, and is used to constrain the allowable operating parameter range of the pulverizing system during the start-up and shutdown process: the initial physical limit load boundary of the equipment is determined based on the design parameters of the core equipment of the pulverizing system; the initial physical limit load boundary is shrunk and corrected based on the safe operation indicators in the process constraint parameters; the corrected initial physical limit load boundary is rechecked based on the minimum stable combustion pulverized powder feed rate and the maximum allowable pulverized powder feed rate corresponding to the current operating load of the boiler to generate the final load regulation boundary.

4. The APS-based adaptive optimization start-stop control system for a coal-fired power plant pulverizing system according to claim 3 is characterized in that: The method for obtaining the working condition interaction factor includes: The operating condition data are collected, including online coal quality analysis data, mill operating status data and wind pressure and speed data. The data are preprocessed by standardization and anomaly elimination. Based on the principal component analysis method, the operating condition interaction factors reflecting the coupling relationship between coal type characteristics, equipment response behavior and air-powder conveying are extracted. The operating condition interaction factors include coal type crushing efficiency factor, air-powder ratio deviation factor and equipment dynamic response factor, which characterize the coupling characteristics of the pulverizing system under different operating conditions.

5. The APS-based adaptive optimization start-stop control system for a pulverizing system of a thermal power plant according to claim 4 is characterized in that: The method for obtaining the physical side state vector includes: Based on the extracted operating condition interaction factors, coal rheological parameters, equipment health parameters, and gas-solid transport state parameters are further integrated to construct a multidimensional state vector describing the operating characteristics of the pulverizing system. A state-energy mapping model and a state-load mapping model are then established based on this multidimensional state vector. The energy consumption level required for unit load is calculated through the state-energy mapping model, and the maximum load regulation capability of the system under the current working conditions is calculated through the state-load mapping model, and the output forms the physical side state vector.

6. The APS-based adaptive optimization start-stop control system for a coal-fired power plant pulverizing system according to claim 5 is characterized in that: The method for obtaining the energy operation section includes: According to the equipment operating status corresponding to each energy operating section, the energy release rate of the energy operating section per unit time is calculated; the physical side state vector and the equipment operating status are used to construct the control subspace of the energy rheological interval of the pulverizing system. This control subspace reflects the changing law and boundary of the system energy under different operating conditions; according to the numerical range of the energy release rate, the control subspace of the energy rheological interval of the pulverizing system is divided into different energy operating sections.

7. The APS-based adaptive optimization start-stop control system for a coal-fired power plant pulverizing system according to claim 6 is characterized in that: The method for generating a start-stop strategy switching signal includes: For the target operating section, when the start / stop command is issued, the system sets the target energy release rate to guide the control execution direction; the energy release rate per unit time of the current operating section is preset, and the energy release rate difference between the current section and the target section is calculated during operation; A dynamic delay time function is introduced to calculate the execution delay time of the current start-stop strategy and control the execution rhythm of the start-stop action; a dynamic delay time threshold is preset. When the execution delay time of the current start-stop strategy is greater than or equal to the preset dynamic delay time threshold, it is determined that the execution conditions are met and a start-stop strategy switching signal is generated.

8. The APS-based adaptive optimization start-stop control system for a coal-fired power plant pulverizing system according to claim 7 is characterized in that: The method for constructing the real-time optimization space includes: Collect the historical start and stop command sequences issued by the APS, extract the characteristic information of the historical APS start and stop commands, and form the dynamic change curve of the APS start and stop commands; obtain the current equipment health status data and construct the equipment health status vector; Based on the dynamic change curve of the APS start-stop instruction and the equipment health status vector, a real-time optimization space for the start-stop strategy parameters is constructed. The optimal start-stop strategy parameter combination is selected in the real-time optimization space through a greedy algorithm, and the start-stop strategy parameters of the current start-stop strategy are self-iteratively corrected.

9. The APS-based adaptive optimization start-stop control system for a coal-fired power plant pulverizing system according to claim 8, characterized in that: The method for identifying the transient coupling path includes: The control input signals and response output data of each actuator in the milling system are obtained, and the actuator coupling behavior matrix is ​​constructed based on the response relationship between the input and output of each actuator. The actuator coupling behavior matrix is ​​normalized, and the eigenvalue decomposition method is used to extract the main coupling path. Each actuator is modeled as a node, and the coupling relationship is modeled as an edge. A directed graph of the coupling relationship is constructed to identify the transient coupling path existing in the start-stop switching process.

10. The APS-based adaptive optimization start-stop control system for a coal-fired power plant pulverizing system according to claim 9, characterized in that: The method for evaluating the effect of the start-stop execution process includes: A disturbance suppression mechanism is introduced to identify and suppress the destabilizing effects of coal quality disturbances and wind pressure fluctuations on the system in real time during the execution of the start-stop strategy, and to evaluate the effectiveness of the start-stop execution. The disturbance suppression mechanism collects online coal quality analysis data, wind pressure and speed sensor data, and mill load data to identify the sudden change behavior characteristics of coal particle size, moisture content, and volatile matter parameters, as well as the dynamic fluctuation characteristics of the air supply system, and establish a disturbance source characteristic vector. Construct a system disturbance transfer model that includes control input and disturbance input to extract the impact path of the disturbance on the key output variables of the milling system; implement a disturbance suppression strategy based on the disturbance source characteristic vector; By constructing an efficiency scoring function, the efficiency indicators of the milling system are quantified, and then the effect of the start-stop execution process is evaluated.

Images