A deep peak regulation control system for a thermal power unit

Abstract

The application discloses a thermal power unit deep peak regulation control system, relates to the technical field of thermal power unit deep peak regulation, and comprises a deep peak regulation control center, wherein the deep peak regulation control center is communicatively connected with a data acquisition module, a load prediction module, a working condition monitoring module, a distributed control module and a safety monitoring and early warning module. The application divides each subsystem of the thermal power unit into multiple local control units by introducing a distributed control architecture and a bat algorithm optimization, realizes independent and collaborative control, significantly improves the flexibility and response speed of the thermal power unit in the deep peak regulation process, ensures that each subsystem can quickly adjust operation parameters according to actual load demand through the distributed control, and the global optimization capability of the bat algorithm further improves the adaptability and decision efficiency of the system when facing complex working conditions, thereby effectively solving the problem of response lag under the traditional centralized control mode.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of deep peak regulation of thermal power generating units, and particularly relates to a deep peak regulation control system of a thermal power generating unit. BACKGROUND

[0002] In recent years, new energy power generation such as wind power and photovoltaic power has developed rapidly, and the proportion of new energy installed capacity has increased significantly, which has changed the structure of the power market. In the traditional power system, thermal power generating units mainly undertake the task of providing power and electricity, and with the rise of new energy power generation, the role of thermal power generating units gradually changes to provide reliable power, peak regulation and frequency modulation capability as a basic power source. Thermal power generating units need to respond more flexibly to changes in grid load to adapt to the instability of new energy power generation.

[0003] As disclosed in Chinese Patent Publication No. CN118353092A, a deep peak regulation thermal power generating unit control method and control system based on big data driving determines the optimal control amount of the unit under deep peak regulation conditions based on climate data, power consumption data, power generation data and unit historical operation big data, thereby improving the efficiency and accuracy of control.

[0004] In the prior art, the optimal control amount of the unit under deep peak regulation conditions is determined based on climate data, power consumption data, power generation data and unit historical operation big data, and the corresponding optimal control amount is obtained under the corresponding peak regulation instruction, thereby solving the problem that the method for determining the optimal control amount is relatively single and has low adaptability to complex deep peak regulation conditions. However, since deep peak regulation of thermal power generating units involves collaborative control among multiple subsystems, it is difficult to achieve the best control effect when facing different conditions of deep peak regulation, resulting in problems such as slow response of unit load and insufficient peak regulation depth. Therefore, how to adopt a combination of distributed control and a bat algorithm to adapt to complex conditions and speed up the response speed is a problem to be solved by the present application. Therefore, a deep peak regulation control system of a thermal power generating unit is proposed. SUMMARY

[0005] The present application aims to provide a deep peak regulation control system of a thermal power generating unit to solve the problems raised in the background art.

[0006] To solve the above technical problems, the technical solution adopted by the present application is as follows:

[0007] A deep peak regulation control system of a thermal power generating unit comprises a deep peak regulation control center, which is communicatively connected with a data acquisition module, a load prediction module, a working condition monitoring module, a distributed control module and a safety monitoring and early warning module, wherein the modules are electrically connected.

[0008] The deep peak regulation control center is a command center of the whole control system, is responsible for communication connection and coordinated scheduling among modules, integrates module information and issues instructions, realizes centralized management and unified regulation and control of the deep peak regulation process of the thermal power generating unit, and ensures that the modules work cooperatively;

[0009] The data acquisition module is used for collecting and pre-processing operation data of each subsystem of the thermal power generating unit in real time, including key parameters of temperature, pressure, flow, power, rotating speed and load, and ensuring comprehensiveness and real-time performance of data through distributed data acquisition points;

[0010] The load prediction module is used for analyzing load change trend of the thermal power generating unit by using historical operation data;

[0011] The working condition monitoring module is used for monitoring the working condition of the thermal power generating unit and identifying the abnormality of the current working condition;

[0012] The distributed control module is used for dividing each subsystem of the thermal power generating unit into a plurality of local control units, analyzing load change and working condition monitoring results of the thermal power generating unit by using the bat algorithm, finding optimal control parameters and scheduling scheme, and then generating and executing control instructions;

[0013] The safety monitoring and early warning module is used for evaluating the operation effect of the thermal power generating unit, continuously monitoring key parameters in the deep peak regulation process of the thermal power generating unit, triggering an alarm mechanism and taking corresponding safety protection measures once it is found that the key parameters exceed a safety threshold.

[0014] The further improvement of the technical scheme of the present application is that the data acquisition module specifically comprises:

[0015] According to the peak regulation demand of the thermal power generating unit, the data acquisition point layout of each subsystem of the thermal power generating unit is planned, the required operation data including key parameters of temperature, pressure, flow, power, rotating speed and load are determined, meanwhile, the acquisition frequency and time interval are formulated, the operation data acquisition scheme is designed, and it is ensured that the operation state of each subsystem can be comprehensively covered;

[0016] According to the planned acquisition scheme, the operation data of each subsystem of the thermal power generating unit are collected by using the distributed data acquisition points, the actual values of the corresponding key parameters are acquired by the sensors configured in each data acquisition point, and the data are transmitted to the data acquisition module in the form of electric signals, so that the real-time performance and accuracy of the data are ensured;

[0017] The collected original operation data are pre-processed, including the steps of data cleaning and normalization processing;

[0018] The preprocessed operation data is integrated to obtain a thermal power operation sequence table, and a data warehouse is built, and the related data of the thermal power operation sequence table is stored in the data warehouse.

[0019] The further improvement of the technical scheme of the present application is that the load prediction module specifically comprises:

[0020] The historical operation data of the thermal power unit is extracted from the operation records of the thermal power unit, including power, load and corresponding timestamp information, and the data is sorted and aligned according to time sequence to form a unified format;

[0021] The historical operation data is analyzed to extract trend characteristics related to load prediction, including load change rate, load fluctuation amplitude, load change duration and load change frequency, and in combination with historical operation data and operation requirements of the thermal power unit, the reference values of the trend characteristics are preset, and then the trend characteristics and corresponding reference values are integrated to obtain a load trend characteristic sequence table;

[0022] The load trend characteristic sequence table is divided into a training set, a validation set and a test set, and a load prediction model is constructed based on a time sequence analysis framework, the trend characteristics are input, and the load change trend of the thermal power unit is output;

[0023] The load prediction model is constructed, the related data of the load trend characteristic sequence table of the current time period is input, the load trend value of the unit is calculated, and the load change trend of the thermal power unit in the future period of the same time period is predicted.

[0024] The further improvement of the technical scheme of the present application is that the calculation process of the unit load trend value is:

[0025] The trend characteristic related data of the thermal power unit in the current time period is extracted from the load trend characteristic sequence table, including the load change rate, the load fluctuation amplitude, the load change duration and the load change frequency of each time point, and the reference values corresponding to the trend characteristics are determined, that is, the load change rate reference value, the load fluctuation amplitude reference value, the load change duration reference value and the load change frequency reference value;

[0026] For each time point, the ratio of each trend characteristic to its reference value is calculated to reflect the high and low of the actual trend characteristic of the time point relative to the reference value, and the relative change rate of each trend characteristic is obtained;

[0027] For each time point, the square root of the sum of squares of the relative change rates of the load change rate and the load fluctuation amplitude is calculated as the numerator part;

[0028] For each time point, the result of adding the relative change rate of the load change duration to the relative change rate of the load change frequency is substituted into an exponential function to obtain the value of the denominator part, the use of the exponential function emphasizes the influence of the load change duration and the load change frequency, and the denominator as a whole reflects the comprehensive influence of the duration and the frequency on the unit load change;

[0029] The numerator part obtained by calculation is divided by the denominator part to obtain the exponential contribution value of each time point, and then the exponential contribution values of all time points are added, and the sum is the unit load trend value.

[0030] The further improvement of the technical scheme of the present application is that the working condition monitoring module specifically comprises:

[0031] Extract the operating data collected from each subsystem of the thermal power unit, including key parameters such as temperature, pressure, flow rate, power, rotating speed and load, and synchronize and align the data of different subsystems through time stamp, eliminate dimension difference by using Z-score standardization or Min-Max normalization, unify heterogeneous data into time series data set, and ensure data time sequence consistency and comparability;

[0032] Extract the working condition characteristics reflecting the operating conditions of the thermal power unit from the time series data set, and then determine the sub-features of each working condition characteristic, and classify the historical operating data by using a clustering algorithm, analyze the historical operating data and the standard feature mode under normal working conditions, establish a typical working condition mode library, and determine the reference values corresponding to each working condition characteristic sub-feature, wherein for the temperature working condition characteristic, the sub-features include main steam temperature, reheat steam temperature, condenser temperature and bearing temperature, for the pressure working condition characteristic, the sub-features include main steam pressure, condenser pressure and fuel pressure, for the flow rate working condition characteristic, the sub-features include fuel flow rate, feed water flow rate and air flow rate, for the power working condition characteristic, the sub-features include turbine output power, generator output power and reactive power, for the rotating speed working condition characteristic, the sub-features include turbine rotating speed and generator rotating speed, and for the load working condition characteristic, the sub-features include unit active load, load change rate and load fluctuation amplitude;

[0033] By using a similarity matching algorithm, the real-time working condition characteristics are compared with the standard feature mode in the typical working condition mode library, the working condition similarity is calculated, and the deviation degree of the current working condition from the typical working condition mode is quantified;

[0034] Combined with the historical operating data and the operating requirements of the thermal power unit, multi-level matching thresholds of the working condition similarity are set, which are normal matching threshold and abnormal matching threshold respectively, and then the state of the current working condition is analyzed to distinguish between normal working condition and abnormal working condition, so as to judge whether the current working condition of the system is abnormal.

[0035] The further improvement of the technical scheme of the present application is that the calculation process of the working condition similarity is:

[0036] The working condition features reflecting the operation working condition of the thermal power generating unit are extracted from the time series data set, including temperature, pressure, flow, power, rotating speed and load, and sub-features of each working condition feature;

[0037] For each sub-feature of the working condition feature, the absolute difference between the actual value and the reference value is calculated, and then the ratio of the absolute difference to the reference value is calculated to determine the relative deviation degree of each sub-feature;

[0038] For each sub-feature of the working condition feature, the change rate integral of the actual value in the time interval [0, T] is calculated, and the change rate integral deviation penalty function is calculated in combination with the exponential function;

[0039] For each sub-feature of the working condition feature, the relative deviation degree and the change rate integral deviation penalty function are combined to analyze its contribution to the working condition similarity, and the static deviation degree and the dynamic change degree of the sub-feature are comprehensively considered to obtain the similarity contribution value of each sub-feature;

[0040] The similarity contribution values of all sub-features of the working condition feature are summed and averaged to calculate the working condition similarity, that is, the overall working condition similarity, which reflects the deviation degree of the current working condition from the typical working condition mode.

[0041] The further improvement of the technical scheme of the present application is that the distributed control module comprises a cooperative control unit, a bat algorithm optimization unit and a control execution unit;

[0042] The cooperative control unit is used to disperse the control function to the controllers corresponding to each subsystem, and each sub-controller independently completes the preliminary control of the corresponding subsystem and performs local cooperative control.

[0043] The bat algorithm optimization unit is used to globally optimize the load change and working condition monitoring result of the thermal power generating unit under the distributed control framework by using the bat algorithm, so as to find the optimal control parameters and scheduling scheme.

[0044] The control execution unit is used to generate control instructions in combination with the optimal control parameters and scheduling scheme, to perform real-time control on each subsystem of the thermal power generating unit, to adjust the operating parameters, and to realize independent and cooperative control of each subsystem through distributed control, thereby improving the flexibility and reliability of the system.

[0045] The further improvement of the technical scheme of the present application is that the bat algorithm optimization unit specifically comprises:

[0046] Under the distributed control framework, the load change and working condition monitoring result of the thermal power unit is converted into an optimization problem, a target function and a constraint condition are defined, wherein the defined target function is to maximize the peak regulation efficiency, the constraint condition is the load response rate, the upper and lower limits of the equipment output and the working condition stability, then a bat population is initialized, each individual represents a set of control parameters, and an initial solution is generated by random sampling, the algorithm parameters including the pulse frequency range, the loudness attenuation rate and the search space boundary are set to ensure that the population diversity covers the feasible solution region, the pulse frequency range is [0, 2], the loudness attenuation rate is 0.9, and the search space boundary is ±10% of the rated value of the equipment.

[0047] Based on the biological characteristics of the bat algorithm, the search behavior of the individual in the solution space is simulated, each bat adjusts the pulse frequency and loudness (the initial value is 1 and attenuates with iteration) through a dynamic update formula, generates a new solution in combination with the current global optimal solution, updates the search speed of the bat in the solution space by using a speed update formula to explore the solution space, and meanwhile, a dynamic inertia weight is introduced, the weight is increased in the initial search stage to enhance the global search ability, and the weight is reduced in the later stage to accelerate the local convergence, so that the global search and local development ability are balanced, and it is ensured that all individuals always meet the physical constraint condition.

[0048] The target function value of each bat individual is calculated, the global optimal solution and the individual historical optimal solution are updated according to the target function value, a greedy strategy is adopted to select a better solution, and the bat predation behavior is simulated, if the new solution is better than the current solution and the loudness meets the condition, the new solution is accepted and the loudness is reduced, otherwise the original solution is retained and the pulse frequency is adjusted, the population is updated through iteration, the global optimal solution is gradually approached, and the convergence trend of each iteration is recorded to evaluate the algorithm efficiency, if the target function value fluctuates by less than 0.1% for 5 consecutive iterations, the termination condition is triggered.

[0049] The final converged global optimal solution is subjected to feasibility verification, whether the constraint condition (the load response rate is greater than or equal to 2% per minute, and the equipment output is within the rated range) is met is checked, if the verification is passed, the optimal control parameters and the scheduling scheme are output, if the constraint condition is not met, local search or population re-initialization is started, and the optimization result is synchronized to the collaborative control unit to drive each sub-controller to adjust the operation parameters, so that the load dynamic optimization and working condition adaptive adjustment of the thermal power unit are carried out.

[0050] The further improvement of the technical scheme of the present application is that the control execution unit specifically comprises:

[0051] The control execution unit receives the optimal control parameters and scheduling scheme output by the Bat Algorithm Optimization Unit, parses them into control instructions that can be executed by each subsystem, and decomposes the global optimization objective into corresponding control parameters such as boiler fuel quantity, turbine valve opening, and generator power setpoint. It then dynamically corrects these parameters based on the current operating conditions, generating an instruction set that includes timing constraints and priority tags to ensure that the instructions are compatible with the distributed control node interface protocol.

[0052] Distributed control distributes control commands to each subsystem controller in real time, triggering independent control processes. Each subsystem performs autonomous adjustment based on closed-loop control using local sensor data, ensuring that operating parameters respond quickly to command requirements, while simultaneously uploading the execution status to the control execution unit.

[0053] The control execution unit continuously monitors the operating status of each subsystem of the thermal power unit, collects real-time operating data, and compares it with the optimized control parameters and scheduling scheme. If deviations or abnormalities are found, the control commands are adjusted and the operating parameters are corrected to ensure that the subsystem operates in an optimized state.

[0054] A further improvement to the technical solution of the present invention is that the security monitoring and early warning module specifically includes:

[0055] The safety monitoring and early warning module continuously monitors various key parameters during the deep peak shaving process of thermal power units, and comprehensively evaluates the operating effect of thermal power units to analyze whether various key parameters are within the normal operating range.

[0056] By comparing the current key parameters with preset safety thresholds, it is determined whether the current operating status meets the safety requirements. Once any key parameter is found to exceed the preset safety threshold, the alarm mechanism is immediately triggered and an alarm message is issued. The alarm message is issued through various means such as audible and visual alarms, SMS notifications, and system prompts to notify operators and maintenance personnel to perform corresponding maintenance measures. At the same time, relevant information of the alarm event is recorded.

[0057] Continuously monitor the status of thermal power units, track key parameters that trigger alarms, and report the implementation status of maintenance measures to the monitoring system until the key parameters return to normal range.

[0058] Due to the adoption of the above technical solution, the technical progress achieved by this invention compared to the prior art is as follows:

[0059] 1. This invention provides a deep peak-shaving control system for thermal power units. By introducing a distributed control architecture and the Bat algorithm for optimization, the subsystems of the thermal power unit are divided into multiple local control units, realizing independent and collaborative control. This significantly improves the flexibility and response speed of the thermal power unit during deep peak shaving. Distributed control ensures that each subsystem can quickly adjust its operating parameters according to actual load demand, while the global optimization capability of the Bat algorithm further enhances the system's adaptability and decision-making efficiency when facing complex operating conditions, thus effectively solving the problem of response lag in the traditional centralized control mode.

[0060] 2. This invention provides a deep peak-shaving control system for thermal power units. It utilizes big data analysis and load forecasting technology, combined with real-time and historical operating data of thermal power units, to predict load change trends and formulate optimal control parameters and scheduling schemes accordingly. This not only improves peak-shaving efficiency but also reduces operating costs by minimizing unnecessary energy waste and equipment wear. Attached Figure Description

[0061] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0062] Figure 1 This is a schematic diagram of the system functional modules of the present invention;

[0063] Figure 2 This is a schematic diagram of the workflow of the bat algorithm optimization unit of the present invention. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0065] Example 1, as Figure 1 , Figure 2 As shown, the present invention provides a deep peak shaving control system for thermal power units, including a deep peak shaving control center. The deep peak shaving control center is communicatively connected to a data acquisition module, a load prediction module, an operating condition monitoring module, a distributed control module, and a safety monitoring and early warning module, wherein the modules are electrically connected to each other.

[0066] The deep peak regulation control center is a command center of the whole control system, is responsible for communication connection and coordination scheduling among modules, integrates information of the modules and issues instructions, realizes centralized management and unified regulation and control on the deep peak regulation process of the thermal power unit, and ensures collaborative work of the modules;

[0067] The data acquisition module is used for real-time acquisition and pre-processing of operation data of each subsystem of the thermal power unit, including key parameters of temperature, pressure, flow, power, rotating speed and load, ensures comprehensiveness and real-time of the data through distributed arrangement of data acquisition points, plans layout of the data acquisition points of each subsystem of the thermal power unit according to the peak regulation demand of the thermal power unit, determines required operation data including key parameters of temperature, pressure, flow, power, rotating speed and load, at the same time, formulates acquisition frequency and time interval, designs operation data acquisition scheme, and ensures comprehensive coverage of operation states of each subsystem, wherein, the temperature includes main steam temperature, reheat steam temperature, exhaust gas temperature, bearing temperature and the like, the pressure includes main steam pressure, reheat steam pressure, feed water pressure, lubricating oil pressure and the like, the flow includes main steam flow, feed water flow, fuel flow, cooling water flow and the like, the power includes generator output power, steam turbine shaft power and the like, the rotating speed includes steam turbine rotating speed, feed water pump rotating speed and the like, and the load includes grid demand load, actual load of the unit and the like, according to the planned acquisition scheme, the operation data of each subsystem of the thermal power unit is acquired through the distributed arrangement of the data acquisition points, the actual values of the corresponding key parameters are acquired through the configured sensors of each data acquisition point, and the data is transmitted to the data acquisition module in the form of electric signal, the real-time and accuracy of the data is ensured, the acquired original operation data is pre-processed, including data cleaning and normalization processing steps, wherein, through the data cleaning, the noise and abnormal value are removed, the data is filtered, the data curve is smoothed, and the data is normalized to unify the data to the same dimension and range, the quality and consistency of the data are improved, the pre-processed operation data is integrated, the thermal power operation sequence table is obtained, and the data warehouse is built, and the related data of the thermal power operation sequence table is stored in the data warehouse;

[0068] The load prediction module is configured to analyze the load change trend of the thermal power unit by using historical operation data, extract historical operation data of the thermal power unit from the operation record of the thermal power unit, including power, load and corresponding timestamp information, sort and align the data according to time sequence, form a unified format, perform feature analysis on the historical operation data, extract trend features related to load prediction, including load change rate, load fluctuation amplitude, load change duration and load change frequency, preset reference values of each trend feature in combination with historical operation data and operation requirements of the thermal power unit, and then integrate each trend feature and the corresponding reference value to obtain a load trend feature sequence table. The load change rate is the change amount of the load in a unit time, expressed in MW / min (megawatt / minute), reflecting the speed of load change, and is used to analyze the response capability of the thermal power unit to load fluctuation. The load fluctuation amplitude is the difference between the maximum and minimum values of the load in a specific time period, usually expressed in MW, quantifying the severity of load change, and is used to analyze the fluctuation characteristics of the load. The load change duration is the time for the load to change from one state to another, usually expressed in minutes, evaluating the persistence of load change, and is used for unit start-stop decision and fuel supply planning. The load change frequency is the number of load changes in a unit time, usually expressed in times / hour, reflecting the frequency of load change, and is used to evaluate the fatigue damage and service life of the unit equipment. The load trend feature sequence table is divided into a training set, a validation set and a test set, and a basic framework based on time sequence analysis is selected to build a load prediction model, input the trend features, and output the load change trend of the thermal power unit. The model is trained through the training set, and the model parameters are adjusted to optimize the prediction accuracy. The performance of the model is evaluated by using the validation set to ensure that the model can accurately capture the trend and regularity of load change. The constructed model is evaluated by using the test set to improve the prediction accuracy and generalization ability of the model, and then the final load prediction model is obtained. The constructed load prediction model is used to input the related data of the load trend feature sequence table of the current time period, calculate the unit load trend value, and predict the load change trend of the thermal power unit in the future period of the same time period.

[0069] The calculation process of the unit load trend value is as follows:

[0070] The trend characteristic related data of the thermal power unit in the current time period is extracted from the load trend characteristic sequence table, including the load change rate, the load fluctuation amplitude, the load change duration and the load change frequency of each time point, and the corresponding reference values of the trend characteristics are determined, i.e. the load change rate reference value, the load fluctuation amplitude reference value, the load change duration reference value and the load change frequency reference value. For each time point, the ratio of each trend characteristic to the reference value is calculated to reflect the high and low of the actual trend characteristic relative to the reference value at the time point, and the relative change rate of each trend characteristic is obtained. For each time point, the square root of the sum of the squares of the relative change rates of the load change rate and the load fluctuation amplitude is calculated to comprehensively reflect the relative changes of the load change rate and the load fluctuation amplitude, and the index reflecting the combined action of the two is formed as the numerator part. For each time point, the result of adding the relative change rate of the load change duration to the relative change rate of the load change frequency is substituted into the exponential function to obtain the value of the denominator part. The use of the exponential function emphasizes the influence of the load change duration and the load change frequency. The denominator as a whole reflects the comprehensive influence of the duration and the frequency on the load change of the unit. The numerator part obtained by calculation is divided by the denominator part to obtain the exponential contribution value at each time point. Then the exponential contribution values at all time points are added, and the sum is the load trend value of the unit.

[0071] The calculation expression of the load trend value of the unit is as follows:

[0072]

[0073] In the formula, L is the load trend value of the unit, reflecting the comprehensive trend of the load change of the thermal power unit. The larger the value is, the more intense the load change is. n is the number of sample points calculated in the time period. OCR i is the load change rate of the i-th time point, with the unit of MW / min, indicating the amount of load change per unit time, reflecting the speed of load change. OCR base is the load change rate reference value, which is preset according to historical operation data and operation requirements of the thermal power unit, and is used to measure the relative level of the actual load change rate. OVA i is the load fluctuation amplitude of the i-th time point, with the unit of MW, indicating the difference between the maximum and minimum values of the load in a certain time period, quantifying the intensity of load change. OVA base is the load fluctuation amplitude reference value. OCD i is the load change duration of the i-th time point, with the unit of minutes, indicating the time duration of the load change from one state to another. OCD base is the load change duration reference value. OCF i is the load change frequency of the i-th time point, with the unit of times / hour, indicating the number of load changes per unit time, reflecting the frequency of load change. OCFbase For the load change frequency reference value, when all actual load characteristics are far below the reference value, the index approaches 0, indicating that the load change is gentle; when the actual load characteristics approach or exceed the reference value, the index gradually increases, indicating that the load change is intense, when the unit load trend value is lower, it indicates that the load change of the thermal power unit is relatively stable, and the unit is in a relatively stable operation state, at this time, the operation risk of the unit is lower, and the intensity of peak shaving can be appropriately reduced to improve the operation efficiency, when the unit load trend value is higher, the load change is intense, and the unit needs to pay high attention, and more active peak shaving measures may need to be taken;

[0074] The working condition monitoring module is configured to monitor the working condition of the thermal power generating unit, identify the abnormality of the current working condition, help the system adopt an adjustment strategy according to the working condition state, thereby improving the accuracy and efficiency of the peak shaving process, extract the operation data collected from each subsystem of the thermal power generating unit, including the key parameters of temperature, pressure, flow rate, power, rotating speed and load, and synchronize the data of different subsystems through time stamp alignment, eliminate the dimensional difference by using Z-score standardization or Min-Max normalization, unify the heterogeneous data into a time series data set, and ensure the consistency and comparability of the data time series, extract the working condition features reflecting the operation working condition of the thermal power generating unit from the time series data set, and then determine the sub-features of each working condition feature, and classify the historical operation data by using a clustering algorithm, analyze the historical operation data and the standard feature mode under the normal working condition, establish a typical working condition mode library, and determine the reference values corresponding to each working condition feature sub-feature, wherein for the working condition feature of temperature, the sub-features thereof include the main steam temperature, the reheat steam temperature, the condenser temperature and the bearing temperature, the main steam temperature reflects the efficiency of boiler combustion and steam generation, and the operating condition of the steam turbine, the reheat steam temperature affects the efficiency and operating safety of the steam turbine, the condenser temperature affects the back pressure and circulation efficiency of the steam turbine, and the bearing temperature reflects the mechanical operating state of the unit, and an excessively high temperature may indicate a lubrication or centering problem, for the working condition feature of pressure, the sub-features thereof include the main steam pressure, the condenser pressure and the fuel pressure, the main steam pressure affects the steam flow rate and the output power of the steam turbine, the condenser pressure and the condenser temperature jointly affect the thermal efficiency of the steam turbine, and the fuel pressure affects the working state of the fuel supply system and the combustion efficiency, for the working condition feature of flow rate, the sub-features thereof include the fuel flow rate, the feed water flow rate and the air flow rate, the fuel flow rate is directly related to the combustion intensity of the boiler and the steam generation amount, the feed water flow rate affects the water circulation and steam generation of the boiler, and the air flow rate affects the combustion efficiency and pollutant emission, for the working condition feature of power, the sub-features thereof include the output power of the steam turbine, the output power of the generator and the reactive power, the output power of the steam turbine reflects the power generation capacity and operating efficiency of the unit, the output power of the generator and the power of the steam turbine jointly reflect the overall power generation performance of the unit, and the reactive power reflects the ability of the unit to support the voltage of the power grid, for the working condition feature of rotating speed, the sub-features thereof include the rotating speed of the steam turbine and the rotating speed of the generator, the rotating speed of the steam turbine affects the output power and mechanical stability of the steam turbine, and the rotating speed of the generator is usually synchronized with the rotating speed of the steam turbine, thereby affecting the power generation frequency, and for the working condition feature of load, the sub-features thereof include the active load of the unit, the load change rate and the load fluctuation amplitude, the active load of the unit reflects the active power demand of the power grid borne by the unit, the load change rate reflects the speed and flexibility of the load adjustment of the unit, and the load fluctuation amplitude reflects the stability of the load of the unit, by using a similarity matching algorithm, the real-time working condition features are compared with the standard feature modes in the typical working condition mode library, the working condition similarity is calculated, the deviation degree of the current working condition from the typical working condition mode is quantified, and the change trend of the similarity in the time dimension is analyzed by using a sliding window technology,Identify short-term fluctuations and long-term deviations, generate working condition deviation heat map, intuitively show the abnormal tendency of each feature dimension, set multi-level matching threshold of working condition similarity according to historical operation data and operation demand of thermal power unit, and set normal matching threshold and abnormal matching threshold, and then analyze the state of the current working condition to distinguish normal working condition and abnormal working condition, so as to judge whether the current working condition of the system is abnormal.

[0075] The calculation process of working condition similarity is as follows:

[0076] The working condition characteristics reflecting the operation condition of the thermal power unit are extracted from the time series data set, including temperature, pressure, flow, power, speed and load, as well as the sub-features of each working condition characteristic. For each sub-feature of the working condition characteristic, the absolute difference between the actual value and the reference value is calculated, and then the ratio of the absolute difference to the reference value is calculated to determine the relative deviation degree of each sub-feature. By dividing the reference value, the influence of different characteristic dimensions is eliminated, so that the deviation degree of different characteristics is comparable. For each sub-feature of the working condition characteristic, the change rate integral of the actual value in the time interval [0, T] is calculated, and the change rate integral deviation penalty function is calculated by combining the exponential function. The change rate integral reflects the change amplitude of the sub-feature in the time interval. The greater the change rate, the greater the integral value, indicating that the sub-feature has greater fluctuation in the time interval. The value of the exponential function decreases with the increase of the integral value, so that the characteristics with greater change amplitude are given greater deviation penalty. For each sub-feature of the working condition characteristic, the relative deviation degree and the change rate integral deviation penalty function are combined to analyze its contribution to the working condition similarity. The static deviation degree and dynamic change degree of the sub-feature are considered comprehensively to obtain the similarity contribution value of each sub-feature. The similarity contribution values of all sub-features of the working condition characteristic are summed and averaged to calculate the working condition similarity, that is, the overall working condition similarity, which reflects the deviation degree of the current working condition from the typical working condition mode.

[0077] The calculation expression of working condition similarity is as follows:

[0078]

[0079] In the formula, S is the working condition similarity, which is used to quantify the deviation degree of the current working condition from the typical working condition mode. The smaller the value, the smaller the deviation degree, and the closer the working condition to the normal. N is the total number of sub-features of the working condition characteristic, F j is the actual value of the jth sub-feature of the working condition characteristic, F base，j is the jth sub-feature reference value of the working condition characteristic, that is, the standard value under normal working condition, which is used to measure the deviation degree of the actual value, F j(t) is a function of time, representing the actual value of the jth working condition characteristic sub-feature at time t, T is the upper limit of the time interval, i.e. the end time of the considered time range, S is in the range of 0 to 1, when S approaches 0, it means that the current working condition is highly consistent with the typical working condition mode, and the deviation is extremely small, when S approaches 1, it means that the current working condition deviates from the typical working condition mode, and the working condition is abnormal, the normal working condition is that the actual value of each working condition characteristic sub-feature and the reference value are close, the relative deviation is small, and the change rate is also small, so the S value is close to 0, the abnormal working condition is that when one or more working condition characteristic sub-features are abnormal, the relative deviation and the change rate increase, and the S value will increase significantly, exceeding the set normal matching threshold, and entering the abnormal state;

[0080] The distributed control module is used for dividing each subsystem of the thermal power generating unit into multiple local control units, each control unit independently adjusts and coordinates with other units, and analyzes the load change and working condition monitoring result of the thermal power generating unit by using the bat algorithm to find the optimal control parameter and scheduling scheme, and then generates and executes the control instruction.

[0081] The safety monitoring and early warning module is used for evaluating the operation effect of the thermal power generating unit and continuously monitoring each key parameter in the deep peak shaving process of the thermal power generating unit, and once it is found that the key parameter exceeds the safety threshold, the alarm mechanism is triggered, and corresponding safety protection measures are taken.

[0082] In embodiment 2, as shown in the accompanying drawings, on the basis of embodiment 1, the application provides a technical solution: Figure 1 , Figure 2 Preferably, the distributed control module comprises a cooperative control unit, a bat algorithm optimization unit and a control execution unit.

[0083] The cooperative control unit is used for dispersing the control function to the controllers corresponding to each subsystem, and each sub-controller independently completes the preliminary control of the corresponding subsystem and performs local cooperative control.

[0084] The cooperative control unit specifically comprises: based on a hierarchical distributed architecture, the control task of the whole thermal power generating unit is decomposed into multiple sub-tasks including boiler combustion control, steam turbine load regulation, generator power balance, fuel supply management, etc., and the sub-tasks are distributed to the controllers of the corresponding subsystems; each sub-controller is logically isolated by an independent computing unit, ensuring that the basic operation of the corresponding subsystem can be maintained when communication is interrupted or fails; the authority range of each sub-controller is determined in the task distribution stage (for example, the boiler controller only adjusts the fuel quantity and air quantity), a redundant backup mechanism is established to ensure reliable execution of the control task; each sub-controller performs preliminary control on the corresponding subsystem according to the preset control strategy (PID control); the sub-controller adjusts the operating parameters of the subsystem according to the real-time collected operating data and in combination with the preset control strategy to meet the basic operating requirements of the subsystem, wherein the goal of preliminary control is to ensure that each subsystem operates within a normal range; after preliminary control is completed, each sub-controller exchanges operating state information through a standardized communication interface (CAN bus) with other sub-controllers, and adjusts its own operating parameters according to the requirements of adjacent or related subsystems to perform local cooperative operation;

[0085] The bat algorithm optimization unit is used to globally optimize the load variation and working condition monitoring results of the thermal power generating unit under the distributed control framework by using the bat algorithm, to find the optimal control parameters and scheduling scheme, and to convert the load variation and working condition monitoring results of the thermal power generating unit into an optimization problem under the distributed control framework, define the objective function and constraint conditions, wherein the defined objective function is to maximize the peak regulation efficiency, and the constraint conditions are the load response rate, the upper and lower limits of equipment output and the working condition stability, and then initialize the bat population, each individual represents a set of control parameters, and an initial solution is generated by random sampling, algorithm parameters including pulse frequency range, loudness decay rate and search space boundary are set to ensure that the population diversity covers the feasible solution region, the pulse frequency range is [0, 2], the loudness decay rate is 0.9, and the search space boundary is ±10% of the rated value of the equipment, based on the biological characteristics of the bat algorithm, the search behavior of individuals in the solution space is simulated, each bat adjusts the pulse frequency and loudness (initial value 1, attenuates with iteration) through a dynamic update formula, generates a new solution in combination with the current global optimal solution, and updates the search speed of the bat in the solution space by using a speed update formula to explore the solution space, while a dynamic inertia weight is introduced to increase the weight in the early stage of search to enhance the global search ability, and to reduce the weight in the later stage to speed up local convergence, balance the global search and local development ability, and ensure that all individuals always meet the physical constraint conditions;

[0086] The calculation expression of the dynamic update formula is as follows:

[0087] f k =f min +(f max -f min )·rand;

[0088] where f k is the current pulse frequency of the kth bat, f min is the minimum value of the pulse frequency of the bat, usually taking 0 or a value close to 0, f max is the maximum value of the pulse frequency of the bat, usually taking 2, and rand is a random number uniformly distributed in the interval [0, 1], f k The value range of f min is between [f max , f best ], and as the iteration proceeds, the bat will gradually tend to use a higher frequency for more fine search;

[0089] The calculation expression of the velocity update formula is as follows:

[0090]

[0091] where x is the velocity of the kth bat in the u+1th generation, ω is a dynamic inertia weight for balancing the global search and local development ability, usually taking a value in the interval [0, 1], and gradually decreasing as the iteration proceeds, is the velocity of the kth bat in the uth generation, x best is the position of the current global optimal solution, is the position of the kth bat in the uth generation, and in the initial stage of the bat algorithm, the dynamic inertia weight ω is larger, so that the bat can maintain a larger speed and enhance the global search ability to explore a wider solution space. As the iteration proceeds, ω gradually decreases, and the speed of the bat also decreases accordingly, so as to accelerate the local convergence and improve the search precision. In the search process, the speed of the bat is dynamically adjusted according to the distance between the current position and the global optimal solution, the pulse frequency and the dynamic inertia weight, so as to balance the global search and local development ability;

[0092] The target function value of each bat individual is calculated, the global optimal solution and individual historical optimal solution are updated according to the target function value, a better solution is selected by using a greedy strategy, and the bat predation behavior is simulated. If the new solution is better than the current solution and the loudness meets the condition, the new solution is accepted and the loudness is reduced, otherwise the original solution is retained and the pulse frequency is adjusted. The population is updated by iteration to gradually approach the global optimal solution, and the convergence trend of each iteration is recorded to evaluate the efficiency of the algorithm. If the target function value fluctuates by less than 0.1% for 5 consecutive iterations, the termination condition is triggered. The feasibility of the final converged global optimal solution is verified, and whether the constraint condition (load response rate ≥ 2% / min, equipment output within the rated range) is met is checked. If the verification is passed, the optimal control parameters and scheduling scheme are output, if not, the local search or re-initialization of the population is started, and the optimization results are synchronized to the cooperative control unit to drive each sub-controller to adjust the operating parameters, and the dynamic optimization of the thermal power unit load and the adaptive adjustment of the working condition are carried out.

[0093] The calculation expression of the target function value of each bat individual is as follows:

[0094]

[0095] In the formula, Fit is the target function value of each bat individual, representing the optimization degree of peak regulation efficiency, the larger the value, the higher the peak regulation efficiency, K is the number of load demand points, P p is the actual output of the pth load demand point, unit: MW, P base，p is the reference output of the pth load demand point, unit: MW, representing the output of the point under normal working condition, M is the number of equipment, R o is the load response rate of the oth equipment, unit: MW / min, R base，o is the reference load response rate of the oth equipment, unit: MW / min, representing the load response rate of the equipment under normal working condition, λ is the weight coefficient, used to balance the contribution of load demand and equipment output constraint, the value range is usually between 0 and 1. When the target function value approaches 0, it means that the peak regulation efficiency is very low, and the constraints of load demand and equipment output are not met. When the target function value gradually increases, it means that the peak regulation efficiency increases, and the constraints of load demand and equipment output are met.

[0096] The control execution unit is configured to generate control instructions in combination with the optimal control parameters and the scheduling scheme, to perform real-time control on each subsystem of the thermal power generating unit, to adjust the operation parameters, to realize independent and collaborative control on each subsystem through distributed control, to improve the flexibility and reliability of the system, to receive the optimal control parameters and the scheduling scheme output by the bat algorithm optimization unit, to analyze the optimal control parameters and the scheduling scheme into executable control instructions for each subsystem, to decompose the global optimization target into corresponding control parameters such as the boiler fuel quantity, the turbine valve opening degree, and the generator power set value, to combine the current working condition characteristics to dynamically correct the control instructions, to generate an instruction set containing time sequence constraints and priority labels, to ensure that the instruction is compatible with the distributed control node interface protocol, to distribute the control instructions to each subsystem controller in real time through distributed control, to trigger an independent control process, to perform autonomous adjustment based on the local sensor data closed-loop control of each subsystem, to ensure that the operation parameters quickly respond to the instruction requirements, and to upload the execution status to the control execution unit, to continuously monitor the operation status of each subsystem of the thermal power generating unit, to collect real-time operation data, and to compare the real-time operation data with the optimized control parameters and the scheduling scheme, to adjust the control instructions and correct the operation parameters if a deviation or an abnormal condition is found, and to ensure that the subsystems operate in an optimized state.

[0097] The safety monitoring and early warning module specifically comprises:

[0098] The safety monitoring and early warning module continuously monitors each key parameter in the deep peak shaving process of the thermal power generating unit, and comprehensively evaluates the operation effect of the thermal power generating unit, analyzes whether each key parameter is within a normal operation range, compares the current key parameter with a preset safety threshold, judges whether the current operation state meets the safety requirement, triggers an alarm mechanism and sends an alarm information as soon as any key parameter exceeds the preset safety threshold, wherein the alarm information is sent through various ways such as audible and visual alarm, short message notification, system prompt, etc., to notify the operating personnel and maintenance personnel to perform corresponding maintenance measures, at the same time, records the related information of the alarm event, continuously monitors the state of the thermal power generating unit, tracks the key parameter that triggers the alarm, and feeds back the execution situation of the maintenance measures to the monitoring system until the key parameter returns to the normal range.

[0099] The above is merely a specific implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which shall be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A deep peak-shaving control system for thermal power units, comprising a deep peak-shaving control center, characterized in that: The deep peak shaving control center is communicatively connected to a data acquisition module, a load forecasting module, an operating condition monitoring module, a distributed control module, and a safety monitoring and early warning module, wherein the modules are electrically connected to each other. The data acquisition module is used to collect and preprocess the operating data of each subsystem of the thermal power unit in real time, including key parameters such as temperature, pressure, flow rate, power, speed and load. The load forecasting module is used to analyze the load change trend of thermal power units using historical operating data; The operating condition monitoring module is used to monitor the operating condition of the thermal power unit and identify abnormalities in the current operating condition; The distributed control module is used to divide the various subsystems of the thermal power unit into multiple local control units, and to analyze the load changes and operating condition monitoring results of the thermal power unit using the bat algorithm to find the optimal control parameters and scheduling scheme, and then generate and execute control commands. The distributed control module includes a cooperative control unit, a bat algorithm optimization unit, and a control execution unit. The collaborative control unit is used to distribute control functions to the controllers corresponding to each subsystem and perform local collaborative control. The Bat Algorithm Optimization Unit is used to perform global optimization of the load changes and operating condition monitoring results of thermal power units using the Bat Algorithm, to find the optimal control parameters and scheduling scheme, specifically including: Under the distributed control framework, the load changes and operating condition monitoring results of thermal power units are transformed into optimization problems. Objective functions and constraints are defined. The objective function is to maximize peak shaving efficiency, and the constraints are load response rate, upper and lower limits of equipment output and operating condition stability. Then, the bat population is initialized, with each individual representing a set of control parameters. An initial solution is generated through random sampling, and algorithm parameters including pulse frequency range, loudness attenuation rate and search space boundary are set. Based on the biological characteristics of the bat algorithm, the search behavior of an individual in the solution space is simulated. Each bat adjusts the pulse frequency and loudness through a dynamic update formula, and generates a new solution by combining the current global optimal solution. The search speed of the bat in the solution space is updated by a speed update formula to explore the solution space. At the same time, dynamic inertia weight is introduced to balance the global search and local exploration capabilities. The objective function value for each individual bat is calculated. The global optimum and the individual's historical optimum are updated based on the objective function value. A greedy strategy is used to select a better solution and the bat's predation behavior is simulated. If the new solution is better than the current solution and the loudness meets the condition, the new solution is accepted and the loudness is reduced. Otherwise, the original solution is retained and the pulse frequency is adjusted. The population is updated iteratively to gradually approach the global optimum. The convergence trend of each iteration is recorded to evaluate the algorithm efficiency. If the objective function value fluctuates by less than 0.1% for 5 consecutive iterations, the termination condition is triggered. The feasibility of the finally converged global optimal solution is verified to check whether the constraints are met. If the verification is successful, the optimal control parameters and scheduling scheme are output. If not, a local search is started or the population is re-initialized. The optimization results are synchronized to the cooperative control unit to drive each sub-controller to adjust the operating parameters and perform dynamic optimization of the thermal power unit load and adaptive adjustment of the operating conditions. The control execution unit is used to generate control commands by combining the optimal control parameters and scheduling scheme, and to perform real-time control on each subsystem of the thermal power unit and adjust the operating parameters. The safety monitoring and early warning module is used to continuously monitor various key parameters during the deep peak shaving process of thermal power units. If the parameters exceed the safety threshold, an alarm mechanism is triggered, and corresponding safety protection measures are taken.

2. The deep peak-shaving control system for thermal power units according to claim 1, characterized in that: The data acquisition module specifically includes: Based on the peak-shaving requirements of thermal power units, the layout of data acquisition points for each subsystem of the thermal power unit is planned, the required operating data to be collected is determined, including key parameters such as temperature, pressure, flow rate, power, speed and load, and the acquisition frequency and time interval are determined, and an operating data acquisition scheme is designed. According to the planned data collection scheme, the operation data of each subsystem of the thermal power unit is collected by using distributed data collection points. Each data collection point obtains the actual values ​​of the corresponding key parameters through the configured sensors and transmits the data to the data acquisition module in the form of electrical signals. The collected raw operational data is preprocessed, including data cleaning and normalization steps. The preprocessed operational data is integrated to obtain a thermal power plant operation sequence table, and a data warehouse is built to store the relevant data of the thermal power plant operation sequence table in the data warehouse.

3. The deep peak-shaving control system for thermal power units according to claim 1, characterized in that: The load forecasting module specifically includes: Historical operating data of thermal power units are extracted from their operating records, including power, load, and corresponding timestamp information, and the data is sorted and aligned according to time series. Feature analysis is performed on historical operating data to extract trend features related to load forecasting, namely load change rate, load fluctuation amplitude, load change duration and load change frequency. Combined with historical operating data and the operating requirements of thermal power units, benchmark values ​​for each trend feature are preset, and then each trend feature and its corresponding benchmark value are integrated to obtain a load trend feature sequence table. The load trend feature sequence table is divided into training set, validation set and test set. A time series analysis-based infrastructure is selected to build a load prediction model. The trend features are input and the load change trend of thermal power units is output. Using the established load forecasting model, and inputting relevant data from the load trend characteristic sequence table for the current time period, along with the load trend value of the power unit, the load change trend of the thermal power unit over a future period of the same time period can be predicted.

4. The deep peak-shaving control system for thermal power units according to claim 3, characterized in that: The calculation process for the unit load trend value is as follows: Extract relevant data on the trend characteristics of thermal power units in the current time period from the load trend characteristic sequence table, including the load change rate, load fluctuation amplitude, load change duration and load change frequency at each time point, and determine the benchmark values ​​corresponding to each trend characteristic, namely the benchmark value of load change rate, the benchmark value of load fluctuation amplitude, the benchmark value of load change duration and the benchmark value of load change frequency. For each time point, the ratio of each trend feature to its baseline value is calculated to obtain the relative rate of change of each trend feature; For each time point, calculate the square root of the sum of squares of the relative rates of change of load change rate and load fluctuation amplitude, and use it as the numerator; For each time point, the result of adding the relative rate of change of the duration of load change to the relative rate of change of the frequency of load change is substituted into the exponential function to obtain the value of the denominator. Divide the calculated numerator by the denominator to obtain the exponential contribution value at each time point. Then, add up the exponential contribution values ​​at all time points, and the sum is the unit load trend value.

5. A deep peak-shaving control system for thermal power units according to claim 1, characterized in that: The operating condition monitoring module specifically includes: The operation data collected from various subsystems of the thermal power unit, including key parameters such as temperature, pressure, flow rate, power, speed and load, are extracted and unified into a time series dataset through timestamp alignment and standardization. Operating condition features reflecting the operating conditions of thermal power units are extracted from time-series datasets. Sub-features of each operating condition feature are then determined, and clustering algorithms are used to classify historical operating data. The standard feature patterns of historical operating data and normal operating conditions are analyzed to establish a typical operating condition pattern library. The benchmark values ​​corresponding to the sub-features of each operating condition feature are determined. For temperature operating condition features, the sub-features include main steam temperature, reheat steam temperature, condenser temperature, and bearing temperature. For pressure operating condition features, the sub-features include main steam pressure, condenser pressure, and fuel pressure. For flow operating condition features, the sub-features include fuel flow rate, feedwater flow rate, and air flow rate. For power operating condition features, the sub-features include turbine output power, generator output power, and reactive power. For speed operating condition features, the sub-features include turbine speed and generator speed. For load operating condition features, the sub-features include unit active load, load change rate, and load fluctuation amplitude. By using a similarity matching algorithm, the real-time operating condition features are compared with the standard feature patterns in the typical operating condition pattern library to calculate the operating condition similarity and quantify the degree of deviation between the current operating condition and the typical operating condition pattern. By combining historical operating data and the operating requirements of thermal power units, a multi-level matching threshold for operating condition similarity is set, namely the normal matching threshold and the abnormal matching threshold. Then, the current operating condition is analyzed to distinguish between normal and abnormal operating conditions, thereby determining whether the current operating condition of the system is abnormal.

6. A deep peak-shaving control system for thermal power units according to claim 5, characterized in that: The calculation process for the similarity of the working conditions is as follows: Extract operating condition features reflecting the operating conditions of thermal power units from time-series datasets, as well as sub-features of each operating condition feature; For each sub-feature of the working condition, calculate the absolute difference between its actual value and the benchmark value, and then calculate the ratio of the absolute difference to the benchmark value to determine the relative deviation of each sub-feature. For each sub-feature of the working condition, calculate the integral of the rate of change of its actual value over the time interval, and combine it with the exponential function to calculate the penalty function for deviation of the integral of the rate of change. For each sub-feature of the working condition feature, the contribution of the relative deviation degree and the integral deviation penalty function of the rate of change to the working condition similarity is analyzed to obtain the similarity contribution value of each sub-feature. The similarity contribution values ​​of the sub-features of all working condition features are summed and averaged to obtain the working condition similarity, which is the overall working condition similarity, reflecting the degree of deviation between the current working condition and the typical working condition pattern.

7. A deep peak-shaving control system for thermal power units according to claim 1, characterized in that: The control execution unit specifically includes: The control execution unit receives the optimal control parameters and scheduling scheme output by the bat algorithm optimization unit, parses them into control instructions that can be executed by each subsystem, decomposes the global optimization objective into corresponding control parameters, dynamically corrects them in combination with the current operating conditions, and generates an instruction set containing timing constraints and priority labels. Distributed control distributes control commands to the controllers of each subsystem in real time, triggering independent control processes. Each subsystem performs autonomous adjustment based on closed-loop control using local sensor data, and simultaneously uploads its execution status to the control execution unit. The control execution unit continuously monitors the operating status of each subsystem of the thermal power unit, collects real-time operating data, and compares it with the optimized control parameters and scheduling scheme. If deviations or abnormalities are found, the control commands are adjusted and the operating parameters are corrected.

8. A deep peak-shaving control system for thermal power units according to claim 1, characterized in that: The security monitoring and early warning module specifically includes: The safety monitoring and early warning module continuously monitors various key parameters during the deep peak shaving process of thermal power units, and comprehensively evaluates the operating effect of thermal power units to analyze whether various key parameters are within the normal operating range. By comparing the current key parameters with preset safety thresholds, it is determined whether the current operating status meets the safety requirements. Once any key parameter is found to exceed the preset safety threshold, the alarm mechanism is immediately triggered and an alarm message is issued to notify the operators and maintenance personnel to perform corresponding maintenance measures. At the same time, relevant information of the alarm event is recorded. Continuously monitor the status of thermal power units, track key parameters that trigger alarms, and report the implementation status of maintenance measures to the monitoring system until the key parameters return to normal range.

Images