Combination strategy optimization method and system for multiple coal mills

Abstract

The invention relates to the technical field of optimization control of a fire coal pulverizing system of a thermal power plant, and discloses a combination strategy optimization method and system for multiple coal mills, and the method comprises the following steps: S1, building a multi-dimensional dynamic sensing system of the operation states of the coal mills, coal type adaptability parameters, barrel vibration spectrum characteristics and outlet pulverized coal fineness distribution of each coal mill and instantaneous load fluctuation data of a driving motor are obtained; and S2, constructing a comprehensive performance portrait of the coal mill based on the historical operation efficiency and the equipment health degree, wherein the performance portrait at least comprises an equipment efficiency attenuation trend, a key component wear early warning level and a historical average fault-free operation duration. By establishing a multi-dimensional dynamic sensing system and a comprehensive performance portrait, refined, digital and prospective management of the running state of the coal mill is realized, so that formulation of a combined strategy is changed from experience-based driving to data-based driving, and scientificity and accuracy of decision making are remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of optimization control technology of coal pulverizing system in thermal power plant, in particular to a multi-mill combination strategy optimization method and system. BACKGROUND

[0002] In large coal-fired thermal power generating units, the coal pulverizing system is the key link connecting coal supply and boiler combustion, and its operation efficiency directly affects the economy, reliability and environmental protection of the unit. Currently, power plants usually configure multiple coal mills to run in parallel. The traditional mill combination and load distribution strategy mainly relies on the experience of operating personnel or uses simple fixed rules such as first start and first stop and average load.

[0003] This traditional method has obvious drawbacks. First, it does not fully consider the performance differences of each mill caused by wear and aging, which can easily lead to some mills running in non-economic intervals for a long time, resulting in high overall power consumption. Second, it cannot finely match the real-time changes of the coal quality entering the furnace, affecting the fineness of the pulverized coal and the stability of the combustion. Third, during the switching process of the mill start and stop, the sudden change of load can easily cause fluctuations in the main steam pressure and temperature of the boiler, threatening the stable operation of the unit. SUMMARY

[0004] The purpose of the present application is to provide a multi-mill combination strategy optimization method and system to solve the problems raised in the background.

[0005] To achieve the above purpose, the present application provides the following technical solution: a multi-mill combination strategy optimization method, comprising the following steps: Step S1: Establish a multi-dimensional dynamic perception system of mill operation state to obtain coal type adaptability parameters, cylinder vibration frequency spectrum characteristics, outlet coal fineness distribution and instantaneous load fluctuation data of the driving motor of each mill; Step S2: Construct a mill comprehensive performance portrait based on historical operation efficiency and equipment health, which at least includes equipment efficiency attenuation trend, key component wear warning level and historical average trouble-free operation time; Step S3: According to the boiler load instruction and online coal quality data, generate the core task instruction of mill combination, which at least includes total pulverizing capacity and target coal fineness specification; Step S4: Based on the multi-dimensional dynamic perception system and the comprehensive performance portrait, execute the coordinated matching and dynamic optimization instruction of mill combination to generate an optimized combination strategy including the main operating unit, standby unit and load distribution ratio; Step S5: According to the optimized combination strategy, output the mill start and stop instruction and load adjustment instruction to the field execution mechanism.

[0006] As a preferred technical solution of the present application, in the step S1, the coal type adaptability parameters are obtained by online coal quality analyzer and historical operation records of the coal mill, the cylinder vibration frequency spectrum characteristics are collected by multi-axis vibration sensors arranged at key positions of the coal mill, the outlet coal fineness distribution is obtained by directly measuring with online laser particle size analyzer installed on the coal pipeline, or indirectly inferred by a soft measurement model based on the load of the coal mill, the primary air volume and the grindability index of the coal, and the instantaneous load fluctuation data of the driving motor are obtained by integrating the change trend of the stator temperature rise rate, the bearing seat vibration high frequency component and the specific harmonic component in the current spectrum.

[0007] As a preferred technical solution of the present application, the specific process of constructing the comprehensive performance image in the step S2 includes: S21, integrating the equipment maintenance records from the power plant management information system, the offline performance test reports and the real-time operation data obtained by the multi-dimensional dynamic sensing system; S22, quantitatively evaluating the wear warning level of the key components of the coal mill based on the component replacement history and the routine inspection results in the equipment maintenance records; S23, fitting to generate the equipment efficiency attenuation trend curve of the coal mill based on the historical output and energy consumption data in the offline performance test reports and the real-time operation data; S24, statistically updating the historical average trouble-free operation time length of the coal mill based on the fault records in the equipment maintenance records and the continuous operation time in the real-time operation data; S25, fusing the wear warning level, the equipment efficiency attenuation trend curve and the historical average trouble-free operation time length to give each coal mill a dynamically updated performance index.

[0008] As a preferred technical solution of the present application, between the step S3 and the step S4, there is also a step of constructing the feasibility operation domain of the coal mill combination, which specifically includes the following steps: S3A1, based on the total pulverizing capacity and the target coal fineness specification in the core task instruction, screening one or more coal mills with the highest coincidence degree of the coal type adaptability parameters associated with the superior coal characteristics and the current online coal quality data from all coal mills to form an initial candidate unit set; S3A2, based on the comprehensive performance image, removing the coal mills with the wear warning level of the key components exceeding the safety limit value or the slope of the equipment efficiency attenuation trend curve greater than the preset attenuation rate from the initial candidate unit set to form a safety candidate unit set; S3A3. Based on the real-time operating status data of each coal mill in the set of safe candidate units, determine the upper and lower limits of output of each coal mill under the current operating conditions, and construct a feasible operating domain for coal mill combination that meets the total pulverization requirements based on the combination of the upper and lower limits of output of all safe coal mills.

[0009] As a preferred embodiment of the present invention, the collaborative matching and dynamic optimization process further includes: establishing a load transfer buffer mechanism between coal mills, wherein the specific steps of the load transfer buffer mechanism include: S41. Upon receiving the instruction to switch operating combinations, the strategy generation and optimization module locks the load increase operation of the coal mill to be shut down and maintains the current load of the target coal mill. S42. The instruction output and execution module sends an instruction to the actuator of the target coal mill to increase the loading force slowly at a rate less than the first preset rate, while simultaneously monitoring the outlet coal powder temperature and primary air volume of the target coal mill. S43. When the outlet coal powder temperature of the target coal mill tends to stabilize and the primary air volume reaches the preset range of the corresponding load, the instruction output and execution module sends an instruction to the actuator of the coal mill to be withdrawn, so that the loading force is slowly reduced at a rate less than the second preset rate. S44. During the process of reducing the loading force, continuously compare the sum of the instantaneous output of the target coal mill and the coal mill to be withdrawn, and verify the sum with the total pulverization requirement in the core task instruction in real time.

[0010] S45. When the load of the coal mill to be shut down drops to the preset low load safety threshold, the instruction output and execution module issues the final instruction to stop the operation of the coal mill.

[0011] As a preferred embodiment of the present invention, the method further includes: Step S6: During the execution of the optimized combination strategy, continuously monitor the boiler combustion stability parameters and environmental indicators; Step S7: When combustion stability parameters or environmental indicators are detected to deviate from the preset benchmark, the re-optimization process of the combined strategy is triggered to re-evaluate and adjust the coal mill combination in operation.

[0012] As a preferred technical solution of the present invention, the re-optimization process of the trigger combination strategy includes: activating different levels of response mechanisms according to the degree of deviation; when there is a slight deviation, compensation is made by fine-tuning the load distribution ratio between operating units; when there is a significant deviation, a standby coal mill is activated to replace the unit in the current combination that has mismatched performance or poor condition.

[0013] A multi-coal mill combination strategy optimization system, including: A multi-dimensional state perception module is used to execute step S1, and it includes a coal quality analysis unit, a vibration monitoring unit, a coal powder fineness detection unit, and a motor load sensing unit. The performance profile building module is used to perform step S2. It is connected to the power plant management information system to obtain maintenance records and historical data. The strategy generation and optimization module is used to execute step S4, and its core is a strategy engine with built-in collaborative matching rules and dynamic optimization logic. The instruction output and execution module is used to execute step S5, converting the strategy into executable control signals; The operation feedback and re-optimization module is used to execute steps S6 and S7, receive feedback signals from the boiler side in real time, and decide whether to initiate strategy adjustment.

[0014] As a preferred embodiment of the present invention, the system further includes a strategy simulation and verification module. Before the instruction output and execution module takes action, the module simulates the generated optimized combination strategy based on the current equipment status and load demand, predicts its impact on the boiler operating status, and corrects the strategy based on the prediction results.

[0015] As a preferred technical solution of the present invention, the multi-dimensional state perception module integrates a data credibility assessment sub-module. This sub-module performs consistency verification and noise filtering on the collected real-time data, and provides data with credibility higher than a set threshold to the performance profile construction module and the strategy generation and optimization module.

[0016] Compared with the prior art, the beneficial effects of the present invention are: 1. By establishing a multi-dimensional dynamic perception system and comprehensive performance profile, refined, digital and forward-looking management of the coal mill's operating status has been achieved, enabling the formulation of combined strategies to shift from relying on experience to being data-driven, significantly improving the scientific nature and accuracy of decision-making.

[0017] 2. By constructing a feasible operating domain and performing collaborative matching and dynamic optimization within it, the generated optimized combination strategy is ensured to meet current production needs while fully guaranteeing the safety and economy of equipment operation, effectively extending the life of key equipment.

[0018] 3. The innovative load transfer buffer mechanism achieves a smooth load transition during the switching process of coal mill operation combinations through start-up followed by shutdown, gradient adjustment, and real-time verification. This minimizes the impact on boiler combustion stability and improves the overall operating quality of the unit.

[0019] 4. By introducing an operational feedback and re-optimization mechanism, a closed-loop control system is formed, from strategy generation and execution to feedback and correction. This enables the system to have adaptive adjustment capabilities, effectively cope with disturbances such as coal quality fluctuations and load changes, and ensure that the system is in the optimal operating state for a long time.

[0020] 5. The entire method and system, by optimizing the operation combination and load distribution of coal mills, effectively reduces the plant power consumption rate and improves the coal utilization rate while ensuring boiler demand. At the same time, it reduces pollutant emissions through stable combustion, resulting in significant economic and environmental benefits. Attached Figure Description

[0021] Fig. 1 This is a schematic diagram of the overall process of the multi-coal mill combination strategy optimization method of the present invention; Fig. 2 This is a flowchart illustrating the process of constructing a comprehensive performance profile of a coal mill in this invention. Fig. 3 This is a flowchart illustrating the process of constructing a feasible operating domain for a coal mill combination in this invention. Detailed Implementation

[0022] 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, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] Example 1 Please see Figs. 1 to 3 This invention provides a method for optimizing the combination strategy of multiple coal mills, including the following steps: Step S1: Establish a multi-dimensional dynamic sensing system for the operating status of coal mills, and obtain coal type adaptability parameters, cylinder vibration spectrum characteristics, outlet coal powder fineness distribution, and instantaneous load fluctuation data of each coal mill. Step S2: Construct a comprehensive performance profile of the coal mill based on historical operating efficiency and equipment health. The performance profile should include at least the equipment efficiency decline trend, the wear warning level of key components, and the historical average fault-free operating time. Step S3: Based on the boiler load command and online coal quality data, generate the core task command for the coal mill assembly. This command shall include at least the total pulverizing capacity and the target pulverized coal specifications. Step S4: Based on the multi-dimensional dynamic perception system and comprehensive performance profile, execute the collaborative matching and dynamic optimization instructions for the coal mill combination to generate an optimized combination strategy that includes the main operating unit, the standby unit and the load allocation ratio; Step S5: Based on the optimized combination strategy, output the start / stop command and load adjustment command of the coal mill to the field actuator.

[0024] Furthermore, in step S1, the coal type adaptability parameters are obtained through correlation analysis between the online coal quality analyzer and the historical operation log of the coal mill; the cylinder vibration spectrum characteristics are collected by multi-axis vibration sensors arranged in key parts of the coal mill; the fineness distribution of the outlet coal powder is obtained by direct measurement by the online laser particle size analyzer installed on the coal powder pipeline, or indirectly inferred by a soft measurement model based on the coal mill loading force, primary air volume and coal grindability index; and the instantaneous load fluctuation data of the drive motor is obtained by integrating the change trends of the motor stator temperature rise rate, the high-frequency component of the bearing housing vibration and the specific harmonic component in the current spectrum.

[0025] Furthermore, the specific process of constructing the comprehensive performance profile in step S2 includes: S21. Integrate equipment maintenance records, offline performance test reports, and real-time operation data obtained from the power plant management information system and the multi-dimensional dynamic perception system; S22. Based on the component replacement history and routine inspection results in the equipment maintenance records, quantitatively assess the wear warning level of key components of the coal mill; S23. Based on the historical output and energy consumption data in the offline performance test report and real-time operation data, a curve of equipment efficiency decay trend of the coal mill is fitted and generated. S24. Based on the fault records in the equipment maintenance records and the continuous running time in the real-time operation data, calculate and update the historical average fault-free running time of the coal mill. S25. The wear warning level, equipment efficiency decline trend curve and historical average fault-free running time are integrated to give each coal mill a dynamically updated performance index.

[0026] Furthermore, between steps S3 and S4, a feasible operating domain for the coal mill assembly is constructed, specifically including the following steps: S3A1. Based on the total pulverizing capacity and target coal powder specifications in the core task instructions, select one or more coal mills from all coal mills that have the highest overlap between the advantageous coal type characteristics associated with the coal type adaptability parameters and the current online coal quality data, and form an initial candidate set of mill groups. S3A2. Based on the comprehensive performance profile, coal mills with key component wear warning levels exceeding safety limits or equipment efficiency degradation trend curve slopes greater than preset degradation rates are removed from the initial candidate unit set to form a safe candidate unit set. S3A3. Based on the real-time operating status data of each coal mill in the safety candidate unit set, determine the upper and lower limits of the output of each coal mill under the current operating conditions, and construct a feasible operating domain for coal mill combination that meets the total pulverization requirements based on the combination of the upper and lower limits of the output of all safe coal mills.

[0027] Furthermore, the collaborative matching and dynamic optimization process also includes: establishing a load transfer buffer mechanism between coal mills, the specific steps of which include: S41. Upon receiving the instruction to switch operating combinations, the strategy generation and optimization module locks the load increase operation of the coal mill to be shut down and maintains the current load of the target coal mill. S42. The instruction output and execution module sends instructions to the actuator of the target coal mill to increase the loading force slowly at a rate less than the first preset rate, while simultaneously monitoring the outlet coal powder temperature and primary air volume of the target coal mill. S43. When the outlet coal powder temperature of the target coal mill tends to stabilize and the primary air volume reaches the preset range of the corresponding load, the instruction output and execution module sends an instruction to the actuator of the coal mill to be withdrawn, so that the loading force is slowly reduced at a rate less than the second preset rate. S44. During the process of reducing the loading force, continuously compare the sum of the instantaneous output of the target coal mill and the coal mill to be withdrawn, and verify the sum with the total pulverization requirement in the core task instruction in real time.

[0028] S45. When the load of the coal mill to be shut down drops to the preset low load safety threshold, the instruction output and execution module issues the final instruction to stop the operation of the coal mill.

[0029] Furthermore, the methods also include: Step S6: During the implementation of the optimized combination strategy, continuously monitor the boiler combustion stability parameters and environmental indicators; Step S7: When combustion stability parameters or environmental indicators are detected to deviate from the preset benchmark, the re-optimization process of the combined strategy is triggered to re-evaluate and adjust the coal mill combination in operation.

[0030] Furthermore, the re-optimization process for triggering the combination strategy includes: initiating different levels of response mechanisms based on the degree of deviation; when there is a slight deviation, compensation is made by fine-tuning the load distribution ratio between operating units; when there is a significant deviation, a standby coal mill is started to replace the units in the current combination that are mismatched in performance or in poor condition.

[0031] A multi-coal mill combination strategy optimization system, including: The multi-dimensional state perception module is used to execute step S1, and includes a coal quality analysis unit, a vibration monitoring unit, a coal powder fineness detection unit, and a motor load sensing unit. The performance profile building module is used to execute step S2. It connects to the power plant management information system to obtain maintenance records and historical data. The strategy generation and optimization module is used to execute step S4. Its core is a strategy engine with built-in collaborative matching rules and dynamic optimization logic. The instruction output and execution module is used to execute step S5, converting the strategy into executable control signals; The operation feedback and re-optimization module is used to execute steps S6 and S7, receive feedback signals from the boiler side in real time, and decide whether to initiate strategy adjustment.

[0032] Furthermore, the system also includes a strategy simulation and verification module. Before the instruction output and execution module action, this module simulates the generated optimized combination strategy based on the current equipment status and load demand, predicts its impact on the boiler operating status, and corrects the strategy based on the prediction results.

[0033] Furthermore, the multi-dimensional state perception module integrates a data credibility assessment sub-module. This sub-module performs consistency verification and noise filtering on the collected real-time data, and provides data with credibility higher than a set threshold to the performance profile construction module and the strategy generation and optimization module.

[0034] Example 2 Based on Example 1, this example provides a specific application scenario.

[0035] A 660MW coal-fired power plant has five identical coal mills (A, B, C, D, and E) in its pulverizing system. The system and method of this invention are applied for optimized control.

[0036] Step S1: Data is acquired in real time using an online coal quality analyzer, vibration sensor, laser particle size analyzer, etc. For example, if the grindability index (HGI) of the coal currently fed into the furnace is 58, it is classified as a relatively difficult-to-grind coal.

[0037] Step S2: The performance profile building module retrieves historical data, showing that the roller sleeve wear warning level of coal mill C is high and the performance index is low. Coal mill B has the longest historical average fault-free operation time and the best performance index. Coal mill A has a good record of adaptability to low HGI coal.

[0038] Execution step S3: The boiler load command is 500MW, and the core task command is generated: the total pulverizing capacity requirement is 110t / h, and the target pulverized coal fineness is R90=18%.

[0039] Execution step S3A: Construct a feasible operating domain.

[0040] S3A1: Based on coal type adaptability, three coal mills, A, B, and D, were selected as initial candidates.

[0041] S3A2: Based on the performance profile, C machines with poor health status are removed, and E machines are temporarily avoided due to their obvious recent efficiency decline trend. The safe candidate machine set is {A, B, D}.

[0042] S3A3: The upper limits of the output of the three coal mills A, B, and D under the current operating conditions are determined to be 45t / h, 48t / h, and 43t / h, respectively, and the lower limits of the output are all 15t / h. The feasible output range of the {A, B, D} combination is calculated to be [45t / h, 136t / h], which meets the requirement of a total pulverizing capacity of 110t / h.

[0043] Step S4: The strategy generation and optimization module generates an optimized combination strategy based on the collaborative matching rules: the main operating units are A and B, the load allocation is 50t / h for unit A and 60t / h for unit B, and the standby unit is unit D.

[0044] Execution step S5: The system outputs instructions to start coal mills A and B and distribute the load according to the strategy.

[0045] After running for 2 hours, the standby unit D needs to be started due to the load increasing to 600MW.

[0046] Implement load transfer buffering mechanism: S41: Lock the load on machine B to increase, and maintain the current state of machine D.

[0047] S42: Slowly increase the loading force of the D unit while simultaneously monitoring its outlet temperature and primary air volume.

[0048] S43: Once the outlet temperature of unit D stabilizes at 75℃, the primary air volume reaches 80km / h. 3 After / h, the loading force of machine B is slowly reduced.

[0049] S44: Real-time verification shows that the total output of A+B+D is stable at around 130t / h.

[0050] S45: After the load of machine B drops to the safety threshold of 35t / h, stop its decrease, and the new combination of machines A, B, and D will operate stably.

[0051] Throughout the entire switching process, the maximum fluctuation of the boiler main steam pressure was less than 0.5 MPa, which is far better than the fluctuation of more than 1.0 MPa under the traditional switching method.

[0052] Comparison Example In the same power plant, without employing the optimization method of this invention, relying solely on the experience of operators to combine coal mills and allocate loads, under the same load variation conditions, if operators choose to start mill D and manually adjust the loads of mills A, B, and D, the following situation occurs due to the lack of system state awareness and coordinated matching: 1. The A unit, which is best suited to the current coal type, was not prioritized for startup. Instead, the load was distributed evenly, resulting in an increase in the overall pulverizing unit consumption of approximately 0.8 kWh / t.

[0053] 2. During the startup of Unit D and load adjustment, the operation was not synchronized, which caused the total pulverizing capacity to fluctuate by more than ±8t / h in a short period of time, resulting in a fluctuation of 1.2MPa in the main steam pressure of the boiler, which impacted the stable operation of the unit.

[0054] 3. Insufficient attention was paid to the health status of coal mill C. Frequent start-ups and shutdowns were carried out despite its already high vibration levels. A week later, unplanned shutdown for maintenance was caused by bearing damage.

[0055] Experimental data and analysis description To quantify the effectiveness of this invention, a one-month comparative test was conducted between the experimental group (implementing this invention) and the traditional manual operation (control group). Key data are shown in the table below:

[0056] Analysis and Explanation: 1. Improved economic efficiency: The significant reduction in unit consumption of the pulverizing system is mainly due to the fact that the present invention always prioritizes the combination of coal mills operating in the high-efficiency range and achieves precise load distribution, thereby reducing energy loss.

[0057] 2. Enhanced stability: The significant reduction in main steam pressure fluctuations directly demonstrates the effectiveness of the load transfer buffer mechanism. Smooth load switching ensures the stability of boiler operation and reduces equipment fatigue wear.

[0058] 3. Reliability assurance: The experimental group achieved zero unplanned downtime of the coal mill. Thanks to the accurate assessment and early warning of the equipment health status by the comprehensive performance profile, the maintenance strategy has shifted from post-maintenance to predictive maintenance, and high-risk equipment has been proactively avoided.

[0059] 4. Environmental protection and energy efficiency improvement: The improvement in boiler combustion efficiency and the reduction in NOx emission concentration are due to the optimized combination strategy that ensures more stable pulverized coal fineness and more reasonable coal distribution, thereby improving the boiler combustion conditions.

[0060] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for optimizing the combination strategy of multiple coal mills, characterized in that, Includes the following steps: Step S1: Establish a multi-dimensional dynamic sensing system for the operating status of coal mills, and obtain coal type adaptability parameters, cylinder vibration spectrum characteristics, outlet coal powder fineness distribution, and instantaneous load fluctuation data of each coal mill. Step S2: Construct a comprehensive performance profile of the coal mill based on historical operating efficiency and equipment health. The performance profile shall include at least the equipment efficiency decline trend, the wear warning level of key components, and the historical average fault-free operating time. Step S3: Based on the boiler load command and online coal quality data, generate the core task command for the coal mill assembly. This command shall include at least the total pulverizing capacity and the target pulverized coal specifications. Step S4: Based on the multi-dimensional dynamic perception system and the comprehensive performance profile, execute the collaborative matching and dynamic optimization instructions for the coal mill combination to generate an optimized combination strategy that includes the main operating unit, the standby unit and the load allocation ratio; Step S5: Based on the optimized combination strategy, output the start / stop command and load adjustment command of the coal mill to the field actuator.

2. The method for optimizing the combination strategy of multiple coal mills according to claim 1, characterized in that, In step S1, the coal type adaptability parameters are obtained through correlation analysis between the online coal quality analyzer and the historical operation log of the coal mill. The cylinder vibration spectrum characteristics are collected by multi-axis vibration sensors arranged in key parts of the coal mill. The fineness distribution of the outlet coal powder is obtained by direct measurement by an online laser particle size analyzer installed on the coal powder pipeline, or indirectly inferred by a soft measurement model based on the coal mill loading force, primary air volume and coal grindability index. The instantaneous load fluctuation data of the drive motor is obtained by integrating the change trend of the motor stator temperature rise rate, the high-frequency component of the bearing housing vibration and the specific harmonic component in the current spectrum.

3. The method for optimizing the combination strategy of multiple coal mills according to claim 1, characterized in that, The specific process of constructing the comprehensive performance profile in step S2 includes: S21. Integrate equipment maintenance records, offline performance test reports, and real-time operation data obtained from the power plant management information system and the multi-dimensional dynamic perception system; S22. Based on the component replacement history and routine inspection results in the equipment maintenance record, quantitatively assess the wear warning level of the key components of the coal mill; S23. Based on the offline performance test report and the historical output and energy consumption data in the real-time operation data, a curve showing the decline trend of the equipment efficiency of the coal mill is fitted and generated. S24. Based on the fault records in the equipment maintenance records and the continuous running time in the real-time running data, calculate and update the historical average fault-free running time of the coal mill. S25. The wear warning level, the equipment efficiency decay trend curve and the historical average fault-free running time are integrated to assign a dynamically updated performance index to each coal mill.

4. The method for optimizing the combination strategy of multiple coal mills according to claim 1, characterized in that, Between steps S3 and S4, a feasible operating domain for the coal mill assembly is constructed, which specifically includes the following steps: S3A1. Based on the total pulverizing capacity and target coal powder specifications in the core task instructions, select one or more coal mills from all coal mills that have the highest overlap between the advantageous coal type characteristics associated with the coal type adaptability parameters and the current online coal quality data, and form an initial candidate set of mill groups. S3A2. Based on the comprehensive performance profile, coal mills whose key component wear warning levels exceed safety limits or whose equipment efficiency decay trend curve slopes are greater than preset decay rates are removed from the initial candidate unit set to form a safe candidate unit set. S3A3. Based on the real-time operating status data of each coal mill in the set of safe candidate units, determine the upper and lower limits of output of each coal mill under the current operating conditions, and construct a feasible operating domain for coal mill combination that meets the total pulverization requirements based on the combination of the upper and lower limits of output of all safe coal mills.

5. The method for optimizing the combination strategy of multiple coal mills according to claim 1, characterized in that, The collaborative matching and dynamic optimization process also includes: establishing a load transfer buffer mechanism between coal mills, the specific steps of which include: S41. Upon receiving the instruction to switch operating combinations, the strategy generation and optimization module locks the load increase operation of the coal mill to be shut down and maintains the current load of the target coal mill. S42. The instruction output and execution module sends an instruction to the actuator of the target coal mill to increase the loading force slowly at a rate less than the first preset rate, while simultaneously monitoring the outlet coal powder temperature and primary air volume of the target coal mill. S43. When the outlet coal powder temperature of the target coal mill tends to stabilize and the primary air volume reaches the preset range of the corresponding load, the instruction output and execution module sends an instruction to the actuator of the coal mill to be withdrawn, so that the loading force is slowly reduced at a rate less than the second preset rate. S44. During the process of reducing the loading force, continuously compare the sum of the instantaneous output of the target coal mill and the coal mill to be withdrawn, and verify the sum with the total pulverization requirement in the core task instruction in real time. S45. When the load of the coal mill to be shut down drops to the preset low load safety threshold, the instruction output and execution module issues the final instruction to stop the operation of the coal mill.

6. The method for optimizing the combination strategy of multiple coal mills according to claim 1, characterized in that, The method further includes: Step S6: During the execution of the optimized combination strategy, continuously monitor the boiler combustion stability parameters and environmental indicators; Step S7: When combustion stability parameters or environmental indicators are detected to deviate from the preset benchmark, the re-optimization process of the combined strategy is triggered to re-evaluate and adjust the coal mill combination in operation.

7. The method for optimizing the combination strategy of multiple coal mills according to claim 1, characterized in that, The re-optimization process of the trigger combination strategy includes: activating different levels of response mechanisms according to the degree of deviation; when there is a slight deviation, compensation is made by fine-tuning the load distribution ratio between operating units; when there is a significant deviation, a standby coal mill is activated to replace the unit in the current combination that is mismatched in performance or in poor condition.

8. A multi-coal mill combination strategy optimization system, characterized in that, include: A multi-dimensional state perception module is used to execute step S1, and it includes a coal quality analysis unit, a vibration monitoring unit, a coal powder fineness detection unit, and a motor load sensing unit. The performance profile building module is used to perform step S2. It is connected to the power plant management information system to obtain maintenance records and historical data. The strategy generation and optimization module is used to execute step S4, and its core is a strategy engine with built-in collaborative matching rules and dynamic optimization logic. The instruction output and execution module is used to execute step S5, converting the strategy into executable control signals; The operation feedback and re-optimization module is used to execute steps S6 and S7, receive feedback signals from the boiler side in real time, and decide whether to initiate strategy adjustment.

9. The multi-coal mill combination strategy optimization system according to claim 8, characterized in that, The system also includes a strategy simulation and verification module. Before the instruction output and execution module takes action, this module simulates the generated optimized combination strategy based on the current equipment status and load demand, predicts its impact on the boiler operating status, and corrects the strategy based on the prediction results.

10. The multi-coal mill combination strategy optimization system according to claim 8, characterized in that, The multi-dimensional state perception module integrates a data credibility assessment submodule, which performs consistency verification and noise filtering on the collected real-time data and provides data with credibility higher than a set threshold to the performance profile construction module and the strategy generation and optimization module.

Images