Operation regulation and control method and system for pulverizing unit matched with coal-fired boiler during thermal power peak regulation

Abstract

The invention provides an operation regulation and control method for a pulverizing unit matched with a coal-fired boiler during thermal power peak shaving, and belongs to the technical field of deep peak shaving boilers of coal-fired power plants. The operation regulation and control method comprises the following steps: determining a first typical particle size distribution interval when the coal-fired boiler is in a normal state and a second typical particle size distribution interval when the coal-fired boiler is in a peak regulation state, and establishing a mathematical intelligent model between the coal-fired particle size and the thermal power generation system performance; the number and working parameters of flour mills are configured; and when the thermal power generation system is in a normal state or a peak regulation state, according to the calculated fire coal granularity requirement, in combination with the real-time monitoring data and the optimization result of the mathematical intelligent model, determining and starting a corresponding number of flour mills, and dynamically adjusting the working parameters of the flour mills. The number of the flour mills is increased on the basis of one original flour mill, and the running states of the flour mills are finely regulated and controlled, so that the flour mills can efficiently run under different working conditions, and the requirements of a thermal power generation system are met.

Description

Technical Field

[0001] The present invention relates to the technical field of deep peak shaving boilers in coal-fired power plants, and particularly to an operation control method and system for a pulverizing unit that cooperates with a coal-fired boiler during thermal power peak shaving. Background Art

[0002] Generally, in the power system, the required power loads of each power plant are constantly changing. In order to maintain the balance of active power and keep the system frequency stable, the power generation department needs to correspondingly change the power generation of the generator to adapt to the change of the power consumption load. When a thermal power unit performs deep peak shaving, the total coal amount of the boiler gradually decreases, the furnace temperature gradually drops, and the combustion gradually deteriorates. When reaching a certain critical stable combustion load point, the boiler must take appropriate measures to stabilize combustion, such as adjusting the air volume and velocity of the forced draft fan, adjusting the orientation of the flame nozzle, and reducing the coal feeding amount of the coal feeder.

[0003] In the prior art, most attention is paid to coal-fired boilers. For example, Chinese invention application (title: "A Coal-fired Boiler System and a Thermal Power Generation System with Deep Peak Shaving Capability", publication number: CN118274335A, publication date: July 2, 2024) discloses a coal-fired boiler system and a thermal power generation system with deep peak shaving capability, which mainly involves the improvement of coal-fired boilers. Another example is Chinese invention (title: "A Thermal Power Peak Shaving System and Method Based on Closed-cycle Hydrogen-oxygen Combustion", patent number: CN118242625B, announcement date: September 6, 2024), which actually also involves the transformation of coal-fired boilers. However, relatively few studies on the operation state control of pulverizers配套 with coal-fired boilers during thermal power peak shaving have been publicly reported. Summary of the Invention

[0004] The present invention aims to provide an operation control method for a pulverizing unit that cooperates with a coal-fired boiler during thermal power peak shaving. Based on the original one pulverizer, the number of pulverizers is increased, and the refined control of the operation state of the pulverizers is carried out so that they can operate efficiently under different working conditions and meet the requirements of the thermal power generation system.

[0005] The technical solution adopted by the present invention is as follows:

[0006] An operation control method for a pulverizing unit that cooperates with a coal-fired boiler during thermal power peak shaving, comprising the following steps:

[0007] Step S1: Collect coal particle size information of coal-fired boilers in the thermal power generation system under normal and peak-shaving conditions respectively, and combine it with the corresponding coal-fired boiler operating status monitoring data to determine the first typical particle size distribution range when the coal-fired boiler is under normal conditions and the second typical particle size distribution range when it is under peak-shaving conditions; at the same time, combine the power generation monitoring data of the thermal power generation system to establish a mathematical intelligent model between coal particle size and the performance of the thermal power generation system.

[0008] Step S2: Based on the first typical particle size distribution range and the second typical particle size distribution range, and combined with the optimization results of the mathematical intelligent model, configure the number of grinding mills and set the working parameters of each grinding mill.

[0009] Step S3: When the thermal power generation system is in normal condition, based on the coal particle size requirement calculated by the controller of the thermal power generation system, combined with the real-time monitoring data of the coal-fired boiler and the optimization results of the mathematical intelligent model, determine and start the corresponding number of grinding mills, and dynamically adjust the working parameters of the grinding mills.

[0010] Step S4: When the thermal power generation system is in peak shaving mode, based on the coal particle size requirement calculated by the controller of the thermal power generation system, combined with the real-time monitoring data of the coal-fired boiler and the optimization results of the mathematical intelligent model, the corresponding number of grinding mills are re-determined and started, and the working parameters of the grinding mills are dynamically adjusted.

[0011] Furthermore, in steps S3 and S4, the working status of each grinding mill is monitored synchronously; if a grinding mill is in an abnormal state, a backup grinding mill is activated and the corresponding working parameters are configured.

[0012] Furthermore, the specific execution process of step S1 includes:

[0013] Step S11: In each operating cycle, coal samples are collected from the coal transportation of the thermal power generation system according to the preset collection frequency, and the particle size of the coal samples is tested to obtain the particle size distribution data of each coal sample; at the same time, the working status monitoring data of the coal-fired boiler and the power generation monitoring data of the thermal power generation system are recorded during the sampling.

[0014] Step S12: All collected particle size distribution data are summarized and organized according to normal state and peak shaving state to form two independent datasets, corresponding to normal state and peak shaving state respectively; statistical analysis is performed on each dataset, statistical characteristics are calculated, and combined with the corresponding coal-fired boiler operating status monitoring data, the first typical particle size distribution interval when the coal-fired boiler is in normal state and the second typical particle size distribution interval when it is in peak shaving state are determined respectively.

[0015] Step S13: Clean all collected particle size distribution data and corresponding power generation monitoring data, extract key features affecting power generation performance from the particle size distribution data, normalize the extracted key features and corresponding power generation monitoring data, and finally use machine learning to obtain a mathematical intelligent model between coal particle size and thermal power generation system performance.

[0016] Furthermore, the machine learning algorithms used in the mathematical intelligence model in step S13 include, but are not limited to, support vector machines, neural networks, decision trees, or random forests.

[0017] Furthermore, the specific execution process of step S2 is as follows:

[0018] Step S21: Based on the first typical particle size distribution range and the second typical particle size distribution range, and combined with the coal demand and particle size requirements of the thermal power generation system under different conditions, the number of grinding mills required under normal and peak-shaving conditions is calculated by using a mathematical intelligent model according to the coal demand and particle size requirements.

[0019] Step S22: Based on the number of grinding mills calculated by the mathematical intelligent model, formulate a combination scheme for the grinding mills and determine the configuration method of the grinding mills;

[0020] Step S23: Assign preliminary operating parameters to each grinding mill according to the grinding mill combination scheme;

[0021] Step S24: Based on the optimization results of the mathematical intelligent model, optimize and adjust the working parameters of each grinding mill.

[0022] Furthermore, the specific execution process of step S3 is as follows:

[0023] Step S31: When the thermal power generation system is in normal condition, the controller of the thermal power generation system calculates the required coal particle size range based on the current power generation load demand and the pre-established correspondence between power generation load and coal particle size demand.

[0024] Step S32: Compare the calculated coal particle size range with the first typical particle size distribution range to determine the number of grinding mills and operating parameters that match it.

[0025] Step S33: Send start commands to the corresponding number of grinding mills and set the determined operating parameters to each grinding mill so that the grinding mills can operate according to the set parameters and provide coal with the required particle size to the coal-fired boiler.

[0026] Furthermore, the comparison process in step S32 employs a minimum error matching algorithm to ensure the optimality of the matching results.

[0027] Furthermore, the specific execution process of step S4 is as follows:

[0028] Step S41: When the thermal power generation system is in peak shaving mode, the controller of the thermal power generation system calculates the current required coal particle size range based on the changes in power generation load during peak shaving and the pre-established correspondence between power generation load and coal particle size requirements.

[0029] Step S42: Compare the calculated coal particle size range with the second typical particle size distribution range to determine the number of grinding mills and operating parameters that match it.

[0030] Step S43: Send start command to the corresponding number of grinding mills and set the determined working parameters to each grinding mill so that the grinding mills can operate according to the set parameters and provide coal with the required particle size to the coal-fired boiler.

[0031] Furthermore, the comparison process in step S42 employs a minimum error matching algorithm to ensure the optimality of the matching results.

[0032] Based on the same inventive concept, this invention also provides an operation control system for a pulverizing unit that works in conjunction with a coal-fired boiler during peak shaving of thermal power plants, comprising the aforementioned operation control method for a pulverizing unit that works in conjunction with a coal-fired boiler during peak shaving of thermal power plants, including:

[0033] The acquisition and model building module is used to collect coal particle size information of coal-fired boilers in the thermal power generation system under normal and peak-shaving conditions, respectively, and combine it with the corresponding coal-fired boiler operating status monitoring data to determine the first typical particle size distribution range and the second typical particle size distribution range corresponding to the coal-fired boilers under normal and peak-shaving conditions, respectively; at the same time, combined with the power generation monitoring data of the thermal power generation system, a mathematical intelligent model between coal particle size and the performance of the thermal power generation system is established.

[0034] The configuration module is used to configure the number of grinding mills and set the working parameters of each grinding mill based on the first typical particle size distribution range and the second typical particle size distribution range, combined with the optimization results of the mathematical intelligent model.

[0035] The operation and control module is used to determine and start a corresponding number of grinding mills and dynamically adjust their operating parameters when the thermal power generation system is in normal operation, based on the coal particle size requirement calculated by the controller of the thermal power generation system, combined with the real-time monitoring data of the coal-fired boiler and the optimization results of the mathematical intelligent model; when the thermal power generation system is in peak-shaving operation, it re-determines and starts a corresponding number of grinding mills and dynamically adjusts their operating parameters based on the coal particle size requirement calculated by the controller of the thermal power generation system, combined with the real-time monitoring data of the coal-fired boiler and the optimization results of the mathematical intelligent model.

[0036] The beneficial effects of this invention are:

[0037] This invention provides a method and system for controlling the operation of a grinding mill unit in conjunction with a coal-fired boiler during peak shaving in thermal power plants. The design involves increasing the number of grinding mills and configuring different operating parameters based on the existing single grinding mill, followed by dynamic control. This method offers the following advantages:

[0038] (1) Precise control of the grinding mill's operating status: By collecting coal particle size information from coal-fired boilers under normal and peak-shaving conditions, and combining it with operating status monitoring data to determine typical particle size distribution ranges, the requirements for coal particle size under different operating conditions can be accurately understood. Furthermore, by combining power generation monitoring data to establish a mathematical intelligent model, the operating status of the grinding mill can be finely controlled, enabling it to operate efficiently under different operating conditions, meeting the needs of thermal power generation systems, and broadening the research and improvement direction for thermal power peak shaving.

[0039] (2) Improve the overall performance and efficiency of the system: Configure the number of grinding mills and set the working parameters according to the optimization results of the typical particle size distribution range and the mathematical intelligent model. This can ensure that the grinding mills operate with the optimal parameters under normal and peak conditions, thereby improving grinding efficiency, reducing energy waste, and thus improving the performance and power generation efficiency of the entire thermal power generation system and reducing operating costs.

[0040] (3) Enhance system adaptability and flexibility: This method can dynamically adjust the operating parameters of the grinding mill according to the different output states (normal and peak shaving) of the thermal power generation system, so that the system has stronger adaptability and flexibility, can better cope with the changes in grid load and peak shaving demand, improve the peak shaving capacity of thermal power units, and enhance their competitiveness in the electricity market. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a flowchart illustrating the operation and control method of the grinding mill unit that works in conjunction with a coal-fired boiler during peak shaving in this embodiment. Detailed Implementation

[0043] The embodiments of the invention will now be described in detail with reference to the accompanying drawings.

[0044] A method for controlling the operation of a pulverizing unit in conjunction with a coal-fired boiler during peak shaving in thermal power plants, the process of which is shown in the attached figure. Figure 1 As shown in the figure. This operation control method includes the following steps:

[0045] Step S1: Collect coal particle size information (such as particle size distribution range, particle size distribution curve, average particle size, D50 particle size, etc., which can be obtained by sieve analysis or laser particle size analysis) for coal-fired boilers in the thermal power generation system under normal (i.e., non-peak shaving) and peak shaving conditions. Combine this with the corresponding coal-fired boiler operating status monitoring data (such as combustion chamber temperature, flue gas temperature, flue gas composition (such as CO2, CO, O2 concentration), steam flow rate, pressure and temperature, feedwater flow rate and temperature, equipment running time, fault alarm signals, etc., which can be obtained by various sensors). Determine the first typical particle size distribution range for coal-fired boilers under normal conditions and the second typical particle size distribution range for coal-fired boilers under peak shaving conditions. At the same time, combine the power generation monitoring data of the thermal power generation system (power generation, power output, thermal efficiency, etc.) to establish a mathematical intelligent model between coal particle size and the performance of the thermal power generation system.

[0046] Step S2: Based on the first typical particle size distribution range and the second typical particle size distribution range, and combined with the optimization results of the mathematical intelligent model, configure the number of grinding mills and set the working parameters of each grinding mill (such as rotation speed, feed rate, air volume, grinding pressure, and sieving accuracy).

[0047] Step S3: When the thermal power generation system is in normal condition, based on the coal particle size requirement calculated by the controller of the thermal power generation system, combined with the real-time monitoring data of the coal-fired boiler and the optimization results of the mathematical intelligent model, determine and start the corresponding number of grinding mills, and dynamically adjust the working parameters of the grinding mills.

[0048] Step S4: When the thermal power generation system is in peak shaving mode, based on the coal particle size requirement calculated by the controller of the thermal power generation system, combined with the real-time monitoring data of the coal-fired boiler and the optimization results of the mathematical intelligent model, the corresponding number of grinding mills are re-determined and started, and the working parameters of the grinding mills are dynamically adjusted.

[0049] The beneficial effects of the above technical solutions are: (1) Precise control of the operating status of the grinding mill: By collecting coal particle size information of the coal-fired boiler under normal and peak-shaving conditions respectively, and combining the working status monitoring data to determine the typical particle size distribution range, it is possible to accurately understand the requirements of coal particle size under different working conditions. In addition, by combining the power generation monitoring data to establish a mathematical intelligent model, it is possible to achieve fine control of the operating status of the grinding mill, so that it can operate efficiently under different working conditions, meet the needs of the thermal power generation system, and also broaden the research and improvement direction of thermal power peak shaving. (2) Improve the overall performance and efficiency of the system: By configuring the number of grinding mills and setting the working parameters according to the optimization results of the typical particle size distribution range and the mathematical intelligent model, it is possible to ensure that the grinding mill operates with the optimal parameters under normal and peak-shaving conditions, thereby improving grinding efficiency, reducing energy waste, and thus improving the performance and power generation efficiency of the entire thermal power generation system and reducing operating costs. (3) Enhance system adaptability and flexibility: This method can dynamically adjust the operating parameters of the grinding mill according to the different output states (normal and peak shaving) of the thermal power generation system, so that the system has stronger adaptability and flexibility, can better cope with the changes in grid load and peak shaving demand, improve the peak shaving capacity of thermal power units, and enhance their competitiveness in the electricity market.

[0050] Furthermore, in steps S3 and S4, the operating status of each grinding mill (such as operating current, vibration frequency, temperature, pressure, etc., which can be obtained through various sensors) is monitored synchronously; if a grinding mill is abnormal, a backup grinding mill is activated and its corresponding operating parameters are configured to be the same as those of the abnormal grinding mill.

[0051] The beneficial effects of the above scheme are: (1) Ensuring stable system operation: In steps S3 and S4, the working status of each grinding mill is monitored synchronously, and when a grinding mill malfunctions, a backup grinding mill is activated in a timely manner and the corresponding working parameters are configured. This can effectively avoid the interruption of coal supply or the failure of particle size due to grinding mill failure, ensuring the stable operation of the thermal power generation system and reducing economic losses and safety hazards caused by equipment failure. (2) Improving equipment utilization and reliability: By monitoring the working status of the grinding mill in real time, potential problems of the equipment can be detected and dealt with in a timely manner, extending the service life of the equipment and improving the utilization and reliability of the equipment. At the same time, the configuration of the backup grinding mill also provides redundancy for the system, further enhancing the reliability of the system.

[0052] Furthermore, the specific execution process of step S1 includes:

[0053] Step S11: In each operating cycle, coal samples are collected from the coal transportation of the thermal power generation system according to a preset collection frequency (e.g., once per hour), and the coal samples are subjected to particle size testing to obtain particle size distribution data for each coal sample; at the same time, the working status monitoring data of the coal-fired boiler and the power generation monitoring data of the thermal power generation system are recorded during the sampling.

[0054] Step S12: All collected particle size distribution data are summarized and organized according to normal state and peak shaving state to form two independent datasets, corresponding to normal state and peak shaving state respectively; statistical analysis is performed on each dataset to calculate statistical characteristics (such as mean, standard deviation, variance, etc.), and combined with the corresponding coal-fired boiler operating status monitoring data, the first typical particle size distribution interval when the coal-fired boiler is in normal state and the second typical particle size distribution interval when it is in peak shaving state are determined respectively.

[0055] Step S13 involves cleaning all collected particle size distribution data and corresponding power generation monitoring data (e.g., removing outlier data, filling in missing data, eliminating duplicate data), extracting key features affecting power generation performance (e.g., particle size distribution range and D50 particle size) from the particle size distribution data (e.g., using feature selection algorithms such as principal component analysis and correlation analysis), normalizing the extracted key features and corresponding power generation monitoring data, and finally using machine learning to obtain a mathematical intelligent model between coal particle size and thermal power generation system performance.

[0056] The beneficial effects of the above scheme are: (1) Improve the accuracy of data collection and analysis: By collecting coal samples and conducting particle size tests at a preset frequency in each operating cycle, a large amount of accurate particle size distribution data can be obtained, providing a reliable data foundation for subsequent analysis and model establishment. At the same time, by summarizing and organizing the data according to normal and peak-shaving states and then conducting statistical analysis, the typical particle size distribution range can be determined more accurately, providing a more scientific basis for the control of the grinding mill. (2) Enhance the accuracy and reliability of the model: After cleaning the collected data, extracting key features and normalizing them, a mathematical intelligent model is established using machine learning, which can effectively remove noise and interference in the data, highlight the impact of key factors on power generation performance, thereby improving the accuracy and reliability of the model, making it better reflect the relationship between coal particle size and the performance of thermal power generation system, and providing stronger support for the optimization and control of the grinding mill.

[0057] Furthermore, the machine learning algorithms used in the mathematical intelligence model in step S13 include, but are not limited to, support vector machines, neural networks, decision trees, or random forests.

[0058] The beneficial effects of the above technical solution are: providing multiple modeling options and improving model adaptability; clarifying that mathematical intelligent models can employ various machine learning algorithms such as support vector machines, neural networks, decision trees, or random forests, providing flexibility for selecting appropriate algorithms based on data characteristics and modeling needs in practical applications. Different algorithms have their own advantages in handling different types of data and problems. By providing multiple options, it is possible to better adapt to different working conditions and data characteristics, further improving the performance and adaptability of the model, and providing more reliable model support for the precise control of the grinding mill.

[0059] Furthermore, the specific execution process of step S2 is as follows:

[0060] Step S21: Based on the first typical particle size distribution range and the second typical particle size distribution range, and combined with the coal demand and particle size requirements of the thermal power generation system under different conditions (normal state and peak shaving state), the number of grinding mills required under normal state and peak shaving state is calculated respectively by mathematical intelligent model according to the coal demand and particle size requirements.

[0061] Step S22: Based on the number of grinding mills calculated by the mathematical intelligent model, formulate a combination scheme for the grinding mills and determine the configuration method of the grinding mills;

[0062] Step S23: According to the grinding mill combination scheme (e.g., 3 units in normal state and 5 units in peak state), assign preliminary operating parameters to each grinding mill;

[0063] Step S24: Based on the optimization results of the mathematical intelligent model, optimize and adjust the working parameters of each grinding mill.

[0064] The beneficial effects of the above technical solutions are: (1) Optimizing the configuration and parameter settings of the grinding mill: Through the more detailed execution process of step S2, including calculating the number of grinding mills based on the typical particle size distribution range and coal demand, formulating combination schemes, allocating preliminary working parameters, and optimizing and adjusting working parameters, the grinding mills can be configured more scientifically and rationally, and the optimal working parameters can be set for them. This helps to give full play to the performance of the grinding mills, improve grinding efficiency and quality, and further enhance the operating efficiency and economy of the thermal power generation system. (2) Realizing the refined management of the grinding mills: From the calculation of the number of grinding mills to the formulation of combination schemes, and then to the allocation and optimization of working parameters, the whole process reflects the refined management of the grinding mills. This refined management method can fully consider the impact of various factors on the operation of the grinding mills, realize the efficient operation of the grinding mills and the rational utilization of resources, and provide a strong guarantee for the stable operation of the thermal power generation system.

[0065] Furthermore, the specific execution process of step S3 is as follows:

[0066] Step S31: When the thermal power generation system is in normal condition, the controller of the thermal power generation system calculates the required coal particle size range based on the current power generation load demand and the pre-established correspondence between power generation load and coal particle size demand.

[0067] Step S32: Compare the calculated coal particle size range with the first typical particle size distribution range to determine the number of grinding mills and operating parameters that match it.

[0068] Step S33: Send start commands to the corresponding number of grinding mills and set the determined operating parameters to each grinding mill so that the grinding mills can operate according to the set parameters and provide coal with the required particle size to the coal-fired boiler.

[0069] The beneficial effects of the above technical solution are: (1) To achieve precise start-up and parameter setting of the grinding mill: When the thermal power generation system is in normal output state, this step details how to determine the number of matching grinding mills and working parameters based on the coal particle size requirement calculated by the controller, combined with the first typical particle size distribution range and the optimization results of the mathematical model, and send start-up instructions and setting parameters to the corresponding grinding mills. This process can ensure that the grinding mill operates with the most suitable parameters under normal working conditions, providing coal that meets the particle size requirements for the coal-fired boiler, thereby improving combustion efficiency, reducing pollutant emissions, and ensuring the stable and efficient operation of the thermal power generation system. (2) To improve the automation and intelligence level of system operation: By calculating the coal particle size requirement by the controller and comparing it with the typical particle size distribution range, the operating parameters of the grinding mill are automatically determined, realizing the automated start-up and parameter setting of the grinding mill, reducing manual intervention, improving the operating efficiency and intelligence level of the system, and reducing the workload of operators and the risk of operational errors.

[0070] Furthermore, the comparison process in step S32 employs a minimum error matching algorithm to ensure the optimality of the matching results.

[0071] The beneficial effects of the above scheme are: (1) Improve the comparison accuracy and matching effect: The minimum error matching algorithm is used to compare the calculated coal particle size range with the first typical particle size distribution range, which can ensure the optimality of the matching result. The minimum error matching algorithm finds the closest matching item by minimizing the error. Compared with other simple comparison methods, it can more accurately determine the number of grinding mills and working parameters that best match the current needs, thereby improving the operation effect of the grinding mill and the system performance, and better meeting the operating requirements of the thermal power generation system under normal output conditions. (2) Improve the stability and reliability of system operation: Through accurate comparison and matching, it can be ensured that the grinding mill always operates in the best state, providing a stable and compliant coal supply to the coal-fired boiler, reducing problems such as unstable combustion caused by non-compliant particle size, thereby improving the stability and reliability of the entire thermal power generation system, and reducing equipment failure rate and maintenance costs.

[0072] Furthermore, the specific execution process of step S4 is as follows:

[0073] Step S41: When the thermal power generation system is in peak shaving mode, the controller of the thermal power generation system calculates the current required coal particle size range based on the changes in power generation load during peak shaving and the pre-established correspondence between power generation load and coal particle size requirements.

[0074] Step S42: Compare the calculated coal particle size range with the second typical particle size distribution range to determine the number of grinding mills and operating parameters that match it.

[0075] Step S43: Send start command to the corresponding number of grinding mills and set the determined working parameters to each grinding mill so that the grinding mills can operate according to the set parameters and provide coal with the required particle size to the coal-fired boiler.

[0076] The beneficial effects of the above technical solutions are: (1) Adapting to the grinding mill regulation requirements under peak shaving conditions: When the thermal power generation system is in peak shaving condition, this step details how to determine the number of matching grinding mills and operating parameters based on the coal particle size requirements calculated by the controller, combined with the second typical particle size distribution range and the optimization results of the mathematical model, and send start-up instructions and setting parameters to the corresponding grinding mills. This process can ensure that the grinding mill can also operate with appropriate parameters under peak shaving conditions, providing coal-fired boilers with coal that meets the particle size requirements, thereby improving the peak shaving capacity of thermal power units and better adapting to the needs of grid load changes. (2) Enhancing the flexibility and adaptability of the system under peak shaving conditions: Under peak shaving conditions, the power generation load changes more frequently. By using the minimum error matching algorithm for comparison and matching, the operating parameters of the grinding mill can be adjusted quickly and accurately, enabling the system to flexibly cope with load changes during peak shaving, improving the system's peak shaving flexibility and adaptability, and providing strong support for the safe and stable operation of the grid.

[0077] Furthermore, the comparison process in step S42 employs a minimum error matching algorithm to ensure the optimality of the matching results.

[0078] The beneficial effects of the above technical solutions are: (1) Further optimize the matching accuracy under peak shaving conditions: Similar to the aforementioned solutions, the minimum error matching algorithm is used to ensure the optimality of the comparison process under peak shaving conditions. It can more accurately determine the number of grinding mills and operating parameters that best match the coal particle size requirements during peak shaving, further improve the operation effect and system performance of the grinding mills under peak shaving conditions, and better meet the complex needs of the thermal power generation system during peak shaving. (2) Improve the stability and reliability of the system under complex conditions: Under peak shaving conditions, the operating conditions of the system are relatively complex. Through accurate comparison and matching, it can ensure that the grinding mill always operates in the best state, reduce problems such as combustion instability caused by non-compliance with particle size requirements, thereby improving the stability and reliability of the entire thermal power generation system under complex conditions, reducing equipment failure rate and maintenance costs, and ensuring the safe operation of the system.

[0079] Based on the same inventive concept, this invention also provides an operation control system for a pulverizing unit that works in conjunction with a coal-fired boiler during peak shaving of thermal power plants, comprising the aforementioned operation control method for a pulverizing unit that works in conjunction with a coal-fired boiler during peak shaving of thermal power plants, including:

[0080] The acquisition and model building module is used to collect coal particle size information of coal-fired boilers in the thermal power generation system under normal and peak-shaving conditions, respectively, and combine it with the corresponding coal-fired boiler operating status monitoring data to determine the first typical particle size distribution range and the second typical particle size distribution range corresponding to the coal-fired boilers under normal and peak-shaving conditions, respectively; at the same time, combined with the power generation monitoring data of the thermal power generation system, a mathematical intelligent model between coal particle size and the performance of the thermal power generation system is established.

[0081] The configuration module is used to configure the number of grinding mills and set the working parameters of each grinding mill based on the first typical particle size distribution range and the second typical particle size distribution range, combined with the optimization results of the mathematical intelligent model.

[0082] The operation and control module is used to determine and start a corresponding number of grinding mills and dynamically adjust their operating parameters when the thermal power generation system is in normal operation, based on the coal particle size requirement calculated by the controller of the thermal power generation system, combined with the real-time monitoring data of the coal-fired boiler and the optimization results of the mathematical intelligent model; when the thermal power generation system is in peak-shaving operation, it re-determines and starts a corresponding number of grinding mills and dynamically adjusts their operating parameters based on the coal particle size requirement calculated by the controller of the thermal power generation system, combined with the real-time monitoring data of the coal-fired boiler and the optimization results of the mathematical intelligent model.

[0083] The beneficial effects of the above technical solutions are: (1) Systematization and engineering application of the method: By constructing a dedicated operation and control system to implement the control method described above, the various steps and functions in the method are modularized and systematized, so that they can be better applied in actual engineering. The system includes an acquisition and model building module, a configuration module and an operation and control module, which can realize the full-process automated management from data acquisition and model building to mill configuration and operation control, improve the operability and practicality of the method, and facilitate its promotion and application in thermal power plants. (2) Improve the integration and coordination of the system: The system integrates the functions of coal particle size monitoring, mill configuration and operation control of the thermal power plant system into one, realizing the collaborative work between the functional modules. Through the overall coordination and optimization of the system, the advantages of each module can be fully utilized, the operating efficiency and performance of the entire system can be improved, and the efficient operation and refined management of the thermal power plant system under normal and peak conditions can be realized, bringing significant economic and social benefits to the enterprise.

[0084] The following is a more specific example to illustrate this.

[0085] A thermal power plant has a 600MW coal-fired generating unit equipped with a coal-fired boiler. To improve the unit's peak-shaving capacity and operating efficiency, it was decided to add one more grinding mill to the existing one, and to adopt optimized operation and control methods. The specific steps are as follows:

[0086] [1] Data collection and model building

[0087] 1.1 Data Collection:

[0088] Coal samples were collected during normal operation and peak-shaving operation, once per hour.

[0089] The particle size distribution data of the collected coal samples were obtained by using a laser particle size analyzer.

[0090] Simultaneously, the operating status monitoring data of the coal-fired boiler is recorded, including combustion chamber temperature, flue gas temperature, flue gas composition (CO2, CO, O2 concentration), steam flow rate, pressure and temperature, feedwater flow rate and temperature, etc.

[0091] Record power generation monitoring data of thermal power generation systems, including power load, power output, thermal efficiency, etc.

[0092] 1.2 Data Processing and Analysis:

[0093] The collected granularity distribution data were summarized and organized according to normal state and peak-shaving state, forming two independent datasets.

[0094] Perform statistical analysis on each dataset and calculate statistical characteristics, including mean particle size, median particle size, standard deviation, coefficient of variation, skewness, kurtosis, fine particle content (less than 0.1 mm), and coarse particle content (greater than 3 mm).

[0095] Data cleaning removes outliers and noise, and extracts key features (such as average particle size, fine particle content, and coarse particle content).

[0096] The extracted key features and power generation monitoring data are normalized for input into the machine learning model.

[0097] 1.3 Establishment of Mathematical Intelligent Model:

[0098] Support Vector Machine (SVM) was chosen as the machine learning algorithm, and normalized data was input into the model for training.

[0099] The model inputs include key characteristics of coal particle size and power generation monitoring data, and the outputs are the optimal operating parameters (such as rotational speed, feed rate, and air volume) and quantity configuration of the grinding mill.

[0100] The model is optimized and validated using methods such as cross-validation to ensure its accuracy and reliability.

[0101] [2] Grinding mill configuration and parameter settings

[0102] 2.1 Calculation of the number of grinding mills:

[0103] Based on the coal demand and particle size requirements under normal and peak-shaving conditions, and combined with the optimization results of the mathematical intelligent model, the required number of grinding mills is calculated respectively.

[0104] Under normal conditions, the model calculation results indicate that one grinding mill is needed; under peak shaving conditions, the model suggests increasing to two grinding mills.

[0105] 2.2 Grinding mill combination scheme formulation:

[0106] Based on the number of grinding mills calculated by the model, a combination scheme for the grinding mills is formulated. Under normal conditions, grinding mill No. 1 is used; under peak-shaving conditions, grinding mills No. 1 and No. 2 are started simultaneously.

[0107] 2.3 Parameter Allocation and Optimization:

[0108] Based on the grinding mill assembly plan, preliminary operating parameters, such as rotation speed, feed rate, and air volume, are assigned to each grinding mill.

[0109] Based on the optimization results of the mathematical intelligent model, the operating parameters of each grinding mill are optimized and adjusted. For example, under normal conditions, the rotational speed of grinding mill No. 1 is set to 1000 r / min, the feed rate is 50 t / h, and the air volume is 1000 m³ / h; under peak-shaving conditions, the rotational speed of grinding mill No. 1 is adjusted to 1200 r / min, the feed rate is 60 t / h, and the air volume is 1200 m³ / h; the rotational speed of grinding mill No. 2 is set to 1100 r / min, the feed rate is 40 t / h, and the air volume is 1100 m³ / h.

[0110] [3] Operation and control of the grinding mill under normal conditions

[0111] 3.1 Estimation of Coal Particle Size Requirements:

[0112] When the thermal power generation system is in normal output state, the controller calculates the required coal particle size range of 0.05 mm to 1.5 mm based on the current power generation load demand (e.g., 550MW) and the pre-established correspondence between power generation load and coal particle size demand.

[0113] 3.2 Determination of the number and parameters of the grinding mill:

[0114] The calculated coal particle size range was compared with the first typical particle size distribution range (0.05 mm to 1.5 mm). The minimum error matching algorithm was used to determine that the number of matching grinding mills was 1, with the following operating parameters: rotation speed 1000 r / min, feed rate 50 t / h, and air volume 1000 m³ / h.

[0115] 3.3 Grinding mill start-up and parameter settings:

[0116] A start command is sent to the No. 1 grinding mill, and the determined operating parameters are set on the grinding mill so that it can operate according to the set parameters and provide coal that meets the particle size requirements for the coal-fired boiler.

[0117] 3.4 Real-time monitoring and dynamic adjustment:

[0118] The working status of the No. 1 grinding mill is monitored synchronously, including parameters such as operating current, vibration frequency, temperature, and pressure.

[0119] Based on real-time monitoring data and the optimization results of mathematical models, the operating parameters of the grinding mill are dynamically adjusted to ensure that it always operates in the optimal state.

[0120] [4] Operation control of grinding mill under peak shaving conditions

[0121] 4.1 Calculation of Coal Particle Size Requirements:

[0122] When the thermal power generation system is in peak shaving mode, the controller calculates the current required coal particle size range of 0.05 mm to 2.0 mm based on the changes in power generation load during the peak shaving period (such as the power generation load fluctuating between 300MW and 600MW) and the pre-established correspondence between power generation load and coal particle size requirements.

[0123] 4.2 Determination of the number and parameters of the grinding mill:

[0124] The calculated coal particle size range was compared with the second typical particle size distribution range (0.05 mm to 2.0 mm). Using the minimum error matching algorithm, the number of matching grinding mills was determined to be 2, with the following operating parameters: No. 1 grinding mill speed 1200 r / min, feed rate 60 t / h, air volume 1200 m³ / h; No. 2 grinding mill speed 1100 r / min, feed rate 40 t / h, air volume 1100 m³ / h.

[0125] 4.3 Grinding mill start-up and parameter settings:

[0126] Start-up commands are sent to grinding mills No. 1 and No. 2, and the determined operating parameters are set on each grinding mill so that it can operate according to the set parameters and provide coal with the required particle size to the coal-fired boiler.

[0127] 4.4 Real-time monitoring and dynamic adjustment:

[0128] The operating status of grinding mills No. 1 and No. 2 is monitored synchronously, including parameters such as operating current, vibration frequency, temperature, and pressure.

[0129] Based on real-time monitoring data and the optimization results of mathematical models, the operating parameters of the grinding mill are dynamically adjusted to ensure that it always operates in the optimal state.

[0130] [5] Effectiveness Evaluation

[0131] Improved combustion efficiency: Under normal and peak-shaving conditions, by optimizing the operating parameters of the grinding mill, the coal particle size is ensured to meet the boiler combustion requirements, resulting in a significant improvement in combustion efficiency and a reduction in the emission of unburned carbon.

[0132] Through the above embodiments, it can be seen that the operation and control method of the pulverizing unit in conjunction with the coal-fired boiler during peak shaving of thermal power can effectively improve the operating efficiency, combustion efficiency and peak shaving capacity of the thermal power generation system, while reducing pollutant emissions and operating costs, and has significant economic and social benefits.

Claims

1. A method for controlling the operation of a pulverizing unit in conjunction with a coal-fired boiler during peak shaving in thermal power plants, characterized in that, Includes the following steps: Step S1: Collect coal particle size information of coal-fired boilers in the thermal power generation system under normal and peak-shaving conditions respectively, and combine it with the corresponding coal-fired boiler operating status monitoring data to determine the first typical particle size distribution range when the coal-fired boiler is under normal conditions and the second typical particle size distribution range when it is under peak-shaving conditions; at the same time, combine the power generation monitoring data of the thermal power generation system to establish a mathematical intelligent model between coal particle size and the performance of the thermal power generation system. Step S2: Based on the first typical particle size distribution range and the second typical particle size distribution range, and combined with the optimization results of the mathematical intelligent model, configure the number of grinding mills and set the working parameters of each grinding mill. Step S3: When the thermal power generation system is in normal condition, based on the coal particle size requirement calculated by the controller of the thermal power generation system, combined with the real-time monitoring data of the coal-fired boiler and the optimization results of the mathematical intelligent model, determine and start the corresponding number of grinding mills, and dynamically adjust the working parameters of the grinding mills. Step S4: When the thermal power generation system is in peak shaving mode, based on the coal particle size requirement calculated by the controller of the thermal power generation system, combined with the real-time monitoring data of the coal-fired boiler and the optimization results of the mathematical intelligent model, the corresponding number of grinding mills are re-determined and started, and the working parameters of the grinding mills are dynamically adjusted.

2. The method for operation and control of a pulverizing unit in conjunction with a coal-fired boiler during peak shaving in thermal power plants, as described in claim 1, is characterized in that... In steps S3 and S4, the working status of each grinding mill is monitored synchronously; if a grinding mill is in an abnormal state, a backup grinding mill is activated and the corresponding working parameters are configured.

3. The method for operation and control of a pulverizing unit in conjunction with a coal-fired boiler during peak shaving in thermal power plants, as described in claim 1, is characterized in that... The specific execution process of step S1 includes: Step S11: In each operating cycle, coal samples are collected from the coal transportation of the thermal power generation system according to the preset collection frequency, and the particle size of the coal samples is tested to obtain the particle size distribution data of each coal sample; at the same time, the working status monitoring data of the coal-fired boiler and the power generation monitoring data of the thermal power generation system are recorded during the sampling. Step S12: All collected particle size distribution data are summarized and organized according to normal state and peak shaving state to form two independent datasets, corresponding to normal state and peak shaving state respectively; statistical analysis is performed on each dataset, statistical characteristics are calculated, and combined with the corresponding coal-fired boiler operating status monitoring data, the first typical particle size distribution interval when the coal-fired boiler is in normal state and the second typical particle size distribution interval when it is in peak shaving state are determined respectively. Step S13: Clean all collected particle size distribution data and corresponding power generation monitoring data, extract key features affecting power generation performance from the particle size distribution data, normalize the extracted key features and corresponding power generation monitoring data, and finally use machine learning to obtain a mathematical intelligent model between coal particle size and thermal power generation system performance.

4. The method for operation and control of a pulverizing unit in conjunction with a coal-fired boiler during peak shaving in thermal power plants, as described in claim 3, is characterized in that... The machine learning algorithms used in the mathematical intelligence model in step S13 include, but are not limited to, support vector machines, neural networks, decision trees, or random forests.

5. The method for operation control of a pulverizing unit in conjunction with a coal-fired boiler during peak shaving in thermal power plants, as described in claim 1, is characterized in that... The specific execution process of step S2 is as follows: Step S21: Based on the first typical particle size distribution range and the second typical particle size distribution range, and combined with the coal demand and particle size requirements of the thermal power generation system under different conditions, the number of grinding mills required under normal and peak-shaving conditions is calculated by using a mathematical intelligent model according to the coal demand and particle size requirements. Step S22: Based on the number of grinding mills calculated by the mathematical intelligent model, formulate a combination scheme for the grinding mills and determine the configuration method of the grinding mills; Step S23: Assign preliminary operating parameters to each grinding mill according to the grinding mill combination scheme; Step S24: Based on the optimization results of the mathematical intelligent model, optimize and adjust the working parameters of each grinding mill.

6. The method for operation and control of a grinding mill unit in conjunction with a coal-fired boiler during peak shaving in thermal power plants, as described in claim 1, is characterized in that... The specific execution process of step S3 is as follows: Step S31: When the thermal power generation system is in normal condition, the controller of the thermal power generation system calculates the required coal particle size range based on the current power generation load demand and the pre-established correspondence between power generation load and coal particle size demand. Step S32: Compare the calculated coal particle size range with the first typical particle size distribution range to determine the number of grinding mills and operating parameters that match it. Step S33: Send start commands to the corresponding number of grinding mills and set the determined operating parameters to each grinding mill so that the grinding mills can operate according to the set parameters and provide coal with the required particle size to the coal-fired boiler.

7. The method for operation and control of a grinding mill unit in conjunction with a coal-fired boiler during peak shaving in thermal power plants, as described in claim 6, is characterized in that... The comparison process in step S32 employs a minimum error matching algorithm to ensure the optimality of the matching results.

8. The method for operation and control of a pulverizing unit in conjunction with a coal-fired boiler during peak shaving in thermal power plants, as described in claim 1, is characterized in that... The specific execution process of step S4 is as follows: Step S41: When the thermal power generation system is in peak shaving mode, the controller of the thermal power generation system calculates the current required coal particle size range based on the changes in power generation load during peak shaving and the pre-established correspondence between power generation load and coal particle size requirements. Step S42: Compare the calculated coal particle size range with the second typical particle size distribution range to determine the number of grinding mills and operating parameters that match it. Step S43: Send start command to the corresponding number of grinding mills and set the determined working parameters to each grinding mill so that the grinding mills can operate according to the set parameters and provide coal with the required particle size to the coal-fired boiler.

9. The method for operation and control of a grinding mill unit in conjunction with a coal-fired boiler during peak shaving in thermal power plants, as described in claim 8, is characterized in that... The comparison process in step S42 employs a minimum error matching algorithm to ensure the optimality of the matching results.

10. An operation control system for a pulverizing unit cooperating with a coal-fired boiler during peak shaving of thermal power plants, to implement the operation control method for a pulverizing unit cooperating with a coal-fired boiler during peak shaving of thermal power plants as described in any one of claims 1 to 9, characterized in that, include: The acquisition and model building module is used to collect coal particle size information of coal-fired boilers in the thermal power generation system under normal and peak-shaving conditions, respectively, and combine it with the corresponding coal-fired boiler operating status monitoring data to determine the first typical particle size distribution range and the second typical particle size distribution range corresponding to the coal-fired boilers under normal and peak-shaving conditions, respectively; at the same time, combined with the power generation monitoring data of the thermal power generation system, a mathematical intelligent model between coal particle size and the performance of the thermal power generation system is established. The configuration module is used to configure the number of grinding mills and set the working parameters of each grinding mill based on the first typical particle size distribution range and the second typical particle size distribution range, combined with the optimization results of the mathematical intelligent model. The operation and control module is used to determine and start a corresponding number of grinding mills and dynamically adjust their operating parameters when the thermal power generation system is in normal operation, based on the coal particle size requirement calculated by the controller of the thermal power generation system, combined with the real-time monitoring data of the coal-fired boiler and the optimization results of the mathematical intelligent model; when the thermal power generation system is in peak-shaving operation, it re-determines and starts a corresponding number of grinding mills and dynamically adjusts their operating parameters based on the coal particle size requirement calculated by the controller of the thermal power generation system, combined with the real-time monitoring data of the coal-fired boiler and the optimization results of the mathematical intelligent model.

Images