Thermal power plant comprehensive benefit measuring and calculating system based on fuel index difference

Abstract

The invention discloses a thermal power plant comprehensive benefit measuring and calculating system based on fuel index difference, and belongs to the technical field of benefit measuring and calculating. In order to solve the problem that the error of a result measured by an existing measuring and calculating system is large, the temperature of a furnace bottom heating surface is detected, the slagging condition is judged, the detected result is transmitted to an early warning unit, then a monitoring visualization module is used for displaying data collected and sorted by a data unit in a visualization mode, and a three-dimensional coordinate system is established; a boiler bottom heating surface is combined with a coordinate system, when the slagging range is detected, a three-dimensional slagging profile diagram is drawn, when the slagging thickness is detected, the thicker the slagging is, the darker the marking color is, after each time of work is completed, detection and drawing need to be carried out so that the newly added slagging range and thickness each time can be recorded, and the detection efficiency is improved. Therefore, the relation between the fire coal index difference and the comprehensive benefit of the thermal power plant is accurately calculated, and the scheme which enables the comprehensive cost of the thermal power plant to be lowest is determined.

Description

Technical Field

[0001] The invention relates to the technical field of benefit calculation, and in particular to a comprehensive benefit calculation system for a thermal power plant based on fuel index differences. Background Art

[0002] In order to control the cost of power generation, many power plants currently try to buy low-cost low-quality coal, rather than high-priced high-quality coal close to the designed coal type. However, long-term use of low-quality coal will lead to a series of problems such as increased wear of boiler equipment, increased maintenance costs, increased number of four-tube explosions, and reduced equipment output. There is an optimal point between the coal procurement cost, boiler operation cost, and wear and tear maintenance cost, which makes the overall cost of the power plant the lowest. Therefore, studying the influence of coal quality on the overall cost of power plants and conducting quantitative analysis to find the most economical coal type is of great significance to coal procurement and economic operation of power plants.

[0003] In the existing technology, only the relationship between coal quality and comprehensive benefits is considered. Although the coal quality is constantly changed to achieve the best comprehensive benefits, during the trial process, the heating surface at the bottom of the boiler will gradually slag. As the slag becomes thicker and thicker, the heat transfer efficiency of the boiler will gradually decrease. In addition, in the existing technology, the slag treatment at the bottom of the boiler is not comprehensive enough, which indirectly leads to inaccurate results of fuel difference and comprehensive benefit calculation, and large errors. Summary of the invention

[0004] The purpose of the present invention is to provide a comprehensive benefit calculation system for a thermal power plant based on fuel index differences, so as to solve the problem of large errors in the results calculated by the calculation system in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: a comprehensive benefit calculation system for a thermal power plant based on fuel index differences, comprising:

[0006] Data unit for:

[0007] Responsible for collecting various types of raw data from all aspects of the thermal power plant, and cleaning, classifying and integrating the collected data;

[0008] Model units for:

[0009] According to the problems to be solved and the characteristics of the data collected from the data units, multiple model frameworks are established and subsequently verified and calibrated;

[0010] Scenario unit for:

[0011] Based on the model built by the model unit, and also based on the different conditions and parameter combinations set, simulate various operating scenarios, select appropriate coal procurement plans, and evaluate the plans;

[0012] Early warning unit for:

[0013] Provide early warning of boiler operating parameters in thermal power plants and predict and manage faulty boilers.

[0014] Furthermore, the data unit includes:

[0015] Data collection module and data sorting module,

[0016] The data acquisition module includes:

[0017] Coal quality analysis module for:

[0018] Carry out quality inspection on purchased coal, install coal quality analyzer at the coal entry point, and detect various coal indicators in real time;

[0019] Boiler quality monitoring module for:

[0020] Conduct wear test on the boiler and observe the slagging condition on the heating surface of the furnace bottom. Determine the slagging condition by detecting the temperature of the heating surface of the furnace bottom and transmit the detected results to the early warning unit to determine the slagging range and thickness.

[0021] Combustion efficiency monitoring module for:

[0022] By analyzing the three indicators of the utilization degree of heat generated after combustion, the content of incomplete combustion products and the temperature distribution in the furnace, the combustion effect of coal under the current working conditions can be accurately grasped, which is convenient for adjusting the combustion parameters, including the coal feeding amount and the air intake amount. If the combustion effect under the current working conditions does not meet the actual situation, a judgment is made. When 20% < combustion efficiency < 50%, the coal intake amount is adjusted, otherwise re-test. After adjusting the coal intake amount, the judgment continues. When 20% < combustion efficiency < 60%, the air intake amount is adjusted, otherwise re-test. After adjusting the air intake amount, the judgment continues. When the combustion efficiency is < 80%, the boiler quality monitoring module will perform slagging detection on the bottom of the boiler, otherwise it means normal, and the judgment result will be transmitted to the early warning unit.

[0023] Exhaust emission monitoring module for:

[0024] The exhaust gas generated by boiler combustion is continuously monitored to detect the emission concentration and emission amount of various pollutants to ensure that it meets environmental protection standards. At the same time, the boiler combustion status can be fed back based on the emission data, and the results can be transmitted to the early warning unit to assist in adjusting the operating parameters to achieve cleaner combustion.

[0025] Furthermore, the data sorting module includes:

[0026] Data cleaning module, used to:

[0027] Identify and handle outliers, duplicate data, and erroneous records in the data. Through the set algorithm, remove invalid data, correct inaccurate data, ensure the accuracy and completeness of the data, and provide a data basis for subsequent work;

[0028] Coal quality classification module for:

[0029] According to the established coal quality evaluation standards and analysis results, coal from different batches and sources is classified according to quality grades, and the coal information is transmitted to the boiler quality monitoring module to understand the corresponding coal information when there is a problem with the boiler quality;

[0030] Data collection module for:

[0031] The data that have been sorted, cleaned and classified are integrated and aggregated to form a unified and complete data collection, which is convenient for daily inspection by staff and provides data support for subsequent boiler health management.

[0032] Furthermore, the model unit includes: a model selection and construction module and a model verification and calibration module,

[0033] The model selection building module is used to:

[0034] A hybrid model combining multiple linear regression and neural network was selected to build a model with coal quality parameters as independent variables and coal procurement cost, wear and tear maintenance cost and comprehensive cost as dependent variables.

[0035] Model validation and calibration module for:

[0036] A cross-validation verification method is adopted, and a portion of independent data is used to test the performance of the model, evaluate the accuracy and reliability of the model. At the same time, the model is recalibrated regularly according to the verification results and new situations in the actual operation process to ensure that the model is always consistent with the actual operating conditions of the power plant, maintain its effectiveness and practicality, and provide model support for subsequent scenario unit simulation scenarios.

[0037] Furthermore, the model selection and construction module includes: a model optimization module and a model learning module.

[0038] The model optimization module is used to:

[0039] Use the particle swarm optimization algorithm to optimize the parameters of the built model, improve the accuracy, stability and generalization ability of the model, so that it can better fit the actual data, more accurately reflect the internal relationship between the variables, and improve the model's prediction and analysis effect on the actual situation;

[0040] Model learning module for:

[0041] Use processed historical data and real-time data to train and learn the optimized model, so that the model can continuously "grasp" the laws and patterns in the data, so that it can accurately output the corresponding prediction results or analysis conclusions based on the relevant input variables;

[0042] In the process of optimizing the parameters of the built model using the particle swarm optimization algorithm, represents the individual optimal position of the i-th particle at the t-th iteration, represents the position of the i-th particle at the t+1th iteration, and f(·) represents the objective function, then:

[0043] The formula for updating the optimal position of an individual is:

[0044] Set gbest (t) represents the global optimal position at the tth iteration, with N particles, represents the position of the i-th particle at the t+1th iteration, and f(·) represents the objective function;

[0045] Define a function j * To find the particle index that minimizes the objective function value:

[0046] The formula for updating the global optimal position is expressed as:

[0047]

[0048] In the problem of optimizing the comprehensive cost of a power plant, f(·) is expressed as the comprehensive cost function of coal quality parameters or equipment operation parameters. The position of the particle can be expressed as the value of these parameters. By continuously iteratively updating the optimal position, we can eventually find the parameter combination that minimizes the comprehensive cost.

[0049] Furthermore, the scenario unit includes:

[0050] Scenario simulation module for:

[0051] According to the model selection and building module, the model is simulated to simulate various operation scenarios, so as to fully understand the operation status and cost changes of the power plant, provide a basis for formulating comprehensive and flexible response strategies, and enhance the power plant's ability to cope with different working conditions;

[0052] Program evaluation module for:

[0053] A comprehensive and systematic evaluation is conducted on each set of coal procurement plans from the perspective of cost-effectiveness, environmental protection indicators, and equipment operation stability. The advantages and disadvantages of each plan are compared and analyzed to select the plan that best meets the overall interests and long-term development needs of the power plant, ensuring that the adopted plan can both control costs and ensure the stable and clean operation of the power plant. If the number of disadvantages of the evaluated plan is greater than the number of advantages, information is fed back to the model verification and calibration module to recalibrate the model.

[0054] Furthermore, the scenario simulation module includes:

[0055] Parameter setting module, used for:

[0056] Combined with the produced model, various key parameters for constructing different simulation scenarios are determined, specifically setting different coal price ranges to reflect the quality of coal, setting different health status parameters of equipment, and setting rated power generation. By adjusting these parameters, a variety of specific simulation scenarios with practical reference value can be depicted;

[0057] Cost calculation module for:

[0058] According to different simulation scenarios, calculate the various costs of the power plant under the corresponding simulation scenarios, specifically the coal procurement cost and wear and tear maintenance cost, to provide accurate cost data support for evaluating the economic feasibility of different plans and assist in selecting the optimal operation and procurement plan;

[0059] Coal procurement plan formulation module, used to:

[0060] Taking into account the cost calculation results, coal quality analysis and environmental protection requirements, a variety of coal procurement plans are formulated to specify the purchase quantity, purchase channel and purchase time of different types of coal, aiming to obtain coal resources of appropriate quality that meet the production needs of power plants at the optimal cost.

[0061] Furthermore, the early warning unit includes:

[0062] Real-time monitoring module for:

[0063] With the help of IoT technology, the operating parameters and status information of boilers, combustion processes, and exhaust emissions can be obtained and updated in real time, allowing power plant operators to grasp the real-time situation at any time and detect any abnormal changes in time, providing the most timely data support for subsequent early warning, decision-making, and maintenance work;

[0064] Intelligent decision-making module for:

[0065] Combining real-time monitoring data and model analysis results, intelligent algorithms are used to automatically generate reasonable decision-making recommendations for current operating conditions.

[0066] Furthermore, the real-time monitoring module includes:

[0067] Monitoring and visualization module for:

[0068] Display the data collected and sorted by the data unit in a visual form to facilitate timely discovery of problems and decision-making;

[0069] Intelligent early warning module for:

[0070] Dynamically analyze the real-time monitoring data of the combustion efficiency monitoring module and the exhaust emission monitoring module, automatically identify potential risks of equipment failure, combustion abnormality, and excessive emissions based on the preset warning thresholds and abnormality judgment rules, and issue alarm information in a timely manner to remind relevant personnel to take countermeasures in advance;

[0071] Information push module, used for:

[0072] The alarm information issued by the intelligent early warning module is sent to the corresponding operation and maintenance personnel and management personnel in a timely and accurate manner through SMS and mobile application push, ensuring that key information can be obtained in the first time, improving the timeliness and effectiveness of problem response;

[0073] Among them, a three-dimensional coordinate system is established through the monitoring visualization module, and the heating surface at the bottom of the boiler is combined with the coordinate system. When detecting the slagging range, a three-dimensional slagging contour map is drawn. When detecting the slagging thickness, the thicker the slagging, the darker the marking color. After each work is completed, detection and drawing are required to record the newly added slagging range and thickness each time, and superimposed in the coordinate system. Different colors are used to represent different slagging each time. At the same time, the information obtained by the coal quality analysis module is used to mark the type of coal on the slagging contour.

[0074] Furthermore, the intelligent decision-making module includes:

[0075] Equipment health management module, used for:

[0076] Based on the data collated by the data collation module, the health status of the equipment is comprehensively evaluated, and future failures and remaining service life of the equipment are predicted. The equipment is managed in a graded manner through quantitative health indicators, providing a scientific basis for formulating accurate equipment maintenance and update plans, and achieving effective management of the entire life cycle of the equipment;

[0077] Maintenance plan generation module for:

[0078] According to the equipment health assessment results provided by the equipment health management module and the suggestions given by the intelligent decision-making module, a detailed and reasonable equipment maintenance plan is automatically generated. The maintenance plan is then simulated through the scenario simulation module, including adjusting the quality and type of coal and removing slag at the bottom of the boiler. After the maintenance is completed, actual maintenance operations are carried out to ensure the reliability and stability of the equipment and extend the service life of the equipment.

[0079] Compared with the prior art, the present invention has the following beneficial effects:

[0080] Under the existing technology, the results calculated by the measurement system have large errors. The present invention uses a coal quality analysis module to perform quality inspection on the purchased coal, installs a coal quality analyzer at the coal entry point, and detects various indicators of the coal in real time. At the same time, the boiler quality monitoring module is used to detect the wear of the boiler and observe the slagging condition of the heating surface at the bottom of the furnace. The slagging condition is determined by detecting the temperature of the heating surface at the bottom of the furnace, and the detected results are transmitted to the early warning unit to determine the slagging range and thickness. The monitoring visualization module is then used to display the data collected and sorted by the data unit in a visualized form, which is convenient for timely discovery of problems and decision-making. A three-dimensional coordinate system is established, and the heating surface at the bottom of the boiler is combined with the coordinate system. When detecting the slagging range, a three-dimensional slagging contour map is drawn. When detecting the slag thickness, the thicker the slag, the darker the color of the mark. After each work is completed, it is necessary to detect and draw in order to record the scope and thickness of each new slag, and at the same time overlay them in the coordinate system, and use different colors to represent different slag each time. At the same time, the information obtained by the coal quality analysis module is used to mark the type of coal on the slag contour, so that after each work is completed, the slag at the bottom of the boiler can be statistically analyzed. Combined with the type of coal used each time, it can be determined which type of coal has a small slag range and thin thickness. Combined with the price of coal, it can be determined which type of coal has both a suitable price and low damage to the boiler, thereby accurately calculating the relationship between the difference in coal indicators and the comprehensive benefits of the thermal power plant, and determining which solution makes the comprehensive cost of the thermal power plant the lowest. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 The figure is an overall flow chart of the comprehensive benefit calculation system of a thermal power plant based on fuel index differences of the present invention. DETAILED DESCRIPTION

[0082] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0083] See also Figure 1 , the present invention provides the following technical solutions:

[0084] A comprehensive benefit calculation system for thermal power plants based on fuel index differences, comprising:

[0085] Data unit for:

[0086] Responsible for collecting various types of raw data from all aspects of the thermal power plant, and cleaning, classifying and integrating the collected data;

[0087] Model units for:

[0088] According to the problems to be solved and the characteristics of the data collected from the data units, multiple model frameworks are established and subsequently verified and calibrated;

[0089] Scenario unit for:

[0090] Based on the model built by the model unit, and also based on the different conditions and parameter combinations set, simulate various operating scenarios, select appropriate coal procurement plans, and evaluate the plans;

[0091] Early warning unit for:

[0092] Provide early warning of boiler operating parameters in thermal power plants and predict and manage faulty boilers.

[0093] The data units include:

[0094] Data collection module and data sorting module,

[0095] The data acquisition module includes:

[0096] Coal quality analysis module for:

[0097] Carry out quality inspection on purchased coal, install coal quality analyzer at the coal entry point, and detect various coal indicators in real time;

[0098] Boiler quality monitoring module for:

[0099] Conduct wear test on the boiler and observe the slagging condition on the heating surface of the furnace bottom. Determine the slagging condition by detecting the temperature of the heating surface of the furnace bottom and transmit the detected results to the early warning unit to determine the slagging range and thickness.

[0100] Combustion efficiency monitoring module for:

[0101] By analyzing the three indicators of the utilization degree of heat generated after combustion, the content of incomplete combustion products and the temperature distribution in the furnace, the combustion effect of coal under the current working conditions can be accurately grasped, which is convenient for adjusting the combustion parameters, including the coal feeding amount and the air intake amount. If the combustion effect under the current working conditions does not meet the actual situation, a judgment is made. When 20% < combustion efficiency < 50%, the coal intake amount is adjusted, otherwise re-test. After adjusting the coal intake amount, the judgment continues. When 20% < combustion efficiency < 60%, the air intake amount is adjusted, otherwise re-test. After adjusting the air intake amount, the judgment continues. When the combustion efficiency is < 80%, the boiler quality monitoring module will perform slagging detection on the bottom of the boiler, otherwise it means normal, and the judgment result will be transmitted to the early warning unit.

[0102] During the operation of the boiler, if the combustion efficiency suddenly becomes low, there are three factors. The first is the low air intake and insufficient oxygen supply, which leads to low combustion efficiency. The second is insufficient coal intake, which leads to combustion stagnation, resulting in low combustion efficiency. The third is that there is too much slagging on the heating surface at the bottom of the boiler and heat transfer is blocked, resulting in low combustion efficiency. The combustion efficiency monitoring module is used to detect and determine which specific factor has caused the reduction in combustion efficiency. If there is too much slagging on the heating surface at the bottom of the boiler, a signal will be sent to the intelligent early warning module, causing it to sound an alarm.

[0103] Exhaust emission monitoring module for:

[0104] The exhaust gas generated by boiler combustion is continuously monitored to detect the emission concentration and emission amount of various pollutants to ensure that it meets environmental protection standards. At the same time, the boiler combustion status can be fed back based on the emission data, and the results can be transmitted to the early warning unit to assist in adjusting the operating parameters to achieve cleaner combustion.

[0105] The data sorting module includes:

[0106] Data cleaning module, used to:

[0107] Identify and handle outliers, duplicate data, and erroneous records in the data. Through the set algorithm, remove invalid data, correct inaccurate data, ensure the accuracy and completeness of the data, and provide a data basis for subsequent work;

[0108] Coal quality classification module for:

[0109] According to the established coal quality evaluation standards and analysis results, coal from different batches and sources is classified according to quality grades, and the coal information is transmitted to the boiler quality monitoring module to understand the corresponding coal information when there is a problem with the boiler quality;

[0110] Data collection module for:

[0111] The data that have been sorted, cleaned and classified are integrated and aggregated to form a unified and complete data collection, which is convenient for daily inspection by staff and provides data support for subsequent boiler health management.

[0112] The model unit includes: model selection and construction module and model verification and calibration module.

[0113] The model selection building module is used to:

[0114] A hybrid model combining multiple linear regression and neural network was selected to build a model with coal quality parameters as independent variables and coal procurement cost, wear and tear maintenance cost and comprehensive cost as dependent variables.

[0115] Model validation and calibration module for:

[0116] A cross-validation verification method is adopted, and a portion of independent data is used to test the performance of the model, evaluate the accuracy and reliability of the model. At the same time, the model is recalibrated regularly according to the verification results and new situations in the actual operation process to ensure that the model is always consistent with the actual operating conditions of the power plant, maintain its effectiveness and practicality, and provide model support for subsequent scenario unit simulation scenarios.

[0117] The model selection and construction module includes: model optimization module and model learning module.

[0118] The model optimization module is used to:

[0119] Use the particle swarm optimization algorithm to optimize the parameters of the built model, improve the accuracy, stability and generalization ability of the model, so that it can better fit the actual data, more accurately reflect the internal relationship between the variables, and improve the model's prediction and analysis effect on the actual situation;

[0120] Model learning module for:

[0121] Use processed historical data and real-time data to train and learn the optimized model, so that the model can continuously "grasp" the laws and patterns in the data, so that it can accurately output the corresponding prediction results or analysis conclusions based on the relevant input variables;

[0122] In the process of optimizing the parameters of the built model using the particle swarm optimization algorithm, represents the individual optimal position of the i-th particle at the t-th iteration, represents the position of the i-th particle at the t+1th iteration, and f(·) represents the objective function, then:

[0123] The formula for updating the optimal position of an individual is:

[0124] Set gbest (t) represents the global optimal position at the tth iteration, with N particles, represents the position of the i-th particle at the t+1th iteration, and f(·) represents the objective function;

[0125] Define a function j * To find the particle index that minimizes the objective function value:

[0126] The formula for updating the global optimal position is expressed as:

[0127]

[0128] In the problem of optimizing the comprehensive cost of a power plant, f(·) is expressed as the comprehensive cost function of coal quality parameters or equipment operation parameters. The position of the particle can be expressed as the value of these parameters. By continuously iteratively updating the optimal position, we can eventually find the parameter combination that minimizes the comprehensive cost.

[0129] Update the individual optimal formula: The value of is either 0 or 1;

[0130] if but at this time because Will keep The value of

[0131] if but at this time because will be multiplied by 0;

[0132] Update the global optimal formula: First, find the particle index j with the minimum objective function value at the t+1th iteration * ;

[0133] Then according to The value of determines whether to update the global optimal position;

[0134] if Then update to Otherwise keep gbest t constant.

[0135] The scenario units include:

[0136] Scenario simulation module for:

[0137] According to the model selection and building module, the model is simulated to simulate various operation scenarios, so as to fully understand the operation status and cost changes of the power plant, provide a basis for formulating comprehensive and flexible response strategies, and enhance the power plant's ability to cope with different working conditions;

[0138] Program evaluation module for:

[0139] A comprehensive and systematic evaluation is conducted on each set of coal procurement plans from the perspective of cost-effectiveness, environmental protection indicators, and equipment operation stability. The advantages and disadvantages of each plan are compared and analyzed to select the plan that best meets the overall interests and long-term development needs of the power plant, ensuring that the adopted plan can both control costs and ensure the stable and clean operation of the power plant. If the number of disadvantages of the evaluated plan is greater than the number of advantages, information is fed back to the model verification and calibration module to recalibrate the model.

[0140] The scenario simulation module includes:

[0141] Parameter setting module, used for:

[0142] Combined with the produced model, various key parameters for constructing different simulation scenarios are determined, specifically setting different coal price ranges to reflect the quality of coal, setting different health status parameters of equipment, and setting rated power generation. By adjusting these parameters, a variety of specific simulation scenarios with practical reference value can be depicted;

[0143] Cost calculation module for:

[0144] According to different simulation scenarios, calculate the various costs of the power plant under the corresponding simulation scenarios, specifically the coal procurement cost and wear and tear maintenance cost, to provide accurate cost data support for evaluating the economic feasibility of different plans and assist in selecting the optimal operation and procurement plan;

[0145] Coal procurement plan formulation module, used to:

[0146] Taking into account the cost calculation results, coal quality analysis and environmental protection requirements, a variety of coal procurement plans are formulated to specify the purchase quantity, purchase channel and purchase time of different types of coal, aiming to obtain coal resources of appropriate quality that meet the production needs of power plants at the optimal cost.

[0147] The early warning unit includes:

[0148] Real-time monitoring module for:

[0149] With the help of IoT technology, the operating parameters and status information of boilers, combustion processes, and exhaust emissions can be obtained and updated in real time, allowing power plant operators to grasp the real-time situation at any time and detect any abnormal changes in time, providing the most timely data support for subsequent early warning, decision-making, and maintenance work;

[0150] Intelligent decision-making module for:

[0151] Combining real-time monitoring data and model analysis results, intelligent algorithms are used to automatically generate reasonable decision-making recommendations for current operating conditions.

[0152] The real-time monitoring module includes:

[0153] Monitoring and visualization module for:

[0154] Display the data collected and sorted by the data unit in a visual form to facilitate timely discovery of problems and decision-making;

[0155] Intelligent early warning module for:

[0156] Dynamically analyze the real-time monitoring data of the combustion efficiency monitoring module and the exhaust emission monitoring module, automatically identify potential risks of equipment failure, combustion abnormality, and excessive emissions based on the preset warning thresholds and abnormality judgment rules, and issue alarm information in a timely manner to remind relevant personnel to take countermeasures in advance;

[0157] Information push module, used for:

[0158] The alarm information issued by the intelligent early warning module is sent to the corresponding operation and maintenance personnel and management personnel in a timely and accurate manner through SMS and mobile application push, ensuring that key information can be obtained in the first time, improving the timeliness and effectiveness of problem response;

[0159] Among them, a three-dimensional coordinate system is established through the monitoring visualization module, and the heating surface at the bottom of the boiler is combined with the coordinate system. When detecting the slagging range, a three-dimensional slagging contour map is drawn. When detecting the slagging thickness, the thicker the slagging, the darker the marking color. After each work is completed, detection and drawing are required to record the newly added slagging range and thickness each time, and superimposed in the coordinate system. Different colors are used to represent different slagging each time. At the same time, the information obtained by the coal quality analysis module is used to mark the type of coal on the slagging contour.

[0160] Intelligent decision-making modules include:

[0161] Equipment health management module, used for:

[0162] Based on the data collated by the data collation module, the health status of the equipment is comprehensively evaluated, and future failures and remaining service life of the equipment are predicted. The equipment is managed in a graded manner through quantitative health indicators, providing a scientific basis for formulating accurate equipment maintenance and update plans, and achieving effective management of the entire life cycle of the equipment;

[0163] Maintenance plan generation module for:

[0164] According to the equipment health assessment results provided by the equipment health management module and the suggestions given by the intelligent decision-making module, a detailed and reasonable equipment maintenance plan is automatically generated. The maintenance plan is then simulated through the scenario simulation module, including adjusting the quality and type of coal and removing slag at the bottom of the boiler. After the maintenance is completed, actual maintenance operations are carried out to ensure the reliability and stability of the equipment and extend the service life of the equipment.

[0165] Specifically, the coal quality analysis module is used to test the quality of the purchased coal, and a coal quality analyzer is installed at the coal entry point to test various coal indicators in real time. At the same time, the boiler quality monitoring module is used to test the wear of the boiler and observe the slagging condition of the heating surface at the bottom of the furnace. The slagging condition is determined by detecting the temperature of the heating surface at the bottom of the furnace, and the detected results are transmitted to the early warning unit to determine the slagging range and thickness. The monitoring visualization module is then used to display the data collected and sorted by the data unit in a visualized form, which is convenient for timely discovery of problems and decision-making. A three-dimensional coordinate system is established, and the heating surface at the bottom of the boiler is combined with the coordinate system. When detecting the slagging range, a three-dimensional slagging contour map is drawn. When detecting the slagging thickness, the more slagging there is, the more The thicker the mark, the darker the color. After each work is completed, it is necessary to detect and draw in order to record the scope and thickness of each new slagging, and display them in superposition in the coordinate system, and use different colors to represent different slagging each time. At the same time, the information obtained by the coal quality analysis module is used to mark the type of coal on the slagging contour. Therefore, after each work is completed, the slagging at the bottom of the boiler can be statistically analyzed. Combined with the type of coal used each time, it can be determined which type of coal has a small slagging range and thin thickness. Combined with the price of coal, it can be determined which type of coal has both a suitable price and low damage to the boiler. In this way, the relationship between the difference in coal indicators and the comprehensive benefits of the thermal power plant can be accurately calculated, so as to determine which plan makes the comprehensive cost of the thermal power plant the lowest.

[0166] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A comprehensive benefit calculation system for thermal power plants based on fuel index differences, characterized in that: include: Data unit for: Responsible for collecting various types of raw data from all aspects of the thermal power plant, and cleaning, classifying and integrating the collected data; Model units for: According to the problems to be solved and the characteristics of the data collected from the data units, multiple model frameworks are established and subsequently verified and calibrated; Scenario unit for: Based on the model built by the model unit, and also based on the different conditions and parameter combinations set, simulate various operating scenarios, select appropriate coal procurement plans, and evaluate the plans; Early warning unit for: Provide early warning of boiler operating parameters in thermal power plants and predict and manage faulty boilers.

2. A thermal power plant comprehensive benefit calculation system based on fuel index difference as claimed in claim 1, characterized in that: The data unit includes: Data collection module and data sorting module, The data acquisition module includes: Coal quality analysis module for: Carry out quality inspection on purchased coal, install coal quality analyzer at the coal entry point, and detect various coal indicators in real time; Boiler quality monitoring module for: Conduct wear test on the boiler and observe the slagging condition on the heating surface of the furnace bottom. Determine the slagging condition by detecting the temperature of the heating surface of the furnace bottom and transmit the detected results to the early warning unit to determine the slagging range and thickness. Combustion efficiency monitoring module for: By analyzing the three indicators of the utilization degree of heat generated after combustion, the content of incomplete combustion products and the temperature distribution in the furnace, the combustion effect of coal under the current working conditions can be accurately grasped, which is convenient for adjusting the combustion parameters, including the coal feeding amount and the air intake amount. If the combustion effect under the current working conditions does not meet the actual situation, a judgment is made. When 20% < combustion efficiency < 50%, the coal intake amount is adjusted, otherwise re-test. After adjusting the coal intake amount, the judgment continues. When 20% < combustion efficiency < 60%, the air intake amount is adjusted, otherwise re-test. After adjusting the air intake amount, the judgment continues. When the combustion efficiency is < 80%, the boiler quality monitoring module will perform slagging detection on the bottom of the boiler, otherwise it means normal, and the judgment result will be transmitted to the early warning unit. Exhaust emission monitoring module for: The exhaust gas generated by boiler combustion is continuously monitored to detect the emission concentration and emission amount of various pollutants to ensure that it meets environmental protection standards. At the same time, the boiler combustion status can be fed back based on the emission data, and the results can be transmitted to the early warning unit to assist in adjusting the operating parameters to achieve cleaner combustion.

3. A thermal power plant comprehensive benefit calculation system based on fuel index difference as claimed in claim 2, characterized in that: The data sorting module comprises: Data cleaning module, used to: Identify and handle outliers, duplicate data, and erroneous records in the data. Through the set algorithm, remove invalid data, correct inaccurate data, ensure the accuracy and completeness of the data, and provide a data basis for subsequent work; Coal quality classification module for: According to the established coal quality evaluation standards and analysis results, coal from different batches and sources is classified according to quality grades, and the coal information is transmitted to the boiler quality monitoring module to understand the corresponding coal information when there is a problem with the boiler quality; Data collection module for: The data that have been sorted, cleaned and classified are integrated and aggregated to form a unified and complete data collection, which is convenient for daily inspection by staff and provides data support for subsequent boiler health management.

4. A thermal power plant comprehensive benefit calculation system based on fuel index difference as claimed in claim 3, characterized in that: The model unit includes: a model selection and construction module and a model verification and calibration module. The model selection building module is used to: A hybrid model combining multiple linear regression and neural network was selected to build a model with coal quality parameters as independent variables and coal procurement cost, wear and tear maintenance cost and comprehensive cost as dependent variables. Model validation and calibration module for: A cross-validation verification method is adopted, and a portion of independent data is used to test the performance of the model, evaluate the accuracy and reliability of the model. At the same time, the model is recalibrated regularly according to the verification results and new situations in the actual operation process to ensure that the model is always consistent with the actual operating conditions of the power plant, maintain its effectiveness and practicality, and provide model support for subsequent scenario unit simulation scenarios.

5. A thermal power plant comprehensive benefit calculation system based on fuel index difference as claimed in claim 4, characterized in that: The model selection and construction module includes: a model optimization module and a model learning module. The model optimization module is used to: Use the particle swarm optimization algorithm to optimize the parameters of the built model, improve the accuracy, stability and generalization ability of the model, so that it can better fit the actual data, more accurately reflect the internal relationship between the variables, and improve the model's prediction and analysis effect on the actual situation; Model learning module for: Use processed historical data and real-time data to train and learn the optimized model, so that the model can continuously "grasp" the laws and patterns in the data, so that it can accurately output the corresponding prediction results or analysis conclusions based on the relevant input variables; In the process of optimizing the parameters of the built model using the particle swarm optimization algorithm, we set pbest i (t) represents the individual optimal position of the i-th particle at the t-th iteration, represents the position of the i-th particle at the t+1th iteration, and f(·) represents the objective function, then: The formula for updating the optimal position of an individual is: Set gbest (t) represents the global optimal position at the tth iteration, with N particles, represents the position of the i-th particle at the t+1th iteration, and f(·) represents the objective function; Define a function j * To find the particle index that minimizes the objective function value: The formula for updating the global optimal position is expressed as: In the problem of optimizing the comprehensive cost of a power plant, f(·) is expressed as the comprehensive cost function of coal quality parameters or equipment operation parameters. The position of the particle can be expressed as the value of these parameters. By continuously iteratively updating the optimal position, we can eventually find the parameter combination that minimizes the comprehensive cost.

6. A thermal power plant comprehensive benefit calculation system based on fuel index difference as claimed in claim 5, characterized in that: The scenario unit includes: Scenario simulation module for: According to the model selection and building module, the model is simulated to simulate various operation scenarios, so as to fully understand the operation status and cost changes of the power plant, provide a basis for formulating comprehensive and flexible response strategies, and enhance the power plant's ability to cope with different working conditions; Program evaluation module for: A comprehensive and systematic evaluation is conducted on each set of coal procurement plans from the perspective of cost-effectiveness, environmental protection indicators, and equipment operation stability. The advantages and disadvantages of each plan are compared and analyzed to select the plan that best meets the overall interests and long-term development needs of the power plant, ensuring that the adopted plan can both control costs and ensure the stable and clean operation of the power plant. If the number of disadvantages of the evaluated plan is greater than the number of advantages, information is fed back to the model verification and calibration module to recalibrate the model.

7. A thermal power plant comprehensive benefit calculation system based on fuel index difference as claimed in claim 6, characterized in that: The scenario simulation module comprises: Parameter setting module, used for: Combined with the produced model, various key parameters for constructing different simulation scenarios are determined, specifically setting different coal price ranges to reflect the quality of coal, setting different health status parameters of equipment, and setting rated power generation. By adjusting these parameters, a variety of specific simulation scenarios with practical reference value can be depicted; Cost calculation module for: According to different simulation scenarios, calculate the various costs of the power plant under the corresponding simulation scenarios, specifically the coal procurement cost and wear and tear maintenance cost, to provide accurate cost data support for evaluating the economic feasibility of different plans and assist in selecting the optimal operation and procurement plan; Coal procurement plan formulation module, used to: Taking into account the cost calculation results, coal quality analysis and environmental protection requirements, a variety of coal procurement plans are formulated to specify the purchase quantity, purchase channel and purchase time of different types of coal, aiming to obtain coal resources of appropriate quality that meet the production needs of power plants at the optimal cost.

8. A thermal power plant comprehensive benefit calculation system based on fuel index difference as claimed in claim 7, characterized in that: The early warning unit comprises: Real-time monitoring module for: With the help of IoT technology, the operating parameters and status information of boilers, combustion processes, and exhaust emissions can be obtained and updated in real time, allowing power plant operators to grasp the real-time situation at any time and discover any abnormal changes in time, providing the most timely data support for subsequent early warning, decision-making, and maintenance work; Intelligent decision-making module for: Combining real-time monitoring data and model analysis results, intelligent algorithms are used to automatically generate reasonable decision-making recommendations for current operating conditions.

9. A thermal power plant comprehensive benefit calculation system based on fuel index difference as claimed in claim 8, characterized in that: The real-time monitoring module comprises: Monitoring and visualization module for: Display the data collected and sorted by the data unit in a visual form to facilitate timely discovery of problems and decision-making; Intelligent early warning module for: Dynamically analyze the real-time monitoring data of the combustion efficiency monitoring module and the exhaust emission monitoring module, automatically identify potential risks of equipment failure, combustion abnormality, and excessive emissions based on the preset warning thresholds and abnormality judgment rules, and issue alarm information in a timely manner to remind relevant personnel to take countermeasures in advance; Information push module, used for: The alarm information issued by the intelligent early warning module is sent to the corresponding operation and maintenance personnel and management personnel in a timely and accurate manner through SMS and mobile application push, ensuring that key information can be obtained in the first time, improving the timeliness and effectiveness of problem response; Among them, a three-dimensional coordinate system is established through the monitoring visualization module, and the heating surface at the bottom of the boiler is combined with the coordinate system. When detecting the slagging range, a three-dimensional slagging contour map is drawn. When detecting the slagging thickness, the thicker the slagging, the darker the marking color. After each work is completed, detection and drawing are required to record the newly added slagging range and thickness each time, and superimposed in the coordinate system. Different colors are used to represent different slagging each time. At the same time, the information obtained by the coal quality analysis module is used to mark the type of coal on the slagging contour.

10. A thermal power plant comprehensive benefit calculation system based on fuel index difference as claimed in claim 9, characterized in that: The intelligent decision-making module includes: Equipment health management module, used for: Based on the data collated by the data collation module, the health status of the equipment is comprehensively evaluated, and future failures and remaining service life of the equipment are predicted. The equipment is managed in a graded manner through quantitative health indicators, providing a scientific basis for formulating accurate equipment maintenance and update plans, and achieving effective management of the entire life cycle of the equipment; Maintenance plan generation module for: According to the equipment health assessment results provided by the equipment health management module and the suggestions given by the intelligent decision-making module, a detailed and reasonable equipment maintenance plan is automatically generated. The maintenance plan is then simulated through the scenario simulation module, including adjusting the quality and type of coal and removing slag at the bottom of the boiler. After the maintenance is completed, actual maintenance operations are carried out to ensure the reliability and stability of the equipment and extend the service life of the equipment.

Images