A method and system for monitoring coal-fired power generation capacity

Abstract

This invention relates to the field of power system monitoring and dispatching technology, and discloses a method and system for monitoring coal-fired power generation capacity. This invention achieves dynamic monitoring of the power generation capacity of coal-fired units by collecting real-time operating data and inputting it into a pre-constructed comprehensive evaluation model of coal-fired power generation capacity. Compared with methods that rely solely on a single rated capacity or a single limiting factor, this invention considers macro-constraints such as power dispatching plans, market coal supply forecasts, and power plant management decisions, as well as micro-operating factors such as equipment parameters, coal quality parameters, and operating condition parameters, thus providing a more comprehensive reflection of the actual power generation capacity of coal-fired units during operation.

Description

Technical Field

[0001] This invention relates to the field of power system monitoring and dispatching technology, specifically to a method and system for monitoring coal-fired power generation capacity. Background Technology

[0002] Coal-fired power generation, as the cornerstone of conventional power supply, plays an increasingly prominent role as a stabilizing force, especially against the backdrop of large-scale grid integration of new energy sources and increased power system volatility. Accurate monitoring and forecasting of the power generation capacity of coal-fired units is a crucial prerequisite for power dispatching departments to formulate scientific and safe dispatching plans and ensure a reliable power supply.

[0003] However, the power generation capacity of coal-fired units is not a static rated value, but is dynamically constrained by multiple complex factors. Existing monitoring methods often consider three factors at a macro level: power supply, available coal in the market, and power plant production decisions. They assess power generation capacity by taking the minimum of these three factors, but cannot accurately reflect the real-time impact of micro-dynamic changes such as equipment status, coal quality fluctuations, and deviations in operating parameters on instantaneous power generation capacity. On the other hand, existing technologies also collect operating parameters of important auxiliary equipment, perform cluster analysis to obtain typical operating conditions, and calculate power generation capacity considering equipment health status, coal quality, key operating parameters, and heating conditions, finally taking the minimum value. However, this lacks a comprehensive consideration of the coupling relationships and dynamic weights between various factors. For example, when equipment health status slightly declines but coal quality significantly improves, the actual power generation capacity may not be simply determined by a single worst-case factor. Summary of the Invention

[0004] The purpose of this invention is to overcome the problems of existing coal-fired power generation capacity monitoring methods, which are difficult to integrate macro-constraints such as power dispatch, coal supply, and business decision-making with micro-states such as equipment health, coal quality fluctuations, and deviations in operating parameters, and lack multi-factor dynamic coupling and adaptive weight adjustment. This invention provides a method and system for monitoring coal-fired power generation capacity.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for monitoring coal-fired power generation capacity, comprising the following steps: Collect real-time operating data of coal-fired power units; Real-time operational data is input into a pre-built comprehensive assessment model of coal-fired power generation capacity; Based on power dispatching plans, market coal supply forecasts, and power plant operation decisions, calculate the power generation capacity value under macroeconomic constraints; Based on equipment parameters, coal quality parameters, and operating condition parameters, the health status of coal-fired power units, coal quality adaptability, and deviations from operating parameters are evaluated, and the power generation capacity under equipment condition constraints is calculated. The current real-time operating data is matched with a preset typical operating condition feature library, and the weight coefficients corresponding to the power generation capacity value under macro constraints and the power generation capacity value under equipment status limitations are dynamically determined based on the matching results. Based on the weighting coefficients, the power generation capacity values ​​under macro-constraints and those under equipment condition limitations are weighted and fused together. The pre-constructed comprehensive evaluation model for coal-fired power generation capacity is then trained to obtain the comprehensive power generation capacity evaluation value of the coal-fired unit.

[0006] A further improvement of this invention is that the real-time operating data includes equipment parameters, coal quality parameters, operating condition parameters, and environmental parameters.

[0007] A further improvement of this invention lies in the following specific method for calculating the power generation capacity value under macroeconomic constraints, based on power dispatching plans, market coal supply forecasts, and power plant operation decisions: Obtain the power dispatch plan, parse the power dispatch plan to obtain the grid dispatch instructions, regional load forecast and thermal power unit start-up mode, and calculate the upper limit of power generation capacity based on the power system demand-side constraints according to the grid dispatch instructions, regional load forecast and thermal power unit start-up mode. Obtain market coal supply forecasts, analyze market coal supply forecasts to obtain total market coal supply, regional coal transportation capacity, power plant coal inventory and contract fulfillment rate. Based on the total market coal supply, regional coal transportation capacity, power plant coal inventory and contract fulfillment rate, calculate the upper limit of power generation capacity based on fuel supply constraints. Obtain power plant operation decisions, analyze these decisions to obtain the on-grid electricity price, coal procurement cost, and power plant marginal revenue. Based on the on-grid electricity price, coal procurement cost, and power plant marginal revenue, calculate the upper limit of power generation capacity based on the power plant's economic benefit constraints. The minimum value among the upper limit of power generation capacity based on the demand side of the power system, the upper limit of power generation capacity based on the fuel supply side, and the upper limit of power generation capacity based on the economic benefits of power plants is determined as the power generation capacity value under macro constraints.

[0008] A further improvement of this invention lies in the following method for evaluating the equipment health status, coal quality adaptability, and deviations in operating parameters of a coal-fired power unit based on equipment parameters, coal quality parameters, and operating condition parameters, and calculating the power generation capacity value under equipment condition limitations: Acquire equipment parameters, coal quality parameters, and operating condition parameters. Based on the equipment parameters, identify the current operating condition through a clustering algorithm. Calculate the health status of key auxiliary equipment using a neural network model. Calculate the power generation capacity value under the equipment health status limit based on equipment redundancy configuration and health status. Based on coal quality parameters, combined with the maximum coal feed rate of the coal feeder and the output characteristics of the coal mill, the limiting values ​​of coal quality changes on boiler combustion stability and unit output are calculated. Monitor whether the main steam temperature, main steam pressure and reheat steam temperature in the operating conditions deviate from the preset safety threshold, and set the corresponding load limit or load reduction rate according to the deviation result; The minimum value among the power generation capacity value under equipment health condition restrictions, the restrictions on boiler combustion stability and unit output caused by coal quality changes, and the power generation capacity value corresponding to load restrictions is determined as the power generation capacity value under equipment condition restrictions.

[0009] A further improvement of this invention lies in the following method for dynamically determining the weighting coefficients corresponding to the power generation capacity value under macroscopic constraints and the power generation capacity value under equipment status limitations based on the matching results, by matching the current real-time operating data with a preset typical operating condition feature library: Obtain the characteristic vectors of different typical operating conditions, the power generation capacity value under macro constraints, the power generation capacity value under equipment status limitations, and the actual operating power generation capacity value, and construct a typical operating condition feature library. Extract the current operating condition feature vector corresponding to the current real-time operating data; Calculate the similarity between the current operating condition feature vector and the feature vectors of each typical operating condition in the typical operating condition feature library; Select the most similar typical working conditions as historical samples; Based on historical samples, the optimal weighting coefficients corresponding to the power generation capacity under macroscopic constraints and the power generation capacity under equipment condition constraints are solved using partial least squares regression.

[0010] A further improvement of this invention lies in the following specific method for weighted fusion of the power generation capacity value under macroscopic constraints and the power generation capacity value under equipment condition limitations, based on weighting coefficients: Obtain the weighting coefficients corresponding to the power generation capacity values ​​under macro constraints, and perform weighted processing on the power generation capacity values ​​under macro constraints based on the weighting coefficients corresponding to the power generation capacity values ​​under macro constraints. Obtain the weighting coefficients corresponding to the power generation capacity values ​​under equipment status constraints, and perform weighted processing on the power generation capacity values ​​under equipment status constraints based on the weighting coefficients corresponding to the power generation capacity values ​​under equipment status constraints. The power generation capacity value under the weighted macro-constraints and the power generation capacity value under the weighted equipment condition constraints are combined to obtain the comprehensive power generation capacity assessment value.

[0011] A further improvement of this invention is that the comprehensive power generation capacity assessment value obtained from each monitoring is compared with the subsequent actual output of the coal-fired unit to calculate the assessment error. When the evaluation error exceeds the preset threshold, the current real-time operating data and the corresponding actual output data will be added to the typical working condition feature library. The optimal weight coefficients are recalculated based on the updated typical working condition feature library.

[0012] A further improvement of this invention is that, after obtaining the comprehensive power generation capacity assessment value of the coal-fired unit, it also includes: Based on the comprehensive power generation capacity assessment value, retrieve historical operating conditions similar to the current operating conditions; Obtain the maximum load regulation rate of coal-fired power units under historical operating conditions; Based on the comprehensive power generation capacity assessment value, the maximum load regulation rate, and the preset time period, the maximum load that the coal-fired unit can carry in the future preset time period is predicted.

[0013] Secondly, the present invention provides a monitoring system for coal-fired power generation capacity, comprising the following steps: The data acquisition module is used to collect real-time operating data of coal-fired power units; The model building module is used to input real-time operating data into a pre-built comprehensive evaluation model of coal-fired power generation capacity; The macro-constraint calculation module is used to calculate the power generation capacity value under macro-constraints based on power dispatching plans, market coal supply forecasts, and power plant operation decisions. The status constraint calculation module is used to evaluate the equipment health status, coal quality adaptability, and deviation of operating parameters of coal-fired units based on equipment parameters, coal quality parameters, and operating condition parameters, and to calculate the power generation capacity value under equipment status constraints. The weight adjustment module is used to match the current real-time operating data with a preset typical operating condition feature library, and dynamically determine the weight coefficients corresponding to the power generation capacity value under macro constraints and the power generation capacity value under equipment status limitations based on the matching results. The fusion training module is used to weight and fuse the power generation capacity value under macro-constraints and the power generation capacity value under equipment condition limitations according to the weight coefficients, and to train the pre-built comprehensive evaluation model of coal-fired power generation capacity to obtain the comprehensive power generation capacity evaluation value of coal-fired units.

[0014] A further improvement of the present invention is that it also includes a visualization module for displaying in real time the equipment health status, macro-constraints, comprehensive power generation capacity assessment value and future maximum load prediction curve of the coal-fired unit, and issuing a warning message when any constraint triggers an alarm threshold.

[0015] Compared with the prior art, the present invention has the following beneficial effects: This invention achieves dynamic monitoring of the power generation capacity of coal-fired power units by collecting real-time operating data and inputting it into a pre-constructed comprehensive evaluation model of coal-fired power generation capacity. Compared with methods that rely solely on a single rated capacity or limiting factor, this invention considers macro-constraints such as power dispatch plans, market coal supply forecasts, and power plant management decisions, as well as micro-operating factors such as equipment parameters, coal quality parameters, and operating condition parameters. This provides a more comprehensive reflection of the actual power generation capacity of coal-fired power units during operation. By assessing equipment health status, coal quality adaptability, and deviations in operating parameters, it can promptly identify limitations on unit output caused by equipment deterioration, coal quality fluctuations, or abnormalities in key operating parameters, improving the real-time nature and security of power generation capacity assessment. Furthermore, this invention matches current real-time operating data with a typical operating condition feature library and dynamically determines the weighting coefficients corresponding to the power generation capacity values ​​under macro-constraints and those under equipment condition limitations based on the matching results. Weighted fusion is then performed, allowing the assessment results to adaptively adjust with changes in operating conditions, avoiding assessment biases caused by simply taking the minimum value or using fixed weights. Therefore, this invention can obtain a comprehensive power generation capacity assessment value that is more in line with the current actual operating conditions, providing more accurate and reliable data support for coal-fired unit operation control, power grid dispatching and power generation planning. Attached Figure Description

[0016] Figure 1 This is a flowchart of the present invention; Figure 2 This is a system diagram of the present invention. Detailed Implementation

[0017] To further understand the content of this invention, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments are merely illustrative and not limiting of the invention.

[0018] Example 1: See Figure 1 A method for monitoring coal-fired power generation capacity includes the following steps: S1 collects real-time operating data of coal-fired power units.

[0019] S2 inputs real-time operating data into a pre-built comprehensive evaluation model of coal-fired power generation capacity.

[0020] S3 calculates the power generation capacity value under macroeconomic constraints based on power dispatch plans, market coal supply forecasts, and power plant operation decisions.

[0021] S4 assesses the health status of coal-fired power units, coal quality adaptability, and deviations from operating parameters based on equipment parameters, coal quality parameters, and operating condition parameters, and calculates the power generation capacity value under equipment condition limitations.

[0022] S5 matches the current real-time operating data with a preset typical operating condition feature library, and dynamically determines the weight coefficients corresponding to the power generation capacity value under macro constraints and the power generation capacity value under equipment status limitations based on the matching results.

[0023] S6. Based on the weighting coefficients, the power generation capacity value under macro-constraints and the power generation capacity value under equipment condition constraints are weighted and fused together to train the pre-built comprehensive evaluation model of coal-fired power generation capacity, thereby obtaining the comprehensive power generation capacity evaluation value of the coal-fired unit.

[0024] Example 2: See Figure 2 A monitoring system for coal-fired power generation capacity includes the following steps: The data acquisition module is used to collect real-time operating data of coal-fired power units.

[0025] The model building module is used to input real-time operating data into a pre-built comprehensive evaluation model of coal-fired power generation capacity.

[0026] The macro-constraint calculation module is used to calculate the power generation capacity value under macro-constraints based on power dispatch plans, market coal supply forecasts, and power plant operation decisions.

[0027] The state constraint calculation module is used to evaluate the equipment health status, coal quality adaptability, and deviation of operating parameters of coal-fired power units based on equipment parameters, coal quality parameters, and operating condition parameters, and to calculate the power generation capacity value under equipment state constraints.

[0028] The weight adjustment module is used to match the current real-time operating data with a preset typical operating condition feature library, and dynamically determine the weight coefficients corresponding to the power generation capacity value under macro constraints and the power generation capacity value under equipment status limitations based on the matching results.

[0029] The fusion training module is used to weight and fuse the power generation capacity value under macro-constraints and the power generation capacity value under equipment condition limitations according to the weight coefficients, and to train the pre-built comprehensive evaluation model of coal-fired power generation capacity to obtain the comprehensive power generation capacity evaluation value of coal-fired units.

[0030] Example 3: This embodiment provides a method for monitoring coal-fired power generation capacity, which includes the following steps: Step S1: Collect real-time operating data of the coal-fired power unit.

[0031] Real-time operating data of the coal-fired power unit is collected through a data acquisition module. This real-time operating data includes equipment parameters, coal quality parameters, operating condition parameters, and environmental parameters. Specifically, the data acquisition module can connect to SIS systems, DCS systems, and other data systems to achieve real-time acquisition of the coal-fired power unit's operating status.

[0032] Table 1 Real-time running data collection content

[0033] Step S2: Input the real-time operating data into the pre-built comprehensive evaluation model of coal-fired power generation capacity.

[0034] The model building module inputs real-time operational data into a pre-built comprehensive evaluation model for coal-fired power generation capacity. This comprehensive evaluation model includes a macro-constraint calculation module for handling macro-constraint factors, a state constraint calculation module for handling equipment state limitations, a weight adjustment module for dynamically determining weight coefficients, and a fusion training module for weighted fusion and model training.

[0035] Table 2. Modules and Output Results of the Comprehensive Assessment Model for Coal-fired Power Generation Capacity

[0036] Step S3: Based on the power dispatch plan, market coal supply forecast, and power plant operation decisions, calculate the power generation capacity value under macro constraints.

[0037] The macro-constraint calculation module calculates macro-level constraints, which may include power supply constraint calculation, coal supply constraint calculation, and business decision constraint calculation.

[0038] First, the power dispatch plan is obtained and parsed to obtain the grid dispatch instructions, regional load forecasts, and thermal power unit start-up methods. Based on the grid dispatch instructions, regional load forecasts, and thermal power unit start-up methods, the upper limit of power generation capacity based on the demand-side constraints of the power system is calculated, denoted as . If the power grid dispatching instruction explicitly requires load limiting, then The load limit value corresponding to the scheduling instruction is directly retrieved.

[0039] Secondly, market coal supply forecasts are obtained and analyzed to determine the total available coal supply, regional coal transportation capacity, power plant coal inventory, and contract fulfillment rate. This is based on current on-site coal inventory. Future contract coal delivery plans Regional coal transportation corridor guarantee capacity index Dynamically predict the total amount of coal available for power generation in the future. Combined with the current coal consumption rate for power generation of the units. Calculate the upper limit of power generation capacity based on fuel supply-side constraints. :

[0040] in, This indicates the total amount of coal available for power generation in the near future. This represents the current coal consumption rate for power generation by the generating unit. It also considers the safety threshold for inventory levels. When the current coal inventory in the plant Below the inventory safety threshold At that time, the upper limit of power generation capacity based on fuel supply-side constraints It is further limited by the number of days of inventory available.

[0041] Secondly, the power plant's operational decisions are obtained and analyzed to derive the on-grid electricity price, coal procurement cost, and marginal revenue of the power plant. This is based on the current on-grid electricity price. and the price of coal delivered to the plant Calculate the marginal profit per unit of electricity generated. .when A negative value indicates that power generation is unprofitable. Based on the power plant's operational decisions, the power plant can choose to reduce power generation to mitigate losses. This leads to the upper limit of power generation capacity based on the power plant's economic constraints. .

[0042] Finally, the upper limit of power generation capacity will be based on the demand-side constraints of the power system. Upper limit of power generation capacity based on fuel supply-side constraints and the upper limit of power generation capacity based on the economic benefits of power plants The minimum value in the range is determined as the power generation capacity value under macroscopic constraints. :

[0043] Step S4: Based on equipment parameters, coal quality parameters, and operating condition parameters, assess the equipment health status, coal quality adaptability, and deviation status of operating parameters of the coal-fired unit, and calculate the power generation capacity value under equipment condition limitations.

[0044] The state constraint calculation module calculates the micro-equipment state of the coal-fired unit. The state constraint calculation module may include equipment health status calculation, coal quality adaptability calculation, and operating parameter deviation calculation.

[0045] First, equipment parameters, coal quality parameters, and operating condition parameters are acquired. Based on the equipment parameters, the current operating condition is identified using a clustering algorithm. In one implementation, [the algorithm] utilizes... A Gaussian Mixture Model (GMM) is used to cluster historical operating data, dividing it into several typical operating conditions, for example, around 100. For each typical operating condition, a backpropagation (BP) neural network is used to train and obtain the normal operating parameter ranges for each key auxiliary equipment. Subsequently, the current operating condition is matched with the most similar typical operating condition, and the real-time health status of each key auxiliary equipment is obtained by calculating the cosine similarity between the current parameter vector and the normal parameter vector. ,in ∈[0,1].

[0046] The number of unavailable devices is counted based on equipment redundancy configurations, including one active and one standby, two active and one standby, etc. When the number of unavailable devices of the same type exceeds the capacity of the redundancy configuration, the unit output is determined to be limited by the equipment status. The power generation capacity value under equipment health status limitations is... It can be calculated based on a combination of equipment redundancy and equipment health, for example:

[0047] in, This indicates the power generation capacity value under the limitations of the equipment's health status. Indicates the rated load of the coal-fired power unit. Indicates the first Real-time health status of key auxiliary equipment. Indicates the first The weight of the impact of key auxiliary equipment on the unit output.

[0048] Secondly, based on coal quality parameters, combined with the maximum coal feed rate of the coal feeder and the output characteristics of the coal mill, the limiting values ​​of coal quality changes on boiler combustion stability and unit output are calculated. Specifically, this is based on the lower heating value of the coal fed into the furnace in real time. volatile matter Coal quality parameters are used to assess boiler combustion stability and pulverizer output. When coal quality deteriorates, the boiler may not be able to reach its rated evaporation capacity even when the coal feeder is running at full speed. Power generation capacity under coal quality constraints. The maximum total coal feeding rate of the coal feeder Boiler thermal efficiency under current coal quality and turbine heat rate Jointly determined:

[0049] in, This represents the power generation capacity value under coal quality restrictions. This indicates the maximum total coal feeding rate of the coal feeder. This indicates the net calorific value of the coal fed into the furnace in real time. This indicates the boiler thermal efficiency under the current coal quality. This indicates the turbine heat rate. When the volatile matter content is too low or the ash content is too high, the load reduction logic is further triggered.

[0050] Secondly, the system monitors whether the main steam temperature, main steam pressure, and reheat steam temperature deviate from preset safety thresholds, and sets corresponding load limits or load reduction rates based on the deviations. Furthermore, it can also monitor key parameters such as condenser back pressure and generator temperature. If any key parameter exceeds the normal operating range, or its corresponding real-time health level falls below a preset threshold, the system issues an alarm and sets load limits according to preset rules. For example, when the main steam temperature drops by 10°C, a forced load reduction of 5% is implemented. When the boiler main fuel trip (MFT) or turbine emergency trip system (ETS) alarm is triggered, the corresponding power generation capacity will be limited by the load. Set to 0 immediately.

[0051] Finally, the power generation capacity value under the equipment health status limit. Limits on boiler combustion stability and unit output due to changes in coal quality and the power generation capacity value corresponding to the load limit The minimum value in the range is determined as the power generation capacity value under equipment condition limitations. :

[0052] Step S5: Match the current real-time operating data with the preset typical operating condition feature library, and dynamically determine the weight coefficients corresponding to the power generation capacity value under macro constraints and the power generation capacity value under equipment status limitations based on the matching results.

[0053] The weight adjustment module constructs and calls a typical operating condition feature library. The weight adjustment module first obtains the operating condition feature vectors and the power generation capacity values ​​under macroscopic constraints corresponding to different typical operating conditions. Power generation capacity under equipment condition limitations and actual operating power generation capacity value A typical operating condition feature library is constructed. The operating condition feature vector can be composed of features such as load, ambient temperature, coal quality, and the health status of key equipment.

[0054] When it is necessary to assess the power generation capacity at the current moment, the weight adjustment module extracts the current operating condition feature vector corresponding to the current real-time operating data. The feature vector of the current working condition is calculated using Euclidean distance or cosine similarity algorithms. The similarity between the typical working condition feature vectors and the typical working condition feature vectors in the typical working condition feature library is used to select a preset number of typical working conditions with the highest similarity as historical samples. In one implementation, the most similar typical working conditions are selected. A typical working condition, for example =10.

[0055] Based on the selected historical samples, the partial least squares regression (PLSR) method is used to solve for the power generation capacity value under macroscopic constraints. Power generation capacity under equipment condition limitations The corresponding optimal weighting coefficients. Specifically, with and As the independent variable, the actual operating power generation capacity value As the dependent variable, the following linear combination model is established:

[0056] in, This represents the weighting coefficient corresponding to the power generation capacity value under macroeconomic constraints. This represents the weighting coefficient corresponding to the power generation capacity value under equipment condition limitations. This represents the error term. Partial least squares regression can extract components with strong explanatory power for the dependent variable when multicollinearity exists among the independent variables, thereby obtaining the optimal fusion weights for macroscopic constraints and equipment status under the current operating conditions.

[0057] Step S6: Based on the weighting coefficients, the power generation capacity value under macro constraints and the power generation capacity value under equipment condition limitations are weighted and fused together to train the pre-constructed comprehensive evaluation model of coal-fired power generation capacity, thereby obtaining the comprehensive power generation capacity evaluation value of the coal-fired unit.

[0058] The weighting coefficients corresponding to the power generation capacity value under macroscopic constraints are obtained through the fusion training module. And based on this weighting coefficient, the power generation capacity value under macroeconomic constraints Perform weighted processing; obtain the weighting coefficients corresponding to the power generation capacity values ​​under equipment status constraints. And based on this weighting coefficient, the power generation capacity value under equipment condition constraints is calculated. The power generation capacity is then weighted; subsequently, the weighted power generation capacity value under macro-constraints and the weighted power generation capacity value under equipment condition constraints are merged to obtain the comprehensive power generation capacity assessment value. :

[0059] Through the above process, the integrated training module no longer simply takes the minimum value of a single limiting factor, but dynamically determines the degree of influence of macro-constraints and equipment status on the final power generation capacity under the current operating conditions based on actual operating experience under similar historical conditions, thereby achieving the training and optimization of the comprehensive evaluation model for coal-fired power generation capacity.

[0060] Step S7: Predict the maximum load that the coal-fired unit can carry in the future within a preset time period.

[0061] After obtaining the comprehensive power generation capacity assessment value Subsequently, based on the comprehensive power generation capacity assessment value Search for historical operating conditions similar to the current operating conditions to obtain the maximum load regulation rate of the coal-fired unit under those historical conditions. Based on the comprehensive power generation capacity assessment value Maximum load regulation rate and preset time period Predicting the maximum load that coal-fired power units can carry within a predetermined time period in the future. :

[0062] in, This indicates the maximum load that can be carried within a preset time period in the future. In one implementation, this represents a preset time period. It lasts for 15 minutes; This represents the maximum load regulation rate of the unit retrieved from similar historical operating conditions, in MW / min.

[0063] Example 4: This embodiment provides a monitoring system for coal-fired power generation capacity. The system includes a data acquisition module, a model building module, a macro-constraint calculation module, a state constraint calculation module, a weight adjustment module, a fusion training module, and a visualization display module.

[0064] The data acquisition module is used to collect real-time operating data of the coal-fired power unit. This real-time operating data includes equipment parameters, coal quality parameters, operating condition parameters, and environmental parameters.

[0065] The model building module is used to input real-time operating data into a pre-built comprehensive evaluation model of coal-fired power generation capacity. The comprehensive evaluation model of coal-fired power generation capacity is used to perform integrated calculations on the power generation capacity value under macro-constraints and the power generation capacity value under equipment condition limitations, and output a comprehensive power generation capacity evaluation value.

[0066] The macro-constraint calculation module is used to calculate the power generation capacity value under macro-constraints based on power dispatch plans, market coal supply forecasts, and power plant operation decisions. Specifically, the macro-constraint calculation module is used to calculate the upper limit of power generation capacity based on power system demand-side constraints, the upper limit of power generation capacity based on fuel supply-side constraints, and the upper limit of power generation capacity based on power plant economic benefit constraints, and determines the minimum value among the three as the power generation capacity value under macro-constraints.

[0067] The condition constraint calculation module is used to assess the health status, coal quality adaptability, and deviations from operating parameters of coal-fired power units based on equipment parameters, coal quality parameters, and operating condition parameters, and to calculate the power generation capacity value under equipment condition constraints. Specifically, the condition constraint calculation module calculates the power generation capacity value under equipment health condition constraints, the constraints on boiler combustion stability and unit output caused by coal quality changes, and the power generation capacity value corresponding to load constraints, and determines the minimum value among the three as the power generation capacity value under equipment condition constraints.

[0068] The weight adjustment module is used to match the current real-time operating data with a preset typical operating condition feature library, and dynamically determine the weight coefficients corresponding to the power generation capacity value under macro constraints and the power generation capacity value under equipment status limitations based on the matching results.

[0069] The fusion training module is used to weight and fuse the power generation capacity value under macro-constraints and the power generation capacity value under equipment condition constraints according to the weight coefficients, and to train the pre-built comprehensive evaluation model of coal-fired power generation capacity to obtain the comprehensive power generation capacity evaluation value of coal-fired units.

[0070] The visualization module is used to display the equipment health status, macro-constraints, comprehensive power generation capacity assessment value, and future maximum load forecast curve of coal-fired units in real time, and to issue early warning information when any constraint triggers the alarm threshold.

[0071] Example 5 To further improve the long-term accuracy and adaptability of the comprehensive assessment model for coal-fired power generation capacity, this embodiment also includes a fusion training module used to integrate the comprehensive power generation capacity assessment values ​​obtained from each monitoring session. With the actual output of coal-fired units Compare and calculate the evaluation error. :

[0072] When the evaluation error When the threshold is exceeded, a weight correction mechanism is triggered. In one implementation, the preset threshold is 5%. After the weight correction mechanism is triggered, the current operating condition feature vector corresponding to the current real-time operating data is adjusted. Power generation capacity under macroeconomic constraints Power generation capacity under equipment condition limitations and actual operating power generation capacity value A new set of samples is added to the typical operating condition feature library. Subsequently, based on the updated typical operating condition feature library, the optimal weight coefficients are recalculated. This enables the comprehensive evaluation model of coal-fired power generation capacity to adapt to long-term changes such as power plant equipment aging, coal source changes, and scheduling strategy adjustments, thereby improving the model's continuous evaluation capability.

[0073] Example 6: At the system deployment level, to achieve efficient data processing and real-time response, this embodiment adopts a cloud-edge collaborative deployment approach. Edge computing nodes are deployed on the power plant side, where the core computing tasks of the data acquisition module and the state constraint calculation module are deployed. The edge computing nodes are used to rapidly process high-frequency DCS data, perform real-time assessments of equipment health status, coal quality adaptability, and deviations from operating parameters, and obtain the power generation capacity value under equipment state constraints. and will Key alarm information is uploaded to the cloud.

[0074] The cloud-based deployment includes a model building module, a macro-constraint calculation module, a weight adjustment module, and a fusion training module. The cloud is used to process macro-level data related to grid dispatch, fuel market, and operational decisions, and to perform weight calculations and model training tasks. The cloud calculates the power generation capacity value under macro-constraints. After adjusting for weighting factors, the results are sent to edge computing nodes, which or the cloud then complete the comprehensive power generation capacity assessment. The calculation and display.

[0075] By employing the aforementioned cloud-edge collaboration approach, we can ensure the real-time nature of equipment status limitation calculations while fully utilizing the computing and storage capabilities of the cloud to process macroscopic data and model training tasks, thereby improving the response speed and assessment accuracy of the coal-fired power generation capacity monitoring system.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for monitoring coal-fired power generation capacity, characterized in that, Includes the following steps: Collect real-time operating data of coal-fired power units; Real-time operational data is input into a pre-built comprehensive assessment model of coal-fired power generation capacity; Based on power dispatching plans, market coal supply forecasts, and power plant operation decisions, calculate the power generation capacity value under macroeconomic constraints; Based on equipment parameters, coal quality parameters, and operating condition parameters, the health status of coal-fired power units, coal quality adaptability, and deviations from operating parameters are evaluated, and the power generation capacity under equipment condition constraints is calculated. The current real-time operating data is matched with a preset typical operating condition feature library, and the weight coefficients corresponding to the power generation capacity value under macro constraints and the power generation capacity value under equipment status limitations are dynamically determined based on the matching results. Based on the weighting coefficients, the power generation capacity values ​​under macro-constraints and those under equipment condition limitations are weighted and fused together. The pre-constructed comprehensive evaluation model for coal-fired power generation capacity is then trained to obtain the comprehensive power generation capacity evaluation value of the coal-fired unit.

2. The method for monitoring coal-fired power generation capacity according to claim 1, characterized in that, Real-time operational data includes equipment parameters, coal quality parameters, operating condition parameters, and environmental parameters.

3. The method for monitoring coal-fired power generation capacity according to claim 1, characterized in that, Based on power dispatching plans, market coal supply forecasts, and power plant operational decisions, the specific method for calculating the power generation capacity value under macroeconomic constraints is as follows: Obtain the power dispatch plan, parse the power dispatch plan to obtain the grid dispatch instructions, regional load forecast and thermal power unit start-up mode, and calculate the upper limit of power generation capacity based on the power system demand-side constraints according to the grid dispatch instructions, regional load forecast and thermal power unit start-up mode. Obtain market coal supply forecasts, analyze market coal supply forecasts to obtain total market coal supply, regional coal transportation capacity, power plant coal inventory and contract fulfillment rate. Based on the total market coal supply, regional coal transportation capacity, power plant coal inventory and contract fulfillment rate, calculate the upper limit of power generation capacity based on fuel supply constraints. Obtain power plant operation decisions, analyze these decisions to obtain the on-grid electricity price, coal procurement cost, and power plant marginal revenue. Based on the on-grid electricity price, coal procurement cost, and power plant marginal revenue, calculate the upper limit of power generation capacity based on the power plant's economic benefit constraints. The minimum value among the upper limit of power generation capacity based on the demand side of the power system, the upper limit of power generation capacity based on the fuel supply side, and the upper limit of power generation capacity based on the economic benefits of power plants is determined as the power generation capacity value under macro constraints.

4. The method for monitoring coal-fired power generation capacity according to claim 1, characterized in that, Based on equipment parameters, coal quality parameters, and operating condition parameters, the health status of coal-fired power units, coal quality adaptability, and deviations from operating parameters are assessed. The specific method for calculating the power generation capacity under equipment condition constraints is as follows: Acquire equipment parameters, coal quality parameters, and operating condition parameters. Based on the equipment parameters, identify the current operating condition through a clustering algorithm. Calculate the health status of key auxiliary equipment using a neural network model. Calculate the power generation capacity value under the equipment health status limit based on equipment redundancy configuration and health status. Based on coal quality parameters, combined with the maximum coal feed rate of the coal feeder and the output characteristics of the coal mill, the limiting values ​​of coal quality changes on boiler combustion stability and unit output are calculated. Monitor whether the main steam temperature, main steam pressure and reheat steam temperature in the operating conditions deviate from the preset safety threshold, and set the corresponding load limit or load reduction rate according to the deviation result; The minimum value among the power generation capacity value under equipment health condition restrictions, the restrictions on boiler combustion stability and unit output caused by coal quality changes, and the power generation capacity value corresponding to load restrictions is determined as the power generation capacity value under equipment condition restrictions.

5. The method for monitoring coal-fired power generation capacity according to claim 1, characterized in that, The specific method for matching current real-time operating data with a preset typical operating condition feature library, and dynamically determining the weighting coefficients corresponding to the power generation capacity value under macro constraints and the power generation capacity value under equipment condition limitations based on the matching results is as follows: Obtain the characteristic vectors of different typical operating conditions, the power generation capacity value under macro constraints, the power generation capacity value under equipment status limitations, and the actual operating power generation capacity value, and construct a typical operating condition feature library. Extract the current operating condition feature vector corresponding to the current real-time operating data; Calculate the similarity between the current operating condition feature vector and the feature vectors of each typical operating condition in the typical operating condition feature library; Select the most similar typical working conditions as historical samples; Based on historical samples, the optimal weighting coefficients corresponding to the power generation capacity under macroscopic constraints and the power generation capacity under equipment condition constraints are solved using partial least squares regression.

6. The method for monitoring coal-fired power generation capacity according to claim 1, characterized in that, The specific method for weighted fusion of power generation capacity under macroscopic constraints and power generation capacity under equipment condition limitations, based on weighting coefficients, is as follows: Obtain the weighting coefficients corresponding to the power generation capacity values ​​under macro constraints, and perform weighted processing on the power generation capacity values ​​under macro constraints based on the weighting coefficients corresponding to the power generation capacity values ​​under macro constraints. Obtain the weighting coefficients corresponding to the power generation capacity values ​​under equipment status constraints, and perform weighted processing on the power generation capacity values ​​under equipment status constraints based on the weighting coefficients corresponding to the power generation capacity values ​​under equipment status constraints. The power generation capacity value under the weighted macro-constraints and the power generation capacity value under the weighted equipment condition constraints are combined to obtain the comprehensive power generation capacity assessment value.

7. The method for monitoring coal-fired power generation capacity according to claim 1, characterized in that, The comprehensive power generation capacity assessment value obtained from each monitoring is compared with the subsequent actual output of the coal-fired unit to calculate the assessment error; When the evaluation error exceeds the preset threshold, the current real-time operating data and the corresponding actual output data will be added to the typical working condition feature library. The optimal weight coefficients are recalculated based on the updated typical working condition feature library.

8. The method for monitoring coal-fired power generation capacity according to claim 1, characterized in that, After obtaining the comprehensive power generation capacity assessment value of the coal-fired unit, it also includes: Based on the comprehensive power generation capacity assessment value, retrieve historical operating conditions similar to the current operating conditions; Obtain the maximum load regulation rate of coal-fired power units under historical operating conditions; Based on the comprehensive power generation capacity assessment value, the maximum load regulation rate, and the preset time period, the maximum load that the coal-fired unit can carry in the future preset time period is predicted.

9. A monitoring system for coal-fired power generation capacity, characterized in that, Includes the following steps: The data acquisition module is used to collect real-time operating data of coal-fired power units; The model building module is used to input real-time operating data into a pre-built comprehensive evaluation model of coal-fired power generation capacity; The macro-constraint calculation module is used to calculate the power generation capacity value under macro-constraints based on power dispatching plans, market coal supply forecasts, and power plant operation decisions. The status constraint calculation module is used to evaluate the equipment health status, coal quality adaptability, and deviation of operating parameters of coal-fired units based on equipment parameters, coal quality parameters, and operating condition parameters, and to calculate the power generation capacity value under equipment status constraints. The weight adjustment module is used to match the current real-time operating data with a preset typical operating condition feature library, and dynamically determine the weight coefficients corresponding to the power generation capacity value under macro constraints and the power generation capacity value under equipment status limitations based on the matching results. The fusion training module is used to weight and fuse the power generation capacity value under macro-constraints and the power generation capacity value under equipment condition constraints according to the weight coefficients, and to train the pre-built comprehensive evaluation model of coal-fired power generation capacity to obtain the comprehensive power generation capacity evaluation value of coal-fired units.

10. A monitoring system for coal-fired power generation capacity according to claim 9, characterized in that, It also includes a visualization module, which displays the equipment health status, macro-constraints, comprehensive power generation capacity assessment value, and future maximum load forecast curve of the coal-fired unit in real time, and issues a warning message when any constraint triggers the alarm threshold.

Images