Method, system, equipment and medium for predicting energy consumption index of thermal power plant by using yield

Abstract

The invention discloses a method, a system, equipment and a medium for predicting thermal power plant energy consumption indexes by using yield, and belongs to the technical field of thermal power plant energy management. The method comprises the following steps: obtaining thermal power plant steam turbine performance test data, and determining parameter types of the steam turbine performance test data; establishing a heat balance equation set based on the first law of thermodynamics according to the parameter type; obtaining thermal power plant yield plan data; performing calculation processing on the heat balance equation set and the yield plan data to obtain thermal power plant operation parameters; and calculating a thermal power plant energy consumption index according to the thermal power plant operation parameters, wherein the thermal power plant energy consumption index is used for making a fuel purchase plan and optimizing a unit operation mode. According to the method, the accuracy and adaptability of energy consumption index prediction are improved, the calculation process is simplified, the prediction time is shortened, a scientific basis is provided for making a fuel purchase plan and optimizing a unit operation mode, and the economic benefits of a thermal power plant are improved.

Description

Technical Field

[0001] This invention relates to the field of energy management technology for thermal power plants, specifically to methods, systems, equipment, and media for predicting energy consumption indicators of thermal power plants using output. Background Technology

[0002] Predicting energy consumption indicators for combined heat and power (CHP) plants is a key technology in energy management, crucial for optimizing plant operation and improving resource utilization efficiency. Traditional CHP plant energy consumption prediction methods primarily rely on empirical formulas and historical data regression models. From linear regression models to neural network prediction models, and more recently, support vector machines and deep learning models, prediction techniques have continuously evolved. Currently, widely used energy consumption prediction methods can be categorized into three main types: physical model-based methods, data-driven methods, and hybrid methods that combine physical models and data. Physical model-based methods construct thermodynamic system models based on fundamental thermodynamic principles and predict energy consumption indicators by solving heat balance equations. Data-driven methods utilize historical operating data and employ statistical learning or machine learning algorithms to build prediction models. Hybrid methods attempt to combine the advantages of both, fitting data under the constraints of a physical model to improve prediction accuracy.

[0003] However, existing technologies still have many shortcomings in predicting energy consumption indicators for thermal power plants. Physical model-based methods often struggle to accurately reflect operating conditions under aging equipment and off-design conditions, and are poorly adaptable to frequently changing load conditions. Data-driven methods, while capable of capturing complex nonlinear relationships, lack physical interpretation and require high-quality and abundant data; their prediction accuracy decreases when data is scarce or operating conditions change significantly. Hybrid methods, attempting to integrate the advantages of both approaches, often struggle to effectively balance physical constraints and data fitting, leading to increased model complexity and reduced practicality. Particularly when production plans are frequently adjusted, existing methods cannot quickly and accurately predict energy consumption changes, failing to meet the real-time decision-making needs of thermal power plants. Furthermore, existing technologies often neglect the coupling relationship between turbine performance parameters and production plan data, failing to reflect the impact of working fluid parameter changes on energy consumption indicators, thus affecting the scientific rigor of fuel procurement and unit operation optimization decisions. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by this invention is: how to solve the problems of poor model adaptability, low prediction accuracy and high computational complexity in existing thermal power plant energy consumption prediction technology, so as to meet the rapid prediction needs of thermal power plants under variable operating conditions?

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a method for predicting the energy consumption index of a thermal power plant using output, comprising the following steps: acquiring turbine performance test data of the thermal power plant; determining the parameter type of the turbine performance test data; establishing a set of heat balance equations based on the first law of thermodynamics according to the parameter type; acquiring thermal power plant output plan data; performing calculations on the set of heat balance equations and the output plan data to obtain thermal power plant operating parameters; and calculating the thermal power plant energy consumption index based on the thermal power plant operating parameters, wherein the thermal power plant energy consumption index is used for fuel procurement planning and unit operation mode optimization.

[0007] As a preferred embodiment of the method for predicting the energy consumption index of a thermal power plant using output as described in this invention, the step of obtaining the performance test data of the thermal power plant turbine includes: extracting the operation record of the most recent performance test of the turbine from the distributed control system of the thermal power plant to obtain the performance test data of the thermal power plant turbine; standardizing the performance test data of the thermal power plant turbine; and determining the parameter type of the turbine performance test data based on the standardized performance test data of the thermal power plant turbine.

[0008] As a preferred embodiment of the method for predicting the energy consumption index of a thermal power plant using output as described in this invention, the step of establishing a set of heat balance equations based on the first law of thermodynamics according to the parameter type includes: extracting thermodynamic parameters from the parameter type; establishing an energy conservation relationship between the thermodynamic parameters based on the first law of thermodynamics; expressing the energy conservation relationship as the set of heat balance equations and calibrating the coefficients of the set of heat balance equations. The beneficial effects of this preferred embodiment are: establishing an energy conservation relationship between thermodynamic parameters based on the first law of thermodynamics, expressing it as a set of heat balance equations, and calibrating the coefficients form a mathematical model that accurately reflects the energy conversion process of a thermal power plant. This model not only has a solid theoretical foundation but also achieves effective integration with actual operating conditions through coefficient calibration, significantly improving the model's adaptability to complex operating conditions and its prediction accuracy.

[0009] As a preferred embodiment of the method for predicting the energy consumption index of a thermal power plant using output as described in this invention, the step of obtaining thermal power plant output plan data includes: obtaining basic output data and environmental impact factor data from the thermal power plant production management system; verifying and standardizing the basic output data and the environmental impact factor data to generate a standard output plan dataset for heat balance calculation.

[0010] As a preferred embodiment of the method for predicting the energy consumption index of a thermal power plant using production output as described in this invention, the step of processing the heat balance equations and the production plan data includes: substituting the production plan data into the heat balance equations and constructing a solution matrix; solving the matrix using an iterative algorithm to obtain the solution result; determining the operating parameters of the thermal power plant based on the solution result, and verifying the validity of the operating parameters. The beneficial effects of this preferred embodiment are: by substituting the production plan data into the heat balance equations and constructing a solution matrix, using an iterative algorithm to solve the equations and verify their validity, efficient calculation of parameters for complex thermal systems is achieved. This method integrates theoretical models with actual data, finds the optimal solution through iterative optimization, effectively avoids the accumulation of calculation errors, and ensures the accuracy and stability of the predicted operating parameters.

[0011] As a preferred embodiment of the method for predicting the energy consumption index of a thermal power plant using output as described in this invention, the step of solving the matrix using an iterative algorithm includes: setting initial iteration values ​​and iteration termination conditions; executing the iterative calculation process, calculating the deviation between the intermediate results of the iterative calculation process and historical operating data; if the deviation exceeds a preset threshold, adjusting the correction coefficient and re-executing the iterative calculation process; if the deviation does not exceed the preset threshold, recording the final solution value and generating the thermal power plant operating parameters; the correction coefficient includes a thermal efficiency correction coefficient, a working fluid flow correction coefficient, and a thermodynamic parameter correction coefficient; the iterative algorithm further includes establishing a response surface model to accelerate iterative convergence, setting a convergence acceleration factor to adjust the iteration step size, dynamically adjusting the correction coefficient to adapt to different operating conditions, and fusing multiple iteration results using a weighted average method. The beneficial effects of this preferred technical solution are as follows: by setting the initial value and termination condition of the iteration, dynamically adjusting the correction coefficient, and accelerating convergence through the response surface model, an adaptive iterative solution mechanism is constructed. This mechanism can intelligently adjust the calculation process according to the deviation between the calculation results and historical data, which not only improves the solution efficiency, but also enhances the model's adaptability to different operating conditions, ensuring reliable calculation results in the complex and ever-changing operating environment of thermal power plants.

[0012] As a preferred embodiment of the method for predicting the energy consumption index of a thermal power plant using output as described in this invention, the step of estimating the energy consumption index of the thermal power plant based on the operating parameters of the thermal power plant includes: extracting boiler efficiency, steam production, turbine cylinder efficiency, and power generation output coefficient from the operating parameters of the thermal power plant; calculating the coal consumption for power supply based on the boiler efficiency and the steam production; calculating the plant power consumption rate based on the turbine cylinder efficiency and the power generation output coefficient; collecting multiple sets of operating data under different operating conditions; constructing an operating condition-energy consumption correspondence model based on the multiple sets of operating data under different operating conditions; generating an energy consumption curve based on the operating condition-energy consumption correspondence model; analyzing the changing trend of the energy consumption curve and identifying the energy consumption sensitive interval; determining the optimal operating condition point; and generating a fuel procurement plan suggestion and a unit operation mode optimization scheme based on the optimal operating condition point. The beneficial effects of this preferred technical solution are as follows: by extracting key operating parameters to calculate energy consumption indicators and constructing an operating condition-energy consumption correspondence model based on multiple sets of operating condition data, a comprehensive analysis and optimization of the energy consumption characteristics of thermal power plants is realized. This solution can not only accurately predict the energy consumption level of a single operating condition, but also draw a complete energy consumption curve, identify energy consumption sensitive intervals, and determine the optimal operating condition point, providing a comprehensive and scientific decision-making basis for fuel procurement planning and unit operation mode optimization.

[0013] Another object of the present invention is to provide a system for predicting the energy consumption index of thermal power plants using output.

[0014] To address the aforementioned technical problems, this invention provides the following technical solution: a system for predicting the energy consumption index of a thermal power plant using production output, comprising: a data acquisition module for acquiring turbine performance test data of a thermal power plant and determining the parameter type of the turbine performance test data; an equation construction module for establishing a set of heat balance equations based on the first law of thermodynamics according to the parameter type; a plan acquisition module for acquiring thermal power plant production plan data as the main variable in the method of predicting the energy consumption index of a thermal power plant using production output; a parameter calculation module for performing calculations on the heat balance equations and the production plan data to obtain the operating parameters of the thermal power plant; and an index estimation module for estimating the energy consumption index of the thermal power plant based on the operating parameters of the thermal power plant.

[0015] The present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, characterized in that the processor executes the computer program to implement the steps of the method for predicting the energy consumption index of a thermal power plant using output.

[0016] The present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of the method for predicting the energy consumption index of a thermal power plant using production output.

[0017] The beneficial effects of this invention are as follows: By acquiring turbine performance test data and determining parameter types, this invention overcomes the limitations of traditional methods that rely on historical data statistical regression, thus giving the prediction model a stronger physical interpretation capability. Based on the first law of thermodynamics, a set of heat balance equations is established. Compared to purely data-driven methods, this physical model can more accurately reflect the inherent laws in the energy conversion process, improving the model's generalization ability. Using production plan data as the main variable solves the problem that traditional physical models are difficult to adapt to frequently changing load conditions, enhancing the model's adaptability to different operating conditions. Through the calculation and processing of the heat balance equations and production plan data, the correlation calculation between various parameters in the thermal system is realized, avoiding the cumulative error caused by single-parameter prediction. Based on the operating parameters of the thermal power plant, energy consumption indicators are extrapolated, establishing a bridge from process parameters to economic indicators, allowing the prediction results to directly serve management decisions. In summary, this invention, through the organic combination of physical models and actual production data, significantly improves prediction accuracy while maintaining computational simplicity. Especially under conditions of frequent changes in operating conditions, the improvement in prediction accuracy exceeds the expectations of conventional technological advancements, providing more reliable decision support for fuel procurement and operation optimization in thermal power plants. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 The above is a flowchart of a method for predicting the energy consumption index of a thermal power plant using output, provided as an embodiment of the present invention. Detailed Implementation

[0020] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0021] Example 1, referring to Figure 1 This is the first embodiment of the present invention, which provides a method for predicting the energy consumption index of a thermal power plant using output, including:

[0022] S100: Obtain performance test data of steam turbines in thermal power plants and determine the parameter types of the steam turbine performance test data;

[0023] S200: Establish a set of heat balance equations based on the first law of thermodynamics according to the parameter type;

[0024] S300: Obtain production plan data for thermal power plants and use the production plan data as the main variable in the method of using production to predict the energy consumption index of thermal power plants;

[0025] S400: The thermal balance equations and production plan data are processed to obtain the operating parameters of the thermal power plant;

[0026] S500: Calculates the energy consumption index of a thermal power plant based on its operating parameters. The energy consumption index is used for fuel procurement planning and unit operation optimization.

[0027] It should be noted that the operation of a combined heat and power (CHP) plant is a complex thermodynamic process. Traditional energy consumption forecasting methods mainly rely on empirical formulas or simple regression models, which are insufficient to accurately reflect energy consumption variations under different operating conditions. Especially when power generation and heating supply fluctuate frequently, traditional forecasting methods have significant errors. Furthermore, the efficiency of equipment such as boilers and turbines in CHP plants changes over time, making energy consumption forecasting even more difficult. In addition, external factors such as different fuel qualities and ambient temperature also significantly impact the energy consumption of CHP plants. Therefore, accurate forecasting of CHP plant energy consumption indicators has significant economic and technical value.

[0028] Therefore, to address the aforementioned energy consumption prediction problem, a set of heat balance equations based on the first law of thermodynamics is constructed through steps S100-S500. Using the final performance test data of the steam turbine as a benchmark, and combining it with planned production data such as power generation and heat supply, accurate calculations of operating parameters such as boiler efficiency, steam production, and turbine cylinder efficiency are achieved. Furthermore, energy consumption indicators such as coal consumption for power supply and plant power consumption rate are derived, providing a scientific basis for the formulation of fuel procurement plans and the optimization of unit operation modes in thermal power plants. This invention fully utilizes the combination of actual operating data from thermal power plants and theoretical models, significantly improving the accuracy of energy consumption indicator prediction and adapting to prediction needs under different operating conditions.

[0029] Example 2, refer to Figure 1 This is the second embodiment of the present invention. Based on the first embodiment, a method for predicting the energy consumption index of a thermal power plant using output is provided.

[0030] In this embodiment of the invention, step S100, obtaining the performance test data of the steam turbine in a thermal power plant, includes extracting the operation record of the most recent performance test of the steam turbine from the distributed control system of the thermal power plant to obtain the performance test data of the steam turbine in the thermal power plant; standardizing the performance test data of the steam turbine in the thermal power plant; and determining the parameter type of the steam turbine performance test data based on the standardized performance test data of the steam turbine in the thermal power plant.

[0031] In an optional implementation, the acquisition of the thermal power plant turbine performance test data in step S100 can also be achieved by retrieving historical performance test data that is closest to the current production conditions from a historical database, and then using a similarity matching algorithm to select the data group with the highest reference value as the thermal power plant turbine performance test data.

[0032] In another optional implementation, the acquisition of the power plant turbine performance test data in step S100 can also be carried out by online monitoring. The operating parameters such as temperature, pressure and flow rate are collected in real time by a sensor network deployed in key parts of the turbine. After noise filtering and outlier processing, a complete set of turbine performance parameters is formed as the basic data for subsequent analysis.

[0033] In this embodiment of the invention, step S200, which establishes a set of heat balance equations based on the parameter type, includes the following steps A1-A4:

[0034] A1: Extract thermodynamic parameters from parameter types;

[0035] A2: Establish the energy conservation relationship between the aforementioned thermodynamic parameters based on the first law of thermodynamics;

[0036] A3: Express the energy conservation relationship as a set of heat balance equations;

[0037] A4: Perform coefficient calibration on the heat balance equations.

[0038] Specifically, in A1, key thermodynamic parameters such as main steam parameters (e.g., temperature, pressure, flow rate), feedwater parameters (e.g., temperature, pressure), extraction parameters at each stage (e.g., temperature, pressure, flow rate), and exhaust parameters (e.g., temperature, pressure) are extracted from the turbine performance test data. These parameters reflect the critical state points of energy conversion in the power plant's turbine system and are the fundamental data for establishing the heat balance equation.

[0039] In section A2, based on the first law of thermodynamics, the energy conservation relationships between various thermodynamic parameters are established. Specifically, this includes: the balance between the main steam energy input and the energy output of each stage of extraction steam, work, and exhaust steam; the heat balance of each stage of feedwater heaters; and the energy balance of the boiler feedwater system. These relationships follow the fundamental principle that energy cannot be created or destroyed, but only transformed from one form to another.

[0040] In section A3, the aforementioned energy conservation relationships are transformed into a mathematical set of heat balance equations. These include: the main steam total energy equation, the energy distribution equations for each stage of steam extraction, the energy balance equation for the feedwater heating system, and the heat-work conversion equations. These equations together constitute a complete set of heat balance equations, used to describe the energy flow and conversion processes in the steam turbine system of a thermal power plant.

[0041] In A4, the coefficients in the heat balance equations are calibrated by comparing historical operating data and equipment performance characteristics. This includes precise adjustments to key parameters such as the turbine internal efficiency coefficient, extraction coefficients at each stage, and pipeline heat loss coefficient, ensuring that the equations accurately reflect the energy conversion relationships under actual operating conditions.

[0042] For example, for the ultra-high pressure steam turbine system of a 300MW thermal power plant, its main steam parameters are temperature 540℃, pressure 16.7MPa, and flow rate 950t / h. When establishing a heat balance equation set by extracting these parameters, coefficients can be set such as turbine internal efficiency of 0.88, feedwater heater efficiency of 0.95, and heating network efficiency of 0.97, constructing a heat balance equation set containing 15 variables and 12 equations. When there are deviations between actual operating conditions and design conditions, the efficiency coefficients can be adjusted using actual operating data. For instance, when the load drops to 70%, the turbine internal efficiency may need to be adjusted to 0.85 to accurately reflect the thermodynamic performance under non-design conditions.

[0043] In an optional implementation, the method of establishing the heat balance equation set in step S200 can also adopt a model construction method based on thermodynamic cycle theory. This method regards the thermal power plant as a Rankine cycle system, establishes sub-models for equipment such as boiler, steam turbine, condenser and feedwater pump, and then integrates the sub-models into a complete heat balance system model through the connection relationship between working fluid flow and energy flow.

[0044] In another optional implementation, the thermal balance equation set in step S200 can also be established by using the thermal network analysis method, which treats each piece of equipment in the thermal power plant as a network node and the working fluid flow as a network connection, and establishes a network flow equation set based on the node balance principle. This method is particularly suitable for dealing with complex thermal systems and can flexibly meet the calculation needs under different operating conditions.

[0045] In this embodiment of the invention, obtaining the thermal power plant production plan data in step S300 includes the following steps B1-B2:

[0046] B1: Obtain basic production data and environmental impact factor data from the thermal power plant's production management system;

[0047] B2: Verify and standardize the production base data and the environmental impact factor data to generate a standard production plan dataset for heat balance calculation.

[0048] Specifically, in B1, the basic production data obtained from the thermal power plant's production management system mainly includes production indicators such as planned daily power generation, planned heat supply, and load curves. Environmental impact factor data includes predicted ambient temperature, humidity, atmospheric pressure, and fuel characteristic parameters (such as calorific value and volatile matter content). These data together constitute the key external factors affecting the energy consumption level of thermal power plants.

[0049] In B2, the acquired data undergoes validation and standardization, primarily including: data integrity checks to ensure no missing values; data consistency checks to ensure data from different sources remain consistent in time scale and units of measurement; data reasonableness checks to remove outliers and erroneous data; and data standardization to convert data of different dimensions into standard units and formats. This ultimately generates a standard production plan dataset for heat balance calculations, providing a unified data foundation for subsequent calculations.

[0050] For example, the planned data for a thermal power plant for the next day includes: power generation 4800 MWh, heat supply 2400 GJ, average ambient temperature 5℃, and coal calorific value 22.5 MJ / kg. After verification, it was found that the power generation data was 15% higher than the historical average for the same period. This data was confirmed to be correct by checking with the dispatch plan; the heat supply was basically in line with the predicted load; the ambient temperature was within a reasonable range; and the coal calorific value was slightly lower than the design value but within an acceptable range. After standardization, a unified 24-hour load curve dataset was formed, which served as the input conditions for heat balance calculations.

[0051] In an optional implementation, the production plan data of the thermal power plant obtained in step S300 can also be combined with the power grid dispatch plan and heating demand forecast, taking into account the fluctuation characteristics and seasonal changes of the power and heat load, to generate more accurate production plan forecast data.

[0052] In another optional implementation, the acquisition of thermal power plant production plan data in step S300 can also incorporate historical data analysis from the same period, and the production plan data can be corrected and optimized through a time series model to improve the accuracy of data prediction.

[0053] In this embodiment of the invention, step S400 involves calculating and processing the heat balance equations and the production plan data, including the following steps C1-C3:

[0054] C1: Substitute the production plan data into the heat balance equations and construct the solution matrix;

[0055] C2: Solve the matrix using an iterative algorithm to obtain the solution;

[0056] C3: Based on the solution results, determine the operating parameters of the thermal power plant and verify the validity of the operating parameters.

[0057] Specifically, in C1, production plan data is substituted into the equations as known variables of the heat balance equation system. This mainly involves substituting core production indicators such as planned power generation and heat supply, as well as external conditions such as ambient temperature, as constraints or boundary conditions into the equation system. Then, a solution matrix is ​​constructed to transform the nonlinear equation system into a matrix form suitable for numerical solution, establishing the correlation between variables and forming a complete linear or nonlinear equation system matrix.

[0058] In C2, iterative algorithms are used to solve for the constructed matrix. Commonly used iterative algorithms include the Newton-Raphson method and the Gauss-Seidel method. Initial values ​​are usually set based on parameters from the design conditions or historical similar conditions. Through multiple iterative calculations, the variable values ​​are continuously adjusted until the convergence condition is met, and the final solution is obtained.

[0059] In C3, key operating parameters of the thermal power plant are determined based on the solution results, including boiler efficiency, steam production, turbine cylinder efficiency, unit heat supply ratio, and power generation output coefficient. The validity of these operating parameters is verified primarily through comparison with historical operating data, verification of physical constraints, and expert judgment to ensure that the parameters are within reasonable ranges and conform to thermodynamic laws.

[0060] For example, when a thermal power plant has a planned load of 250MW and a heat supply of 80GJ / h, these data are substituted into the heat balance equations and solved using Newton's iterative method. With a convergence accuracy of 0.1%, a stable solution is obtained after 7 iterations. The calculation results show: boiler efficiency of 91.2%, steam production of 910t / h, turbine cylinder efficiency of 83.5%, unit heat supply ratio of 0.32, and power generation output coefficient of 0.78. Verification by comparing with the design performance curve shows an error of less than 3%, confirming the validity of the results.

[0061] In an optional implementation, the calculation process in step S400 can also employ the thermodynamic characteristic curve method. This method establishes a mapping relationship between load and efficiency based on the characteristic curves of the equipment (such as the turbine efficiency curve, boiler load curve, etc.), and quickly solves the operating parameters under different load conditions through interpolation calculation.

[0062] In another optional implementation, the calculation process in step S400 can also adopt the state-space analysis method, which treats the operating state of the thermal power plant as a point in a multi-dimensional state space, describes the changes in the system state under different production plans through state transition equations, and thus solves the dynamic change law of each operating parameter.

[0063] In this embodiment of the invention, step S500, which calculates the energy consumption index of the thermal power plant based on the operating parameters of the thermal power plant, includes the following steps D1-D7:

[0064] D1: Extract the boiler efficiency, steam production, turbine cylinder efficiency, and power generation output coefficient from the operating parameters of the thermal power plant;

[0065] D2: Calculate the coal consumption for power supply based on the boiler efficiency and the steam production;

[0066] D3: Calculate the plant power consumption rate based on the turbine cylinder efficiency and the power generation output coefficient;

[0067] D4: Collect multiple sets of operating data under different working conditions;

[0068] D5: Based on the operating data under the multiple sets of different operating conditions, construct a model of the correspondence between operating conditions and energy consumption;

[0069] D6: Generate an energy consumption curve based on the aforementioned operating condition-energy consumption correspondence model;

[0070] D7: Analyze the changing trend of the energy consumption curve, identify the energy consumption sensitive range; determine the optimal operating condition point, and generate fuel procurement plan suggestions and unit operation mode optimization schemes based on the optimal operating condition point.

[0071] Specifically, in D1, key indicators are extracted from the operating parameters of the thermal power plant calculated in the previous step. These indicators are the core basis for estimating energy consumption levels. Boiler efficiency reflects the efficiency of converting fuel into steam thermal energy; steam production represents the amount of steam generated by the boiler per unit time; turbine cylinder efficiency represents the efficiency of converting steam thermal energy into mechanical energy; and the power generation output coefficient reflects the ratio of the turbine's work done to its theoretical work done.

[0072] In D2, the coal consumption for power generation is calculated based on boiler efficiency and steam production. Coal consumption for power generation is an important indicator of the economics of power generation. The calculation needs to consider factors such as fuel calorific value, boiler efficiency, steam parameters, and power generation efficiency, and calculate the amount of standard coal required per unit of power generation using the energy balance principle.

[0073] In D3, the plant power consumption rate is calculated based on the turbine cylinder efficiency and the power generation output coefficient. The plant power consumption rate represents the proportion of electricity consumed by the power plant itself to the total power generated, and is an important indicator for measuring the energy utilization efficiency within the power plant. Factors such as auxiliary equipment load and system losses must be considered during the calculation.

[0074] In steps D4-D6, operating data under multiple different operating conditions are collected to construct an operating condition-energy consumption correspondence model and generate energy consumption curves. This process analyzes the energy consumption variation patterns under different loads and heating ratios, establishes the mapping relationship between operating condition parameters and energy consumption indicators, and forms intuitive energy consumption curves, providing a basis for operation optimization.

[0075] In D7, the changing trends of the energy consumption curve are analyzed to identify energy-sensitive zones and determine the optimal operating condition. Energy-sensitive zones refer to the operating areas where energy consumption indicators are most sensitive to changes in operating conditions, and these typically require special attention. The optimal operating condition refers to the operating state where energy consumption indicators are optimal while meeting production requirements. Based on these analytical results, scientific fuel procurement plan recommendations and unit operation optimization schemes can be generated.

[0076] For example, based on the analysis of multiple sets of operating data, a thermal power plant found that when the load is between 60% and 80%, the coal consumption for power generation is 310-315 g / kWh; when the load is below 50% or above 90%, the coal consumption for power generation rapidly increases to over 330 g / kWh. The plant's power consumption rate reaches its optimal value of 4.8% at 70% load, and increases when the load is too low or too high. The analysis results indicate that the energy-sensitive ranges for this unit are 50%-60% and 80%-90% load, with the optimal operating point being 75% load and a 30% heat supply ratio. Based on this, the fuel procurement plan recommends adjusting the coal type structure, increasing the proportion of coal with a calorific value of 22-23 MJ / kg; the unit operation optimization scheme suggests avoiding the energy-sensitive ranges, operating within the 65%-85% load range as much as possible, and appropriately increasing the heat supply ratio to achieve optimal energy consumption.

[0077] In an optional implementation, the method for calculating the energy consumption index of the thermal power plant in step S500 can also adopt a multi-objective optimization algorithm, which simultaneously considers multiple performance parameters such as coal consumption, plant power consumption rate, and environmental protection indicators, and provides decision-makers with a variety of optional operating schemes through the Pareto optimal solution set.

[0078] In another optional implementation, the method of calculating the energy consumption index of the thermal power plant in step S500 can also introduce an economic analysis model to convert the energy consumption index into an economic cost index, taking into account market factors such as fuel price fluctuations and electricity price changes, and determining the optimal operation plan from the perspective of maximizing economic benefits.

[0079] In summary, the method for predicting the energy consumption index of a thermal power plant based on production output provided by this invention achieves accurate prediction of the energy consumption index of a thermal power plant based on production output through steps such as obtaining turbine performance test data, establishing a set of heat balance equations, obtaining production plan data, calculating and processing operating parameters, and estimating energy consumption index. This provides a scientific basis for fuel procurement planning and unit operation optimization, and effectively improves the economic benefits and operating efficiency of thermal power plants.

[0080] The method for predicting the energy consumption index of a thermal power plant using output as described in this embodiment mainly employs the heat balance equations based on the first law of thermodynamics for energy consumption calculation. This method has a solid theoretical foundation and also takes into account the needs of practical engineering applications, adapting to the variable operating environment of thermal power plants and providing accurate energy consumption prediction results. Embodiment 3 is the third embodiment of the present invention, differing from the previous two embodiments in that: if the function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0081] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, a computer-readable medium can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0082] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0083] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0084] Example 4 is the fourth embodiment of the present invention. This embodiment provides a system for predicting the energy consumption index of a thermal power plant using output, including...

[0085] The data acquisition module is used to acquire steam turbine performance test data from thermal power plants and determine the parameter types of the steam turbine performance test data;

[0086] The equation building module is used to establish a set of heat balance equations based on the first law of thermodynamics, according to the parameter type.

[0087] The planning acquisition module is used to acquire thermal power plant production plan data as the main variable in the method of using production to predict thermal power plant energy consumption indicators.

[0088] The parameter calculation module is used to calculate and process the heat balance equations and production plan data to obtain the operating parameters of the thermal power plant.

[0089] The indicator calculation module is used to calculate the energy consumption indicators of a thermal power plant based on its operating parameters.

[0090] 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 preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for predicting the energy consumption index of a thermal power plant using output, characterized in that: include, Acquire performance test data of a steam turbine in a thermal power plant and determine the parameter types of the steam turbine performance test data; Establish a set of heat balance equations based on the first law of thermodynamics according to the parameter type; Obtain production plan data from thermal power plants; The heat balance equations and the production plan data are used to calculate and process the power plant operating parameters. The energy consumption index of the thermal power plant is calculated based on the operating parameters of the thermal power plant. The energy consumption index of the thermal power plant is used for fuel procurement planning and unit operation mode optimization.

2. The method for predicting the energy consumption index of a thermal power plant using output as described in claim 1, characterized in that: The acquisition of steam turbine performance test data from thermal power plants includes: Extract the operation record of the most recent performance test of the steam turbine from the distributed control system of the thermal power plant to obtain the steam turbine performance test data of the thermal power plant; The performance test data of the steam turbine in the thermal power plant were standardized. The parameter type of the turbine performance test data is determined based on the standardized thermal power plant turbine performance test data.

3. The method for predicting the energy consumption index of a thermal power plant using output as described in claim 2, characterized in that: The step of establishing a set of heat balance equations based on the first law of thermodynamics according to the parameter type includes: Extract the thermodynamic parameters from the parameter type; The energy conservation relationship between the aforementioned thermodynamic parameters is established based on the first law of thermodynamics. The energy conservation relationship is expressed as the heat balance equations and the coefficients of the heat balance equations are calibrated.

4. The method for predicting the energy consumption index of a thermal power plant using output as described in claim 3, characterized in that: The acquisition of thermal power plant production plan data includes: Obtain basic production data and environmental impact factor data from the thermal power plant's production management system; The basic production data and the environmental impact factor data are verified and standardized to generate a standard production plan dataset for heat balance calculation.

5. The method for predicting the energy consumption index of a thermal power plant using output as described in claim 4, characterized in that: The step of calculating and processing the heat balance equations and the production plan data includes: Substitute the production plan data into the heat balance equations and construct the solution matrix; The matrix is ​​solved using an iterative algorithm to obtain the solution. Based on the solution results, the operating parameters of the thermal power plant are determined, and the validity of the operating parameters is verified.

6. The method for predicting the energy consumption index of a thermal power plant using output as described in claim 5, characterized in that: The method of solving the matrix using an iterative algorithm includes: Set the initial value and termination condition for the iteration; Perform an iterative calculation process and calculate the deviation between the intermediate results of the iterative calculation process and the historical running data; If the deviation exceeds a preset threshold, the correction coefficient is adjusted and the iterative calculation process is re-executed; if the deviation does not exceed the preset threshold, the final solution value is recorded, and the operating parameters of the thermal power plant are generated; the correction coefficient includes thermal efficiency correction coefficient, working fluid flow correction coefficient, and thermal parameter correction coefficient; the iterative algorithm also includes establishing a response surface model to accelerate iterative convergence, setting a convergence acceleration factor to adjust the iteration step size, dynamically adjusting the correction coefficient to adapt to different operating conditions, and fusing multiple iteration results through a weighted average method.

7. The method for predicting the energy consumption index of a thermal power plant using output as described in claim 6, characterized in that: The calculation of energy consumption indicators of the thermal power plant based on the operating parameters of the thermal power plant includes: Extract the boiler efficiency, steam production, turbine cylinder efficiency, and power generation output coefficient from the operating parameters of the thermal power plant. Calculate the coal consumption for power supply based on the boiler efficiency and the steam production. The plant power consumption rate is calculated based on the turbine cylinder efficiency and the power generation output coefficient. Collect multiple sets of operating data under different operating conditions; construct an operating condition-energy consumption correspondence model based on the multiple sets of operating data under different operating conditions; Energy consumption curves are generated based on the aforementioned operating condition-energy consumption correspondence model; Analyze the changing trend of the energy consumption curve to identify energy-sensitive intervals; Determine the optimal operating condition point, and based on the optimal operating condition point, generate a fuel procurement plan recommendation and an optimized unit operation mode scheme.

8. A system for predicting energy consumption indicators of a thermal power plant using output, wherein the method for predicting energy consumption indicators of a thermal power plant using output as described in any one of claims 1 to 7 is characterized in that, include: The data acquisition module is used to acquire steam turbine performance test data from thermal power plants and determine the parameter types of the steam turbine performance test data; The equation construction module is used to establish a set of heat balance equations based on the first law of thermodynamics according to the parameter type. The planning acquisition module is used to acquire thermal power plant production plan data as the main variable in the method of using production to predict thermal power plant energy consumption indicators. The parameter calculation module is used to calculate and process the heat balance equations and the production plan data to obtain the operating parameters of the thermal power plant. The indicator calculation module is used to calculate the energy consumption indicators of the thermal power plant based on the operating parameters of the thermal power plant.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for predicting the energy consumption index of a thermal power plant using output, as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for predicting the energy consumption index of a thermal power plant using output, as described in any one of claims 1 to 7.

Images