A method and system for intelligent optimization of the cold-end system of a coal-fired power unit considering electricity prices

Abstract

This invention discloses an intelligent optimization method and system for the cold-end system of a coal-fired power unit considering electricity prices, relating to the field of thermal power generation technology. The method includes the following steps: acquiring real-time node electricity prices, predicted electricity price sequences, and operating parameters of the coal-fired power unit, including generator output power, real-time back pressure, circulating water temperature, circulating water pump operating frequency, and cooling fan speed. This invention constructs a dynamic safe operating range through a turbine back pressure safety sub-model, a circulating water pump safety sub-model, and a cold-end thermal stress safety sub-model, improving the operational safety and adaptability of the cold-end system. Through dual-objective Pareto optimization of economics and energy consumption, and adaptive screening of the coal-to-electricity value ratio, it achieves optimal operating decisions under different electricity price environments. Simultaneously, it incorporates equipment lifespan loss costs into the optimization process and, in conjunction with safety constraints limiting frequent adjustments, effectively reduces equipment wear and improves the overall economic efficiency, energy saving, and operational stability of the coal-fired power unit throughout its lifecycle.

Description

Technical Field

[0001] This invention relates to the field of thermal power generation technology, specifically to an intelligent optimization method and system for the cold-end system of a coal-fired unit that takes into account electricity prices. Background Technology

[0002] The cold-end system of a coal-fired power unit maintains condenser vacuum and turbine back pressure through a circulating cooling water system. Its operating status directly affects the unit's power generation efficiency, coal consumption for power supply, and plant power consumption. Traditional optimization methods for the cold end of coal-fired power units typically aim to reduce coal consumption for power supply. This is achieved by analyzing the relationship between turbine back pressure, circulating water pump power consumption, and condenser heat exchange characteristics to determine the optimal operating back pressure, and then adjusting and controlling it in conjunction with meteorological parameters such as ambient temperature and circulating water temperature. With the gradual advancement of the electricity spot market, the operation mode of coal-fired power units is gradually shifting from the traditional planned power generation model to a market-oriented revenue-driven model. Units not only need to focus on coal consumption indicators but also need to comprehensively consider factors such as real-time electricity price fluctuations, unit grid connection revenue, and auxiliary equipment operating costs. Meanwhile, the circulating water system in the cold end system has significant thermal inertia, and its cooling capacity changes with a noticeable time lag. Therefore, how to achieve coordinated control of economic optimization and safe operation of the cold end system under fluctuating electricity prices has become an important research direction in the field of intelligent operation of thermal power units.

[0003] Existing cold-end optimization technologies for coal-fired power units are primarily based on a fixed coal consumption optimization approach, assuming a constant value for electricity. This lacks responsiveness to real-time electricity price signals from the market and prevents dynamic adjustments to cold-end operation strategies based on peak-valley price changes. This can lead to uneconomical operations during low-price periods, where higher plant power consumption is sacrificed for limited coal consumption reductions. Conversely, it cannot improve grid connection revenue during high-price periods by adjusting back pressure. Furthermore, existing technologies typically perform static optimization only for the current operating conditions, failing to fully consider the significant thermal inertia of the cooling water system. They lack cross-period coordinated control capabilities for "pre-peak cooling storage and peak-hour cooling release," and cannot optimize the transfer of plant power consumption between different price periods. Moreover, most existing cold-end optimization methods rely on fixed safety boundaries or empirical thresholds for control, failing to dynamically generate safe operating ranges based on load, water temperature, and equipment status. They also fail to factor in fatigue losses from frequent adjustments to circulating pumps, fans, and other equipment into economic costs, potentially leading to accelerated equipment wear due to excessive tracking of electricity price fluctuations. At the same time, existing technologies lack a unified economic criterion based on the ratio of electricity price to coal price, making it impossible to comprehensively weigh the value of slightly increased power generation revenue and slightly increased plant power consumption, and thus failing to meet the operational needs of maximizing the full-cycle revenue of coal-fired units in the context of the electricity spot market.

[0004] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent optimization method and system for the cold-end system of a coal-fired power unit that takes into account electricity prices, so as to solve the problems in the background art mentioned above.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an intelligent optimization method for the cold-end system of a coal-fired power unit considering electricity prices, comprising the following steps: The system acquires real-time node electricity prices, predicted electricity price sequences, and operating parameters of coal-fired power units, including generator output power, real-time back pressure, circulating water temperature, circulating water pump operating frequency, and cooling fan speed. For the operating parameters of coal-fired units, the dynamic safe operating range is calculated using the turbine back pressure safety sub-model, the circulating water pump safety sub-model, and the cold end thermal stress safety sub-model. The dynamic safe operating range includes the back pressure safety range, the circulating water pump frequency safety range, and the water temperature change rate constraint. A dual-objective optimization model is constructed within the dynamic safe operation range. The dual-objective optimization model includes an economic objective function and an energy consumption objective function. The economic objective function includes net on-grid power, electricity price, coal consumption cost, and equipment life loss cost. The energy consumption objective function is characterized by the power supply coal consumption rate. A multi-objective evolutionary algorithm is used to iteratively solve the economic objective function and the energy consumption objective function to generate a Pareto front set composed of non-dominated solutions; Calculate the ratio of electricity price to coal price, and perform adaptive screening based on the Pareto front set. When the ratio of electricity price to coal price is higher than a preset threshold, select the economic priority solution; when the ratio of electricity price to coal price is lower than a preset threshold, select the energy-saving priority solution; when the ratio of electricity price to coal price is between the two preset thresholds, select the equilibrium solution. For the high electricity price period in the predicted electricity price sequence, increase the operating frequency of the circulating water pump and the speed of the cooling fan during the low electricity price period to form a cooling capacity reserve, and reduce the operating frequency of the circulating water pump and the speed of the cooling fan during the high electricity price period to release the cooling capacity; The operation results are constrained and verified. Once the dynamic safe operating range is met, control commands for the circulating water pump and cooling fan are output, and the next optimization cycle begins.

[0007] Preferably, data collaborative processing is performed around the electricity price forecasting and operating condition data collection process to improve the economic regulation and response capability of the cold-end system. The steps are as follows: Access real-time node electricity price data from the electricity market, read real-time electricity price information corresponding to different time points, and record the time series of electricity price changes; A time-series neural network prediction model is constructed by importing historical electricity price data, historical load data, and historical operating condition data, and rolling predictions are made for future time periods to generate a future electricity price change sequence. Collect generator output power, unit real-time back pressure, circulating water inlet temperature, cooling tower inlet and outlet water temperatures, circulating water pump operating frequency, number of circulating water pumps in operation, and cooling fan speed information, and record the corresponding time tags simultaneously. Real-time electricity price information, predicted electricity price sequences, and unit operation information are compiled to form a cold-end system operation dataset, which is then transmitted to the cold-end optimization computing unit for operation status analysis.

[0008] Preferably, the operating condition analysis process is performed on the dynamic generation process of the safe operating boundary of the cold end system to improve the unit's operational stability. The steps are as follows: Establish a turbine back pressure safety sub-model, input unit load parameters, circulating water temperature parameters, and condenser heat exchange status parameters, and read turbine operating condition information; Calculate the upper and lower safe back pressure limits corresponding to the current operating conditions, form the turbine back pressure operating range, and output the corresponding back pressure boundary data; Construct a safety sub-model for the circulating water pump, retrieve the characteristic curves of the circulating water pump and the resistance parameters of the circulating water pipeline, and calculate the operating frequency range, frequency variation range, and circulating water flow variation state of the circulating water pump. A cold-end thermal stress safety sub-model is introduced to calculate the circulating water temperature change rate, circulating water pump frequency adjustment rate, and thermal stress change information, and integrate them to form a dynamic safe operating range.

[0009] Preferably, target analysis is performed on the coordinated adjustment process of cold-end system revenue and energy consumption to improve the overall operating efficiency of the unit. The steps are as follows: Establish an economic objective function, import information on net on-grid power, real-time electricity price, coal consumption rate, and standard coal unit price, and generate parameters for calculating economic benefits. The data includes the frequency variation of the circulating water pump, the speed variation of the cooling fan, and the number of adjustment actions of the auxiliary equipment at the cold end, and generates equipment life loss cost data. Construct an energy consumption objective function corresponding to the coal consumption rate of power supply, read the coal consumption data of power supply under different operating conditions, and form energy consumption evaluation parameters for the cold end system; The economic objective function and the energy consumption objective function are integrated to form a dual-objective collaborative operation model, and the objective function data set corresponding to different operating states is output.

[0010] Preferably, the operation scheme is screened by combining the multi-objective optimization process of the cold end system to enhance the global optimization capability. The steps are as follows: Import the dynamic safe operating range and the dual-objective optimization model, and read the back pressure operating parameters, circulating water pump operating parameters and cooling fan operating parameters; The multi-objective evolutionary algorithm is invoked to generate multiple sets of candidate running schemes, and population initialization, crossover calculation, and mutation calculation are performed on the candidate running schemes; Perform non-dominated sorting calculations, sort and analyze the economic objective function values ​​and energy consumption objective function values ​​corresponding to different operating schemes, and record the non-dominated operating status; Select non-dominated operating solutions that satisfy the dynamic safe operating range, form the Pareto front set, and output the back pressure operating results corresponding to different operating schemes.

[0011] Preferably, the operational strategy is adjusted based on the linkage between electricity and coal prices to enhance adaptability to different market conditions. The steps are as follows: Obtain real-time electricity price information and standard coal unit price information, and establish data on the correspondence between electricity price and coal price; Calculate the ratio of electricity price to coal price, identify the current electricity price operating status within a range, and output the corresponding electricity price range information; Determine the economic range corresponding to the current operating stage, match the economic priority strategy, energy-saving priority strategy, or equilibrium operation strategy, and read the corresponding operating scheme of the Pareto front set; Perform a screening analysis on the undominated operating solutions of the Pareto front set, and output the corresponding operating schemes and corresponding back pressure operating parameters.

[0012] Preferably, the cold energy pre-storage regulation is carried out in conjunction with the thermal inertia change process of the cold end system to improve operating revenue during periods of high electricity prices. The steps are as follows: Analyze and predict the trend of electricity price series changes, identify the high electricity price operating range in the future set period, and record the corresponding time range; Retrieve the Pareto front-focused operating scheme and read the operating information of circulating water temperature, circulating water pump operating frequency, and cooling fan speed; Increase the operating frequency of the circulating water pump and the speed of the cooling fan to increase the circulating water flow and the heat dissipation capacity of the cooling tower, reduce the circulating water temperature and form a cold energy reserve; Adjust the operating load of the cold-end auxiliary equipment, reduce the operating frequency of the circulating water pump and the speed of the cooling fan, and maintain the operating status of the circulating water temperature and back pressure by pre-storing cold energy.

[0013] Preferably, life loss analysis is performed on the adjustment actions of the cold-end auxiliary equipment to reduce the risk of equipment damage during operation. The steps are as follows: Collect statistics on the variation range of the operating frequency of the circulating water pump, the variation range of the cooling fan speed, and the corresponding adjustment time information; Record the number of adjustment actions of the circulating water pump and cooling fan, generate equipment adjustment frequency data, and organize the corresponding operating status information; Import frequency variation amplitude data and adjustment frequency data, calculate equipment life loss cost, and form a set of equipment life loss parameters; The cost of equipment life loss is imported into the economic objective function, and the evaluation results of equipment life loss corresponding to different operating states are output.

[0014] Preferably, the operation status verification process is performed on the control command output process of the cold end system to improve and optimize operational stability. The steps are as follows: Receive the optimized operation results of the cold end system and read the corresponding back pressure operating parameters, circulating water operating parameters, and cooling fan operating parameters; Verify the back pressure operating boundary, the rate of change of circulating water temperature, the range of change of circulating water pump frequency, and the operating status of circulating water flow. The operating frequency of the circulating water pump, the number of circulating water pumps in operation, the speed of the cooling fan, and the operating status of the cold-end auxiliary equipment were checked, and the corresponding operation verification results were compiled. Output control commands to the circulating water pump and cooling fan, start the next cycle of optimized operation calculation, and update the current operating status data.

[0015] An intelligent optimization system for the cold-end system of a coal-fired power unit, taking electricity prices into account, includes a data sensing and prediction module, a core decision optimization module, and an execution and feedback module. The data perception and prediction module collects unit operating parameters in real time, including generator power, back pressure, circulating water temperature, circulating water pump operating status, and cooling fan operating status. It connects to the real-time node marginal electricity price of the electricity market and has a built-in time-series neural network model for predicting electricity prices and loads in future periods. The core decision optimization module receives unit operating parameters, real-time node marginal electricity price, and predicted electricity price sequence output by the data perception and prediction module. It embeds a dual-objective optimization model to solve for the optimal back pressure and corresponding cold-end equipment control commands in real time within the dynamic safe operation range. The dual-objective optimization model includes economic objectives and energy consumption objectives. The economic objectives include net revenue from grid connection, coal consumption cost, and equipment life loss cost. The energy consumption objective is represented by the power supply coal consumption rate, and the Pareto front solution is adaptively screened based on the ratio of electricity price to coal price. The execution and feedback module receives the cold end equipment control commands output by the core decision optimization module, sends the cold end equipment control commands to the actuators of the circulating water pump frequency converter and the cooling fan frequency converter, and sends back confirmation of the execution status.

[0016] The technical effects and advantages provided by the present invention in the above technical solution are as follows: This invention constructs a coupled dynamic safe operating range in real time using a turbine back pressure safety sub-model, a circulating water pump safety sub-model, and a cold-end thermal stress safety sub-model. This allows for dynamic adjustment of safety boundaries based on changes in unit load, circulating water temperature, and equipment operating status. Compared to traditional fixed-limit control methods, this more realistically reflects the actual operating capacity of the cold-end system of a coal-fired unit. Since equipment safety margins vary significantly under different operating conditions, fixed safety boundaries are prone to insufficient protection or overly conservative operation. The dynamic safe operating range, however, refreshes safety constraints in real time during each optimization cycle, ensuring that the optimized operation of the cold-end system remains within the safe and feasible domain. This effectively reduces operational risks such as turbine last-stage blade vibration, circulating water pump cavitation, and thermal stress shock, improving the operational stability and reliability of the cold-end system.

[0017] This invention constructs a dual-objective Pareto optimization framework that coordinates economic efficiency and energy consumption. During the optimization process, it preserves the objective trade-off between economic benefits and coal consumption for power generation, avoiding the subjective problems caused by manually setting weights in traditional single-objective weighted optimization methods. By introducing an adaptive screening mechanism based on the ratio of electricity to coal value, the optimization strategy can be automatically switched according to the real-time relationship between electricity and coal prices. During periods of high electricity prices, priority is given to maximizing electricity sales revenue; during periods of low electricity prices, priority is given to minimizing coal consumption; and during periods of stable electricity prices, both economic efficiency and energy conservation are considered. This achieves dynamic adaptive adjustment of the cold-end operation strategy under different market conditions. Compared to traditional fixed operation modes, it can more effectively adapt to the fluctuating characteristics of electricity prices in the spot market, improving the overall operational efficiency and market competitiveness of coal-fired units throughout their entire lifecycle.

[0018] This invention incorporates equipment lifespan depreciation costs, determined by both the frequency modulation amplitude and the adjustment frequency, into the economic objective function. It integrates the mechanical wear, thermal fatigue, and equipment impact caused by frequent adjustments of circulating water pumps and cooling fans into a comprehensive economic evaluation system, thereby avoiding over-optimization based solely on short-term economic gains. Simultaneously, by dynamically constraining the operating frequency of the circulating water pump, the rate of water temperature change, and the equipment adjustment amplitude within a safe operating range, it effectively suppresses high-frequency, large-amplitude adjustment behavior, reducing the risk of equipment damage caused by long-term, frequent operation of cold-end auxiliary equipment. Compared to traditional control methods that solely pursue short-term gains, this invention improves operational economy while protecting equipment lifespan, extending the long-term stable operating cycle of critical auxiliary equipment such as circulating water pumps and cooling fans. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0020] Figure 1 This is the main flowchart of the present invention.

[0021] Figure 2 This is a diagram of the overall system architecture of the present invention. Detailed Implementation

[0022] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the description of this disclosure will be more complete and fully convey the concept of the exemplary embodiments to those skilled in the art.

[0023] This invention provides, for example Figure 1 The method for intelligent optimization of the cold-end system of a coal-fired power unit, taking into account electricity prices, includes the following steps: The system acquires real-time node electricity price information from the current electricity market and connects to real-time electricity price data published by the electricity spot market platform to reflect the dynamic changes in the value of electricity at different time points. Simultaneously, a prediction model based on a time-series neural network is used to predict electricity price trends within a specified future time period. This time-series neural network employs a long short-term memory (LSTM) network model, trained using historical electricity price data, historical load change data, and time series features to generate ultra-short-term predicted electricity price sequences for the next one to four hours. This allows for the early identification of potential high and low electricity price periods, providing a forward-looking decision-making basis for subsequent economic operation and regulation of the cold-end system.

[0024] While acquiring electricity price information, the system simultaneously collects operating parameters of the cold-end system of the coal-fired power unit. These parameters include generator output power, real-time back pressure, circulating water inlet temperature, cooling tower inlet temperature, cooling tower outlet temperature, circulating water pump operating frequency, number of circulating water pumps in operation, and cooling fan speed. Specifically, generator output power reflects the current unit load level; real-time back pressure reflects the condenser vacuum operating status; circulating water inlet temperature and cooling tower inlet and outlet temperatures characterize the cold-end heat exchange capacity and circulating cooling effect; circulating water pump operating frequency and number of pumps in operation reflect the circulating cooling water flow regulation status; and cooling fan speed reflects changes in the cooling tower's heat dissipation capacity.

[0025] The collected real-time operating parameters, together with real-time node electricity prices, constitute the cold-end system operating status dataset, serving as the data input basis for subsequent dynamic safe operating range calculations and dual-objective optimization. A temporal linkage is established between the predicted electricity price sequence and the real-time electricity price. By identifying future electricity price trends in advance, it is possible to predict whether a high-price operating range will exist in the future, thus providing predictive support for the subsequent pre-peak cooling storage adjustment of the cold-end system. Simultaneously, continuous acquisition of unit operating parameters can also reflect the real-time changes in the operating status of the coal-fired unit's cold-end system, providing real-time operating condition data support for dynamic safety boundary updates, circulating water pump operation adjustments, and cooling fan control.

[0026] By synchronously acquiring real-time node electricity prices, predicted electricity price sequences, and cold-end operating parameters, it is possible to uniformly link electricity market price signals with the cold-end operating status of coal-fired units. This introduces a market-oriented operating mechanism on the basis of traditional cold-end energy-saving optimization, thereby providing basic data conditions for the coordinated optimization of subsequent economic and energy consumption targets, and improving the revenue adjustment capability and operational flexibility of coal-fired units in the electricity spot market environment.

[0027] Based on the mechanistic characteristics of each core component of the cold-end system, the coupled dynamic safe operating range is calculated in real time during each optimization cycle. This ensures that the cold-end system always operates within a safe and feasible range under different loads, ambient temperatures, and circulating water conditions. The dynamic safe operating range does not use fixed operating limits, but rather involves real-time coupled calculations of the turbine, circulating water pumps, and cold-end thermal stress state to form a dynamically updated safety boundary that changes with operating conditions. This improves the safety and adaptability of the cold-end system's optimization control process.

[0028] The turbine backpressure safety sub-model calculates the permissible backpressure operating range under current operating conditions based on the unit's real-time load, condenser heat transfer characteristics, and circulating water inlet temperature. The exhaust flow state of the turbine's last-stage blades varies significantly under different load conditions. When the unit load decreases, the exhaust volumetric flow rate decreases, making the turbine's last-stage blades more susceptible to backflow, vibration, and wet steam scouring. Therefore, the permissible backpressure range needs to be dynamically adjusted according to load changes. Changes in condenser heat transfer capacity and circulating water temperature also directly affect the condenser vacuum level. Therefore, the upper limit of backpressure safety and the lower limit of physical achievable backpressure under current operating conditions are obtained through real-time calculations. in, This indicates the upper limit of the safe back pressure under the current operating conditions, which is used to limit the safe operating range of the last stage blades of the steam turbine under high back pressure. It represents the physical lower limit of back pressure that can be achieved under the current operating conditions, and is used to reflect the lowest achievable back pressure under the combined effect of condenser heat exchange capacity, circulating water temperature and vacuum system capacity.

[0029] The circulating water pump safety sub-model calculates the operating frequency adjustment range of the circulating water pump in real time based on the pump's characteristic curve and the resistance characteristics of the circulating water pipeline. The circulating water pump has a stable operating range under different flow rate and head conditions. When the operating point deviates from the safe range, problems such as cavitation, surge, motor overload, and pipeline impact are prone to occur. Therefore, the safe range for circulating water pump frequency adjustment is calculated using the pump's flow-head characteristics and the current pipeline resistance status. Simultaneously calculate the maximum permissible frequency change amplitude during a single adjustment process: in, Indicates the minimum safe operating frequency for the circulating water pump; This indicates the highest safe operating frequency for the circulating water pump; This indicates the maximum allowable frequency change during a single frequency adjustment, used to limit equipment shocks and hydraulic disturbances caused by rapid fluctuations in the frequency of the circulating water pump.

[0030] The thermal stress sub-model of the cold-end system analyzes the thermal stress of high-heat-capacity components such as the cooling tower water tank, condenser water chamber, and main circulating water pipeline. During rapid temperature changes in the circulating water, a temperature gradient forms within the metal structure, further generating thermal stress. When this thermal stress exceeds the allowable range of the material, it can easily lead to material fatigue, weld damage, and reduced equipment lifespan. Therefore, a one-dimensional unsteady-state thermal conduction equation for the components and the allowable stress of the material are used to calculate the maximum permissible rate of water temperature change under current operating conditions. And the maximum allowable adjustment rate of the circulating water pump frequency: in, This indicates the maximum allowable rate of change of circulating water temperature under the current operating conditions, used to limit excessive temperature fluctuations in the circulating water system within a short period of time; This indicates the maximum allowable adjustment rate of the circulating water pump frequency, used to limit thermal shock caused by rapid changes in circulating water flow.

[0031] In winter, under low-temperature conditions, the circulating water base temperature is low, and the materials of the cold-end equipment have a high tolerance to temperature fluctuations. Therefore, the allowable rate of water temperature change and frequency adjustment rate are relatively increased. However, in summer, under high-temperature conditions, the equipment is in a high-temperature operating state for a long time, and the thermal stress sensitivity of the materials is enhanced. The allowable adjustment boundary is tightened accordingly to avoid further aggravation of thermal fatigue problems.

[0032] By jointly calculating the turbine back pressure safety sub-model, the circulating water pump safety sub-model, and the cold end thermal stress sub-model, a multi-dimensional dynamic safe operating range for the cold end system is finally formed: The dynamic safe operating range includes multiple sets of constraints, such as back pressure operating boundary, circulating water pump frequency operating boundary, circulating water temperature change rate boundary, and circulating water pump frequency adjustment rate boundary. This dynamic safe operating range is refreshed according to real-time operating conditions in each optimization cycle, thereby ensuring that the subsequent optimization solution process always operates within a safe and feasible range, and avoiding the problems of excessive conservatism or insufficient safety margin that exist in traditional fixed limit control methods.

[0033] By calculating the dynamic safe operating range in real time, it is possible to achieve dynamic matching between the operating boundary of the cold end system and the unit load, circulating water temperature and equipment thermal state, thereby improving the safe operation capability of the cold end system under different electricity price environments and different operating conditions, and providing a reliable safety constraint basis for subsequent economic and energy consumption synergistic optimization.

[0034] Within the feasible region defined by the dynamic safe operating range, a dual-objective optimization model is established to coordinate economic efficiency and energy consumption. By performing multi-objective optimization on the operating state of the cold-end system, the model aims to improve the revenue and control energy consumption of coal-fired units under different electricity price environments. The dual-objective optimization model no longer adopts the traditional single-method approach of minimizing power supply coal consumption. Instead, it simultaneously considers factors such as electricity market revenue, coal consumption, and equipment regulation losses. Two parallel objective functions are used to comprehensively evaluate the operating state of the cold-end system, thereby improving the economy and flexibility of cold-end system operation and regulation.

[0035] The economic objective function is used to characterize the comprehensive economic benefits of a coal-fired power unit under current operating conditions, and its expression is: in: This represents the net power output to the grid, reflecting the actual effective power generation output of a coal-fired power unit. The net power output to the grid deducts the plant's power consumption by auxiliary equipment such as circulating water pumps and cooling fans, thus accurately reflecting the unit's net output capacity that can ultimately be used for electricity sales. Real-time electricity prices reflect the market value of a unit of electricity in the current electricity market. These prices fluctuate dynamically with changes in supply and demand in the spot electricity market. During periods of high electricity prices, increasing net on-grid power can generate higher revenue from electricity sales, while during periods of low prices, greater attention needs to be paid to plant power consumption and coal consumption control. The coal consumption rate reflects the level of coal consumption per unit of electricity generated under the current operating conditions of a coal-fired power unit. The coal consumption rate is directly related to turbine back pressure, circulating water temperature, and condenser heat exchange efficiency. Lowering the back pressure typically improves the unit's thermal economy, thereby reducing the coal consumption rate. This represents the standard coal price per unit, used to reflect the cost level of coal. Coal cost and coal consumption rate together determine fuel expenditure during the power generation process; therefore, changes in coal prices directly affect the economic operation strategy of the cold-end system. This represents the equivalent lifespan loss cost resulting from equipment adjustment actions, reflecting the wear and tear caused by frequency regulation of circulating water pumps and cooling fans. While frequent equipment adjustments can improve short-term economic benefits, they also increase the risk of bearing fatigue, mechanical wear, and motor impact. Therefore, it is necessary to convert equipment lifespan loss into economic costs and incorporate it into optimization objectives.

[0036] in: This indicates the amplitude of frequency change, reflecting the degree of change in the frequency of the circulating water pump or the speed of the cooling fan during the adjustment process. The greater the amplitude of frequency change, the more pronounced the mechanical shock and hydraulic disturbance experienced by the equipment, and the higher the level of equipment lifespan loss. This indicates the adjustment frequency, reflecting the number of times a circulating water pump or cooling fan performs adjustment actions per unit of time. Increased adjustment frequency leads to the equipment operating in a state of frequent start-stop or frequent frequency conversion for extended periods, thus accelerating equipment fatigue and wear.

[0037] By incorporating equipment lifespan depreciation costs into the economic objective function, we can not only avoid excessive tracking of real-time electricity price fluctuations, but also improve the long-term operational stability of the cold-end system and prevent equipment lifespan reduction due to frequent adjustments.

[0038] The energy consumption objective function is used to characterize the energy-saving level during the operation of a coal-fired power unit, and its expression is: in: The power supply coal consumption rate is used as a direct indicator of the energy consumption level of the cold-end system. The lower the power supply coal consumption rate, the higher the thermal efficiency of the coal-fired unit and the better the fuel utilization level.

[0039] Using the coal consumption rate for power supply as the energy consumption objective function ensures that the energy-saving baseline of coal-fired units is maintained even during periods of low electricity prices. When real-time electricity prices are insufficient to support high-intensity cooling operation, the optimization objective automatically shifts towards energy conservation by reducing the frequency of circulating water pumps and the operating load of cooling fans, thereby reducing plant power consumption and avoiding the uneconomical situation of trading high plant power consumption for limited revenue growth.

[0040] In the dual-objective optimization model, there is a natural coupling between the economic objective and the energy consumption objective. While reducing back pressure can improve the thermal economy of the turbine and increase the unit's output capacity, it may also increase the power consumption of circulating water pumps and cooling fans. Conversely, reducing the operating power of auxiliary equipment at the cold end can reduce plant power consumption, but it may lead to increased back pressure and increased coal consumption. Therefore, the two objective functions are not simply independent but rather form a dynamic equilibrium relationship under different operating conditions and electricity prices.

[0041] By establishing a dual-objective optimization model, market revenue, coal consumption, and equipment lifespan loss can be considered simultaneously within the dynamic safe operating range, thereby achieving synergistic optimization of the cold-end system's economy and energy efficiency, and providing the objective function basis for subsequent Pareto front solutions and electricity price response optimization.

[0042] Within the feasible region defined by the dynamic safe operating range, a multi-objective evolutionary algorithm is employed to simultaneously iteratively solve for the economic and energy consumption objectives. By conducting multiple rounds of searching and filtering of the objective function values ​​under different operating conditions, a set of non-dominated solutions that meets the requirements of multi-objective collaborative optimization is generated. The multi-objective evolutionary algorithm uses a swarm search mechanism to simultaneously search multiple candidate operating points throughout the entire feasible region, thereby avoiding the problem of traditional single-objective optimization easily getting trapped in local optima and improving the global optimization capability of the cold-end system under complex operating conditions.

[0043] The multi-objective evolutionary algorithm employs a non-dominated sorting genetic algorithm for iterative optimization. Within each optimization cycle, turbine back pressure is used as the core regulating variable, while simultaneously considering the impact of circulating water pump operating frequency, cooling fan operating status, and cold-end auxiliary equipment power consumption on both economic and energy consumption objectives. In the algorithm initialization phase, multiple candidate operating individuals are generated, each corresponding to a cold-end system operating state. Different operating states correspond to different back pressure levels, circulating water flow rates, and cooling intensities. Subsequently, the economic objective function value and energy consumption objective function value are calculated for each candidate operating individual, and all candidate individuals are sorted according to the non-dominated relationship.

[0044] When a candidate operating entity is no worse than other operating entities in both the economic and energy consumption objectives, it is determined to be a non-dominated solution. Multiple non-dominated solutions together constitute the Pareto front set. There is no absolute superiority or inferiority relationship among the operating points in the Pareto front set; instead, they form different degrees of balance between economic benefits and energy-saving effects. Therefore, it can provide multiple feasible solutions for selecting operating strategies under different electricity price scenarios.

[0045] The expression for the Pareto front set generated by iteratively solving using a multi-objective evolutionary algorithm is as follows: in: Let Pareto front set be the set of all non-dominated solutions that satisfy the constraints of the dynamic safe operating range. Each element in the Pareto front set corresponds to a cold-end system operation scheme that can simultaneously consider both economic efficiency and energy consumption.

[0046] Indicates the first Each non-dominated solution corresponds to a turbine back pressure operating point. Different back pressure operating points correspond to different condenser vacuum states and different cold-end auxiliary equipment operating loads, which in turn affect the power generation efficiency and plant power consumption of the coal-fired unit.

[0047] Indicates the first The economic objective function value corresponding to each non-dominated solution reflects the economic benefit level of the current operating scheme under the combined effects of electricity price revenue, coal cost, and equipment lifespan depreciation. The higher the economic objective function value, the higher the overall benefit that the corresponding operating scheme can obtain.

[0048] Indicates the first The energy consumption objective function value corresponding to each non-dominated solution is used to reflect the coal consumption level for power supply under the current operating scheme. The lower the energy consumption objective function value, the better the energy-saving effect of the corresponding operating scheme.

[0049] This indicates the non-dominated solution number, used to distinguish the order of different operating schemes in the Pareto front set. Different numbers correspond to different cold-end operating states and different combinations of objective functions.

[0050] This represents the total number of lumped non-dominated solutions at the Pareto front. The number of non-dominated solutions changes dynamically with the current operating conditions, the dynamic safe operating range, and the objective function.

[0051] In the iterative process of the multi-objective evolutionary algorithm, each round of computation requires performing crossover, mutation, and non-dominated sorting operations on candidate running individuals. Crossover generates new candidate running states, improving search space coverage through different combinations of running parameters; mutation increases the diversity of running schemes, preventing premature convergence; and non-dominated sorting filters running schemes with superior overall performance and gradually eliminates inferior running states. Simultaneously, a dynamic safe operating range verification is required for all candidate running individuals; only running schemes that meet the back pressure safety boundary, circulating water pump operating boundary, and thermal stress constraint conditions can enter the Pareto front set.

[0052] Because economic and energy consumption objectives are mutually constrained, different operating schemes in the Pareto front set exhibit different optimization tendencies. When the operating point is biased towards low back pressure, the turbine's thermal economy improves and coal consumption decreases, but the power consumption of circulating water pumps and cooling fans increases. When the operating point is biased towards high back pressure, the power consumption of cold-end auxiliary equipment decreases, but the unit's power generation efficiency decreases, leading to increased coal consumption for power supply. Therefore, the Pareto front set can fully preserve the objective trade-off between economic and energy consumption objectives, providing a candidate operating basis for subsequent optimization of electricity price response and selection of coal-to-power ratio.

[0053] By employing a multi-objective evolutionary algorithm to simultaneously solve the dual-objective optimization model, the subjectivity issues caused by manual weight allocation in traditional single-objective optimization methods can be avoided. At the same time, the dynamic optimization capability of the cold-end system under complex operating conditions can be improved, thereby providing multi-scheme decision support for the revenue optimization operation of coal-fired units in the electricity spot market environment.

[0054] After constructing the Pareto front set, the value relationship between electricity and coal prices is further introduced. Multiple non-dominated solutions in the Pareto front set are adaptively screened, thereby automatically adjusting the cold-end system operation strategy under different market environments. In the electricity spot market environment, real-time electricity prices fluctuate significantly, and the value of electricity varies greatly across different time periods, while coal costs remain relatively stable. Therefore, it is necessary to use the relative relationship between electricity and coal prices to determine whether the current operating stage prioritizes economic benefit optimization or energy-saving operation optimization. By establishing a coal-to-electricity value ratio index, power generation revenue and coal costs can be uniformly mapped to the same economic evaluation dimension, enabling dynamic switching of the cold-end system operation strategy according to market price changes.

[0055] The expression for the value ratio of thermal coal is: in: The coal-to-electricity value ratio reflects the relative relationship between the current value of a unit of electricity and the unit cost of coal. A higher coal-to-electricity value ratio indicates that the current revenue from electricity sales is higher relative to the cost of coal, and the unit operation is more inclined to increase the revenue from power generation; a lower coal-to-electricity value ratio indicates that the current value of electricity is relatively low, and more attention needs to be paid to coal consumption and plant power control.

[0056] Real-time electricity prices reflect the current electricity market transaction prices. These prices fluctuate dynamically based on grid load levels, market supply and demand, and changes in renewable energy output. High electricity prices typically correspond to peak grid load periods, during which increasing grid-connected electricity can yield higher economic returns; conversely, low electricity prices typically correspond to off-peak load periods, during which blindly increasing the power consumption of auxiliary cooling equipment can easily lead to decreased operational efficiency.

[0057] The standard coal unit price reflects the cost level of a unit of coal. It is used to convert coal consumption into a uniform economic cost, thus forming a value comparison relationship between revenue and cost together with the real-time electricity price.

[0058] After obtaining the coal-to-power ratio, the system automatically selects the corresponding optimization strategy based on the ratio. When the coal-to-power ratio is high, it indicates that the current electricity sales revenue is far higher than the cost of coal, and in this case, prioritizing the improvement of the unit's economic benefits is the priority. When the coal-to-power ratio is low, it indicates that the current electricity price is insufficient to cover the higher operating costs, and in this case, prioritizing the reduction of coal consumption and plant power consumption is the priority. When the coal-to-power ratio is in the middle range, a balance needs to be struck between economic efficiency and energy conservation.

[0059] When the value ratio of thermal coal meets the following: This indicates that we are currently in a phase of high electricity prices and low coal prices, at which point an economic-first strategy should be adopted. Under this economic-first strategy, we should consider the Pareto frontier. Selecting an economic objective function The largest running solution.

[0060] in: This represents a preset high coal-to-power ratio threshold, used to define high-yield operating ranges. When the coal-to-power ratio exceeds this threshold, the operating objectives of the cold-end system shift towards increasing power generation revenue.

[0061] This represents the Pareto front set generated by a multi-objective evolutionary algorithm. Each running point in the Pareto front set corresponds to a cold-end running scheme that satisfies the dynamic safe running interval constraint.

[0062] This represents the economic objective function, used to reflect the overall economic benefit level corresponding to the operational plan. The larger the economic objective function, the higher the grid connection revenue that the corresponding operational plan can obtain.

[0063] During periods of high electricity prices, the energy consumption objective function is allowed. A moderate increase in power generation can be achieved in exchange for higher electricity sales revenue. At this point, by appropriately enhancing cooling capacity to reduce back pressure, the unit's output power can be increased, and the amount of electricity fed into the grid can be increased, thereby improving overall economic returns.

[0064] When the value ratio of thermal coal meets the following: This indicates that we are currently operating in a phase of low electricity prices and high coal prices, at which point an energy-saving priority strategy should be adopted. Under this strategy, energy conservation should be prioritized, starting from the Pareto frontier. Selecting the energy consumption objective function The smallest running solution.

[0065] in: This represents a preset low coal-to-power ratio threshold, used to define energy-saving operating ranges. When the coal-to-power ratio falls below this threshold, the focus of cold-end system operation shifts to reducing coal consumption and auxiliary equipment power consumption.

[0066] This represents the energy consumption objective function, used to reflect the coal consumption level for power supply corresponding to the operating scheme. The smaller the energy consumption objective function, the better the energy-saving effect of the unit.

[0067] During periods of low electricity prices, reducing the operating frequency of circulating water pumps and the speed of cooling fans can decrease plant power consumption, thereby preventing a decline in operating revenue due to low electricity prices.

[0068] When the value ratio of thermal coal meets the following: This indicates that current electricity and coal prices are in a relatively balanced state, at which point an equilibrium strategy is adopted. Under the equilibrium strategy, points close to the utopian ideal are selected from the Pareto front. The compromise solution with the minimum Euclidean distance.

[0069] in: This represents the maximum value of the Pareto frontier's centralized economic objective function; This represents the minimum value of the Pareto front intensive energy consumption objective function.

[0070] The utopian ideal point represents the ideal operating state that theoretically achieves both maximum economic benefits and minimum coal consumption, while the operating solution with the minimum Euclidean distance represents the optimal balance between economic efficiency and energy conservation under current conditions.

[0071] Through an adaptive screening mechanism driven by the value ratio of coal and electricity, the operating targets of the cold-end system can be automatically adjusted according to the real-time market environment, avoiding the problem that the traditional fixed optimization mode cannot adapt to changes in electricity prices. At the same time, it fully preserves the objective trade-off relationship between different operating schemes in the Pareto front, improving the revenue optimization capability and operational flexibility of coal-fired units in the electricity spot market.

[0072] After obtaining the predicted electricity price sequence for a future time period, the system continuously analyzes and makes rolling judgments on future electricity price trends. When the prediction results indicate that there is a high electricity price operating range in the future, the cooling system no longer performs static optimization only for the current operating revenue. Instead, it utilizes the large thermal inertia characteristics of the circulating cooling water system to proactively adjust the current operating state, thereby achieving advance storage and delayed release of cooling capacity in the time dimension, and improving the overall operating revenue of coal-fired units in the electricity spot market environment.

[0073] The circulating cooling water system has a large heat capacity, and significant thermal inertia exists within the cooling tower pool, circulating water pipes, and condenser water chambers. When the circulating water temperature drops, it can maintain this low temperature for a certain period, thus giving the circulating cooling water system a certain "virtual energy storage" capacity. Utilizing this characteristic, cooling capacity can be increased in advance during periods of low electricity prices, shifting some of the plant's electricity consumption to these lower-priced periods, and reducing power consumption by auxiliary equipment at the cooling end during periods of high electricity prices, thereby achieving cross-period transfer of plant electricity consumption and optimizing revenue.

[0074] When the predicted electricity price sequence indicates the possibility of a period of high electricity prices in the future, a forward-looking bias adjustment is applied to the already selected Pareto optimal operating solution during the current low electricity price operation phase. This bias adjustment process is not performed independently of the dynamic safe operating range, but rather moves the operating point along the Pareto front towards stronger cooling within the entire safety constraint range. Stronger cooling corresponds to lower circulating water temperature, lower condenser back pressure, and higher cold-end heat exchange capacity.

[0075] During the forward bias process, the circulating cooling water flow rate is increased by raising the operating frequency of the circulating water pump, while the cooling fan speed is increased to enhance the cooling tower's heat dissipation capacity. With the increased circulating water flow rate, the condenser's heat exchange capacity improves, allowing the circulating water to remove more heat from the turbine exhaust steam. The increased cooling fan speed enhances the cooling tower's airflow capacity, further improving the circulating water's cooling effect. Under the combined action of the circulating water pump and cooling fan, the circulating water temperature gradually decreases below the target value for normal operation, thus creating an additional cooling capacity reserve.

[0076] The resulting cold energy reserves are mainly stored in the cooling tower water pool, the main circulating water pipeline, and the condenser circulating water system. Due to the large thermal inertia of the circulating cooling water system, the low-temperature circulating water will not quickly return to its original temperature in a short period of time. Therefore, it can continue to maintain a low circulating water temperature and a low back pressure level during future periods of high electricity prices.

[0077] Throughout the precooling process, the operating point remains within the dynamic safe operating range. The operating frequency of the circulating water pump, the speed of the cooling fan, the rate of change of water temperature, and the range of back pressure changes are all limited by the dynamic safety boundary, thereby avoiding problems such as increased thermal stress, increased equipment impact, or instability in the circulating water system due to excessive precooling. At the same time, the precooling range is not a fixed value, but changes dynamically with the predicted electricity price level, the duration of future high electricity prices, and the current operating status of the cold end system.

[0078] When the predicted period of high electricity prices arrives, the cold-end system switches from pre-cooling mode to economic mode. At this time, the operating frequency of the circulating water pumps and the speed of the cooling fans gradually decrease, reducing the power consumption of the cold-end auxiliary equipment, thereby lowering the plant's power load and increasing the net power output to the grid. Because a low-temperature circulating water reserve has already been established, even with reduced circulating water pump operating frequency and cooling fan speed, the circulating cooling water system can still maintain a low circulating water temperature and a low turbine back pressure level by relying on the stored cooling capacity.

[0079] By releasing previously stored cooling capacity, the rapid rise in back pressure can be suppressed while reducing power consumption of auxiliary equipment at the cold end. This prevents condenser vacuum deterioration caused by reduced load operation of auxiliary equipment, thereby maintaining high power generation efficiency and high grid-connected power. During periods of high electricity prices, the increase in net grid-connected power can directly increase electricity sales revenue. Therefore, this operating mode can effectively improve the economic profitability of coal-fired units in the electricity spot market.

[0080] Proactive bias regulation not only transforms the operation mode of the cold-end system from "real-time response" to "predictive response," but also converts the thermal inertia of the circulating cooling water system into usable virtual energy storage capacity. Traditional cold-end optimization typically only performs static adjustments based on the current operating conditions, while proactive bias regulation can use future electricity price forecasts to adjust the cold-end operating state in advance, thereby achieving operational optimization across time scales.

[0081] By proactively enhancing cooling during periods of low electricity prices and releasing cooling capacity during periods of high electricity prices, some of the plant's electricity consumption can be shifted from high-price periods to low-price periods. This reduces the proportion of auxiliary equipment power consumption during periods of high electricity prices and increases the effective grid-connected power during these periods. Furthermore, because operational adjustments are always constrained by a dynamic safe operating range, it is possible to improve economic benefits while ensuring the operational safety and long-term stability of the cold-end equipment.

[0082] After obtaining the predicted electricity price sequence for a future set period, continuous rolling analysis is conducted on the future electricity price change trend. When the prediction results indicate that there will be a high electricity price range in the future, the operation mode of the cooling system changes from the traditional real-time response mode to a forward-looking adjustment mode with predictive capabilities. By adjusting the operating status of the circulating cooling water system in advance, the cooling capacity is stored in advance and released later, thereby improving the overall operating benefits of the coal-fired unit under different electricity price stages.

[0083] The cooling tower pool, main circulating water pipeline, and condenser water chamber in a circulating cooling water system all possess significant heat capacity characteristics, and the temperature change of the circulating water exhibits a marked lag effect. Therefore, the system can maintain a relatively low temperature for a certain period of time. Utilizing this thermal inertia characteristic, cooling capacity can be enhanced in advance during periods of low electricity prices, storing the cold energy generated by the low-temperature circulating water within the cooling water system. In the future, during periods of high electricity prices, the stored cold energy can be used to maintain a low back pressure operating state, thereby reducing the power consumption of auxiliary equipment at the cold end during periods of high electricity prices.

[0084] When high electricity prices are predicted for the future, a forward-looking bias adjustment is made to the currently selected operating schemes. This bias adjustment process is carried out within the dynamic safe operating range, with the operating point moving along the Pareto front towards stronger cooling. Stronger cooling corresponds to higher circulating cooling capacity and lower circulating water temperature. This is achieved by increasing the operating frequency of the circulating water pumps to increase the circulating water flow rate and increasing the cooling fan speed to enhance the cooling tower's heat dissipation capacity, thereby improving the overall heat exchange efficiency of the circulating cooling water system.

[0085] As the circulating water flow rate and heat dissipation capacity increase, the circulating water temperature gradually decreases below the target value for normal operation, forming an additional cooling capacity reserve. The resulting low-temperature circulating water can be maintained within the circulating water system for a certain period of time, with the cooling capacity mainly stored in the cooling tower water pool, circulating water pipes, and condenser heat exchange area. Due to the large thermal inertia of the circulating cooling water system, even if the operating load of the cold-end auxiliary equipment is subsequently reduced, the system can still rely on the previously stored cooling capacity to maintain a low circulating water temperature and a low turbine back pressure.

[0086] With the arrival of periods of high electricity prices, the cold-end system gradually switches from pre-cooling mode to economic operation mode. At this time, the operating frequency of the circulating water pumps and the speed of the cooling fans are reduced, decreasing the power consumption of the cold-end auxiliary equipment, thereby reducing the plant's power load and increasing the net power output to the grid. Because a cooling capacity reserve has already been established, the circulating water temperature will not rise immediately, thus maintaining a low back pressure while reducing auxiliary equipment power consumption and preventing rapid deterioration of the condenser vacuum.

[0087] By releasing previously stored cooling capacity, low plant power consumption can be achieved during periods of high electricity prices, thereby increasing effective electricity sales revenue during these periods. Simultaneously, the cooling capacity release process can smooth out back pressure fluctuations, reduce operational instability caused by changes in circulating water flow, and improve the operational stability of the cold-end system.

[0088] The entire forward bias adjustment process is always constrained by the dynamic safe operating range. The operating frequency of the circulating water pump, the speed of the cooling fan, the rate of change of water temperature, and the range of change of back pressure are all within the safe boundary, thereby avoiding problems such as increased thermal stress, aggravated equipment impact, and abnormal operation of the circulating water system caused by excessive cooling.

[0089] By utilizing the thermal inertia of the circulating cooling water system to form an operation mode of "storing cold before peak hours and releasing cold during peak hours", it is possible to transfer plant power between different electricity price periods, arrange more auxiliary equipment power consumption to be completed during low-price electricity periods, and reduce the proportion of cold-end auxiliary equipment power consumption during high-price electricity periods, thereby improving the overall economic operation capability and operational flexibility of coal-fired units in the electricity spot market environment.

[0090] This invention constructs a coupled dynamic safe operating range in real time using a turbine back pressure safety sub-model, a circulating water pump safety sub-model, and a cold-end thermal stress safety sub-model. This allows for dynamic adjustment of safety boundaries based on changes in unit load, circulating water temperature, and equipment operating status. Compared to traditional fixed-limit control methods, this more realistically reflects the actual operating capacity of the cold-end system of a coal-fired unit. Since equipment safety margins vary significantly under different operating conditions, fixed safety boundaries are prone to insufficient protection or overly conservative operation. The dynamic safe operating range, however, refreshes safety constraints in real time during each optimization cycle, ensuring that the optimized operation of the cold-end system remains within the safe and feasible domain. This effectively reduces operational risks such as turbine last-stage blade vibration, circulating water pump cavitation, and thermal stress shock, improving the operational stability and reliability of the cold-end system.

[0091] This invention constructs a dual-objective Pareto optimization framework that coordinates economic efficiency and energy consumption. During the optimization process, it preserves the objective trade-off between economic benefits and coal consumption for power generation, avoiding the subjective problems caused by manually setting weights in traditional single-objective weighted optimization methods. By introducing an adaptive screening mechanism based on the ratio of electricity to coal value, the optimization strategy can be automatically switched according to the real-time relationship between electricity and coal prices. During periods of high electricity prices, priority is given to maximizing electricity sales revenue; during periods of low electricity prices, priority is given to minimizing coal consumption; and during periods of stable electricity prices, both economic efficiency and energy conservation are considered. This achieves dynamic adaptive adjustment of the cold-end operation strategy under different market conditions. Compared to traditional fixed operation modes, it can more effectively adapt to the fluctuating characteristics of electricity prices in the spot market, improving the overall operational efficiency and market competitiveness of coal-fired units throughout their entire lifecycle.

[0092] This invention incorporates equipment lifespan depreciation costs, determined by both the frequency modulation amplitude and the adjustment frequency, into the economic objective function. It integrates the mechanical wear, thermal fatigue, and equipment impact caused by frequent adjustments of circulating water pumps and cooling fans into a comprehensive economic evaluation system, thereby avoiding over-optimization based solely on short-term economic gains. Simultaneously, by dynamically constraining the operating frequency of the circulating water pump, the rate of water temperature change, and the equipment adjustment amplitude within a safe operating range, it effectively suppresses high-frequency, large-amplitude adjustment behavior, reducing the risk of equipment damage caused by long-term, frequent operation of cold-end auxiliary equipment. Compared to traditional control methods that solely pursue short-term gains, this invention improves operational economy while protecting equipment lifespan, extending the long-term stable operating cycle of critical auxiliary equipment such as circulating water pumps and cooling fans.

[0093] This invention provides, for example Figure 2 The system shown is an intelligent optimization system for the cold end system of a coal-fired power unit that takes electricity prices into account. It includes a data sensing and prediction module, a core decision optimization module, and an execution and feedback module. The data perception and prediction module collects unit operating parameters in real time, including generator power, back pressure, circulating water temperature, circulating water pump operating status, and cooling fan operating status. It connects to the real-time node marginal electricity price of the electricity market and has a built-in time-series neural network model for predicting electricity prices and loads in future periods. The core decision optimization module receives unit operating parameters, real-time node marginal electricity price, and predicted electricity price sequence output by the data perception and prediction module. It embeds a dual-objective optimization model to solve for the optimal back pressure and corresponding cold-end equipment control commands in real time within the dynamic safe operation range. The dual-objective optimization model includes economic objectives and energy consumption objectives. The economic objectives include net revenue from grid connection, coal consumption cost, and equipment life loss cost. The energy consumption objective is represented by the power supply coal consumption rate, and the Pareto front solution is adaptively screened based on the ratio of electricity price to coal price. The execution and feedback module receives the cold end equipment control commands output by the core decision optimization module, sends the cold end equipment control commands to the actuators such as the circulating water pump frequency converter and the cooling fan frequency converter, and sends back confirmation of the execution status.

[0094] The present invention provides an intelligent optimization method for the cold end system of a coal-fired power unit that takes into account electricity prices. This method is implemented through the aforementioned intelligent optimization system for the cold end system of a coal-fired power unit that takes into account electricity prices. For details of the specific method and process of the intelligent optimization system for the cold end system of a coal-fired power unit that takes into account electricity prices, please refer to the embodiment of the above-mentioned intelligent optimization method for the cold end system of a coal-fired power unit that takes into account electricity prices, which will not be repeated here.

[0095] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for intelligent optimization of the cold-end system of a coal-fired power unit considering electricity prices, characterized in that, Includes the following steps: The system acquires real-time node electricity prices, predicted electricity price sequences, and operating parameters of coal-fired power units, including generator output power, real-time back pressure, circulating water temperature, circulating water pump operating frequency, and cooling fan speed. For the operating parameters of coal-fired units, the dynamic safe operating range is calculated using the turbine back pressure safety sub-model, the circulating water pump safety sub-model, and the cold end thermal stress safety sub-model. The dynamic safe operating range includes the back pressure safety range, the circulating water pump frequency safety range, and the water temperature change rate constraint. A dual-objective optimization model is constructed within the dynamic safe operation range. The dual-objective optimization model includes an economic objective function and an energy consumption objective function. The economic objective function includes net on-grid power, electricity price, coal consumption cost, and equipment life loss cost. The energy consumption objective function is characterized by the power supply coal consumption rate. A multi-objective evolutionary algorithm is used to iteratively solve the economic objective function and the energy consumption objective function to generate a Pareto front set composed of non-dominated solutions; Calculate the ratio of electricity price to coal price, and perform adaptive screening based on the Pareto front set. When the ratio of electricity price to coal price is higher than a preset threshold, select the economic priority solution; when the ratio of electricity price to coal price is lower than a preset threshold, select the energy-saving priority solution; when the ratio of electricity price to coal price is between the two preset thresholds, select the equilibrium solution. For the high electricity price period in the predicted electricity price sequence, increase the operating frequency of the circulating water pump and the speed of the cooling fan during the low electricity price period to form a cooling capacity reserve, and reduce the operating frequency of the circulating water pump and the speed of the cooling fan during the high electricity price period to release the cooling capacity; The operation results are constrained and verified. Once the dynamic safe operating range is met, control commands for the circulating water pump and cooling fan are output, and the next optimization cycle begins.

2. The intelligent optimization method for the cold-end system of a coal-fired power unit considering electricity prices according to claim 1, characterized in that, The following steps are involved in the collaborative data processing related to electricity price forecasting and operational condition data collection: Access real-time node electricity price data from the electricity market, read real-time electricity price information corresponding to different time points, and record the time series of electricity price changes; A time-series neural network prediction model is constructed by importing historical electricity price data, historical load data, and historical operating condition data, and rolling predictions are made for future time periods to generate a future electricity price change sequence. Collect generator output power, unit real-time back pressure, circulating water inlet temperature, cooling tower inlet and outlet water temperatures, circulating water pump operating frequency, number of circulating water pumps in operation, and cooling fan speed information, and record the corresponding time tags simultaneously. Real-time electricity price information, predicted electricity price sequences, and unit operation information are compiled to form a cold-end system operation dataset, which is then transmitted to the cold-end optimization computing unit for operation status analysis.

3. The intelligent optimization method for the cold-end system of a coal-fired power unit considering electricity prices according to claim 1, characterized in that, The following steps are taken to perform operational condition analysis and processing on the dynamic generation process of the safe operating boundary of the cold-end system: Establish a turbine back pressure safety sub-model, input unit load parameters, circulating water temperature parameters, and condenser heat exchange status parameters, and read turbine operating condition information; Calculate the upper and lower safe back pressure limits corresponding to the current operating conditions, form the turbine back pressure operating range, and output the corresponding back pressure boundary data; Construct a safety sub-model for the circulating water pump, retrieve the characteristic curves of the circulating water pump and the resistance parameters of the circulating water pipeline, and calculate the operating frequency range, frequency variation range, and circulating water flow variation state of the circulating water pump. A cold-end thermal stress safety sub-model is introduced to calculate the circulating water temperature change rate, circulating water pump frequency adjustment rate, and thermal stress change information, and integrate them to form a dynamic safe operating range.

4. The intelligent optimization method for the cold-end system of a coal-fired power unit considering electricity prices according to claim 1, characterized in that, The following steps are taken to perform target analysis on the coordinated adjustment of cold-end system revenue and energy consumption: Establish an economic objective function, import information on net on-grid power, real-time electricity price, coal consumption rate, and standard coal unit price, and generate parameters for calculating economic benefits. The data includes the frequency variation of the circulating water pump, the speed variation of the cooling fan, and the number of adjustment actions of the auxiliary equipment at the cold end, and generates equipment life loss cost data. Construct an energy consumption objective function corresponding to the coal consumption rate of power supply, read the coal consumption data of power supply under different operating conditions, and form energy consumption evaluation parameters for the cold end system; The economic objective function and the energy consumption objective function are integrated to form a dual-objective collaborative operation model, and the objective function data set corresponding to different operating states is output.

5. The intelligent optimization method for the cold-end system of a coal-fired power unit considering electricity prices according to claim 1, characterized in that, The following steps are taken to screen operational schemes based on the multi-objective optimization process of the cold-end system: Import the dynamic safe operating range and the dual-objective optimization model, and read the back pressure operating parameters, circulating water pump operating parameters and cooling fan operating parameters; The multi-objective evolutionary algorithm is invoked to generate multiple sets of candidate running schemes, and population initialization, crossover calculation, and mutation calculation are performed on the candidate running schemes; Perform non-dominated sorting calculations, sort and analyze the economic objective function values ​​and energy consumption objective function values ​​corresponding to different operating schemes, and record the non-dominated operating status; Select non-dominated operating solutions that satisfy the dynamic safe operating range, form the Pareto front set, and output the back pressure operating results corresponding to different operating schemes.

6. The intelligent optimization method for the cold-end system of a coal-fired power unit considering electricity prices according to claim 1, characterized in that, The steps for adjusting operational strategies based on the linkage between electricity and coal prices are as follows: Obtain real-time electricity price information and standard coal unit price information, and establish data on the correspondence between electricity price and coal price; Calculate the ratio of electricity price to coal price, identify the current electricity price operating status within a range, and output the corresponding electricity price range information; Determine the economic range corresponding to the current operating stage, match the economic priority strategy, energy-saving priority strategy, or equilibrium operation strategy, and read the corresponding operating scheme of the Pareto front set; Perform a screening analysis on the undominated operating solutions of the Pareto front set, and output the corresponding operating schemes and corresponding back pressure operating parameters.

7. The intelligent optimization method for the cold-end system of a coal-fired power unit considering electricity prices according to claim 1, characterized in that, The following steps are taken to adjust the cold load pre-storage based on the thermal inertia change process of the cold end system: Analyze and predict the trend of electricity price series changes, identify the high electricity price operating range in the future set period, and record the corresponding time range; Retrieve the Pareto front-focused operating scheme and read the operating information of circulating water temperature, circulating water pump operating frequency, and cooling fan speed; Increase the operating frequency of the circulating water pump and the speed of the cooling fan to increase the circulating water flow and the heat dissipation capacity of the cooling tower, reduce the circulating water temperature and form a cold energy reserve; Adjust the operating load of the cold-end auxiliary equipment, reduce the operating frequency of the circulating water pump and the speed of the cooling fan, and maintain the operating status of the circulating water temperature and back pressure by pre-storing cold energy.

8. The intelligent optimization method for the cold-end system of a coal-fired power unit considering electricity prices according to claim 1, characterized in that, The following steps are taken to analyze the lifespan loss of auxiliary equipment in the cold end: Collect statistics on the variation range of the operating frequency of the circulating water pump, the variation range of the cooling fan speed, and the corresponding adjustment time information; Record the number of adjustment actions of the circulating water pump and cooling fan, generate equipment adjustment frequency data, and organize the corresponding operating status information; Import frequency variation amplitude data and adjustment frequency data, calculate equipment life loss cost, and form a set of equipment life loss parameters; The cost of equipment life loss is imported into the economic objective function, and the evaluation results of equipment life loss corresponding to different operating states are output.

9. The intelligent optimization method for the cold-end system of a coal-fired power unit considering electricity prices according to claim 1, characterized in that, The following steps are taken to perform operational status verification processing on the control command output process of the cold-end system: Receive the optimized operation results of the cold end system and read the corresponding back pressure operating parameters, circulating water operating parameters, and cooling fan operating parameters; Verify the back pressure operating boundary, the rate of change of circulating water temperature, the range of change of circulating water pump frequency, and the operating status of circulating water flow. The operating frequency of the circulating water pump, the number of circulating water pumps in operation, the speed of the cooling fan, and the operating status of the cold-end auxiliary equipment were checked, and the corresponding operation verification results were compiled. Output control commands to the circulating water pump and cooling fan, start the next cycle of optimized operation calculation, and update the current operating status data.

10. An intelligent optimization system for the cold-end system of a coal-fired power unit considering electricity prices, used to implement the intelligent optimization method for the cold-end system of a coal-fired power unit considering electricity prices as described in any one of claims 1-9, characterized in that, It includes a data perception and prediction module, a core decision optimization module, and an execution and feedback module: The data perception and prediction module collects unit operating parameters in real time, including generator power, back pressure, circulating water temperature, circulating water pump operating status, and cooling fan operating status. It connects to the real-time node marginal electricity price of the electricity market and has a built-in time-series neural network model for predicting electricity prices and loads in future periods. The core decision optimization module receives unit operating parameters, real-time node marginal electricity price, and predicted electricity price sequence output by the data perception and prediction module. It embeds a dual-objective optimization model to solve for the optimal back pressure and corresponding cold-end equipment control commands in real time within the dynamic safe operation range. The dual-objective optimization model includes economic objectives and energy consumption objectives. The economic objectives include net revenue from grid connection, coal consumption cost, and equipment life loss cost. The energy consumption objective is represented by the power supply coal consumption rate, and the Pareto front solution is adaptively screened based on the ratio of electricity price to coal price. The execution and feedback module receives the cold end equipment control commands output by the core decision optimization module, sends the cold end equipment control commands to the actuators of the circulating water pump frequency converter and the cooling fan frequency converter, and sends back confirmation of the execution status.

Images