Electric heating collaborative water supply temperature raising system for supercritical coal-fired unit

Abstract

The invention provides an electric heating collaborative water supply temperature raising system for a supercritical coal-fired unit. The electric heating collaborative water supply temperature raising system for the supercritical coal-fired unit comprises an electric heater, a steam extraction heater and a control system, and the control system comprises a data collection module used for collecting a power grid dispatching instruction, new energy output, real-time electricity price and unit operation parameters in real time; the multi-time-scale load prediction module is used for predicting unit loads of different time scales based on a deep learning algorithm; and the multi-objective optimization decision module optimizes the distribution ratio of the electric heating power to the steam extraction amount by taking the lowest coal consumption, the lowest peak regulation cost, the highest new energy consumption and the lowest equipment life loss as objectives. The electric heating collaborative water supply temperature raising system for the supercritical coal-fired unit has the advantages that the peak regulation flexibility, the operation economy and the equipment safety of the unit can be remarkably improved, and multi-objective optimization is achieved.

Description

Technical Field

[0001] This invention relates to the field of coal-fired power generation technology, and in particular to an electrothermal combined feedwater heating system for supercritical coal-fired units. Background Technology

[0002] With the ongoing transformation of my country's energy structure, the installed capacity of new energy sources such as wind power and photovoltaics is rapidly increasing, profoundly changing the characteristics of power grid operation. Traditional supercritical coal-fired units primarily rely on steam extraction heating for their feedwater systems, revealing significant technical bottlenecks when undertaking deep peak-shaving tasks: steam extraction parameters deteriorate as load decreases, leading to unreliable feedwater temperatures and impacting unit efficiency and safety; the system also suffers from high thermal inertia and slow response, making it difficult to adapt to minute-level frequency regulation requirements. While existing electric heating auxiliary technologies can alleviate these problems, they generally suffer from limitations such as simplistic control strategies and one-sided optimization objectives. They often employ simple feedback control based on temperature deviations, lacking the integrated utilization of multi-source information such as grid dispatch instructions, new energy output forecasts, and electricity market signals, thus failing to achieve multi-objective coordinated optimization of economy, environmental protection, and flexibility. Especially with the gradual improvement of market mechanisms such as real-time electricity pricing and carbon trading, traditional systems lack intelligent decision-making capabilities, making it difficult to fully realize the technical and economic potential of coordinated electric-thermal peak shaving.

[0003] Therefore, it is necessary to provide a new electrothermal combined feedwater heating system for supercritical coal-fired units to solve the above-mentioned technical problems. Summary of the Invention

[0004] The technical problem solved by this invention is to provide an electrothermal synergistic feedwater heating system for supercritical coal-fired units that can significantly improve the unit's peak-shaving flexibility, operating economy, and equipment safety, and achieve multi-objective optimization.

[0005] To solve the above-mentioned technical problems, the present invention provides an electrothermal combined feedwater temperature raising system for supercritical coal-fired units, comprising: an electric heater, an extraction steam heater, and a control system, wherein the control system comprises:

[0006] The data acquisition module is used to collect real-time power grid dispatch instructions, new energy output, real-time electricity prices, and unit operating parameters.

[0007] The multi-timescale load forecasting module uses deep learning algorithms to predict unit load at different time scales.

[0008] The multi-objective optimization decision module optimizes the allocation ratio of electric heating power and steam extraction with the objectives of minimizing coal consumption, minimizing peak shaving costs, maximizing new energy consumption, and minimizing equipment lifespan loss.

[0009] The electricity price response module adjusts the power and heat coordination strategy based on real-time electricity prices and carbon trading prices.

[0010] The fuzzy adaptive coordinated control module coordinates the control of the electric heater and the extraction steam regulating valve.

[0011] Preferably, the multi-timescale load forecasting module includes:

[0012] The ultra-short-term prediction module uses an LSTM neural network combined with an attention mechanism to predict the load for 5-15 minutes.

[0013] The short-term forecasting module uses a CNN-LSTM hybrid network to forecast loads from 1 to 4 hours.

[0014] The intraday forecasting module uses a Transformer architecture to forecast load over 4-24 hours.

[0015] Preferably, the multi-objective optimization decision module employs an improved NSGA-III algorithm, with the objective function being:

[0016] ;

[0017] in, Let coal consumption be the objective function. The objective function for peak shaving cost is... Let the objective function be the curtailment rate of renewable energy. The objective function is the equipment lifespan loss. , , , It is a dynamic weighting coefficient that is adjusted in real time according to the power grid demand.

[0018] Preferably, the electricity price response module includes an electricity price-carbon price coupled response model, and the comprehensive cost calculation function is:

[0019] ;

[0020] in, Electric heating power, For real-time electricity prices, To contribute power for peak shaving The unit price for peak shaving compensation. For carbon emissions, This refers to the price of carbon trading.

[0021] Preferably, the fuzzy adaptive coordination control module includes:

[0022] Main controller: Fuzzy PID controller, with fuzzy rules based on temperature deviation e and the rate of change of deviation. Adjustment , , parameter;

[0023] Feedforward compensator: based on load change rate Pre-allocated heating power;

[0024] Coordinator: The game theory approach is used to resolve the coupling conflict between electric heating and steam extraction control.

[0025] Preferably, it also includes a multi-mode operation module, providing at least four operation modes: deep peak shaving mode, economically optimal mode, new energy consumption mode, and safety margin mode.

[0026] Preferably, the economically optimal mode includes a thermal storage control strategy based on real-time electricity prices, where the electricity price is below a threshold. Electric heating and thermal storage are activated when the electricity price is above a threshold. Reduce electric heating and utilize stored heat.

[0027] The present invention also provides an operation method for an electrothermal combined feedwater temperature raising system for a supercritical coal-fired unit, comprising the following steps:

[0028] S1: Real-time acquisition of power grid dispatch instructions, new energy output forecasts, real-time electricity prices, and unit operating parameters;

[0029] S2: Utilize a multi-timescale load forecasting module to predict the unit load at different time scales in the future;

[0030] S3: With coal consumption, peak shaving, new energy consumption, and equipment life as objectives, the optimal power and heat allocation ratio is solved through a multi-objective optimization decision-making module.

[0031] S4: Adjust the power-heat coordination strategy through the electricity price response module based on real-time electricity price and carbon price;

[0032] S5: The electric heater and the extraction steam regulating valve are coordinated and controlled through the fuzzy adaptive coordination control module;

[0033] S6: Based on actual operating data, dynamically correct the prediction model and optimize model parameters.

[0034] Preferred multi-objective optimization weight coefficients ~ The dynamic adjustment rules are as follows:

[0035] When the power grid's peak-shaving demand is urgent, increase Weight;

[0036] When the rate of curtailment of renewable energy increases, increase Weight;

[0037] When the unit's operating time exceeds 60% of its design life, increase Weights.

[0038] Preferably, in step S5, the specific process of fuzzy adaptive coordinated control includes:

[0039] (1) Calculate the water supply temperature setpoint Compared with actual value deviation e and rate of change of deviation ;

[0040] (2) Determine the PID parameter adjustment amount using a fuzzy rule table , , ;

[0041] (3) Based on load change rate Calculate feedforward compensation ;

[0042] (4) Using game theory to coordinate electric heating control commands and extraction steam control commands Given the conflict, find the Nash equilibrium point.

[0043] Compared with related technologies, the electrothermal combined feedwater temperature raising system for supercritical coal-fired units provided by this invention has the following beneficial effects:

[0044] This invention provides an electrothermal synergistic feedwater heating system for supercritical coal-fired power units, which can significantly improve the overall operational performance of supercritical coal-fired power units in new power systems. Through intelligent multi-objective optimization and coordinated control, it can effectively enhance the unit's peak-shaving flexibility and response speed, enabling it to quickly adapt to frequent fluctuations in grid load and providing key support for the stable consumption of high-proportion renewable energy. By optimizing the spatiotemporal distribution of electrothermal power, it can significantly reduce the unit's operating coal consumption and overall cost, while improving its ability to participate in electricity market bidding. Through intelligent coordinated control strategies, it can mitigate the thermal stress impact of frequent load changes on key equipment, helping to extend the unit's service life. Attached Figure Description

[0045] Figure 1 This is a schematic diagram of the electrothermal combined feedwater temperature raising system for supercritical coal-fired units provided by the present invention.

[0046] Figure 2 The flowchart illustrates the operation method of the electrothermal combined feedwater temperature raising system for supercritical coal-fired units provided by this invention. Detailed Implementation

[0047] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0048] Please refer to the following: Figure 1 and Figure 2 ,in, Figure 1This is a schematic diagram of the electrothermal combined feedwater temperature raising system for supercritical coal-fired units provided by the present invention. Figure 2 A flowchart illustrating the operation method of an electrothermal combined feedwater heating system for a supercritical coal-fired unit provided by the present invention. The electrothermal combined feedwater heating system for a supercritical coal-fired unit includes: an electric heater, a steam extraction heater, and a control system, wherein the control system includes:

[0049] The data acquisition module is used to collect multi-dimensional operational data in real time, including power grid dispatch instructions, new energy output forecasts, real-time electricity price signals, and unit operating parameters. The data acquisition module interacts with the power plant monitoring system (SIS) and distributed control system (DCS) through a high-speed data bus to ensure the real-time performance and accuracy of the data.

[0050] A multi-timescale load forecasting module, which employs a hybrid deep learning architecture to achieve accurate load forecasting for units at different time scales, includes:

[0051] Ultra-short-term forecasting module: It adopts a long short-term memory (LSTM) neural network combined with an attention mechanism to predict ultra-short-term unit load changes of 5-15 minutes, providing a basis for real-time control;

[0052] Short-term forecasting module: Employs a hybrid model of convolutional neural network and long short-term memory network (CNN-LSTM) to predict short-term unit load trends of 1-4 hours for optimized scheduling;

[0053] Intraday forecasting module: Adopting the Transformer architecture, it forecasts the intraday unit load distribution for 4-24 hours and supports day-ahead planning.

[0054] The multi-objective optimization decision module adopts an improved third-generation non-dominated sorting genetic algorithm (NSGA-III) to achieve multi-objective collaborative optimization. The module aims to optimize the allocation ratio of electric heating power and steam extraction volume with the objectives of minimizing coal consumption, minimizing peak shaving costs, maximizing new energy consumption, and minimizing equipment lifespan loss.

[0055] The objective function to be optimized is:

[0056] ;

[0057] in, Let coal consumption be the objective function. The objective function for peak shaving cost is... Let the objective function be the curtailment rate of renewable energy. The objective function is the equipment lifespan loss. , , , It is a dynamic weighting coefficient that is adjusted in real time according to the power grid demand.

[0058] The electricity price response module is used to adjust the power and heat coordination strategy based on real-time electricity prices and carbon trading prices. This module incorporates electricity price signals and carbon trading prices into the optimization process, establishing an electricity price-carbon price coupled response model. The comprehensive cost calculation function is as follows:

[0059] ;

[0060] in, This represents the electric heating power, indicating the energy consumption. Real-time electricity prices are used to reflect the supply and demand situation in the electricity market. The power contribution for peak shaving is used to reflect the degree of support the unit provides for grid stability; The peak-shaving compensation unit price is the standard by which the power grid compensates for peak-shaving services. Carbon emissions represent environmental costs; The carbon trading price reflects the carbon market conditions.

[0061] A fuzzy adaptive coordinated control module coordinates the control of the electric heater and the extraction steam regulating valve. This module employs intelligent control to resolve the coupling control between electric heating and extraction steam heating, including:

[0062] Main controller: Employs a fuzzy PID controller. The fuzzy PID control algorithm is based on the temperature deviation e and the rate of change of the deviation. Adjustment , , parameter;

[0063] Feedforward compensator: based on load change rate Pre-allocate electrical heating power to improve system response speed;

[0064] Coordinator: The game theory approach is used to resolve the coupling conflict between electric heating and steam extraction control, and to seek the optimal Nash equilibrium point.

[0065] It also includes a multi-mode operation module, which provides at least four operation modes to adapt to different power grid demands and operating conditions. The four operation modes include:

[0066] Deep peak shaving mode: prioritizes the use of electric heating to quickly respond to the grid's peak shaving needs;

[0067] Optimal economic model: Thermal storage control strategy based on real-time electricity price, when the electricity price is below a threshold. Electric heating and thermal storage are activated when the electricity price is above a threshold. Reduce electric heating and utilize stored heat;

[0068] New energy consumption mode: The ratio of electricity to heat is automatically adjusted according to the fluctuation of new energy output to maximize the consumption of new energy;

[0069] Safety margin mode: Retains sufficient steam extraction heating capacity to ensure safe and stable system operation.

[0070] The present invention also provides an operation method for an electrothermal combined feedwater temperature raising system for a supercritical coal-fired unit, comprising the following steps:

[0071] S1: Data Acquisition and Processing

[0072] Real-time collection of diverse data such as power grid dispatch instructions, new energy output forecasts, real-time electricity prices, and unit operating parameters; and data quality verification and preprocessing.

[0073] S2: Multi-timescale load forecasting

[0074] Using hybrid deep learning models to predict unit loads at different time scales in the future provides data support for optimization decisions;

[0075] S3: Multi-objective optimization decision-making:

[0076] With coal consumption, peak-shaving cost, new energy consumption and equipment life as objectives, the improved NSGA-III algorithm is used to solve the optimal power and heat distribution ratio.

[0077] S4: Adjustment of Electricity Price Response Strategy

[0078] Based on real-time electricity and carbon price signals, the power-heat synergy strategy is dynamically adjusted to achieve economical operation.

[0079] S5: Intelligent Coordination Control

[0080] A fuzzy adaptive control algorithm is used to achieve precise coordinated control of the electric heater and the extraction steam regulating valve, specifically including:

[0081] S51: Calculate the feedwater temperature setpoint Compared with actual value deviation e and rate of change of deviation ;

[0082] S52: Determine PID parameter adjustment amount using fuzzy rule table , , ;

[0083] S53: Based on load change rate Calculate feedforward compensation ;

[0084] S54: Using game theory to coordinate electric heating control commands and extraction steam control commands Given the conflict, find the Nash equilibrium point;

[0085] S6: Adaptive model parameter correction:

[0086] Based on actual operational data, the prediction model is dynamically adjusted and model parameters are optimized to ensure the long-term performance of the system, with weighting coefficients... ~ The dynamic adjustment rules specifically include:

[0087] When the power grid's peak-shaving demand is urgent, increase Weighting is prioritized to meet peak-shaving requirements;

[0088] When the rate of curtailment of renewable energy increases, increase Weighting and enhancing the capacity for renewable energy consumption;

[0089] When the unit's operating time exceeds 60% of its design life, increase Weighting extends the lifespan of equipment.

[0090] The working principle of the electrothermal synergistic feedwater temperature raising system for supercritical coal-fired units provided by this invention is as follows:

[0091] first.

[0092] Compared with related technologies, the electrothermal combined feedwater temperature raising system for supercritical coal-fired units provided by this invention has the following beneficial effects:

[0093] This invention provides an electrothermal co-current feedwater heating system for supercritical coal-fired power units. The outer frame 1 and the inner frame 3 are fixedly connected by the guide shaft 21. One end of the torsion spring 22 is fixed to the guide shaft 21, and the other end of the torsion spring 22 is fixed to the fixing sleeve 23. After the latch 6 is opened, the inner frame 3 automatically springs up under the elastic force of the torsion spring 22, making operation more convenient and making reasonable use of the windowsill space. This facilitates indoor ventilation and heat dissipation, and also makes it easy to clean the dust accumulated between the inner frame 3 and the outer frame 1. When the inner frame 3 is opened, it is perpendicular to the outer frame 1, which does not affect the light and can effectively prevent rainwater from entering the room from the windowsill, thus improving the waterproof performance of the windowsill. The support structure 7 is connected between the inner frame 3 and the outer frame 1, and the inner frame 3, the outer frame 1, and the support structure 7 form a spatial triangular structure, which improves the stability of the inner frame 3.

[0094] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. An electrothermal combined feedwater heating system for supercritical coal-fired units, comprising an electric heater, an extraction steam heater, and a control system, characterized in that: The control system includes: The data acquisition module is used to collect real-time power grid dispatch instructions, new energy output, real-time electricity prices, and unit operating parameters. The multi-timescale load forecasting module uses deep learning algorithms to predict unit load at different time scales. The multi-objective optimization decision module optimizes the allocation ratio of electric heating power and steam extraction with the objectives of minimizing coal consumption, minimizing peak shaving costs, maximizing new energy consumption, and minimizing equipment lifespan loss. The electricity price response module adjusts the power and heat coordination strategy based on real-time electricity prices and carbon trading prices. The fuzzy adaptive coordinated control module coordinates the control of the electric heater and the extraction steam regulating valve.

2. The electrothermal combined feedwater heating system for supercritical coal-fired units according to claim 1, characterized in that, The multi-timescale load forecasting module includes: The ultra-short-term prediction module uses an LSTM neural network combined with an attention mechanism to predict the load for 5-15 minutes. The short-term forecasting module uses a CNN-LSTM hybrid network to forecast loads from 1 to 4 hours. The intraday forecasting module uses a Transformer architecture to forecast load over 4-24 hours.

3. The electrothermal combined feedwater heating system for supercritical coal-fired units according to claim 1, characterized in that, The multi-objective optimization decision module employs an improved NSGA-III algorithm, with the objective function being: ； in, Let coal consumption be the objective function. The objective function for peak shaving cost is... Let the objective function be the curtailment rate of renewable energy. The objective function is the equipment lifespan loss. , , , It is a dynamic weighting coefficient that is adjusted in real time according to the power grid demand.

4. The electrothermal combined feedwater heating system for supercritical coal-fired units according to claim 1, characterized in that, The electricity price response module includes an electricity price-carbon price coupled response model, and the comprehensive cost calculation function is: ； in, Electric heating power, For real-time electricity prices, To contribute power for peak shaving The unit price for peak shaving compensation. For carbon emissions, This refers to the price of carbon trading.

5. The electrothermal combined feedwater heating system for supercritical coal-fired units according to claim 1, characterized in that, The fuzzy adaptive coordination control module includes: Main controller: Fuzzy PID controller, with fuzzy rules based on temperature deviation e and the rate of change of deviation. Adjustment , , parameter; Feedforward compensator: based on load change rate Pre-allocated heating power; Coordinator: The game theory approach is used to resolve the coupling conflict between electric heating and steam extraction control.

6. The electrothermal combined feedwater heating system for supercritical coal-fired units according to claim 1, characterized in that, It also includes a multi-mode operation module, providing at least four operation modes: deep peak shaving mode, economically optimal mode, new energy consumption mode, and safety margin mode.

7. The electrothermal combined feedwater heating system for supercritical coal-fired units according to claim 6, characterized in that, The optimal economic model includes a thermal energy storage control strategy based on real-time electricity prices, which works when the electricity price is below a threshold. Electric heating and thermal storage are activated when the electricity price is above a threshold. Reduce electric heating and utilize stored heat.

8. A method for operating an electrothermal synergistic feedwater heating system for a supercritical coal-fired unit based on any one of claims 1-7, characterized in that, Includes the following steps: S1: Real-time acquisition of power grid dispatch instructions, new energy output forecasts, real-time electricity prices, and unit operating parameters; S2: Utilize a multi-timescale load forecasting module to predict the unit load at different time scales in the future; S3: With coal consumption, peak shaving, new energy consumption, and equipment life as objectives, the optimal power and heat allocation ratio is solved through a multi-objective optimization decision module. S4: Adjust the power-heat coordination strategy through the electricity price response module based on real-time electricity price and carbon price; S5: The electric heater and the extraction steam regulating valve are coordinated and controlled through the fuzzy adaptive coordination control module; S6: Based on actual operating data, dynamically adjust the prediction model and optimize model parameters.

9. The operating method of the electrothermal combined feedwater temperature raising system for supercritical coal-fired units according to claim 8, characterized in that, Multi-objective optimization weight coefficients ~ The dynamic adjustment rules are as follows: When the power grid's peak-shaving demand is urgent, increase Weight; When the rate of curtailment of renewable energy increases, increase Weight; When the unit's operating time exceeds 60% of its design life, increase Weights.

10. The operating method of the electrothermal combined feedwater temperature raising system for supercritical coal-fired units according to claim 8, characterized in that, In S5, the specific process of fuzzy adaptive coordinated control includes: (1) Calculate the water supply temperature setpoint Compared with actual value deviation e and rate of change of deviation ; (2) Determine the PID parameter adjustment amount using a fuzzy rule table , , ; (3) Based on load change rate Calculate feedforward compensation ; (4) Using game theory to coordinate electric heating control commands and extraction steam control commands Find the Nash equilibrium point in the case of conflict.

Images