CN-121984051-A - Unit control optimization method and system based on thermoelectric load condition

CN121984051ACN 121984051 ACN121984051 ACN 121984051ACN-121984051-A

Abstract

The invention relates to the field of energy management and optimal scheduling, and discloses a unit control optimization method and a unit control optimization system based on thermoelectric load conditions, which are used for realizing high-efficiency energy utilization, effectively reducing energy waste, reducing carbon emission and promoting high-efficiency collaborative operation of renewable energy sources by integrating advanced prediction, optimization, intelligent control and maintenance technologies; the system has stronger economy, can improve the operation efficiency of the unit, reduces the risk of unplanned shutdown, and finally provides a reliable, environment-friendly, economical and intelligent thermoelectric unit control optimization scheme for users.

Inventors

CHEN BO
GUAN SHIPIAN
CAI LIANG
YANG XIAOLONG
HU ZUNMIN
SUN ZIWEN
YANG ZHEN
LU YANNING
YUE JUNFENG
WANG YAOU
SHI TIAN

Assignees

江苏方天电力技术有限公司

Dates

Publication Date: 20260505
Application Date: 20260123

Claims (10)

1. A unit control optimization system based on thermoelectric load conditions, the system comprising: the data acquisition and monitoring module is used for acquiring the operation parameters of the unit, including electric load, thermal load, fuel consumption, temperature and pressure; The thermoelectric load prediction module is used for predicting future thermoelectric loads based on historical data, power grid demands, ambient temperature and user heat demand; The optimizing and scheduling module is used for optimizing the start-stop strategy and the output distribution of the unit according to the real-time thermoelectric load prediction result so as to reduce the fuel consumption and improve the energy utilization rate; The intelligent control module is used for combining the optimal scheduling result and the unit operation state, adjusting the unit operation parameters in real time and realizing thermoelectric coordination control; the waste heat recovery and energy storage module is used for recovering and storing waste heat discharged by the unit so as to improve the heat utilization efficiency; The low-carbon emission and environment-friendly optimizing module is used for monitoring and optimizing carbon emission of the unit and adjusting the operation strategy of the unit by combining a carbon transaction market; The multi-energy coupling scheduling module is used for scheduling in coordination with renewable energy sources such as wind energy, photovoltaic, an energy storage system and the like to realize optimal scheduling and load balancing; and the fault prediction and intelligent maintenance module is used for predicting faults in advance and taking preventive maintenance measures based on the operation data of the artificial intelligent analysis unit.
2. The unit control optimizing system based on thermoelectric load conditions of claim 1, wherein the thermoelectric load prediction module adopts a deep learning algorithm, including a long-short time memory network (LSTM) and a transducer model, to improve thermoelectric load prediction accuracy.
3. The system of claim 1, wherein the optimization scheduling module uses a multi-objective optimization algorithm including Genetic Algorithm (GA), particle Swarm Optimization (PSO), and Reinforcement Learning (RL) to optimize unit start-stop and thermoelectric output distribution.
4. The unit control optimizing system based on thermoelectric load conditions of claim 1, wherein the intelligent control module adopts a fuzzy control algorithm and a self-adaptive neural network, and automatically adjusts unit operation parameters based on real-time working conditions to ensure thermoelectric matching degree and stability.
5. The unit control optimizing system based on thermoelectric load condition of claim 1, wherein the waste heat recovery and energy storage module comprises a phase change energy storage device and a heat pump system, and can store excessive heat when the thermal load fluctuates and release the excessive heat when the thermal load fluctuates, so that the heat utilization efficiency is improved.
6. The unit control optimizing system based on thermoelectric load conditions of claim 1, wherein the low carbon emission and environmental protection optimizing module comprises a carbon emission monitoring sensor, a carbon capture device (CCUS) and a carbon trade market interface, and the unit carbon emission is calculated in real time and combined with a carbon trade market price optimizing operation strategy.
7. The unit control optimizing system based on thermoelectric load conditions of claim 1, wherein the multi-energy coupling scheduling module is capable of cooperating with a distributed energy system (DER) and dynamically adjusting the output of a thermoelectric unit, wind energy, photovoltaic and energy storage equipment through an intelligent scheduling algorithm to realize complementary operation of multiple energy sources.
8. The unit control optimizing system based on thermoelectric load condition of claim 1, wherein said failure prediction and intelligent maintenance module employs digital twin technology to construct a virtual model of unit operation, and performs real-time monitoring and failure prediction in combination with edge calculation to reduce unplanned downtime.
9. The unit control optimizing system based on thermoelectric load conditions of claim 1, wherein the system further comprises an economy evaluation and decision support module for providing an optimal economy operation strategy based on factors such as unit operation cost, electric power market price, fuel cost, etc., so as to improve overall economic benefit.
10. The method and system for optimizing unit control based on thermoelectric load conditions according to claims 1-9, characterized in that the method steps are as follows: s1, data acquisition and monitoring The data acquisition and monitoring module is utilized to acquire real-time operating parameters of the unit, including but not limited to: Electrical load parameters (generated power, grid demand, transformer load, etc.); Heat load parameters (steam flow, heat supply network backwater temperature, heat supply demand, etc.); fuel consumption data (fuel type, combustion efficiency, heating value, etc.); environmental parameters (air temperature, humidity, wind speed, etc.); S2. Thermoelectric load prediction Based on historical data and real-time monitoring data, a long-short-time memory network (LSTM) and a transducer model are adopted to predict future thermoelectric load, and the method mainly comprises the following steps: Short-term prediction (1-24 hours) for real-time optimization of unit operation; Medium-long term prediction (1 day-1 week) for making an optimized scheduling plan; multivariable input (power grid load demand, seasonal variation, weather conditions and the like) improves prediction accuracy; S3, unit optimizing and scheduling Based on the predicted thermoelectric load, optimizing the unit operation schedule by adopting a multi-objective optimization algorithm (genetic algorithm GA, particle swarm optimization PSO, reinforcement learning RL), comprising: The start-stop strategy of the unit is optimized, the start-stop of the unit is reasonably arranged, and the energy loss caused by frequent start-stop is avoided; the thermoelectric ratio is optimized, the generating capacity and the heating capacity of the unit are adjusted according to the heating demand, and the energy utilization efficiency is improved; dynamic load distribution, namely reasonably distributing loads among a plurality of units to realize economic operation; S4, intelligent control and real-time adjustment And the operation parameters of the unit are dynamically adjusted by adopting fuzzy control and a self-adaptive neural network and combining an optimal scheduling result and the real-time working condition of the unit, such as: fuel supply quantity is adjusted, and combustion efficiency is optimized; the heating temperature is adjusted to match the requirements of users, so that the energy waste is reduced; Steam flow is optimized, and heat supply stability is guaranteed; S5, waste heat recovery and energy storage optimization The phase-change energy storage device and the heat pump system are adopted to store redundant heat at low load and release the redundant heat at high load; the temperature of the heat supply network water supply and return is regulated in real time, the waste heat utilization is optimized, and the overall energy efficiency of the system is improved; s6, low-carbon emission and environment-friendly optimization Carbon emission monitoring, namely installing a carbon emission sensor, and monitoring the emission quantity of the unit CO 2 in real time; Carbon Capture and Utilization (CCUS), dynamically adjusting the carbon capture system to improve carbon emission reduction efficiency; optimizing carbon transaction, adjusting unit operation strategies by combining carbon market price, and reducing carbon emission cost; S7, multi-energy coupling scheduling The wind power generation unit is operated in cooperation with renewable energy sources, and the wind power, photovoltaic and energy storage equipment are combined to optimize the output of the cogeneration unit; An intelligent scheduling strategy is used for dynamically adjusting the output of a unit, wind energy and photovoltaic through a distributed energy management system (DER) to realize multi-energy complementation; s8, fault prediction and intelligent maintenance A digital twin technology is adopted to construct a virtual model of the unit operation, and real-time monitoring is carried out by combining with edge calculation; analyzing the running state of the equipment through a deep learning algorithm (CNN, LSTM), predicting faults in advance and taking preventive maintenance measures; The remote diagnosis system is combined, so that the risk of unplanned shutdown is reduced, and the stability of the unit is improved; S9, economic evaluation and optimization decision An economic optimization model is built based on factors such as the price of an electric power market, the cost of fuel, the running and maintenance cost of equipment and the like; adopting game theory and optimization algorithm to balance economic benefit and operation safety and provide optimal operation strategy; And by combining big data analysis, the unit operation plan is dynamically adjusted, so that the economy and stability are ensured.

Description

Unit control optimization method and system based on thermoelectric load condition Technical Field The invention relates to the field of energy management and optimal scheduling, in particular to a unit control optimization method and system based on thermoelectric load conditions. Background With the continuous increase of global energy demands and the improvement of environmental protection requirements, how to improve the energy utilization efficiency and reduce the carbon emission becomes an important subject in the field of modern energy production and consumption. The cogeneration (Combined Heat and Power, CHP) system is used as a high-efficiency and low-carbon energy utilization mode and is widely applied to the fields of industry and urban heat supply. By simultaneously generating electric power and heat energy, the cogeneration system can remarkably improve the energy utilization efficiency, reduce the consumption of traditional energy and further reduce the emission of carbon dioxide. However, during operation of the cogeneration unit, many challenges are often faced, including load fluctuations, low energy utilization efficiency, equipment failure risk, carbon emission control, and the like. These problems not only affect the operation stability of the unit, but also increase the operation cost and reduce the overall economic benefit. Therefore, accurate control and optimization of the thermoelectric load condition become key to realizing efficient and stable operation of the cogeneration system. To address these issues, unit control optimization systems based on thermoelectric load conditions have been developed. Through accurate thermoelectric load prediction, real-time optimal scheduling, intelligent control and maintenance, the system can ensure the optimal running state of the unit under different load conditions, and the aims of energy conservation and emission reduction are realized. Disclosure of Invention The invention provides a unit control optimization method and a unit control optimization system based on thermoelectric load conditions, which are used for solving the technical problems in the background art. The invention provides the following technical scheme: a unit control optimization system based on thermoelectric load conditions, the system comprising: the data acquisition and monitoring module is used for acquiring the operation parameters of the unit, including electric load, thermal load, fuel consumption, temperature and pressure; The thermoelectric load prediction module is used for predicting future thermoelectric loads based on historical data, power grid demands, ambient temperature and user heat demand; The optimizing and scheduling module is used for optimizing the start-stop strategy and the output distribution of the unit according to the real-time thermoelectric load prediction result so as to reduce the fuel consumption and improve the energy utilization rate; The intelligent control module is used for combining the optimal scheduling result and the unit operation state, adjusting the unit operation parameters in real time and realizing thermoelectric coordination control; the waste heat recovery and energy storage module is used for recovering and storing waste heat discharged by the unit so as to improve the heat utilization efficiency; The low-carbon emission and environment-friendly optimizing module is used for monitoring and optimizing carbon emission of the unit and adjusting the operation strategy of the unit by combining a carbon transaction market; The multi-energy coupling scheduling module is used for scheduling in coordination with renewable energy sources such as wind energy, photovoltaic, an energy storage system and the like to realize optimal scheduling and load balancing; and the fault prediction and intelligent maintenance module is used for predicting faults in advance and taking preventive maintenance measures based on the operation data of the artificial intelligent analysis unit. Preferably, the thermoelectric load prediction module adopts a deep learning algorithm, including a long-short time memory network (LSTM) and a transducer model, so as to improve the thermoelectric load prediction accuracy. Preferably, the optimization scheduling module adopts a multi-objective optimization algorithm, including a Genetic Algorithm (GA), a particle swarm optimization algorithm (PSO) and Reinforcement Learning (RL), so as to optimize unit start-stop and thermoelectric output distribution. Preferably, the intelligent control module adopts a fuzzy control algorithm and a self-adaptive neural network, and automatically adjusts the running parameters of the unit based on real-time working conditions so as to ensure the thermoelectric matching degree and stability. Preferably, the waste heat recovery and energy storage module comprises a phase change energy storage device and a heat pump system, can store redundant heat when the thermal load fluctuates an