Industrial Park Waste Heat Recovery Method and Related Devices Based on Multi-Objective Optimization Model

Abstract

This invention belongs to the field of industrial waste heat recovery technology, and discloses a method and related device for industrial park waste heat recovery based on a multi-objective optimization model. By collecting real-time data on waste heat resources, energy load, and energy equipment operation in the industrial park, a pre-trained model is used to predict waste heat supply and energy demand. The data is then input into the multi-objective optimization model to solve for the optimal allocation strategy and equipment control parameters, and finally, commands are issued to realize waste heat recovery. This method effectively improves the dynamic adaptability, multi-energy collaborative optimization capability, decision-making accuracy, and system scalability of the waste heat recovery system, achieving full recovery of waste heat resources, energy supply and demand balance, reduced operating costs, and extended equipment lifespan.

Description

Technical Field

[0001] This invention belongs to the field of industrial waste heat recovery, and particularly relates to a method and related apparatus for waste heat recovery in industrial parks based on a multi-objective optimization model. Background Technology

[0002] Currently, industrial waste heat recovery technology is widely used in parks and other scenarios. Existing technologies mostly adopt the "fixed heat exchange + single energy supplement" model, which recovers waste heat with fixed parameters through a pre-set heat exchanger and converts it into thermal or cold energy at a fixed temperature. It is combined with supplementary energy equipment such as air source heat pumps and electric thermal storage. The control logic is mainly based on preset thresholds to realize simple start and stop of the equipment, which is the mainstream technical solution in the industry.

[0003] Existing industrial waste heat recovery technologies face several pressing issues: First, they lack dynamic adaptability. Designs based on fixed parameters cannot respond in real time to dynamic fluctuations in flue gas volume and temperature, leading to insufficient waste heat recovery or energy supply imbalances. Second, optimization is limited to a single dimension, focusing only on the operating status of individual devices without considering the coordinated operation optimization of multiple energy devices such as waste heat exchangers and air source heat pumps, resulting in energy waste or insufficient supply. Third, decision-making lacks precision, relying on empirical thresholds for control without incorporating quantitative decisions based on park energy load forecasts and equipment operating efficiency models, resulting in low energy utilization efficiency and poor economic benefits. Fourth, scalability is insufficient. Most systems are customized designs, making it difficult to quickly adjust operating strategies when park energy demands and waste heat resource characteristics change, resulting in poor adaptability.

[0004] It is evident that existing industrial waste heat recovery technologies suffer from poor dynamic adaptability, insufficient collaborative optimization, low decision-making accuracy, and weak scalability. Summary of the Invention

[0005] This invention provides a method and related device for industrial park waste heat recovery based on a multi-objective optimization model. This method can effectively solve the problems of poor dynamic adaptability, insufficient collaborative optimization, low decision-making accuracy and weak scalability of existing industrial waste heat recovery technologies.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: A method for waste heat recovery in industrial parks based on a multi-objective optimization model includes: Data on waste heat resources from waste heat generating equipment in industrial parks, energy load data from energy supply facilities, and equipment operation data from energy equipment are collected. The waste heat resource data includes flue gas flow rate, flue gas temperature, and flue gas composition. The energy load data includes real-time heating and cooling loads, process heat demand, and domestic hot water demand. The equipment operation data includes operating efficiency, energy consumption, output power, and operating status information. Waste heat resource data is input into a pre-trained waste heat resource prediction model, and the waste heat supply prediction value is output; energy load data of energy supply facilities is input into a pre-trained energy load prediction model, and the energy demand prediction value is output. The predicted values ​​of waste heat supply, energy demand, and equipment operation data are input into a pre-constructed multi-objective optimization model. An evolutionary multi-objective optimization algorithm is used to solve the multi-objective optimization model to obtain the optimal allocation strategy and equipment control parameters. The multi-objective optimization model takes maximizing waste heat recovery efficiency, minimizing energy supply cost, and minimizing equipment operating losses as joint optimization objectives, and takes equipment operating limits, energy supply stability, and environmental emission standards as constraints. The equipment control parameters are sent as optimization decision instructions to the control systems of each energy device to realize waste heat recovery in the industrial park.

[0007] Furthermore, the basic model of the waste heat resource prediction model adopts the ARIMA time series analysis model and is trained based on historical waste heat resource data; the waste heat resource prediction model is used to predict the future trend of waste heat flue gas volume and temperature changes by combining the production plan of waste heat generating equipment; the basic model of the energy load prediction model adopts the random forest machine learning model and is trained based on historical energy load data; the energy load prediction model is used to integrate ambient temperature, ambient humidity, production schedule, and personnel flow factors to predict the energy demand of various areas of the park.

[0008] Furthermore, the objective function F of the multi-objective optimization model is as follows: minF = -ω1×η + ω2×C + ω3×L In the formula, η is the waste heat recovery efficiency, C is the energy supply cost, and L is the equipment operating loss; ω1, ω2, and ω3 are the corresponding weighting coefficients, satisfying ω1+ω2+ω3=1; The constraints of the multi-objective optimization model are as follows:

[0009] In the formula, P i Let P be the operating power of the i-th energy device. min P max S represents the upper and lower limits of equipment power, and S is an indicator of energy supply stability. th Here, E is the stability threshold, and E is the pollutant emission value. limit These are the limits set by environmental emission standards.

[0010] Furthermore, in the step of inputting the waste heat supply forecast, energy demand forecast, and equipment operation data into a pre-constructed multi-objective optimization model, and solving the multi-objective optimization model using an evolutionary multi-objective optimization algorithm to obtain the optimal allocation strategy and equipment control parameters, the evolutionary multi-objective optimization algorithm employs an improved particle swarm optimization algorithm, with the specific particle update formula as follows: Speed ​​update formula: v i (t+1)=ω·v i (t)+c1·r1·(pbest i (t)-x i (t))+c2·r2·(gbest(t)-x i (t)) Position update formula: x i (t+1)=x i (t)+v i (t+1) In the formula, ω is the inertia weight, c1 and c2 are both learning factors, r1 and r2 are both random numbers in the interval [0, 1], and v i (t) represents the velocity of the i-th particle at time t; x i (t) represents the position of the i-th particle at time t; pbest i gbest(t) represents the optimal position of the i-th individual particle; gbest(t) represents the global optimal position.

[0011] Furthermore, in the step of inputting the waste heat supply forecast, energy demand forecast, and equipment operation data into a pre-constructed multi-objective optimization model, and solving the multi-objective optimization model using an evolutionary multi-objective optimization algorithm to obtain the optimal allocation strategy and equipment control parameters, the evolutionary multi-objective optimization algorithm employs a genetic algorithm, and the specific calculation rules are as follows: Fitness function: fitness = α·(1 / η) + β·C + γ·L; where α + β + γ = 1, α, β, and γ are the weights corresponding to waste heat recovery efficiency, energy supply cost, and equipment operating loss, and are normalization coefficients; In the formula, fitness is the fitness value of the genetic algorithm; η is the waste heat recovery efficiency; C is the energy supply cost; and L is the equipment operating loss. Selection operator: Use roulette wheel selection to screen for superior individuals; Crossover operator: Gene recombination is achieved through single-point crossover; Mutation operator: Gene perturbation is achieved using Gaussian mutation; The optimal allocation strategy and equipment control parameters are solved iteratively by selecting operators, crossover operators, and mutation operators.

[0012] Furthermore, it also includes a closed-loop feedback correction step: Real-time collection of actual operating parameters of energy equipment and energy supply effect data, and comparison of actual operating data with waste heat supply forecast, energy demand forecast, and optimization target value; If the data deviation exceeds the preset threshold, the parameters of the waste heat resource prediction model, energy load prediction model, and multi-objective optimization model will be corrected, and the optimal allocation strategy and equipment control parameters will be solved again.

[0013] Furthermore, the optimal allocation strategy adopts a waste heat cascade utilization strategy: Waste heat quality is classified according to waste heat temperature and flow rate. High-temperature waste heat is allocated to the heating / cooling process, and low-temperature waste heat is allocated to the domestic hot water supply / process heat replenishment process. The decision-making instructions are dynamically adjusted and optimized based on the seasonal energy consumption characteristics of the park, including: During the heating season: increase the heat exchange load of high-temperature heat exchangers, reduce the power consumption of solid thermal storage units, and adjust the hot water supply temperature according to the fluctuations in heat load; Cooling season: Match the efficiency model of the absorption chiller to allocate high-temperature waste heat, and adjust the air source heat pump load according to the cooling period of the factory and dormitory buildings; During the transitional season: high-temperature waste heat is prioritized to drive ORC generator sets for power generation, low-temperature waste heat is used to supply domestic hot water, and air source heat pumps are started to supplement the waste heat when it is insufficient.

[0014] An industrial park waste heat recovery system based on a multi-objective optimization model includes: The data acquisition module is used to collect waste heat resource data from waste heat generation equipment in the industrial park, energy load data from energy supply facilities, and equipment operation data from energy equipment. The waste heat resource data includes flue gas flow rate, flue gas temperature, and flue gas composition. The energy load data includes real-time heating and cooling loads, process heat demand, and domestic hot water demand. The equipment operation data includes operating efficiency, energy consumption, output power, and operating status information. The prediction module is used to input waste heat resource data into a pre-trained waste heat resource prediction model and output waste heat supply prediction values; and to input energy load data of energy supply facilities into a pre-trained energy load prediction model and output energy demand prediction values. The objective optimization module is used to input the waste heat supply forecast, energy demand forecast, and equipment operation data into a pre-constructed multi-objective optimization model. An evolutionary multi-objective optimization algorithm is used to solve the multi-objective optimization model to obtain the optimal allocation strategy and equipment control parameters. The multi-objective optimization model takes maximizing waste heat recovery efficiency, minimizing energy supply cost, and minimizing equipment operating losses as joint optimization objectives, and takes equipment operating limits, energy supply stability, and environmental emission standards as constraints. The instruction output module is used to send equipment control parameters as optimization decision instructions to the control systems of various energy devices to realize waste heat recovery in the industrial park.

[0015] An industrial park waste heat recovery device based on a multi-objective optimization model includes: Memory, used to store computer programs; A processor is used to implement the above-described waste heat recovery method for industrial parks based on a multi-objective optimization model when executing the computer program.

[0016] A computer-readable storage medium storing a computer program, which, when executed by a processor, is used to implement the above-described industrial park waste heat recovery method based on a multi-objective optimization model.

[0017] Compared with the prior art, the present invention has the following beneficial effects: This invention provides a waste heat recovery method for industrial parks based on a multi-objective optimization model. It involves real-time collection of waste heat resources, energy load, and energy equipment operation data from the industrial park. A pre-trained model is used to predict waste heat supply and energy demand, which are then input into the multi-objective optimization model to solve for the optimal allocation strategy and equipment control parameters. Finally, commands are issued to achieve waste heat recovery. A multi-objective optimization model is constructed with the joint optimization objectives of maximizing waste heat recovery efficiency, minimizing energy supply costs, and minimizing equipment operating losses. Under constraints of equipment operating limits, energy supply stability, and environmental emission standards, an evolutionary multi-objective optimization algorithm is used for quantitative solutions, thereby dynamically responding to fluctuations and coordinating the operation of multiple devices. This method effectively improves the dynamic adaptability, multi-energy collaborative optimization capability, decision-making accuracy, and system scalability of the waste heat recovery system, achieving full recovery of waste heat resources, energy supply and demand balance, reduced operating costs, and extended equipment lifespan. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the energy supply and demand balance in the park for each quarter, provided as an embodiment of the present invention. Figure 2 A comparison chart of the efficiency of core equipment in a waste heat recovery system provided in an embodiment of the present invention; Figure 3 A typical daily cooling and heating load variation curve of the park provided in this embodiment of the invention; Figure 4 A trend diagram of future economic benefits provided for embodiments of the present invention; Figure 5 The core flowchart of a waste heat recovery method for industrial parks based on a multi-objective optimization model is provided in an embodiment of the present invention. Figure 6This is a schematic diagram of a waste heat recovery system for an industrial park based on a multi-objective optimization model, provided as an embodiment of the present invention. Detailed Implementation

[0019] To further understand the content of this invention, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments are merely illustrative and not limiting of the invention.

[0020] The technical terms involved in this invention are explained as follows: ARIMA (Autoregressive Integrated Moving Average) is a classic time series analysis method that combines three components: autoregression (AR), differencing (I), and moving average (MA). It is suitable for forecasting stationary or non-stationary time series that can be stationary through differencing.

[0021] ORC generator set: It is a power generation device that uses Organic Rankine Cycle (ORC) technology to convert medium and low temperature thermal energy into electrical energy.

[0022] As mentioned in the background technology, existing waste heat recovery methods for industrial parks have the following defects: (1) Lack of dynamic adaptability: Existing solutions are designed with fixed parameters as the core, which cannot respond to the dynamic changes of waste heat resources (flue gas volume, temperature) in real time, resulting in insufficient waste heat recovery or energy supply imbalance. (2) Single optimization dimension: Only the operating status of a single device is considered, without considering the coordinated operation optimization of multiple energy devices (waste heat exchangers, air source heat pumps, solid heat storage units, etc.), resulting in energy waste or insufficient supply. (3) Lack of precision in decision-making: Control is based on experience thresholds, without combining park energy load forecasts, equipment operating efficiency models, etc. for quantitative decision-making, resulting in low energy utilization efficiency and poor economic benefits. (4) Insufficient scalability: Existing systems are mostly customized designs, and when park energy demand and waste heat resource characteristics change, it is difficult to quickly adjust the operating strategy, resulting in poor adaptability.

[0023] To address the aforementioned issues, this embodiment provides a waste heat recovery method for industrial parks based on a multi-objective optimization model. This method constructs a multi-dimensional mathematical model to achieve accurate modeling and real-time optimization of the dynamic characteristics of waste heat resources, the energy load demand of the park, and the operating efficiency of multi-energy equipment. This achieves the goals of efficient cascade utilization of waste heat resources, coordinated operation of multi-energy equipment, stable and reliable energy supply, and maximization of economic benefits, making it suitable for the waste heat recovery and comprehensive energy supply needs of industrial clusters such as the Xi'an Electric Power Xianyang Industrial Park.

[0024] For example, such as Figure 5As shown, this embodiment provides a waste heat recovery method for industrial parks based on a multi-objective optimization model, including: Data on waste heat resources from waste heat generating equipment in industrial parks, energy load data from energy supply facilities, and equipment operation data from energy equipment are collected. The waste heat resource data includes flue gas flow rate, flue gas temperature, and flue gas composition. The energy load data includes real-time heating and cooling loads, process heat demand, and domestic hot water demand. The equipment operation data includes operating efficiency, energy consumption, output power, and operating status information. Waste heat resource data is input into a pre-trained waste heat resource prediction model, and the waste heat supply prediction value is output; energy load data of energy supply facilities is input into a pre-trained energy load prediction model, and the energy demand prediction value is output. The predicted values ​​of waste heat supply, energy demand, and equipment operation data are input into a pre-constructed multi-objective optimization model. An evolutionary multi-objective optimization algorithm is used to solve the multi-objective optimization model to obtain the optimal allocation strategy and equipment control parameters. The multi-objective optimization model takes maximizing waste heat recovery efficiency, minimizing energy supply cost, and minimizing equipment operating losses as joint optimization objectives, and takes equipment operating limits, energy supply stability, and environmental emission standards as constraints. The equipment control parameters are sent as optimization decision instructions to the control systems of each energy device to realize waste heat recovery in the industrial park.

[0025] As can be seen, this method aims at waste heat recovery efficiency, energy cost, and equipment loss, while using equipment operating limits and supply stability as constraints. By combining time series analysis and machine learning algorithms, it achieves accurate prediction of waste heat supply and energy demand. This method couples the dynamic characteristics of waste heat resources, energy load prediction, and equipment operating efficiency into a single model, breaking through the limitations of existing single-dimensional modeling. Furthermore, based on an improved particle swarm optimization algorithm (or an alternative algorithm), it achieves dynamic balance optimization of multiple objectives, including waste heat recovery efficiency, energy cost, and equipment loss. In addition, this method establishes a closed-loop feedback control mechanism, continuously correcting model parameters and optimization strategies through real-time data feedback to ensure the stability and adaptability of the system under complex operating conditions.

[0026] The waste heat recovery method provided in this embodiment will be further explained below with reference to the accompanying drawings: This embodiment provides a waste heat recovery method for industrial parks based on a multi-objective optimization model. Specifically, it is applied to an industrial park containing 5 kilns, 2 RTO furnaces, and 1 smelting furnace as core waste heat generating equipment. It is also equipped with high-temperature / low-temperature flue gas heat exchangers, air-source chiller / hot water units, solid-state energy storage hot water units, ORC generator sets, and other energy equipment to achieve efficient recovery and rational utilization of waste heat. The specific implementation process is as follows: First, data is collected through sensors deployed on the waste heat generating equipment and energy-consuming terminals. Flue gas flow and temperature sensors are installed at the outlets of the aforementioned waste heat generating equipment, with a sampling frequency set to 1 minute / time. Simultaneously, load monitoring sensors are installed on the air conditioning systems, radiators, and domestic hot water supply points of various factory buildings, office buildings, and dormitories within the park to collect three types of core data in real time. The waste heat resource data includes flue gas flow, flue gas temperature, and flue gas composition; the energy load data includes the real-time heating and cooling loads of various areas within the park (e.g., real-time cooling and heating loads of each area). Figure 3 As shown), the data includes process heat demand and domestic hot water demand. Equipment operation data includes the operating efficiency, energy consumption, output power, and operating status information of energy equipment such as heat exchangers, air source chillers, solid energy storage water heaters, and ORC generator sets. The data is also connected to the control systems of each energy equipment to ensure the real-time and completeness of data acquisition.

[0027] By precisely deploying sensors at the outlet of the waste heat generation equipment and setting a sampling frequency of 1 minute, the dynamic changes of waste heat resources can be captured in real time, avoiding the data lag caused by excessively long sampling intervals. Simultaneously, it covers all energy-consuming terminals and equipment in the park, achieving comprehensive collection of three types of data: waste heat resources, energy load, and equipment operation. This breaks through the limitations of incomplete and non-real-time data collection in existing technologies, providing accurate and complete data support for subsequent predictive modeling and optimization, ensuring the reliability of subsequent model predictions and optimization decisions, and laying a data foundation for improving waste heat recovery efficiency. Specifically, the efficiency of the core equipment in the waste heat recovery system is as follows: Figure 2 As shown.

[0028] In this embodiment, the collected waste heat resource data is input into a pre-trained waste heat resource prediction model, which outputs a waste heat supply prediction value; the energy load data of the energy supply facilities is input into a pre-trained energy load prediction model, which outputs an energy demand prediction value. The waste heat resource prediction model is based on an ARIMA time series analysis model, trained on historical waste heat resource data of the park in 2025, and is used to predict the trend of waste heat flue gas volume and temperature changes in the next hour by combining the production plan of waste heat generating equipment (such as kiln operation batches). The energy load prediction model is based on a random forest machine learning model, also trained on historical energy load data of the above time period, and is used to integrate ambient temperature, ambient humidity, production schedules, and personnel flow factors to predict the energy demand of various areas of the park. Through model training and calibration, the prediction error of the two models is ensured to be controlled within 5%.

[0029] By employing the ARIMA time series analysis model combined with production planning to predict waste heat resources, the system can accurately capture the temporal variation patterns of waste heat flue gas volume and temperature, adapting to the cyclical fluctuations of waste heat generating equipment and avoiding the shortcomings of single prediction models that cannot adapt to changes in production plans. Furthermore, by using a random forest machine learning model to integrate multiple influencing factors to predict energy load, the system can fully consider the impact of multi-dimensional variables such as environment, production, and personnel on energy demand. This solves the problem of large prediction deviations caused by traditional energy load prediction neglecting the coupling effect of multiple factors, and controls the prediction error to within 5%. This achieves accurate prediction of waste heat supply and energy demand, providing reliable prediction data for subsequent multi-objective optimization solutions, avoiding unreasonable optimization decisions due to prediction deviations, and improving the adaptability of the waste heat recovery system.

[0030] Specifically, the predicted values ​​of waste heat supply, energy demand, and equipment operation data are input into a pre-constructed multi-objective optimization model. An evolutionary multi-objective optimization algorithm is used to solve the model, yielding the optimal allocation strategy and equipment control parameters. The multi-objective optimization model takes maximizing waste heat recovery efficiency, minimizing energy supply costs, and minimizing equipment operating losses as its joint optimization objectives, with constraints including equipment operating limits, energy supply stability, and environmental emission standards. Its objective function F is as follows: minF = -ω1×η + ω2×C + ω3×L In the formula, η is the waste heat recovery efficiency, C is the energy supply cost, and L is the equipment operating loss; ω1, ω2, and ω3 are the corresponding weighting coefficients, satisfying ω1+ω2+ω3=1; in this embodiment, ω1=0.4, ω2=0.3, and ω3=0.3 are set, which can be dynamically adjusted according to the actual operating needs of the park; the constraints are as follows:

[0031] In the formula, Pi Let P be the operating power of the i-th energy device. min P max S represents the upper and lower limits of equipment power, and S is an indicator of energy supply stability. th Here, E is the stability threshold, and E is the pollutant emission value. limit To meet environmental emission standards and limits; at the same time, through individual equipment testing and system integration, to obtain equipment operating data under different operating conditions, calibrate the equipment efficiency model, and ensure that the model output is consistent with the actual operating characteristics.

[0032] Therefore, this embodiment uses waste heat recovery efficiency, energy supply cost, and equipment operating losses as joint optimization objectives, breaking away from the problem of neglecting one aspect for another caused by a single optimization objective in the prior art, and achieving a dynamic balance of multiple objectives, such as... Figure 1 As shown, this approach ensures efficient waste heat recovery while reducing energy costs and equipment wear. By setting reasonable weighting coefficients, it can adapt to the actual operational needs of the park, enhancing the practicality of the optimization model. Furthermore, by using equipment operating limits, energy supply stability, and environmental emission standards as constraints, it ensures that optimization decisions meet the requirements of equipment operation safety, reliable energy supply, and environmental protection. This avoids equipment damage, energy supply interruptions, or excessive pollutants caused by pursuing optimization goals. The calibrated equipment efficiency model further improves the accuracy of the optimization solution, ensuring the feasibility of the optimal allocation strategy and equipment control parameters.

[0033] In this embodiment, the evolutionary multi-objective optimization algorithm preferentially adopts the improved particle swarm optimization algorithm, and the specific particle update formula is as follows: Speed ​​update formula: v i (t+1)=ω·v i (t)+c1·r1·(pbest i (t)-x i (t))+c2·r2·(gbest(t)-x i (t)) Position update formula: x i (t+1)=x i (t)+v i (t+1) In the formula: ω is the inertia weight, c1 and c2 are both learning factors, r1 and r2 are both random numbers in the interval [0, 1], v i (t) represents the velocity of the i-th particle at time t; x i (t) represents the position of the i-th particle at time t; pbest i(t) represents the optimal position of the i-th individual particle; gbest(t) represents the global optimal position. This improved particle swarm optimization algorithm is used to solve the multi-objective optimization model, and the optimal allocation strategy and equipment control parameters are obtained quickly.

[0034] In this embodiment, the improved particle swarm optimization algorithm, by introducing inertia weights and learning factors, balances the algorithm's global optimization capability and local optimization accuracy. It avoids the shortcomings of traditional particle swarm optimization algorithms, such as being prone to getting trapped in local optima and having slow convergence speed. It can quickly solve multi-objective optimization models, obtain optimal allocation strategies and equipment control parameters, shorten the optimization decision time, improve the response speed of the waste heat recovery system, and ensure the optimality of the solution results. It can fully utilize the value of waste heat resources, achieve a balance of multiple optimization objectives, and adapt to the real-time requirements of waste heat recovery in industrial parks.

[0035] As another preferred embodiment, the evolutionary multi-objective optimization algorithm can also adopt a genetic algorithm. The specific calculation rules are as follows: fitness function: fitness=α·(1 / η)+β·C+γ·L; where α+β+γ=1, α, β, and γ are the weights corresponding to waste heat recovery efficiency, energy supply cost, and equipment operating loss, and are normalization coefficients. In the formula, fitness is the fitness value of the genetic algorithm; η is the waste heat recovery efficiency; C is the energy supply cost; and L is the equipment operating loss.

[0036] The selection operator uses a roulette wheel method to select superior individuals, the crossover operator uses single-point crossover to achieve gene recombination, and the mutation operator uses Gaussian mutation to achieve gene perturbation. By iteratively solving the optimal allocation strategy and equipment control parameters through the selection operator, crossover operator, and mutation operator, this scheme is suitable for scenarios with a large number of energy devices in the park and complex constraints.

[0037] In this embodiment, the genetic algorithm, through iterative operations of three operators—selection, crossover, and mutation—possesses strong global optimization capabilities and can adapt to scenarios with a large number of devices and complex constraints. It compensates for the shortcomings of the improved particle swarm optimization algorithm in terms of insufficient optimization accuracy in complex scenarios. At the same time, by reasonably setting the fitness function, multiple optimization objectives are incorporated into it, ensuring that the solution can achieve a balance between waste heat recovery efficiency, energy supply cost, and equipment operating losses. This provides flexible optimization algorithm selection for industrial parks in different scenarios, improving the applicability and scalability of this method.

[0038] Explained, the optimal allocation strategy in this embodiment adopts a waste heat cascade utilization strategy. Specifically, waste heat quality is classified according to waste heat temperature and flow rate. High-temperature waste heat is allocated to the heating / cooling stage, and low-temperature waste heat is allocated to the domestic hot water supply / process heat replenishment stage. At the same time, the decision-making instructions are dynamically adjusted and optimized according to the seasonal energy consumption characteristics of the park. Specifically, during the heating season, the heat exchange load of the high-temperature heat exchanger is increased, the power consumption of the solid thermal storage unit is reduced, and the hot water supply temperature is adjusted according to the heat load fluctuation. When the waste heat flue gas volume is 30% higher than the predicted value, the heat exchange load of the high-temperature heat exchanger is increased, and the power consumption of the solid thermal storage unit is reduced. When the nighttime heat load of the office building decreases by 50%, the hot water supply temperature is adjusted to avoid energy waste. During the cooling season, high-temperature waste heat is allocated according to the efficiency model of the absorption chiller, and the air source heat pump load is adjusted according to the cooling time of the factory and dormitory buildings. During the transition season, high-temperature waste heat is prioritized to drive the ORC generator set to generate electricity, and low-temperature waste heat is used to supply domestic hot water. When waste heat is insufficient, the air source heat pump is started to supplement it, ensuring optimal energy cascade utilization efficiency.

[0039] In this embodiment, by dividing the allocation process according to the quality of waste heat, the graded utilization of waste heat resources is realized, avoiding energy waste caused by the low-grade utilization of high-temperature waste heat and improving the overall efficiency of waste heat recovery. Combined with the dynamic adjustment decision instructions based on the seasonal energy consumption characteristics of the park, it can adapt to the differences in energy demand in different seasons. During the heating season, it reduces electricity consumption and avoids waste; during the cooling season, it matches the cooling time and improves the rationality of supply; and during the transition season, it prioritizes power generation to supplement the insufficient waste heat. This further optimizes the allocation efficiency of waste heat resources and achieves seamless collaboration between the waste heat recovery system and the supplementary energy equipment, maximizing the utilization value of waste heat resources and reducing the park's dependence on traditional energy.

[0040] In this embodiment, the waste heat recovery method further includes a closed-loop feedback correction step, which specifically involves: collecting the actual operating parameters of the energy equipment and the energy supply effect data in real time; comparing the actual operating data with the predicted values ​​of waste heat supply, energy demand, and optimization targets; if the data deviation exceeds a preset threshold (the preset threshold is 3% in this embodiment), then correcting the parameters of the waste heat resource prediction model, the energy load prediction model, and the multi-objective optimization model, and resolving the optimal allocation strategy and equipment control parameters to form a complete closed-loop control.

[0041] The explainable closed-loop feedback correction mechanism can monitor the deviation between the actual operating status of the system and the model prediction and optimization target in real time. When the deviation exceeds the preset threshold, the model parameters are corrected in time. This solves the problem of model inaccuracy caused by fluctuations in waste heat resources, energy load, or equipment aging. It ensures that the optimization decision always adapts to the actual operating conditions of the park, improves the stability and adaptability of the waste heat recovery system, avoids the decline in waste heat recovery efficiency, energy waste, or equipment damage caused by model deviation, and realizes the continuous optimization of the waste heat recovery system.

[0042] As a further preferred embodiment, in addition to the improved particle swarm optimization algorithm and genetic algorithm mentioned above, an optimization scheme based on model predictive control (MPC) or an optimization scheme based on reinforcement learning can also be used to achieve the same invention objective. The core idea of ​​the optimization scheme based on model predictive control (MPC) is to construct a state-space model of the waste heat recovery system, and to continuously optimize the decision scheme for each control cycle based on the predicted data (waste heat supply, energy load) for multiple future time periods, taking into account the dynamic response and stability of the system. It is suitable for scenarios with extremely high requirements for energy supply stability. The core idea of ​​the optimization scheme based on reinforcement learning is to use the comprehensive benefits of the system's long-term operation (cumulative waste heat recovery amount, cumulative energy cost savings) as the reward function, and to gradually optimize the waste heat recovery and equipment control strategies through interactive learning between the agent and the environment. It is suitable when the changing patterns of waste heat resources and energy load in the park are complex and it is difficult to establish an accurate mathematical model. The core logic of the above alternative schemes all revolves around "data modeling - multi-objective optimization - closed-loop feedback", with only differences in the selection of optimization algorithms. All of them can achieve the core objective of this invention.

[0043] The availability of multiple optimization algorithms enables this method to adapt to the actual needs and technical conditions of different industrial parks. The MPC-based solution improves the stability of energy supply and meets the needs of high-stability scenarios. The reinforcement learning-based solution solves the problem of difficulty in establishing accurate mathematical models under complex operating conditions. By using data-driven strategy optimization, the applicability and scalability of this method are further improved, breaking the limitations of a single optimization algorithm and ensuring that different types of industrial parks can achieve efficient waste heat recovery, thus expanding the application scope of this method.

[0044] Finally, the equipment control parameters obtained from the above solution are used as optimization decision instructions and sent to the control systems of each energy device. Specifically, these include control instructions such as heat exchanger heat exchange power, air source heat pump start-up and shutdown status, and heat storage unit charging and discharging rhythm, to realize waste heat recovery in the industrial park. At the same time, through modular design, the data acquisition, model building, optimization decision, and execution feedback modules are independently encapsulated, which has good scalability and portability and can be applied to the comprehensive utilization of waste heat recovery in Xi'an Electric Power Xianyang Park and similar industrial clusters.

[0045] As can be seen, directly sending the optimized equipment control parameters to the control systems of each device achieves automated control of waste heat recovery, reduces manual intervention, improves the efficiency and accuracy of system operation, and avoids decision-making biases caused by manual operation. The modular design allows each module to be independently upgraded and maintained, reducing system maintenance costs. It also possesses good portability, enabling rapid application to other similar industrial clusters, expanding the application scenarios of this method, enhancing its practicality and promotional value, and ultimately achieving efficient, economical, and stable recovery of waste heat resources in industrial parks, achieving the goals of energy conservation, emission reduction, and environmental protection. Future economic benefits include… Figure 4 As shown.

[0046] like Figure 6 As shown, this embodiment also provides an industrial park waste heat recovery system based on a multi-objective optimization model, including: The data acquisition module is used to collect waste heat resource data from waste heat generation equipment in the industrial park, energy load data from energy supply facilities, and equipment operation data from energy equipment. The waste heat resource data includes flue gas flow rate, flue gas temperature, and flue gas composition. The energy load data includes real-time heating and cooling loads, process heat demand, and domestic hot water demand. The equipment operation data includes operating efficiency, energy consumption, output power, and operating status information. The prediction module is used to input waste heat resource data into a pre-trained waste heat resource prediction model and output waste heat supply prediction values; and to input energy load data of energy supply facilities into a pre-trained energy load prediction model and output energy demand prediction values. The objective optimization module is used to input the waste heat supply forecast, energy demand forecast, and equipment operation data into a pre-constructed multi-objective optimization model. An evolutionary multi-objective optimization algorithm is used to solve the multi-objective optimization model to obtain the optimal allocation strategy and equipment control parameters. The multi-objective optimization model takes maximizing waste heat recovery efficiency, minimizing energy supply cost, and minimizing equipment operating losses as joint optimization objectives, and takes equipment operating limits, energy supply stability, and environmental emission standards as constraints. The instruction output module is used to send equipment control parameters as optimization decision instructions to the control systems of various energy devices to realize waste heat recovery in the industrial park.

[0047] The present invention also provides an industrial park waste heat recovery device based on a multi-objective optimization model, comprising: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of the industrial park waste heat recovery method based on the multi-objective optimization model.

[0048] The present invention also provides a computer program product, including a computer program / instruction that, when executed by a processor, implements the steps of the industrial park waste heat recovery method based on a multi-objective optimization model.

[0049] When the processor executes the computer program, it implements the steps of the above-mentioned industrial park waste heat recovery based on a multi-objective optimization model, such as: collecting waste heat resource data of waste heat generating equipment in the industrial park, energy load data of energy supply facilities, and equipment operation data of energy equipment; wherein, the waste heat resource data includes flue gas flow rate, flue gas temperature, and flue gas composition; the energy load data includes real-time heating and cooling loads, process heat demand, and domestic hot water demand; the equipment operation data includes operating efficiency, energy consumption, output power, and operating status information; Waste heat resource data is input into a pre-trained waste heat resource prediction model, and the waste heat supply prediction value is output; energy load data of energy supply facilities is input into a pre-trained energy load prediction model, and the energy demand prediction value is output. The predicted values ​​of waste heat supply, energy demand, and equipment operation data are input into a pre-constructed multi-objective optimization model. An evolutionary multi-objective optimization algorithm is used to solve the multi-objective optimization model to obtain the optimal allocation strategy and equipment control parameters. The multi-objective optimization model takes maximizing waste heat recovery efficiency, minimizing energy supply cost, and minimizing equipment operating losses as joint optimization objectives, and takes equipment operating limits, energy supply stability, and environmental emission standards as constraints. The equipment control parameters are sent as optimization decision instructions to the control systems of each energy device to realize waste heat recovery in the industrial park.

[0050] For example, the computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing preset functions, the instruction segments describing the execution process of the computer program in the industrial park waste heat recovery equipment based on a multi-objective optimization model. For example, the computer program can be divided into a data acquisition module, a prediction module, an objective optimization module, and an instruction output module; the specific functions are as follows: The data acquisition module is used to collect waste heat resource data from the industrial park waste heat generating equipment, energy load data from the energy supply facilities, and equipment operation data from the energy equipment; wherein, the waste heat resource data includes flue gas flow rate, flue gas temperature, and flue gas composition; the energy load data includes real-time heating and cooling loads, process heat demand, and domestic hot water demand; the equipment operation data includes operating efficiency, energy consumption, output power, and operating status information; the prediction module is used to input the waste heat resource data into a pre-trained waste heat resource prediction model and output a waste heat supply prediction value; the prediction module outputs the waste heat resource data into a pre-trained waste heat resource prediction model and outputs a waste heat supply prediction value; the prediction module outputs the energy load data from the energy supply facilities and outputs the predicted waste heat resource data into a pre-trained waste heat resource prediction model and outputs a predicted waste heat supply value; the prediction module ... The system inputs load data into a pre-trained energy load prediction model and outputs predicted energy demand values. The objective optimization module inputs waste heat supply prediction values, energy demand prediction values, and equipment operation data into a pre-constructed multi-objective optimization model. An evolutionary multi-objective optimization algorithm is used to solve the multi-objective optimization model to obtain the optimal allocation strategy and equipment control parameters. The multi-objective optimization model uses maximizing waste heat recovery efficiency, minimizing energy supply costs, and minimizing equipment operating losses as joint optimization objectives, with constraints including equipment operating limits, energy supply stability, and environmental emission standards. The instruction output module sends the equipment control parameters as optimization decision instructions to the control systems of each energy device to realize waste heat recovery in the industrial park.

[0051] The industrial park waste heat recovery equipment based on a multi-objective optimization model can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. This equipment may include, but is not limited to, processors and memory. Those skilled in the art will understand that the above examples of industrial park waste heat recovery equipment based on a multi-objective optimization model do not constitute a limitation on such equipment. It may include more components than described above, or combine certain components, or use different components. For example, the industrial park waste heat recovery equipment based on a multi-objective optimization model may also include input / output devices, network access devices, buses, etc.

[0052] The processor referred to can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, or any conventional processor. This processor serves as the control center for the industrial park waste heat recovery system based on a multi-objective optimization model, connecting various parts of the waste heat recovery equipment using various interfaces and lines.

[0053] The memory can be used to store the computer program and / or modules. The processor realizes various functions of the industrial park waste heat recovery equipment based on the multi-objective optimization model by running or executing the computer program and / or modules stored in the memory and calling the data stored in the memory.

[0054] The memory may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function (such as sound playback, image playback, etc.). The data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). Furthermore, the memory may include high-speed random access memory and non-volatile memory, such as hard disks, RAM, plug-in hard disks, smart media cards (SMC), secure digital cards (SD cards), flash cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0055] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the aforementioned method for industrial park waste heat recovery based on a multi-objective optimization model.

[0056] If the modules / units integrated in the industrial park waste heat recovery system based on the multi-objective optimization model are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.

[0057] Based on this understanding, the present invention can implement all or part of the processes in the above-mentioned industrial park waste heat recovery method based on a multi-objective optimization model, or it can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of the above-mentioned industrial park waste heat recovery method based on a multi-objective optimization model. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or a preset intermediate form, etc.

[0058] The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0059] It should be noted that the content contained in the computer-readable storage medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0060] Compared with existing waste heat recovery technologies in industrial parks, this invention provides a waste heat recovery method and related apparatus for industrial parks based on a multi-objective optimization model, which has the following advantages: This invention collects real-time data on waste heat resources, energy load, and equipment operation in industrial parks. It uses a pre-trained prediction model to output predicted values ​​for waste heat supply and energy demand. These are then input into a multi-objective optimization model with the joint optimization objectives of maximizing waste heat recovery efficiency, minimizing energy supply costs, and minimizing equipment operating losses. Under constraints of equipment operating limits, energy supply stability, and environmental emission standards, an evolutionary multi-objective optimization algorithm is employed to solve for the optimal allocation strategy and control parameters. Dynamic adjustments are made through closed-loop feedback and tiered utilization strategies. This method, based on quantitative models and intelligent algorithms, achieves supply and demand forecasting, multi-objective collaborative optimization, and adaptive correction. This method effectively overcomes the problems of poor dynamic adaptability, insufficient collaborative optimization, low decision-making accuracy, and weak scalability in existing technologies. It significantly improves the responsiveness, multi-energy collaborative efficiency, scientific decision-making, and environmental adaptability of waste heat recovery systems, achieving full recovery of waste heat resources, optimized energy supply and demand balance, reduced operating costs, and extended equipment lifespan, thus comprehensively improving energy utilization efficiency and economic benefits.

[0061] The above embodiments are merely one of the implementation methods for achieving the technical solution of the present invention. The scope of protection claimed by the present invention is not limited to this embodiment, but also includes any variations, substitutions and other implementation methods that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for waste heat recovery in industrial parks based on a multi-objective optimization model, characterized in that, include: Data on waste heat resources from waste heat generating equipment in industrial parks, energy load data from energy supply facilities, and equipment operation data from energy equipment are collected. The waste heat resource data includes flue gas flow rate, flue gas temperature, and flue gas composition. The energy load data includes real-time heating and cooling loads, process heat demand, and domestic hot water demand. The equipment operation data includes operating efficiency, energy consumption, output power, and operating status information. Waste heat resource data is input into a pre-trained waste heat resource prediction model, and the waste heat supply prediction value is output; energy load data of energy supply facilities is input into a pre-trained energy load prediction model, and the energy demand prediction value is output. The predicted values ​​of waste heat supply, energy demand, and equipment operation data are input into a pre-constructed multi-objective optimization model. An evolutionary multi-objective optimization algorithm is used to solve the multi-objective optimization model to obtain the optimal allocation strategy and equipment control parameters. The multi-objective optimization model takes maximizing waste heat recovery efficiency, minimizing energy supply cost, and minimizing equipment operating losses as joint optimization objectives, and takes equipment operating limits, energy supply stability, and environmental emission standards as constraints. The equipment control parameters are sent as optimization decision instructions to the control systems of each energy device to realize waste heat recovery in the industrial park.

2. The method for waste heat recovery in industrial parks based on a multi-objective optimization model according to claim 1, characterized in that, The basic model of the waste heat resource prediction model adopts the ARIMA time series analysis model and is trained based on historical waste heat resource data; the waste heat resource prediction model is used to predict the future trend of waste heat flue gas volume and temperature changes by combining the production plan of waste heat generating equipment. The basic model of the energy load prediction model is a random forest-based machine learning model, trained on historical energy load data. The energy load prediction model is used to predict the energy demand of various areas of the park by integrating factors such as ambient temperature, ambient humidity, production schedules, and personnel flow.

3. The method for waste heat recovery in industrial parks based on a multi-objective optimization model according to claim 1, characterized in that, The objective function F of the multi-objective optimization model is as follows: minF = -ω1×η + ω2×C + ω3×L In the formula, η is the waste heat recovery efficiency, C is the energy supply cost, and L is the equipment operating loss; ω1, ω2, and ω3 are the corresponding weighting coefficients, satisfying ω1+ω2+ω3=1; The constraints of the multi-objective optimization model are as follows: In the formula, P i is the running power of the i th energy equipment, P min , P max is the upper and lower limits of the equipment power, S is the energy supply stability index, S th is the stability threshold, E is the pollutant emission value, E limit is the environmental protection emission standard limit value.

4. The method for waste heat recovery in industrial parks based on a multi-objective optimization model according to claim 1, characterized in that, In the step of inputting the waste heat supply forecast, energy demand forecast, and equipment operation data into a pre-constructed multi-objective optimization model, and solving the multi-objective optimization model using an evolutionary multi-objective optimization algorithm to obtain the optimal allocation strategy and equipment control parameters, the evolutionary multi-objective optimization algorithm employs an improved particle swarm optimization algorithm, and the specific particle update formula is as follows: Speed ​​update formula: v i (t+1) = ω · v i (t) + c1 · r1 · (pbest i (t) - x i (t)) + c2 · r2 · (gbest(t) - x i (t)) Position update formula: x i (t+1)=x i (t)+v i (t+1) In the formula, ω is the inertia weight, c1 and c2 are both learning factors, r1 and r2 are both random numbers in the interval [0, 1], and v i (t) represents the velocity of the i-th particle at time t; x i (t) represents the position of the i-th particle at time t; pbest i gbest(t) represents the optimal position of the i-th individual particle; gbest(t) represents the global optimal position.

5. The method for waste heat recovery in industrial parks based on a multi-objective optimization model according to claim 1, characterized in that, In the step of inputting the waste heat supply forecast, energy demand forecast, and equipment operation data into a pre-constructed multi-objective optimization model, and solving the multi-objective optimization model using an evolutionary multi-objective optimization algorithm to obtain the optimal allocation strategy and equipment control parameters, the evolutionary multi-objective optimization algorithm uses a genetic algorithm, and the specific calculation rules are as follows: Fitness function: fitness = α·(1 / η) + β·C + γ·L; where α + β + γ = 1, α, β, and γ are the weights corresponding to waste heat recovery efficiency, energy supply cost, and equipment operating loss, and are normalization coefficients; In the formula, fitness is the fitness value of the genetic algorithm; η is the waste heat recovery efficiency; C is the energy supply cost; and L is the equipment operating loss. Selection operator: Use roulette wheel selection to screen for superior individuals; Crossover operator: Gene recombination is achieved through single-point crossover; Mutation operator: Gene perturbation is achieved using Gaussian mutation; The optimal allocation strategy and equipment control parameters are solved iteratively by selecting operators, crossover operators, and mutation operators.

6. The method for waste heat recovery in industrial parks based on a multi-objective optimization model according to claim 1, characterized in that, It also includes a closed-loop feedback correction step: Real-time collection of actual operating parameters of energy equipment and energy supply effect data, and comparison of actual operating data with waste heat supply forecasts, energy demand forecasts, and optimization target values; If the data deviation exceeds the preset threshold, the parameters of the waste heat resource prediction model, energy load prediction model, and multi-objective optimization model will be corrected, and the optimal allocation strategy and equipment control parameters will be solved again.

7. The method for waste heat recovery in industrial parks based on a multi-objective optimization model according to claim 1, characterized in that, The optimal allocation strategy adopts a waste heat cascade utilization strategy: Waste heat quality is classified according to waste heat temperature and flow rate. High-temperature waste heat is allocated to the heating / cooling process, and low-temperature waste heat is allocated to the domestic hot water supply / process heat replenishment process. The decision-making instructions are dynamically adjusted and optimized based on the seasonal energy consumption characteristics of the park, including: During the heating season: increase the heat exchange load of high-temperature heat exchangers, reduce the power consumption of solid thermal storage units, and adjust the hot water supply temperature according to the fluctuations in heat load; Cooling season: Match the efficiency model of the absorption chiller to allocate high-temperature waste heat, and adjust the air source heat pump load according to the cooling period of the factory and dormitory buildings; During the transition season: Priority is given to using high-temperature waste heat to drive ORC generator sets for power generation, while low-temperature waste heat is used to supply domestic hot water. If waste heat is insufficient, air source heat pumps are started to supplement it.

8. A waste heat recovery system for industrial parks based on a multi-objective optimization model, characterized in that, include: The data acquisition module is used to collect waste heat resource data from waste heat generation equipment in the industrial park, energy load data from energy supply facilities, and equipment operation data from energy equipment. The waste heat resource data includes flue gas flow rate, flue gas temperature, and flue gas composition. The energy load data includes real-time heating and cooling loads, process heat demand, and domestic hot water demand. The equipment operation data includes operating efficiency, energy consumption, output power, and operating status information. The prediction module is used to input waste heat resource data into a pre-trained waste heat resource prediction model and output waste heat supply prediction values; and to input energy load data of energy supply facilities into a pre-trained energy load prediction model and output energy demand prediction values. The objective optimization module is used to input the waste heat supply forecast, energy demand forecast, and equipment operation data into a pre-constructed multi-objective optimization model. An evolutionary multi-objective optimization algorithm is used to solve the multi-objective optimization model to obtain the optimal allocation strategy and equipment control parameters. The multi-objective optimization model takes maximizing waste heat recovery efficiency, minimizing energy supply cost, and minimizing equipment operating losses as joint optimization objectives, and takes equipment operating limits, energy supply stability, and environmental emission standards as constraints. The instruction output module is used to send equipment control parameters as optimization decision instructions to the control systems of various energy devices to realize waste heat recovery in the industrial park.

9. A waste heat recovery device for industrial parks based on a multi-objective optimization model, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the waste heat recovery method for industrial parks based on a multi-objective optimization model as described in any one of claims 1-7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it is used to implement the waste heat recovery method for industrial parks based on a multi-objective optimization model as described in any one of claims 1-7.

Images