A multi-objective optimization method for oven temperature field uniformity based on CFD simulation and integrated surrogate model

Abstract

This invention relates to a multi-objective optimization method for oven temperature field uniformity based on CFD simulation and an integrated surrogate model, belonging to the field of intelligent optimization control technology for industrial ovens. The method includes: determining the optimization variables affecting the oven temperature field distribution and their value ranges; generating input conditions using Latin hypercube sampling; establishing a virtual sample library of the oven temperature field based on CFD simulation and extracting performance indicators such as temperature field uniformity, steady-state time, and energy consumption; training an integrated surrogate model using the sample data; embedding the trained surrogate model into the NSGA-II multi-objective genetic algorithm to perform multi-objective optimization of the oven operating parameters; and finally verifying and analyzing the optimization results. By replacing time-consuming CFD iterative calculations with a surrogate model, synergistic optimization among oven temperature field uniformity, steady-state time, and energy consumption is achieved. This invention is applicable to the temperature field optimization design and operating parameter optimization of loaded baking equipment such as constant temperature drying ovens for tobacco.

Description

Technical Field

[0001] This invention relates to a method for temperature field control and optimization of industrial ovens, and more particularly to a multi-objective optimization method based on CFD simulation and integrated surrogate model, which is used to improve the temperature field uniformity of the oven, shorten the steady-state time and reduce energy consumption, belonging to the field of intelligent design and process optimization technology of industrial ovens. Background Technology

[0002] In industrial ovens, temperature uniformity directly impacts product quality, energy consumption, and production efficiency during heating, drying, and baking processes. Traditional oven control relies primarily on manual experience or single-objective regulation, which presents several problems in practical applications. First, existing ovens often use local measurement points to obtain temperature data, failing to comprehensively reflect the temperature distribution across all areas within the oven. Second, airflow velocity, a key parameter affecting temperature uniformity and heat transfer efficiency, is often neglected, leading to uneven heat flow distribution and difficulty in maintaining a stable temperature field. Furthermore, high-precision CFD simulations require lengthy single-run solutions, hindering rapid optimization across a wide range of operating conditions.

[0003] Furthermore, existing optimization methods often focus on single objectives, such as temperature field uniformity or energy consumption, lacking multi-objective optimization strategies that simultaneously consider steady-state time, energy consumption, and temperature field uniformity. Current simulation and optimization techniques are inefficient, unable to quickly obtain high-performance operating conditions, and have limited ability to explore complex parameter spaces. Therefore, a novel oven temperature field optimization method is needed that can combine CFD simulation with integrated surrogate models to quickly predict temperature field performance and achieve comprehensive optimization of temperature field uniformity, steady-state time, and energy consumption through multi-objective optimization, thereby improving oven performance and production efficiency. Summary of the Invention

[0004] This invention relates to a multi-objective optimization method for oven temperature field uniformity based on CFD simulation and integrated surrogate model.

[0005] The specific technical solution adopted in this invention is as follows:

[0006] This invention provides a multi-objective intelligent optimization method for oven temperature field optimization. First, it determines the optimization objectives and corresponding variable ranges, such as temperature field uniformity, steady-state time, and energy consumption. Then, it uses optimal Latin hypercube sampling to generate working condition combinations covering the parameter space. Next, it uses an experimentally verified CFD model for batch simulation, extracting key output indicators to construct an input-output virtual sample library. After data preprocessing, it trains and integrates a surrogate model to establish a high-precision prediction model. This model is then embedded into the NSGA-II multi-objective genetic algorithm for optimization, obtaining a Pareto optimal solution set. Representative working conditions with optimal uniformity, optimal energy consumption, and optimal compromise are selected from this set. Finally, the optimization effect is verified through actual oven experiments.

[0007] The advantages and positive effects of this invention are as follows:

[0008] (1) High-precision temperature field prediction: By constructing a CFD virtual sample library and an integrated proxy model, the temperature field distribution of the box under different working conditions can be predicted quickly and accurately, and the temperature uniformity analysis of the whole field can be realized.

[0009] (2) Multi-objective optimization capability: Combine the NSGA-II algorithm to simultaneously optimize temperature field uniformity, steady-state time and energy consumption, realize the trade-off between various objectives, and improve the operating efficiency of the oven.

[0010] (3) Efficient operating condition screening: The proxy model replaces the time-consuming CFD simulation, which significantly improves the efficiency of optimization calculation and makes large-scale parameter space exploration and operating condition screening possible.

[0011] (4) Flexible adaptability: This method is applicable to industrial ovens of different sizes and structures, supports multiple working condition combinations for optimization, improves the level of intelligent temperature field control and reduces energy consumption, and achieves efficient, stable and uniform oven temperature field control. Attached Figure Description

[0012] When considered in conjunction with the accompanying drawings, the invention will be better understood and its accompanying advantages readily apparent from the following detailed description. However, the accompanying drawings, which are provided to further illustrate the invention and constitute a part of this invention, are intended to explain the invention and do not constitute an undue limitation thereof.

[0013] Figure 1 Figure for the summary of the specification

[0014] Figure 2 This is a three-dimensional structural diagram of the oven of the present invention.

[0015] Figure 3 This is a mesh partitioning diagram for the computational domain of the drying oven.

[0016] Figure 4 Streamline trace diagram of the original structure of the drying oven

[0017] Figure 5 Temperature distribution diagram of the drying oven

[0018] Figure 6 Flow rate distribution diagram of the drying oven Detailed Implementation

[0019] The present invention will be further illustrated below with reference to the accompanying drawings and embodiments. However, these embodiments are merely illustrative, and the scope of protection of the present invention is not limited to these embodiments.

[0020] Combination Figures 2-6 This invention establishes a three-dimensional geometric model inside the oven. Figure 2), and perform mesh generation within the computational domain ( Figure 3 This forms a computational model that can be used for CFD simulation. During the simulation process, streamline trace analysis (…) Figure 4 Temperature distribution analysis Figure 5 ) and velocity distribution analysis ( Figure 6 A comprehensive evaluation of the air circulation and temperature uniformity inside the oven was conducted.

[0021] Based on CFD simulation results, this invention constructs an input-output virtual sample library. Inputs include optimization variables such as heating power, fan speed, and duct layout, while outputs include key indicators such as maximum temperature difference, temperature dispersion, steady-state time, and energy consumption. Subsequently, a high-precision prediction model is established by training an integrated surrogate model (Stacking combining XGBoost and MLP) through data preprocessing. This model is used to quickly predict the temperature and flow field distributions under different operating conditions.

[0022] The trained surrogate model is embedded into the NSGA-II multi-objective genetic algorithm to jointly optimize temperature field uniformity, steady-state time, and energy consumption, obtaining a Pareto optimal solution set. Based on the optimization results, representative operating conditions with optimal uniformity, optimal energy consumption, and optimal compromise are selected, and experimental verification is conducted in an actual oven to ensure that the optimization scheme can achieve the expected results.

[0023] This embodiment achieves precise control and intelligent management of the oven temperature field through a combination of CFD simulation, surrogate model prediction, and multi-objective optimization. Experimental results show that this method can significantly improve temperature field uniformity, shorten steady-state time, and reduce energy consumption, and is applicable to industrial ovens of different sizes and structures.

[0024] The above examples are only for the purpose of helping to understand the core idea of ​​the present invention; at the same time, those skilled in the art will know that there will be changes in the specific implementation methods and application scope based on the idea of ​​the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A multi-objective optimization method for oven temperature field uniformity based on CFD simulation and integrated surrogate model, characterized in that, Includes the following steps: Determine the optimization objectives, optimization variables, and variable ranges for the oven temperature field; use sampling methods to generate input conditions covering the parameter space; Batch CFD simulations were performed based on the input operating conditions to obtain oven temperature field distribution data and construct a virtual sample library; the sample data were preprocessed and an ensemble surrogate model was trained; the trained ensemble surrogate model was embedded into a multi-objective genetic algorithm for optimization to obtain a Pareto optimal solution set; the Pareto optimal solutions were screened and representative operating conditions were selected for experimental verification.

2. The method according to claim 1, characterized in that, The optimization variables include heating power, circulating fan speed, air outlet angle, and load layout parameters, while the constraints include the target temperature range and equipment operating safety boundaries.

3. The method according to claim 1 or 2, characterized in that, The virtual sample library is obtained through batch CFD simulation, and the input conditions are generated using the optimal Latin hypercube sampling method to achieve uniform coverage of the optimized variable parameter space.

4. The method according to any one of claims 1 to 3, characterized in that, The integrated surrogate model training includes sample data preprocessing, surrogate model training, and model performance verification, which is used to establish the mapping relationship between optimization variables and temperature field performance indicators.

5. The method according to any one of claims 1 to 4, characterized in that, The multi-objective genetic algorithm includes population initialization, non-dominated sorting, crowding calculation, crossover mutation, and termination determination steps to obtain a Pareto optimal solution set.

6. The method according to any one of claims 1 to 5, characterized in that, The representative operating conditions include the optimal solution for temperature field uniformity, the optimal solution for energy consumption, and the compromise solution for overall performance. The optimization results are verified through actual oven experiments.

Images