Temperature field prediction is of great importance in the thermal design of systems engineering, and building the surrogate model is an effective way for the task. Generally, large amounts of labeled data are required to guarantee a good prediction performance of the surrogate model, especially the deep learning model, which have more parameters and better representational ability. However, labeled data, especially high-fidelity labeled data, are usually expensive to obtain and sometimes even impossible. To solve this problem, this paper proposes a pithy deep multi-fidelity model (DMFM) for temperature field prediction, which takes advantage of low-fidelity data to boost the performance with less high-fidelity data. First, a pre-train and fine-tune paradigm are developed in DMFM to train the low-fidelity and high-fidelity data, which significantly reduces the complexity of the deep surrogate model. Then, a self-supervised learning method for training the physics-driven deep multi-fidelity model (PD-DMFM) is proposed, which fully utilizes the physics characteristics of the engineering systems and reduces the dependence on large amounts of labeled low-fidelity data in the training process. Two diverse temperature field prediction problems are constructed to validate the effectiveness of DMFM and PD-DMFM, and the result shows that the proposed method can greatly reduce the dependence of the model on high-fidelity data.
翻译:在系统工程的热设计中,温度田地预测非常重要,而建立代谢模型是完成任务的有效途径。一般而言,需要大量贴标签数据才能保证代谢模型,特别是具有更多参数和更好代表性的深学习模型的良好预测性能。然而,贴标签数据,特别是高纤维标签数据,通常非常昂贵,而且有时甚至不可能获得。为了解决这个问题,本文件提议为温度实地预测采用一个深厚的多纤维模型(DMFM),利用低忠诚度数据提高性能,使用较低忠诚度数据提高性能。首先,在DMFM开发了一种预先和微调模型,以培训低信任度和高忠诚度数据,从而大大降低深度代谢模型的复杂程度。然后,提出了一种自我控制学习方法,用于培训物理学驱动的深厚多纤维模型(DMFMFM)模型(D-DFMFM),充分利用低忠诚度数据的物理特性,并减少DMFMD的高度依赖性能预测过程。