Uncertainty quantification in machine learning for engineering design and health prognostics: A tutorial
Uncertainty quantification in machine learning for engineering design and health prognostics: A tutorial
复制标题
DOI：
10.1016/j.ymssp.2023.110796
复制
发表时间：
2023-05
影响因子：
8.4
通讯作者：
V. Nemani;Luca Biggio;Xun Huan;Zhen Hu;Olga Fink;A. Tran;Yan Wang;X. Du;Xiaoge Zhang
中科院分区：
文献类型：
--
作者：
V. Nemani;Luca Biggio;Xun Huan;Zhen Hu;Olga Fink;A. Tran;Yan Wang;X. Du;Xiaoge Zhang
在机器学习 (ML) 模型之上，不确定性量化 (UQ) 充当安全保证的重要层，可以通过实现健全的风险评估和管理来制定更有原则性的决策。昆士兰大学支持的机器学习模型的安全性和可靠性改进有可能显着促进机器学习解决方案在高风险决策环境中的广泛采用，例如医疗保健、制造和航空等。在本教程中，我们的目标是为 ML 模型提供新兴 UQ 方法的整体视角，特别关注神经网络以及这些 UQ 方法在解决工程设计以及预测和健康管理问题中的应用。为了实现这一目标，我们首先对与 ML 模型 UQ 相关的不确定性类型、来源和原因进行全面分类。接下来，我们提供了几种最先进的 UQ 方法的教程式描述：高斯过程回归、贝叶斯神经网络、神经网络集成和专注于谱归一化神经高斯过程的确定性 UQ 方法。基于数学公式，我们随后定量和定性地检查这些昆士兰大学方法的合理性（通过玩具回归示例），从不同维度检查它们的优点和缺点。然后，我们回顾了通常用于评估分类和回归问题中预测不确定性质量的定量指标。随后，我们讨论了 UQ of ML 模型在解决工程设计和健康预测中具有挑战性的问题中日益重要的作用。两个案例研究（源代码可在 GitHub 上找到）用于演示这些 UQ 方法，并比较它们在锂离子电池早期寿命预测（案例研究 1）和涡扇发动机剩余使用寿命预测（案例研究 2）方面的性能。
On top of machine learning (ML) models, uncertainty quantification (UQ) functions as an essential layer of safety assurance that could lead to more principled decision making by enabling sound risk assessment and management. The safety and reliability improvement of ML models empowered by UQ has the potential to significantly facilitate the broad adoption of ML solutions in high-stakes decision settings, such as healthcare, manufacturing, and aviation, to name a few. In this tutorial, we aim to provide a holistic lens on emerging UQ methods for ML models with a particular focus on neural networks and the applications of these UQ methods in tackling engineering design as well as prognostics and health management problems. Towards this goal, we start with a comprehensive classification of uncertainty types, sources, and causes pertaining to UQ of ML models. Next, we provide a tutorial-style description of several state-of-the-art UQ methods: Gaussian process regression, Bayesian neural network, neural network ensemble, and deterministic UQ methods focusing on spectral-normalized neural Gaussian process. Established upon the mathematical formulations, we subsequently examine the soundness of these UQ methods quantitatively and qualitatively (by a toy regression example) to examine their strengths and shortcomings from different dimensions. Then, we review quantitative metrics commonly used to assess the quality of predictive uncertainty in classification and regression problems. Afterward, we discuss the increasingly important role of UQ of ML models in solving challenging problems in engineering design and health prognostics. Two case studies with source codes available on GitHub are used to demonstrate these UQ methods and compare their performance in the life prediction of lithium-ion batteries at the early stage (case study 1) and the remaining useful life prediction of turbofan engines (case study 2).