This paper is aimed at using the newly developing field of physics informed machine learning (PIML) to develop models for predicting the remaining useful lifetime (RUL) aircraft engines. We consider the well-known benchmark NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) data as the main data for this paper, which consists of sensor outputs in a variety of different operating modes. C-MAPSS is a well-studied dataset with much existing work in the literature that address RUL prediction with classical and deep learning methods. In the absence of published empirical physical laws governing the C-MAPSS data, our approach first uses stochastic methods to estimate the governing physics models from the noisy time series data. In our approach, we model the various sensor readings as being governed by stochastic differential equations, and we estimate the corresponding transition density mean and variance functions of the underlying processes. We then augment LSTM (long-short term memory) models with the learned mean and variance functions during training and inferencing. Our PIML based approach is different from previous methods, and we use the data to first learn the physics. Our results indicate that PIML discovery and solutions methods are well suited for this problem and outperform previous data-only deep learning methods for this data set and task. Moreover, the framework developed herein is flexible, and can be adapted to other situations (other sensor modalities or combined multi-physics environments), including cases where the underlying physics is only partially observed or known.

This workshop continues discussions and explorations started in January 2016 and January 2018 at the first and second editions of the workshop. A revolution in statistics and machine learning (ML) is underway. Modern algorithms can now learn high level abstractions via hierarchical models, leading to break- through accuracy in benchmarks for computer vision, language, etc. Underlying these advances is a strong and deep connection to various aspects of applied mathematics and statistical physics. For example, proper choice of statistical force allows to screen interaction and learn graphical models governing multi-dimensional distributions efficiently, gauge transformations from physics guide incorporation of symmetries in the neural network design, dynamical system interpretation helps to understand and improve performance of most efficient deep learning schemes, etc. This workshop seeks perspectives on leveraging the deep connection between ML and physics, but now with the goal to better understand and model physical systems, static and dynamic.