A Hybrid Learning Approach to Prognostics and Health Management Applied to Military Ground Vehicles Using Time-Series and Maintenance Event Data

Abstract

Attempts to leverage operational time-series data in Condition Based Maintenance (CBM) approaches to optimize the life cycle management and Reliability, Availability, and Maintainability (RAM) of military vehicles have encountered several obstacles over decades of data collection. These obstacles have beset similar approaches on civilian ground vehicles, as well as on aircraft and other complex systems. Analysis of operational data is critical because it represents a continuous recording of the state of the system. Applying rudimentary data analytics to operational data can provide insights like fuel usage patterns or observed reliability of one vehicle or even a fleet. Monitoring trends and analyzing patterns in this data over time, however, can provide insight into the health of a vehicle, a complex system, or a fleet, predicting mean time to failure or compiling logistic or life cycle needs. Such High-Performance Data Analytics (HPDA) on operational time-series datasets has been historically difficult due to the large amount of data gathered from vehicle sensors, the lack of association between clusters observed in the data and failures or unscheduled maintenance events, and the deficiency of unsupervised learning techniques for time-series data. We present an HPDA environment and a method of discovering patterns in vehicle operational data that determines models for predicting the likelihood of imminent failure, referred to as Parameter-Based Indicators (PBIs). Our method is a data-driven approach that uses both time-series and relational maintenance data. This hybrid approach combines both supervised and unsupervised machine learning and data analytic techniques to correlate labeled, relational maintenance event data with unlabeled operational time-series data utilizing the DoD High Performance Computing (HPC) capabilities at the U.S. Army Engineer Research and Development Center. In leveraging both time-series and relational data, we demonstrate a means of fast, purely data-driven model creation that is more broadly applicable and requires less a priori information than physics informed, data-driven models. By blending these approaches, this system will be able to relate some lifecycle management goals through the workflow to generate specific PBIs that will predict failures or highlight appropriate areas of concern in individual or collective vehicle histories.

Early life-cycle prediction of reliability

“…Discussions with the Bond research team included topics related to the previously researched supervised and unsupervised methods, the extent to which these methods were considered during the previous model development process, and data analysis scripts used to explore the ground vehicle data set. Similarities exist between the previous hybrid approach research (Bond et al 2020) and the post hoc approach considered by this research project.…”

“…Data for the ground vehicles were collected through a controller area network (CAN) bus and consist of 60 columns at 1 value per second. Previous research efforts examined semi-supervised and unsupervised machine learning methods by which to explore and analyze the data set (Bond et al 2020). Discussions with the Bond research team included topics related to the previously researched supervised and unsupervised methods, the extent to which these methods were considered during the previous model development process, and data analysis scripts used to explore the ground vehicle data set.…”

“…The pipelined, caching architecture allowed for faster iterative model development and avoided duplication of computational tasks between consecutive runs locally and on the HPC, which enabled more flexible use of HPC time and increased flexibility of data importing. The pipelined, caching architecture was derived after analyzing sample code from the research of Bond et al (2020). The deployment of this architecture allowed for an easy transition of the model to other data sets (e.g., other ground vehicles, air vehicles, etc.…”