Using Data From Similar Systems for Data-Driven Condition Diagnosis and Prognosis of Engineering Systems: A Review and an Outline of Future Research Challenges

Abstract

Prognostics and health management (PHM) is an engineering approach dealing with the diagnosis, prognosis, and management of the health state of engineering systems. Methods that can analyze system behavior, fault conditions, and degradation are crucial for PHM applications, as they create the basis for determining, predicting, and monitoring the health of engineering systems. Data-driven methods have been proven to be suitable for automated diagnosis or prognosis due to their pattern recognition and anomaly detection abilities. Moreover, they do not require knowledge of the underlying degradation process. However, training data-driven methods usually requires a large amount of data, whose collection, cleansing, organization, and preparation are generally very time-consuming and costly. There are usually little or no run-to-failure data available at market launch, especially for new systems such as new machine generations. Nevertheless, related systems, hereinafter referred to as similar systems, often already exist, differing only in some technical characteristics. In this paper, the similar system problem is defined, and explanations of the difficulties that arise when using data from similar systems are presented. Furthermore, it is discussed why the usage of these data offers great potential for condition diagnosis and prognosis of engineering systems. An overview of data-driven methods that can be used to utilize data from similar systems is provided, and the methods that such systems already consider are highlighted. Two related research areas are identified, namely, fleet learning and transfer learning. In the paper, it is shown that similar system approaches will become an important branch of research in PHM. However, some difficulties must be overcome.INDEX TERMS Condition diagnosis, condition prognosis, data-driven methods, fleet learning, prognostics and health management (PHM), similar system approach, similar system problem, transfer learning.

A Study on the Effectiveness of Time Series Similarity Measures for the Comparison of Degradation Curves of Similar Engineering Systems

“…Therefore, measures of similarity between such distributions are useful to compare cross-sectional data. A detailed list of such measures with further subdivisions can be found in [5].…”

“…Therefore, it is difficult to use data from systems operating under different environmental and operating conditions and belonging to different system variants with different technical characteristics. However, if data-driven methods could deal with these differences, the use of these data would have great potential for improving the condition diagnosis and prognosis of engineering systems [5].…”

“…In transfer learning, this is referred to as a negative transfer. Measuring similarity is therefore essential when using data from similar systems [5]. A similarity analysis should be performed before training datadriven methods to decide whether the use of data from other systems is promising or whether the differences are too large and a negative transfer is to be expected.…”

A Comparative Study on Methods for Fusing Data-Driven and Physics-Based Models for Hybrid Remaining Useful Life Prediction of Air Filters

“…Transfer learning aims to use data or models from other domains to increase predictive accuracy or training efficiency in the domain concerned. In diagnostics and prognostics, transfer learning can be used to leverage data from other operating conditions or even from similar engineering systems [14]. In active learning, it is estimated which data points are the most informative for training.…”

A lifetime prediction model based on two-path convolution with attention mechanism and bidirectional long short-term memory network

“…The emergence of deep learning technologies has provided new solutions for bearing lifetime prediction. Deep learning has achieved significant results in handling large-scale data and complex pattern recognition in recent years, offering fresh perspectives for solving bearing lifetime prediction problems [6]. Nie et al selected similar features based on the correlation between bearings and time series, feeding them into a convolutional neural network (CNN) to predict bearing life [7].…”