Search

Scientific research frequently involves the use of computational tools and methods. Providing thorough documentation, open-source code, and data -- the creation of reproducible computational research -- helps others understand a researcher's work. Here, we explore computational reproducibility, broadly, and from within the field of prognostics and health management (PHM). The adoption of reproducible computational research practices remains low across scientific disciplines and within PHM. Our text mining of more than 300 articles, from publications engaged in PHM research, showed that fewer than 1% of researchers made their code and data available to others. Although challenges remain, there are also clear opportunities, and benefits, for engaging in reproducible computational research. Highlighting an opportunity, we introduce an open-source software tool, called PyPHM, to assist PHM researchers in accessing and preprocessing common industrial datasets., Comment: For associated code, see https://github.com/tvhahn/arxiv-code-search and https://github.com/tvhahn/PyPHM Revisions: added additional description of text mining procedure and improved some figures. Results unchanged

Machine learning can be enhanced through the integration of external knowledge. This method, called knowledge informed machine learning, is also applicable within the field of Prognostics and Health Management (PHM). In this paper, the various methods of knowledge informed machine learning, from a PHM context, are reviewed with the goal of helping the reader understand the domain. In addition, a knowledge informed machine learning technique is demonstrated, using the common IMS and PRONOSTIA bearing data sets, for remaining useful life (RUL) prediction. Specifically, knowledge is garnered from the field of reliability engineering which is represented through the Weibull distribution. The knowledge is then integrated into a neural network through a novel Weibull-based loss function. A thorough statistical analysis of the Weibull-based loss function is conducted, demonstrating the effectiveness of the method on the PRONOSTIA data set. However, the Weibull-based loss function is less effective on the IMS data set. The results, shortcomings, and benefits of the approach are discussed in length. Finally, all the code is publicly available for the benefit of other researchers., Comment: Accepted in Journal of Prognostics and Health Management. For associated code see https://github.com/tvhahn/weibull-knowledge-informed-ml