Accurate prediction of product failures becomes critical for various reasons such as understanding design quality, evaluating the warranty performance of manufacturers, and defining cost-efficient repair strategies. In this work, a large dataset of over 530,000 repairs and maintenance of medical devices is investigated by employing three computational techniques including machine learning, frequency analysis, and Discrete Time Markov Chain (DTMC). The objective is to analyze the performance of product design by predicting several key parameters including the number of repairs, the time of product failure, and the time to repair. First, Support Vector Machine (SVM) as one of the machine learning models with four kernel functions is used to forecast the timing of the next failure or repair request in the system for two different products and two different failure types, namely random failure and physical damage. Second, a frequency analysis is conducted to explore the product quality level based on product failure and the time to repair it. The best probability distributions are fitted for the number of failures, the time between failures, and time to repair. Finally, the repair service decision process is modeled by using a DTMC model, and the best repair decisions are determined based on the proposed model. The results reveal the value of big data analytics and machine learning tools in analyzing post-market product performance and the impact of design quality on the cost of repair and maintenance operations.


Machine Learning, Frequency Analysis and Markov Chain Model for Analyzing Product Repair and Maintenance Service Decisions

Division / Sponsors: 
Design Engineering Division and Computers & Information In Engineering Division


Paper Proceedings: https://asmedigitalcollection.asme.org/IDETC-CIE/IDETC-CIE2020/volume/83907

IDETC2020 - Virtual Conference

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.