报告题目：Data analytics of maintenance policies in Product-as-a-Service environment

时间：2025年10月23日（周四）下午15:00-17:00

报告地点：主楼317

报告人：Ou Tang教授，林雪平大学

报告人简介：

Ou Tang holds a full professorship in Production Economics since 2010 at Linköping University, Sweden, where he obtained a PhD in 2000. He served as associate editor and editor in the International Journal of Production Economics since 2008, he is the past-president of the International Society for Inventory Research, and current president of the European Decision Science Institute. Ou Tang’s principal research interest is in the field of operations and supply chain management, more specifically it includes inventory modelling, manufacturing planning and control systems, closed loop supply chain management, sustainable supply chains，supply chain risk management, and China related operations management issues. He has published more than 100 scientific articles in international journals such as the European Journal of Operational Research, Computers and Operations Research, Omega, International Journal of Production Economics, Production and Operations Management, and others. Ou Tang has extensive industrial experience with his research projects. As the principal investigator, he has audited and analyzed production and logistics systems, and proposed improvement suggestions in about 50 companies such as Volvo, Scania, Toyota, Siemens, Hewlett-Packard, General Electric, Ericsson, Electrolux, IKEA，Sapa, SSAB, Stora Enso, Alfa lava, Atlas Copco, SKF, among others.

报告内容简介：

Original equipment manufacturers nowadays are shifting towards a product-as-a-service strategy. Their maintenance responsibility should ensure reliable equipment for efficient operations on the customers’ site. Since maintenance decisions rely essentially on product’s failure time affected by usage patterns, differentiating maintenance could potentially reduce failures and maintenance costs, but meanwhile it requires methods for identifying customer groups in datasets with mixed failure information. Therefore, this study proposes a model and an algorithm to derive parameters from examine high order moments in a mixed Weibull distribution, thereby exploring the underlying customer groups. The advantage of distinguishing the mixed customer groups will be obvious when no single group dominates, or the failure rate is increasing and has a large value, or down time cost is significant. Using real data in a case company, we identify products with such a potential. In addition, when bimodality coefficient is medium or high, and when the ratio of two scale factors is high, there is a tendency of two modes in the distribution and distinguishing customer groups becomes essential. Our proposed model and algorithm help to realise such conditions by observing data and its moments. The study results provide guidelines for improving maintenance performance in a product-as-a-service environment.

（承办：管理科学与物流系、科研与学术交流中心）