ABSTRACT
To improve manufacturing processes, it is essential to find the root causes of occurring problems, in order to solve them permanently. Automatic Root Cause Analysis (ARCA) solutions aid analysts in finding such root causes, by using automatic data analysis to improve the digital decision. When trying to locate the root cause of a problem in a manufacturing process, a phenomenon can occur that disrupts the application of ARCA solutions. Overlap, as we denominated, is a phenomenon where local synchronicities in the manufacturing process lead to data where it is impossible to discern the influence of each location in the quality of products, which impedes automated diagnosis, especially when using classifiers. This paper identifies and defines overlap, and proposes a two-phase ARCA solution that uses factor-ranking algorithms, instead of classifiers. The proposed solution is evaluated in simulated and real case-study data. Results proved the presence of overlap in the datasets, and its negative impact on classifiers. The proposed solution has a positive performance detecting root causes even in the presence of overlap.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Data availability statement
The data from the Mockup and Stochastic Simulation experiments is available from the corresponding author, Eduardo e Oliveira, upon reasonable request.
The data from the Real Case-Study experiments is not available due to commercial restrictions.
Additional information
Funding
Notes on contributors
Eduardo e Oliveira
Eduardo e Oliveira received the MSc degree in industrial engineering and management from Faculdade de Engenharia da Universidade do Porto in 2015. He is currently pursuing a PhD degree at the same school. He is a researcher at INESC TEC, and his research interests include data mining and diagnosis in manufacturing. He is also an Invited Auxiliary Professor of Information Systems at the Department of Industrial Engineering and Management at the Faculty of Engineering of the University of Porto.
Vera L. Miguéis
Vera L. Miguéis is an Assistant Professor in the Department of Industrial Engineering and Management at the Faculty of Engineering of the University of Porto, Portugal. She received her Ph.D. in Industrial Engineering and Management from the same school. She is a researcher at INESC TEC, and her research interests include data analytics and quantitative methods to support the decision-making process. She has been mainly working on analytical customer relationship management and data mining. She has published papers in several international journals, namely focusing on retailing, education, and manufacturing sectors.
José L. Borges
José L. Borges PhD in Computer Science from the University College of London, U.K., MSc in Electronic Engineering and Computers from the Faculty of Engineering, University of Porto and graduation in Mechanical Engineering from the Faculty of Engineering, University of Porto. Associate Professor in the Department of Industrial Engineering and Management at the Faculty of Engineering, University of Porto, and Researcher at the INESC TEC. Teaches courses in Statistics, Data Mining, Information Systems, Human Computer Interaction and Data Visualisation. 30+ papers in international journals, ISI proceedings and book chapters. Supervision or co-supervision of 4 completed PhD thesis and of 3 ongoing thesis. Supervision of +45 master thesis.