Teses de Mestrado ESTiG
Permanent URI for this community
Browse
Browsing Teses de Mestrado ESTiG by Sustainable Development Goals (SDG) "04:Educação de Qualidade"
Now showing 1 - 1 of 1
Results Per Page
Sort Options
- Intelligent System for Miscalibration Detection and Quality Prediction in Automotive Assembly LinePublication . Gonçalves, Waldyr Turquetti; Leitão, Paulo; Barbosa, José; Borges, André PinzThis work applies data analysis techniques, Machine Learning and Optimization Algorithms to develop two data analysis systems in the OpenZDM project for the assembly measuring stations in the workshop of an automotive plant. These systems were designed to generate insights into the production line, helping the industry to achieve Zero Defect Manufacturing (ZDM) goals. The case study chapter presents the context for understanding the characteristics of the case study. The following chapters detail the tools created to implement the ZDM strategies. The first is the system for identifying the miscalibration of measuring stations, consisting of a microservice that provides alerts informing whether or not the stations are miscalibrated. The second system is the diagnostic system, made up of four microservices. Within the functionalities of this system, there is the functionality responsible for making quality predictions and the other for improving the hyperparameters of the prediction model. The tests carried out demonstrated theneffectiveness of the systems in dealing with the large volume of data and creating useful insights for the production line. In addition, the cases of miscalibration detection and the prediction process have been validated, affirming the usefulness of the services within the automotive factory’s production line.