A Data-Driven Method for Monitoring of Repetitive Systems: Applications to Robust Wear Monitoring of a Robot Joint

Carvalho Bittencourt, André,1984-Linköpings universitet,Reglerteknik,Tekniska högskolan (author)

This paper presents a method for monitoring of systems that operate in a repetitive manner. Considering that data batches collected from a repetitive operation will be similar unless in the presence of an abnormality, a condition change is inferred by comparing the monitored data against a nominal batch. The method proposed considers the comparison of data in the distribution domain, which reveals information of the data amplitude. This is achieved with the use of kernel density estimates and the Kullback-Leibler distance. To decrease sensitivity to unknown disturbances while increasing sensitivity to faults, the use of a weighting vector is suggested which is chosen based on a labeled dataset. The framework is simple to implement and can be used without process interruption, in a batch manner. The method was developed with interests in industrial robotics where a repetitive behavior is commonly found. The problem of wear monitoring in a robot joint is studied based on data collected from a test-cycle. Real data from accelerated wear tests and simulations are considered. Promising results are achieved where the method output shows a clear response to the wear increases.

Saarinen, KariABB Corporate Research (author)
Sander Tavallaey, ShivaABB Corporate Research (author)
Gunnarsson, SvanteLinköpings universitet,Reglerteknik,Tekniska högskolan(Swepub:liu)svagu90 (author)
Linköpings universitetReglerteknik (creator_code:org_t)

By the author/editor: Carvalho Bittenc ...; Saarinen, Kari; Sander Tavallaey ...; Gunnarsson, Svan ...

About the subject

ENGINEERING AND TECHNOLOGY: ENGINEERING AND ...; and Electrical Engin ...; and Robotics

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.