VIDEOS

Maintenance opportunity windows using AI

DAIMP Research Project Outcomes

Data-driven algorithm to predict throughput bottlenecks in production system (Full paper here)


A generic hierarchical clustering approach for detecting bottlenecks in manufacturing (Full paper here)

PODCASTS

DigiTalk Pod: 7. Big Data for Big Decisions in Maintenance Guest: Mukund Subramaniyan, PhD student, Chalmers University of Technology “The data speaks about the behavior of the production system” Instead of defining big data in terms of “what” and “how”, Mukund Subramaniyan invites us to asks: “why” big data? In this episode, Mukund Subramaniyan shares his adventure and precious knowledge as cross-disciplinary PhD student, bridging the gap between computer science and production engineering. His motto? Big data for big decisions. Mukund sees the potential of data in the production system, and uses his mathematical skills, combined with his knowledge about production systems’ operations, to find the most efficient and effective way to transform data into knowledge. His mission is to help managers and engineers in the production and maintenance departments to make more accurate decisions with higher degree of confidence. Mukund’s position in terms of balance between automation and human’s contribution is that algorithms should be giving an augmented intelligence to humans as opposed to be the representatives of an artificial intelligence that does all the job, simply put. Mukund argues that 60-70 % of the work can be done by algorithms, and the remaining part of the work is up to the humans, who judge the results according to their experience, and make the final decision.  Check out Mukund’s publications: Subramaniyan, M., Skoogh, A., Salomonsson, H., Bangalore, P., Gopalakrishnan, M., & Sheikh Muhammad, A. (2018). Data-driven algorithm for throughput bottleneck analysis of production systems. Production & Manufacturing Research, 6(1), 225-246. Subramaniyan, M., Skoogh, A., Gopalakrishnan, M., Salomonsson, H., Hanna, A., & Lämkull, D. (2016). An algorithm for data-driven shifting bottleneck detection. Cogent Engineering, 3(1), 1239516. DOI: