Here you can find the summary of the research projects that I worked at the intersection of manufacturing and artificial intelligence
Industrial Partners: Capgemini, Siemens, Volvo Group, SKF and Husqvarna Group
Academic Partners: Chalmers University, Skövde University
September 2022 - Current
It is a 3-year, 5 M SEK research project funded by VINNOA (The Swedish Innovation Agency), named Trustworthy Predictive Maintenance (TPdM). The aim is to provide AI-based predictive maintenance solutions to the manufacturing industries. Specifically, the project intends to create human-centered AI solutions that amplify and augment rather than displace the human workforce in a factory. And this can will be achieved by providing interpretable and explainable results, all of which will help humans to make confident and quick decisions. The expected effects of the project are reduced downtime, increased productivity and robustness, and improved competence in the manufacturing community, thus enhancing the competitiveness of Swedish manufacturing companies.
Industrial Partners: IBM, SAS, Siemens, Gestamp, Visual Components, Volkswagen, Whirlpool, Benteler, Philips, Atlantis
Academic Partners: Chalmers University, Bonn University, Politecnico Milano, Fraunhofer IEM
September 2019 - February 2021
Supervisor: Prof. Anders Skoogh
The purpose of the project is to develop open interfaces for the development of big data pipelines for advanced analysis services and data visualization supported by the main digital engineering, simulation, operations and industrial quality control platforms. I am developing data-driven algorithms that can analyse the production flow and optimize it to achieve higher throughput.
You can read more about the project here.
Industrial Partners: Volvo Group, Volvo Cars, Scania AB, IFS, AXXOS AB
Academic Partners: Chalmers, KTH, MDH
February 2016 - February 2019
Supervisor: Prof. Anders Skoogh
This project had four different work packages (WP1-WP4) focussed on increasing the efficiency of maintenance planning in production systems. I worked in WP2 that is focussed on developing data-driven algorithms using statistical and machine learning tools to improve the efficiency of back office maintenance planning of production systems.
You can read more about the project and its outcomes here.
4. Data Analytics and Maintenance Preparedness – Volvo Maintenance Management System (DAMP- VMMS)
Industrial Partners: Volvo Group
Academic Partners: Chalmers
September 2015 - December 2015
Supervisor: Prof. Anders Skoogh
The purpose of the project is to investigate and develop a model for criticality classification of production resources from a maintenance perspective. I developed a data-driven algorithm to identify critical resources from production system event logs.
You can read more about the data-driven algorithm here.