Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

MachineHealth: Towards Healthy Machines and Predictive Maintenance with AI.

Reference number
Coordinator Örebro universitet - Institutionen för naturvetenskap och teknik
Funding from Vinnova SEK 479 000
Project duration April 2018 - November 2018
Status Completed
Venture The strategic innovation programme for Swedish mining and metal producing industry - SIP Swedish Mining Innovation
Call STRIM fall 2017

Purpose and goal

The purpose of this project was to develop AI algorithms that could extract long term patterns and trends from events collected from mining machinery. The trends and patterns were presented in a manner that was easily accessible to the end users, furthermore the patterns were extracted not only for one specific machine but also amoung families of machines, and different end users. In this way a global analysis of the machines could be made and systematic patterns across groups could be found in order to provide a step for the manufacturer towards predictive maintenance and efficiency.

Expected results and effects

The results of the project provided an analysis on a dataset of several different machines over a period of time. Different AI techniques were used which looked at correlations and co-appearance within the data. Certain events such as errors and warnings that occured on specific machines were investigated. The effect of this analysis and pilot is twofold. First, we provide a high level view of the data in the context of when machines are used. Second, our algorithms can reveal information about the machines which are not intuitive to the domain experts.

Planned approach and implementation

The project was done in close collaboration with Epiroc and partners. A dataset was provided by Epiroc which consisted of their customers data. The dataset was processed in order to be anonymised to the research team. The research team, provided algorithms to analyse the data and discussons with the partners involved were conducted regularly. In addition to the results of the project, significant focus on 1) long term research challenges 2)integration into business 3) benefit and value chain was made in the project.

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 14 January 2019

Reference number 2017-05442

Page statistics