Smart maintenance
Join us in renewing production maintenance!
#smartmaintenancechalmers

Production Service and Maintenance Systems


This is how we make an impact:
 
  • Setting the agenda for Smart Maintenance
  • Spreading inspiration and knowledge about Smart Maintenance, e.g. in university and industry courses
  • Being the link between production and maintenance
  • Together with industry!

Swedish manufacturing industry is at half capacity

Production disturbances cost Swedish industry more than 100 billion SEK each year, with an Overall Equipment Effectiveness (OEE) at just about 50 percent in average. Hence there are big efficiency gains to be made, and actors that don't use the potentials of digitalisation will have a hard time to cope in a global competitive market.

The manufacturing industry is in the middle of a comprehensive digitalisation journey and business all over the world are currently implementing concepts like Industry 4.0. This often leads to production systems with a higher grade of automation and vaster capabilities to automatically analyze states and make own decisions. There is also an increasing demand in the world for sustainable production.

Smart maintenance is the future of digitalised production

Smart maintenance will decrease downtime by improving the co-operation between production and maintenance organisations. This is made possible by for example shared methods, tools and a common production and maintenance planning. Since smart maintenance means that decisions are based on data, it also requires shared data and information sources.
 
To achieve higher efficiency in the manufacturing industry there is a need for a new way to work with maintenance. That is why we, the research group Production Service and Maintenance Systems, is gathering industry actors and researchers to develop new strategies for the maintenance of the future - smart maintenance in a digitalised production.
Smart maintenance explainer
Smart maintenance is an organizational design for maintenance in a digitalised industry:

  • Decision making based on data
  • The collective competences of the maintenance staff are used
  • Maintenance is a part of the whole business internally
  • Maintenance is a part of the whole business externally
Increased capacity, robustness, and predictability mean a better economy, fewer risks for the staff and lower energy consumption. Smart maintenance is a part of a sustainable future.



Open the image for more information (in Swedish only).


Digitalk podcast - the future of maintenance

Digitalk podcast the future of maintenance Digitalk podcast bid data for big decisions in maintenance Digitalk podcast assessing smart maintenance

 







Research projects

We have research projects within all four head principals of Smart Maintenance. You can find publications and information using the links under each project.

DAIMP - Data Analytics in Maintenance Planning

Film om DAIMP projektetThe DAIMP project connects data structures on a machine level to analyses needed on a systems level. Expected results are for example: data and information structures for improved internal and external collaboration, algorithms for predictive and prescriptive analytics, and data–driven criticality analysis to support differentiated maintenance planning.
 

Smart Maintenance Assessment (SMASh)

The main idea is to develop a Smart Maintenance Assessment (SMA) tool for benchmarking of maintenance organizations within and across companies. Such a tool will help organizations to implement Smart Maintenance through extended collaboration within the maintenance community.
 

Data-driven disturbance handling (D3H)

The major effect goal of the Data-driven disturbance handling project is to digitalize established disturbance handling tools by making them data-driven and, thus, more effective. Desired effects include reduced disturbance frequency, increased Overall Equipment Effectiveness, and better opportunities for cost-effective automation.

Predictive Maintenance using Advanced Cluster Analysis (PACA)

The PACA project aims to develop PdM algorithms, based on advanced cluster analysis, to increase the precision  and make them understandable for decision makers.
 
 

Researchers

Anders Skoogh, research leader. Focus on production system services and maintenance.
Torbjörn Ylipää, lecturer
Maheshwaran Gopalakrishnan, PhD student
Jon Bokrantz, PhD student
Mukund Subramaniyan, PhD student​
Camilla Lundgren, PhD student
Ebru Turanoglu-Bekar, post-doc
Adriana Ito, PhD student
Omkar Salunkhe, PhD student

Published: Wed 13 May 2020.