Today, many Swedish manufacturers have access to an enormous amount of data from production and products in use. Despite proven AI (artificial intelligence) techniques, digital technologies and lifecycle engineering (LCE) methods, applying these in combination to industrial cases with the holistic, lifecycle perspective is scarce. This project brings together expertise from AI and LCE to Product/Service Systems for Swedish manufacturing firms in a multidisciplinary research effort to utilise latest techniques efficiently for Swedish production industry.
The project will also develop a plan on how to utilize this hybrid approach in production and maintenance for complex, longlife products manufactured by global firms based in Sweden and in the context of suitable demonstrators. Three value chains will be investigated: Siemens Industrial Turbomachinery (SIT), Volvo Construction Equipment (VCE) and Semcon and with their selected customer. A plan to develop a demonstrator for each value chain will be documented.
The major expected impacts of this project (Step 1) and the forthcoming demonstration project (Step 2) on Swedish industry lie in their improved capacity and competitiveness in production and maintenance. The market potential for AI to be applied in practice is huge. Improved environmental performance is also expected.
Linköpings Universitet (LiU) is the project coordinator and provides expertise about LCE. Mälardalens Högskola contributes through its expertise on AI and provides a case from VCE. SIT provides its own case. Semcon provides a case from its own customers and potential solutions for the three cases. Imagimob provides parts of the technical solutions for the three cases.
To create an inventory of AI techniques for maintenance services, apply AI techniques to three industrial cases, and evaluate their economic and environmental implications.
Industrial production systems typically include many process steps performed by automatic or semi-automatic machines. Depending on the different variables, these machines age and thereby affecting both the quality of the manufacturing step and the resource requirements
Recent research from Chalmers have shown that by slightly tuning robot motions, the energy use can be reduced by 10 –30%, with preserved cycle time.
Improve the efficiency of sawmills, including improved monitoring and maintenance of the production line. This by sharing data via digital twin between the actors in the maintenance chain.
TriBlade is a new ground-breaking technology for rotor blades in wind turbines, which have the potential to affect the entire wind power market. The technology has been developed by Winfoor in collaboration with Lund University and is based on each rotor blade designed as a truss.
Maintenance in existing plants is becoming increasingly important, where predictive maintenance has become an emerging technology. The use of decision support tools contributes to environmentally and economically sustainable production. Within this project, different types of digital twins have been designed and evaluated. Specifically, new predictive model types have been tested in two different industrial case studies; a heat exchanger at SSAB and a profiled header at Svenska Fönster AB.
The long-term goal of the research project is to develop hardware and software platform, i.e. modular systems that enables production workers to easily build and implement IoT-aided improvement solutions at the production shop floor
The project aims at facilitating the implementation of Smart Maintenance through extended collaboration within the maintenance community.
Develop and validate predictive maintenance algorithms based on AI and ML. The vision is failure free production
To demonstrate the new technology with robots that enable Swedish companies to develop innovative new products for automated production o maintenance.
The project aims to digitalize established tools for production disturbance handling.
The goal is to mirror the production and make custom information available for industry personnel.