Cognitive Predictive Maintenance and Quality Assurance using EXplainable AI and Machine Learning (CPMXai)
The practice of predictive maintenance has escalated since the advancement in Artificial Intelligence (AI) and Machine Learning (ML). It anticipates the maintenance required, avoiding unnecessary costs (saving time, energy, money and resources) and breakdowns of machines.
However, for more accurate and better predictions cognitive predictive maintenance is required. The AI/ML for cognitive predictive models require all algorithms to be based on supervised and unsupervised learning, requires labelled data where the amount of data is huge as it comprises of historical data, sensor data, related proprietary resources and many more. Again, the decisions generated by the model can also be difficult to comprehend without any explanation.
CPMXai aims to resolve these issues by forming a collaboration between the leading industry partners, SMEs, research institutes and universities. The collaborated consortium comprises of expert personals from the different entities with experience, skills and knowledge to these problems.
CPMXai has 3 objectives:
- Identify use cases in the industries.
- Develop a new automatic data labelling tool with the help of digital twin and lastly.
- Develop a selfmonitoring, self-learning, self-explainable system to predict.
CPMXai will develop a digital twin for cognitive predictive maintenance through automatic data labelling, AI/ML and Explainable AI (XAI) to reduce unwanted situations and enhance maintenance in manufacturing and production processes. By applying XAI and digital twin technology, CPMXai will lessen the flaws in the processes and products and increase reliability of the production system, bringing enhanced business competitiveness as well as economic and environmental sustainability.
Shahina Begum, MDH
→ Mälardalen University
→ Seco Tools
→ Hitachi High-Tech Europe GmbH
→ SPMInstrument AB
→ Nordic Electronic Partner (NEP)
→ Momento AB
→ GKN Driveline Köping AB, Köping