Inzu Group – Rotodynamic System Preventive Maintenance Optimisation (A_BHS)
Inzu Group
Sector: Industry
Business Case
Current maintenance of these types of systems (such as hold baggage screening systems) is either preventive (regardless of actual usage) or corrective (resulting in system downtime, lower availability and higher repair costs). The aim is to see if it is possible to optimise it.
Objectives
Generate a system health indicator using a single measurement system that collects data from a line of up to 30 similar rotodynamic systems. This involves applying start-up difference classification algorithms and measuring mechanical degradation through consumption data.
Use case
The system can utilise the existing control system, minimising the required sensors and assessing mechanical performance through energy consumption. It can operate independently from the control system as well.
Infrastructure
Edge Computing
Technology
Machine learning and deep learning
Data
Private time series datasets
Resources
It was necessary to involve experts in HW, FW, SW development, mechanical and structural engineers, and experts in algorithms and artificial intelligence. Virtually all Aingura staff were involved at some stage of development.
Difficulties and learning
Detecting starters to avoid the limitation of being connected to the control system was the biggest challenge of the project.
KPIs (business impact and metrics of the model)
Reduced unscheduled stops >80%. Reduced the cost of preventive maintenance by 50% and the cost of corrective maintenance by 20%. Payback period of less than 2 years.
Funding
The development was 80% funded by our own resources and 20% from customer projects.
Collaborators, Partners
Multiple: UPM, BSC, UPC
