Current Situation
Each factory manages the maintenance of its assets with various levels of success. Some use condition-based monitoring, but there is limited ability to predict failures before they occur. Maintenance teams tend to be older workers that are nearing retirement, leaving knowledge gaps behind with no easy way to fill them.
Goals and Objectives
Highest levels of asset availability results in less factory downtime and lower capital appropriation spending. There will also be a lower cost of maintenance delivery and a reduction in overall labor costs.
Technology Deployed
Hardware: Servers, storage, IoT, smartphones, and tablets
Software: Big Data/analytics, cognitive/AI, machine learning, cloud, mobile, ERP, MES, APM, and SLM
Service: Business services and IT services
Use Case Summary
Machine learning algorithms that build an accurate predictive model of potential failures that can be used to alert maintenance teams in real time; maintenance resources that can be optimized through a tiered support structure, depending on the issue, type of asset, criticality, and so forth