Predictive maintenance in Schneider Electric

Initially, Schneider Electric ran an analysis on the problematic machine to determine the main cause of the downtime and assess the machine health. After this analysis, they discovered it was partly due to the long timeframe applied for changing old parts. To address this issue Schneider Electric began regularly changing components. However, only 18% of the unplanned downtime was related to the age of components. Based on this, Schneider Electric installed temperature and current sensors to monitor this critical machine’s behavior. The data from these sensors was stored in Aveva Insight, then passed into Senseye PdM to be analyzed against historical data. Using powerful AI and ML algorithms based on mechanical frameworks, Senseye PdM was able to automatically provide maintenance engineers with alerts before the machine would fail. For example, machine operators were notified before a spindle or counter spindle would break giving a 7-point improvement in OEE.