Predictive Analytics: How to Improve Availability of Manufacturing Equipment in Automotive Firms
Shikha Singh, Roshan Batheri, Joyal Dias
Abstract
In the current production scenario, asset management and performance are necessities. Predictive and prescriptive maintenance permits various industries to analyze historical data in real time for the purpose of optimization of industrial operations, such as production, manufacturing, supplantation, etc., to increase productivity and cumulative outcome. The data-driven Industry 4.0 paradigm provides various competitive advantages affecting productivity, quality, and key performance indicators (KPIs). It considers three essential indicators of availability, quality, and performance. Overall equipment efficiency has become the target KPI for most manufacturing companies. This article presents the unique condition-monitoring-based predictive maintenance framework incorporated into the modern world to create a machine-learning-based predictive maintenance approach for automotive industries. We also provide insights into the various methods utilized for data acquisition for a condition-based predictive maintenance framework. The proposed framework has been validated by collecting the raw data from the water pump machine through sensors to preprocess and analyze the performance indicators. The equipment's remaining useful lifetime was calculated based on the data points acquired in real time by calculating the adjacent variation. The developed dashboard has allowed the visible monitoring of all possible anomalies and the remaining useful life of equipment while the machine runs in real time.