Bangalore, Karnataka, India
Summary
Contributed to the development and implementation of a machine learning-driven predictive maintenance system aimed at optimizing equipment performance and minimizing downtime.
Highlights
Collaborated with UNISYS to introduce a machine learning-driven approach to predictive maintenance, significantly minimizing equipment downtime and maximizing production efficiency.
Achieved 98.7% accuracy, 87.04% precision, and 71.21% recall in forecasting machine operational states, enabling reliable and proactive maintenance decisions.
Classified diverse failure types with 98.35% accuracy, enhancing the precision of proactive maintenance strategies.
Utilized AI and ML techniques to build robust models, ensuring high predictive performance and operational reliability within the system.