Devank Khare

About Devank Khare

I am an industrial analytics professional working at the intersection of power plant engineering, machine learning, and digital transformation. Currently serving as an Assistant Manager at Adani Power, I apply data science, predictive modeling, and process optimization techniques to improve reliability, efficiency, and cost performance in large-scale power generation environments.With hands‑on experience across Python, Power BI, OSI PI, and machine learning frameworks, I specialize in:Predictive maintenance & anomaly detectionPlant performance optimizationHigh-frequency sensor data analysisReal-time analytics & KPI dashboardsStatistical modeling for operational insightsBoiler-turbine–auxiliary system optimizationI combine domain knowledge from plant operations with modern ML techniques such as regression models, time series forecasting, clustering, XGBoost, and anomaly detection algorithms. My goal is to build scalable, interpretable AI solutions that enhance asset health, reduce downtime, and support a smarter and more reliable power ecosystem.Looking forward to opportunities in Data Science, Industrial AI, Power Sector Analytics, and Digital Transformation roles.

Experience

1. Assistant Manager

   Adani Power

   Jul 2023 — Present · Madhya Pradesh, IN

   Key Responsibilities:Designed & deployed machine learning models for equipment health monitoring, anomaly detection, and time‑series–based predictive maintenance.Built Power BI dashboards and Streamlit apps for real-time monitoring, KPI reporting, calibration insights, and predictive alerts.Engineered data pipelines integrating OSI PI, DCS/PLC sensors, SAP, and industrial historian data for analytics workflows.Performed process optimization studies for boiler, turbine, and auxiliary systems using statistical and ML techniques.Collaborated with O&M, electrical, mechanical, and IT teams to embed analytics into daily operational decision‑making.Key Achievements:Reduced unplanned breakdowns by 20–30% using ML-based predictive maintenance models.Improved boiler & turbine efficiency by 2–3% through data‑driven tuning and parameter optimization.Automated monthly KPI reporting, reducing manual work by 40% and accelerating leadership insights.Implemented anomaly detection algorithms saving 15% in annual maintenance cost.Enhanced asset availability by 10% via data‑backed maintenance planning.

Education

• LNCT Group of Colleges

  Bachelor of Technology - BTech, Electronics and Communications Engineering

  2019 — 2023