SSIs Presentation by Arnab.pdf

Transcript

1. Self-Introduction My name is M M Raian Mowla Arnab. I have completed my Bachelor in Electrical and Electronic Engineering from the International Islamic University Chittagong (IIUC). Presently I am engaged in working at an Oil and Gas refinery plant as a HSE Engineer. My expertise lies in managing electrical systems, ensuring the efficient operation, and promoting workplace safety. During my undergraduate studies, I gained a comprehensive understanding of electrical and power systems engineering through a well-rounded curriculum that emphasized both theoretical and practical aspects. With a decade of experience in the power generation industry, I have built a strong foundation in electrical systems, power electronics, and systems integration. During my career, I’ve seen how smart technologies, like automation and intelligent sensors, are transforming modern engineering. I believe the MSc in Smart Systems Integrated Solutions (SSIs) is the ideal opportunity to achieve this goal and advance my career in this exciting field.
2. Predictive Maintenance Tools in Power Plant Optimization Slide 2: Introduction Project Overview: • Upgraded and optimized a 100 MW power generation facility • Implemented predictive maintenance tools to improve operational efficiency • Reduced unplanned downtime by 10% and ensured reliable power delivery Objective: • Enhance system reliability through real-time monitoring and data-driven maintenance.
3. Slide 3: How Predictive Maintenance Worked Sensor Deployment: • Installed smart sensors on critical equipment (turbines, generators, pumps, motors). Monitored key parameters: • Vibration: To detect imbalance and mechanical wear. (PCB Piezotronics) • Temperature: To identify overheating and lubrication issues.(PT100) • Oil Quality: To ensure proper lubrication and detect contamination.(Parker iCount) • Electrical Performance: To monitor voltage, current, and power factor.(Fluke 435-II) Data Collection & IoT Integration: • Sensors transmitted real-time data to a centralized monitoring system. • Created a digital twin for virtual tracking of plant operations. Data Analysis & Predictive Algorithms: • Machine learning algorithms analyzed sensor data. • Trend analysis identified deviations from normal conditions. • Example: Abnormal bearing vibration or temperature rise triggered alerts. Condition-Based Alerts: • Alerts notified the maintenance team for proactive action. • Maintenance was scheduled based on equipment condition, not fixed intervals. Maintenance Action: • Targeted inspections and repairs prevented failures. • Improved component lifespan and overall system health.
4. Slide 4: Workflow Diagram Predictive Maintenance Flow: • [Smart Sensors] ➔ [IoT Gateway] ➔ [Data Analysis] ➔ [Alerts] ➔ [Preventive Action] ➔ [Continuous Monitoring]
5. Slide 5: Results Achieved • 10% Reduction in Unplanned Downtime: Early detection prevented unexpected breakdowns. • 20% Cost Savings: Reduced emergency repairs and optimized spare part usage. • Improved Efficiency: Reliable equipment ensured smooth power generation. • Better Resource Allocation: Maintenance teams focused on critical tasks.
6. Slide 6: Conclusion Key Takeaways: • Predictive maintenance transformed plant operations from reactive to proactive. • Real-time monitoring ensured early fault detection and timely intervention. • Enhanced efficiency, cost savings, and system reliability. Future Scope: • Expand predictive maintenance across other plant units. • Integrate AI-driven analytics for even more precise fault detection.