IIT Bombay · Business & Management

Application of AI in Reliability Engineering - Prognostics and Systems Health Management (PHM)

Prof. Prabhakar V Varde · 60 free video lectures

Artificial Intelligence enabled Prognostics and Health Management (PHM) in general and its implementation at system level is relatively a new field in R&D and academics. The advantage of implementing PHM is it tracks the subject SSCs (System, Structure and Component) performance and thereby provide…

▶ Play on Open Lecture HallCourse page ↗

Lectures

  1. Lecture 1 : Prognostics and Health Management: A Systems Approach
  2. Lecture 2 : Introduction and Background Aspects of Prognostics and Health Management Systems Approach
  3. Lecture 3 : Systems Approach- I
  4. Lecture 4 : Systems Approach (Continued / Risk-Based Engineering & ARCOM)
  5. Lecture 5 : A Brief Overview of Prognostics and Health Management
  6. Lecture 6 : Artificial Intelligence and Machine Learning Enabled Reliability Assurance
  7. Lecture 7 : Advanced PHM Technologies and Approaches
  8. Lecture 8 : Artificial Intelligence and Machine Learning Enabled Reliability Assurance (Part 2)
  9. Lecture 9 : Advanced Machine Learning Techniques for PHM
  10. Lecture 10 : Data-Driven PHM: Implementation, Training, and ANN Configuration
  11. Lecture 11 : Introduction to Systems Approach in Prognostics and Health Management (PHM)
  12. Lecture 12 : System Modeling Approaches in PHM: Deterministic vs. Probabilistic Frameworks and PRA Methods
  13. Lecture 13 : Fundamentals of Probabilistic Risk Assessment: Boolean Logic, Fault Tree Gates, Cut Sets, and Common Cause Failures
  14. Lecture 14 : Probability Distributions in Probabilistic Risk Assessment: Continuous and Discrete Models
  15. Lecture 15 : Statistical Estimation, Maximum Likelihood Estimation (MLE), and Bayesian Updating in PRA
  16. Lecture 16 : Introduction to Sensors and Data Acquisition Systems
  17. Lecture 17 : Sensor Specifications, Functional Properties, and Application Areas
  18. Lecture 18 : Data Acquisition Systems (DAQ) Architecture and Signal Processing
  19. Lecture 19 : Sensor Systems for Electronics PHM and Common Cause Failure
  20. Lecture 20 : Sensor System Attributes, Performance Quantification, and Role of Process Parameters
  21. Lecture 21 : Introduction to the Physics of Failure (PoF) Approach for Electronics
  22. Lecture 22 : Failure Mode, Mechanism, and Effect Analysis (FMMEA) and Time-to-Failure Models
  23. Lecture 23 : Fatigue Induced Degradation and Virtual Qualification Testing
  24. Lecture 24 : Potential of PoF for PHM and Life Consumption Monitoring
  25. Lecture 25 : Canary Devices for Early Warning in PHM
  26. Lecture 26 : AI, Machine Learning, Deep Learning, and Role of Statistical Methods
  27. Lecture 27 : Supervised, Unsupervised, and Reinforced Learning Approaches
  28. Lecture 28 : Probabilistic Methods – Part A: Parametric Approaches
  29. Lecture 29 : Probabilistic Methods – Part B: Error Estimation and Interval Estimation
  30. Lecture 30 : Non-Parametric Methods
  31. Lecture 31 : Advanced Prognostic Modeling Techniques and Data-Driven Approaches
  32. Lecture 32 : Remaining Useful Life (RUL) Estimation Methodologies
  33. Lecture 33 : Machine Learning and Neural Networks in Prognostics
  34. Lecture 34 : Physics-of-Failure (PoF) and Degradation Mechanisms
  35. Lecture 35 : System-Level Prognostics, Health Management Integration, and Case Studies
  36. Lecture 36 : Introduction to Data Analytics for PHM
  37. Lecture 37 : Data Preprocessing and Feature Selection Techniques
  38. Lecture 38 : Feature Extraction Techniques: PCA, Autoencoders, and Case Studies
  39. Lecture 39 : Advanced Feature Extraction: LDA, Isomap, and Self-Organizing Maps (SOM)
  40. Lecture 40 : Fuzzy Data Analysis and Fuzzy Logic in PHM
  41. Lecture 41: Introduction to Deep Learning in Prognostics and Health Management (PHM)
  42. Lecture 42: Deep Learning Considerations for PHM, Agentic AI, and Generative Approaches
  43. Lecture 43: Deep Learning Algorithms (Part A): CNN, RNN, and LSTM Architectures
  44. Lecture 44: Deep Learning Algorithms (Part B): DNN, GAN, DBN, and Deep Reinforcement Learning
  45. Lecture 45: Role of Uncertainty Prediction and Monte Carlo Simulation in PHM
  46. Lecture 46 : Introduction to Systems Approach in PHM
  47. Lecture 47 : State-of-the-Art and Requirements of PHM
  48. Lecture 48 : Risk-Based Approach for System Modeling
  49. Lecture 49 : Identification and Prioritization for Implementing PHM
  50. Lecture 50 : Prognostics and Health Management Metrics
  51. Lecture 51 : AI-Enabled Reliability Assurance and Prognostics
  52. Lecture 52 : Case Study and Data Set Understanding for Run-to-Failure Experiments
  53. Lecture 53 : Proposed Methodology: Deep Learning Framework for RUL Prediction
  54. Lecture 54 : Model Training, Evaluation Metrics, and Results Discussion
  55. Lecture 55 : Introduction to Loose Part Monitoring System (LPMS)
  56. Lecture 56 : Introduction to Anomaly Detection in PHM
  57. Lecture 57 : Techniques for Anomaly Detection
  58. Lecture 58 : Case Study: General Description & Characterization of Aluminum Electrolytic Capacitors (AEC)
  59. Lecture 59 : Failure Modes, Criteria & Degradation Modeling of AECs
  60. Lecture 60 : Experimental Observations, Anomaly Detection & Conclusion on AECs

From NPTEL (IITs and IISc) · CC BY-NC-SA. More from IIT Bombay.

Open Lecture Hall is free, with no ads and no sign-up. It is not run by or connected to any university; the lectures are the universities' own free recordings, played from where they host them. About & rights