Syllabus

Module 1( 12 Hrs):
Concepts of Condition Monitoring and Data mining: Introduction to Maintenance strategies, Condition monitoring, Vibration Analysis, Oil Analysis, Motor Circuit Analysis, Thermography, Acoustic Technology, Performance Monitoring Using Automation Data, Introduction to the Concept of Diagnostics, Process of Diagnosis, History of Diagnosis, Big Data in Maintenance, Maintenance Data, Data for Diagnosis and Prognosis.

Module 2 (08 Hrs):
Challenges of Condition Monitoring Using AI Techniques: Anomaly Detection, Types of Anomaly, Rare Class Mining, Chance Discovery, Novelty Detection, Exception Mining, Noise Removal, The Black Swan.

Module 3 (10 Hrs):
Input and Output Data: Supervised Failure Detection, Semi supervised Failure Detection, Unsupervised Failure Detection, Individual Failures, Contextual Failures, Collective Failures. Response Surface Approaches to Modeling: Classification-Based Techniques, SVM-Based Approaches, Bayesian Networks–Based Approaches, Liquid State Machines and Other Reservoir.

Module 4 (08 Hrs):
Cluster-Based Technique in condition monitoring: Categorization versus Classification, Categorization for Semisupervised and Unsupervised, Issues Using Cluster Analysis, Contextual Clustering.
Statistical Techniques in condition monitoring: Use of Stochastic Distributions to Detect Outliers, Issues Related to Data Set Size, Parametric Techniques, Nonparametric Techniques.

Familiarize with the concept of condition-based maintenance for effective utilization of machines.

Impart knowledge of artificial intelligence for machinery fault monitoring and diagnosis.

Learn various issues encountered while applying AI tools in condition monitoriting data.

Learn various cluster based AI technicquies used in condition based monitoring

CO1: Select the proper maintenance strategies and condition monitoring techniques for identification of failure in a machine.
CO2: Acquire various signals data in a dynamic mechanical system for analysis in various AI and ML Tools
CO3: Predict the faulty component in a machine by analysing the acquired vibration signals through diffent AI and ML techniques
CO4: Build different classifier model for machine learning based fault diagnosis of rotating machines
CO5: understand Cluster-Based Technique in condition monitoring

Diego Galar Pascual, Artificial Intelligence Tools Decision Support Systems In Condition Monitoring And Diagnosis, CRC Press, Taylor & Francis, 2015 , DOI: https://doi.org/10.1201/b18384

Amiya Ranjan Mohanty, Machinery Condition Monitoring: Principles and Practices, CRC Press, Taylor & Francis, 2014 , DOI: https://doi.org/10.1201/9781351228626

K.P.Soman, ShyamDiwakar and V.Ajay, Data Mining: Theory and Practice, PHI Learning Pvt. Ltd, 2009 , ISBN:9788120328976, 8120328973

Cornelius Scheffer and PareshGirdhar, Practical Machinery Vibration Analysis and Predictive 3 Maintenance, Newnes, 2004. , https://doi.org/10.1016/B978-0-7506-6275-8.X5000-0