Practical AI in Manufacturing

OMRON-TP SkillsFuture Queen Bee Programme

Course Overview

This course will equip participants with the technical skills to apply machine learning algorithms and deploying practical Artificial Intelligence (AI) models with an industrial edge controller for anomaly detection and predictive maintenance. The course will also cover the essential concepts and background for data analysis on supervised and unsupervised machine learning models and their applications in advanced manufacturing. They will be exposed to the manufacturing AI industry use cases deployed at the smart factory within Temasek Polytechnic Advanced Manufacturing Centre.

What You’ll Learn

Perform data processing in machine learning

• Identify data types and categories
• Describe data collection protocols
• Perform data transformation and editing
• Apply feature selection on data sets
• Examine outliers and unbalanced data sets

Apply classification analysis

• Explain the logistic regression method
• Examine the prediction outcome in classification
• Develop different types of classifiers
• Illustrate optimising methods and performance evaluation in classification
• Apply decision tree and decision forest learning
• Apply support vector machine
• Apply regression analysis in advanced manufacturing

Apply Linear Regression

• State the standard metrics in regression analysis
• Explain the linear regression method
• Develop different types of linear regression models
• Illustrate optimising methods and performance evaluation
• Apply decision tree learning with threshold
• Apply regression analysis in advanced manufacturing

Describe the fundamental concepts of edge computing and machine learning

• Explain the fundamental of edge computing
• Explain the fundamental of supervised machine learning
• Identify the different types of machine learning models
• Describe the application of edge computing and machine learning in predictive analytics

Implement machine learning models in edge processor

• Introduction to the major functional components of an edge AI controller
• Generate a plan for predictive maintenance
• Apply tools and libraries to collect data
• Develop a machine learning model with trained data
• Deploy a machine learning model to edge processor
• Analyse the performance of applied Artificial Intelligence (AI) models in predictive maintenance

Course Schedule

Date: 24 – 25 August 2023

Duration: 2 days – Face to Face and 8 hours of self-paced e-learning

Time: 9am – 5pm

Certification

Participants will be issued with a Certificate of Performance upon meeting 75% of the required course attendance.

Brought to you by: