AI in Manufacturing and Predictive Maintenance Training Course

Module 1: Introduction to Smart Manufacturing and IIoT

• Evolution from Industry 3.0 to Industry 4.0 and the role of the "Smart Factory"
• Architectural layers of IIoT: Sensors, Gateways, Cloud, and Edge
• Connectivity protocols: MQTT, OPC-UA, and Modbus for AI integration
• Understanding the "Economic Value" of AI on the production line
• Security considerations for connected manufacturing environments
• Practical session: Configuring a simulated MQTT broker to stream real-time sensor data

Module 2: Industrial Data Acquisition and Preprocessing

• Types of industrial data: Time-series, vibrational, acoustic, and thermal
• Signal processing techniques: Fast Fourier Transform (FFT) for vibration analysis
• Handling missing sensor data and outlier detection in noisy environments
• Feature engineering for machinery: Calculating rolling mean, kurtosis, and crest factors
• Data labeling strategies for maintenance: Failure modes vs. healthy states
• Practical session: Building a preprocessing pipeline for high-frequency vibrational data

Module 3: Fundamentals of Predictive Maintenance (PdM)

• Comparing Maintenance Strategies: Reactive, Preventive, and Predictive
• Identifying critical assets and selecting appropriate sensors for PdM
• Supervised learning for failure classification: Predicting "What" will fail
• Multi-class classification for different failure modes (e.g., bearing vs. motor)
• Cost-benefit analysis of PdM implementations
• Practical session: Building a classification model to predict motor failure types using Scikit-Learn

Module 4: Anomaly Detection for Industrial Equipment

• Unsupervised learning for detecting "Unseen" equipment behavior
• Implementing Isolation Forests and One-Class SVMs for machinery monitoring
• Autoencoders for reconstruction-based anomaly detection in telemetry
• Setting dynamic alarm thresholds to prevent "False Alerts"
• Root Cause Analysis (RCA) through anomaly feature contribution
• Practical session: Developing an anomaly detection system for a water pump system

Module 5: Estimating Remaining Useful Life (RUL)

• Defining RUL: Predicting "When" a machine will fail
• Regression techniques for RUL: Linear models vs. Gradient Boosting
• Advanced RUL estimation using LSTMs (Long Short-Term Memory) networks
• Handling "Censored Data" in machinery life cycles
• Evaluating RUL models using Mean Absolute Error and RMSE
• Practical session: Implementing an RUL prediction model using the NASA Turbofan Engine dataset

• ---

Module 6: AI for Quality Control and Computer Vision

• Introduction to automated visual inspection using CNNs (Convolutional Neural Networks)
• Real-time surface defect detection: Scratches, dents, and welding flaws
• Object detection for verifying part assembly and count
• Deploying YOLO (You Only Look Once) models for high-speed production lines
• Transfer learning for manufacturing: Using pre-trained models on small datasets
• Practical session: Training an image classifier to detect defects on a metal surface dataset

Module 7: Reinforcement Learning for Production Optimization

• Introduction to Reinforcement Learning (RL) in a manufacturing context
• Optimizing robotic arm path planning for speed and energy efficiency
• Dynamic production scheduling and bottleneck mitigation using RL agents
• Energy management: Reducing "Peak Demand" charges through intelligent load shifting
• Warehouse and inventory optimization using autonomous agents
• Practical session: Simulating a warehouse picking task optimized by a Reinforcement Learning agent

Module 8: Digital Twins and Virtual Commissioning

• Concept and value of the "Digital Twin": Synchronizing physical and virtual assets
• Using physics-based models to augment AI data (Synthetic Data Generation)
• Virtual Commissioning: Testing AI logic in a simulation before physical rollout
• Integrating real-time sensor streams with 3D factory visualizations
• Scenario planning and "What-if" analysis using digital twins
• Practical session: Building a simple digital twin of a conveyor belt to test predictive logic

Module 9: Edge AI and Industrial Model Deployment

• Why "Edge"? Reducing latency and bandwidth for shop-floor AI
• Hardware overview: Nvidia Jetson, Coral TPU, and Industrial PCs
• Model compression techniques: Quantization and Pruning for edge devices
• Implementing "Inference at the Source": AI inside PLCs and sensors
• Using Docker and Microservices for industrial AI deployment
• Practical session: Quantizing a trained defect detection model for deployment on a low-power edge device

Module 10: MLOps and Scaling AI in the Factory

• Strategies for scaling AI from one machine to an entire enterprise
• Monitoring model performance and "Concept Drift" in evolving factory conditions
• Automated retraining pipelines for industrial machine learning
• Change Management: Training the workforce to work alongside AI assistants
• Building a roadmap for long-term AI maturity in manufacturing
• Practical session: Setting up a model monitoring dashboard to track PdM accuracy across multiple assets

Requirements:

• Participants should be reasonably proficient in English.
• Applicants must live up to Armstrong Global Institute admission criteria.

Terms and Conditions

1. Discounts: Organizations sponsoring Four Participants will have the 5th attend Free

2. What is catered for by the Course Fees: Fees cater for all requirements for the training – Learning materials, Lunches, Teas, Snacks and Certification. All participants will additionally cater for their travel and accommodation expenses, visa application, insurance, and other personal expenses.

3. Certificate Awarded: Participants are awarded Certificates of Participation at the end of the training.

4. The program content shown here is for guidance purposes only. Our continuous course improvement process may lead to changes in topics and course structure.

5. Approval of Course: Our Programs are NITA Approved. Participating organizations can therefore claim reimbursement on fees paid in accordance with NITA Rules.

Booking for Training

Simply send an email to the Training Officer on training@armstrongglobalinstitute.com and we will send you a registration form. We advise you to book early to avoid missing a seat to this training.

Or call us on +254720272325 / +254725012095 / +254724452588

Payment Options

We provide 3 payment options, choose one for your convenience, and kindly make payments at least 5 days before the Training start date to reserve your seat:

1. Groups of 5 People and Above – Cheque Payments to: Armstrong Global Training & Development Center Limited should be paid in advance, 5 days to the training.

2. Invoice: We can send a bill directly to you or your company.

3. Deposit directly into Bank Account (Account details provided upon request)

Cancellation Policy

1. Payment for all courses includes a registration fee, which is non-refundable, and equals 15% of the total sum of the course fee.

2. Participants may cancel attendance 14 days or more prior to the training commencement date.

3. No refunds will be made 14 days or less before the training commencement date. However, participants who are unable to attend may opt to attend a similar training course at a later date or send a substitute participant provided the participation criteria have been met.

Tailor Made Courses

This training course can also be customized for your institution upon request for a minimum of 5 participants. You can have it conducted at our Training Centre or at a convenient location. For further inquiries, please contact us on Tel: +254720272325 / +254725012095 / +254724452588 or Email training@armstrongglobalinstitute.com

Accommodation and Airport Transfer

Accommodation and Airport Transfer is arranged upon request and at extra cost. For reservations contact the Training Officer on Email: training@armstrongglobalinstitute.com or on Tel: +254720272325 / +254725012095 / +254724452588