Module 1: Foundations of Industrial Data and Python Environment Setup

• Characteristics of industrial data: time-series, sensor readings, categorical logs
• Installation and configuration of Python, Anaconda, and Jupyter Notebooks
• Introduction to the Python environment and basic data structures (lists, dictionaries)
• Principles of reproducible code using virtual environments and dependency management
• Overview of key Python libraries: NumPy, Pandas, and Matplotlib

Practical session: Setting up the Python environment, installing required libraries, and loading a large industrial machine log file into a Pandas DataFrame.

Module 2: Python Fundamentals for Industrial Data Processing (Pandas)

• Mastering the Pandas DataFrame structure for tabular industrial data
• Data selection, slicing, and indexing using loc and iloc
• Data cleaning: handling missing values (imputation and removal), and outliers
• Data aggregation and grouping for summarizing equipment performance
• Introduction to functional programming concepts in Pandas

Practical session: Cleaning a raw sensor dataset by handling multiple types of missing values and aggregating daily summaries of operational parameters.

Module 3: Time Series Analysis of Sensor Data (Resampling and Filtering)

• Understanding the structure of industrial time-series data and datetime indices
• Resampling techniques: aggregating high-frequency data (e.g., from seconds to minutes)
• Interpolation methods to handle short gaps in continuous sensor readings
• Applying rolling statistics (mean, standard deviation) to smooth noisy data
• Detecting and handling seasonality and trends in long-term operational data

Practical session: Resampling 1-second vibration data to 1-minute averages and applying an Exponentially Weighted Moving Average (EWMA) to identify subtle trends.

Module 4: Advanced Data Preprocessing and Feature Engineering

• Creating time-based features (time since last event, day of week, shift indicator)
• Calculating shift and lag features for modeling sequential machine states
• Feature scaling and normalization for machine learning models
• Encoding categorical variables (e.g., machine type, fault code)
• Dimensionality reduction techniques (e.g., Principal Component Analysis - PCA) for complex processes

Practical session: Generating time-to-failure (TTF) features and applying standard scaling to sensor readings in preparation for model building.

Module 5: Descriptive and Exploratory Data Analysis in Python

• Summarizing data using descriptive statistics (mean, median, standard deviation, quartiles)
• Visualizing sensor data over time using Matplotlib and Seaborn
• Creating correlation matrices to understand relationships between process variables
• Plotting distribution of key quality and performance metrics
• Identifying periods of high variability and potential data quality issues

Practical session: Generating a descriptive statistics report and creating a visual dashboard layout of key metrics using Python plots.

Module 6: Statistical Process Control (SPC) and Anomaly Detection

• Introduction to Statistical Process Control and its application in manufacturing
• Calculating control limits and creating Shewhart Control Charts (X-bar, R-charts)
• Interpreting control chart patterns for process instability
• Implementing basic anomaly detection algorithms (e.g., Isolation Forest, Z-score)
• Identifying and flagging abnormal equipment behavior or sensor drift

Practical session: Implementing an X-bar and R control chart in Python on a key process metric and flagging out-of-control observations.

Module 7: Predictive Maintenance: Classification Models in Python

• Defining the Predictive Maintenance problem (predicting failure/non-failure)
• Introduction to classification algorithms (Logistic Regression, Random Forest, SVM)
• Training and evaluating models using Scikit-learn (e.g., cross-validation)
• Understanding and using classification metrics: Precision, Recall, F1-Score, and ROC curves
• Strategies for handling imbalanced datasets (e.g., few failures vs. many non-failures)

Practical session: Building a Random Forest model to predict equipment failure within the next 48 hours and evaluating its performance metrics.

Module 8: Regression Models for Process Optimization

• Applying regression for predicting continuous variables (e.g., energy consumption, yield)
• Implementing Linear Regression, Ridge, and Lasso for process modeling
• Evaluating regression model performance (R-squared, MAE, RMSE)
• Interpreting feature importance to understand factors driving process outcomes
• Optimizing process settings based on model coefficients

Practical session: Building a regression model to predict the energy consumption of a piece of equipment based on its operational features and interpreting the coefficients.

Module 9: Introduction to Power BI for Data Connection

• Overview of the Power BI interface, components, and purpose in industrial settings
• Connecting to data sources: flat files, SQL databases, and web services
• Understanding data flow from source to report (ETL process)
• Importing cleaned and modeled Python outputs (e.g., failure predictions)
• Setting up parameters and data source credentials

Practical session: Connecting Power BI to the finalized Python-processed dataset containing both sensor readings and failure predictions.

Module 10: Data Transformation and M-Query for Industrial Data

• Utilizing the Power Query Editor for last-mile data preparation
• Mastering essential transformations: pivoting/unpivoting sensor readings
• Creating custom columns and functions using M-Query language
• Merging and appending different data streams (e.g., sensor data with work order logs)
• Ensuring data is formatted correctly for Power BI's reporting layer

Practical session: Using M-Query to merge the equipment hierarchy list with the sensor data table and apply a conditional column for equipment status.

Module 11: Data Modeling for Manufacturing and IoT Datasets

• Principles of dimensional modeling (Fact and Dimension tables) in manufacturing
• Creating and managing relationships (e.g., Equipment, Time, Faults, Work Orders)
• Developing a robust Time Dimension table for temporal analysis
• Optimizing the data model for performance with large industrial datasets
• Managing many-to-many relationships for complex asset structures

Practical session: Designing a comprehensive data model for a production line, defining one-to-many relationships between the main sensor log and dimension tables.

Module 12: DAX Fundamentals for Calculating Operational Metrics

• Introduction to DAX (Data Analysis Expressions) syntax and concepts
• Creating calculated measures for aggregation (Total Runtime, Total Downtime)
• Understanding Filter Context vs. Row Context and the CALCULATE function
• Calculating rolling averages, year-to-date (YTD), and prior-period performance
• Implementing complex Industrial KPIs: OEE (Availability, Performance, Quality), Mean Time Between Failures (MTBF)

Practical session: Writing three key DAX measures: Availability for OEE, a 30-day rolling average for Yield, and the MTBF metric.

Module 13: Creating Interactive Performance Dashboards in Power BI

• Principles of effective industrial dashboard design and data hierarchy
• Utilizing standard Power BI visuals (Gauges, Cards, Tables, Line Charts)
• Implementing conditional formatting and data alerts for immediate action
• Designing user interactions: slicers, drill-through, and report filters
• Ensuring the dashboard is optimized for large screens in a control room setting

Practical session: Building the main dashboard canvas, including a large OEE gauge and key performance cards linked to the DAX metrics.

Module 14: Integrating Python Visuals and Scripts into Power BI

• Enabling and configuring the Python script engine within Power BI
• Writing Python scripts to generate custom statistical or machine learning visuals
• Passing processed data seamlessly from the Power BI model to Python
• Troubleshooting integration issues and managing security considerations
• Embedding Python-generated visuals (e.g., SPC charts, feature importance plots) into the Power BI report

Practical session: Using a Python script within Power BI to generate a custom SPC chart for a quality metric and displaying it on the report page.

Module 15: Root Cause Analysis and Drill-Through Reporting

• Designing drill-through pages to move from high-level KPIs to granular details
• Implementing filtering mechanisms to isolate specific failures or process deviations
• Using visuals like Decomposition Trees and Key Influencers for automated RCA
• Creating historical trend comparisons to benchmark performance
• Documenting and communicating RCA findings through the Power BI report

Practical session: Implementing a drill-through action from the OEE Availability metric to a detail page showing the top 5 contributing downtime reasons.

Module 16: Data Security and Governance in Industrial Analytics

• Principles of securing sensitive operational data and intellectual property
• Implementing Row-Level Security (RLS) to restrict data views based on user roles
• Best practices for securing data gateways and data connections
• Understanding data retention policies and regulatory compliance (e.g., process data logging)
• Managing workspace roles and access permissions in the Power BI Service

Practical session: Applying RLS to the Power BI model to ensure different user groups can only see data for their assigned equipment or production line.

Module 17: Automating Data Pipelines and Dashboard Deployment

• Understanding the Power BI Service workspace and deployment pipelines
• Setting up a data gateway for continuous data refresh from on-premise sources
• Configuring scheduled refresh and managing refresh history
• Publishing and distributing dashboards using Power BI Apps and embedding options
• Strategies for monitoring report usage and data source health

Practical session: Publishing the final report to the Power BI Service and configuring the data source and refresh settings for automation.

Module 18: Final Capstone Project: End-to-End Industrial Analytics

• Defining the final project based on a complex industrial use case (e.g., quality prediction)
• Participants execute the full pipeline: Python cleaning and modeling to Power BI visualization
• Peer review and expert feedback on model accuracy, DAX calculations, and dashboard design
• Presenting strategic operational insights derived from the final dashboard
• Strategies for adopting advanced analytics and continuous improvement in the industrial workplace

Practical session: Presenting the final, comprehensive Power BI Industrial Analytics dashboard, highlighting the Python modeling results, and defending the operational recommendations.

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