MATLAB & Simulink

DATA ANALYSIS AND MACHINE LEARNING

Predictive Maintenance with MATLAB

Course Highlights

This two-day course focuses on data analytics, signal processing, and machine learning techniques needed for predictive maintenance and condition monitoring workflows. Attendees will learn how to use MATLAB to import data, extract features, and estimate the condition and remaining useful life of equipment.  
 

 Topics include:

  • Importing and organizing data  

  • Creating custom visualizations 

  • Creating classification and regression models  

  • Preprocessing to improve data quality, and extract time and frequency domain features 

  • Estimating Remaining Useful Life (RUL) 

  • Interactive workflows with apps  
     

Partners 

09_MW_logo_RGB.jpg

Upcoming Program

xilinx ATP 黑.png

Techsource Systems is
Mathworks Sole and Authorised Distributor and Training Partner

Who should attend 

This course is intended for data scientists, engineers and managers who need to analyze signals (time series data) for data analytics and predictive maintenance applications. 

Course Prequisites 

MATLAB Fundamentals 

Course Benefits 

Upon the completion of the course, the participants will be able to

- organize data for Predictive Maintenance applications

- create visualization of machine features and condition indicators

- create classification and regression models for anomaly detection and prediction

- preprocess data to improve data quality and extract time and frequency domain features

- estimate remaining useful life (RUL) - use diagnostic feature designer 
 

Course Outline

Day 1 of 2:

Importing Data and Processing Data

Objective: Bring data into MATLAB and organize it for analysis, including handling missing values. Process raw imported data by extracting and manipulating portions of data.  

- Store data using MATLAB data types  

- Import with datastores  

- Process data with missing elements  

- Process big data with tall arrays  

 

Finding Natural Patterns in Data

Objective: Use unsupervised learning techniques to group observations based on a set of condition indicators and discover natural patterns in a data set.  
- Find natural clusters within data  

- Perform dimensionality reduction  

- Evaluate and interpret clusters within data 

 

Building Classification Models

Objective: Use supervised learning techniques to perform predictive modelling for classification problems. Evaluate the accuracy of a predictive model.  

- Classify with the Classification Learner app  

- Train classification models from labeled data  

- Validate trained classification models  - Improve performance with hyperparameter optimization 

 

Day 2 of 2:

Exploring and Analyzing Signals

Objective: Interactively explore and visualize signal processing features in data.  

- Import, visualize, and browse signals to gain insights  

- Make measurements on signals  

- Compare multiple signals in the time and frequency domains  

- Perform interactive spectral analysis  

- Extract regions of interest  

- Generate MATLAB scripts for automation

 

Preprocessing Signals to Improve Data Set Quality and Generate Features

Objective: Learn techniques to clean signal sets with operations such as resampling, removing outliers, and filling gaps. Interactively generate and rank features.  

- Use resampling to handle nonuniformly sampled signals  

- Fill gaps in uniformly sampled signals  

- Perform resampling to ensure common time base across signals  

- Use the Signal Analyzer app to design and apply filter  

- Use File Ensemble Datastore to import data  

- Use the Diagnostic Feature Designer app to automatically generate and rank features  

- Perform machinery diagnosis using envelope spectrum  

- Locate outliers and replace with acceptable samples  

- Detect changepoints and perform automatic signal segmentation 

 

Estimating Time to Failure

Objective: Explore data to identify features and train decision models to predict remaining useful life.  

- Select condition indicators  

- Use lifespan data to estimate remaining useful life using survival models  

- Use run-to-threshold data to estimate remaining useful life using degradation models  

- Use run-to-failure data to estimate remaining useful life using similarity models