Course Overview
In this workshop, you’ll learn how to identify anomalies and failures in time series data, estimate the remaining useful life of the corresponding parts, and use this information to map anomalies to failure conditions. You’ll be able to leverage predictive maintenance to manage failures and avoid costly unplanned downtimes. To begin, you’ll learn the key challenges around identifying anomalies that can lead to costly breakdowns. We’ll discuss how you can leverage your company’s time-series data to predict outcomes using machine learning classification models with XGBoost. Then, you’ll learn how to apply predictive maintenance procedures by using an LSTM-based model to predict the failure of a device and avoid downtime. Finally, you will experiment with autoencoders to detect anomalies by using the time series sequences from the previous steps. At the conclusion of the workshop, you’ll learn how to:
- Predict part failures using machine learning classification models with XGBoost
- Train GPU LSTM-based models using Keras and TensorFlow for failure prediction in time series
- Detect anomalies using an autoencoder and Seq2Seq models
- Experiment with generative adversarial network (GAN) models to detect anomalies
Please note that once a booking has been confirmed, it is non-refundable. This means that after you have confirmed your seat for an event, it cannot be cancelled and no refund will be issued, regardless of attendance.
Prerequisites
- Experience with Python
- Basic understanding of data processing and deep learning
Suggested materials to satisfy prerequisites: Python Tutorial, Getting Started with Deep Learning
Course Objectives
- Use AI-based predictive maintenance to prevent failures and unplanned downtimes
- Identify key challenges around detecting anomalies that can lead to costly breakdowns
- Use time-series data to predict outcomes with XGBoost-based machine learning classification models
- Use an LSTM-based model to predict equipment failure
- Use anomaly detection with time-series autoencoders to predict failures when limited failure-example data is available