Applications of AI for Predictive Maintenance

8 hours of instruction

Discover 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.

OBJECTIVES

1. Use AI-based predictive maintenance to prevent failures and unplanned downtimes
2. Identify key challenges around detecting anomalies that can lead to costly breakdowns
3. Use time-series data to predict outcomes with XGBoost-based machine learning classification models
4. Use an LSTM-based model to predict equipment failure
5. Use anomaly detection with time-series autoencoders to predict failures when limited failure-example data is available

PREREQUISITES

None

SYLLABUS & TOPICS COVERED

1. Introduction
   • Meet the instructor
   • Create an account
2. Training XG Boost Models With RAPIDS
   • Prepare real data for efficient GPU ingestion with RAPIDS cuDF.
   • Train a classification model using GPU-accelerated XGBoost and CPU-only XGBoost.
   • Compare and discuss performance and accuracy results for XGBoost using CPUs, GPUs, and
3. GPUs with cuDF.
   • Training LSTM Models Using Keras And Tensor Flow
   • Prepare sequenced data for time-series model training.
   • Build and train a deep learning model with LSTM layers using Keras.
   • Evaluate the accuracy of the model
4. Training Autoencoders For Anomaly Detection
   • Build and train an LSTM autoencoder.
   • Develop and train a 1D convolutional autoencoder.
   • Experiment with hyperparameters and compare the results of the models.

SOFTWARE REQUIREMENTS

Each participant will be provided with dedicated access to a fully configured, GPU-accelerated workstation in the cloud.