Applications of AI for Predictive Maintenance

Applications of AI for Predictive MaintenanceAAPMNVNvidiaNV-AAPM1.0<ul> <li>Use AI-based predictive maintenance to prevent failures and unplanned downtimes</li><li>Identify key challenges around detecting anomalies that can lead to costly breakdowns</li><li>Use time-series data to predict outcomes with XGBoost-based machine learning classification models</li><li>Use an LSTM-based model to predict equipment failure</li><li>Use anomaly detection with time-series autoencoders to predict failures when limited failure-example data is available</li></ul><ul> <li>Experience with Python</li><li>Basic understanding of data processing and deep learning</li></ul>Suggested materials to satisfy prerequisites: Python Tutorial, Getting Started with Deep LearningIntroduction <ul> <li>Meet the instructor.</li><li>Create an account at courses.nvidia.com/join</li></ul>Training XGBoost Models with RAPIDS for Time Series <ul> <li>Learn how to predict part failures using XGBoost classification on GPUs with cuDF:<ul> <li>Prepare real data for efficient GPU ingestion with RAPIDS cuDF.</li><li>Train a classification model using GPU-accelerated XGBoost and CPU-only XGBoost.</li><li>Compare and discuss performance and accuracy results for XGBoost using CPUs, GPUs, and GPUs with cuDF.</li></ul></li></ul>Training LSTM Models Using Keras and TensorFlow for Time Series <ul> <li>Learn how to predict part failures using a deep learning LSTM model with time-series data:<ul> <li>Prepare sequenced data for time-series model training.</li><li>Build and train a deep learning model with LSTM layers using Keras.</li><li>Evaluate the accuracy of the model.</li></ul></li></ul>Training Autoencoders for Anomaly Detection <ul> <li>Learn how to predict part failures using anomaly detection with autoencoders:<ul> <li>Build and train an LSTM autoencoder.</li><li>Develop and train a 1D convolutional autoencoder.</li><li>Experiment with hyperparameters and compare the results of the models.</li></ul></li></ul>Assessment and Q&A- 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- Experience with Python - Basic understanding of data processing and deep learning Suggested materials to satisfy prerequisites: Python Tutorial, Getting Started with Deep LearningIntroduction - Meet the instructor. - Create an account at courses.nvidia.com/join Training XGBoost Models with RAPIDS for Time Series - Learn how to predict part failures using XGBoost classification on GPUs with cuDF: - 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 GPUs with cuDF. Training LSTM Models Using Keras and TensorFlow for Time Series - Learn how to predict part failures using a deep learning LSTM model with time-series data: - 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. Training Autoencoders for Anomaly Detection - Learn how to predict part failures using anomaly detection with autoencoders: - Build and train an LSTM autoencoder. - Develop and train a 1D convolutional autoencoder. - Experiment with hyperparameters and compare the results of the models. Assessment and Q&A1 jour500.00500.00500.00500.00500.00420.00500.00690.00