Native anomaly detection features - Amazon IoT SiteWise
Services or capabilities described in Amazon Web Services documentation might vary by Region. To see the differences applicable to the China Regions, see Getting Started with Amazon Web Services in China (PDF).

Native anomaly detection features

The Amazon IoT SiteWise platform offers a range of powerful features that can transform your industrial operations:

  • Predictive maintenance: Detect failures early, and integrates with work order systems to act on insights.

  • Tight integration with Amazon IoT SiteWise: Leverage the tight integration into your existing infrastructure, eliminating the need to move your data to an external service.

  • Automatic model selection and training: Benefit from this support from Amazon IoT SiteWise, without requiring any machine learning expertise.

  • Customize your inference scheduling: Schedule inference jobs to align with your operational needs and shift timings.

  • Labeled data: Improve accuracy with known failure intervals during model training.

  • Model evaluation with pointwise diagnostics: Evaluate model performance at the event level.

  • Scalable across assets: Create computation models for individual assets or across multiple assets to achieve scalability.

  • Sensor-level insights: Gain detailed diagnostics that identify the specific sensor(s) contributing to an anomaly.

  • Faster time to value: Move from sensor modeling to anomaly detection in a matter of hours, not weeks.