4. Use Case Enablement

This article contains the following sections:


Before providing an in-depth discussion of the use cases that the Sight Machine platform can enable, it is important to illustrate the types of data required to enable each use case, and the requirements of each type of data. This section provides a framework for assessing the data inventory taken to a number of use cases.

Data Fitness Framework

The following chart shows a mapping between use cases and data types, outlining data fitness at a high level.

Use Cases Glossary

The following describes the various use cases:

  • Visibility > KPI Watermarking: Track and compare key performance indicator (KPIs) across facilities, lines, assets, and over time.
  • Visibility > Contextualized Data Visualization/Analysis: Visualize cleansed and contextualized data across data sources in a single data model.
  • Traceability: Attribute data across facilities and processes to a single part/lot.
  • Availability Improvement Analysis: Increase availability by analyzing unplanned downtime events.
  • Quality Improvement > RCA: Determine the root cause of a reduction in quality.
  • Quality Improvement > False Positive/False Negative Reduction Analysis: Ensure that poor-quality parts/lots do not reach customers, and reduce the time spent reviewing good-quality parts/lots flagged as defective.
  • Performance Improvement Analysis > Asset In-Cycle Process Time: Increase asset performance.
  • Performance Improvement Analysis > Line Bottleneck Analysis: Identify and resolve bottlenecks within a line.

Data Types Glossary

The following describes the various data types:

  • Process Data > Productive: Data associated with the production process while material is moving in-process.
  • Process Data > Non-Productive: Data associated with the production process during non-productive machine use (either planned or unplanned).
  • Quality Data: In-line or lab-quality data.
  • Part/Lot Data: Data used to track the material flow through one or more asset.