Signal Validation Service¶
The Signal Validation Service validates sensor time series data of an entity. The API offers a set of common operations for signal validation.
The service enables a user to analyze data based on custom settings, like thresholds or data window sizes. The service response can be used for special post-processing or alerting tasks.
For accessing this service you need to have the respective roles listed in Analytics Services roles and scopes.
Time series data are used as input for signal validation. Depending on the property set, a time series consists of a timestamp and one or more related properties and values. If a time series has multiple properties, you have to define the property to be analyzed by the Signal Validation Service.
The Signal Validation Service can perform different checks on the data. Each check requires its own set of parameters. For example, the range check has parameters for an upper and lower limit for detecting range violations. For more information on the individual checks and alerts, refer to the Basics section
The validation output varies with the input, but is at least an event consisting of a description and a timestamp.
Signal Validation Service can be used in two modes:
This mode is intended to be used for small data sets. All the required configuration and data is provided in the request. The API calls are carried out synchronously and results will be available immediately in the response.
Direct Interactive Mode¶
This mode is intended to be used when the user does not want to pass IoT Time Series data in the request body. In direct interactive mode, the Signal Validation Service can communicate with IoT Time Series to fetch the IoT Time Series data. The user should provide the asset details and time range to the Signal Validation Service API's instead of passing the IoT Time Series data in the request body. The API calls are carried out synchronously and results are available immediately in the response.
The Signal Validation Service exposes its API for realizing the following tasks:
- Detect range violations
- Detect spikes
- Detect noise
- Detect jumps
- Detect/interpolate gaps
- Detect bias
- In Interactive mode, the service can process a maximum of 20000 time series records.
- In Direct Interactive mode, the service can process a maximum of 20000 time series records containing a maximum of 3 variables obtained from IoT Time Series service.
The manager of a brewery wants to detect some abnormal characteristics of the production line.
The manager collects time series data of a relevant sensor of the production line using the IoT Time Series Service. The manager feeds the Signal Validation Service API with this time series and evaluates the response.
Any questions left?
Except where otherwise noted, content on this site is licensed under the MindSphere Development License Agreement.