Skip to content

Latest commit

 

History

History
86 lines (45 loc) · 2.71 KB

big-data.md

File metadata and controls

86 lines (45 loc) · 2.71 KB

Title: Big Data for Manufacturing

Submitter(s):

Michael Lagally

Reviewer(s):

Tracker Issue ID:

Category:

Class:

Status:

Target Users

Device owners, cloud provider.

Motivation:

Production lines for industrial manufacturing consist of multiple machines, where each machine incorporates sensors for various values. A failure of a single machine can cause defective products or a stop of the entire production.

Big data analysis enables to identify behavioral patterns across multiple production lines of the entire production plant and across multiple plants.

The results of this analysis can be used for optimizing consumption of raw materials, checking the status of production lines and plants and predicting and preventing fault conditions.

Expected Devices:

Various sensors, e.g. temperature, light, humidity, vibration, noise, air quality.

Expected Data:

Discrete sensor values, such as temperature, light, humidity, vibration, noise, air quality readings. The data can be delivered periodically or on demand.

Dependencies:

Thing Description: groups of devices, aggregation / composition mechanism, thing templates Discovery/Onboarding: Onboarding of groups of devices

Description:

A company owns multiple factories which contain multiple production lines. Examples are production lines, environment sensors, These devices collect data from multiple sensors and transmit this information to the cloud. Sensor data is stored in the cloud, can be visualized and analyzed using machine learning / AI.

The cloud service allows to manage single and groups of devices. Combining the data streams from multiple devices allows to get an easy overview of the state of all connected devices in the user's realm.

In many cases there are groups of devices of the same kind, so the aggregation of data across devices can serve to identify anomalies or to predict impending outages.

The cloud service allows to manage single and groups of devices and can help to identify abonormal conditions. For this purpose a set of rules can be defined by the user, which raises alerts towards the user or triggers actions on devices based on these rules.

This enables the early detection of pending problems and reduces the risk of machine outages, quality problems or threats to the environment or life of humans.

Variants:

<Describe possible use case variants, if applicable>

Gaps:

Existing standards:

Comments:

See also Digital Twin use case.