Multicast Sensor Stream Processing for Scalable Industrial Controllers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial control systems are not designed for high-performance computing of high-volume rich context data, leading to a technology gap in processing high-speed, high-bandwidth streaming data required for advanced AI applications like object detection and robotic operations.
Innovation Solution
A system utilizing packetization and sequential tagging of streaming sensor data, combined with a multicast protocol for communication and a modular design to distribute processing tasks across multiple processing units, enabling scalable processing throughput without network bandwidth constraints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If industrial controllers use traditional design for high reliability and determinism, then reliability is improved, but processing performance for high-volume data deteriorates
Solution Approach 1:
The system segments the data processing function from the control function by introducing separate processing units that receive data via multicast. The controller retains its reliability-focused design while processing units handle high-volume data processing in parallel, resolving the contradiction between reliability and processing throughput.
2Device complexity
If a single processing unit handles all data processing, then device complexity is reduced, but processing throughput deteriorates
Solution Approach 1:
The processing function is segmented into multiple independent processing units that can operate in parallel. Each unit handles a portion of the data stream, increasing overall throughput while maintaining relatively simple individual unit designs. The multicast mechanism coordinates these units without requiring complex inter-unit communication.
Solution Approach 2:
Multiple processing units are merged into a coordinated system through the multicast data distribution mechanism. The controller acts as a central coordinator that distributes data to multiple processing units, combining their processing power while maintaining system-level coordination through the standardized multicast protocol.
3Speed
If high-volume data is processed in real-time, then processing speed is improved, but network bandwidth requirements increase
Solution Approach 1:
Multiple processing units share a single multicast data stream through the network. Instead of each unit requiring a separate data connection, the multicast mechanism allows one data stream to be efficiently distributed to multiple endpoints, reducing overall network bandwidth consumption while enabling parallel processing at high speed.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A system for processing data in an industrial environment includes a sensor that communicates sensor data acquired from a factory floor as a multicast data stream where each frame is tagged with a sequence identifier indicative of a position of that frame in the data stream. A network switch distributes the data stream to a group of multicast endpoints. The system includes a controller with a plurality of modularly connected processing units. Each processing unit is further connected to the network switch and configured as a respective endpoint of the group of multicast endpoints. Each processing unit selectively processes frames of the data stream in dependence of the sequence identifier of individual frames by executing a data processing module, to produce an output result associated with each processed frame. The controller assembles the output result and the sequence identifier of each processed frame from the plurality of processing units.