Thingswise, Dell EMC, Xilinx, China Unicom, and CAICT
Manufacturing: Industrial Automation (Automotive components)
The application of Artificial Intelligence (AI) in manufacturing is a fledgling field of development. Two primary areas which need to be explored are how AI algorithms can be applied to solve real-world problems on the manufacturing floor and how they should be deployed optimally from edge to cloud. It also needs demonstrable successes for its broad adaption. Additionally, the challenge exists to bring the requisite IT/AI and OT expertise together, to converge production domain knowledge with AI models and apps, to enable this development.
The testbed is designed to establish an end-to-end Industrial Internet platform that consists of an edge computing platform and a cloud computing platform.In the edge platform, AI models and edge applications are run for the local optimization of manufacturing processes. In the cloud platform, they are run to enable global and long-term optimization, e.g. across production lines and plants. The edge platform also supports connectivity to and data collection from the equipment while the cloud enables historical data accumulation and storage and supports AI model building.
The cloud computing platform also provides the capability for enabling industrial app DevOps processes supporting collaboration between AI/IT developers and plant engineers in creating, testing and running data/AI model-driven industrial applications.
How It Works:
The testbed seeks to validate the platform and explore technical approaches to solve the following specific manufacturing problems:
- To apply deep learning to improve quality assurance of an automobile part to substantially increase defect detection accuracy and reduce dependence on manual inspection.
- To apply online analytics to production process data to assess product quality to reduce the dependence on destructive inspection and seek opportunities to adjust the process parameters dynamically to ensure the battery quality.
- To apply analytics to work cells and overall production throughput, and identify performance bottlenecks in a large automobile part production line involving thirty stations and make recommendations to increase the production rate.
- To enable predictive maintenance for large production machines by applying machine learning analytics to determine optimal timing of replacing worn components in the machines to prevent quality degradation in products.
This testbed seeks to address the traditional manufacturing objectives: to lower production cost, improve product quality and increase manufacturing efficiency by applying the Industrial Internet technology and promote the application of AI in the manufacturing environment.
It also seeks to ease the development of customized industrial apps by creating a framework to bring AI modeling, app development and production domain expertise together to foster an ecosystem so that they can collaborate effectively.
This testbed is to test machine learning algorithms, technologies, and technical frameworks to apply Artificial Intelligence optimally distributed from edge to cloud to solve specific production quality, cost & efficiency problems in an automotive manufacturing environment.
It will also explore a framework and ways to bring AI modeling, app development and production domain expertise together as an ecosystem to foster the industrial app market for exchange of domain knowledge and the capabilities needed for the development of smart manufacturing applications.
Interested in learning more about the Optimizing Manufacturing Processes with Artificial Intelligence Testbed?