PRESS RELEASE: In September 2022, China Mobile and ZTE jointly completed the world’s first pilot project of the Cloud SPN computing network convergence solution in Changzhou, Jiangsu. This innovative solution is mainly applicable to the scenario where traditional quality inspection is upgraded to AI-enabled one in industrial manufacturing. It enables cloud collaboration and the new artificial intelligence intelligent inspection algorithm model to help customers with automatic quality inspection of production line spray codes. It adds AI boards to the SPN product platform in the existing commercial network, uploads AI algorithm models to upgrade current product capabilities, and provides high-end ubiquitous computing services.
Before this, there were a variety of “pain points” for quality inspection in some industrial parks: lack of intelligent measures, reliance on manual inspection and massive consumption of human resources; expensive dedicated devices deployed for automatic inspection, many variations of inspection samples, and inflexible custom algorithms for dedicated devices, which make it difficult to update the inspection system; low accuracy for partial automatic local inspection, real-time adjustment of system parameters and high service costs. China Mobile and ZTE’s Cloud SPN Computing and Network Convergence Solution makes heavy use of existing SPN capabilities to provide local lightweight computing resources for the fleet and consolidate edge computing, cloud computing and network capabilities into the collaboration solution of edge cloud. Applied to an industrial park where SPN devices with AI boards are added to rapidly deploy local applications, it extends the public cloud to the limit by virtue of the low latency of the transport network to collect data in parks and process real-time services locally. The analysis of the initial demand and the results of the preliminary tests are used to verify the methods of solving the three big problems:
- Low-latency metro transport networks that support fine-grained cutoff private lines ensure secure data isolation in ToB application access to the cloud, extend the public cloud to the park, and move public cloud intelligence to the park .
- The production line in the park is implemented with transport access devices that integrate artificial vision chips and applications. From training samples, they can quickly use AI models for real-time local inspection and keep user data in the factory and maintain confidentiality.
- Broad coverage transport access devices can integrate computing power for ubiquitous deployment. Cloud collaboration architecture contributes to lightweight edge computing and the intrinsic computing power of network devices significantly reduces the costs of deployment and operation and maintenance of high-end IT services.
For example, in a technology quality inspection scenario. a specific controller and an industrial camera work with the PLC (Programmable Logic Controller) for original quality inspection on site. Several problems arise in the process: there is no service data association between quality inspection workstations on the production line, and a set of specific controllers and industrial cameras need to be deployed separately at each workstation. The driver is complex in the process of quality inspection or standard changes, which makes it difficult to update. The responsiveness of the controller agent service cannot keep up with the requirement and the service localization is weak. After launching the SPN cloud computing network convergence solution for a pilot test, the ZTE HEC (Hyper-Edge Computing) device (SPN 6180H access device integrating artificial intelligence boards) is deployed on the production line to inspect the quality of the spray codes in the eighth job and do the joint debug test to address the customer’s requirements for the spray codes. This is the first time that local smart computing services for industry customers have been offered on SPN devices. In the second phase, in-depth cooperation will continue. One HEC device can gradually take over the inspection tasks of seven other workstations on the production line. The advantages of the global solution stand out:
- Data between processes can be analyzed and managed centrally, and new services such as full process failure prediction of the production line can be offered in the future.
- Even if a process or standard is changed at a workstation, the software and algorithm model can be trained to quickly put the new inspection procedure into use, making it easy to upgrade.
- In addition to the advantages of ZTE in location services, a model can be trained on the mobile cloud later through the coordination of the edge cloud, and an inference can be made on the local SPN device. The model can be delivered to the HEC device at the factory via the SPN MAN channel for uploading and updating online.
- The Cloud SPN compute and network convergence solution reduces the cost more than the previous industrial park controller solution.
The solution upgrades traditional quality inspection to a high-precision, AI-enabled one. Leveraging a wide range of SPN devices invested in China Mobile’s existing networks, it generates a new edge-cloud collaboration model for innovative applications, validates the feasibility of ubiquitous hyper-edge computing applications, and lays a foundation for the operator to drive ToB Services as a result of the duplicability of scenarios.
Subscribe to our daily Volver newsletter