A Scalable Cloud–Edge Collaborative Approach for Intelligent Low-Code Fault Diagnosis: Successful Applications of Agile Migration Deployment in Heterogeneous Fault Diagnosis Scenarios
Fang Luo, Jiafu Wan, Hu Cai, Shiyong Wang, Zhibo Pang, Mejdl Safran, Salman A. AlQahtani
Abstract
In contemporary production systems, the escalating complexity and magnitude of equipment pose challenges to operational control processes, making them prone to failures. This vulnerability stems from dynamic randomness, multisource uncertainty, high coupling, and robust interferences, thereby rendering the execution of multisource domain fault knowledge fusion and the deployment of agile fault diagnosis across various scenarios exceptionally challenging. Hence, a low-code intelligent fault diagnosis platform tailored for intricate fault diagnosis contexts is introduced, integrating a cloud-based elastic infrastructure with low-code scalable capabilities and a self-developed edge-adaptive system. In addition to a comprehensive discussion of key generic technologies, the proposed diagnostic platform showcases fault diagnosis applications on a Süddeutsche Elektromotorenwerke (SEW) reduction platform and a wind turbine generator. These exemplifications effectively deliver full-lifecycle agile fault diagnosis management capabilities, enhancing diagnostic accuracy and efficiency for this context.