The dynamic fault environment, incremental data accumulation, and specific needs in train transmission systems make continual learning essential for fault diagnosis. Recent advancements in continual learning have improved diagnostic adaptability, but current methods face challenges: 1) Complex architectures to prevent catastrophic forgetting increase training difficulty and computational costs, hindering deployment. 2) Lack of new class samples leads to delayed model evolution due to long sample accumulation periods. This article introduces a lightweight continual learning method based on model expansion. A hash space metric mechanism using lightweight convolution is developed to reduce computational costs while maintaining accuracy. Additionally, a joint strategy of knowledge enhancement and compression improves model evolution by refining knowledge subsets. Compared with the state-of-the-art method, the proposed method reduces parameters by 2.59 times, FLOPs by 2.67 times, and inference time by 2.89 times, and leads by 2.5% and 0.23% in incremental accuracy and incremental forgetting rate, respectively.

Real-time transmission of high-frequency signals in online fault diagnosis challenges the limited bandwidth. However, reducing the volume of data transmission will compromise the data quality and drop the accuracy of fault diagnosis. This article synergizes data transmission and fault diagnosis to simultaneously achieve high transmission reduction ratio and fault diagnostic accuracy. First, a novel long sequence dual prediction scheme (L-DPS) is proposed to reduce the high-frequency data transmission online while ensuring the data precision. Second, a resource-efficient transformer model is proposed to improve the precision and speed of long sequence prediction in L-DPS, thus effectively improving its transmission reduction ratio and applicable frequency. Finally, a precision-adaptive fault diagnosis model is proposed to tackle precision differences in the transmission-restored data, thus effectively improving the accuracy of fault diagnosis. Experiments based on the real-world dataset confirm that the solution can cope with high-frequency data up to 20.69 KHz and achieve 94.16% transmission reduction and 99.43% fault diagnosis accuracy.

High-frequency time-series data such as vibration signals will consume a lot of communication resources and require very high network bandwidth. Reducing the amount of data transmission while ensuring its availability is particularly important and challenging in high-frequency scenarios. Dual prediction scheme (DPS) can significantly reduce the amount of data transmission while ensuring data accuracy. However, traditional DPS cannot be applied to high-frequency scenarios due to the limitation of the mechanism design and model inference speed. We propose a novel long sequence DPS to efficiently reduce the volume of high-frequency data transmission in real time. To overcome the accuracy degradation due to gradient vanishing in long sequence prediction, we also propose an attention-based prediction model. Furthermore, we propose Informer to reduce the model’s computational complexity and enable fast inference and deployment on resource-constrained edge gateways. Experiments based on the real-world dataset show that the proposed scheme can efficiently cope with high-frequency data, reduce its transmission volume, and ensure data accuracy.

Many computation-intensive industrial applications need to be run in the cloud, which relies on a lot of sharply varying data transmitted from the industrial field. To save the communication bandwidth and ensure data with required accuracy obtained by the cloud, we design a data transmission architecture based on dual prediction scheme and cloud-edge collaboration and a dual-mode algorithm based on deep learning. With the proposed architecture, a deep learning model is deployed and synchronized on the edge and cloud sides. Further, the proposed algorithm can help the cloud for computation with locally predicted data or real-time data from the edge, depending on whether the predicted data are adequately accurate. A physical validation platform including a sensor, an edge gateway, and a cloud server is built, and drastically changing real vibration data are collected to validate the proposed scheme. The results show that the proposed scheme can reduce 88.66% of data transmission while guaranteeing deviations less than 0.1.

With the rapid development of smart manufacturing, edge computing-oriented microservice platforms are emerging as an important part of production control. In the containerized deployment of microservices, layer sharing can reduce the huge bandwidth consumption caused by image pulling, and chain sharing can reduce communication overhead caused by communication between microservices. The two sharing methods use the characteristics of each microservice to share resources during deployment. However, due to the limited resources of edge servers, it is difficult to meet the optimization goals of the two methods at the same time. Therefore, it is of critical importance to realize the improvement of service response efficiency by balancing the two sharing methods. This paper studies the optimal microservice deployment strategy that can balance layer sharing and chain sharing of microservices. We build a problem that minimizes microservice image pull delay and communication overhead and transform the problem into a linearly constrained integer quadratic programming problem through model reconstruction. A deployment strategy is obtained through the successive convex approximation (SCA) method. Experimental results show that the proposed deployment strategy can balance the two resource sharing methods. When the two sharing methods are equally considered, the average image pull delay can be reduced to 65% of the baseline, and the average communication overhead can be reduced to 30% of the baseline.