The rapid development of information and communication technologies has facilitated machining condition monitoring toward a data-driven paradigm, of which the Industrial Internet of Things (IIoT) serves as the fundamental basis to acquire data from physical equipment with sensing technologies as well as to learn the relationship between the system condition and the collected condition monitoring data. However, most data-driven methods suffer from using a single-domain space, ignoring the importance of the learned features, and failing to incorporate the handcrafted features assisted by domain knowledge. To solve these limitations, a novel deep learning approach is proposed for machining condition monitoring in the IIoT environment, which consists of three phases, including: 1) the unsupervised parallel feature extraction; 2) adaptive feature importance weighting; and 3) hybrid feature fusion. First, separate sparse autoencoders are utilized to conduct the unsupervised parallel feature extraction, which enables to learn abstract feature representation from multiple domain spaces simultaneously. Then, an attention module is designed for the adaptive feature importance weighting, which can assign higher weights to those critical features accordingly. Moreover, a hybrid feature fusion is deployed to complement the automatic feature learning and further yield better model performance by fusing the handcrafted features assisted by domain knowledge. Finally, a real-life case study and extensive experiments have been conducted to show the effectiveness and superiority of the proposed approach.

Condition monitoring plays a crucial role in securing smooth production, which has been facilitated into a cyber-physical system (CPS) integration paradigm with the new information and communication technologies and data-driven intelligence. However, traditional methods limit its successful deployment from the different distribution of training data and testing data, the missing relationships between the input signals, and the insufficient data size. To overcome these limitations, a novel graph-based adaptation framework with edge-cloud orchestration is proposed. A three-stage edge-cloud orchestration mechanism is encapsulated with CPS architecture. The proposed graph-based approach mainly consists of an adaptive multihop branch ensemble module to intelligently aggregate the node information, a distance metric learner to autonomously align the data distribution, and a classifier module to automatically generate the pseudolabeled data to guide the edge-cloud orchestration and output results. Finally, a real-life case study and extensive experiments are conducted to prove the effectiveness of the proposed approach.