Abstract
Recently, digital twins (DTs) have become a research hotspot in smart manufacturing, and using DTs to assist defect recognition has also become a development trend. Real-time data collection is one of the advantages of DTs, and it can help the realization of real-time defect recognition. However, DT-driven defect recognition cannot be realized unless some bottlenecks of the recognition models, such as the time efficiency, have been solved. To improve the time efficiency, novel defect class recognition is an essential problem. Most of the existing methods can only recognize the known defect classes, which are available during training. For new incoming classes, known as novel classes, these models must be rebuilt, which is time-consuming and costly. This greatly impedes the realization of DT-driven defect recognition. To overcome this problem, this paper proposes a deep lifelong learning method for novel class recognition. The proposed method uses a two-level deep learning architecture to detect and recognize novel classes, and uses a lifelong learning strategy, weight imprinting, to upgrade the model. With these improvements, the proposed method can handle novel classes timely. The experimental results indicate that the proposed method achieves good results for the novel classes, and it has almost no delay for production. Compared with the rebuilt methods, the time cost is reduced by at least 200 times. This result suggests that the proposed method has good potential in the realization of DT-driven defect recognition.
Digital Twins Collaboration for Automatic Erratic Operational Data Detection in Industry 4.0
