The intelligent monitoring of cutting tools used in the manufacturing industry is steadily becoming more convenient. To accurately predict the state of tools and tool breakages, this study proposes a tool wear prediction technique based on multi-sensor information fusion. First, the vibrational, current, and cutting force signals transmitted during the machining process were collected, and the features were extracted. Next, the Kalman filtering algorithm was used for feature fusion, and a predictive model for tool wear was constructed by combining the ResNet and long short-term memory (LSTM) models (called ResNet-LSTM). Experimental data for thin-walled parts obtained under various machining conditions were utilized to monitor the changes in tool conditions. A comparison between the ResNet and LSTM tool wear prediction models indicated that the proposed ResNet-LSTM model significantly improved the prediction accuracy compared to the individual LSTM and ResNet models. Moreover, ResNet-LSTM exhibited adaptive noise reduction capabilities at the front end of the network for signal feature extraction, thereby enhancing the signal feature extraction capability. The ResNet-LSTM model yielded an average prediction error of 0.0085 mm and a tool wear prediction accuracy of 98.25%. These results validate the feasibility of the tool wear prediction method proposed in this study.

Purpose: Traditional gas tungsten arc welding (GTAW) and GTAW-based wire and arc additive manufacturing (WAAM) are notably different. These differences are crucial to the process stability and surface quality in GTAW WAAM. This paper addresses special characteristics and the process control method of GTAW WAAM. The purpose of this paper is to improve the process stability with sensor information fusion in omnidirectional GTAW WAAM process. Design/methodology/approach: A wire feed strategy is proposed to achieve an omnidirectional GTAW WAAM process. Thus, a model of welding voltage with welding current and arc length is established. An automatic control system fit to the entire GTAW WAAM process is established using both welding voltage and welding current. The effect of several types of commonly used controllers is examined. To assess the validity of this system, an arc length step experiment, various wire feed speed experiments and a square sample experiment were performed. Findings: The research findings show that the resented wire feed strategy and arc length control system can effectively guarantee the stability of the GTAW WAAM process. Originality/value: This paper tries to make a foundation work to achieve omnidirectional welding and process stability of GTAW WAAM through wire feed geometry analysis and sensor information fusion control model. The proposed wire feed strategy is implementable and practical, and a novel sensor fusion control method has been developed in the study for varying current GTAW WAAM process.

In the field of electronics manufacturing, electronic component classification facilitates the management and recycling of the functional and valuable electronic components in electronic waste. Current electronic component classification methods are mainly based on deep learning, which requires a large number of samples to train the model. Owing to the wide variety of electronic components, collecting datasets is a time-consuming and laborious process. This study proposed a Siamese network-based classification method to solve the electronic component classification problem for a few samples. First, an improved visual geometry group 16 (VGG-16) model was proposed as the feature extraction part of the Siamese neural network to improve the recognition performance of the model under small samples. Then, a novel channel correlation loss function that allows the model to learn the correlation between different channels in the feature map was designed to further improve the generalization performance of the model. Finally, the nearest neighbor algorithm was used to complete the classification work. The experimental results show that the proposed method can achieve high classification accuracy under small sample conditions and is robust for electronic components with similar appearances. This improves the classification quality of electronic components and reduces the training sample collection cost.