With the rapid development of the Industrial Internet of Things (IIoT), the scale of industrial equipment has expanded, leading to an increasing diversity of communication protocols and a significant rise in data transmission volume within industrial networks. Traditional communication systems, constrained by concurrency and throughput limitations, struggle to meet the demands of massive data transmission. To address this issue, this paper proposes a distributed high-availability message communication model for IIoT (DUA-MQTT) based on the OPC UA architecture. It integrates the distributed MQTT protocol to enhance concurrency and throughput performance. Additionally, to improve the information processing capability of the proposed model, this paper designs an information-modeling model based on industrial unstructured text data (MAC-GC), which generates structured data nodes that comply with the OPC UA information model specification through hierarchical annotation, accurately mapping device functions and attributes. Experimental results show that, compared with traditional communication models, the DUA-MQTT model reduces end-to-end latency by 28.6% and increases throughput by 22.2%, effectively enhancing the concurrency of data transmission. In terms of information-modeling capabilities, MAC-GC outperforms other models in accuracy (0.9701), recall (0.9601), and F1 score (0.9651), effectively improving the utilization efficiency and modeling accuracy of unstructured data.

Accurate identification of tool wear conditions is of great significance for extending tool life, ensuring processing quality, and improving production efficiency. Current research shows that signals collected by a single sensor have limited dimensions and cannot comprehensively capture the degradation process of tool wear, while multi-sensor fusion recognition methods cannot effectively handle the complementarity and redundancy between heterogeneous sensor data in feature extraction and fusion. To address these issues, this paper proposes Hi-MDTCN (Hierarchical Multi-scale Dilated Temporal Convolutional Network). In the network, we propose a hierarchical signal analysis framework that processes the signal in segments. When processing intra-segment signals, we design a Multi-channel one-dimensional convolutional network with attention mechanism to capture local wear features at different time scales and fuse them into a unified representation. When processing signal segments, we design a Bi-TCN module to further capture long-term dependencies in wear evolution, mining the overall trend of tool wear over time. Hi-MDTCN adopts a dilated convolution mechanism, which can achieve an extremely large receptive field without building an overly deep network structure, effectively solving problems faced by recurrent neural networks in long sequence modeling such as gradient vanishing, low training efficiency, and poor parallel computing capability, achieving efficient parallel capture of long-range dependencies in time series. Finally, the proposed method is applied to the PHM2010 milling data. Experimental results show that the model’s tool condition recognition accuracy is higher than traditional methods, demonstrating its effectiveness for practical applications.