The vibration signal of mechanical equipment in operating environments is the key to describing fault characteristics, but due to thez influence of equipment density and environmental interference, the accuracy of fault diagnosis is often affected by noise. In this paper, a fault diagnosis method based on a 1D Multi-Channel Improved Convolutional Neural Network (1DMCICNN) is proposed. By introducing BiLSTM, an attention mechanism and a local sparse structure of a two-channel Convolutional Neural Network, the feature information of the noisy timing signal is fully extracted at different scales while reducing the computational parameters. The model is verified through experiments under different signal-to-noise ratios and loads. The results show that the accuracy of 1DMCICNN is 98.67%, 99.71%, 99.04%, and 99.71% on different load and speed datasets. Meanwhile, compared with the unoptimized two-channel Convolutional Neural Network, the training parameters are reduced by 55.58%.

With the rise of digital twin technology, the application of digital twin technology to industrial automation provides a new direction for the digital transformation of the global smart manufacturing industry. In order to further improve production efficiency, as well as realize enterprise digital empowerment, this paper takes a welding robot arm as the research object and constructs a welding robot arm digital twin system. Using three-dimensional modeling technology and model rendering, the welding robot arm digital twin simulation environment was built. Parent–child hierarchy and particle effects were used to truly restore the movement characteristics of the robot arm and the welding effect, with the help of TCP communication and Bluetooth communication to realize data transmission between the virtual segment and the physical end. A variety of UI components were used to design the human–machine interaction interface of the digital twin system, ultimately realizing the data-driven digital twin system. Finally, according to the digital twin maturity model constructed by Prof. Tao Fei’s team, the system was scored using five dimensions and 19 evaluation factors. After testing the system, we found that the combination of digital twin technology and automation is feasible and achieves the expected results.

This study focuses on optimizing the flow field uniformity within a vertical honeycomb wet electrostatic precipitator (WESP), which is a critical prerequisite for achieving high particulate removal efficiency. For a vertical honeycomb WESP with an air capacity of 25,000 m³/h, the internal flow field is optimized by adjusting the opening ratio and aperture ratio of the airflow equalizing plate, installing additional deflector plates, and adding additional airflow equalizing plates at strategic locations. The optimization reduces the velocity relative standard deviation at the anode inlet section to 0.14. Through 1:1-scale equipment construction and testing, the particle concentration at the outlet is stabilized below 10 mg/Nm³, with an average removal efficiency of 95.88%—a 5.7% improvement over the original model. This study solves the design dependency on empirical guidance for vertical honeycomb WESP in the food industry, providing a green technology paradigm for low-carbon industrial emissions.

This study focuses on the application of vertical honeycomb wet electrostatic precipitator (WESP) in food processing and animal feed production industries, addressing sustainable development challenges in industrial air pollution control. For a vertical honeycomb wet electrostatic precipitator with an air capacity of 25000 m³/h, the internal flow field is optimized by adjusting the aperture rate and aperture ratio of the airflow equalizing plate, installing additional deflector plates, and adding additional airflow equalizing plates from multiple perspectives. The optimization reduces the velocity relative standard deviation at the anode inlet section to 0.14. Through 1:1 scale equipment construction and testing, the particle concentration at the outlet is stabilized below 10 mg/Nm³, with an average removal efficiency of 95.88%—a 5.7% improvement over the original model. The optimized WESP demonstrates reduced energy consumption by 15%, water recycling efficiency ≥95%, and material recyclability of 90%, aligning with global sustainable development goals (SDGs). This study solves the design dependency on empirical guidance for vertical honeycomb WESP in the food industry, providing a green technology paradigm for low-carbon industrial emissions.