International Journal of Mechatronics and Manufacturing Systems (6 papers in press)

Regular Issues

• Optimal Compensation Approach of Roots Vacuum Pump Rotor considering Pumping Performance and Dimensional Accuracy  
  by Can Yuan, Sitong Xiang, Cheng Wu, Xin Pan, Jianguo Yang 
  Abstract: Roots vacuum pumps are vital in scientific and industrial applications. Traditional performance optimization focuses on rotor profile design but neglects machining errors, limiting real-world effectiveness. This paper proposes a rotor compensation optimization method considering both pumping performance and dimensional accuracy. Firstly, a nonlinear mapping model of rotor radial clearance and pumping performance is established. Then, the radial clearance of the traditional mirror compensation (MC) surface is optimized using a genetic algorithm to obtain the optimized clearance and compensation surface. Experimental results show a 91.83% reduction in average dimensional deviation, a 4.23% increase in flow rate, and a 7.01% decrease in exhaust temperature. Compared to MC, the optimized method improves dimensional error compensation by 30.23%, flow rate by 1.78%, and lowers exhaust temperature by 3.46%. This method significantly enhances rotor accuracy and performance.
  Keywords: Roots vacuum pump; Pumping performance; Dimensional accuracy; Rotor clearance; Optimal compensation.
  DOI: 10.1504/IJMMS.2025.10075043
   
  
• Multi-Objective Optimisation of Selective U-Shaped Disassembly Lines for Sustainable Manufacturing Systems  
  by Jiaqi Hu, YongGao Fu, Chao Wan, ShaLi You, ManQian Xie, Rui Jin 
  Abstract: The research presented in the article directly contributes to the broader domain of manufacturing systems by addressing a critical aspect of sustainable production -end-of-life product disassembly. Specifically, it introduces a selective U-shaped disassembly line balancing model that integrates multiple objectives: operational efficiency, carbon footprint reduction, and worker safety. This model enhances conventional manufacturing system design by incorporating reverse logistics and environmentally conscious practices, thereby aligning with the goals of circular manufacturing. The application of an advanced dual-stage optimisation artificial bee colony
  Keywords: manufacturing systems; disassembly line balancing; multi-objective optimization; artificial bee colony algorithm.
  DOI: 10.1504/IJMMS.2025.10076231
   
  
• Punch Wear Estimation through Burr Height Analysis with Mel-Frequency Cepstral Coefficients and Artificial Neural Network  
  by Tushar Badgujar, V.A. Kolhe, Swapnil D. Galande, Prashant S. Tile 
  Abstract: This study introduces a real-time punch wear monitoring system tailored for the sheet metal trimming process using acoustic emission and a data-driven interface. The approach uses burr height as a key indicator of tool degradation and categorizes punch wear into three distinct states: freshly ground, partially worn, and fully worn. The process acoustic signals are denoised and converted into Mel-Frequency Cepstral Coefficients (MFCCs). These features are subsequently fed into a feed-forward artificial neural network (ANN) to accurately classify the punch wear condition. The approach is inspired by experienced machine operators who can intuitively discern punch wear from the sound emitted during trimming operations. On a collected dataset the model achieved 99.26% accuracy during training and 97.45% accuracy during testing. The system tracked progressive punch wear, demonstrating robustness to process noise and repeatability across runs. The system enables continuous, non-invasive tool monitoring, reducing manual inspection, unplanned downtime and improving product quality.
  Keywords: Punch Wear Detection; Burr Formation; Sheet Metal Trimming; Acoustic Signal; Wavelet Transform; MFCC; ANN; Real-time Monitoring.
  DOI: 10.1504/IJMMS.2025.10076237
   
  
• Utility-Driven Operator-Information Co-Regulation Process: A Human-Centred Motivational Perspective  
  by Martina Cardamone, Giovanni Mirabelli, Antonio Padovano, Vittorio Solina 
  Abstract: Human performance in procedural work varies even under standardised conditions, revealing limits in traditional prescription-based error prevention. This study adopts an abductive, single-case design in industrial remanufacturing to explore how cognitive and motivational regulation shape procedural adherence. Through three iterative cycles of systematic combining, five analytical constructs were identified, leading to the dynamic motivational filtering model. The model conceptualises adaptive guidance as state information co-regulation, where content is dynamically filtered via a predictive utility function and latent-state estimation. Formalised through a Kalman-based architecture, the system infers the operators evolving state by integrating motivation as an active control variable. Two illustrative use cases provide a functional proof of concept, demonstrating the models logic in regulating real-time information flow. The framework provides a computational foundation for next-generation humanmachine interfaces that sustain attention, autonomy, and safety in complex Industry 5.0 environments.
  Keywords: Adaptive procedural guidance; human–machine interaction; Human-centred factories; cognitive–motivational regulation; procedural variability; adaptive automation; operator state estimation.
  DOI: 10.1504/IJMMS.2025.10076901
   
  
• Experimental and Simulation Modelling Investigations on Adaptive Air-Jet Support Technology for Mirror Milling  
  by Zhiheng Yuan, Guoliang Liu, Jack Fei 
  Abstract: Thin-walled components are essential parts of many precision physical instruments and national defence equipment. Mirror milling represents one of the most advanced machining techniques for such structures. To address the limitations of conventional rigid supports, this study proposes an adaptive air-jet support technology. Numerical simulations were conducted to analyse the effects of nozzle geometry on air-jet force, and the optimal design was obtained. An adaptive air-jet support device and control system were then developed. Based on full-factorial experiments, a neural network model for predicting axial milling force was established to determine control parameters under different cutting conditions. This enables real-time adaptive control of the air jet. Experimental results show that the proposed method effectively enhance the stability and improves surface quality, providing a non-contact solution for enhancing mirror milling performance.
  Keywords: Mirror milling; Air-jet support; Axial milling force; Surface quality; Simulation.
  DOI: 10.1504/IJMMS.2025.10077332
   
  
• Deep Learning-Based Wafer Fabrication Quality Assessment in Semiconductor Manufacturing  
  by Jinxing Zhao, Quan Meng, Haolan Zheng, Yuhao Fan, Zinuo Zeng 
  Abstract: Semiconductor manufacturing relies heavily on wafer fabrication quality, as it directly determines the performance and reliability of downstream electronic and optoelectronic devices. To address the challenges of reliability and efficiency in wafer quality assessment, we propose a deep learning-based multi-label defect detection and classification method for wafer fabrication. The method employs the ShuffleNetV2 for feature extraction, and the Sigmoid activation function for multi-label outputs. The CB-Focal Loss was introduced to tackle class imbalance while the coordinate attention mechanism was integrated to enhance the model's focus on defect regions. Experiments on our own AFM-Wafer dataset demonstrate that, compared with the baseline model, new model achieves 0.51%, 1.39%, 1.31%, and 1.24% increases in Accuracy, L-Precision, L-Recall and L-F1 score, respectively while maintaining nearly the same parameter count and inference speed. This research demonstrates how advanced computer vision and deep learning complement traditional manufacturing and economic merits.
  Keywords: Wafer Fabrication; Deep Learning; Defect Detection; Quality Assessment; Semiconductor Manufacturing.
  DOI: 10.1504/IJMMS.2025.10077423