International Journal of Mechatronics and Manufacturing Systems (10 papers in press)

Regular Issues

• Omnidirectional Service Robot: From Design to Trajectory Tracking Control  
  by Sohrab Allahyari, Ramin Mersi, Mohammad Reza Haghjoo, Vahid Fakhari 
  Abstract: This paper presents the comprehensive design, modeling, and tracking control of a service robot, a three-wheeled omnidirectional mobile robot covering all stages of development, including experimentation with a prototype. The system features a lightweight yet sturdy structure, drive and control systems, and a wireless user interface accessible through smartphones, among other components. The robot’s kinematics and dynamics are meticulously studied, and an openloop model is derived with careful consideration of the primary nonlinearities within the robot. Two effective closed-loop controllers focusing on low-level control are proposed in this work. Firstly, an independent joint proportionalintegral (PI) controller utilizes velocity feedback control of motors in joint space. Secondly, additional outer position loops empower a cascade-modified proportional-integral-derivative (PID) controller. Several evaluation experiments were conducted, demonstrating the effectiveness of the tracking control and showcasing good agreement between simulation and experimental results.
  Keywords: Mobile Robotics; Omnidirectional wheel; Embedded system; Modeling; Trajectory tracking control.
  DOI: 10.1504/IJMMS.2024.10066228
   
  
• Inspection of thin-walled blade profile considering curvature characteristics and machining deformation  
  by Jingwen Lao, Sitong Xiang, Hainan Zhang, Ben Yu, Jianguo Yang 
  Abstract: Abstract: Thin-walled blades are prone to machining deformation, while the traditional inspection method does not consider the machining deformation. This paper proposes an inspection method of the blade based on curvature characteristics and machining deformation. According to the curvature and machining deformation, the blade is divided into different sections and areas. In each area, the chord deviation method is used but the chord deviation value and the amount of sampling points are optimized according to the proportions of machining deformation of each region. Compared with traditional methods, the overall fitting maximum and average deviation of the blade is reduced by 37.5% and 16.3%, meanwhile the amount of sampling points is reduced by 18.8%. The proposed method matches the blade curvature characteristics and the machining deformation, and improves the efficiency and accuracy of inspection.
  Keywords: Keywords: Thin-walled blades; Sampling point planning; Machining deformation; Curvature characteristics.
  DOI: 10.1504/IJMMS.2024.10066229
   
  
• Tribological mechanism of different types of nanoparticles at the ultrasonic vibration assisted turning interface of titanium alloy  
  by Haoran Ma, Jintao Zheng, Xiangjun Li, Jian Tang, Xinfu Liu, Guoliang Liu 
  Abstract: Ultrasonic vibration assisted turning with nanofluid minimum quantity lubrication (UVAT-NMQL) has proven to be an effective means of improving the processing property. To further understand the tribological mechanism of different types of nanoparticles at the cutting zone, seven types of nanofluids were employed in the UVAT-NMQL processes of titanium alloy. The results indicate that the carbon nanotubes, with a one-dimensional tubular structure, can exhibit the adsorption filling effect and a similar effect to rolling bearings, effectively reducing the main cutting forces. High-hardness three-dimensional nanoparticles (alumina and diamond) also function similarly to rolling bearings, but they are more susceptible to being squeezed into the machined surface. Graphene and molybdenum disulfide, with two-dimensional lamellar structures, easily spread on the workpiece surface and contribute to friction-reduction through interlayer shear behavior. Increasing the layers of graphene nanosheets and the length of carbon nanotubes appropriately can further improve their anti-wear effect.
  Keywords: Ultrasonic vibration assisted turning; Minimum quantity lubrication; Nanofluid; Titanium alloy.
  DOI: 10.1504/IJMMS.2024.10066230
   
  
• Deep learning-based recovery of cutting tool vibrations from spatiotemporally aliased video  
  by Harsh Singh Rajput, Varun Raizada, Mohit Law 
  Abstract: Visual vibrometry involves motion registration of vibrating objects from their video using image processing and computer vision methods. Its advantages include being full-field, contactless and not requiring sophisticated data acquisition devices. To leverage its use to record motion of cutting tools that vibrate at high frequencies and with small motion requires video to be recorded at high speeds and resolutions. However, since cameras trade speed for resolution, motion can become spatiotemporally aliased. This paper shows that it is possible to recover motion by upsampling the spatiotemporally aliased video using CNN-based deep learning methods. Since the upsampled motion’s spectra has at least as many peaks as the upsampled rate, we also present a simple method to deduce true modes from observed ones. Methods presented are generalized and can measure high frequency and small vibratory motion using even low-speed and resolution cameras.
  Keywords: deep learning; CNN; convolutional neural networks; aliasing; upsampling; visual vibrometry; cutting tools.
  DOI: 10.1504/IJMMS.2024.10066231
   
  

Special Issue on: Artificial Intelligence for Smart Manufacturing and Mechatronics

• Collaborative Resilience: Taxonomy-Informed Neural Networks for Smart Assets’ Maintenance in Hostile Industry 4.0 Environments  
  by Vagan Terziyan, Oleksandra Vitko 
  Abstract: This article explores knowledge-informed machine learning and particularly Taxonomy-Informed Neural Networks to enhance data-driven smart assets’ maintenance by contextual knowledge. Focusing on assets within the same class that may exhibit subtle variations, we introduce a weighted Lehmer mean as a dynamic mechanism for knowledge integration. The method considers semantic distances between the asset-in-question and others in the class, enabling adaptive weighting based on behavioral characteristics. This preserves the specificity of individual models, accommodating heterogeneity arising from manufacturing and operational factors. In the adversarial learning context, suggested method ensures robustness and resilience against adversarial influences. Our approach assumes a kind of federated learning from neighboring assets while maintaining a detailed understanding of individual asset behaviors within a class. By combining smart assets with digital twins, federated learning, and adversarial knowledge-informed machine learning, this study underscores the importance of collaborative intelligence for efficient and adaptive maintenance strategies in Industry 4.0 and beyond.
  Keywords: neural networks; knowledge-informed machine learning; taxonomy; smart asset; digital twin; maintenance; federated learning; adversarial learning; robustness; Industry 4.0.
  DOI: 10.1504/IJMMS.2024.10064064
   
  
• DEVELOPMENT OF A ROBUST INDICATOR FOR ONLINE CHATTER DETECTION  
  by Ejiofor Matthew Dialoke, Hongrui Cao, Jianghai Shi 
  Abstract: During the milling process, chatter is one of the most uncontrollable and unwanted occurrences. To prevent damage to the workpiece and to monitor and detect chatter as quickly as possible, a reliable indicator is essential. This paper proposes a robust root mean square (RRMS) indicator for online chatter identification. Using weighted techniques, the two-time domain indicators Root Mean Square (RMS) and Kurtosis (K) are combined to develop the proposed indicator, RRMS, with improved detection accuracy. The Short-Time Fourier Transform (STFT) was used to visualize the changing frequency components in the Time-Frequency Representation (TFR). The efficacy of the proposed indicator for online detection was confirmed by a series of milling tests. The 3-sigma rule is used to calculate the threshold, and the RRMS is employed for detection. Because the results demonstrate a heightened sensitivity to chatter, we concluded that RRMS is extremely suitable for online detection.
  Keywords: Chatter detection; Acoustic signal; Weighted technique; Variable cutting depth; Variational mode decomposition (VMD).
  DOI: 10.1504/IJMMS.2024.10064065
   
  
• Multivariate analysis of AISI-52100 steel machining: A combined finite element-artificial intelligence approach  
  by Anastasios Tzotzis, Nikolaos Efkolidis, César García, Panagiotis Kyratsis 
  Abstract: The present study focuses on the analysis of AISI-52100 steel hard-turning with standardized square inserts. The process is being studied in terms of the resultant cutting force and the cutting power under a wide range of four key machining parameters: the cutting speed, the feed rate, the depth of cut and the tool nose radius. First of all, an updated Finite Element Method (FEM) model has been used to generate a data set, which in turn was used to train an artificial Neural Network (ANN), minimizing this way the required experimental work and the utilization of high amounts of computing resources. The developed networks were evaluated with regard to their reliability, revealing increased levels of accuracy. The Mean Absolute Percentage Error (MAPE) was calculated equal to 8.1% for the force prediction network and 11.2% for the power prediction network respectively. Furthermore, the multivariate interaction was evaluated and visualized.
  Keywords: AISI-52100 turning; cutting forces; cutting power; 3D FEM; ANN; DEFORM-3D; artificial intelligence.
  DOI: 10.1504/IJMMS.2024.10064869
   
  
• Automated Repairing Process of Metal Components in Manufacturing with Directed Energy Deposition  
  by Daniel Knüttel, Anneke Orlandini, Stefano Baraldo, Anna Valente, Emanuele Carpanzano, Konrad Wegener 
  Abstract: The importance of repairing processes is increasingly gaining in importance. In this regard, Directed Energy Deposition (DED) is a promising metal additive manufacturing technology for the refurbishment of components. However, the practical implementation and daily utilization of such process for repairing purposes introduces a high amount of complexity. The repairing processes are labour and time intensive, thus limiting their adoption in industry. This work demonstrates the automation of the repairing process by leveraging AI based methods and further algorithms to overcome current limitations. The proposed workflow covers the repairing process starting from the reverse engineering of the damaged part by a 3D scanner integrated within the machine, up to the material addition by DED, to enable a more profitable solution and a step towards circular economy.
  Keywords: Circular economy; manufacturing; process automation; repairing; metals; lasers; directed energy deposition; additive manufacturing; artificial intelligence.
  DOI: 10.1504/IJMMS.2024.10066232
   
  
• Thermal Signal-enhanced Unscented Kalman Filter for Tool Wear Prediction  
  by Xianzhe Fu, Fan Zhaoyan, Burak Sencer, Karl Haapala 
  Abstract: Tool wear is a gradual failure of cutting components generally caused by complex cutting conditions during the machining processes. This paper presented a thermal signal-enhanced tool wear prediction method to predict tool wear development during the cutting process. The smart tool samples the multi-modal sensor signals, including tool temperature, vibration, strain, and acoustic emission, which were processed through a neural network model and an Unscented Kalman Filter (UKF) to predict the tool wear size. Specifically, the measured tool temperature was considered as a tool wear status indicator to update the state transition function in the UKF and enhance the prediction accuracy with the presence of noises in the sensor signals. This method was validated on a commercial CNC lathe. The experimental results showed that the new method achieved an improvement of 8% in tool wear prediction accuracy compared to the conventional UKF.
  Keywords: tool wear prediction; Unscented Kalman filter; tool health; multi-sensor system; thermal signals; deep learning; feature extraction.
  DOI: 10.1504/IJMMS.2024.10066325
   
  

Special Issue on: IJSM2023 Artificial Intelligence in Robotics and Manufacturing Automation

• A critical review of contribution of evolutionary techniques to machining parameter optimization  
  by Uday Shanker Dixit, Faladrum Sharma 
  Abstract: Optimization of machining processes has been an active research area for over six decades. In the last three decades, several evolutionary optimization methods have been utilized. This article offers a brief history of optimization in machining followed by a detailed discussion on the application of evolutionary optimization methods. The focus is narrowed down to traditional machining processes, where a wedge shaped material removes the material in the form of chips. The article highlights the challenges in choosing a suitable algorithm, given the empirical nature of available comparative studies lacking a solid mathematical basis. Further research is needed to understand the similarities and contrasts among evolutionary optimization methods. It is also prudent to focus on the proper modelling of the processes (preferably with the help of big data), integrating the machine tools with proper sensors and developing strategies for online optimization.
  Keywords: Evolutionary optimization; Machining; Soft computing; Nonlinear programming; Genetic algorithm; Particle swarm optimization.
  DOI: 10.1504/IJMMS.2024.10066233