International Journal of Manufacturing Research (5 papers in press)

Regular Issues

• Novel Multi-step based process Modelling and Prediction of Thermodynamic Properties of Steam using Machine Learning  
  by Ashwani Kharola, Kiran Sharma, Vishwjeet Choudhary 
  Abstract: This study investigates different machine learning techniques for precise prediction of various thermodynamic properties of steam. Calculating interpolated values of different thermodynamic properties is a time consuming and tedious task. Therefore, different machine learning models are proposed in the study. The techniques considered for prediction include feed-forward neural network (FFNN), nonlinear autoregressive neural network (NARNN) and adaptive fuzzy inference system (ANFIS). An optimal FFNN model has been designed by varying the number of neurons (n) in hidden layer, i.e. n = 10, 20, 30, 40 and 50. Additionally, a novel NARNN model has been proposed in this study having 10 neurons in hidden layer for predicting different thermodynamic properties of steam through multi-step ahead predictions. The study further proposes an optimal ANFIS model designed considering the appropriate shape and number of membership functions. The performance of proposed techniques was finally measured in terms of different error indicators for better validation.
  Keywords: process modelling; multistep ahead prediction; thermodynamic properties; steam; optimisation; prediction; feed-forward neural network; FFNN.
  DOI: 10.1504/IJMR.2024.10066908
   
  
• Analytical Modelling of the Cutter Workpiece Engagement and the Undeformed Chip Thickness for Circular Ball end Milling Path for Adaptive Feed Rate  
  by Sai Lotfi, Belguith Rami, Regaieg Amine, Maaloul Makram 
  Abstract: In the ball end milling process, the stability of the process depends on the variations of the cutter workpiece engagement region (CWER) and the instantaneous undeformed chip thickness (IUCT). These two parameters influence cutting forces, tool wear, and machining stability. Previous works have modelled the CWER and the IUCT in the case of linear interpolation, but curvilinear and circular interpolations have not been studied yet. In this study, we focus on the curvilinear path, which is assumed to be the junction of several circular tool paths with a radius equal to the programmed value of the circle circumscribed. The method is described with a geometrical and analytical approach for determining the CWER and the IUCT in the case of concave and convex paths, both in down and up milling. The approach also proposes feed rate optimisation to maintain a constant maximum IUCT along the tool path.
  Keywords: ball end milling; cutter workpiece engagement region; CWER; undeformed chip thickness; tooth trajectory; circular interpolation; adaptive feed rate.
  DOI: 10.1504/IJMR.2024.10066912
   
  
• Addressing Omni-Channel Supply Chain Challenges: the Importance of Supply Chain Coordination  
  by Abolfazl Dehghan, Mahboobeh Honarvar, M.B. Fakhrzad, Ahmad Sadegheih 
  Abstract: This research paper discusses the development of collaborative and non-collaborative decision-making approaches in an omni-channel supply chain. The objective is to enhance integration between online and offline channels by implementing the buy online and pick-up in store (BOPS) strategy. The decisions under consideration involve pricing and retailer service level (RSL) determination by the retailer, as well as delivery time and online service level (OSL) determination by the supplier. In this study, we utilise a Nash game approach to examine the decision-making problem, where both the retailer and supplier are motivated to maximise their respective profits within decentralised, centralised, and coordinated systems. The research findings indicate that in the centralised system, as the cost coefficient of OSL increases, there is a decrease in the values of price variables and RSL. However, in the decentralised system, the values of these variables increase. Additionally, in the centralised system, an increase in the OSL parameter leads to a corresponding increase in the delivery time. Conversely, in the decentralised system, the value of this decision variable decreases. The present study also provides some managerial insights through the analysis of the critical parameters of the model.
  Keywords: online service level; pricing; delivery time; retailer service level; coordination; omni-channel.
  DOI: 10.1504/IJMR.2024.10067197
   
  
• A Comparative Study of Different Machine Learning Approaches for Predicting Cutting Force and Surface Roughness during Ultrasonic-Assisted Milling  
  by Yasmine El-Taybany, Ghada Elhendawy 
  Abstract: This study utilises machine learning (ML) approaches to predict the performance of ultrasonic-assisted milling (UAM) of soda-lime glass based on the experimental results. The main goal is to model UAM performance and investigate the potential of ML in predicting the cutting force and surface roughness. Four different ML algorithms, mainly multilayer perceptron (MLP), self-organising maps (SOM), support vector machine (SVM), and principal component analysis (PCA), have been used and compared with the experimental data. To evaluate the accuracy of each ML technique, the mean square error (MSE), normalised root mean square error (NRMSE), and correlation coefficient (r) for each model have been obtained and compared. The findings prove that the proposed ML approaches can model UAM process, as the predicted results indicate good agreement with the experimental values. In particular, the results show that MLP and SOM are more reliable and accurate methods for predicting the cutting force and surface roughness.
  Keywords: cutting force; surface roughness; ultrasonic-assisted milling; machine learning; modelling; prediction.
  DOI: 10.1504/IJMR.2024.10067788
   
  
• Evaluating Human-Centric Cyber Security Risks in the Manufacturing Industry  
  by Gonul Ayranci, Melisa Ozbiltekin-Pala, Yesim Deniz Ozkan-Ozen 
  Abstract: With rapidly developing technology and digitalisation, the importance of cybersecurity is increasing, underlining the importance of human-centric cybersecurity risks, especially in the manufacturing industry. This study aims to reveal the sector's human-centric cybersecurity risks due to the manufacturing industry's complex processes and continuity-based structure. In this study, eight risks were identified and evaluated using the fuzzy CRITIC method. This study identified the top three human-centric cybersecurity risks in the manufacturing industry as follows: employee resistance to cybersecurity practices and data privacy, lack of employee training and education on cybersecurity and lack of human-machine integration. This comprehensive analysis of human-centric cybersecurity risks in the manufacturing industry highlights the need for cybersecurity strategies to include human-centric measures. The results suggest that managers, security professionals, and practitioners develop an effective combat strategy against human-centric cybersecurity risks in the manufacturing industry.
  Keywords: manufacturing; risk management; cybersecurity; digital transformation.
  DOI: 10.1504/IJMR.2024.10068139