International Journal of Manufacturing Research (8 papers in press)

Regular Issues

• AI Tools for Advancement of Manufacturing Sector: a Systematic Review, Bibliometric Analysis, Thematic Synthesis, and Technological Framework Development  
  by Kunal Sharma, Vikrant Sharma, Mukheshwar Yadav 
  Abstract: The burgeoning field of artificial intelligence (AI) has had a profound impact on a wide range of industrial sectors. This transformative paradigm shift aims to fundamentally change traditional manufacturing methodologies. The primary goal of this study is to provide a comprehensive overview of the current state and future path of AI applications in manufacturing settings. A bibliometric analysis is carried out to determine the evolutionary path of AI-centric research in the manufacturing domain. Subsequently, a thematic synthesis is performed to categorise and combine the findings, revealing overarching themes. Furthermore, this study adds significantly to the field by providing a technological framework for the integration and deployment of AI tools aimed at augmenting manufacturing processes. Research into AI in the manufacturing sector has increased dramatically since 2019, concentrating mainly on machine learning, deep learning and computer vision. The framework outlines major barriers, factors that help and practical uses of AI, giving industry partners valuable ideas. The combined insights from this study provide a solid foundation for informed decision making, strategic planning, and the development of future innovations at the intersection of AI and manufacturing.
  Keywords: Artificial Intelligence (AI); AI Tools; Manufacturing Sector; Bibliometric Analysis; Thematic Analysis; Framework Development.
  DOI: 10.1504/IJMR.2025.10072918
   
  
• New Method for Estimating Additive Blooming on the Surface of Vulcanised Rubbers  
  by Jose D.E. Jesus Cabrera-Castro, Roberto Zitzumbo Guzmán, María Blanca Becerra Rodriguez, Anayansi Estrada Monje 
  Abstract: The blooming of additives on the surface of vulcanised rubber samples has been evaluated. Blooming is the accumulation of additives that have migrated from inside the rubber sample to the surface, manifesting themselves as whitish stains. The determination of the surface bloom was carried out using two methods, a traditional method and a newly developed method. The traditional method is the gravimetric method and the new method developed is the Euclidean distance method, which consists of a system composed of artificial vision, image processing and a mathematical model. The Rvalues confirmed that a Fick-type diffusion model (linear with t1/2) suitably describes the blooming process. Both Spearman ( = 1.0, p = 0.000) and Pearson (r > 0.91) correlations were strong, validating the method has ability to accurately capture the temporal dynamics of blooming.
  Keywords: -test statistics; blooming; vulcanised rubber; image processing; euclidean distance; aesthetic quality of rubber; mechanical properties.
  DOI: 10.1504/IJMR.2025.10072983
   
  
• A Meta-Heuristic-Based Framework for Sustainable P-hub Network Design of Perishable Items under Fuzzy Time Uncertainty  
  by Saeed Zameni, Seyed Esmaeil Najafi, Seyed Mohammad Hajimolana, Seyed Mojtaba Sajadi 
  Abstract: In this paper, a novel mathematical model is presented for designing a sustainable hub network for perishable commodity transportation, taking into account social responsibility, environmental impact, and economic viability. As many real world problems have non deterministic parameters, the time parameters are considered fuzzy numbers in the model. To validate the model, the model is solved on a small scale using GAMS software after linearisation. However, due to the nondeterministic polynomial time nature of the problem, an efficient meta-heuristic algorithm is proposed using MATLAB software. The algorithm has been validated on small and medium scale instances using the AP and CAB datasets. The results show that the proposed NSGA-II algorithm achieves an average solution gap of 0.017% while significantly reducing computational time compared to exact methods. The proposed model and algorithm can assist decision makers in designing sustainable and efficient supply chain networks for perishable products.
  Keywords: P-Hub location problem; Sustainable supply systems; Food logistics network; Fuzzy multi-objective nonlinear optimisation; Perishable goods.
  DOI: 10.1504/IJMR.2025.10073024
   
  
• Contract design and implementation in the era of Industry 4.0: a systematic analysis  
  by Cheng Wang, Mengna Hu, Zhuowei Zheng, Longyan Wei, Xun Xu 
  Abstract: Smart manufacturing under the background of Industry 4.0 requires organisations to carry out digital transformation from three dimensions: vertical integration, horizontal integration and end-to-end integration. Contract or mechanism design is needed when integration happens among different ownerships. To explore the contracts in smart manufacturing, with the help of bibliometrics, 5,087 related literature were retrieved based on the Web of Science, covering the period from 2000 to 2024. Bibliometric results are presented from the perspectives of global contribution, leading countries/regions, related research areas, institutions, journals, authors, the most cited publications and keywords. Hot topics and trends are excavated from highly cited papers and hot papers. Based on the bibliometric results, we confirm that blockchain and smart contracts are key to the realisation of contracts in smart manufacturing. Finally, this paper provides a systematic analysis of contract design and implementation driven by blockchain and smart contracts in horizontal and end-to-end integration. [Submitted 15 January 2023; Accepted 6 November 2024]
  Keywords: Industry 4.0; contract design; contract implementation; smart manufacturing; vertical integration; horizontal integration; end-to-end integration; blockchain; smart contracts; bibliometrics.
  DOI: 10.1504/IJMR.2024.10069160
   
  
• Deep learning-driven parts feature extraction and surface reconstruction for efficient parts pairing  
  by Xuezhen Li, Xiao Lu, Zhehan Chen, Ning Zhao, Lechang Yang 
  Abstract: Assembly stands as a crucial process in industrial manufacturing, but traditional manual parts pairing is often inefficient. Previous research has highlighted the potential of deep learning for feature extraction and 3D reconstruction from point clouds. We introduces an innovative method based on deep learning for high-precision feature extraction and surface reconstruction aimed at parts pairing. By defining essential assembly features and employing the random sample consensus method, geometric dimensions and surface topography data are acquired. Subsequently, deep learning is utilised to directly regress the surface distance function from point samples, enabling detailed surface modelling of parts and supporting assembly simulation within the digital twin framework. A case study for validation reveals that after optimisation, 30 shaft parts and 30 hole parts are successfully matched, with an average uniformity increase of 0.024. This demonstrates the proposed method's superior effectiveness and accuracy in feature extraction and surface reconstruction. [Submitted 26 June 2023; Accepted 17 December 2024]
  Keywords: parts paring; features extracting; surface reconstruction; non-contact measuring; deep learning.
  DOI: 10.1504/IJMR.2024.10069271
   
  
• Assessment of turning performance of POM-C and PA.6 using Taguchi, VIKOR, TOPSIS and CoCoSo methods, incorporating AHP and FUCUM  
  by Mounia Kaddeche, Septi Boucherit, Salim Belhadi, Mohamed Athmane Yallese 
  Abstract: Despite their widespread use in modern manufacturing for producing mechanical parts, the machining of unreinforced polymer materials like PA-6 and POM-C has received limited attention in the existing literature. The distinctive semi-crystalline nature of these materials necessitates specific machining approaches. This investigation aims to address this gap by focusing on process control for machining polymer parts, targeting optimal cutting parameter configurations for shaping processes. The parameters include cutting speed (Vc), feed rate (f), and depth of cut (ap), while outcomes such as surface roughness (SR), tangential cutting force (Fz), cutting power (Pc), and material removal rate (MRR) are evaluated. Single-objective optimisation was conducted using the Taguchi philosophy, and three multi-objective MCDM methods (VIKOR, TOPSIS, and CoCoSo) were used. The findings indicate that the VIKOR method outperforms the others, achieving a favourable compromise among the objectives. By incorporating the AHP and FUCOM weighting methods, The TOPSIS and CoCoSo methods strike a balance between product quality (Fz and Ra) and productivity (MRR and Pc). [Submitted 26 April 2024; Accepted 19 March 2025]
  Keywords: polyacetal; POM-C; polyamide; PA-6; Vise Kriterijumska Optimisacija Kompromisno Resenje; VIKOR; TOPSIS; combined compromise solution; CoCoSo; AHP; FUCOM.
  DOI: 10.1504/IJMR.2024.10072916
   
  
• ANN-GA integrated acrylic milling optimisation for energy consumption, machining time and MRR  
  by Shanta Saha, Mohammad Muhshin Aziz Khan, Ahmed Sayem, Md. Alamgir Hossen, Pankoj Nandi 
  Abstract: This study explores the application of the artificial neural network-genetic algorithm (ANN-GA) approach to optimise CNC milling parameters for acrylic machining, focusing on energy efficiency, material removal rate (MRR), and machining time. A set of experiments were conducted via full factorial design to investigate the impact of these parameters on the responses, with spindle speed demonstrating the most significant influence. The mathematical model was developed to predict responses using ANN, with the selected network, achieving the lowest mean square error of 0.0019. By integrating GA with ANN, multi-objective optimisation was achieved, minimising energy consumption and machining time while maximising MRR. The optimised solutions offered the best combinations of operating parameters to enhance overall performance in the given cutting condition. Validation through confirmation tests demonstrated the efficacy of the ANN-GA approach, with error margins below 5%. The optimised results showcase the effectiveness of the ANN-GA method, providing adaptable solutions for manufacturers to balance conflicting objectives in CNC milling. [Submitted 2 September 2024; Accepted 26 June 2025]
  Keywords: acrylic plastic; CNC milling; multi-objective optimisation; ANN-GA.
  DOI: 10.1504/IJMR.2024.10072722
   
  
• Optimisation of process parameters for laser-assisted micro-milling of Inconel718  
  by Chen Cong, Jiachen Hao, Xiaohong Lu, Zhe Liu, Steven Y. Liang 
  Abstract: Inconel718 has high corrosion resistance and strength, making it widely used in aerospace and other demanding fields. Laser-assisted micro-milling (LAMM) offers a potential method for high-quality, efficient machining of Inconel718 micro-components. However, achieving both high surface quality and efficiency is challenging due to the complex, multi-physics nature of the process. This study investigates the effects of spindle speed, feed per tooth, axial cutting depth, and laser power on surface roughness. Surface roughness and material removal rate (MRR) models are established, with the average and maximum relative error of 10.22% and 11.13%. Interaction effects significantly influence surface roughness, particularly among spindle speed/laser power and feed per tooth/axial cutting depth. Targeting low surface roughness and high MRR, a genetic algorithm was employed to optimise parameters, yielding a Pareto optimal solution set. This research provides guidance for process parameter selection in LAMM Inconel718. [Submitted 12 September 2024; Accepted 26 June 2025]
  Keywords: laser-assisted micro-milling; LAMM; Inconel718; parameters optimisation; surface roughness prediction; genetic algorithm; GA.
  DOI: 10.1504/IJMR.2024.10072723