International Journal of Manufacturing Technology and Management (28 papers in press)

Regular Issues

• Transmission error compensation method for small module gears of CNC machine tools based on discretization decoupling calculation  
  by Huiqin Li, Jing Chang, Baofeng Zhang 
  Abstract: In order to improve the stability of gear transmission process and reduce transmission failure rate, a transmission error compensation method based on discretization decoupling calculation was proposed for small module gears of CNC machine tools. Analyze the dynamic changes in the gear transmission process, and set up sensors to collect the gear meshing frequency and transmission meshing frequency. Based on the sensing signal, establish a transmission error analysis model. The discretization analysis concept is introduced into the model, and the difference between the theoretical tooth surface and the actual machined tooth surface is taken as the transmission error. After the decoupling calculation, the error compensation amount is obtained.Experiment show that this method can control the gear transmission failure rate between 0.042 and 0.065, and maintain the transmission output power between 2800kW and 3000kW, indicating that this method can effectively achieve compensation for transmission errors.
  Keywords: CNC machine tools; Small module gear; Dynamics; Sensors; Transmission error; Discretization principle; Decoupling calculation; Error compensation.
  DOI: 10.1504/IJMTM.2023.10061700
   
  
• Automatic Fault Diagnosis Method for Mining Hydraulic Support Based on Fuzzy Analysis  
  by Minjie Chen, Rongjin Yang 
  Abstract: A fuzzy analysis based automatic fault diagnosis method for mining hydraulic supports is proposed with the goal of improving fault detection rate, reducing misdiagnosis rate, and improving diagnostic efficiency. Firstly, for the structure of mining hydraulic support, real-time data collection of mining hydraulic support work is carried out through multiple DS18B20 sensor arrays; then, the moving average method is used to denoise the collected data, and the artificial bee colony algorithm is used to extract fault features; finally, based on the results of data denoising and feature extraction, a fuzzy rule library is established using expert experience and knowledge, and fault diagnosis is achieved through fuzzy reasoning and deblurring. The experimental results show that the highest fault detection rate of the proposed method is 83.5%, and the misdiagnosis rate remains below 2%, with a relatively short fault diagnosis time.
  Keywords: fuzzy analysis; hydraulic support; fault diagnosis; moving average method; fuzzy rule library; artificial bee colony.
  DOI: 10.1504/IJMTM.2023.10062073
   
  
• Fault Information Identification Method of Industrial Production Equipment Based on Industrial internet of things  
  by Yun Yang  
  Abstract: In order to solve the problems of low recognition accuracy and long recognition time existing in the existing fault information recognition methods for industrial production equipment, this paper proposes a fault information recognition method for industrial production equipment based on the industrial internet of things. First, based on the industrial internet of things technology, build an information collection platform for industrial production equipment; then, based on wavelet coefficients, the equipment signal is pre-processed and the fault features of industrial production equipment are extracted based on sparse expression; finally, a least squares support vector model is constructed to classify fault signals and achieve recognition of industrial production equipment fault information. Through experiments, it can be seen that the accuracy of using the method proposed in this article for recognition is always above 96%, and the recognition time is always within 7.50 s, which has good recognition effect and efficiency.
  Keywords: industrial internet of things; IIoT; industrial production equipment; fault information; wavelet coefficients; sparse encoding; least squares support vector machine.
  DOI: 10.1504/IJMTM.2023.10062074
   
  
• Optimization Method for Human Resource Scheduling in Manufacturing Industry Based on Decision Tree Algorithm  
  by Huan Wang, Hao Wang 
  Abstract: To overcome the problems of low efficiency in traditional labour resource allocation and poor measurement of employee competence, this paper designs a manufacturing human resource scheduling optimisation method based on decision tree algorithm. Firstly, determine the principles of resource scheduling optimisation and obtain scheduling optimisation parameters; then, using entropy calculation method to calculate the importance of parameters, establish a decision tree to obtain a classification scheduling optimisation rule set, and sort the parameter attributes; finally, the Gini index is used to classify the sample parameters and construct a decision tree for resource scheduling optimisation, achieving the final scheduling optimisation. The results show that the overall allocation efficiency under this method is higher than 98%, and the competency measurement level is all A, which improves the efficiency of labour resource allocation and has a good measurement of employee competency.
  Keywords: decision tree algorithm; manufacturing human resources; scheduling optimisation; employee competency; degree of collaboration; Gini index.
  DOI: 10.1504/IJMTM.2023.10062075
   
  
• Research on automatic planning algorithm of surfacing repair path based on 3D vision technology  
  by Zhonghua Ni, Xinhua Wang 
  Abstract: To solve the problems existing in the traditional automatic planning algorithm of surfacing repair path, an automatic planning algorithm of surfacing repair path based on 3D vision technology is proposed. Firstly, the one-way planning distance is calculated, the pixel value containing weld in the target image is set to 0 based on 3D vision technology, the threshold value of weld is calculated, the surfacing repair path planning target is constructed, and the planning nodes are set. Calculate the displacement value of the component that needs welding deformation, and get the automatic planning result of surfacing repair path. The experimental results show that the target location result obtained by the proposed algorithm is more accurate, and the characteristics of the weld test sample image can be accurately planned. The average root mean square error after the supplement is smaller, which is 0.1 cm, indicating that the proposed method can effectively improve the path planning effect.
  Keywords: 3D vision technology; surfacing; repair the path; automatic planning algorithm; planning distance.
  DOI: 10.1504/IJMTM.2023.10062079
   
  
• A Control Method for Disordered Sorting of Industrial Robots Based on Binocular Stereo Vision  
  by Shudong He 
  Abstract: Controlling the disorderly sorting of industrial robots can significantly improve sorting efficiency, reduce costs, and improve production efficiency. Therefore, this article proposes a method for disorderly sorting control of industrial robots based on binocular stereo vision. Firstly, the binocular stereo vision method is used to calibrate the sorting items of industrial robots; secondly, the binocular parallax principle is used to obtain the depth information of the selected items and extract the pose of the sorting target object; then, the rotation method is used to extract the minimum bounding rectangle, and the motion equation of the object to be sorted and the end of the robot is constructed; finally, implement unordered sorting control based on machine vision. The results show that the calibration error of the proposed method is only 1.6%, and the control accuracy is as high as 96.2%, indicating that the proposed method can effectively improve the sorting effect.
  Keywords: binocular stereo vision; unordered sorting; improve the A* algorithm; binocular parallax; depth information.
  DOI: 10.1504/IJMTM.2023.10062083
   
  
• Scheduling method for industrial production processes in cloud manufacturing environment  
  by Yang Zhang, Meng-jun Huang, Chao Xu 
  Abstract: A method for scheduling industrial production processes in a cloud manufacturing environment is proposed with the aim of improving the scheduling effectiveness of industrial production processes. Establish a cloud manufacturing platform architecture, comprehensively consider industrial production tasks, processes, loading and unloading, and transportation links, and establish a scheduling framework in the cloud manufacturing environment; minimise industrial production time, production costs, and transportation scheduling frequency as the scheduling objective function, set production process constraints and production equipment constraints. Optimise the attraction term and random term of the standard firefly algorithm, and continuously optimise the objective function through multiple iterations to obtain the optimal scheduling result. The experimental results indicate that the production cost, transportation scheduling frequency, and industrial production time of this method are relatively low, indicating its feasibility.
  Keywords: cloud manufacturing; industrial production; production process scheduling; objective function; constraints; firefly algorithm.
  DOI: 10.1504/IJMTM.2023.10062084
   
  
• Online recognition method for appearance defects in mechanical parts processing based on machine vision  
  by Qian Meng, Pengfei Shi 
  Abstract: In order to solve the shortcomings of traditional parts appearance defect recognition methods with low recognition accuracy and long recognition time, this paper proposes an online recognition method for mechanical parts processing appearance defects based on machine vision. Firstly, the image acquisition environment of mechanical parts based on machine vision is determined. Secondly, the part image is pre-processed; thirdly, the maximum entropy segmentation method is used to complete the image segmentation. Finally, the defect texture features of the part image are extracted, and the support vector machine algorithm is combined to realise the online recognition of the appearance defects of mechanical parts. Experiments show that the recognition time of the proposed method never exceeds 600 s, the recognition accuracy is 93.75%, and the average time overhead of identifying a part is 0.5 s, which has high recognition accuracy and less time overhead, and has better application performance.
  Keywords: machine vision; mechanical parts; cosmetic imperfections; online recognition; variable threshold technology; maximum entropy segmentation.
  DOI: 10.1504/IJMTM.2023.10062086
   
  
• Product Design Sketch Defect Detection Method Based on Feature Extraction  
  by Liwei Sun 
  Abstract: There are problems with high false alarm rates and low registration of defect features in product design sketch defect detection. To this end, a defect detection method for product design sketches based on feature extraction is designed. First, the Gaussian filter method is introduced to remove the noise in the product design sketch, and grayscale processing is carried out. Secondly, linear transformation of product design sketches expands the grayscale range of sketch defects and changes the local enhancement effect. Finally, through the PCA algorithm in the feature extraction algorithm, the defect features of the product design sketch are extracted, and the product design sketch with this feature is regarded as an image with defects. The results show that the proposed method can effectively reduce the false alarm rate in detection and improve the registration degree of defect features, with a maximum registration degree of about 99%.
  Keywords: feature extraction; product design sketch; defect detection; grayscale; PCA algorithm; defect feature extraction.
  DOI: 10.1504/IJMTM.2023.10062087
   
  
• A Method for Predicting the Remaining Life of Mechanical Equipment in Production Lines Based on Similarity Features  
  by Xiangyang Mei, Tianbiao Yang, Wenyou Gao 
  Abstract: In order to shorten the time required for predicting the remaining life of mechanical equipment and reduce prediction errors, this paper proposes a method for predicting the remaining life of mechanical equipment in production lines based on similarity features. Firstly, obtain the vibration signals of mechanical equipment in the production line and extract signal features; then, calculate the similarity characteristics between the degradation indicators of mechanical equipment. Finally, the DTW method is used to measure the similarity of the overall lifespan of mechanical equipment, and the final remaining lifespan of the predicted samples is calculated based on the actual remaining lifespan of each reference sample and corresponding weights, achieving residual lifespan prediction. The results show that the prediction time of our method is only four seconds, and the prediction error does not exceed 8.33%, which verifies the effectiveness of our method.
  Keywords: similarity feature; DTW method; normalisation processing; local similarity; EEMD.
  DOI: 10.1504/IJMTM.2023.10062088
   
  
• How can the Adoption of Industry 4.0 Technologies Drive Innovation in Manufacturing Companies? Evidence from China and Korea  
  by Yongping Zhong, Hee Cheol Moon 
  Abstract: Digital manufacturing can optimize the production process and prompt adaptation to dynamic market changes, thereby enhancing firm performance. This study confirmed that adopting Industry 4.0 technology can positively impact technological competitiveness and knowledge acquisition. Both technological competitiveness and knowledge acquisition play crucial roles in promoting product, process and organizational innovation, ultimately leading to improved firm performance. The results indicated that the adoption of Industry 4.0 technology indirectly influences innovations through enhanced technological competitiveness and knowledge acquisition. More importantly, the findings also provide empirical evidence that the type of country moderated the resulting outcomes of Industry 4.0 technology in the manufacturing industry. This study, therefore, contributes to a deeper understanding of the transformation driven by Industry 4.0 in manufacturing by exploring the resulting outcomes of Industry 4.0 technology in different countries. This insight can guide managers in formulating more effective strategies to bolster innovation and enhance firm performance.
  Keywords: Industry 4.0; innovation; technological competitiveness; knowledge acquisition.
  DOI: 10.1504/IJMTM.2025.10069746
   
  
• Financial risk early warning method for modern manufacturing enterprises based on RBF neural network  
  by Yanyan Cao 
  Abstract: To detect potential financial risks in advance, reduce the rate of missed and false alarms in risk warning, and improve the accuracy of warning, a modern manufacturing enterprise financial risk warning method based on RBF neural network is proposed. Firstly, network coding methods are used to collect financial data such as total asset turnover rate, current ratio, and net profit margin of modern manufacturing enterprises. Secondly, the K-nearest neighbour method is used to remove outliers from the above data to improve the accuracy of risk warning results. Finally, based on the financial data of modern manufacturing enterprises and the financial risk warning results, a financial risk warning model is constructed using RBF neural network to achieve financial risk warning. The research results indicate that the method has low false positives and false positives rate, and a high F₁ value, which is beneficial for improving the accuracy and effectiveness of enterprise management decisions.
  Keywords: RBF neural network; modern manufacturing enterprises; financial risk warning; network coding; K-nearest neighbour method.
  DOI: 10.1504/IJMTM.2024.10066205
   
  
• Multi-objective optimisation method of cutting parameters of CNC machine tools based on improved genetic algorithm  
  by Zhenzhuo Wang, Yijie Zhu 
  Abstract: To improve the energy efficiency level of CNC machine tool processing, reduce production costs and energy consumption, a multi-objective optimisation method for cutting parameters of CNC machine tools based on improved genetic algorithm is proposed. Firstly, a multi-objective optimisation model for cutting parameters of CNC machine tools was constructed with the minimum energy consumption, maximum benefit, and maximum timeliness as objective functions, combined with three constraints of cutting speed, cutting power, and feed rate. Then, the objective function values of the cutting parameters of the CNC machine tool are sorted by non-dominated sorting based on the dominated effect. Finally, an improved Pareto genetic multi-objective optimisation method is designed using the improved niche technique and the vector modulus fitness function as the criterion for outliers, in order to obtain the optimal multi-objective optimisation of the cutting parameters of the CNC machine tool. The experimental results show that the method improves the feed speed, cutting speed and cutting depth, reduces the machining energy consumption, machining cost and machining time, and has good application effect.
  Keywords: CNC machine tools; objective function; cutting parameters; constraints; goal optimisation; improved genetic algorithm.
  DOI: 10.1504/IJMTM.2024.10066203
   
  
• Industrial IoT heterogeneous device access authentication for enterprise production management  
  by Yalin Wang 
  Abstract: To address the low accuracy, lengthy duration, and poor application effects of traditional methods, an industrial IoT heterogeneous device access authentication method for enterprise production management is proposed. This method utilises grey prediction techniques for predicting industrial IoT communication channel resources and constructing a communication channel model for industrial IoT. Based on the constructed model, industrial IoT communication data is obtained and the AdaBoost algorithm is employed to identify the identities of the industrial IoT heterogeneous devices. Leveraging enterprise production management as the foundation for the construction of the heterogeneous device access authentication architecture, this architecture combines the identity recognition results and achieves device access authentication through steps such as key initialisation, key extraction, and mutual authentication. The experimental results demonstrate that this method achieves a maximum authentication accuracy of 97.6%, a maximum authentication time of 84.1 ms, and exhibits good application effects.
  Keywords: enterprise production management; industrial IoT; heterogeneous devices; access authentication; communication channel model; key extraction.
  DOI: 10.1504/IJMTM.2024.10066200
   
  
• A contrast enhancement method for product packaging images based on adaptive equalisation  
  by Huimin Wang, Chao Gao, Yaning Li 
  Abstract: In order to solve the problems of low peak signal-to-noise ratio and poor product contrast in traditional product packaging image contrast enhancement, a product packaging image contrast enhancement method based on adaptive equalisation is proposed. Build a product packaging image acquisition architecture, obtain packaging images, and use guided filtering methods to denoise the images. Divide the denoised image into two sub images, perform equalisation on the histograms of the sub images within their respective ranges, merge the two sub histograms after equalisation, and obtain the contrast-enhanced product packaging image. The experimental results show that the maximum peak signal-to-noise ratio of the proposed method is 56.8dB, the maximum contrast value of the product packaging image is 0.46, and the maximum enhancement task time is 0.67s. The image contrast enhancement effect is good.
  Keywords: adaptive equalisation; product packaging; contrast enhancement; CMOS image sensor; guided filtering.
  DOI: 10.1504/IJMTM.2024.10066208
   
  
• A colour matching method for industrial product packaging driven by multidimensional image information  
  by Yaning Li, Yanna Shangguan, Chao Gao 
  Abstract: In order to overcome the problems of poor matching accuracy and long matching time in traditional industrial product packaging colour matching methods, the paper proposes a colour matching method for industrial product packaging driven by multidimensional image information. Firstly, collect multi-dimensional sensory information from industrial product packaging images; Then, clustering of packaging cognitive information is driven by dimensional image information to extract colour features from packaging images; Finally, the Lagrange function is introduced to calculate colour similarity, and a packaging colour matching model is constructed based on Bayesian analysis. Penalty parameters are introduced for model solving to obtain the final colour matching result. The results show that the accuracy of packaging colour matching under the proposed method can reach 99.32%, and the accuracy of colour matching can reach 99.6%, which verifies the matching effect of the proposed method.
  Keywords: driven by multidimensional image information; multidimensional perceptual information; Lagrange function; Bayesian.
  DOI: 10.1504/IJMTM.2024.10066207
   
  
• A workflow task scheduling algorithm based on parallel layering and priority  
  by Yongyi Huang 
  Abstract: This study aims to improve the overall execution efficiency of the system by dividing workflow tasks into multiple levels and executing tasks at different levels simultaneously. Firstly, a parallel layered approach is adopted to partition the execution order of tasks, construct a task dependency graph, and dynamically adjust task granularity based on computational complexity to avoid conflicts and competition between tasks. Secondly, based on the results of workflow task partitioning, calculate task priorities and arrange each task in priority order. Finally, based on the calculation of priority, a greedy algorithm is used for workflow scheduling. The experimental results show that the algorithm can effectively utilise parallel computing resources, optimise the execution order of tasks, reduce task waiting time, and improve the overall load balancing and resource utilisation of the system, thereby enhancing the task scheduling effect and performance of the workflow system.
  Keywords: parallel layering; priority; workflow; task scheduling; task dependency graph; greedy algorithm.
  DOI: 10.1504/IJMTM.2024.10066206
   
  
• Optimisation method for product design based on improved genetic algorithm  
  by Yonghong Shao 
  Abstract: To optimise the satisfaction of product design applications and reduce production costs, a product design optimisation method based on improved genetic algorithm is proposed in this study. This method is first based on principal component analysis to determine the product shape image. Then, based on this, a multi-objective optimisation model for product shape is constructed, and the objective function design is completed. Finally, a dissimilarity operator is introduced to improve the genetic algorithm. The improved genetic algorithm is applied to solve the objective function and achieve product shape design optimisation. The experiment was conducted on automobiles as the research object, and the experimental results showed that the application of the proposed method can improve user satisfaction with product shape and appearance design, enhance the strength of the car's external structure, reduce product production costs, and is superior to the comparative method. The application effect is good.
  Keywords: genetic algorithm; product design; appearance; multi-objective optimisation design.
  DOI: 10.1504/IJMTM.2025.10069871
   
  
• Abnormal node detection method for industrial internet of things based on dynamic trust evaluation algorithm  
  by Bin Cai 
  Abstract: In order to accurately detect abnormal nodes, an industrial internet of things (IIoT) abnormal node detection method based on dynamic trust evaluation algorithm is proposed. Dynamic trust evaluation considers direct trust, recommendation trust, and historical behavioural trust. This evaluation establishes the trustworthiness of each node in the IIoT. Features are extracted from nodes within the positioning range based on their correlations. These features help identify abnormal nodes accurately. Weighted tracking tasks analyse the trust level of each node and collected data to identify anomalies. Detection results are compared with actual outcomes. Test results show accurate node trust evaluation and consistent detection of abnormal nodes. Implementing this method enhances IIoT's security and reliability by efficiently identifying and responding to abnormal nodes.
  Keywords: dynamic trust evaluation algorithm; industrial internet of things; IIoT; abnormal node detection; node characteristics.
  DOI: 10.1504/IJMTM.2024.10066204
   
  
• Multi-objective scheduling of industrial intelligent manufacturing workshops based on variable neighbourhood genetic algorithm  
  by Junzhi Song 
  Abstract: Traditional multi-objective scheduling methods in industrial intelligent manufacturing workshops suffer from low efficiency and long scheduling minimisation time. To address this issue, a new multi-objective scheduling method of industrial intelligent manufacturing workshops based on variable neighbourhood genetic algorithm is designed. Industrial intelligent manufacturing workshop multi-objective parameters are selected, including completion time, completion process, machine load, and cost. A multi-objective scheduling function is built using the obtained parameters. The variable neighbourhood genetic algorithm is employed to generate neighbourhood sequences and initial solutions, and genetic operations such as encoding, mutation, and crossover are applied to form a new population, thereby achieving the solution of the objective function and realising optimal scheduling. The test results show that the algorithm proposed in this paper can improve the multi-objective scheduling efficiency of industrial intelligent manufacturing workshops and reduce the minimum scheduling time.
  Keywords: intelligent manufacturing workshop; variable neighbourhood genetic algorithm; multi-objective scheduling; parameters; objective function.
  DOI: 10.1504/IJMTM.2024.10066790
   
  
• Evaluation of industrial robot loading and unloading capability based on the combination of subjective and objective under cloud manufacturing  
  by Yan Guo 
  Abstract: The existing evaluation methods for loading and unloading capacity have the problem of low accuracy. Therefore, an evaluation method based on a combination of subjective and objective factors is proposed. Firstly, in the cloud manufacturing environment, collect data on the loading and unloading capabilities of industrial robots. Secondly, establish an evaluation system, determine the subjective weight of evaluation indices based on the improved analytic hierarchy process, and determine the objective weight of evaluation indices based on the entropy method. Finally, the evaluation indices are graded and combined with the weighted average method to obtain the evaluation results of the loading and unloading capacity of industrial robots. Experimental results have shown that the sensitivity of the evaluation results of this method always remains above 90%, and the highest consistency can reach 95%.
  Keywords: subjective and objective; industrial robot; loading and unloading capacity; evaluation system; improved analytic hierarchy process; entropy method.
  DOI: 10.1504/IJMTM.2024.10066201
   
  
• Grey improvement model for intelligent supply chain demand forecasting  
  by Xinghong Jia, Jun Wang, Tian Tian Ma, Qiong Wang 
  Abstract: This study helps to realise the balance between supply and demand of aquatic products and rational allocation of logistics resources. In previous studies, the prediction results of most models are not satisfactory for the cold chain logistics demand of aquatic products characterised by small-lot, low-quality uncertain data. In this paper, the traditional grey model and the grey BP neural network combination model are used to simulate and predict the demand for aquatic products cold chain logistics, and analysed and compared. The results show that compared with the traditional grey model, the grey BP neural network model has a reduced prediction error, an ideal ability to handle nonlinear systems and can take into account many influencing factors. Meanwhile, the robustness and generalisation ability of the model were verified by testing it on the dataset of similar scenarios. The method provides an innovative way for aquatic products cold chain logistics demand forecasting, which helps optimise the aquatic products supply chain in China and promotes the prosperous development of cold chain.
  Keywords: demand forecasting; intelligent supply chain; BP neural network model.
  DOI: 10.1504/IJMTM.2024.10065819
   
  
• The main contributions of digitalisation to servitisation  
  by Márcio Henrique Fronteli, Edson Pacheco Paladini 
  Abstract: Digital servitisation has aroused the interest of many researchers and managers. IoT, big data, and cloud computing are the most prominent technologies. This study sought to investigate the impact of other digital technologies (DTechs) on servitisation. This research is based on an exploratory-qualitative approach covering 146 published articles selected from the Scopus and Web of Science databases. We grouped the digital technologies that impacted servitisation positively. Our results were synthesised into four categories. These procedures allowed for building a framework that shows the contribution potential of digitisation as a success factor of servitisation, as well as competitive opportunities based on the combination of DTs. Digitisation is confirmed as the main driver for the development of digital-servitisation based business models. Our results aim to contribute to the industry in terms of establishing innovation strategies for business models.
  Keywords: servitisation; digitisation; digital technologies; DTechs; digital servitisation; DS.
  DOI: 10.1504/IJMTM.2024.10066063
   
  
• Analysing the process and quality evaluation of body-in-white part inspection methodology using augmented reality: an investigation  
  by Dhiviandran Chadaran, Ainul Akmar Mokhtar, Hilmi Hussin 
  Abstract: Automotive body manufacturing runs based on processes and each process requires a cycle time. Producing good quality products within the stipulated cycle time is necessary. Measuring the quality of finished product is also part of the cycle and consumes time. Standard average time has been investigated and discussed for a case study of 30 samples from a similar product. Datum point inspection method using checking fixtures is discussed and measuring points of the product are determined. Finding inconsistencies of process time and rejected product are discussed. Measuring the quality of the finished product is also part of the process. An average of 71.6% of time was used for datum measurement. The advancement of augmented reality in measuring the quality of manufactured products has been investigated and discovered that there is a 20% in reduction of datum measurement process time compared to conventional method. This research ought to be an interactive approach in quality inspection, replacing the need for hardcopy instruction manuals as well as time saving process in contrast to conventional method.
  Keywords: augmented reality; process time; datum point; quality; inspection.
  DOI: 10.1504/IJMTM.2024.10066812
   
  
• Fixture devices monitoring for machining condition optimisation aided by machine learning  
  by Felipe Alves de Oliveira Perroni, Ugo Ibusuki, Eduardo de Senzi Zancul, Klaus Schützer, Cláudio Nogueira de Meneses, Thiago Cannabrava de Sousa 
  Abstract: This paper focuses on applying recent digitisation technologies for machining process improvement based on fixture device monitoring. Industry 4.0 technologies support smart monitoring of manufacturing processes, enabling semi-autonomous tool process parameters adjustment, reducing human-machine interactions, resulting in more accurate process improvements. The paper aims to present the results of a project development and validation of a machining conditioning monitoring system, combining measures conducted directly in the spindle unit and fixture devices. The machining condition monitoring system, aided by a machine learning algorithm, uses vibration data to determine the tool's maximum wear. The project, a collaborative effort by two universities, was designed for practical application and rigorously tested in a real-world operational environment at an automotive company.
  Keywords: device monitoring; condition monitoring system; process optimisation; machine learning.
  DOI: 10.1504/IJMTM.2025.10068059
   
  
• Challenges towards manufacturing transformation to Industry 4.0  
  by Choudhury Abul Anam Rashed, Mst. Nasima Bagum, Syeda Kumrun Nahar, Md. Mehedi Hasan Kibria 
  Abstract: To cope with the rapid growth of technology, the manufacturing sector needs to incorporate updated technology and innovations. Several obstacles need to be addressed before the implementation of the updated technology. The research objectives are to identify the challenges hindering the transformation towards I4.0 and prioritise the challenges. Twelve challenges are determined by an extensive literature review and consultation with relevant experts. A semi-structured questionnaire-based survey was performed in the manufacturing sector. Based on the obtained data from 125 respondents, statistical analysis was performed using Microsoft Excel and SPSS 25. Based on the results, a conceptual model was developed and tested with PLS-SEM 4.0. The results showed that lack of sufficient capital, high expenditure in implementation, legislative problems, insufficient technological knowledge, lack of proper structure, deficiency of skilled workforce, cheap labour, etc., are the major challenges in implementing cutting-edge technology and innovations in the manufacturing sector.
  Keywords: challenges; cutting edge technology; Industry 4.0; I4.0; manufacturing transformation; digital and e-manufacturing.
  DOI: 10.1504/IJMTM.2025.10068054
   
  
• Optimising aesthetic automotive component manufacturing: comparative analysis of injection pressure in injection compression moulding vs. injection moulding  
  by Yousef Amer, Praveen Kelath, Ashraf Zaghwan 
  Abstract: This study investigates the injection pressure differences between injection moulding (IM) and injection compression moulding (ICM) processes for manufacturing aesthetic automotive interior components. Using Autodesk Moldflow® software, we conducted a simulation-based analysis of ICM injection pressure for various specimens with wall thicknesses ranging from 1 mm to 4 mm and flow lengths from 50 mm to 300 mm, using PC Lexan LS1 material. The results show that the pressure disparity between IM and ICM increases with thicker walls and shorter flow lengths, ranging from 30% to 51%. Correlation analysis indicates a strong positive relationship (0.999) between IM and ICM, which is supported by regression analysis. Physical trials validate the simulation outcomes. Future research should address parameters such as material selection and process constraints. The implementation of ICM could enhance manufacturing efficiency for aesthetic automotive components, offering cost reductions and new business opportunities.
  Keywords: injection compression moulding; ICM; simulation; injection pressure; Moldflow®; Radome badges; automotive; injection moulding.
  DOI: 10.1504/IJMTM.2025.10068314
   
  

Special Issue on: Big Data and AI for Process Innovation in the Industry 4.0 Era

• Research on total amount prediction of import and export trade data based on combined predicting model  
  by Jianxin Chen, Xiaoke Zhao 
  Abstract: In order to overcome the problems of low index significance, low prediction efficiency and low prediction accuracy in the process of prediction of import and export trade data, a new research method for total amount prediction of import and export trade data based on combined prediction model. Combine neural network prediction method and support vector machine prediction method to build a combined prediction model. Through the back propagation process, it can reduce the error between the expected and the actual output, and modify the network threshold and weight, so as to realize the classification of samples in high-dimensional space in support vector machine, and the two methods are combined to complete the prediction of total import and export trade data. The experimental results show that the significance of the proposed method is close to 100%, the prediction time is within 0.5 min, and the prediction accuracy is more than 90%.
  Keywords: Combination predicting model; Import and export trade; Data predicting; Influencing factors.