Manufacturing Systems Research Articles

Harmony search algorithm to enhance approach to permutation flow shop scheduling problem

The permutation flow-shop scheduling problem (PFSP) is one of the widely analysed and investigated problems within the general field of scheduling, as its major focus is on the allocation and sequencing of a set of jobs across a set of machines in order to minimize the makespan or satisfy other criteria. This paper further generalizes the problem to the distributed permutation flow-shop scheduling problem (DPFSP), namely in a manufacturing system with multiple factories, where every factory employs identical machines; with the objective of achieving the least makespan at the worst factory in terms of processing time. We resolve the issue through a Harmony Search Algorithm (HSA), a metaheuristic model developed from the musical harmonisation concept, together with constraint programming techniques, including interval variables and non-adjacent constraints. The problemsolving algorithm incorporates a lower bound estimation heuristic for efficiently directing the search in the right possible solution zone. Performance evaluation on both the small benchmark and the large benchmark data set showed the ability of the HSA to perform the different assignment in various problem scenarios that include the different number of jobs, machines and factories to support them. Comparisons with the best-known values established the performance of the HSA algorithm in identifying high quality solutions for the PFSP in less computation time.

Optimization strategy of computer numerical control machining process parameters in biomanufacturing mold

With the rapid development of biomanufacturing technology in the medical and pharmaceutical fields, the demand for high-precision and high-quality molds has surged. When Computer numerical control (CNC) machining biomanufacturing molds, the optimization of process parameters becomes the key to improve efficiency and quality. The purpose of this study is to explore the optimization strategy of CNC machining process parameters to achieve the best surface quality, dimensional accuracy and machining efficiency. Through literature review, the spindle speed, feed speed and cutting depth are selected as the key parameters, and the multi-objective optimization model is constructed by response surface method, which is solved by genetic algorithm. The experiment shows that the process parameters of CNC system in mold manufacturing are cutting speed 100 (m/min), feed rate 0.2 (mm/rev) and cutting depth 0.5 (mm), which will effectively reduce the manufacturing cost, and effectively control the alarm times within 35 times in different processing equipment, greatly reduce the risk. The optimization strategy can significantly improve the surface quality and productivity of the mold and reduce the cost. The comparative analysis verifies the effectiveness of the method, which provides new theoretical and technical support for CNC machining in the field of biomanufacturing.

A knowledge empowered graph learning feature selection method based on variation propagation effect representation and analysis for human-centric manufacturing systems

As the construction goals of manufacturing systems shift from Industry 4.0 to Industry 5.0, the development goals of manufacturing systems have also shifted from technology driven to human-centric. Feature Selection (FS) of manufacturing systems plays an important role in helping human control and upgrade manufacturing system quality. However, due to the propagation of variations in manufacturing systems, traditional FS methods cannot accurately select the key features that have an important disturbance to quality indicator. In this paper, a process knowledge-enabled FS method is proposed to obtain key features of quality indictor (QI) that would cause bias of prediction model accuracy. Firstly, a process representation learning algorithm embedded in the process knowledge graph is proposed, which represents the manufacturing variation propagation process during the manufacturing process. Secondly, a feature importance evaluation algorithm based on disturbance intensity judgment rules is proposed to evaluate the importance of process features. Finally, the top k important features are selected as key features based on feature importance ranking. Experimental results demonstrate the proposed method outperforms state-of-art and classic methods in four evaluated indicators. Moreover, the four indicators of MSE, MAE, RMSE, and R 2 have respectively increased by 18%, 16%, 18%, and 33% with 7 features compared to the cutting-edge method.

An Integrated Stochastic Optimization and Simulation Approach to SERU vs. Assembly Line Manufacturing Systems

This research compares SERU manufacturing systems to traditional assembly lines, focusing on the impact of uncertainty in task processing time on production output. The study considers worker skill levels and team identity, using a stochastic mixed integer linear programming approach to model uncertainty and optimize workforce allocation. Discrete event simulation is then integrated to evaluate performance using five key performance indicators (KPIs). Results show that SERU systems outperform traditional lines in terms of throughput when uncertainty is considered. The integrated approach provides more reliable performance data than deterministic optimization alone. The study also highlights the advantages of SERU systems when worker skill levels and team identity are factored in. This research fills a gap in the literature by proposing a stochastic optimization approach that considers uncertainty and worker skill levels, and by integrating stochastic optimization with simulation for comprehensive analysis. This approach provides valuable guidance for production managers in optimizing production systems.

Effect of different corrective force directions applied by spinal orthoses on the patients with adolescent idiopathic scoliosis.

Spinal orthoses are commonly prescribed for adolescent idiopathic scoliosis (AIS), yet their three-dimensional correction was not fully understood. The amount of deformity control largely depends on the corrective forces applied, which remain empirically based due to a lack of consensus on optimal force application. This study investigated the effects of different corrective force directions exerted by spinal orthoses on patients with AIS. A retrospective analysis was conducted on 78 subjects. The trunk was segmented into four quadrants using coronal and sagittal planes from a top-down perspective. Each left or right posterolateral quadrant (with 90°) was further subdivided into zones 1-4, from the sagittal to coronal planes. Based on the zone where the resultant corrective force direction fell, the subjects were categorized into Group 1 (zone 1), Group 2 (zone 2), Group 3 (zone 3), or Group 4 (zone 4). The direction of the corrective force was estimated using modified models of the subjects' bodies, designed through a computer-aided design and manufacturing system integral to the orthosis fabrication process. The effects of corrective forces in different zones on scoliotic spine were assessed. Among the subjects, 3 were in Group 1, 17 in Group 2, 52 in Group 3, and 6 in Group 4. Due to the limited number of subjects, data from Groups 1 and 4 were not analysed. Groups 2 and 3 showed significant reductions in Cobb angle in the coronal plane and plane of maximum curvature (PMC) following orthosis fitting (p < 0.05). Group 2 displayed a significant decrease > 5º in thoracic kyphosis (p < 0.05). Both Groups 2 and 3 exhibited significant reductions in lumbar lordosis. PMC orientation remained unchanged over time (p > 0.05) but was notably higher in Group 2 after orthosis fitting (p < 0.05). Corrective forces applied by spinal orthoses in zones 2 and 3 effectively controlled lateral curve progression. Notably, only forces in zone 3 neither significantly reduced thoracic kyphosis nor exacerbated the deviation of scoliotic spine from the sagittal plane. Further research is needed to validate and expand upon these results.

Literacy Deep Reinforcement Learning-Based Federated Digital Twin Scheduling for the Software-Defined Factory

As user requirements become increasingly complex, the demand for product personalization is growing, but traditional hardware-centric production relies on fixed procedures that lack the flexibility to support diverse requirements. Although bespoke manufacturing has been introduced, it provides users with only a few standardized options, limiting its ability to meet a wide range of needs. To address this issue, a new manufacturing concept called the software-defined factory has emerged. It is an autonomous manufacturing system that provides reconfigurable manufacturing services to produce tailored products. Reinforcement learning has been suggested for flexible scheduling to satisfy user requirements. However, fixed rule-based methods struggle to accommodate conflicting needs. This study proposes a novel federated digital twin scheduling that combines large language models and deep reinforcement learning algorithms to meet diverse user requirements in the software-defined factory. The large language model-based literacy module analyzes requirements in natural language and assigns weights to digital twin attributes to achieve highly relevant KPIs, which are used to guide scheduling decisions. The deep reinforcement learning-based scheduling module optimizes scheduling by selecting the job and machine with the maximum reward. Different types of user requirements, such as reducing manufacturing costs and improving productivity, are input and evaluated by comparing the flow-shop scheduling with job-shop scheduling based on reinforcement learning. Experimental results indicate that in requirement case 1 (the manufacturing cost), the proposed method outperforms flow-shop scheduling by up to 14.9% and job-shop scheduling by 5.6%. For requirement case 2 (productivity), it exceeds the flow-shop method by up to 13.4% and the job-shop baseline by 7.2%. The results confirm that the literacy DRL scheduling proposed in this paper can handle the individual characteristics of requirements.

Evaluation of Performance Improvement Rate of Plastic Production System Using ARENA: A Case Study of Phoenix Plastic Services

Production improvement has become essential to all industrial activity because of the fierce competition among today's production systems and organizations and the unquenchable customer demand. The shorter product life cycle has significantly increased the demand for prompt reactions to increase the productivity and efficiency of these industrial systems. This study examined the evaluation of performance improvement rate of plastic production system using ARENA. The report provided by the plastics industry was used in the study to analyze and assess the rate of performance improvement of the plastic manufacturing system. The location of the bottleneck was determined by the research following a thorough analysis of the plastic company's data, which included information on all manufacturing lines and procedures. The research employed Arena to assess and compute the rate of improvement in system performance while accounting for the material transporting process throughout the production line. The conveyor velocity maintains a lock at 75m/min, despite the company's report stating that the transports run at 30m/min. The optimized and unoptimized processes when obtained from a finished recycling process running for 1000 working hours, indicate that the conveyor process had 1045 and 1027 entity input and output, respectively, and the transporter process had 953 and 929 entities input and output respectively. The remaining number left when considering the number that enters the system with the number that leaves the system went to waste, resulting from the sorting and demagnetization process. The introduction of the conveyor brings 10.549% in the production rate and 50% decrease on expenses spent in labor. Through the conveyor system's speed control factor, which is an automated procedure, the system's percentage increment may be further raised. By raising the conveyor system's speed, more items will be produced. Conveyor system installation free up more space for additional production-related equipment, increasing products formed and the company's profit. The cost of purchasing and installing the conveyor will be covered by the excess profit.

7-axis synchronization-integrated on-the-fly laser texturing system of freeform surface: design and development

Abstract While laser surface texturing (LST) is a promising manufacturing technique for surface functionalization, simultaneously realizing high precision and high efficiency in the LST of complex curved surface is challenging, due to continuously varied geometries of laser-matter incidence. In the present work, we propose a novel manufacturing system of 7-axis on-the-fly LST for complex curved surface, based on the integrated synchronization of 5-axis linkage motion platform with 2-axis galvanometer. Specifically, the algorithm for decomposing spatial texture trajectory on curved surface into low-frequency and high-frequency parts is established, based on which the kinematic model of synchronized 7-axis system is developed to derive the motion of each axis in both 5-axis linkage motion platform and 2-axis galvanometer simultaneously. Subsequently, the synchronized 7-axis LST system is experimentally realized, including the setup of mechanical stages integrated with optical path, the configuration of numerical control unit, and the development of processing software. Finally, case study of 7-axis on-the-fly LST of freeform aluminum surface is performed, and the advantages in terms of processing efficiency and texturing accuracy over 5-axis linkage LST are demonstrated. The correlation of reduced following errors between mechanical stages with the promoted performance of curved surface texturing by the 7-axis on-the-fly LST is further analyzed. Current work provides a feasible solution for establishing the manufacturing system for high performance LST of complex curved surface.

Digital Twin for Flexible Manufacturing Systems and Optimization Through Simulation: A Case Study

Digital Twin for Flexible Manufacturing Systems and Optimization Through Simulation: A Case Study

Advanced Machine Learning Algorithms for Predictive Maintenance in Industrial Manufacturing Systems

In industrial manufacturing systems, predictive maintenance is the process of increasing the rate of productivity and minimizing the time that equipment takes to be out of order through early identification of the equipment that is likely to fail. The main focus of this research is to analyze the possibility of using modern approaches in machine learning to enhance the methods of predictive maintenance. We compare multiple current approaches of deep learning, ensemble methods, and anomaly detection to determine their effectiveness in predicting the maintenance requirements utilizing the sensor and operational data. With the help of a large amount of data, we consider the results of the work of each algorithm for the assessment of the predictive accuracy, the ranking of features, and the detection of anomalies. The findings highlight disparities in the effectiveness of the algorithms in terms of accuracy, precision, and recall, and the deep learning models’ ability to grasp intricate and anomalous patterns. The performance of the maintenance predictions is depicted by the use of visualizations of the performance metrics and feature importance. It also describes the drawbacks of the existing models, such as the problem of data quality and generalization. The study draws attention to the possibility of applying sophisticated machine-learning methods to improve the effectiveness of PM in industrial environments. Possible directions of future research are to enhance the generalization ability of the developed models and to expand the usage of modern trends in the machine learning field to enhance maintenance strategies.

Thermal environment simulation and product visual design of flexible manufacturing system based on robot collaboration

Thermal environment simulation and product visual design of flexible manufacturing system based on robot collaboration

Bandwidth-aware fast inverse lithography technology using Nesterov accelerated gradient

Inverse lithography technology (ILT) is a leading-edge method for improving the resolution and image fidelity of optical lithography systems in semiconductor manufacturing. However, the massive computational complexity of ILT presents the inherent runtime bottleneck, which hinders its application to the large-scale lithography layouts. This paper innovates a fast ILT method by reducing both of the inherent algorithmic complexity and the required iteration number. Based on the diffraction-limited nature of optical lithography system, a bandwidth-aware acceleration approach is applied to reduce the calculation complexities of the forward imaging model and inverse gradient computation in each ILT iteration. In addition, a carefully designed algorithm based on the Nesterov accelerated gradient (NAG) is developed to achieve nearly quadratic convergence rate, thereby reducing the total number of iterations required to obtain the optimal solution. Numerical experiments show that the proposed method can improve the speed by hundreds of times over the traditional gradient-based ILT algorithms without sacrificing accuracy.

A broadband hyperspectral image sensor with high spatio-temporal resolution

Hyperspectral imaging provides high-dimensional spatial–temporal–spectral information showing intrinsic matter characteristics1–5. Here we report an on-chip computational hyperspectral imaging framework with high spatial and temporal resolution. By integrating different broadband modulation materials on the image sensor chip, the target spectral information is non-uniformly and intrinsically coupled to each pixel with high light throughput. Using intelligent reconstruction algorithms, multi-channel images can be recovered from each frame, realizing real-time hyperspectral imaging. Following this framework, we fabricated a broadband visible–near-infrared (400–1,700 nm) hyperspectral image sensor using photolithography, with an average light throughput of 74.8% and 96 wavelength channels. The demonstrated resolution is 1,024 × 1,024 pixels at 124 fps. We demonstrated its wide applications, including chlorophyll and sugar quantification for intelligent agriculture, blood oxygen and water quality monitoring for human health, textile classification and apple bruise detection for industrial automation, and remote lunar detection for astronomy. The integrated hyperspectral image sensor weighs only tens of grams and can be assembled on various resource-limited platforms or equipped with off-the-shelf optical systems. The technique transforms the challenge of high-dimensional imaging from a high-cost manufacturing and cumbersome system to one that is solvable through on-chip compression and agile computation.

Artificial Intelligence Techniques for Sustainable Reconfigurable Manufacturing Systems: An AI-Powered Decision-Making Application Using Large Language Models

Artificial intelligence (AI) offers a promising avenue for developing sustainable reconfigurable manufacturing systems. Although there has been significant progress in these research areas, there seem to be no studies devoted to exploring and evaluating AI techniques for such systems. To address this gap, the current study aims to present a deliberation on the subject matter, with a particular focus on assessing AI techniques. For this purpose, an AI-enabled methodological approach is developed in Python, integrating fuzzy logic to effectively navigate the uncertainties inherent in evaluating the performance of techniques. The incorporation of sensitivity analysis further enables a thorough evaluation of how input variations impact decision-making outcomes. To conduct the assessment, this study provides an AI-powered decision-making application using large language models in the field of natural language processing, which has emerged as an influential branch of artificial intelligence. The findings reveal that machine learning and big data analytics as well as fuzzy logic and programming stand out as the most promising AI techniques for sustainable reconfigurable manufacturing systems. The application confirms that using fuzzy logic programming in Python as the computational foundation significantly enhances precision, efficiency, and execution time, offering critical insights that enable more timely and informed decision-making in the field. Thus, this study not only addresses a critical gap in the literature but also offers an AI-driven approach to support complex decision-making processes.

Deep Learning Solution for Quality Control in a Die Casting Process

Industry 4.0 aims for a digital transformation of manufacturing and production systems, producing what is known as smart factories, where information coming from Cyber-Physical Systems (core elements in Industry 4.0) will be used in all the manufacturing stages to improve productivity. Cyber-physical systems through their control and sensor systems, provide a global view of the process, and generate large amounts of data that can be used for instance to produce datadriven models of the processes. However, having data is not enough, we must be able to store, visualize and analyze them, and to integrate induced knowledge in the whole production process. In this work, we present a solution to automate the quality control process of manufactured parts through image analysis. In particular, we present a Deep Learning solution to detect defects in manufactured parts from thermographic images of a die casting machine at an aluminum foundry.

A framework for data-driven decision making in advanced manufacturing systems: Development and implementation

Integration of sophisticated technologies such as Internet of Things, cyber physical systems and big data analytics have revolutionized the advanced manufacturing systems (AMS). However, implementation of data-driven decision making in AMS still remains challenging due to data heterogeneity, real-time processing demands, and integration complexities. This paper overcomes this challenge by presenting a novel framework for adoption of DDDM in AMS to enhance its decision-making capabilities. This framework consists of six stages: manufacturing stage, sensing stage, data stage, knowledge stage, decision stage, and application stage. The proposed framework leverages big data analytics to extract actionable insights from diverse datasets, integrates CPS to create a seamless interaction between physical and digital systems, and employs IoT technologies for real-time data acquisition and monitoring. The framework is validated through a comprehensive case study involving a CNC milling machine dataset, demonstrating significant improvements in operational efficiency, decision accuracy, and response time. The case study involves detailed data collection steps, preprocessing, and analysis, showcasing the framework’s practical implementation and effectiveness. The results show that the proposed framework addresses existing challenges and provides a scalable solution for DDDM implementation in AMS.

A Three-Level Agent-Based Framework For Resource Allocation Optimization In Flexible Manufacturing Systems

A Three-Level Agent-Based Framework For Resource Allocation Optimization In Flexible Manufacturing Systems

Coupling Coordination and Data Management for Additive Manufacturing Systems Based on Smart Logistics

Additive Manufacturing (AM) has rapidly advanced due to its benefits in reducing material consumption and resource requirements, offering significant opportunities for energy-efficient and environmentally friendly production. As manufacturing technologies evolve, there is growing interest in smart manufacturing, prompting both academia and industry to explore ways to enhance efficiency and sustainability. Effective logistics management plays a crucial role in this context, requiring precise data prediction and optimization. This article introduces a Smart Logistics service to foster dynamic coordination within the smart logistics ecosystem. The first step is to integrate smart logistics components that can communicate effectively and provide specific value-added services. This integration aims to support contemporary industrial and production environments by enhancing decision-making models. The second step involves applying the Coupling Coordination model to assess the development of logistics in conjunction with broader economic growth. This model helps in constructing a high-quality development index system for logistics, which is essential for evaluating the efficiency of logistics operations. The third step is to evaluate the coordination between the automotive, digitalization, and logistics sectors. This assessment provides insights into the overall development levels of cities and highlights the significant impact on sustainable growth within the automotive industry. The final step includes analyzing the progress of coupling coordination in Indian provinces, identifying the transition from minor imbalances to primary coordination, and forecasting that strong coordination will be achieved by 2025. This analysis underscores the potential for mutual growth and cooperation by elevating the logistics sector’s standards and strengthening inter-industry relationships.

Heterogeneous graph neural network for modeling intelligent manufacturing systems

Abstract Currently, manufacturing systems have become more and more complex, often involving multiple machines, systems and processes to produce workpieces. In order to facilitate comprehensive analysis and control of manufacturing processes, the integration of connections between machine level, system level, and process level in manufacturing process modeling is needed. However, traditional graph deep learning models are unable to take into account the heterogeneity of different machines in the system when modeling manufacturing systems. To address this problem, this paper proposes a new approach: modeling manufacturing systems using the heterogeneous graph neural network sample and aggregate algorithm based on cutting-edge Bayesian neural networks and graph deep learning. This method considers the connection between different manufacturing system levels, treats machine operations as nodes, and connects different nodes through material flow and operational similarity. The effectiveness of the method is demonstrated through its application to model an aero-engine blade production line. Extensive numerical experiments show that the proposed graph modeling method is effective in expressing the heterogeneity of different machines and multi-level manufacturing processes. By integrating machine heterogeneity into the modeling of a manufacturing system, it not only facilitates comprehensive analysis and control of the manufacturing process, but also lays the foundation for cost savings and productivity improvements in the manufacturing system.

Using Business Process Model and Notation 2.0 to Deploy Cobots in a Manufacturing System – Case Study

Using Business Process Model and Notation 2.0 to Deploy Cobots in a Manufacturing System – Case Study