Optimization Of Manufacturing Systems Research Articles

On formal modeling, analysis and optimization of reconfigurable manufacturing systems

ABSTRACT This paper deals with the formal specification and multi-objective optimization of reconfigurable manufacturing systems (RMSs). RMSs are characterized by their dynamic structure, crucial for responding to functional variations, adjusting production capacity and overcoming operational dysfuntions promptly and cos-effectively. The effective utilization of this dynamic capability depends on thorough study and optimization of RMS configurations. To tackle this challenge, a novel formalism called genetic reconfigurable object nets (Gen-RONs) is introduced. Gen-RONs formalism integrates the modeling, verification and reconfiguration capabilities of reconfigurable object nets with advanced multi-objective techniques from genetic algorithms. Within Gen-RONs, Petri nets serve to: (i) encode RMS configurations, (ii) manage RMS scheduling and (iii) employ graph transformation theory rules as genetic algorithm operators for real-time system reconfiguration. Thus, Gen-RONs formalism provides a robust framework for optimizing RMSs using genetic algorithms. To ensure deadlock-free RMS configurations, Gen-RONs incorporate a binary tree-based technique. Furthermore, Taguchi’s method is employed to fine-tune genetic algorithm parameters. The contribution of this paper is demonstrated through a case study involving an RMS and the widely used genetic algorithm NSGA-II. Significant gains in terms of the number of solutions (i.e. configurations) and the criteria values are achieved.

Learning-based production, maintenance, and quality optimization in smart manufacturing systems: A literature review and trends

With the introduction of manufacturing paradigms, including Industry 4.0, production research has shifted its focus to enabling intelligent manufacturing systems within industrial environments. These systems can efficiently schedule and control processes and operations using artificial intelligence methods, including machine learning and deep learning. Since 1995, relevant literature has presented several examples of such implementations, addressing topics, for example equipment fault diagnosis and quality inspections. To this end, the present paper strives to present a state-of-the-art review of the learning-based scheduling and control frameworks, which are exploited in the production research. The review is limited to the relevant research between the years 1995 and 2024, surveying approaches in the domains of manufacturing, maintenance, and quality control. To this end, the paper follows a meta-analysis method for the selection and evaluation of relevant research articles. Moreover, research questions are formulated to analyze the obtained findings and seek out insights on aspects of the relevant research, including the inclusion of decision-making models and dissemination of literature. The provided answers, among others, reveal trends and limitations of the state-of-the art research in relation to learning-based scheduling and control.

Artificial neural networks-based modelling of effects of cryogenic electrode treatment, nano-powder, and surfactant-mixed dielectrics on wear performance and dimensional errors on superalloy machining

In the present era dominated by Industry 4.0, the digital transformation and intelligent management of industrial systems is significantly important to enhance efficiency, quality, and the effective use of resources. This underscores the need for a framework that goes beyond merely boosting productivity and work quality, aiming for a net-zero impact from industrial activities. This research introduces a comprehensive and adaptable analytical framework intended to bridge existing gaps in research and technology within the manufacturing sector. It encompasses the essential stages of using artificial intelligence (AI) for modelling and optimizing manufacturing systems. The effectiveness of the proposed AI framework is evaluated through a case study on electric discharge machining (EDM), concentrating on optimizing the electrode wear rate (EWR) and overcut (OC) for aerospace alloy Inconel 617. Utilizing a comprehensive design of experiments, the process modelling through an artificial neural network (ANN) is carried out, accompanied by careful fine-tuning of hyperparameters throughout the training process. The trained models are further assessed using an external validation (Valext) dataset. The results of the sensitivity analysis indicated that the surfactant concentration (Sc) has the highest level of influence, accounting for 52.41% of the observed influence on the EWR, followed by the powder concentration (Cp) with a contribution of 33.14%, and the treatment variable with a contribution of 14.43%. Regarding OC, Sc holds the highest percentage significance at 72.67%, followed by Cp at 21.25%, and treatment at 6.06%. Additionally, parametric optimization (PO) shows that EWR and OC overcome experimental data by 47.05% and 85.00%, respectively, showcasing successful performance optimization with potential applications across diverse manufacturing systems.

A developed products’ families commonality Index based on variants’ similarity.

Abstract Commonality indices used to assess the shared features of product families are crucial tools for benchmarking and redesigning these families. They also play a significant role in optimizing manufacturing systems by adding or removing components/modules to product platforms during delayed customization stages. Although several indices have been developed by researchers to measure commonality across product family variants, these indices are often only suitable for specific applications with specific configurations. In the present research, a new commonality index has been developed based on the similarity features of each pair of variants within a product family. The developed index is useful for clustering family variants into subfamilies, each with high components’ sharing ratio, facilitating the design of necessary product platform/s for delayed customization manufacturing systems. The results of applying this developed index to determine commonality across product family variants were compared with those obtained from several known commonality indices. The new index proved to be effective and sensitive in distinguishing between the commonalities of different product families. Additionally, the index was found to be effective in categorizing products into homogeneous families, grouping variants that share certain similarities and commonality features.

Comparing sequential and integrated models in Reconfigurable Manufacturing Systems optimization

Comparing sequential and integrated models in Reconfigurable Manufacturing Systems optimization

Bottleneck alleviation and scheduling optimization of flexible manufacturing system based on information-energy flow model

The identification and alleviation of bottleneck machines in manufacturing systems are of paramount importance for optimizing production decision-making in enterprises. Extensive research has been conducted by numerous scholars on the identification of bottleneck machines; however, there is a relative scarcity of research, particularly in the context of flexible manufacturing systems, regarding how to effectively alleviate the identified bottlenecks. In this paper, a novel hyper-heuristic evolutionary scheduling algorithm with a bottleneck alleviation strategy based on the information-energy flow model (HESA-BA-IEF) is proposed for training dispatching rules and optimizing decision-making in flexible job shops with bottleneck machines. HESA-BA-IEF constructs an information-energy flow model for flexible job shops based on complex networks. Through this model, dynamic changes in machine processing status and energy consumption during the scheduling process can be effectively simulated, facilitating the accurate identification of bottleneck machines. Moreover, the algorithm adopts the genetic programming hyper-heuristics and introduces a scheduling mechanism considering the alleviation of bottleneck machines to optimize the makespan and total energy consumption, while simultaneously alleviating bottlenecks. Experiments show that HESA-BA-IEF generates dispatching rules that optimize scheduling and alleviate bottlenecks simultaneously. Furthermore, statistical analysis reveals a 7.71% reduction in bottleneck metrics of production line due to 30.40% scheduling rounds with bottleneck alleviation mechanism in effect.

Evaluating the role of inkjet printing in perovskite solar modules manufacturing using mathematical modeling

Enormous gains in efficiency over the last decade have pushed perovskite solar cells towards the cusp of entering into the mass production phase. Given the solution-phase processability and low energy intensity of several techniques, many techniques have been explored to manufacture these cells and modules. Among them, inkjet printing has shown potential for fabricating all the active layers while also achieving higher efficiencies along with the benefits of lower cost and high material efficiency. In this article, we focus on the application of mathematical modeling of the process and understanding the impacts of different decision variables on key performance indicators at various levels. In particular, the screening of decision variables space and their effect on final key performance indicators related to the complete solar module are discussed, highlighting the effectiveness and limitations of using such mechanistic models for manufacturing system optimization.

A machine learning framework for explainable knowledge mining and production, maintenance, and quality control optimization in flexible circular manufacturing systems

In the present study, we employed multiple decision tree algorithms to categorize cases and reflect the most efficient policies constructed by a reinforcement learning algorithm. These approaches treated a complex production, maintenance, and quality control optimization problem within a degrading manufacturing and remanufacturing system. The decision trees’ nodes represent the independent variables, while the trees’ leaves represent the set of function values. The reinforcement learning method revealed all optimization parameters and best policies, which were employed as the training sample for the tree algorithms. After constructing every decision tree, each resulting decision rule was used to solve the optimization problem, and its performance was assessed. Additionally, we performed a sensitivity analysis to determine if the pruning level impacts the objective function value and, generally, the effectiveness of the proposed approach.

A bi-criterion sequence-dependent scheduling problem with order deliveries.

The manufacturing sector faces unprecedented challenges, including intense competition, a surge in product varieties, heightened customization demands, and shorter product life cycles. These challenges underscore the critical need to optimize manufacturing systems. Among the most enduring and complex challenges within this domain is production scheduling. In practical scenarios, setup time is whenever a machine transitions from processing one product to another. Job scheduling with setup times or associated costs has garnered significant attention in both manufacturing and service environments, prompting extensive research efforts. While previous studies on customer order scheduling primarily focused on orders or jobs to be processed across multiple machines, they often overlooked the crucial factor of setup time. This study addresses a sequence-dependent bi-criterion scheduling problem, incorporating order delivery considerations. The primary objective is to minimize the linear combination of the makespan and the sum of weighted completion times of each order. To tackle this intricate challenge, we propose pertinent dominance rules and a lower bound, which are integral components of a branch-and-bound methodology employed to obtain an exact solution. Additionally, we introduce a heuristic approach tailored to the problem's unique characteristics, along with three refined variants designed to yield high-quality approximate solutions. Subsequently, these three refined approaches serve as seeds to generate three distinct populations or chromosomes, each independently employed in a genetic algorithm to yield a robust approximate solution. Ultimately, we meticulously assess the efficacy of each proposed algorithm through comprehensive simulation trials.

Enhancing Data Security Resilience in AI-Driven Digital Transformation: Exploring Industry Challenges and Solutions Through ALCOA+ Principles.

The Medicines and Healthcare Products Regulatory Agency (MHRA) defines data integrity as the maintenance of accuracy, consistency, and completeness of data over time. Recently, "artificial intelligence" has become prevalent across industries, education, culture,and technology, denoting systems that mimic human intelligence and critical thinking using computers and related technologies. This article examines the construction of a robust artificial intelligence (AI) system and the incorporation of ALCOA+ principles for data validation, with a specific focus on enhancing data certainty and security. This study was carried out through a comprehensive review of various Scopus-indexed literature over the past decade. Results and Discussion: AI has been widely applied in Manufacturing System Optimization, involving organizing production systems, including machines, robots, conveyors, and related operations like maintenance and material handling. Moreover, it's used for Process Monitoring, Diagnostics, and Prognostics in medicine, as well as supervision and regulation in industries. Yet, it's not immune to shortcomings, which could result in system biases and jeopardize data security. This article explores the creation of a robust AI system, implementing ALCOA+ for data validation in AI-Driven Digital Transformation to improve data certainty and security in industries. It involves systematically recording AI system activities, ensuring database validity, sustaining data recording practices, regularly updating records, ensuring authenticity and completeness, and facilitating data accessibility for review and audits. As AI integration in education advances, there's a crucial need for oversight to maintain data integrity in these systems.

Optimizing Perishable and Non-Perishable Product Assignment to Packaging Lines in a Sustainable Manufacturing System: An AUGMECON2VIKOR Algorithm

Identifying appropriate manufacturing systems for products can be considered a pivotal manufacturing task contributing to the optimization of operational and planning activities. It has gained importance in the food industry due to the distinct constraints and considerations posed by perishable and non-perishable items in this problem. Hence, this study proposes a new mathematical model - according to knowledge discovery as well as an assignment model to optimize manufacturing systems for perishable, non-perishable, and hybrid products tailored to meet their unique characteristics. In the presented model, three objective functions are taken into account: (1) minimizing production costs by assigning the products to the right set of manufacturing systems, (2) maximizing the product quality by assigning the products to the systems, and (3) minimizing total CO2 emissions of the machines. A numerical example is utilized to evaluate the performance of AUGMECON2VIKOR compared to AUGMECON2. The results show that AUGMECON2VIKOR obtains superior Pareto solutions across all objective functions. Furthermore, the sensitivity analysis explores the positive green impacts, influencing both cost and quality.

Optimizing smart manufacturing systems using digital twin

Presented paper investigates the application of digital twins for the optimisation of intelligent manufacturing systems and focuses on the comparison between simulation modelling results and real-world production conditions. A digital twin was created in the Simio software environment using a data-driven simulation model derived from a real-world production system. Running the digital twin in real time, which was displayed graphically, facilitated the analysis of key parameters, including the number of finished products, average flow time, workstation utilization and product quality. The discrepancies were attributed to the use of random distributions of input data in the dynamic digital twin, as opposed to the long-term measurements and averages in the real-world system. Despite the limitations in the case study, the results underline the financial justification and predictive capabilities of digital twins for optimising production systems. Real-time operation enables continuous evaluation and tracking of parameters and offers high benefits for intelligent production systems. The study emphasises the importance of accurate selection of input data and warns that even small deviations can lead to inaccurate results. Finally, the paper high-lights the role of digital twins in optimising production systems and argues for careful consideration of input data. It highlights the importance of analysing real-world production systems and creating efficient simulation models as a basis for digital twin solutions. The results encourage extending the research to different types of production, from job shop to mass production, in order to obtain a comprehensive optimisation perspective.

Optimization of Cellular Reconfigurable Manufacturing System under Constraints of Machinery Layout

Optimization of Cellular Reconfigurable Manufacturing System under Constraints of Machinery Layout

Evaluation model and algorithm optimization of intelligent manufacturing system on the basis of BP neural network

Intelligent manufacturing is a key direction for the development of the manufacturing industry. Since the level of intelligent manufacturing varies among enterprises, building a scientific and reliable evaluation model is the key to evaluate enterprises. The study optimizes the Back Propagation (BP) neural network based on the Firefly Algorithm (FA) and innovatively introduces the Sparrow Search Algorithm (SSA), which changes the search mechanism of the BP and improves the traditional BP affected by the local optimum. of the traditional BP. In the experimental results, the average error of the improved model is 1.34 % and 0.41 % under the optimal preset parameters, which is significantly better than other advanced algorithms. It is verified that the improved evaluation model in this study has lower error and better effect, which has better application value in the evaluation of intelligent manufacturing system.

PLC-Informed Distributed Game Theoretic Learning of Energy-Optimal Production Policies.

This article describes a novel concept to optimize manufacturing systems distributively through data-based learning. We propose a game-theoretic (GT) learning set-up that is incorporated with accessible control code of the programmable logic controller (PLC) to accelerate the optimal policies learning procedures, instead of learning everything from scratch. Therefore, we offer to process the accessible and available control code into a GT-based learning framework which is subsequently optimized in a fully distributed manner. To this end, we employ the recently developed framework of state-based potential games (PGs) and prove that under mild conditions PLC-informed (PLCi) learning forms a state-based PG framework. We conduct the experiment on a laboratory scale testbed in numerous production scenarios. The experiment's results highlight the major potential of using the PLCi GT-learning, which is the reduction of energy consumption of the production timescales and improvement of production efficiency while nearly halven the learning times.

Optimization with uncertainties: a scheduling example

The optimization of manufacturing systems is rarely a deterministic task in practice, as uncertainties of various origins often have significant impact on the feasibility or quality of a production plan. The decision making process is often a complex multi-stage mechanism that anticipates and reacts to numerous parameter changes, both internal and external. Such optimization problems and the corresponding approaches are often classified and categorized based on the features of the addressed uncertainties and the desired objective. The goal of this paper is twofold. First, a systematic approach is presented to enumerate the possible optimization problems for a given set of uncertainties and degree of freedom in the planning. This approach is illustrated via a scheduling example that is inspired by literature case studies and focuses on financial objectives with varying demands and prices in the market. Then, selected problem classes identified by the approach are discussed in detail, illustrating and examining the available techniques to tackle them, citing literature studies applying the same or similar approaches.

Application of sustainable smart manufacturing technologies and toolkits in the automotive industry

Abstract A more rapid development of smart manufacturing system (SMS) within the automotive industry will significantly promote its competitiveness, which is essential to the economic sustainable development of South Africa. From recent research studies, the automotive sector contributes >7% to the annual gross domestic product of South Africa, and its sustainability is important to the segment through SMS. Thus, SMS deserves greater focus from the government and the industry. Smart manufacturing technology uses machines and tools that are interconnected for the improvement of the manufacturing system and energy optimization. The benefits of SMS include cost reduction, increased productivity, product customization, resources efficiency and minimization of negative environmental impacts. Globally, the automotive industry puts significant emphasis on SMS, considering the ongoing substantial initiatives. To achieve SMS, ultramodern technologies in different areas, varying from cyber-physical systems, smart sensors, complex and large data analytics, Internet of Things, cloud manufacturing, additive manufacturing, energy reduction and hologram are being established and used in manufacturing locations. Therefore, this study is aimed at technologies and toolkits development that will increase the implementation and responsiveness of SMS among automotive manufacturers and support decision makers in planning better SMS capabilities.

Industry 4.0 Implementation Projects: The Cleaner Production Strategy—A Literature Review

The industrial impacts on the environment need to be minimized to reduce climate change, which will benefit human beings. Industry 4.0, the new production paradigm, promises productivity gains for companies that manage to implement it, but it is also dependent on natural resources, impacting the environment. The aim of this study is to identify and analyze possible cleaner production strategies associated with Industry 4.0 to optimize manufacturing systems in Industry 4.0 implementation projects, in addition to reducing the environmental impacts of these companies. Through a literature search, cleaner production strategies associated with Industry 4.0 were identified and classified into ten dimensions (strategy, waste, recycling, life cycle, resources, energy, production, work, performance and environment) contributing to the theory. The possibilities of using Industry 4.0 technologies were analyzed to meet each dimension. The relevance of this study lies in presenting possibilities for using and developing technologies and applications to meet these dimensions of cleaner production and helping those involved in Industry 4.0 projects to implement it more stably, contributing to the theory and practice.

Retracted: Production Scheduling Optimization of Garment Intelligent Manufacturing System Based on Big Data.

[This retracts the article DOI: 10.1155/2022/2293473.].

Manufacturing system optimization using computer-based control kanban loops

The study assessed manufacturing system optimization using computer-based control kanban loops. The study assessed JIT's effect on average throughput-time, demand fill rate, net operating income for a certain product mix complexity and manufacturing overhead level. ARENA/SIMAN and WITNESS simulation tools were used to study implementation. The Drug Process Plant's JIT system reduced end buffer inventory, shortened customer lead time, and improved visual control. The mean response of the simulated new physical system in terms of NOI was 85.54 but gave a mean response of 85.30 when implemented on the shop floor. The mean response of the simulated new physical system in terms of cycle time was 617 but gave a mean response of 634 when implemented on the shop floor. Simulated new physical system in terms of DFR gave a mean response of 93.11 when implemented on the shop floor. Overwhelmingly, the new JIT system outperformed the old physical system. Bangladesh J. Sci. Ind. Res. 57(4), 221-228, 2022