Modern Manufacturing Systems Research Articles

Multi-agent reinforcement learning for integrated manufacturing system-process control

The increasing complexity, adaptability, and interconnections inherent in modern manufacturing systems have spurred a demand for integrated methodologies to boost productivity, improve quality, and streamline operations across the entire system. This paper introduces a holistic system-process modeling and control approach, utilizing a Multi-Agent Reinforcement Learning (MARL) based integrated control scheme to optimize system yields. The key innovation of this work lies in integrating the theoretical development of manufacturing system-process property understanding with enhanced MARL-based control strategies, thereby improving system dynamics comprehension. This, in turn, enhances informed decision-making and contributes to overall efficiency improvements. In addition, we present two innovative MARL algorithms: the credit-assigned multi-agent actor-attention-critic (C-MAAC) and the physics-guided multi-agent actor-attention-critic (P-MAAC), each designed to capture the individual contributions of agents within the system. C-MAAC extracts global information via parallel-trained attention blocks, whereas P-MAAC embeds system dynamics through permanent production loss (PPL) attribution. Numerical experiments underscore the efficacy of our MARL-based control scheme, particularly highlighting the superior training and execution performance of C-MAAC and P-MAAC. Notably, P-MAAC achieves rapid convergence and exhibits remarkable robustness against environmental variations, validating the proposed approach’s practical relevance and effectiveness.

Dynamic scheduling of hybrid flow shop problem with uncertain process time and flexible maintenance using NeuroEvolution of Augmenting Topologies

AbstractA hybrid flow shop is pivotal in modern manufacturing systems, where various emergencies and disturbances occur within the smart manufacturing context. Efficiently solving the dynamic hybrid flow shop scheduling problem (HFSP), characterised by dynamic release times, uncertain job processing times, and flexible machine maintenance has become a significant research focus. A NeuroEvolution of Augmenting Topologies (NEAT) algorithm is proposed to minimise the maximum completion time. To improve the NEAT algorithm's efficiency and effectiveness, several features were integrated: a multi‐agent system with autonomous interaction and centralised training to develop the parallel machine scheduling policy, a maintenance‐related scheduling action for optimal maintenance decision learning, and a proactive scheduling action to avoid waiting for jobs at decision moments, thereby exploring a broader solution space. The performance of the trained NEAT model was experimentally compared with the Deep Q‐Network (DQN) and five classical priority dispatching rules (PDRs) across various problem scales. The results show that the NEAT algorithm achieves better solutions and responds more quickly to dynamic changes than DQN and PDRs. Furthermore, generalisation test results demonstrate NEAT's rapid problem‐solving ability on test instances different from the training set.

Automated generation of digital models for manufacturing systems: The event-centric process mining approach

Digital and simulation models support the design and management of complex systems. However, system modelling is a time-demanding and knowledge-intensive activity. Moreover, modern manufacturing systems are subjected to frequent changes in production plans and subsequent reconfigurations. Therefore, the quick regeneration of the digital models is necessary to align digital twins and cyber-physical systems. This paper proposes a novel event-centric process mining paradigm, a process discovery algorithm, and a set of Key Performance Indicators for the fast and automated generation of digital models and their benchmarking. The discovery algorithm is based on the Event Relationship Graph of the conceptual model of the physical line. The algorithm is tested in four realistic systems of increasing complexity to verify the accuracy in modelling multi-product systems with re-entrant flows and random reworks in the presence of the assembly, disassembly, and split processes beyond the processing operations, and multi-operation workstations. The Event Relationship Graphs of the four systems are presented through the equivalent Petri nets models. The proposed approach is suitable for systems where the sensor positions are known and meaningful, like manufacturing systems, and it is effective for the quick automated generation of digital models for the activities of production planning and control as it requires a few seconds of computation time and a few hours of system observation.

30th international conference on flexible automation and intelligent manufacturing (FAIM2021) special issue: modern manufacturing systems management

30th international conference on flexible automation and intelligent manufacturing (FAIM2021) special issue: modern manufacturing systems management

A modified bi-objective NSGA-II approach to sustainability in reconfiguration planning of dynamic cellular manufacturing systems

Manufacturing plant layouts are developed to facilitate optimal process flow. Modern manufacturing systems must meet present production demands and be adaptable to changes in process flow in the future. Dynamic Cellular Manufacturing Systems (DCMS) increase the flexibility of layouts by reconfiguring cell structure and equipment distribution, to effectively adjust part routings for optimal process flow. Frequent reconfiguring of plant layout may not always be feasible or economical, however, when new product releases are planned, reconfiguring the plant layout to optimise the work-flow may be extremely beneficial. This paper presents a Non-dominated Sorting Genetic Algorithm (NSGA-II) approach to solving a DCMS problem in a sustainable, and responsible manner. A bi-objective integer programming model was developed over multiple planning horizons with fluctuating product demands. This model aims to achieve sustainability by reducing the cost of production, mitigating the environmental impact of production, and minimise negative social impacts on labourers that work in such environments. A penalty function approach was used to enforce the model constraints during optimisation. This study details trade-offs between the economic factors of a DCMS, the environmental implications of reconfiguring such a system, and the social impacts of reconfigurations on the workforce.

Maschinelles Lernen als modernes Werkzeug für Additive Fertigung

Abstract In modern manufacturing systems, quality monitoring is crucial for efficient and cost-effective production. Conventional systems rely on thresholds and process windows, but machine learning (ML) techniques promise greater accuracy and efficiency. However, pre-processing the data is still timeconsuming. This paper presents an approach to visually verify two Variational Autoencoders (VAEs) using contextual information such as print job numbers and timestamps, with the aim of predicting time series data from image data to optimize additive manufacturing processes in time. The approach focuses on the Digital Light Processing (DLP) printing process and emphasizes the importance of accurate data pre-processing and contextual visualization. The approach utilizes VAE-generated latent spaces to improve prediction accuracy in additive manufacturing and implement quality monitoring without thresholds and process windows.

An incremental learning approach to dynamic parallel machine scheduling with sequence-dependent setups and machine eligibility restrictions

Minimizing the tardiness of a parallel machine scheduling problem has been actively studied in modern manufacturing systems. In particular, dynamic parallel machine scheduling problems (DPMSPs) have gained much attention since rescheduling is required to address unpredictable events such as unexpected job arrivals and machine breakdowns, which usually occur in real-world manufacturing systems. To deal with such unpredictable events, many researchers have employed deep supervised learning (SL). However, it is still challenging to solve a DPMSP since SL requires a large number of high-quality schedules for the training neural networks. In this paper, we propose an incremental learning-based scheduling method (ILS) in which neural networks (NNs) are periodically trained by utilizing schedules built from the updated NNs in previous training intervals. Furthermore, to perform training without reducing solution space within a dynamic environment, the proposed method is designed to consider the dependency between consecutive allocations on a machine for the sum of setup time and tardiness. To verify the effectiveness of the proposed method, extensive experiments are carried out in static and dynamic scheduling problems. The experiment results demonstrate that ILS outperforms the existing methods such as dispatching rules, metaheuristics, and DRL-based methods. Additionally, we show that the proposed input features are effective in appropriately selecting job-machine pairs for assigning jobs on eligible machines through deep Shapley additive explanations analysis.

A self-adaptive co-evolutionary algorithm for multi-objective flexible job-shop rescheduling problem with multi-phase processing speed selection, condition-based preventive maintenance and dynamic repairman assignment

Production scheduling and maintenance planning are two interactive factors in modern manufacturing system. However, at present, almost all studies ignore the impact of unpunctual maintenance activities on the integrated production and maintenance scheduling since the unavailabilities of repairmen are dynamically changed, e.g., repairmen increase, decrease and their unavailable intervals update. Under these contexts, this paper addresses a novel integrated optimization problem of condition-based preventive maintenance (CBPM) and production rescheduling with multi-phase processing speed selection and dynamic repairman assignment. More precisely, (1) a novel multi-phase-multi-threshold CBPM policy with remaining-useful-life-based inspection and multi-phase processing speed selection is proposed to obtain some selectable maintenance plans for each production machine; (2) a hybrid rescheduling strategy (HRS) that includes three rescheduling strategies is designed for responding to the dynamic changes of repairman; and (3) an adaptive clustering- and Meta-Lamarckian learning-based bi-population co-evolutionary algorithm (ACML-BCEA) is developed to deal with the concerned problem. In the numerical simulations, the effectiveness of designed operators and proposed ACML-BCEA algorithm is first verified. Next, the superiority and competitiveness of the proposed CBPM policy and HRS are separately demonstrated by comparing with other CBPM policies and rescheduling strategies. After that, a comprehensive sensitivity analysis is performed to analyze the effect of optional range of processing speed, skill level of selectable repairmen and total number of processing phases, and the analyzing results show that these factors all have a significant impact on the integrated optimization.

An Integrated Process Planning and Scheduling problem solved from an adaptive multi-objective perspective

The planning and scheduling of processes are the main foundations of modern manufacturing systems, and their efficient integration represents one of the principal interests in operations research. Most of the reported literature in operations research formulates the optimization process considering a single objective. However, real-world manufacturing systems are influenced by several variables that must be considered in a complete process planning task. To solve this gap, this paper presents a computational study where the main variables of process planning are integrated: production times, production costs, and the Makespan of the system. To incorporate such variables, the problem is reformulated as a multi-objective optimization system by employing an Adapted Non-dominated Sorting Genetic Algorithm ii (ANSGA-ii) methodology. Under such an approach, the ANSGA-ii codifies the process planning elements into its structure to execute the operators for determining the best tradeoff between objectives. In this work, different cases of study are considered and compared with some of the most employed multi-objective approaches in the literature to demonstrate the performance and robustness of the proposed method. Statistical analysis corroborates that the proposed ANSGA-ii can generate competitive results outperforming the techniques employed in the experimental study.

Artificial intelligence and internet of things in manufacturing decision processes

This paper explores the influence of the internet of things (IoT) and artificial intelligence (AI) on the decision-making processes of modern manufacturing systems. With the proliferation of IoT devices and the development of AI technologies, manufacturing companies increasingly leverage these technologies to improve their decision-making abilities. This study aims to investigate the potential benefits, difficulties, and ramifications of integrating IoT and AI in manufacturing systems. The review employs the preferred reporting items for systematic reviews and meta-analyses (PRISMA) method with a systematic mapping process with four research questions. A total of 1282 articles were collected between 2017 and 2023, reviewed in accordance with the inclusion and exclusion criteria, and 66 articles were chosen. The research on IoT and AI technologies influentially affects other research in the production control layer manufacturing area based on the top-ten cited articles. In contrast, the research in this area focused on the operations management layer, specifically manufacturing analytics processes. This paper’s findings contribute to a greater understanding of the impact of IoT and AI on decision-making in modern multi-domain manufacturing systems and provide direction for future research in this field.

Multi Aspect Optimization of Milling Machines : Review

Modern manufacturing supports various aspects of modern life. Modern manufacturing right now is focused on the application of artificial intelligence, acceleration of production, automation production, sustainability and environmental protection. A milling machine is a tool supports in a series of production processes. Its existence supports the production process which is part of the modern manufacturing system. In operating milling machines, several problems that occur, starting from operations, machine capacity, and predictions of machine or tool usage. This study summarizes and reviews previous studies in order to collecting types of milling machine optimization. Multi-aspect optimization obtained includes: optimization with a tool life prediction approach, optimization with a milling process approach, optimization with modification or retrofit, optimization with a production yield approach and finally optimization with operational time. With the results obtained, it is hoped that it can contribute to the optimization of milling machines in the modern manufacturing world. It is hoped that future research will be able to carry out in-depth analysis of each aspect of milling machine optimization has been mentioned.

Rescheduling optimisation of sustainable multi-objective fuzzy flexible job shop under uncertain environment

ABSTRACT The fourth industrial revolution has necessitated the integration of sustainability and customer centricity into modern manufacturing systems, thereby emphasising their significance. However, the production process itself is characterised by inherent uncertainties. Hence, this paper primarily focuses on the multi-objective flexible job shop rescheduling problem with uncertain processing time and new job insertions. Two fuzzy constraints are incorporated: fuzzy processing time and fuzzy due date, which aim to model the uncertainty of processing time and ensure flexibility in meeting deadlines. The objective function aims to optimise both customer satisfaction and energy consumption. To address two types of rescheduling problems: time delay caused by fuzzy features and new job insertions, this paper is dedicated to providing a hybrid adaptative rescheduling strategy that combines a satisfaction-driven policy with two specific rescheduling methods. Moreover, an enhanced version of the non-dominated sorting genetic algorithm II (NSGA-II) is developed, incorporating population initialisation rules and multiple genetic operators to obtain solutions of superior quality. Experimental studies have demonstrated the impact of time delay caused by fuzzy features on customer satisfaction. The proposed hybrid adaptative rescheduling strategy and methods exhibit significant improvements in rescheduling plan performance under uncertain environments.

A lightweight sensor ontology for supporting sensor selection, deployment, and data processing in forming processes

In the era of smart manufacturing, modern manufacturing systems face high demands for enhancing process performance and reducing machine downtime. Sensors and process data are essential for successfully implementing data-driven approaches to guarantee robust and reliable process monitoring, tool conditioning, or quality assurance. However, the accuracy and performance of such approaches are highly dependent on the quality of the gathered sensor data and influenced by the implemented data acquisition and processing methods. For this purpose, this work proposes a lightweight sensor ontology to provide a comprehensive overview to characterize underlying relationships between the physical environment and the quality of the data sets. The extended sensor ontology, in combination with domain knowledge, aims to support engineers in fully exploiting the potential of sensor data to obtain trustworthy data sets in forming technologies. As a result, this approach can improve the implementation of automated and data-driven process monitoring of forming systems and tools.

An enhanced estimation of distribution algorithm with problem-specific knowledge for distributed no-wait flowshop group scheduling problems

With the trend of economic globalization, distributed manufacturing widely exists in modern manufacturing systems. As an extension of the distributed flowshop scheduling problem, the distributed no-wait flowshop group scheduling problem with sequence-dependent setup times (DNFGSP_SDSTs) is investigated in this article. To address DNFGSP_SDSTs with the criterion of minimizing makespan, this study proposes an enhanced estimation of distribution algorithm·(EEDA) with problem-specific knowledge. First, a mixed integer linear programming(MILP) model of DNFGSP_SDSTs is established. Second, based on the characteristics of DNFGSP_SDSTs, five problem-specific properties about local search operators are derived as prior knowledge to reduce computational cost. Third, two NEH-based two-stage heuristics are presented to construct a high-quality population with diversity. Fourth, a probability model with problem-specific knowledge and a family-based updating mechanism are developed to accumulate valuable pattern information from high-quality solutions, while a sampling strategy is designed to generate new populations with the accumulated information. Fifth, several local search operators are devised to refine the obtained solutions. Furthermore, perturbation and reinitialization methods are developed to avoid premature convergence. Finally, the validity of the MILP model is verified by using the Gurobi solver. The parameters of EEDA are tuned through a design of experiments. The effectiveness of key components in EEDA is confirmed through extensive experiments, and the computational comparisons with the state-of-the-art algorithms indicate the effectiveness of the proposed EEDA for solving DNFGSP_SDSTs.

Cycle Time Analysis Of AS/RS (Automated Storage & Retrieval System) Using SCADA

AS/RS is not just a replacement for conventional warehouses, but has become a key element in modern manufacturing systems. However, in its use there are still problems and shortcomings, including the unavailability of a system that can control, supervise, and acquire data from AS/RS and the cycle time when AS/RS performs data storage and retrieval tasks is still below industry standards. To overcome this, a system that is generally called SCADA (Supervisory, Control, and Data Acquisition) is needed. This research uses Arduino Mega 2560 as an AS/RS controller, while the VTSCADA application is used to build a SCADA system on AS/RS. This research uses two approaches. First, calculating the AS/RS cycle time when performing storage and retrieval tasks. Second, comparing the cycle time of the storage system and the retrieval system. The first test results show that the fastest cycle time in the storage system occurs at storage rack point 1 with a time of 3.17 seconds, while the fastest cycle time in the retrieval system occurs at retrieval point 1 with a time of 12.74 seconds. The second test resulted in a difference in cycle time between the storage and retrieval systems, namely 0.42 seconds at storage point 1, 0.38 seconds at storage point 2, 0.51 seconds at storage point 3, 0.31 seconds at storage point 4, and 0.43 seconds at storage point 5. It can be concluded that the application of SCADA to AS/RS is able to increase the cycle time of AS/RS.

Supervised and unsupervised techniques in textile quality inspections

Quality inspection is a critical step in ensuring the quality and efficiency of textile production processes. With the increasing complexity and scale of modern textile manufacturing systems, the need for accurate and efficient quality inspection and defect detection techniques has become paramount. This paper compares supervised and unsupervised Machine Learning techniques for defect detection in the context of industrial textile production, in terms of their respective advantages and disadvantages, and their implementation and computational costs. We explore the use of an autoencoder for the detection of defects in textiles. The goal of this preliminary work is to find out if unsupervised methods can successfully train models with good performance without the need for defect labelled data.

A component-based design approach for energy flexibility in cyber-physical manufacturing systems

AbstractEnergy flexibility of manufacturing systems helps to meet sustainable manufacturing requirements and is getting significant importance with rising energy prices and noticeable climate changes. Considering the need to proactively enable energy flexibility in modern manufacturing systems, this work presents a component-based design approach that aims to embed energy flexibility in the design of cyber-physical production systems. To this end, energy management using Industry 4.0 technologies (e.g., Internet of Things and Cyber-physical Systems) is compared to the literature on energy flexibility in order to evaluate to what extent the energy flexibility practice takes advantage of Industry 4.0 technologies. Another dimension is the coverage of the life cycle of the manufacturing system which guarantees its sustainable design and the ability to achieve energy flexibility by configuring the energy consumption behaviour. A data-based design approach of the energy-flexible components is proposed in the spirit of the Reference Architectural Model Industrie 4.0 (RAMI 4.0), and then it is exemplified using an electric drive (as a component) in order to show the practical applicability of the approach. The energy consumption behaviour of the component is modelled using machine learning techniques. The digital twin of the studied component is developed using Visual Components virtual engineering environment, then its energy consumption behaviour is included in the model allowing the system integrator/decision-maker to configure the component based on the energy availability/price. Finally, external services in terms of an optimisation module and a deep learning module are connected to the digital twin.

Modeling and Simulation of a Digital Twin of a Production System for Industry 4.0 with Work-in-Process Synchronization

One of the main problems of modern manufacturing systems is the increasing complexity related to modern Industry 4.0 technologies that are fundamentally changing manufacturing and logistics processes and operations. Industry 4.0 includes, e.g., flexible automation and robotization, which make complex manufacturing systems difficult to analyze. Some modeling and simulation methods are being used to solve industrial problems and can serve as an interface between the production level and management level. The new trend of the Digital Twin, creating simulation models as similar as possible to the real system, and a Digital Twin framework for a manufacturing line from the automotive industry, was considered. Simulation models typically start from the empty state and some warmup time is required to achieve the stable state. The Key Performance Indicators were also analyzed for the stable state. However, there are many stochastic parameters such as machinery failures, human errors, quality issues, etc., that make the real processes differ from simulated processes, and cause the instability of production throughput and changes in the Work in Process. To analyze the Work in Process in the model, initialization of the model with proper production data is required, as the Digital Twin uses data synchronization with the production database. In this paper, the digital model of a human-robot-operated manufacturing system with Work-in-Process data synchronization is analyzed, and the results of the statistical analysis of simulation experiments are presented. The obtained results show high variability of finished production, which is related to system instability due to random failures, especially when the system starts from an empty state. However, an increase in initial Work in Process results in better efficiency and stability for the whole system. The DT simulation of the manufacturing system can be very helpful, as it becomes a repository of knowledge about the real system and enables the analysis of its dynamics. However, for proper functionality, the model should include information about the current WIP state, which enables the start of the simulation with exactly the same number of queues as in the real system. The presented method can also be used in similar enterprises from other industries, especially for those with discrete processes or high WIP variability, and for further synchronization of other DT parameters.

Parametric Analysis of Tool Wear, Surface Roughness and Energy Consumption during Turning of Inconel 718 under Dry, Wet and MQL Conditions

Economy and productivity are the two most important elements of modern manufacturing systems. Economy is associated with energy-efficient operations, which results in an overall high input-to-output ratio, while productivity is related to quality and quantity. This specific work presents experimental investigations of the use of cooling conditions (dry, MQL and wet) as input variables alongside other input parameters, including depth of cut, feed and cutting speed. This research aimed to investigate the variation in output responses including tool wear, specific cutting energy, and surface roughness while machining Inconel 718, a nickel-based super alloy. For experimentation, three levels of depth of cut, feed, and cutting speed were chosen. The Taguchi method was used for the experimental design. The contribution ratio of each input parameter was ascertained through analysis of variance (ANOVA). Use of coolant showed a positive effect on process parameters, particularly MQL. By adapting the optimum machining conditions, specific cutting energy was improved by 27%, whereas surface roughness and tool wear were improved by 15% and 30%, respectively.

Methodology for Selecting Optimal Knowledge Acquisition Through Analytic Hierarchy Process and Environment Parameters Impact.

In a global economy characterised by increasingly dynamic markets and technologies, the primary importance of intangible resources like knowledge is growing dramatically, especially for small and medium-sized enterprises (SME). Therefore, many companies are trying to support changes by configuring their production systems towards mass customisation. This evolving paradigm shift from mass production to mass customisation brings about complex product lifecycles that require continuous re-engineering/configuration of modern manufacturing systems. Rapid manufacturing companies' changes result in adjusting and updating the existing knowledge base to maintain their competitive advantage. Within companies, different tacit and explicit knowledge are available, relating to resources, processes and components. This data is usually not digitised, and therefore the main challenge for small and medium-sized enterprises is how to automate the knowledge acquisition process, choosing the best tools for knowledge preservation. Starting from the analysis of models presented in the literature, we defined a methodology to support selecting the optimal acquisition of knowledge and preservation in any phase of production systems. In an environment where business uncertainty is the norm, developing knowledge acquisition capabilities is increasingly important. The paper's main contribution is the AHP-PIE methodology, which provides a helpful guideline as a structured and logical means of ranking KA methods for evaluating appropriate tools for a small manufacturing industry organisation.