1,720,983 research outputs found
On the modelling of a decentralized production control system in the Industry 4.0 environment
No full textThe paper deals with a decentralized production control in an Industry 4.0 environment. In such a kind of systems, the capability to deliver a high level of product customization together with reduced response time is crucial to maintain competitiveness and to increase profit. A semi-heterarchical architecture, formed by three levels, in which the first is responsible for meeting business objectives, the second to maintain target system general performances, and the third to tackle operative scheduling problems, is first discussed as a framework for the future implementation in an Industry 4.0 environment. Successively, the problem to model the system form a dynamic point of view is addressed directly at the second architectural level. This paper, in particular, contributes to the semi-heterarchical architecture development, by proposing a first mathematical model of the shop-floor of a such a system, involving the use of the population dynamic modelling. Finally, the results of the first implementation in a simulated environment are reported
On the advances of the Industry 4.0 Manufacturing Planning and Control system architectures
No full textDuring the last decades, the Material Resource Planning system has been considered an essential management tool for facing the manufacture of complex and highly customised products. Nowadays, the recent innovations brought from the Industry 4.0 push for a strong evolution of the Manufacturing Planning and Control System (MPC) architectures, aiming to a new class of control architectures. Among these, the intermediate (i.e., the semi-heterarchical and oligarchical) ones are taking considerable interest from the manufacturing firms due to their increased flexibility degree and productivity enhancement. However, the current scientific literature is still focused on the 'hierarchical' approach of these architectures while the 'horizontal' bargaining among entities and architecture modules need to be further investigated. After a narrative literature review of MPC architecture, this paper will focus on the development of such intermediate architectures. In particular, referring to a semi-heterarchical MPC architecture, this work extends the contributes to the design of the horizontal aspect of the higher level, evaluating the possible advantages of such an application
A novel throughput control algorithm for semi-heterarchical industry 4.0 architecture
Full text linkModern market scenarios are imposing a radical change in the production concept, driving companies’ attention to customer satisfaction through increased product customization and quick response strategies to maintain competitiveness. At the same time, the growing development of Industry 4.0 technologies made possible the creation of new manufacturing paradigms in which an increased level of autonomy is one of the key concepts to consider. Taking the advantage from the recent development around the semi-heterarchical architecture, this work proposes a first model for the throughput control of a production system managed by such an architecture. A cascade control algorithm is proposed considering work-in-progress (WIP) as the primary control lever for achieving a specific throughput target. It is composed of an optimal control law based on an analytical model of the considered production system, and of a secondary proportional-integral-derivative controller capable of performing an additional control action that addresses the error raised by the theoretical model’s. The proposed throughput control algorithm has been tested in different simulated scenarios, and the results showed that the combination of the control actions made it possible to have continuous adjustment of the WIP of the controlled production system, maintaining it at the minimum value required to achieve the requested throughput with nearly zero errors
Assessing the performances of a novel decentralised scheduling approach in Industry 4.0 and cloud manufacturing contexts
No full textThe increasing globalisation process has led to a radical change in the production concept, moving from a mass production paradigm towards one of mass customisation (MC), and focusing on value creation by pursuing customers’ needs and increasing responsiveness. The rapid development of information technologies has also made it possible to create new manufacturing paradigms, such as Industry 4.0 and cloud manufacturing, in which the increased level of autonomy is one of the key concepts for tackling new market challenges. This paper proposes a decentralised scheduling approach that improves the performance of production systems while minimising the usually high work-in-progress (WIP) requirements of the classic centralised scheduling and inventory production control system. Using a semi-heterarchical Manufacturing Planning and Control (MPC) architecture and integrating the Industry 4.0 innovation in a cloud manufacturing environment, this work contributes to the design of the lower level of the MPC architecture. The resulting production controller can allocate jobs following different dispatching rules dynamically. The performances of the proposed approach were assessed for different production scenarios and control parameter settings through an exhaustive experimental campaign based on hybrid simulation tools. The results showed that the proposed low-level controller led to a productivity increase while delivering increased responsiveness
Predicting Failure Probability in Industry 4.0 Production Systems: A Workload-Based Prognostic Model for Maintenance Planning
Full text linkMaintenance of equipment is a crucial issue in almost all industrial sectors as it impacts the quality, safety, and productivity of any manufacturing system. Additionally, frequent production rescheduling due to unplanned and unintended interruptions can be very time consuming, especially in the case of centrally controlled systems. Therefore, the ability to estimate the likelihood that a monitored machine will successfully complete a predefined workload, taking into account both historical data from the machine’s sensors and the impending workload, may be essential in supporting a new approach to scheduling activities in an Industry 4.0 production system. This study proposes a novel approach for integrating machine workload information into a well-established PHM algorithm for Industry 4.0, with the aim of improving maintenance strategies in the manufacturing process. The proposed approach utilises a logistic regression model to assess the health condition of equipment and a neural network computational model to estimate its failure probability according to the scheduled workloads. Results from a prototypal case study showed that this approach leads to an improvement in the prediction of the likelihood of completing a scheduled job, resulting in improved autonomy of CPSs in accepting or declining scheduled jobs based on their forecasted health state, and a reduction in maintenance costs while maximising the utilisation of production resources. In conclusion, this study is beneficial for the present research community as it extends the traditional condition-based maintenance diagnostic approach by introducing prognostic capabilities at the plant shop floor, fully leveraging the key enabling technologies of Industry 4.0
A deep reinforcement learning approach for the throughput control of a flow-shop production system
No full textThis paper proposes a new method for controlling a flow shop in terms of throughput and Work In Process (WIP). In order to achieve a throughput target, a Deep Q-Network (DQN) is used to define the constant WIP quantity in the system. The main contribution of this paper is the novel approach used to formulate the state, action space, and reward function. An extensive preexperimental campaign is conducted to determine the best network structure and appropriate hyperparameter values. Finally, the system's performance is compared to the known results of an analytical model from the literature (Practical Worst Case, PWC)
A novel dispatching rule for semi-heterarchical architectures in the industry 4.0 context
No full textIndustry 4.0 is changing the way to produce, pursuing increased flexibility of production systems and an ever-greater decision-making autonomy of the machines. The aim is to achieve high level of performances even in market scenarios requiring high level of customization, as the Mass Customisation (MC) paradigm imposes. Current hierarchical Manufacturing Planning and Control (MPC) systems showed limits in catching this goal, primarily due to their structural lack of flexibility. For this reason, the interest in the hybrid MPC architectures like the semi-heterarchical one is increasing. The objective of this work is to contribute to the design of such an architecture, proposing a new scheduling mechanism for the lowest decisional level. This mechanism, differently from the ones already proposed in the literature, schedules the next jobs to be admitted in the system choosing them by couples. The proposed rule has been tested through a simulation environment in three different scenarios of demand generation rate. The results showed an improvement in demand absorption and productivity compared to the rules used up to now
Anomaly detection in manufacturing systems with temporal networks and unsupervised machine learning
Full text linkTraditional manufacturing systems face significant challenges in detecting operational anomalies due to the absence of advanced sensor networks and intelligent machinery commonly associated with Industry 4.0. Existing solutions often rely on sophisticated, interconnected infrastructures, which are not feasible in conventional settings. This paper introduces a novel methodology for anomaly detection tailored specifically for traditional manufacturing environments, addressing the gap in cost-effective monitoring solutions. The proposed approach models manufacturing systems as complex temporal networks, where each machine or process is represented as a node and job flows between machines form the network edges over time. The novelty of this method lies in the combination of dynamic network theory with unsupervised machine learning. Statistical features extracted from the temporal networks are processed through dimensionality reduction techniques, specifically Principal Component Analysis (PCA) and Deep Neural Autoencoders, to reduce feature complexity while preserving essential information. The reduced feature sets are then analysed using multiple unsupervised anomaly detection algorithms, including Isolation Forest, One-Class Support Vector Machine (OC-SVM), and Local Outlier Factor (LOF). This approach does not require significant infrastructure upgrades, making it suitable for traditional manufacturing plants while still aligning with Industry 4.0 paradigms. By using only normal job flow data, it provides a cost-effective solution where anomalous data is scarce. The results demonstrate that Local Outlier Factor and Isolation Forest, when combined with Autoencoder-based feature reduction, achieved an F1-score exceeding 84%, with precision close to 99% and recall at 74%. This strong performance underscores the methodology's potential for real-world manufacturing environments, bridging the gap between traditional settings and modern Industry 4.0 paradigms
On the open job-shop scheduling problem: A decentralized multi-agent approach for the manufacturing system performance optimization
Full text linkThis paper investigates a dynamic integration of the process planning and scheduling operations of a typical Open Job-Shop manufacturing system. For this purpose, a modified CNP-based negotiation protocol - through a multi-agent modelling for jobs and operating machines - is proposed. This approach allows the introduction of an agents' hybrid behavior, considering both the own return and the system profit achieving the production performance maximization. Finally, a series of simulation runs are conducted in order to compare the performance of the proposed protocol with a recent optimization approach that uses a simple composite dispatching rule
A data-driven prognostic approach for the battery state-of-charge assessment with regard to machine workload
No full text- …
