The transition toward sustainable manufacturing requires not only high-performance production strategies but also transparent and interpretable decision-making tools. While Machine Learning (ML) has been widely applied in Additive Manufacturing (AM) to predict process outcomes, its adoption often suffers from a lack of interpretability. This study addresses this gap by integrating Explainable AI (XAI) into a data-driven framework for Wire Arc Additive Manufacturing (WAAM), using real experimental data from the deposition of Invar 36 alloy. Two ensemble ML algorithms, XGBoost and Random Forest, were employed to predict key output variables, such as layer width, height, specific energy consumption (SEC), and Global Warming Potential (GWP). SHAP (SHapley Additive exPlanations) values were used to interpret model predictions, revealing feature interdependencies and their relative contributions to each target. By coupling predictive accuracy with interpretability, the proposed framework provides actionable insights for the multi-indicator interpretation of WAAM processes, supporting both energy efficiency and environmental sustainability in AM.

The advent of Industry 4.0 has revolutionised manufacturing systems, introducing unprecedented levels of customisation and variability. Traditional methods for controlling Work-In-Progress (WIP) often fall short in these dynamic environments, necessitating the development of adaptive and intelligent control strategies. This paper explores the application of Reinforcement Learning (RL) for adaptive WIP control in semi-heterarchical architectures for flow-shop production systems. We propose a novel framework that integrates RL, specifically Deep Q-Networks (DQN), with Discrete-Event Simulation (DES) to derive optimal control policies without relying on closed-form mathematical models. Preliminary simulation experiments demonstrate the effectiveness of the proposed approach in handling variations in job processing time variability and throughput reference targets, showcasing the merit and potential of RL for adaptive WIP control.

Maintenance scheduling is critical for many industries, and Deep Reinforcement Learning (DRL) has shown great potential in optimizing scheduling decisions in complex and dynamic environments. This proposal introduces an integrated simulation tool and DRL algorithm for effective maintenance event scheduling and planning in a Flow Shop production line. This comprehensive solution aims to optimize maintenance plans and maximize productivity by combining simulation capabilities with intelligent decision-making via DRL. The integrated simulation tool replicates the production line Flow Shop in a virtual environment, allowing for precise modeling and simulation of machine operations, job flows, and maintenance events. The tool evaluates different maintenance procedures and their impact on overall performance by capturing the system’s dynamics and complexities. The novelty of the approach lies in the fact that the training phase is performed on a single machine, and the policy developed is tested on a Flow Shop line with machines with the same Weibull parameters (α and β) and with machines with different Weibull parameters. The proposed integrated simulation tool and DRL algorithm provide a powerful solution for the scheduling and planning of maintenance events in a production line Flow Shop. By combining simulation capabilities with intelligent decision-making through DRL, this approach offers a comprehensive solution to optimize maintenance strategies and enhance overall production performance in all experimental settings tested.

To stay competitive, modern market scenarios are forcing a radical shift in the manufacturing concept, focusing companies’ attention on customer satisfaction through increased product customization and quick response strategies. Significant progress has been made in the field of Industry 4.0 technologies, but there is still an open gap in the literature regarding methodologies for efficiently managing a manufacturing system’s available productive resources. Spearman et al. proposed the CONtrolled Work-In-Progress (CONWIP) production logic, which allows controlling Work-In-Progress (WIP) in a production system while monitoring throughput. However, in order to face with the increased variability that enters into the production system, an affordable performances estimation tool is still required. Taking advantages of the recent innovation in the field of machine learning, this paper contributes to the development of a tool for estimating the performance of a production line using a deep learning neural network. The results demonstrated that the proposed estimation tool outperforms the current best-known mathematical model when estimating the throughput of a CONWIP Flow-Shop production line with a given processing time distribution and WIP value.

This paper arises from the need to give an answer to a problem of optimization of industrial production in conditions of high rigidity of production constraints. In particular, the production architecture is that of a set of work centers arranged in a typical flow shop. This architecture presents the inability to change the order of machining operations. This implies that the problems of optimization by the latter were always resolved by a classical approach to scheduling. The approach presented in this work uses a System Dynamics simulation model that in despite of an apparent greater complexity if compared to a classical approach, allows, basing on the use of matrices, to identify at each instant the position and the confluence of each single order, and also to decide in a dynamic way operations planning at each work center. This approach has been implemented in a case study but shows to be enough general to be applicable to any company.

The purpose of this paper is to show the impact of simulation software in the production processes. In particular, the study focused on the simulation techniques to model and to optimize the operations. It was carried out a review of different simulation software. Moreover, in this paper it was developed a case study on olive oil production system. In particular, in the case study, it was developed a simulation model that, starting from a scheduling of arrivals in real time, evaluates the performance of the system in order to optimize the parameters that can be chosen according to the requirements (yields optimization, quantity optimization, quality optimization, revenue maximization, etc.).

This work is focused on some simulation tools assessment, usable for the analysis of industrial plants based on a new class of chemical reactors for energy production, obtained from the pyrolysis of organic matrix waste fluids. First of all the authors show a new Arc Flow Plasma technology. Then they analyze a simulation tool usable to understand the operation of the assessed plant to changing configuration conditions of the reactor, as well as the performance trends of the most relevant physical inputs and outputs that characterize the plant. Finally, the paper assesses the reliability of the results obtained, indicating possible future implementations, in terms of simulation model for this class of plants.

The objective of this work is the realization of a tool for decision support: a macro parametric model, consisting of two modules, the Flow Shop Main Module, representative of a typical production system and Sequencing Module, representative of the sequencing according to the FIFO rule of dispatching.

Today we depend more and more on logistic networks, which often know nothing, or worse, on which our power of control is almost zero. It is impossible to imagine a life without certain types of products or food, all of that to get us often follow long and complex network and therefore vulnerable. Let see how increase in energy costs has engulfed many small companies. Differently by rising energy costs, there are also changes that are not so easily predictable, so it is essential for the survival of a company to have “redundant” resources, able to operate strategies and proactive behavior. It's important to be flexible and adapt better to the changes that are imposed by external or even internal conditions. More than on flexibility, it is necessary to focus on the concept of Resilience, which requires the ability to remain calm, to address a crisis, but maybe leave it weakened but with the strength, the ability and the confidence to create a tomorrow of own business, adapting to change.

This paper proposes a System Dynamics approach to manage supply risks. In Supply Chain Risk Management field tools such as modeling and computer simulation are assuming an increasingly important role in supporting strategic, tactical and operational business decisions. In particular, these are applied to the risk sharing phase and to evaluate appropriate management and mitigation strategies. In a company's perspective, a SD approach provides a reading key of reality through an analysis of how policies and decisions influence and are influenced by the environment and how these impact on dynamics of available resources. In this context a model to assess supply risks has been defined. This model considers the operational characteristics of a generic company operating in its supply chain environment, and their interactions. This problem has been approached through several steps with an increasing level of detail. We start by decomposing the supply risk problem in its subparts, in order to understand the mechanisms making this system complex. The simulation based approach proposed here allows to carry out an analysis and subsequent mitigation of supply risks, furthermore providing some counterintuitive advices in order to maximize company's profitability.

The aim of this study is to compare, in terms of cost and safety, two of the most important maintenance policies: Incidental Maintenance and Condition Based Maintenance. This has been accomplished through a simulation based approach. An optimization process has also been carried out in order to choose the optimal maintenance policy. A scenario analysis for the model's key parameters has been carried out finding significant results for several production contexts.

Today even more companies sell their products through the Internet, and therefore it is very important to give customers the best product presentation. To show customers films on a specific product seems to be a winning strategy. But, unfortunately, due to the continuous variation of the Internet transfer rate and the variously different bandwidths available among customers, it is very difficult to assure the best vision to every customer. This paper presents a new method to minimise the side effects due to the aforementioned circumstances, and at the same time maximise the vision quality while minimising the Internet site creation and update costs.