Tommaso Rossi

Learning Factories (LFs) have become increasingly important in engineering education, offering environments where students can engage in experiential learning and connect theoretical knowledge with industrial practice. In 2016, LIUC University established the i-FAB LF, a foosball assembly line where students experience real factory scenarios, as part of educational formats designed to develop skills in lean manufacturing and Industry 4.0. In this context, a variety of activities devoted to industrial engineering students has been developed. Among these, a learning activity centered on the integration of Artificial Intelligence (AI) into quality management stands out as a representative example, fostering the development of the skills required by the new workforce in the context of Industry 5.0 (I5.0). This activity offers a hands-on, team-based learning experience, with its pedagogical foundation rooted in the A3 problem-solving framework, which guides students in systemat ically identifying quality issues, collecting relevant data, and analyzing root causes in the production process. Following this structured analysis, students apply their insights to develop an AI tool leveraging convolutional neural networks to automati cally detect and classify assembly defects. In this way, the A3 process provides both the diagnostic foundation and the data driven roadmap for AI implementation, connecting structured problem solving with innovative technological countermeasures. Taken together, these elements foster skills in creative and innovative thinking, collaboration, data analytics and problem solving – considered as key competencies in the I5.0 paradigm. The contribution of this study is to present the LF-based educational activity and to report students’ perceptions collected through a structured questionnaire on three dimensions: learn ing experience and pedagogical design, collaboration and motivation, and quality of the learning environment.

In the context of Industry 5.0, the development of skills through experiential learning is becoming increasingly important in industrial engineering education. However, traditional assessment methods often fail to capture the effectiveness of these activities and the actual skills acquired by students. This gap calls for new, more adaptive and dynamic approaches to evaluation. To address this need, this study proposes an innovative solution that employs recent Generative Artificial Intelligence (GenAI) technology to develop a dynamic and self-adaptive assessment system designed specifically for experiential learning environments. The proposed model uses a web-based, self-correcting quiz integrated with ChatGPT via OpenAI’s API. Questions are dynamically generated according to Bloom's taxonomy, and the student's responses are checked in real time to adapt the subsequent questions accordingly. At the end of each session, the system automatically provides both quantitative scores and qualitative feedback for each response and for the overall performance. An application case was conducted in i-FAB, the learning factory at Università Carlo Cattaneo - LIUC, in which students were involved in an experiential learning activity aimed at learning and practicing the Data Analytics skills considered fundamental in the Industry 5.0 context. The results obtained from the test of the method demonstrated its validity and consistency with the set objectives. The proposed method is thus a significant contribution to experiential learning research, filling the gap of inadequate assessment systems while leaving room for possible future improvements.

The scope of this study is the development methodology of a Gesture Recognition System (GRS), making use of Artificial Intelligence (AI), and integrated into the Manufacturing Execution System (MES) provided in i-FAB, a learning factory in Università Carlo Cattaneo – LIUC, aiming at improving time tracking and displacement of unnecessary movement on the shop floor. Concerning the Human-Centricity pillar of the Industry 5.0 paradigm, this approach aims at enhancing well-being through the reduction of repetitive and inefficient tasks hence, making the MES systems more user-centric. The developed GRS can recognise certain hand movements related to various inputs to the MES so that users spend less time using a keyboard and touching devices. This leads to a reduction of time loss due to the time associated with tracking time and activity data which in the end optimizes production. Moreover, the system also lessens ergonomic risks that pertain to the tasks being performed, since unnecessary and repetitive movements of the operators are greatly reduced. The research findings indicate that this considerably improves the pace of completion of time and activity tracking on MES systems in a way that is designed to meet the requirements of Industry 5.0 which is focused on promoting a collaborative, safe and healthy environment.

The fourth and fifth industrial revolutions have significantly transformed manufacturing, introducing new perspectives and foundational beliefs, particularly in promoting sustainable manufacturing practices. This shift requires rethinking the competences and decision-making processes that workers must have to work in the new environment. To help students in being competitive on the job market, educational institutions must align their educational programs to address the new requirements. Thus, this research aims to identify the skills that future workers must have to be appealing for companies that want to operate in an environmentally conscious and socially responsible industrial landscape. To do so, a systematic review of existing literature was carried out. To offer a complete overview of the evolution of the competencies and identify important trends, the study tracked the frequency of citations for skills over time. These skills can be taught through learning factories, which can be used to provide students with practical applications of theoretical knowledge, ensuring that learned competencies are not only theoretical but also practical and applicable in real-world scenarios. This research offers valuable insights into the evolving debate on skills, which can be useful for the development of educational programs, learning activities and targeted training initiatives for workers.

The interest of the literature in the theme and application of Virtual Reality in industrial contexts has increased in the last years. Virtual Reality has proven to be a promising technology in a vast variety of applications. Among these, Virtual Reality can be used as a tool to enhance the training of operators under certain conditions, and it can be considered as a way to perform a gamification of the training process. In this research, an application of Virtual Reality to this extent is presented. In particular, the research shows how to implement this technology to provide several advantages to companies, such as the possibility to train operators without line stops as well as to perform training in environments that are not physically developed yet. Indeed, the research presents the development of an application based on Virtual Reality technology in the pharmaceutical sector, aimed at enhancing the training of the operators that need to avoid the cross-contamination of production lots in the white room of the production facility. The results show how to build and structure an application of Virtual Reality that can be used to certify operators in performing certain delicate operations. In doing so, the procedure to develop the application, as well as the tools used in the developing process are presented. Moreover, the research shows also how Virtual Reality technology can be used to train operators to perform operations in environments not yet developed. Finally, an analysis of the response to the gamification of the training process from the operators is presented, to show feedback and issues that may arise in the usage of the application.

The years 2021 and 2022 showed that maritime logistics are prone to interruptions. Ports especially turned out to be bottlenecks with long queues of waiting vessels. This leads to the question of whether this can be (at least partly) mitigated by means of better and more flexible terminal operations. Digital Twins have been in use in production and logistics to increase flexibility in operations and to support operational decision-making based on real-time information. However, the true potential of Digital Twins to enhance terminal operations still needs to be further investigated. A Delphi study is conducted to explore the operational pain points, the best practices to counter them, and how these best practices can be supported by Digital Twins. A questionnaire with 16 propositions is developed, and a panel of 17 experts is asked for their degrees of confirmation for each. The results indicate that today’s terminal operations are far from ideal, and leave space for optimisation. The experts see great potential in analysing the past working shift data to identify the reasons for poor terminal performance. Moreover, they agree on the proposed best practices and support the use of emulation for detailed ad hoc simulation studies to improve operational decision-making.

Research in lean production has recently focused on linking lean production to Industry 4.0 by discussing the positive relationship between them. In the context of Industry 4.0, data science plays a fundamental role, and operations management research is dedicating particular attention to this field. However, the literature on the empirical implementation of data science to lean production is still under-investigated and details are lacking in most of the reported contributions. In this study, multiple case studies were conducted involving the Italian manufacturing sector to collect evidence of the application of data science to support lean production and to understand it. The results provide empirical proof of the link and examples of a variety of data science techniques and tools that can be combined to support lean production practices. The findings offer insights into the applications of the traditional lean plan–do–check–act cycle, supporting feedback on performance metrics, total productive maintenance, total quality management, statistical process control, root cause analysis for problem-solving, visual management, and Kaizen.

Drug distribution performed through hospital pharmacies facilitates public expenditure savings but incurs higher social costs for patients and caregivers. The widespread presence of community pharmacies could support patient access while also improving drug distribution. The implementation of prescriptive data analyses as constrained optimization to achieve specific objectives, could be also applied with good results in the healthcare context. Assuming the perspective of the Italian National Healthcare Service, the present study, built upon existing research in this field, proposes a decision support tool that is able to define which self-administered drugs for chronic diseases should be distributed by community pharmacies, answering to critical challenges in the case of future pandemics and healthcare emergencies, while also providing suggestions for the institutional decision-making process. Moreover, the tool aids in determining the optimal setup of the drug distribution network, comparing centralized (hospital pharmacies) and decentralized (community pharmacies) approaches, as well as their economic and social implications.

For decades researchers have been facing the issue of adapting the economic production quantity (EPQ) to the case of multi-item production contexts characterised by a single (shared) resource with finite capacity. The economic lot scheduling problem (ELSP), which is still of interest to researchers, has addressed this issue. A recent attempt by Rossi et al. (Omega 71:106–113, 2017) addressed the problem while avoiding scheduling. Notwithstanding their relevance, these approaches present limitations in adapting the EPQ model to multi-product ‘pull’ production systems. The present work attempts to overcome these limitations through the development of a methodology based on the equation proposed by Mallya (1992) and restricting items production frequencies to define feasible solutions while avoiding scheduling. The feasibility and performance of the proposed model are evaluated through its application to well-known benchmarking instances (Bomberger’s, Eilon’s and Mallya’s problems) and a large set of test problems.

Of the drug distribution models implemented in the Italian National Healthcare Service provided to guarantee the administration of medication, the drug distribution performed through the hospital channel is an operative strategy that allows for savings in the public expenditure, but often creates higher social costs for patients and caregivers. This distribution model leads to high access to hospitals which, during pandemics, amplifies the risk of contagion, making these healthcare facilities a place where epidemics could spread and negatively affect high-risk patients. Considering their extensive local presence, primary care services and community pharmacies could play an active role to reach patients and ensure the proper distribution of drugs. Based on the differences in these two distribution models, a prescriptive tool could provide suggestions for the institutional decision-making process. When performed by different stakeholders (i.e., policy makers, health authorities or agencies), it could define which drugs should be distributed by primary care pharmacies for the treatment of chronic diseases and provide an answer to critical issues in case of future pandemic situations and healthcare emergencies. Prescriptive data analyses are known as the best methods for formulating prescriptions in the distribution field and constrained optimization sets the values of decision variables to achieve specific objectives, such as a reduction in the number of visitors to the hospital setting. Grounded on previous research in this field, the present study proposes a decision support tool based on a constrained optimization model, establishing which drugs currently dispensed by hospital pharmacies should be distributed by primary care pharmacies. This approach allows for limiting crowding and balances the distribution costs to guarantee equal access to care for patients. The model structure and the possible decision-making outputs reached by applying the prescriptive tool are discussed and the “what-if” analysis is used to ensure the robustness of the simulation approach.