Nuova ricerca

DAVIDE MEZZOGORI

Ricercatore t.d. art. 24 c. 3 lett. A
Dipartimento di Ingegneria "Enzo Ferrari"

Home | Didattica |


Pubblicazioni

2023 - A Keyword, Taxonomy and Cartographic Research Review of Sustainability Concepts for Production Scheduling in Manufacturing Systems [Articolo su rivista]
Bertolini, M.; Leali, F.; Mezzogori, D.; Renzi, C.
abstract

The concept of sustainability is defined as composed of three pillars: social, environmental, and economic. Social sustainability implies a commitment to equity in terms of several “interrelated and mutually supportive” principles of a “sustainable society”; this concept includes attitude change, the Earth’s vitality and diversity conservation, and a global alliance to achieve sustainability. The social and environmental aspects of sustainability are related in the way sustainability indicators are related to “quality of life” and “ecological sustainability”. The increasing interest in green and sustainable products and production has influenced research interests regarding sustainable scheduling problems in manufacturing systems. This study is aimed both at reducing pollutant emissions and increasing production efficiency: this topic is known as Green Scheduling. Existing literature research reviews on Green Scheduling Problems have pointed out both theoretical and practical aspects of this topic. The proposed work is a critical review of the scientific literature with a three-pronged approach based on keywords, taxonomy analysis, and research mapping. Specific research questions have been proposed to highlight the benefits and related objectives of this review: to discover the most widely used methodologies for solving SPGs in manufacturing and identify interesting development models, as well as the least studied domains and algorithms. The literature was analysed in order to define a map of the main research fields on SPG, highlight mainstream SPG research, propose an efficient view of emerging research areas, propose a taxonomy of SPG by collecting multiple keywords into semantic clusters, and analyse the literature according to a semantic knowledge approach. At the same time, GSP researchers are provided with an efficient view of emerging research areas, allowing them to avoid missing key research areas and focus on emerging ones.

2023 - A dynamic operative framework for allocation in automated storage and retrieval systems [Articolo su rivista]
Bertolini, M.; Mezzogori, D.; Neroni, M.; Zammori, F.
abstract

Two very important aspects in automated storage and retrieval systems (AS/RS) are productivity (or performance) and maintenance costs. In the literature, as in industry, it is very difficult to find a solution that guarantees satisfactory results in terms of both. Moreover, all the solutions that the scientific community has proposed are static, i.e., the system's behavior does not change as boundary conditions change. In this paper, we propose an innovative solution known as a dynamic operative framework (DOF), which allows the system to react to changes in operating conditions and guarantees good results in terms of productivity, with a consistent reduction in the distance that handling machines travel and a consequent reduction in maintenance and energy consumption costs. To test the proposed solution, we focused on the shuttle-lift crane AS/RS, a common configuration used to store bundles of long metal bars, and we compared the DOF with four benchmark policies that exploit a class-based reorganization of the stock performed during non-working shifts. Many simulation runs’ results indicated that the DOF ensures a throughput time aligned to that of the benchmarks, but without needing to reorganize the stock during nonworking shifts. In this way, it leads to consistent savings in terms of energy consumption and maintenance costs.

2023 - A scrumban board-based approach to improve material flow in engineering to order (ETO) companies: an industrial application based on action research [Articolo su rivista]
Bertolini, M.; Mezzogori, D.; Neroni, M.; Zammori, F.
abstract

2022 - A Cooperative and Competitive Serious Game for Operations and Supply Chain Management – Didactical Concept and Final Evaluation [Articolo su rivista]
Romagnoli, G.; Galli, M.; Mezzogori, D.; Reverberi, D.
abstract

Abstract—In the last decades, Serious Games (SGs) have been implemented more and more in the engineering field, for both educational and professional purposes. The interest in digital SGs has increased even more in the last years of covid-19 pandemic, due to their location-independent availability and to the possibility to use SGs to apply theoretical knowledge and involve the users in a challenging way. Since the beginning of project Open Digital Laboratory For You (DigiLab4U) in October 2018, the University of Parma started to develop a brand-new SG with a strong focus on Operation and Supply Chain Management. The game has been studied as a multiplayer cooperative and competitive game which projects learners in a fictitious universe where multiple companies compete against each other in the same market. The realization of the game started from the definition of the didactical concept, underwent the user acceptance testing phases (alpha and beta tests) up until reach the release and the corresponding final evaluation feedback.

2022 - A new perspective on Workload Control by measuring operating performances through an economic valorization [Articolo su rivista]
Mezzogori, D.; Romagnoli, Giovanni; Zammori, F.
abstract

Workload Control (WLC) is a production planning and control system conceived to reduce queuing times of job-shop systems, and to offer a solution to the lead time syndrome; a critical issue that often bewilders make-to-order manufacturers. Nowadays, advantages of WLC are unanimously acknowledged, but real successful stories are still limited. This paper starts from the lack of a consistent way to assess performance of WLC, an important burden for its acceptance in the industry. As researchers often put more focus on the performance measures that better confirm their hypotheses, many measures, related to different WLC features, have emerged over years. However, this excess of measures may even mislead practitioners, in the evaluation of alternative production planning and control systems. To close this gap, we propose quantifying the main benefit of WLC in economic terms, as this is the easiest, and probably only way, to compare different and even conflicting performance measures. Costs and incomes are identified and used to develop an overall economic measure that can be used to evaluate, or even to fine tune, the operating features of WLC. The quality of our approach is finally demonstrated via simulation, considering the 6-machines job-shop scenario typically adopted as benchmark in technical literature.

2022 - An Exploratory Research on Adaptability and Flexibility of a Serious Game in Operations and Supply Chain Management [Articolo su rivista]
Romagnoli, G.; Galli, M.; Mezzogori, D.; Zammori, F.
abstract

Serious games (SGs) in industrial engineering education are an established topic, whose implementations are continuously growing. In particular, they are recognized as effective tools to teach and learn subjects like Operations and Supply Chain Management. The research on SGs, however, is primarily focused on displaying applications and teaching results of particular games to achieve given purposes. In this paper, we provide an exploratory research on the flexibility and adaptability of a specific SG to different target groups and students’ needs in the field of operations and supply chain management. We first provide an overview of the SG and introduce its mechanics. Next, we explain how the mechanics has been implemented, by means of a set of parameters and indicators. We report the results of two different game sessions, played by a class of bachelor’s degree students at different levels of difficulty, which were achieved by altering some specific game parameters. By comparing the Key Performance Indicators (KPIs) in the two sessions, we report and discuss the consequences of the modified game parameters, in terms of impact on the difficulty level of the SG measured by the indicators. Experimental results match with our hypothesis, since the increased level of difficulty of sourcing and delivery times only deteriorates the related subset of indicators in the harder game session, without altering the remaining KPIs.

2022 - Challenges and Solutions to Integrate Remote Laboratories in a Cross-University Network [Relazione in Atti di Convegno]
Adineh, H.; Galli, M.; Heinemann, B.; Hohner, N.; Mezzogori, D.; Ehlenz, M.; Uckelmann, D.
abstract

Location-independent networking of laboratory infrastructures is opening new possibilities for teaching and learning. In order to make full use of the possibilities it makes sense to form associations and use real, partly digitized and fully digital laboratories shared across locations. The connection of different laboratories with different equipment and different conditions confronts us with technical challenges. This article presents challenges, which are faced in an international project, as well as possible technical solutions and the way to our decision.

2022 - Comparison between prone and supine nephrolithotomy in pediatric population: a double center experience [Articolo su rivista]
Campobasso, D.; Bocchialini, T.; Bevilacqua, L.; Guarino, G.; Di Pietro, C.; Granelli, P.; Mezzogori, D.; Salsi, P.; Oltolina, P.; Gatti, C.; Puliatti, S.; Ceccarelli, P. L.; Maestroni, U.; Frattini, A.; Bianchi, G.; Micali, S.; Ferretti, S.
abstract

Purpose: Stone disease in the pediatric age is an increasing issue. Percutaneous Nephrolithotomy (PNL) can be used for larger and complex stones. As in adults it can be performed in the supine or prone position. Methods: We retrospectively reviewed two centers’ experience in prone and supine PNL in children to analyze its results and complications. Results: 33 patients underwent prone and 19 supine procedures. Patients in the prone group were younger than in the supine, while no significant differences were found in stone burden, access size, operative time or complications. Complications were: 8 and 4 Clavien 1 for the prone and supine group, respectively, one case of urosepsis (4b) in the prone and 2 cases of Clavien 3 in the supine group (double J stent placement for renal colic and ureteroscopy for steinstrasse). Tubeless procedures and mean nephrostomy time were in favor of the supine group, whereas fluoroscopy time and ureteral drainage stay were in support of the prone group. Stone free rate was better in the supine group (83.3 vs 66.6%), possibly reflecting the capability to perform a combined approach in 12 patients (allowing to reach all the calyx with simultaneous anterograde and retrograde access) or younger age in the prone group (13 vs 2 patients ≤5 years), with no differences in stone burden. Conclusions: Supine approach seems to guarantee higher stone-free rates. Larger series are necessary to determine what the best technique is in terms of X-ray exposure, operative time and complications.

2022 - Including energy saving in planning and scheduling. A case study [Relazione in Atti di Convegno]
Bertolini, M.; Galli, M.; Mezzogori, D.; Neroni, M.
abstract

Production processes consume more natural resources than is ecologically bearable, motivating environmental policies to emphasize the efficient consumption of renewable resources. A key issue in manufacturing is how to optimize processes to produce more with less energy, reducing overall costs and contributing to a green economy. Although most of the energy efficiency gains are achieved through more efficient machines and plants, a significant part of the energy savings can be achieved through optimized production and scheduling plans. Industrial companies plan their production considering many variables, but often neglect those related to energy availability and costs. This paper will address this issue through the design and test of an advanced planning and scheduling system for a manufacturing company. The planning and operation of energy-efficient production systems require the integration of the company's energy management systems and production scheduling, analysing the energy consumption behaviour of components and production processes, and designing optimization methods to deal with different scenarios. In particular, we will develop an optimization model for planning and scheduling operations based on the analysis of a combination of energy availability, costs and consumption patterns, and operational problems.

2022 - Machine-learning models for bankruptcy prediction: do industrial variables matter? [Articolo su rivista]
Bragoli, D.; Ferretti, C.; Ganugi, P.; Marseguerra, G.; Mezzogori, D.; Zammori, F.
abstract

We provide a predictive model specifically designed for the Italian economy that classifies solvent and insolvent firms one year in advance using the AIDA Bureau van Dijk data set for the period 2007–15. We apply a full battery of bankruptcy forecasting models, including both traditional and more sophisticated machine-learning techniques, and add to the financial ratios used in the literature a set of industrial/regional variables. We find that XGBoost is the best performer, and that industrial/regional variables are important. Moreover, belonging to a district, having a high mark-up and a greater market share diminish bankruptcy probability.

2022 - On the use of Serious Games in Operations Management: an investigation on connections between students' game performance and final evaluation [Relazione in Atti di Convegno]
Esposito, G.; Galli, M.; Mezzogori, D.; Reverberi, D.; Romagnoli, G.
abstract

In last twenty years, interest in Serious Games has continuously raised, especially thanks to the technological improvement in computer science and virtual laboratories. A common objective of these games is to enhance practical skills of users by simulating realistic universes in which players could operate and learn. We present a study on the application of a Serious Game in an Operations Management course at the University of Parma. The game is designed as a web-based application replicating a realistic universe in which different e-bike producing companies compete, having a limited number of suppliers and customers. Each company is composed by different students, playing different roles within the company, and collaborating in order to take company strategical decisions. A KPI system has been implemented in order to best evaluate students' work during the game sessions. Also, a post-test has been submitted to students to better understand the perceptions they had towards the game. At the end of the courses, students received their final evaluation in Operations Management. The present paper has the objective to analyse (i) KPIs, (ii) game session duration, and (iii) post-test results, and look for a connection between the data analysed and the final evaluation gave to each student.

2021 - A review of RFID based solutions for indoor localization and location-based classification of tags [Relazione in Atti di Convegno]
Esposito, G.; Mezzogori, D.; Neroni, M.; Rizzi, A.; Romagnoli, Giovanni; Rosa, Mirko
abstract

2021 - Cycle time calculation of shuttle-lift-crane automated storage and retrieval system [Articolo su rivista]
Zammori, F.; Neroni, M.; Mezzogori, D.
abstract

This article deals with cycle time calculation of Automated Storage and Retrieval Systems (AS/RS). Cycle time has a high impact on the operating performance of an AS/RS, and its knowledge is essential, both at the operational and design level. The novelty of this work concerns the peculiar kind of system that is considered, as the focus is on the Shuttle-Lift-Crane AS/RS. This solution, common in the steel sector, is used to store bundles of long metal bars, which are automatically handled by cranes, lifts, and shuttles. The functioning of these machines, which can operate in parallel and independently, is stochastically modeled, and the probability distribution function of the cycle time is computed, both for single and dual command cycles. The model, assessed via discrete event simulation, ensures a high average accuracy of 96% and 98%, under single and dual command cycles, respectively.

2021 - Defining accurate delivery dates in make to order job-shops managed by workload control [Articolo su rivista]
Mezzogori, D.; Romagnoli, G.; Zammori, F.
abstract

Workload control (WLC) is a lean oriented system that reduces queues and waiting times, by imposing a cap to the workload released to the shop floor. Unfortunately, WLC performance does not systematically outperform that of push operating systems, with undersaturated utilizations levels and optimized dispatching rules. To address this issue, many scientific works made use of complex job-release mechanisms and sophisticated dispatching rules, but this makes WLC too complicated for industrial applications. So, in this study, we propose a complementary approach. At first, to reduce queuing time variability, we introduce a simple WLC system; next we integrate it with a predictive tool that, based on the system state, can accurately forecast the total time needed to manufacture and deliver a job. Due to the non-linearity among dependent and independent variables, forecasts are made using a multi-layer-perceptron; yet, to have a comparison, the effectiveness of both linear and non-linear multi regression model has been tested too. Anyhow, if due dates are endogenous (i.e. set by the manufacturer), they can be directly bound to this internal estimate. Conversely, if they are exogenous (i.e. set by the customer), this approach may not be enough to minimize the percentage of tardy jobs. So, we also propose a negotiation scheme, which can be used to extend exogenous due dates considered too tight, with respect to the internal estimate. This is the main contribution of the paper, as it makes the forecasting approach truly useful in many industrial applications. To test our approach, we simulated a 6-machines job-shop controlled with WLC and equipped with the proposed forecasting system. Obtained performances, namely WIP levels, percentage of tardy jobs and negotiated due dates, were compared with those of a set classical benchmark, and demonstrated the robustness and the quality of our approach, which ensures minimal delays.

2021 - Experiencing the Role of Cooperation and Competition in Operations and Supply Chain Management with a Multiplayer Serious Game [Relazione in Atti di Convegno]
Galli, M.; Mezzogori, D.; Reverberi, D.; Romagnoli, G.; Zammori, F.
abstract

We present an innovative, cooperative, and competitive multiplayer serious game, suited for the educational needs of supply chain and operation management post-graduate students. Hence, the objective is to satisfy the ever-increasing requirement of students to have the ability to experience and practice the theory learned in traditional ways, for active knowledge acquisition. To cope with such needs, we designed and implemented a multiplayer online serious game, that provides players with a realistic industrial experience, and teaches them how to take a whole range of day-to day and medium-term challenging decisions. Learners are divided into teams, each one representing an Original Equipment Manufacturer (OEM), in every team the students will collaborate and will compete in the same market, and sharing a limited set of suppliers. To this aim they have to define a strategy to target the best market segmentation. Teachers have the possibility to investigate the decision patters of the learners, analyze KPIs and learning analytics, to better understand the learning process and guide the learners in their educational journey. By means of a preliminary questionnaire, the interest in using the serious game to study operation management was confirmed. In addition, the game was tested by a small group of students, who acknowledged the effectiveness of the game's dynamics as a tool to complement traditional teaching methods.

2021 - Exploiting Machine Learning and Industry 4.0 traceability technologies to re-engineering the seasoning process of traditional Parma's Ham [Relazione in Atti di Convegno]
Mezzogori, D.; Zammori, F.
abstract

The work presents a Machine Learning approach for predicting the quality of the curing process of Parma ham, combined with a study of business process re-engineering, based on RFID and Deep Learning technologies for automatic recognition and tracking of the hams along the curing process. Quality management has proven to be crucial for efficient and effective processes, even more so for the food industry, both for commercial and regulatory purposes. This is even more evident in artisanal-based processes, such as the one concerning traditional Prosciutto di Parma seasoning. The work proposes and compares a Feed-Forward Neural Network and a Random Forest for predicting the distribution of the number of hams by commercial quality class of a given aging lot. Such a prediction, based on origin, process, and curing data, can provide early indications of process output, enabling strategic commercial competitive advantages. The importance of the genetic component in the determination of the final quality is also evaluated, as it is considered one of the most influential external variables. Moreover, following the AS-IS description of the current process, a redesign is proposed, to enable data collection and tracking of individual ham in order to propose a future precision prediction system that would allow even finer control of the process.

2021 - Guideline to Safety and Security in Federated Remote Labs [Articolo su rivista]
Uckelmann, D.; Mezzogori, D.; Esposito, G.; Neroni, M.; Reverberi, D.; Ustenko, M.; Baalsrud-Hauge, J.
abstract

The interest of the educational community in the laboratory- (lab) based education has grown steadily. As remote labs have started to be a reliable alternative to traditional hands-on labs, security and safety issues are becoming increasingly important, as their interconnected nature raises new and challenging issues. The complexity increases when multiple institutions are involved in a federated lab infrastructure. This paper provides a guideline for assessing safety and security in federated labs following the VDI/VDE 2182 guideline and verifies the concept based on remote labs in three different academic institutions.

2021 - Machine Learning for industrial applications: A comprehensive literature review [Articolo su rivista]
Bertolini, M.; Mezzogori, D.; Neroni, M.; Zammori, F.
abstract

Machine Learning (ML) is a branch of artificial intelligence that studies algorithms able to learn autonomously, directly from the input data. Over the last decade, ML techniques have made a huge leap forward, as demonstrated by Deep Learning (DL) algorithms implemented by autonomous driving cars, or by electronic strategy games. Hence, researchers have started to consider ML also for applications within the industrial field, and many works indicate ML as one the main enablers to evolve a traditional manufacturing system up to the Industry 4.0 level. Nonetheless, industrial applications are still few and limited to a small cluster of international companies. This paper deals with these topics, intending to clarify the real potentialities, as well as potential flaws, of ML algorithms applied to operation management. A comprehensive review is presented and organized in a way that should facilitate the orientation of practitioners in this field. To this aim, papers from 2000 to date are categorized in terms of the applied algorithm and application domain, and a keyword analysis is also performed, to details the most promising topics in the field. What emerges is a consistent upward trend in the number of publications, with a spike of interest for unsupervised and especially deep learning techniques, which recorded a very high number of publications in the last five years. Concerning trends, along with consolidated research areas, recent topics that are growing in popularity were also discovered. Among these, the main ones are production planning and control and defect analysis, thus suggesting that in the years to come ML will become pervasive in many fields of operation management.

2021 - Non-Traditional Labs and Lab Network Initiatives: A Review [Articolo su rivista]
Esposito, G.; Mezzogori, D.; Reverberi, D.; Romagnoli, G.; Ustenko, M.; Zammori, F.
abstract

Lab-based education has always played an important role in teaching students. Making remote and virtual labs communicate with one another by creating networks of labs can enhance the traditional way of learning as well as reduce the costs of implementing and using labs. This paper provides a review of the literature on non-traditional labs and lab network initiatives up to 2020. With the term ‘non-traditional labs’, we mean virtual, remote and hybrid labs, whereas with the term ‘lab network’, we indicate a set of two or more cooperating labs typically connected through the internet. In this study, we used a recent and comprehensive framework for data collection, organization, and analysis to gather information on 40 non-traditional labs and lab network initiatives. Thanks to this framework, the outcomes of our work highlight interesting trends of lab-based education, which pertain to didactical, organizational, and technical aspects.

2021 - Safety and Security in Federated Remote Labs – A Requirement Analysis [Relazione in Atti di Convegno]
Uckelmann, D.; Mezzogori, D.; Esposito, G.; Neroni, M.; Reverberi, D.; Ustenko, M.
abstract

Recently, the interest of the educational community in laboratory- (lab-) based education has grown steadily. As remote and virtual labs have started to be a reliable alternative to traditional hands-on labs, security and safety issues are becoming increasingly important, especially in the case of remote laboratories, as their interconnected nature raises new and challenging issues. When multiple institutions are involved in a federated labs infrastructure, the complexity increases. Since a structured approach to assess safety and security for federated remote labs is missing, this paper aims at clarifying the general requirements to be considered and proposes a general concept for assessing safety and security in federated labs. Firstly, we analyze the current state on safety and security in remote labs by means of a literature review. Secondly, we investigate existing requirements and define operational requirements for a safety and security guideline in federated remote labs. Thirdly, we provide an overview about standardization approaches and existing guidelines and suggest a guideline, which matches our requirements analysis.

2021 - Software-based shielding for real-time inventory count in different store areas: A feasibility analysis in fashion retail [Articolo su rivista]
Esposito, G.; Mezzogori, D.; Neroni, M.; Rizzi, A.; Romagnoli, G.
abstract

RFID is an established technology and its implementation has been increasing steadily in different industries in the last decades. An important and relatively recent RFID breakthrough has been that of moving the level of tagging from pallet- or case-level, to item-level. This development has opened up a new set of use cases and benefits, especially in retail. One of these new use cases is the estimation of items' location by positioning and tracking the tags attached to them. This problem is often seen as a classification problem, especially when tags that are read at the retail store must be located either in the sales floor or in the backroom area. The typical approach to ease this classification consists of physically shielding the interested areas via hardware installations, although this solution is expensive and lacks flexibility. In this paper, we present a different solution, namely a software-based shielding approach, to address the classification problem. Our solution makes use of item-level RFID tags and is based on the well-known logistic regression. Whenever a reading session is performed by means of a handheld reader, the classification model estimates in real-time (i.e. within a few seconds) which tagged items are in the same area of the reader and which are not, with no need of any shielding hardware installation. According to the validation preliminary tests presented in this paper, in which we simulated a fashion retail store, the proposed approach has an overall average accuracy of 95.5%.

2021 - Workload control with shifting bottlenecks: Norms optimisation through design of experiments [Articolo su rivista]
Zammori, F.; Ferretti, C.; Ganugi, P.; Mezzogori, D.
abstract

Workload control is a production planning and control system designed to overcome the trade-off between high throughput and short and stable lead time. Specifically, work-in-process is continuously monitored, and new jobs are not admitted in the shop floor until work-in-process drops below predefined threshold values or norms. To exploit performance, norms should be fine-tuned to minimise queues, without generating starvation at the bottleneck machines. The optimisation process is straightforward for a perfectly balanced system, but much harder in case of shifting bottlenecks. The paper focuses on this issue and presents an innovative procedure, based on the response surfaces method, which allows one to optimise the norms in a precise way, keeping unaltered the maximal or desired throughput of the manufacturing system. A comprehensive simulation analysis demonstrated the quality of the proposed approach and showed the importance of using different norms to boost the overall performance of the manufacturing system.

2020 - A constructive algorithm to maximize the useful life of a mechanical system subjected to ageing, with non-resuppliable spares parts [Articolo su rivista]
Zammori, F.; Bertolini, M.; Mezzogori, D.
abstract

In this paper, the focus is on mechanical systems that, like a ship or a submarine, perform risky missions and that must remain operating for the whole mission time. Missions take place far from the operational base and so, in case of failures, although repairs are possible, spares parts cannot be resupplied. Hence, given space constraints, the problem is to define the optimal set of spare parts that should be taken aboard, to maximize the probability to complete the mission. To solve this problem, we propose a constructive algorithm that generates the Pareto Optimal Frontier of all the non-dominated solutions, in terms of the system's reliability and of required space. At first, the algorithm is formulated in a generic way; next, it is contextualized to the common case of Weibull distributed failure times. In this condition, the underlying equations of the model cannot be solved in closed form and an approximated procedure is proposed and validated through extensive numerical simulation. (C) 2020 by the authors; licensee Growing Science, Canada

2020 - Digilab4u: General architecture for a network of labs [Relazione in Atti di Convegno]
Galli, M.; Mezzogori, D.; Reverberi, D.; Uckelmann, D.; Ustenko, M.; Volpi, A.
abstract

The paper presents the architecture designed to create a network of remote and virtual laboratories, to integrate and enhance them with new technologies and methods for lab-based education, within five universities inside the Open Digital Lab For You (DigiLab4U) project. Many factors lead to an increase in interest in networks of labs. The main ones aim on increasing the exploitation of laboratory equipment, together with the increasing necessity of practical experience in students’ careers. Lead by this necessity, the network developed an education environment with a strong focus on Industry 4.0 and Industrial Internet of Things. Moreover, its aim is the integration of new technologies and alternative teaching methods within the environment through an iterative approach. Compliant with these objectives and considering the standards available for such concepts, a new architecture of a network has been created based on the Industrial Reference Internet Architecture. With respect to these standards, the general architecture has been built as a client-server architecture composed of three elements: (i) Client, (ii) Web server, and (iii) Local server. We also took into consideration that the project aims to enlarge the network in the future, making it accessible from different institutions all over the world, to enable the learners to perform new experiments and enhance their skills. Besides, it enables the integration of technologies such as Serious Games and Learning Analytics, as they are becoming more and more widespread and necessary for teaching and assessing the students. To ease the understanding and the scalability of the network, three different points of view architecture has been proposed, by splitting and describing it into software, hardware, and logical perspectives.

2019 - Allocation of items considering unit loads balancing and joint retrieving [Relazione in Atti di Convegno]
Bertolini, M.; Mezzogori, D.; Neroni, M.
abstract

In the last years, the diffusion of lean thinking had a big impact, not only in manufacturing, but in logistics too. Because of one-piece-flow production and the point of view on inventory that considers it as inefficiency, purchasing and shipping batches have become smaller and more varied, requiring to the suppliers more shipments per day, a shorter throughput time, and, in general, higher performances. To improve retrieving performance in automated warehouses, many routing and scheduling procedures are presented in literature, although retrieving can be speeded up starting from the input phase using a correct allocation policy. In this paper, we present a procedure inspired by Genetic Algorithm (GA) for allocation of items inside unit loads. The procedure considers two aspects that are hardly studied in literature, such as unit load weight balancing and market basket analysis aimed at closed allocation of items that are usually jointly retrieved. The first one is a physical necessity, especially required in the steel sector, where objects stocked are heavy. The second one improves the retrieving performance and it increases the possibility to satisfy more order lines with fewer travels. The algorithm proposed was tested using the digital twin of an existing warehouse and comparing the results with the current performances of the real system.

2019 - An entity embeddings deep learning approach for demand forecast of highly differentiated products [Relazione in Atti di Convegno]
Mezzogori, D.; Zammori, F.
abstract

The paper deals with Deep Learning architectures applied to demand forecasting in a complex environment. The focus is on a famous Italian Fashion Company, which periodically performs a sales campaign, to presents its new products' line and to collect customers' orders. Although production follows an MTO strategy, fabrics must be purchased in advance and a forecasting system is required to predict the total quantity sold for each product, at the early stages of the campaign. Due to high product variability, the forecasting system must consider products' similarities and the evolution of customers taste. Additionally, customer and product data are mostly described by categorical variables (hard to reconcile with a predictive task) and, unfortunately, time-series techniques cannot be used because of a sparse dataset. Given these criticalities, we propose an end-to-end approach based on Deep Neural Networks and on Entity Embeddings. A first neural network is trained to predict the total quantity of a given product ordered by a specific customer. Different Embeddings are learned for each customer and product categorical attribute. This gives the network the ability to effectively learn the complex and evolving relationships between products characteristics and customers taste. Next, freezing the learned product's embeddings, a second Recurrent Neural Network is trained to predict the total amount ordered for a given product, incorporating real-time data of customers' orders of the ongoing sales campaign. Ten years of sales have been analyzed and the approach, tested on unseen sales campaigns, has outperformed the forecasting algorithm currently adopted by the fashion firm.

2019 - Comparison of new metaheuristics, for the solution of an integrated jobs-maintenance scheduling problem [Articolo su rivista]
Bertolini, M.; Mezzogori, D.; Zammori, F.
abstract

This paper presents and compares new metaheuristics to solve an integrated jobs-maintenance scheduling problem, on a single machine subjected to aging and failures. The problem, introduced by Zammori et al. (2014), was originally solved using the Modified Harmony Search (MHS) metaheuristic. However, an extensive numerical analysis brought to light some structural limits of the MHS, as the analysis revealed that the MHS is outperformed by the simpler Simulated Annealing by Ishibuchi et al. (1995). Aiming to solve the problem in a more effective way, we integrated the MHS with local minima escaping procedures and we also developed a new Cuckoo Search metaheuristic, based on an innovative Levy Flight. A thorough comparison confirmed the superiority of the newly developed Cuckoo Search, which is capable to find better solutions in a smaller amount of time. This an important result, both for academics and practitioners, since the integrated job-maintenance scheduling problem has a high operational relevance, but it is known to be extremely hard to be solved, especially in a reasonable amount of time. Also, the developed Cuckoo Search has been designed in an extremely flexible way and it can be easily readapted and applied to a wide range of combinatorial problems. (C) 2018 Elsevier Ltd. All rights reserved.

2019 - Deep learning and WLC: How to set realistic delivery dates in high variety manufacturing systems [Relazione in Atti di Convegno]
Mezzogori, D.; Romagnoli, G.; Zammori, F.
abstract

The focus is on workload control, a production planning and control technique that reduces and stabilizes the total throughput time. In these conditions, defining realistic delivery dates should become easier, yet the use of basic techniques often proves to be ineffective. Hence, we propose using statistical and/or neural network techniques to estimate, starting from the current workload of the job shop, the expected lead time of entry jobs, and to use this estimation to define reliable delivering dates. To test the approach, we simulated a 6-machines job-shop and we make predictions using a multi-regressive linear model and a multi-layer neural network. In terms of tardy jobs, both approaches performed very well, with the neural network providing the best results.

2019 - Optimizing Retrieving Performance of an Automated Warehouse for Unconventional Stock Keeping Units [Relazione in Atti di Convegno]
Bertolini, Massimo; Esposito, Giovanni; Mezzogori, Davide; Neroni, Mattia
abstract

In recent years, the diffusion of automated warehouses in different industrial sectors has fostered the design of more complex automated storages and handling solutions. These circumstances, from a technological point of view, have led to the development of automated warehouses that are very different from the classic pallet Automated Storage and Retrieval Systems (AS/RS), both in terms of design and operating logic. A context in which these solutions have spread is the steel sector. Warehouses with innovative layouts and operating logics have been designed to move metal bundles of different sizes, weights and quality levels, instead of standard, interchangeable stock keeping units. Moreover, picking is often not allowed in these warehouses, due to the configuration of the loading units. In this work we propose a meta-heuristic algorithm based on the Simulated Annealing (SA) procedure, which aims to optimize performance during the retrieving phase of an automated warehouse for metal bundles. The algorithm translates the customers’ requests, expressed in terms of item code, quality and weight into a list of jobs. The goal is to optimize the retrieving performance, measured in missions per hour, minimizing the deviations in quality and weight between customer request and the material retrieved. For the validation, a simulation model of an existing warehouse has been created and the performance of the algorithm tested on the simulation model has been compared with the current performance of the warehouse.