Laura Cattaneo

This work illustrates the preliminary results obtained using MATLAB in the Multivariate Calculus module of the first-year Analysis course of the Industrial and Management Engineering Bachelor's degree at LIUC. In the pilot study, MATLAB was made available to a subset of the class during extra-class time, and a questionnaire was administered to this sample of students to gather feedback on their experience. The results were analysed to compare the performance of students who used MATLAB with that of the rest of the class, identifying the strengths and weaknesses of this approach, and suggesting potential future improvements.

The current work contributes to stochastic hybrid flow shop scheduling. After a thorough literature analysis, it is firstly evident that works on stochastic flow shop scheduling are still limited in number; moreover, they often rely on simplifying assumptions; eventually, they may lack in a full viability for industrial application of the proposed models or algorithms. Considering these limitations, the present work proposes a scheduling framework based on Discrete Event Simulation and on Genetic Algorithms. The work stems from a previously published work, therefore, contributes by identifying some inconsistencies in the original algorithm in the so called “limit cases”. Overall, the paper proposes an alternative fitness function to avoid the generation of such inconsistencies; besides, it considers a realistic probability distribution to describe the stochastic processing times for robust scheduling of a hybrid flow shop. The end purpose is to move towards a viable application of optimization algorithms in industrial environments.

Production scheduling has a long history of research but still presents open challenges, when considering production systems with uncertainty. The digitization, and in particular Digital Twins, may play a role in progressing the research field. The paper proposes a framework to exploit the Digital Twin synchronization with the field to include health assessment models into the simulation-based optimization of the production system scheduling. The health assessment is based on a modelling of failure modes and monitoring signals to connect the physical production resources to health and operating states in order to have a more accurate prediction of the makespan with respect to the actual makespan of the production system. The scheduling framework is validated through a laboratory application in the Industry 4.0 Lab at the School of Management of Politecnico di Milano. Copyright (C) 2022 The Authors.

In the recent years, manufacturing companies are investing in sensors and information systems to implement condition-based maintenance (CBM), thus pursuing the benefits of digital transformation. Nevertheless, to implement CBM as advanced digital system, significant investment should be made to gather and manage all needed data from different sources; besides, qualified human resources are required for data analytics. Given this premise, the present paper aims at describing an industrial project where an advanced CBM system for high-critical industrial fans is implemented in a foundry. Indeed, the goal is to use already available data from the extant automation and additional vibration data to develop state detection and to identify any abnormal behaviour of the assets. The evidence from the project is that: i) the vibration analysis remains an easy and cost-effective, yet well-performing way, to monitor the state and the health of machines with rotating components; ii) automatic regulation system may mask the underlying behaviour and degradation of complex assets; iii) already gathered data from extant automation are mainly focused on the process parameters and provides an aid to describe the working state of the assets, but have limited potentialities for novelty detection. Eventually, the paper envisions future development of a more integrated approach aimed at a combined elaboration of data from the extant automation and vibration data. The integrated approach is under development, hence the paper provides insights on the on-going analyses.

This paper aims at describing the key role of Data Quality along the entire development of a Prognostics and Health Management process based on Industrial Artificial Intelligence solutions and ready for industrial application. This is discussed through an industrial case in the textile sector where the importance of Data Quality emerges in different aspects. The industrial case leads to lessons learned useful for further research on a framework for Data Quality in AI-based maintenance systems.

Nowadays, smart factories more and more rely on key enabling technologies to optimize the management of operations. In the maintenance context, predictability is a major characteristic required for advanced monitoring and controlling systems, embedded in Cyber-Physical Systems (CPS), which are the building blocks of smart factories. As such, methodologies and tools proper of the Prognostics and Health Management (PHM) body of knowledge, represent the background on which a company should build their competitive advantage. However, promoting the application of PHM in current industrial scenario is not only a matter of digital technologies, but it encompasses engineering methodologies. These methodologies should be made available to learners so to transfer knowledge to industry. Therefore, a learning-by-doing approach is proposed, which aims at showing how the current software tools provide per se a complete platform for PHM for teaching purposes, without a strong requirement of real testbeds, at least at first sight. Also, the selection of MATLAB allows to transfer knowledge to learners with few or no programming skills. It is demonstrated how the engineering methodologies and tools underlying a robust PHM system could be developed during lectures independently from the availability of a laboratory or industry-like environment if the key characteristics of PHM are properly formalised. Therefore, the basic idea is to support the dissemination of a practical background about PHM, both in physical and virtual classrooms, aimed at providing advanced understanding of CPS-based smart factories.

Today data analytics is vital for companies willing to extrapolate information from their assets to support asset-related decisions. Information is relevant but not enough to exploit the potentials hidden in domain-related knowledge. The focus of this paper is predictive maintenance, herein knowledge is relevant to support the design of a Prognostics and Health Management (PHM) process to achieve a reliable decision-making. In this scope, the paper builds on the presumption that data analytics can be empowered by semantic data modelling to conceptualise and formalize data before the application of any kind of advanced algorithm implementing a data-driven approach. Thus, this research aims at proposing a semantic data model that guides the data analytics by revealing data characteristics and inter-relationships and guarantees completeness to finally support the PHM process. A data-driven approach, joining semantic data modelling and analytics, is proven through examples taken from the controlled environment of the Industry 4.0 Laboratory of the School of Management of Politecnico di Milano.

In the Industry 4.0 vision, Prognostics and Health Management (PHM) is expected to assist domain experts in the generation of maintenance decisions. PHM relies on the processing of data sensed from the manufacturing plant for inferring the future performance of production systems. The acquisition and management of data brings different challenges such as data integration, heterogeneity, search usability and volume. To be best of authors’ knowledge, an information system for sharing maintenance data able to fulfill the aforementioned challenges is not available yet. XRepo is proposed within this paper and faces three of the identified challenges through selected functionality: i) Heterogeneity: stored data is complaint with a standard format that includes the information necessary for performing PHM analysis; ii) Integration: data is uploaded to the repository through files or web services; iii) Search usability: stored data can be filtered by criteria and downloaded. This work is meant to be an initial effort towards the generation of a common information system for PHM analysis.

The use of Condition-based Predictive Maintenance (CBPdM) has grown significantly due to the Industry 4.0 movement and to the advancements in data acquisition, gathering, storing and analytics. In modern maintenance engineering education, there is the need to include CBPdM alongside with traditional maintenance approaches. Within this paper, a case study is proposed for education in Fault Diagnosis Assessment (FDA) using the Problem-based Learning (PBL) approach. Following a PBL approach, the proposed case study consists of a ‘close-to-real-life’ problem and allows the implementation of most of the steps of FDA, and the assessment of the answer through objective metrics. We hope that this work may impulse the production of more educational case studies within the topic of CBPdM.

The present research illustrates a Digital Twin Proof of Concept to support machine prognostics with Low Availability of Run-to-Failure Data. Developed in the scope of the Industry 4.0 Lab of the Manufacturing Group of the School of Management of Politecnico di Milano, the Digital Twin is capable to run in parallel to the drilling machine operations and, as such, it enables to predict the evolution of the most critical failure mode, that is the imbalance in the drilling axis. The real-time monitoring of the drilling machine is realized with a low-cost and retrofit solution, which provides the installation of a Raspberry-Pi accelerometer, able to enhance the extant automation. Relying on a joint use of real-time monitoring and simulation, the Digital Twin implements a random coefficient statistical method through the so-called Exponential Degradation Model, eventually demonstrating to increase the prediction precision as monitoring data arrives. The Digital Twin Proof of Concept is described according to the entire process from data acquisition to Remaining Useful Life prediction, following the MIMOSA OSA-CBM standards.