Laura Cattaneo

Smart factories build on cyber-physical systems as one of the most promising technological concepts. Within smart factories, condition-based and predictive maintenance are key solutions to improve competitiveness by reducing downtimes and increasing the overall equipment effectiveness. Besides, the growing interest towards operation flexibility has pushed companies to introduce novel solutions on the shop floor, leading to install cobots for advanced human-machine collaboration. Despite their reliability, also cobots are subjected to degradation and functional failures may influence their operation, leading to anomalous trajectories. In this context, the literature shows gaps in what concerns a systematic adoption of condition-based and predictive maintenance to monitor and predict the health state of cobots to finally assure their expected performance. This work proposes an approach that leverages on a framework for fault detection and diagnostics of cobots inspired by the Prognostics and Health Management process as a guideline. The goal is to habilitate first-level maintenance, which aims at informing the operator about anomalous trajectories. The framework is enabled by a modular structure consisting of hybrid series modelling of unsupervised Artificial Intelligence algorithms, and it is assessed by inducing three functional failures in a 7-axis collaborative robot used for pick and place operations. The framework demonstrates the capability to accommodate and handle different trajectories while notifying the unhealthy state of cobots. Thanks to its structure, the framework is open to testing and comparing more algorithms in future research to identify the best-in-class in each of the proposed steps given the operational context on the shop floor.

Technological advancements are leading to a world where digital twins will become integral to manufacturing operations management. While wide-ranging applications of digital twins are being researched, robust production scheduling remains an enduring challenge, especially considering the numerous sources of uncertainty in a complex manufacturing system that can affect the validity of the obtained solution. Thus, the article proposes a Prognostics and Health Management (PHM)-enabled digital twin framework to perform job scheduling for a flow shop scheduling problem considering real-time equipment health state. The framework combines the adoption of a Genetic Algorithm optimizer with data-driven modelling leveraging algorithms like Principal Component Analysis and models like Discrete Event Simulation with the purpose to solve the engineering task of scheduling at hand. Building on such a technological blend, the framework incorporates the degradation and fault detection and diagnosis of failure modes across multiple components. The effect of degradation and faults on job processing times is learned as a distribution from the field data. The proposed framework is then validated in a laboratory environment where degradation is produced by inducing degradation and faults in the equipment. By means of various experiments, the optimized makespan is compared for the output schedules in different configurations. When equipment is degraded, production scheduling with PHM-enabled field-synchronized digital twin results in better makespan estimation, if compared to the digital twin without PHM. This shows the superiority of the framework in terms of more realistic makespan estimations, which finally corresponds to improved production schedule optimization, sensitive also to degraded states.

The world is witnessing an all-level digitalization that guides the industry and business to a restructuration in order to adapt to the new requirements of the surrounding environment. That change also concerns the labour of the technical professionals and their formation. As a consequence of this deep consciousness-raising, this chapter will investigate and develop simulation models based on the current digitalization. The aim of this chapter is the exposition of a real case development of “digital twin” models framed as part of the condition-based maintenance paradigm to improve real-time assets operation and maintenance. This model contributes by providing real-time results that could turn into a basis for the industrial management decisions and place them in the Industry 4.0 paradigm environment.

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.

Digitisation offers manufacturing companies new opportunities to improve their operations and competitiveness in the market by unleashing potentialities related to real-time monitoring and control of operating machines. Through condition-based and predictive maintenance, the knowledge about the health state and probability of failure of the machines is improved for better decision-making. Amongst them, CNC machine tools do represent a complex case from a maintenance viewpoint as their operations are ever-changing and their high reliability brings to a lack, or limited set, of run-to-failure data. To address the problem, the research work proposes an operations-aware novelty detection framework for CNC machine tools based on already-in-place controllers. The framework is based on statistical modelling of the behaviour of the machine tools, namely through gradient boosting regression and Gaussian mixture models, to identify the health state considering varying operations through time. The proposed solution is verified on sixteen multi-axis CNC machine tools in a large manufacturing company. The results show that the proposed solution can effectively support maintenance decisions by informing on the health states while discerning between varying operations and abnormal/faulty states of interest. This solution represents a brick in a cloud-edge-based industrial information system stack that can be further developed for shop floor-integrated decision-making.

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.

The capability to predict the behaviour of machines is nowadays experiencing a tremendous growth of interest within Industry 4.0-based manufacturing systems. The route to this end is not straightforward when Run-To-Failure (RTF) data are poorly available or not available at all, thus a strategy must be properly defined. In this proposal, assuming no RTF data, a novelty detection is combined with random coefficient statistical modelling for Remaining Useful Life (RUL) prediction. This approach is formalized by means of a reference framework extending the ISO 13374 - OSA-CBM standards. The framework guides the integration of novelty detection and RUL prediction finally implemented in the scope of a Flexible Manufacturing Line part of the Industry 4.0 Lab of the School of Management of Politecnico di Milano.