An IoT-based and cloud-assisted AI-driven monitoring platform for smart manufacturing: design architecture and experimental validation

Abstract

PurposeThis work aims at proposing a novel Internet of Things (IoT)-based and cloud-assisted monitoring architecture for smart manufacturing systems able to evaluate their overall status and detect eventual anomalies occurring into the production. A novel artificial intelligence (AI) based technique, able to identify the specific anomalous event and the related risk classification for possible intervention, is hence proposed.Design/methodology/approachThe proposed solution is a five-layer scalable and modular platform in Industry 5.0 perspective, where the crucial layer is the Cloud Cyber one. This embeds a novel anomaly detection solution, designed by leveraging control charts, autoencoders (AE) long short-term memory (LSTM) and Fuzzy Inference System (FIS). The proper combination of these methods allows, not only detecting the products defects, but also recognizing their causalities.FindingsThe proposed architecture, experimentally validated on a manufacturing system involved into the production of a solar thermal high-vacuum flat panel, provides to human operators information about anomalous events, where they occur, and crucial information about their risk levels.Practical implicationsThanks to the abnormal risk panel; human operators and business managers are able, not only of remotely visualizing the real-time status of each production parameter, but also to properly face with the eventual anomalous events, only when necessary. This is especially relevant in an emergency situation, such as the COVID-19 pandemic.Originality/valueThe monitoring platform is one of the first attempts in leading modern manufacturing systems toward the Industry 5.0 concept. Indeed, it combines human strengths, IoT technology on machines, cloud-based solutions with AI and zero detect manufacturing strategies in a unified framework so to detect causalities in complex dynamic systems by enabling the possibility of products’ waste avoidance.

Industry 5.0 applications for sustainability: A systematic review and future research directions

“…The present studies discussed the implications of industry 5.0 for smart logistics (e.g., Jafari et al, 2022;Petrillo et al, 2022;Thakur & Kumar Sehgal, 2021). However, modern smart logistics-based manufacturing systems also need to cover other crucial operations, like production planning and maintenance scheduling duties, in sing.…”

“…In the future, it can be applied as a descriptive tool to assess the influence of the event and characterize and measure the dynamics of the intended outcome before and after it. This approach has been suggested to examine the impacts of Kopacek, 2021;Thakur & Kumar Sehgal, 2021;Johri et al, 2021;Fraga-Lamas et al, 2021;Li et al, 2022;Iyengar et al, 2022;Coronado et al, 2022;Lu et al, 2022;Sindhwani et al, 2022;Petrillo et al, 2022;Henriksen et al, 2022;Jafari et al, 2022 Ecosystems advancement 7 (15%) Green manufacturing ( 2 Salimova et al, 2020;Longo et al, 2020;Cillo et al, 2021;Xu et al, 2021;Alvarez-Aros & Bernal-Torres, 2021;Battini et al, 2022;Huang et al, 2022;Kolade & Owoseni, 2022;Orso et al, 2022;Gagnidze & Tbilisi, 2022;Yuan et al, 2022;Grabowska et al, 2022;Waheed et al, 2022;Madhavan et al, 2022;Guruswamy et al, 2022;Zizic et al, 2022;Saniuk et al, 2022;Kaasinen et al, 2022;Akundi et al, 2022;Ivanov, 2022 17 (36%) The previous studies utilized observations, in-depth interviews, and case study methods (Cillo et al, 2021;Kolade & Owoseni, 2022;Salimova et al, 2020). Industry 5.0 for sustainability used techniques like interviews, which are not practically viable.…”

“…ICT will therefore impact routineness, digitization, and structural change in the future, allowing for a more in-depth study of technological unemployment. Moreover, as a part of continued evolution, the suggested smart logistics-based designs may come with an additional module for problem solving (Petrillo et al, 2022). This will be useful in identifying alternative solutions, determining their efficacy, and evaluating their effects on other production processes in future investigations.…”

Guest editorial: Opportunities and threats in providing remote access to manufacturing-related environments

“…Although the basis of digital transformation are ICTs and their shop floor implementation, also supported by remote connection, a pivotal role in future production systems will still be played by humans and by their interaction with the systems for monitoring and control purposes. The first contribution we present for this SI is Petrillo et al (2023). In this paper, the authors apply action research with experimental validation.…”