Artificial Intelligence-based data-driven prognostics in Industry: A survey

TL;DR: This extensive experimental research provides strong empirical proof of the revolutionary power of deep learning algorithms when integrated into Industry 5.0, providing tangible proof of the critical roles deep learning algorithms play in streamlining production lines, increasing energy economy, and boosting product quality in the ever-changing Industry 5.0 environment.

TL;DR: This paper explores AI's role in Industry 5.0, focusing on its implementation at a local glassware company, and examines strategies for market leadership through AI adoption, highlighting its potential to enhance product consistency, reduce costs, and promote sustainability.

Abstract: Purpose This study develops a theoretically grounded understanding of Industry 5.0 (IR5) and proposes an integrative framework to clarify its organisational implications for leading change in digitally transforming socio-technical environments. Design/methodology/approach The study employs a structured integrative review of 160 peer-reviewed articles and seven institutional reports, guided by socio-technical systems theory, to inform the analysis. Findings This study offers a new, concise definition of Industry 5.0 (IR5) as a socially constructed framework that reconfigures industrial systems by embedding the principles of human-centricity, sustainability and resilience into advanced digitalisation. It introduces the IR5 CPC model (conditions-processes-consequences), a comprehensive framework identifying key enabling conditions (e.g. visionary leadership and digital readiness), three digitalisation logics (resilience, sustainability and well-being-driven) and dual outcomes (benefits and risks) across organisational, economic, societal and environmental domains. Research limitations/implications This study encourages empirical research on how AI- and ERP-based (enterprise resource planning) standard operating procedures (SOPs) facilitate IR5-aligned transformation. It also recommends multi-theoretical approaches to capture its socio-technical complexity. Practical implications This study facilitates change leaders in designing phased, ethically aware digital strategies and supports policymakers in aligning incentives and regulations with sustainable, inclusive digitalisation. Originality/value This is the first study to provide a theoretically integrated definition and framework of IR5, bridging fragmented literature and advancing future inquiry.

TL;DR: This survey tries to provide a structured and comprehensive overview of the research on anomaly detection by grouping existing techniques into different categories based on the underlying approach adopted by each technique.

TL;DR: These experiments confirm the hypothesis that the greedy layer-wise unsupervised training strategy mostly helps the optimization, by initializing weights in a region near a good local minimum, giving rise to internal distributed representations that are high-level abstractions of the input, bringing better generalization.

TL;DR: A new learning algorithm for Boltzmann machines that contain many layers of hidden variables that is made more efficient by using a layer-by-layer “pre-training” phase that allows variational inference to be initialized with a single bottomup pass.