Digital Product Passports: AI and Lifecycle Intelligence for Sustainable Industry

The accelerating pace of digital transformation in industrial environments demands more than incremental improvements. It requires the fundamental redesign of how product lifecycle information is captured, managed, and acted upon. The ESPR – Ecodesign for Sustainable Products Regulation (EU 2024/1781) requires that industrial products be designed with reparability, durability, and resource efficiency as key parameters. Moreover, the Corporate Sustainability Reporting Directive (CSRD) mandates companies to disclose detailed environmental, social, and governance (ESG) performance, including product-level ecological data. The Digital Product Passport (DPP) is a foundational instrument within this regulatory landscape. Defined as a digital record containing integrated information across the entire product lifecycle, from raw material origin and manufacturing through use, maintenance, and end-of-life recycling, DPPs will become mandatory for several product categories from 2026 onwards under the ESPR framework, with priority given to textiles, electronics, and batteries. Current DPP approaches focus primarily on product composition, recycling routes, and compliance metadata. DPP data includes general information (material, product, performance), value chain information (processes and compliance), sustainability and circularity information, and repair and maintenance information (repair, disassembly, refurbishment).AI-driven decision-support systems are a significant aspect of industrial environments, directly affecting the economic, environmental, and social impacts of modern businesses. Industry 5.0 standards require redefining industries as human-centric ecosystems, emphasising transparency, sustainability, and the reliability of production processes. Current DPP approaches, however, remain static and they do not dynamically reflect actual operating conditions, equipment degradation or real-time manufacturing parameters. This constitutes a critical gap, as the true environmental footprint and product quality are directly and continuously shaped by the performance of industrial equipment.Predictive and prescriptive maintenance (P2M) methodologies offer a transformative path forward. P2M leverages the integration of all available industrial information, structured or unstructured, with cutting-edge technological tools and specifications, such as blockchain, IoT Sensoring, QR Technology advances, Big Data Analytics, and AI predictive and prescriptive solutions, to support decision-making. Integrating P2M into DPP creates a performance-oriented ecosystem that continuously updates the digital passport, capturing information such as energy consumption, water usage, and CO2 emissions at the batch level.This Research Topic responds to this need by positioning novice human- and value-centred DPP applications that directly enhance the transparency of developed products while simultaneously increasing the productivity, safety, and system reliability of industrial machinery. Furthermore, from an environmental aspect, machinery and equipment production are significant contributors to the overall carbon footprint of industrial processes, and modern predictive or prescriptive maintenance techniques could reduce this footprint. Modern P2M techniques could substantially reduce this footprint by ensuring machinery operates at peak efficiency throughout its operational cycle. Compounding the DPP of industrial machinery with respective predictive and prescriptive maintenance outputs, prognosing the remaining useful life of the systems and suggesting suitable maintenance procedures can significantly increase the impact of DPP approaches.We welcome original research articles, review manuscripts and methods articles covering, but not restricted to:- Innovative DPP design with demonstrations in web-based or industrial environments- Techniques for dynamic DPP allocation utilizing heterogenous data inputs acquired in an agile industrial ecosystem- System architectures for real-time monitoring of production processes integrating IoT Sensoring, QR Technology and blockchain-based traceability.- AI-driven decision-support systems in compliance with DPP solutions, including explainable AI approaches.- Holistic maintenance solutions integrating predictive and prescriptive approaches in industrial processes for product lifecycle management.- Lot-specific and batch-level DPP frameworks reflecting real-time production conditions.- Industrial Key Performance Indicators (KPIs) and statistical outputs of the environmental and economic impact of cutting-edge AI-based DPP solutions.- Performance comparisons under realistic industrial blockchain topologies and edge-computing architectures for monitoring industrial processes.- Scalability and interoperability protocols for P2M in industrial environments for monitoring product lifecycle management processes. Topic editors: Dimitrios Bechtsis, Panagiotis Mallioris, Loucas Protopappas, Alexandra V. Michailidou, Christos Vlachokostas Source: https://www.frontiersin.org/research-topics/80146/digital-product-passports-ai-and-lifecycle-intelligence-for-sustainable-industry