Adaptive retrofitting for industrial machines: utilizing webassembly and peer-to-peer connectivity on the edge

World Wide Web (2024) 27:7 https://doi.org/10.1007/s11280-024-01237-8 Adaptive retrofitting for industrial machines: utilizing webassembly and peer-to-peer connectivity on the edge Otoya Nakakaze1 · István Koren2 · Florian Brillowski3 · Ralf Klamma1 Received: 30 April 2023 / Revised: 19 November 2023 / Accepted: 6 December 2023 / Published online: 25 January 2024 © The Author(s) 2024 Abstract Leveraging previously untapped data sources offers significant potential for value creation in the manufacturing sector. However, asset-heavy shop floors, extended machine replacement cycles, and equipment diversity necessitate considerable investments for achieving smart manufacturing, which can be particularly challenging for small businesses. Retrofitting presents a viable solution, enabling the integration of low-cost sensors and microcontrollers with older machines to collect and transmit data. In this paper, we introduce a concept and a prototype for retrofitting industrial environments using lightweight web technologies at the edge. Our approach employs WebAssembly as a novel bytecode standard, facilitating a consistent development environment from the cloud to the edge by operating on both browsers and bare-metal hardware. By attaining near-native performance and modularity reminiscent of container-based service architectures, we demonstrate the feasibility of our approach. Our prototype was evaluated with an actual industrial robot within a showcase factory, including measurements of data exchange with a cutting-edge data lake system. We further extended the prototype to incorporate a peer-to-peer network that facilitates message routing and WebAssembly software updates. Our technology establishes a foundational framework for the transition towards Industry 4.0. By integrating considerations of sustainability and human factors, it further extends this groundwork to facilitate progression into Industry 5.0. This article belongs to the Topical Collection: Special Issue on Web Information Systems Engineering 2022 Guest Editors: Richard Chbeir, Helen Huang, Yannis Manolopoulos and Fabrizio Silvestri. B B Otoya Nakakaze István Koren Florian Brillowski 1 Chair of Databases and Information Systems, RWTH Aachen University, Ahornstraße 55, Aachen 52074, Germany 2 Chair of Process and Data Science, RWTH Aachen University, Ahornstraße 55, Aachen 52074, Germany 3 Institute of Textile Technology, RWTH Aachen University, Otto-Blumenthal-Straße 1, Aachen 52074, Germany 0123456789().: V,-vol 123 7 Page 2 of 24 World Wide Web (2024) 27:7 Keywords Industry 4.0 · Retrofitting · Edge computing · WebAssembly · Peer-to-Peer 1 Introduction The digital transformation infused by the fourth industrial revolution (Industry 4.0) [1] promises huge opportunities based on new data-driven capabilities. The concept recommends interconnected information technologies such as Internet of Things (IoT) to exploit previously inaccessible data sources. Data can help companies target areas where they can improve their processes to make their manufacturing operations more efficient. In a similar vein, tracking data related to energy and water use, as well as other resources, allows companies to identify areas where they can reduce consumption, thereby enhancing sustainability. Lastly, sensors and actuators can be used to address issues of robot-human collaboration, e.g., to avoid collisions. In summary, the rapid expansion of Industry 4.0 places increasing pressure on manufacturing companies to swiftly adapt and transform their factory operations. However, in today’s shop floors, long-term investments in legacy machines without networking capabilities prevail. The process of replacing an entire machine shop with new equipment is not only expensive and unsustainable, but also leads to undesired downtime. Specifically, small and medium-sized enterprises (SMEs) often face difficulties in handling the initial costs and implementation complexities associated with adopting smart manufacturing environments [2]. In contrast to the advantages of using new technology in manufacturing, the latest information technology might threaten the role of the current workforce. For instance, workers in the operation technology area are not always familiar with IT; new tools might require high-level knowledge. Whereas the primary concern of the fourth industrial revolution is digital transformation, Industry 5.0 emphasizes a human-centric approach [3–5]. The fifth industrial revolution involves the integration of cutting-edge tools with workers. Augmented, virtual, or mixed-reality technologies support people to watch and analyze the production process. Also, uncertain settings in actual physical systems can be simulated in the virtual environment. Collaborative robots assist the human force with dangerous or high-load tasks. In addition, they help us with some processes that need very high precision. Furthermore, the next industrial concept focuses on sustainability and resilience. Sustainable production targets energy efficiency and reduction of waste, such as recycling. Given the dynamic global landscape, marked by factors such as climate change, pandemics, and geopolitical shifts, there is an increasing demand for adaptable production designs to ensure resilience and continuity [6]. Retrofitting refers to the low-cost upgrade of existing equipment [7]. It allows for efficient upgrades by attaching devices, enabling rapid modernization and extending the life of machines. For instance, by monitoring the vibrations of legacy machines with cheap sensors, machine learning models are able to predict breakdowns caused by faulty parts [8]. In addition, existing production lines and know-how can continue to be used without retraining employees; retrofitting reduces the gap between the existing and the newly deployed technology, resulting in simpler worker empowerment. In practice, it is not easy to retrofit production lines, as they consist of different control systems and electromechanical components [9]. There is currently no one-stop solution that can be deployed in a modular and uniform manner. Existing retrofitting examples are either specialized on a particular use case (e.g., [9, 10]) or too general (e.g., the commercial LEGIC 123 World Wide Web (2024) 27:7 Page 3 of 24 7 XDK Secure Sensor Evaluation Kit 1 ); both cannot be easily fitted to custom use cases with heterogeneous machine interfaces. Web technologies, in turn, are excellent in addressing device heterogeneity. For instance, JavaScript runs on front- and backend alike. However, JavaScript is not ideal for running on microcontrollers, as features such as dynamic typing incur a large overhead. We therefore propose the use of WebAssembly (in the following, we use the term’s abbreviation Wasm interchangeably) [11]. It is a low-level language with a compact binary format that gets processed with near-native performance in a sandboxed execution environ (...truncated)