Conference Agenda

This study emphasizes the importance of automatic synthetic data generation in data-driven applications, especially in the development of a 3D computer vision system for engineering contexts such as brownfield factory projects, where no data is readily available. Key points: (1) A successful integration of a synthetic data generator with the S3DIS dataset, leading to a significant enhancement in object detection of previous classes and enabling recognition of new ones; (2) A proposal for a CAD-based configurator for efficient and customizable scene reconstruction from LiDAR scanner point clouds.

The utilization of data in design is a crucial aspect of shaping the product and service development. Despite the lack of extensive research on this subject, this study aims to bridge the gap by introducing the ‘D³IKIT’, a data-driven design process and toolkit. Through workshops, this process and toolkit offer a practical method for creating innovative product and service concepts using data and machine learning. Developed and tested with the participation of 42 individuals, the ‘D³IKIT’ provides valuable insights for both practitioners and academics.

Cyber-Physical-Systems provide extensive data gathering opportunities along the lifecycle, enabling data-driven design to improve the design process. However, its implementation faces challenges, particularly in the initial data capturing stage. To identify those, a comprehensive approach combining a systematic literature review and an industry survey was applied. Four groups of interrelated challenges were identified as most relevant to practitioners: data selection, data availability in systems, knowledge about data science processes and tools, and guiding users in targeted data capturing.

Images provide concise representations of design artifacts and emerge as the primary mode of communication among innovators, engineers, and designers. The advanced of Artificial Intelligence tools which integrates image and textual information can significantly support the Engineering Design process. In this paper we create 5 different datasets combining both images and text of patents and we develop a set of text-based metrics to assess the quality of text for multimodal applications. Finally, we discuss the challenges arising in the development of multimodal patent datasets.

Data-driven design is believed to be empowered by machine learning (ML) with advanced pattern classification and prediction. However, research on how ML can be used to support automotive human-machine interface (HMI) design is lacking. We presented a case study of truck HMI design to understand the current data use and expectations of ML in the design process. Findings show decentralized data practices, the role of expertise in decision-making, and the envisioned reactive use of ML, where we underscore the implications for advancing human-ML collaboration in designing future truck HMI systems.

Despite its transformative impact, a systematic approach to Smart PSS development remains elusive. Addressing this, the study introduces a dynamic conceptual model named DHSmart and its accompanying canvas, adaptable to various contexts and technological advancements. Notably, it offers a structured approach to designing ‘Smart’ in Smart PSS, capturing the interplay between data, humans, and smart systems while directing digitalisation that achieves competitive advantage. It also serves as a unifying framework, enabling meaningful interdisciplinary contributions in theory and practice.