The development of technical systems requires close cooperation of stakeholders from different disciplines. This collaboration takes place in workshops. Driven by digitalization and by the current pandemic such workshops take place primarily online. Suitable collaboration tools and methods are crucial to success. At the beginning of such workshops, use and damage scenarios are identified. In this paper, we presented a method and tool for identifying and modeling use and damage scenarios, which we evaluated in 14 online workshops with a total of 118 participants over a period of almost 3 years.

The information from Real Twins are increasingly used to construct Digital Twins. Acquisition of information from the Real Twin or in other words performing measurements on the Real Twin may lead to effects in the working of Real Twin. For instance, the introduction of sensors may impair certain functions of a Real Twin. Therefore, it is important to analyse the effect of any change that is performed on the Real Twin for achieving the Digital Twin. In this paper, a method for Digital Twin solution is presented that address these aspects as well as its use is demonstrated by a case example.

In the context of condition monitoring and predictive maintenance, collecting accurate data from technical systems is an important corner stone of the advancing digitalization. For gathering precise data of the current state of a system, measurements from within the process can be utilised. To measure in process without disrupting the system is a challenge that can be tackled by using the physical properties of the components of the system. In this paper a method to systematically find such possible sensory utilizable components (SuC), based on their inherent physical effects is presented.

In top-down design, optimal component requirements are difficult to derive, as the feasible components that satisfy these requirements are yet to be designed and hence unknown. Meta models that provide feasibility and mass estimates for component performance are used for optimal requirement decomposition in an existing approach. This paper (1) extends its applicability adapting it to varying design domains, and (2) increases its efficiency by active-learning. Applying it to the design of a robot arm produces a result that is 1% heavier than the reference obtained by monolithic optimization.

Digital Twins and Product-Service Systems are just two of the recent trends in product development. While many presented approaches seem promising, their implementation often face challenges. This is especially true if existing approaches are transferred onto new applications. Diving into these topics this paper presents the basics but also challenges as well as synergies emerging between them. The objective is set, to move from specialised applications to broader approaches that can provide benefit to a range of applications and ease the entrance, particularly, for smaller enterprises.

The paper presents a framework for the integration of the system's design variables, state variables, control strategies, and contextual variables into a design optimization problem to assist early-stage design decisions. The framework is based on a global optimizer incorporating Dynamic Programming, and its applicability is demonstrated by the conceptual design of an electrical hauler. Pareto front of optimal design solutions, in terms of time and cost, together with optimal velocity profiles and battery state-of-charge is visualized for the given mining scenario.

To satisfy customer needs in the best way, companies offer them an almost infinite number of product variants. Although, an identical product was not built before, the values of its attributes must be determined during the product configuration process. This paper introduces a methodical approach to predict the values of product attributes based on customer feature configurations using machine learning. Machine learning reduces the effort compared to rule-based expert systems and is both, more accurate and faster. The approach was validated by predicting vehicle weights using industrial data.

This paper investigates the use of ANNs to model human behaviour in design by comparing the predictive capability of ANNs and engineering students. Function structure models of 15 products are used as input for prediction. The type of information provided varied between topology and vocabulary. Analysis of prediction accuracy showed that ANNs perform comparably to students. However, students are more precise with their predictions. Finally, limitations and future work are discussed, with research questions presented for subsequent research.

Augmented Reality seems a promising tool to provide engaging and effective educational experiences, thanks to its potentiality in stimulating intrinsic motivation, that could influence the learning process and the attitude of the users towards behaviours. This paper presents the Resized Plastic Augmented Reality learning experience, designed on the basis of Dunleavy's framework to provide a systemic overview of the microplastics issue to allow users to understand its mechanisms, educate them about their role in the system and help them to connect this information to their everyday actions.

Engineering changes are necessary to stay competitive, unavoidable and occur more frequently with increased product complexity. Currently, scheduling of engineering changes into production and supply chain is a manual process. With new possibilities in the field of artificial intelligence, this publication presents the vision of a flexible multi-agent system with four agents and a single shared database. By autonomously scheduling changes and predicting KPI impacts of implementation dates, the agent-system provides additional capacity and decision-making support to the organisation.

Digital Engineering is an emerging trend and aims to support engineering design by integrating computational technologies like design automation, data science, digital twins, and product lifecycle management. To enable alignment of industrial practice with state of the art, an industrial survey is conducted to capture the status and identify obstacles that hinder implementation in the industry. The results show companies struggle with missing know-how and available experts. Future work should elaborate on methods that facilitate the integration of Digital Engineering in design practice.

In this paper, we develop a design agent based on reinforcement learning to mimic human design behaviours. A data-driven reward mechanism based on the Markov chain model is introduced so that it can reinforce prominent and beneficial design patterns. The method is implemented on a set of data collected from a solar system design problem. The result indicates that the agent provides higher prediction accuracy than the baseline Markov chain model. Several design strategies are also identified that differentiate high-performing designers from low-performing designers.

The field of autonomous vehicles is gaining wide recognition in the industry, academia as well as social media. However, there is a lack of knowledge on expectations of people regarding this topic. To this end, this paper analyses extant research on perceptions of people in various countries about semi-autonomous and autonomous vehicles. Secondly, based on the findings of this analysis, we developed a questionnaire to gauge the perceptions of the people in Sweden regarding such vehicles. The findings have important implications for the design of AVs in Sweden, and possibly other countries.

This paper addresses the problem of finding a robust optimal design when uncertain parameters in the form of crisp or interval sets are present in the optimization. Furthermore, in order to make the approach as general as possible, direct search methods with the help of sensitivity analysis techniques are employed to optimize the design. Consequently, the presented approach is suitable for black box models for which no, or very little, information of the equations governing the model is available. The design of an electric drivetrain is used to illustrate the benefits of the proposed method.

In objected-oriented design, "smells" are symptoms of code violating design principles. When a deadline is looming, decisions can affect the long-term quality of a code or CAD. Given this and the similarities between object-oriented code and CAD models, this paper introduces a set of CAD smells. These smells are derived from a top-down review of potential CAD smells mapped against the reported code smells that violate abstraction, modularity, encapsulation, and hierarchy principles. This list was further reviewed considering CAD systems and specific examples (some illustrated in the paper).

In automotive digital development, 3D prototype creation is a team effort of designers and engineers, each contributing with ideas and technical evaluations through means of computer simulations. To support the team in the 3D design ideation and exploration task, we propose an interactive design system for assisted design explorations and faster performance estimations. We utilize the advantage of deep learning-based autoencoders to create a low-dimensional latent manifold of 3D designs, which is utilized within an interactive user interface to guide and strengthen the decision-making process.

Supporting product developers in early design phases with Live-Simulation can enhance the quality of early product designs. Live-Simulation can also facilitate a democratization of simulation and puts away pressure from simulation experts. In this paper, a machine learning based quick evaluation tool is proposed to support product developers in interpreting Live-Simulation results. The proposed tool enables a quick evaluation of the Live-Simulation results and enables product developers to further enhance their simulations. The tool is shown within a use case in bike rocker switch design.

Prototyping uses many models over its process, with varying strength and weakness offered by those in the physical vs digital domains. Working across domains is necessary but introduces a transition cost, process complexities, and risks lost learning. Drawing from Digital Twinning, this work explores the creation of integrated physical-digital prototyping workflows, where technology enables simultaneous cross-domain working. It contrasts four case-study implementations of integrated prototyping workflow to current practice, exploring feasibility, value, and implementation challenges.

Deep learning (DL) from various representations have succeeded in many fields. However, we know little about the machine learnability of distinct design representations when using DL to predict design performance. This paper proposes a graph representation for designs and compares it to the common image representation. We employ graph neural networks (GNNs) and convolutional neural networks (CNNs) respectively to learn them to predict drone performance. GCNs outperform CNNs by 2.6-8.1% in predictive validity. We argue that graph learning is a powerful and generalizable method for such tasks.

Design processes managed by algorithms provide solutions and improvements in terms of efficiency, performance, choice of materials, and cost optimization. It is a whole new approach to industrial design in which artificial intelligence participates directly in the design processes. The paper aims to investigate the way we design through algorithms, and consequent changes in thoughts, approaches, and generation of ideas that are rising determining new ways of defining things and their relations.