Current supportive bio-inspired design methods focus on handcrafting the inspiration engineers use to speed up bio-inspired design. However promising, such methods are not scalable as the time investment is shifted to an up-front investment. Furthermore, most proposed methods require the engineer to adopt a new design process. The current study presents FISh, a scalable search method based on the standard engineering design process. By leveraging machine translation between a representative corpus of biological and engineering texts, the engineer can start the search using engineering terminology, which, behind the scenes, is automatically converted to a biological query. This conversion is done using language models trained on patents and biological publications for the engineering and biology domains. Both models are aligned using the most used English words. The biological query is used to retrieve biological documents that describe the most relevant functionality for the engineering query. The presented method allows searching for bio-inspiration using a free-text query. Furthermore, updating the underlying datasets, models and organism aspects is automated, allowing the system to stay up to date without requiring interactive effort. Finally, the search functionality is validated by comparing the search results for the functionality of existing bio-inspired designs with their inspiring organisms.

Improving existing products plays a vital role in enhancing customer satisfaction and coping with changes in the market. Analyzing user experience (UX) to find the deficiencies of existing products and establishing improved schemes is the key to UX-driven product improvement, especially at the conceptual design stage. Although some tools used in conceptual design, such as requirements analysis and knowledge reasoning, have advanced recently, they lack targeted goals and sufficient efficiency in identifying insufficient product attributes and improving existing functions and structures. The challenge lies in considering the influence imposed on design activities by the original product features (including attributes, functions, and structure). In this study, a knowledge-enabled approach and framework that integrates the conceptual design process, online reviews for UX, and knowledge is proposed to support product improvement. Specifically, a decision-making algorithm based on UX analysis is proposed to identify to-be-improved product attributes. Then, through optimizing the previous knowledge application model from knowledge requirement transformation, knowledge modeling, and knowledge reasoning, a smart knowledge reasoning model is established to push knowledge for functional solving of the to-be-improved attributes. A knowledge configuration method is used to modify product features to generate an improved scheme. To demonstrate the feasibility of the proposed approach, a case study of improving an agricultural sprayer is conducted. Through discussion, this study can help to regulate design activities for product improvement, enhance data and knowledge application, and promote divergent thinking during scheme modification.

Research on empathy has been surging in popularity in the engineering design community since empathy is known to help designers develop a deeper understanding of the users’ needs. Because of this, the design community has become more invested in devising and assessing empathic design activities. However, research on empathy has been primarily limited to individuals, meaning we do not know how it impacts team performance, particularly in the concept generation and selection stages of the design process. Specifically, it is unknown how the empathic composition of teams, defined here as the average (elevation) and standard deviation (diversity) of team members’ empathy, would impact design outcomes during nominal group concept generation and early concept screening. Therefore, the goal of the current study is to investigate the impact of team empathy on nominal group concept generation and early concept screening in an engineering design student project. This was accomplished through a computational simulation of 13,482 teams of non-interacting brainstorming individuals generated by a statistical bootstrapping technique. This simulation drew upon a design repository of 806 ideas generated by first-year engineering students. The main findings from the study indicated that the impact of the elevation and diversity of different components of team empathy varied depending upon the specific design outcome (number of ideas, overall creativity, elegance, usefulness, uniqueness) and design stage (concept generation and concept screening). The results from this study can be used to guide team formation in engineering design.

Product data sharing is fundamental for collaborative product design and development. Although the STandard for Exchange of Product model data (STEP) enables this by providing a unified data definition and description, it lacks the ability to provide a more semantically enriched product data model. Many researchers suggest converting STEP models to ontology models and propose rules for mapping EXPRESS, the descriptive language of STEP, to Web Ontology Language (OWL). In most research, this mapping is a manual process which is time-consuming and prone to misunderstandings. To support this conversion, this research proposes an automatic method based on natural language processing techniques (NLP). The similarities of language elements in the reference manuals of EXPRESS and OWL have been analyzed in terms of three aspects: heading semantics, text semantics, and heading hierarchy. The paper focusses on translating between language elements, but the same approach has also been applied to the definition of the data models. Two forms of the semantic analysis with NLP are proposed: a Combination of Random Walks (RW) and Global Vectors for Word Representation (GloVe) for heading semantic similarity; and a Decoding-enhanced BERT with disentangled attention (DeBERTa) ensemble model for text semantic similarity. The evaluation shows the feasibility of the proposed method. The results not only cover most language elements mapped by current research, but also identify the mappings of the elements that have not been included. It also indicates the potential to identify the OWL segments for the EXPRESS declarations.

Engineering design has proven to be a rich context for applying artificial intelligence (AI) methods, but a categorization of such methods applied in AI-based design research works seems to be lacking. This paper presents a focused literature review of AI-based methods mapped to the different stages of the engineering design process and describes how these methods assist the design process. We surveyed 108 AI-based engineering design papers from peer-reviewed journals and conference proceedings and mapped their contribution to five stages of the engineering design process. We categorized seven AI-based methods in our dataset. Our literature study indicated that most AI-based design research works are targeted at the conceptual and preliminary design stages. Given the open-ended, ambiguous nature of these early stages, these results are unexpected. We conjecture that this is likely a result of several factors, including the iterative nature of design tasks in these stages, the availability of open design data repositories, and the inclination to use AI for processing computationally intensive tasks, like those in these stages. Our study also indicated that these methods support designers by synthesizing and/or analyzing design data, concepts, and models in the design stages. This literature review aims to provide readers with an informative mapping of different AI tools to engineering design stages and to potentially motivate engineers, design researchers, and students to understand the current state-of-the-art and identify opportunities for applying AI applications in engineering design.

Welding is the most basic and widely used manufacturing process. Intelligent robotic welding is an area that has received much consideration owing to the widespread use of robots in welding operations. With the dawn of Industry 4.0, machine learning is substantially developing to alleviate issues around applying robotic welding intelligently. Identifying the correct weld joint type is essential for intelligent robotic welding. It affects the quality of the weldment and impacts the per-unit cost. The robot controller must change different welding parameters per joint type to attain the desired weld quality. This article presents an approach that uses image features like edges, corners, and blobs to identify different weld joint types using machine learning algorithms. Feature extractors perform the task of feature extraction. The feature extractor choice is crucial for accurate weld joint identification. The present study compares the performance of five feature extractors, namely (1) Histogram of gradients, (2) Local binary pattern, (3) ReLU3 layer, (4) ReLU4 layer, and (5) Pooling layer of ResNet18 Neural network applied to classifiers like Support Vector machines, K-Nearest Neighbor and Decision trees. We trained and tested the proposed model using the Kaggle Weld joint dataset (for Butt and Fillet Joints) and our in-house dataset (for Vee, lap, and corner joints). The experimental findings show that out of the 15 models, the pre-trained ResNet18 feature extractor with an Support Vector Machines classifier has excellent performance with a threefold recognition accuracy of 98.74% for the mentioned dataset with a computation time of 31 ms per image.

User models that can directly use and learn how to do tasks with unmodified interfaces would be helpful in system design to compare task knowledge and times between interfaces. Including user errors can be helpful because users will always make mistakes and generate errors. We compare three user models: an existing validated model that simulates users’ behavior in the Dismal spreadsheet in Emacs, a newly developed model that interacts with an Excel spreadsheet, and a new model that generates and fixes user errors. These models are implemented using a set of simulated eyes and hands extensions. All the models completed a 14-step task without modifying the system that participants used. These models predict that the task in Excel is approximately 20% faster than in Dismal, including suggesting why, where, and how much Excel is a better design. The Excel model predictions were compared to newly collected human data (N = 23). The model’s predictions of subtask times correlate well with the human data (r2 = .71). We also present a preliminary model of human error and correction based on user keypress errors, including 25 slips. The predictions to data comparison suggest that this interactive model that includes errors moves us closer to having a complete user model that can directly test interface design by predicting human behavior and performing the task on the same interface as users. The errors from the model’s hands also allow further exploration of error detection, error correction, and different knowledge types in user models.