Cold rolling involves large deformation of the workpiece leading to temperature increase due to plastic deformation. This process is highly nonlinear and leads to large computation times to fully model the process. This paper describes the use of dimension-reduced neural networks (DR-NNs) for predicting temperature changes due to plastic deformation in a two-stage cold rolling process. The main objective of these models is to reduce computational demand, error, and uncertainty in predictions. Material properties, feed velocity, sheet dimensions, and friction models are introduced as inputs for the dimensionality reduction. Different linear and nonlinear dimensionality reduction methods reduce the input space to a smaller set of principal components. The principal components are fed as inputs to the neural networks for predicting the output temperature change. The DR-NNs are compared against a standalone neural network and show improvements in terms of lower computational time and prediction uncertainty.

Determining accurate standard time using direct measurement techniques is especially challenging in companies that do not have a proper environment for time measurement studies or that manufacture items requiring complex production schedules. New and specific time measurement techniques are required for such companies. This research developed a novel time estimation approach based on several machine learning methods. The set of collected inputs in the manufacturing environment, including a number of products, the number of welding operations, product's surface area factor, difficulty/working environment factors, and the number of metal forming processes. The data were collected from one of the largest bus manufacturing companies in Turkey. Experimental results demonstrate that when model accuracy was measured using performance measures, k-nearest neighbors outperformed other machine learning techniques in terms of prediction accuracy. “The number of welding operations” and “the number of pieces” were found to be the most effective parameters. The findings show that machine learning algorithms can estimate standard time, and the findings can be used for several purposes, including lowering production costs, increasing productivity, and ensuring efficiency in the execution of their operating processes by other companies that manufacture similar products.

Modern day building design projects require multidisciplinary expertise from architects and engineers across various phases of the design (conceptual, preliminary, and detailed) and construction processes. The Architecture Engineering and Construction (AEC) community has recently shifted gears toward leveraging design optimization techniques to make well-informed decisions in the design of buildings. However, most of the building design optimization efforts are either multidisciplinary optimization confined to just a specific design phase (conceptual/preliminary/detailed) or single disciplinary optimization (structural/thermal/daylighting/energy) spanning across multiple phases. Complexity in changing the optimization setup as the design progresses through subsequent phases, interoperability issues between modeling and physics-based analysis tools used at later stages, and the lack of an appropriate level of design detail to get meaningful results from these sophisticated analysis tools are few challenges that limit multi-phase multidisciplinary design optimization (MDO) in the AEC field. This paper proposes a computational building design platform leveraging concurrent engineering techniques such as interactive problem structuring, simulation-based optimization using meta models for energy and daylighting (machine learning based) and tradespace visualization. The proposed multi-phase concurrent MDO framework is demonstrated by using it to design and optimize a sample office building for energy and daylighting objectives across multiple phases. Furthermore, limitations of the proposed framework and future avenues of research are listed.

Manufacturing industries are looking for efficient assembly planners that can swiftly develop a practically feasible assembly sequence while keeping costs and time to a minimum. Most assembly sequence planners rely on part relations in the virtual environment. Nowadays, tools and robotic grippers perform most of the assembly tasks. Ignoring the critical aspect renders solutions practically infeasible. Additionally, it is vital to test the feasibility of positioning and assembling components while employing robotic grippers and tools prior to their implementation. This paper presents a novel concept named by considering both part and tool geometry to propose “tool integrated assembly interference matrices” (TIAIMs) and a “tool integrated axis-aligned bounding box” (TIAABB) to generate practically feasible assembly sequence plans. Furthermore, the part-concatenation technique is used to determine the best assembly sequence plans for an actual mechanical component. The results show that the proposed approach effectively and efficiently deals with real-life industrial problems.

In engineering and architecture, different approaches have been developed that share the use of graph transformation to automate design processes or to search for design solutions by means of computational design synthesis. In order to give an overview of these approaches, we provide a review of articles published in the last decade. Forty-eight articles were reviewed to determine similarities and differences of these approaches. Research fields in method development for the representation of design problems and the processing of graph transformations, as well as the application of graph transformations in engineering, architecture, and shape grammars were identified. Different approaches for the documentation of the vocabulary and the rules were examined. Finally, different approaches for rule applications were analyzed. Based on found limitations, future research directions are suggested.

Automatically extracting knowledge from small datasets with a valid causal ordering is a challenge for current state-of-the-art methods in machine learning. Extracting other type of knowledge is important but challenging for multiple engineering fields where data are scarce and difficult to collect. This research aims to address this problem by presenting a machine learning-based modeling framework leveraging the knowledge available in fundamental units of the variables recorded from data samples, to develop parsimonious, explainable, and graph-based simulation models during the early design stages. The developed approach is exemplified using an engineering design case study of a spherical body moving in a fluid. For the system of interest, two types of intricated models are generated by (1) using an automated selection of variables from datasets and (2) combining the automated extraction with supplementary knowledge about functions and dimensional homogeneity associated with the variables of the system. The effect of design, data, model, and simulation specifications on model fidelity are investigated. The study discusses the interrelationships between fidelity levels, variables, functions, and the available knowledge. The research contributes to the development of a fidelity measurement theory by presenting the premises of a standardized, modeling approach for transforming data into measurable level of fidelities for the produced models. This research shows that structured model building with a focus on model fidelity can support early design reasoning and decision making using for example the dimensional analysis conceptual modeling (DACM) framework.

The study presented in this paper applies hidden Markov modeling (HMM) to uncover the recurring patterns within a neural activation dataset collected while designers engaged in a design concept generation task. HMM uses a probabilistic approach that describes data (here, fMRI neuroimaging data) as a dynamic sequence of discrete states. Without prior assumptions on the fMRI data's temporal and spatial properties, HMM enables an automatic inference on states in neurocognitive activation data that are highly likely to occur in concept generation. The states with a higher likelihood of occupancy show more activation in the brain regions from the executive control network, the default mode network, and the middle temporal cortex. Different activation patterns and transfers are associated with these states, linking to varying cognitive functions, for example, semantic processing, memory retrieval, executive control, and visual processing, that characterize possible transitions in cognition related to concept generation. HMM offers new insights into cognitive dynamics in design by uncovering the temporal and spatial patterns in neurocognition related to concept generation. Future research can explore new avenues of data analysis methods to investigate design neurocognition and provide a more detailed description of cognitive dynamics in design.

Computer-aided design (CAD) plays an essential role in creative idea generation on 2D screens during the design process. In most CAD scenarios, virtual object translation is an essential operation, and it is commonly used when designers simulate their innovative solutions. The degrees of freedom (DoF) of virtual object translation modes have been found to directly impact users’ task performance and psychological aspects in simulated environments. Little is known in the existing literature about the sense of agency (SoA), which is a critical psychological aspect emphasizing the feeling of control, in translation modes on 2D screens during the design process. Hence, this study aims to assess users’ SoA in virtual object translation modes on mouse-based, touch-based, and handheld augmented reality (AR) interfaces through subjective and objective measures, such as self-report, task performance, and electroencephalogram (EEG) data. Based on our findings in this study, users perceived a greater feeling of control in 1DoF translation mode, which may help them come up with more creative ideas, than in 3DoF translation mode in the design process; additionally, the handheld AR interface offers less control feel, which may have a negative impact on design quality and creativity, as compared with mouse- and touch-based interfaces. This research contributes to the current literature by analyzing the association between virtual object translation modes and SoA, as well as the relationship between different 2D interfaces and SoA in CAD. As a result of these findings, we propose several design considerations for virtual object translation on 2D screens, which may enable designers to perceive a desirable feeling of control during the design process.

Understanding user perceptions of interacting with the virtual world is one of the research focuses in recent years, given the rapid proliferation of virtual reality (VR) and driven to establish the metaverse. Users can generate a familiar connection between their bodies and the virtual world by being embodied in virtual hands, and hand representations can induce users’ embodiment in VR. The sense of embodiment represents the cognitive awareness of one's manifestation and includes three subcomponents: the sense of body ownership, agency and self-location. There is insufficient evidence in the literature about the effects of hand designs on the embodiment, especially based on studying its three subcomponents. This study investigates how virtual hand designs with five realism levels influence the three subcomponents of embodiment in VR. This research employs a self-report questionnaire commonly used in the literature to assess embodiment and evaluates agency and self-location by introducing implicit methods (intentional binding and proprioceptive measurement) derived from psychology. Besides, the objective data of eye tracking is used to explore the connection between embodiment and hand designs, and classifying participants’ eye tracking data to help analyze the link between embodiment and user attention. Overall, this research makes a major contribution through a systematic exploration of users’ embodied experience in VR and offers important evidence of the effects of virtual hand designs on body ownership, agency, and self-location, respectively. In addition, this study provides a valuable reference for further investigation of embodiment through implicit and objective methods, and practical design recommendations for virtual hand design in VR applications.

In the field of content generation by machine, the state-of-the-art text-to-image model, DALL⋅E, has advanced and diverse capacities for the combinational image generation with specific textual prompts. The images generated by DALL⋅E seem to exhibit an appreciable level of combinational creativity close to that of humans in terms of visualizing a combinational idea. Although there are several common metrics which can be applied to assess the quality of the images generated by generative models, such as IS, FID, GIQA, and CLIP, it is unclear whether these metrics are equally applicable to assessing images containing combinational creativity. In this study, we collected the generated image data from machine (DALL⋅E) and human designers, respectively. The results of group ranking in the Consensual Assessment Technique (CAT) and the Turing Test (TT) were used as the benchmarks to assess the combinational creativity. Considering the metrics’ mathematical principles and different starting points in evaluating image quality, we introduced coincident rate (CR) and average rank variation (ARV) which are two comparable spaces. An experiment to calculate the consistency of group ranking of each metric by comparing the benchmarks then was conducted. By comparing the consistency results of CR and ARV on group ranking, we summarized the applicability of the existing evaluation metrics in assessing generative images containing combinational creativity. In the four metrics, GIQA performed the closest consistency to the CAT and TT. It shows the potential as an automated assessment for images containing combinational creativity, which can be used to evaluate the images containing combinational creativity in the relevant task of design and engineering such as conceptual sketch, digital design image, and prototyping image.

Neurotechnology has been applied to gain insights on creativity-related cognitive factors. Prior research has identified relations between cognitive factors and creativity qualitatively; while quantitative relations, such as the relative importance of cognitive factors and creativity, have not been fully determined. Therefore, taking the creative design process as an example, this study using electroencephalography (EEG) aims to objectively identify how creativity-related cognitive factors of retrieval, recall, association, and combination contribute to creativity. The theoretical basis for an EEG-based decoding method to objectively identify which cognitive factors occur in a creative process is developed. Thirty participants were recruited for a practical study to verify the reliability of the decoding method. Based on the methodology, relationships between the relative importance level of the cognitive factor and creative output quality levels were detected. Results indicated that the occurrence of recall and association are reported with a high reliability level by the decoding method. The results also indicated that association is the dominant cognitive factor for higher creative output quality levels. Recall is the dominant cognitive factor for lower creative output quality levels.

With the increasing utilization of machine learning (ML) to enhance products’ capabilities, the design research community has begun to explore how to support the conceptual design of ML-enhanced products. However, UX value creation of ML-enhanced products is still challenging because of ML's unique characteristics and numerous complex factors in conceptual design. To help designers create UX value for ML-enhanced products, we developed the UX value framework and the CoMLUX design process. The proposed framework describes how ML, stakeholders, and context co-create the UX value of ML-enhanced products, and identifies the growability and opacity of ML, helping designers systematically understand the co-creators while avoiding cognitive overload. The CoMLUX design process provides practical guidance for designing ML-enhanced products with growability and transparency. At last, we demonstrate the usage methods of the framework and process in an actual project and summarize the inspirations and limitations of our work.

Analogies provide better concept generation in engineering design. This ideation can be measured by metrics such as usefulness, novelty, variety, quality, completeness, and quantity. In bioinspired design, biological analogies are used to inspire design concepts. Biological analogies have been provided in earlier studies to measure ideation effectiveness. Tools like IDEA-INSPIRE, DANE, etc., allow designers to search analogies using functions, behaviors, and structures. However, we wanted to inquire about the effect of providing a very large number of biological analogies (26), fulfilling the same function to develop bioinspired solutions. In this paper, an empirical study has been performed to analyze the effect of biological analogies on ideation. The designers are exposed to provided multiple biological analogies and generate concepts for which four ideation metrics: novelty, variety, quality, and quantity metrics are evaluated. The results are compared to the unaided condition where other designers are given the same task. A new method to measure variety using a 2D matrix has been presented. The results suggest that designers can generate bioinspired solutions when multiple biological analogies performing similar functions are provided in a presentable format. Statistically, exposure to multiple biological analogies in idea generation can significantly increase the variety of design ideas. The novelty, quality, and quantity for the biological group and control group remain the same.

Predicting the onset of shear localization is among the most challenging problems in machining. This phenomenon affects the process outputs, such as machining forces, surface quality, and machined part tolerances. To predict this phenomenon, analytical, experimental, and numerical methods (especially finite element analysis) are widely used. However, the limitations of each method hinder their industrial applications, demanding a reliable and time-saving approach to predict shear localization onset. Additionally, since this phenomenon largely depends on the type and parameters of the constitutive material model, any change in these parameters requires a new set of simulations, which puts further restrictions on the application of finite element modeling. This study aims to overcome the computational efficiency of the finite element method to predict the onset of shear localization when machining Ti6Al4V using machine learning methods. The obtained results demonstrate that the FCM (fuzzy c-means) clustering ANFIS (adaptive network-based fuzzy inference system) has given better results in both training and testing when it is compared to the ANN (artificial neural network) architecture with an R2 of 0.9981. Regarding this, the FCM-ANFIS is a good candidate to calculate the critical cutting speed. To the best of the authors’ knowledge, this is the first study in the literature that uses a machine learning tool to predict shear localization.

Set-based concurrent engineering (SBCE), a process that develops sets of many design candidates for each subproblem throughout a design project, proposes several benefits compared to point-based processes, where only one design candidate for each subproblem is chosen for further development. These benefits include reduced rework, improved design quality, and retention of knowledge to use in future projects. Previous studies that introduce SBCE in practice achieved success and had very positive future outlooks, but SBCE encounters opposition because its core procedures appear wasteful as designers must divide their time among many designs throughout the process, most of which are ultimately not used. The impacts of these procedures can be explored in detail through open-source computational tools, but currently few exist to do this. This work introduces the Point/Set-Organized Research Teams (PSORT) modeling platform to simulate and analyze a set-based design process. The approach is used to verify statements made about SBCE and investigate its effects on project quality. Such an SBCE platform enables process exploration without needing to commit many projects and resources to any given design.

The use of local natural and recycled feedstock is promising for sustainable construction. However, unlike versatile engineered bricks, natural and recycled feedstock involves design challenges due to their stochastic, sequential, and heterogeneous nature. For example, the practical use of stone masonry is limited, as it still relies on human experts with holistic domain knowledge to determine the sequential organization of natural stones with different sizes/shapes. Reinforcement learning (RL) is expected to address such design challenges, as it allows artificial intelligence (AI) agents to autonomously learn design policy, that is, identifying the best design decision at each time step. As a proof-of-concept RL framework for design automation involving heterogeneous feedstock, a stone masonry design framework is presented. The proposed framework is founded upon a virtual design environment, MasonTris, inspired by the analogy between stone masonry and Tetris. MasonTris provides a Tetris-like virtual environment combined with a finite element analysis (FEA), where AI agents learn effective design policies without human intervention. Also, a new data collection policy, almost-greedy policy, is designed to address the sparsity of feasible designs for faster/stable learning. As computation bottleneck occurs when parallel agents evaluate designs with different complexities, a modification of the RL framework is proposed that FEA is held until training data are retrieved for training. The feasibility and adaptability of the proposed framework are demonstrated by continuously improving stone masonry design policy in simplified design problems. The framework can be generalizable to different natural and recycled feedstock by incorporating more realistic assumptions, opening opportunities in design automation for sustainability.

Design has always been seen as an inherently human activity and hard to automate. It requires a lot of traits that are seldom attributable to machines or algorithms. Consequently, the act of designing is also hard to assess. In particular in an educational context, the assessment of progress of design tasks performed by individuals or teams is difficult, and often only the outcome of the task is assessed or graded. There is a need to better understand, and potentially quantify, design progress. Natural Language Processing (NLP) is one way of doing so. With the advancement in NLP research, some of its models are adopted into the field of design to quantify a design class performance. To quantify and visualize design progress, the NLP models are often deployed to analyze written documentation collected from the class participants at fixed time intervals through the span of a course. This paper will explore several ways of using NLP in assessing design progress, analyze its advantages and shortcomings, and present a case study to demonstrate its application. The paper concludes with some guidelines and recommendations for future development.

This paper reports a systematic literature review with the aim of determining the role of stimuli and other factors, such as timing, the designers’ background, expertise, and experience, in the idea generation phase of conceptual design related to engineering and industrial design and architecture. “Stimulus” is a general expression for a source of information characterized by several features, including the source (internal or external), analogical distance (near or far), and form (textual, visual, or other). Several recent studies have been conducted on this topic involving neurophysiological measurements with significant results. This comprehensive review will help to determine if the neurophysiological results are consistent with those from protocol studies. This allows for determining how the features of stimuli affect – among the related factors – designers’ performance in idea generation. The literature search was carried out using the Snowball and PRISMA methods. A total of 72 contributions were selected from studies adopting protocol analysis or neurophysiological measurements. This study presents a framework to support the selection of stimuli most likely to maximize performance, based on the designer's background and expertise in the different idea generation metrics. The main findings of the framework suggest that visual stimuli enhance the creative performance of designers, regardless of their background, while textual stimuli foster the variety and quality of ideas, but only in engineering and industrial designers. Comparing the findings, the resulting framework reveals aspects of stimuli that require further investigation. These can be considered valuable insights for new directions for design research.

The predictive methods of tool wear are usually based on different algorithm predictors, different source data, and different sensing devices for remaining useful life (RUL). In general, it has challenges to model and ensure all of the cutting conditions that are suitable in the actual cutting process for sustainable manufacturing. In order to overcome the doing large amount of experimental data and predict different tool RULs, this study combines the analytical force modeling, the back-propagation neural network (BPNN) machine learning, and the current sensor which all are integrated in smart machine box (SMB) to realize the practical RUL prediction for on-line and real-time applications. The analytical model of the cutting force coefficients of shear and ploughing was established from average cutting forces, it could reduce the experimental number and predict the different cutting conditions. In general, the loading current of the cutting tool from a spindle motor is relatively easier acquired than the resultant forces. Thus, the loading currents of the spindle are used to train and predict the cutting forces using the BPNN model during intelligent manufacturing. The SMB architecture mainly performed the autonomous actions based on the edge layer, the fog layer, and the cloud layer via the TCP/IP, the MQTT protocol, and the unified communication library. Results showed that a predictive error for the ends of the tool life is about 3–10% that are based on the calculating of the cumulative current ratio.