Concept Generation Research Articles

EXPLORING THE IMPACT OF GENERATIVE STIMULI ON THE CREATIVITY OF DESIGNERS IN COMBINATIONAL DESIGN

AbstractThe ideation process has a significant impact on the initial concept generation and final product creativity of the design. Visual stimuli play an important role in the process of innovative product design. With the increase in computing capability, generative design methods are widely implemented. In this paper, features of design targets and combinational objects in 2 combinational design tasks are fused using adversarial neural generative networks to form the generated stimuli. It is also used with combinational object pictures to investigate the impact on creativity in design ideation. The study invited designers to use and subjectively self-evaluate the two stimuli in a design task. Through analysis of participant data (n=20), the results showed that the generative stimuli had an advantage over the combinational image stimuli in terms of the smoothness of creativity in the design ideation of outcomes. And there is a positive correlation between designers' years of design education and their tendency to prefer generative stimuli. Based on the results obtained, ideas are provided for the study of the influence of visual and generative stimuli on the designer's ideation process.

ЕФЕКТИВНІСТЬ ПОЯСНЮВАЛЬНО-ІЛЮСТРАТИВНОГО МЕТОДУ ПІД ЧАС ВИКЛАДАННЯ ДИСЦИПЛІНИ «ТЕРМОДИНАМІКА» ЗА НАВЧАЛЬНИМ ПЛАНОМ ПІДГОТОВКИ БАКАЛАВРІВ СПЕЦІАЛЬНОСТІ 184 ГІРНИЦТВО

The article examines the explanatory and illustrative method during teaching the academic discipline “Thermodynamics” to higher education institutions students. It is known that the effectiveness of training depends on the teacher’s ability to choose a training method in certain conditions for a specific lesson. The main attention is paid to the aspect of the relevance and effectiveness of the explanatory and illustrative teaching method in modern education, as the scope and possibilities of displaying thermodynamic concepts, processes, methods of thermodynamic analysis have expanded. The explanatory and illustrative teaching method is supposed to ensure students’ understanding of the educational material. Understanding is not just a result, but a process when the learner perceives the connection between the unknown and the known, combines an unknown concept with an already known one, and can compare the unknown with the known. The features and characteristics of the explanatory and illustrative teaching method are analyzed. The advantages of the specified method during the presentation of a large amount of educational material, structuring of information and outlining the connection between the concepts of the discipline “Thermodynamics” are considered. Tables and diagrams, graphs and schemes are an integral part of studying the discipline “Thermodynamics”. It is with the help of them that you can quickly learn the laws of thermodynamic processes of ideal and real gases, cycles of steam power plants, internal combustion engines, and gas turbine plants. Examples of graphic and schematic presentations of some concepts of thermodynamics are considered, which clearly reflect the relationship between new concepts and previously considered ones, and allow mathematical dependencies to be presented schematically or graphically. Graphic display of concepts allows the student to create a set of knowledge on the use of different parameters. The list of the main diagrams used by students in solving applied problems of energy conversion, in particular in thermal energy systems and installations of mining enterprises, is given. The importance of the simultaneous combination of oral explanation with illustrations, schemes, diagrams when teaching the educational discipline «Thermodynamics» is noted. It is determined that if the student gives his examples that illustrate the content of the topic, or can transform the verbal presentation of the material into tabular or graphic form, in the form of formulas, then a conclusion can be drawn about students’ understanding of the material. Learning the discipline consists of a sequence of generation of separate concepts, concepts of a defined topic, and then during the further study of «Thermodynamics» a system of concepts is formed. The key to the success of the formation of concepts is whether the connection between the explanatory concept of the discipline and others, which were previously studied by students, is realized. It was determined that the explanatory and illustrative teaching method is convenient when it is necessary to convey a large amount of educational material in a short period of time. Its use is justified while learning fixed concepts, facts, and laws. It is concluded that in lectures on the discipline «Thermodynamics» it is the explanatory material that plays an important role, since «Thermodynamics» is the foundation of many special disciplines in the future.

Should We Keep Brainstorming to Innovate?

Brainstorming has been established as the gold standard in generating new creative and innovative ideas in organizations. However, brainstorming is less efficient than it seems. This article discusses brainstorming as a method for innovation and highlights managerial insights to improve the generation of innovative concepts.

Improving semantic coverage of data-to-text generation model using dynamic memory networks

AbstractThis paper proposes a sequence-to-sequence model for data-to-text generation, called DM-NLG, to generate a natural language text from structured nonlinguistic input. Specifically, by adding a dynamic memory module to the attention-based sequence-to-sequence model, it can store the information that leads to generate previous output words and use it to generate the next word. In this way, the decoder part of the model is aware of all previous decisions, and as a result, the generation of duplicate words or incomplete semantic concepts is prevented. To improve the generated sentences quality by the DM-NLG decoder, a postprocessing step is performed using the pretrained language models. To prove the effectiveness of the DM-NLG model, we performed experiments on five different datasets and observed that our proposed model is able to reduce the slot error rate rate by 50% and improve the BLEU by 10%, compared to the state-of-the-art models.

A holistic method for radical concept generation based on technological evolution: A case application of DC charging pile

In the rapidly changeable market, radical innovation (RI) is highly demanded by enterprises to improve their product competitiveness. Enterprises need to efficiently generate ideal radical concepts for the successful implementation of RI. However, the existing research on RI mainly focuses on identifying radical concepts through various evaluation methods from the perspective of business and management. This is a post-hoc analysis, which limits the guidance for enterprises to plan and purposefully generate radical concepts from an ex-ante perspective. For the development of RI products in the engineering field, enterprises lack an effective method for the ex-ante generation of radical concepts. To fill the gap, this paper proposes a holistic method for the ex-ante generation of radical concepts according to the technological evolution. An identification method for radical technology opportunities is proposed based on the evolutionary characteristics of the RI technological trajectory. Technological evolution laws and artificial neural networks are used to determine the evolution direction of subsystems for RI, thereby identify the search direction of new technologies. This paper also establishes a technical knowledge evaluation method and an analogy process for the ex-ante generation of radical concepts. The proposed method is applied in the ex-ante design of a DC charging pile for its feasibility and effectiveness. The proposed method not only provides an efficient ex-ante generation process of the radical concept for enterprise engineers, but also has the potential to enrich research on the RI and knowledge innovation.

An Approach to Logical Compatibility Determination for Solution Principles in Morphological Matrix-Based Conceptual Design

Morphological matrix-based conceptual design has been proven to enable the generation of high-quantity, variety, and novelty concepts. Indeed, many studies have proposed methods for enhancing it. However, logical relations for determining the compatibility of solution principles (SPs) in combinatorial solution chain is yet to be established in the literature. This study attempts to develop a logical relation for determining the compatibility of SPs in solution variants chain. The features of the interaction boundary of each solution principle were characterised and vectorially numerated for onward matching of adjacent SPs in a combinatorial solution chain to determine compatibility. The consistency of the compatibility determinant (CD) was tested on engineering designer students. It was found that the students could determine the CD with excellent consistency. Besides, the applicability of logical relation for determining the feasibility of solution variants was tested and found applicable in many trials. Despite the limitation of the study, the results indicate that the logical compatibility determinant is consistent and applicable for the complete exploration of the morphological matrix design space. Therefore, this study provides a foundation for the development of a reliable CAD system for conceptual design.

A space layout design model for concept generation using Function-based spatial planning and structure dynamic deployment

Concept design plays a critical role in product design, aiming to create conceptual schemes that satisfy various constraints. Among them, configuring the functions and structures that meet the user requirements and determining their spatial relationship is a necessary part of generating schemes. While existing methodologies of function and structure solution have been advanced recently, how to avoid overlap and interference in the space of functions and structures when generating schemes so as to maximize the use of the workspace and achieve the functionality of the product remains challenging. To address this issue, a space layout design model for concept generation using function-based spatial planning and structure dynamic deployment is proposed in this study. In the functional analysis phase, a function-based spatial zoning model is created for the functions, and establishing mappings for the spatial relationships and the zones in the space to generate the layout solution by extending and integrating zoned space. After generating conceptual structure, coordinate transformation based position deployment and trajectory analysis based motion space deployment methods are used to deploy spatial layout of the structures. A case study of a machine for electrical insulator detection that includes the integration and interaction of multiple components in space is introduced to demonstrate the feasibility of the proposed model and method.

Explaining cocktail party effect and McGurk effect with a spiking neural network improved by Motif-topology.

Network architectures and learning principles have been critical in developing complex cognitive capabilities in artificial neural networks (ANNs). Spiking neural networks (SNNs) are a subset of ANNs that incorporate additional biological features such as dynamic spiking neurons, biologically specified architectures, and efficient and useful paradigms. Here we focus more on network architectures in SNNs, such as the meta operator called 3-node network motifs, which is borrowed from the biological network. We proposed a Motif-topology improved SNN (M-SNN), which is further verified efficient in explaining key cognitive phenomenon such as the cocktail party effect (a typical noise-robust speech-recognition task) and McGurk effect (a typical multi-sensory integration task). For M-SNN, the Motif topology is obtained by integrating the spatial and temporal motifs. These spatial and temporal motifs are first generated from the pre-training of spatial (e.g., MNIST) and temporal (e.g., TIDigits) datasets, respectively, and then applied to the previously introduced two cognitive effect tasks. The experimental results showed a lower computational cost and higher accuracy and a better explanation of some key phenomena of these two effects, such as new concept generation and anti-background noise. This mesoscale network motifs topology has much room for the future.

Intuition or rationality: Impact of critical thinking dispositions on the cognitive processing of creative information

Creative thinking and critical thinking complement each other and are inseparable. The two fold model theory of creativity believes that the generation of creative thinking includes two processes: concept generation and concept evaluation. Among them, individuals will rely more on non-automatic top-down control processing for cognitive information processing in the process of concept evaluation. Critical thinking belongs to analytical thinking, which focuses on and doubts the information bias in the generation of ideas to restrain. Therefore, this study assumes that the impact of critical thinking on creative thinking will occur in the process of concept evaluation, which is rational judgment rather than intuitive thinking. This study uses event-related potential (ERP) techniques to explore the explicit and implicit mechanisms of cognitive processing of creative information (i.e. role of intuition and rationality) in people with different critical thinking dispositions. The current study includes two experiments. Experiment 1 is an explicit ERP experiment, which uses a priming paradigm to examine the neural mechanisms underlying the explicit processing of creative information by individuals with different critical thinking dispositions. Experiment 2 is an implicit ERP experiment, which uses an alternative Stroop paradigm to examine the neural mechanisms underlying the implicit processing of creative information. Results found that the brain mechanisms of explicit cognition of creative information differed significantly across critical thinking dispositions. For low-critical thinking dispositions, low-creative characters evoked larger N1 waves than high-creative characters initiation conditions. For high-critical thinking dispositions, high-creative words evoked larger P2 waves than low-creative words. However, implicit cognition did not differ significantly. This result suggests that the cognitive processing of creative information by different critical thinkers is a rational thought process. The N1 and P2 components, which are indicators of cognitive sensitivity to creative information, can be used as markers to distinguish among different critical thinking dispositions.

Three unique concept explorations in sketching based on conceptual combinations in associative extension and schematic structure

Sketching is a creative thinking process that can compound ideas to explore novel concepts. Generating novel concepts through sketches involves interpreting a combination of certain elements of the sketch image. As such, combining specific elements of the drawn sketches is of particular interest. In order to analyze the sketching process, this study investigated concept generation by explicitly replacing the attributes of sketches with noun-noun combinations. In this process, corresponding associative extensions and a schematic structure allows for the exploration of unique sketching concepts through property-based, relation-based, and hybrid-based combinations. In doing so, novel concepts can be generated by interpreting the attributes of sketches in unique ways.

Artificial Intelligence in Engineering

Artificial intelligence (AI) has moved past its primitive stages and is now poised to revolutionize various fields, making it a disruptive technology. This technology is expected to completely transform traditional engineering in design, electrical, communication, and renewable energy approaches that have been human-centred. Despite being in its early stages, AI-powered engineering applications can work with vague design parameters and resolve intricate engineering problems that cannot be tackled using traditional design, electrical, communication, and renewable energy methods. This article aims to shed light on the current progress and future research trends in AI applications in engineering concepts, focusing on the ramp-up period of the last 5 years. Various methods such as machine learning, genetic algorithm, and fuzzy logic have been carefully evaluated from an engineering standpoint. AI-powered design studies have been reviewed and categorized for different design stages such as inspiration, idea and concept generation, evaluation, optimization, decision-making, and modeling. The review shows that there has been an increased interest in data-based design methods and explainable artificial intelligence in recent years. The use of AI methods in engineering applications has proven to be efficient, fast, accurate, and comprehensive, particularly with the use of deep learning methods and combinations that address situations where human capacity is inadequate. However, it is crucial to choose the appropriate AI method for an engineering problem to achieve successful results.

Iterative transformations for deeper exploration during concept generation

Engineering designers often generate multiple concepts to increase novelty and diversity among early solution candidates. Many past studies have focused on creating new concepts “from scratch;” however, designers at every level become fixated on their initial designs and struggle to generate different ideas. In line with prior work on design transformations, we propose a concept generation process of iterative transformation to create new ideas by intentionally introducing major changes in form, nature, or function to an existing concept. A study of this concept generation process recruited beginning engineering students likely to benefit from an alternative to "blank slate" generation. Working alone in a single test session, students generated an initial concept for a presented design problem. Then, they were instructed to generate another concept by transforming their initial design into a new concept and repeated this process to create three more concepts. In a second design round, students were asked to consider 7 Design Heuristics strategies to prompt possible transformations for their concepts. Beginning again with their initial concept, each student generated another set of four transformed concepts using iterative transformation. The analysis considered 60 initial concepts and 476 transformed concepts with and without the use of Design Heuristics. We created Design Transformation Diagrams to observe links (sequential, non-sequential, or both) between transformed concepts within each set of four concepts and between the two sets. Three patterns across the diagrams were identified: Fully Sequential, Sequential with Deviation, and Divergent. When aided by Design Heuristics, transformations included more non-sequential links, suggesting synthesis, refinement, and extension of other prior concepts, and resulting in more varied and distinct transformations. This iterative transformation process may support more diversity in concepts generated through a deeper exploration of related concepts without requiring an escape from the influence of existing concepts. Concept generation strategies like Design Heuristics may support engineering students as they learn to expand their early exploration of design concepts.

Applications of Agent-Based Methods in Multi-Energy Systems—A Systematic Literature Review

The need for a greener and more sustainable energy system evokes a need for more extensive energy system transition research. The penetration of distributed energy resources and Internet of Things technologies facilitate energy system transition towards the next generation of energy system concepts. The next generation of energy system concepts include “integrated energy system”, “multi-energy system”, or “smart energy system”. These concepts reveal that future energy systems can integrate multiple energy carriers with autonomous intelligent decision making. There are noticeable trends in using the agent-based method in research of energy systems, including multi-energy system transition simulation with agent-based modeling (ABM) and multi-energy system management with multi-agent system (MAS) modeling. The need for a comprehensive review of the applications of the agent-based method motivates this review article. Thus, this article aims to systematically review the ABM and MAS applications in multi-energy systems with publications from 2007 to the end of 2021. The articles were sorted into MAS and ABM applications based on the details of agent implementations. MAS application papers in building energy systems, district energy systems, and regional energy systems are reviewed with regard to energy carriers, agent control architecture, optimization algorithms, and agent development environments. ABM application papers in behavior simulation and policy-making are reviewed with regard to the agent decision-making details and model objectives. In addition, the potential future research directions in reinforcement learning implementation and agent control synchronization are highlighted. The review shows that the agent-based method has great potential to contribute to energy transition studies with its plug-and-play ability and distributed decision-making process.

Prototyping Strategies to Engage Stakeholders During Early Stages of Design: A Study Across Three Design Domains

Abstract Using prototypes to engage stakeholders during front-end design activities is crucial for successful design outcomes. Compared to prototyping that is used for iterative refinement during back-end engineering design activities, prototyping that informs problem definition, requirements and specifications development, concept generation, and other front-end design activities is understudied. To identify patterns in prototyping strategies for engaging stakeholders during the design front end, we conducted semi-structured interviews with 26 design practitioners across three product design domains: automotive, consumer products, and medical devices. Seventeen strategies evident across the collection of practitioners were used in generally consistent ways, with some variation based on context, e.g., project scope, stakeholders engaged, and the stakeholder interaction situation. Twelve of those 17 strategies were used by industry practitioners across the three domains, and five of those 17 strategies were used by practitioners from the medical device domain and either the automotive or consumer products domain. The descriptions and in-context examples of prototyping strategies used to engage stakeholders during front-end design can guide the design strategies of both experienced and novice designers.

The Impact of Artificial Intelligence on the Graphic Design Industry

Artificial Intelligence (AI) is rapidly transforming many industries, including the field of graphic design. This paper aims to explore the impact of AI on graphic design and how it is shaping the future of the field. Through a literature review, we will examine how AI is being used in graphic design, including the automation of repetitive tasks, the generation of new design concepts, and the creation of personalized designs. We will also explore the potential benefits and drawbacks of AI in graphic design, such as increased efficiency and creativity, but also the loss of human touch and potential job displacement. Additionally, this paper will look at the ethical considerations surrounding the use of AI in graphic design and the implications it has on the industry. Overall, this paper will provide a comprehensive examination of the current state and future potential of AI in graphic design. Keywords: Artificial Intelligence, Graphic Design, Creativity, Technology, Machine Learning ,Design Industry. DOI: 10.7176/ADS/104-01 Publication date: March 31 st 2023

Artificial Intelligence as a pedagogical tool for architectural education: What does the empirical evidence tell us?

Artificial Intelligence (AI) applications in arts and design have beengrowing in popularity in recent years. Numerous AI program applications arepublicly available, both commercial and open source, offering a chance to convertthe textual description of a design or context into original content images. Whilemany research projects tackled AI use in architecture since 2015, there seems to bea lack of empirical evidence of its use in Architecture education as a tool for conceptgeneration. An experimental architecture design course took place in Fall 2022where 34 students utilised AI programs in the conceptual design phase to produceoriginal content images from narratives to help students generate concepts for theirbuildings. The designs of the experimental student groups are compared to anothercontrol group of 50 students which use more traditional conceptual design methodson a similar project in the same semester. This paper aims to highlight theopportunities and challenges of using AI tools in the concept generation phase inarchitecture design education by measuring their effectiveness to increase creativityin form finding. With the use of recent literature in architecture learning theoriesand pedagogies, this experimental approach will be critiqued to provide furtherinsights into AI’s role in architecture education.

Special Issue: Emerging Technologies and Methods for Early-Stage Product Design and Development

Abstract The early-stage product design and development (PDD) process fundamentally involves the processing, synthesis, and communication of a large amount of information to make a series of key decisions on design exploration and specification, concept generation and evaluation, and prototyping. Although most current PDD practices depend heavily on human intuition, advances in computing, communication, and human-computer interaction (HCI) technologies can transform PDD processes by combining the creativity and ingenuity of human designers with the speed and precision of computers. Emerging technologies like artificial intelligence (AI), cloud computing, and extended reality (XR) stand to substantially change the way designers process information and make decisions in the early stages of PDD by enabling new methods such as natural language processing, generative modeling, cloud-based virtual collaboration, and immersive design and prototyping. These new technologies are unlikely to render the human designer obsolete, but rather do change the role that the human designer plays. Thus, it is essential to understand the designer's role as an individual, a team, and a group that forms an organization. The purpose of this special issue is to synthesize state-of-the-art research on technologies and methods that augment the performance of designers in the front-end of PDD—from understanding user needs to conceptual design, prototyping, and development of systems architecture while also emphasizing the critical need to understand the designer and their role as well.

Development of Fused Deposition Modeling of Multiple Materials (FD3M) Through Dynamic Coaxial Extrusion.

Multimaterial additive manufacturing is expanding the design space realizable with 3D printing, yet is largely constrained to sequential deposition of each individual material. The ability to coextrude two materials and change the ratio of materials while printing would enable custom-tailored polymer composites. Here, the evolution of a dynamic material coextrusion process for additive manufacturing capable of printing any ratio between and including two neat input materials is described across 3 hot-end generations and 14 implemented design iterations. The designs evolved with increased understanding of manufacturing constraints associated with the additive manufacturing of metal components with internal flow bore diameters on the order of 2 mm and typical bore length around 50 mm. The second generation overcame this issue by partitioning the design into two pieces to locate the flow channel geometry at the interface between the components so that the details could be easily printed on the components' external surfaces. The third concept generation then focused on minimizing flow channel volume to reduce the average length when transitioning between materials by 92%. The third-generation design was also used to investigate the improvements in dimensional stability during annealing of acrylonitrile butadiene styrene (ABS) made possible by coextruding ABS with a polycarbonate (PC) core. The standard deviation of part shrinkage after annealing was 7.08% for the neat ABS but reduced to 0.24% for the coextruded ABS/PC components.

Towards a pattern language for complex-mode mission concept generation

New space mission profiles arise from the convergence of reduced launch prices, miniaturization of electronics and the maturation of on-orbit servicing technologies. Additionally, a shift towards challenging Lunar objectives pushes for interconnected and complex-mode missions, and trends towards low-cost, sustainability and autonomy also encourage complex modes. The field of space logistics aims to develop conceptual and computational tools to optimize multi-node material-flow networks. However, existing tools insufficiently address the challenge of generating and comparing mission concepts methodically. Through a comprehensive literature review and a case study, we: (1) establish a need for a design support tool for early-phase complex space mission concept generation; (2) establish the potential of a novel approach using pattern languages; (3) propose and describe a concept for an innovative interdisciplinary tool using the identified methods; (4) verify the proposed support tool concept by replicating the Apollo study results as a proof of concept. We created a pattern language in which words are mission concept of operations elements, the grammar is an assembly algorithm allowing to generate options automatically, and the writing system is intuitively readable diagrams illustrating candidate mission modes. Key figures of merit are also automatically compiled. Among the concepts we generated for the Apollo proof of concept study, the four principal candidates considered in 1962 were captured and ranked in the same order as historically and in recent literature. Findings are consistent with Apollo’s choice of designing two modules to be separated in Lunar orbit, thus confirming the proposed tool’s potential. Decision-makers could be supported in the early stages of the mission design process, where most of the value is locked in, by complementing existing methods such as concurrent engineering. Efficiently designing complex-mode missions is key to enabling cost-effective and highly ambitious missions, therefore supporting cislunar economy development. • Gap for a design support tool for early-phase complex space mission design. • Potential of a novel approach using pattern languages and matheuristics. • Proposition and description of a concept for an innovative interdisciplinary tool using pattern languages and matheuristics. • Verification of the proposed support tool concept by recreating the Apollo study results as a proof-of-concept.

Biologically Inspired Design Concept Generation Using Generative Pre-Trained Transformers

Abstract Biological systems in nature have evolved for millions of years to adapt and survive the environment. Many features they developed can be inspirational and beneficial for solving technical problems in modern industries. This leads to a specific form of design-by-analogy called bio-inspired design (BID). Although BID as a design method has been proven beneficial, the gap between biology and engineering continuously hinders designers from effectively applying the method. Therefore, we explore the recent advance of artificial intelligence (AI) for a data-driven approach to bridge the gap. This paper proposes a generative design approach based on the generative pre-trained language model (PLM) to automatically retrieve and map biological analogy and generate BID in the form of natural language. The latest generative pre-trained transformer, namely generative pre-trained transformer 3 (GPT-3), is used as the base PLM. Three types of design concept generators are identified and fine-tuned from the PLM according to the looseness of the problem space representation. Machine evaluators are also fine-tuned to assess the mapping relevancy between the domains within the generated BID concepts. The approach is evaluated and then employed in a real-world project of designing light-weighted flying cars during its conceptual design phase The results show our approach can generate BID concepts with good performance.