To obtain optimal design efficiently in the initial design stage of a ship, a hybrid system is developed by integrating the optimization algorithm and knowledge-based system. The hybrid system can manipulate numeric and symbolic data simultaneously. To increase search efficiency in a design space, the optimization algorithm (optimizer) is implemented by coupling a genetic algorithm (GA) and search method. The optimizer determines a candidate region around the optimum point by using the GA, then searches the optimum point by the search method concentrating in this region, thus reducing calculation time and increasing search efficiency. To generate input data for the optimizer, a rule-based system is developed. Some domain knowledge for ship optimization in the initial design stage is retrieved from a database of existing ship and design experts. The obtained knowledge is stored in the knowledge base. The optimizer incorporates a knowledge-based system with heuristic and analytic knowledge, thereby narrowing the feasible space of the design variables. Therefore, search speed and the capability of finding an optimum point will be increased in comparison with conventional approach. The developed system is applied principally to particulars of optimization of ships with multicriteria. Through application ship design, it shows that the hybrid system can be a useful tool for optimum design.

This paper describes current research toward automating the redesign process. In redesign, a working design is altered to meet new problem specifications. This process is complicated by interactions between different parts of the design, and many researchers have addressed these issues. An overview is given of a large design tool under development, the Circuit Designer's Apprentice. This tool integrates various techniques for reengineering existing circuits so that they meet new circuit requirements. The primary focus of the paper is one particular technique being used to reengineer circuits when they cannot be transformed to meet the new problem requirements. In these cases, a design plan is automatically generated for the circuit, and then replayed to solve all or part of the new problem. This technique is based upon the derivational analogy approach to design reuse. Derivational Analogy is a machine learning algorithm in which a design plan is saved at the time of design so that it can be replayed on a new design problem. Because design plans were not saved for the circuits available to the Circuit Designer's Apprentice, an algorithm was developed that automatically reconstructs a design plan for any circuit. This algorithm, Reconstructive Derivational Analogy, is described in detail, including a quantitative analysis of the implementation of this algorithm.

This paper discusses a work in progress in the development of computer tools for qualitative modeling analysis and evaluation of conceptual structural designs. In the conceptual design stage the description of a structure is incomplete and imprecise, and does not permit the use of traditional numerical analysis tools. We describe a prototype system, QLRS, for qualitative evaluation of lateral load resistance in frames. The primary goal of the evaluation of structural response is to identify undesirable structural behavior. In QLRS, the evaluation process consists of three basic tasks. (1) identification of the story and structure models comprising the lateral load resisting system. We term this task structural system interpretation. (2) Qualitative analysis of the story and structure models, and approximate evaluation of the story drifts. We term this task structural behavior interpretation. (3) Assessment of the performance of the lateral load resisting system, in which the results of the structural system interpretation and the structural behavior interpretation are compared against the requirements for complete load path and relative story drift. Currently, QLRS is able to reason about load path discontinuities and soft-story behavior problems in 2-D moment resisting frames.

Product configuration is a major industrial application domain for constraint satisfaction techniques. Conditional constraint satisfaction problems (CCSPs) and feature models (FMs) have been developed to represent configuration problems in a natural way. CCSPs are like constraint satisfaction problems (CSPs), but they also include potential variables, which might or might not exist in any given solution, as well as classical variables, which are required to take a value in every solution. CCSPs model, for example, options on a car, for which the style of sunroof (a variable) only makes sense if the car has a sunroof at all. FMs are directed acyclic graphs of features with constraints on edges. FMs model, for example, cell phone features, where utility functions are required, but the particular utility function “games” is optional, but requires Java support. We show that existing techniques from formal methods and answer set programming can be used to naturally model CCSPs and FMs. We demonstrate configurators in both approaches. An advantage of these approaches is that the model builder does not have to reformulate the CCSP or FM into a classic CSP, converting potential variables into classical variables by adding a “does not exist” value and modifying the problem constraints. Our configurators automatically reason about the model itself, enumerating all solutions and discovering several kinds of model flaws.

Perspectives on research methodology in the field of “AI and design” are discussed. This perspective is based on a view of a “science of design” focusing on methods of design and on characteristics of design tasks that affect what methods are relevant for a given task. Two methodological issues are discussed: the need to try applying a design method on multiple tasks and domains, and the need to work with collaborators who are experts in the task domain of each research system you build.

Functional design is regarded as a design activity primarily aimed at clarifying customer needs, and developing the functional architecture and solution concepts for a system under development. Existing functional design approaches are mainly focused on how to assist designers in searching for solution principles for desired products, which, however, do not adequately take into account the interactions between a smart system under development and its environment, and cannot explicitly represent the complex functional logic of the system, resulting in that they cannot effectively assist designers in the functional design of smart systems. Therefore, this paper proposes a scenario-integrated approach for functional design of smart systems to address the above issues. Based on the concept of scenario in software engineering, the proposed approach explicitly elaborates how to employ scenarios to express subjective customer needs and how to generate the functional architectures and the corresponding solution concepts through a structured process. The functional design of the automated doors-unlocking system of a smart vehicle is employed to illustrate the proposed approach, which also demonstrates that the proposed approach is suitable for functional design of smart systems.

Published research on design rationale (DR) goes back at least 25 years. Judging by the number of publications and the variety of application domains, there has been a significant increase in related research activities in recent years. For example, there have been other special issues on design rationale (e.g., Carrol & Moran, 1991), workshops in international conferences (e.g., Lee, 1992; Chung & Bañares–Alcántara, 1994), and the first book on design rationale has just appeared (Carrol & Moran, 1996).

Machine learning (ML) is increasingly used to enhance intelligent products in the field of product design. However, ML has a never-ending lifecycle in which its capabilities and technical properties iteratively change as new annotated data are utilized. The never-ending lifecycle of ML (which includes data annotation, model training, and other steps) has led to challenges to the prototyping of ML-enhanced products and requires a high level of ML literacy in designers. To facilitate the prototyping of ML-enhanced products and improve the ML literacy of designers, we draw inspiration from a design method called Material Lifecycle Thinking (MLT), which regards ML as a continuously evolving design material. Based on the MLT, we proposed a cyclical prototype workflow and developed inML Kit, a toolkit enabling designers to make functional ML prototypes and improve ML literacy by involving them in the never-ending ML lifecycle. The toolkit was designed, iterated, and implemented through the participatory design process with experienced designers in this field. We evaluated inML Kit by conducting a controlled user study where our toolkit was compared with Google AIY. The evaluation results imply that our inML Kit helps designers to make functional ML prototypes while improving their ML literacy.

The original ideas on design abduction, inspired by treatments in philosophy of science, had a narrow conception on how novelty emerges in design, when looked at in terms of logic. The authors have previously presented a re-proposed notion of abduction in design, taking the differences between science and design into account. Now, in this article, the invention of the airplane by the Wright brothers is analyzed as a retrospective case study. Key parts of the re-proposed notion of design abduction are demonstrated, and two new types of design abduction are identified, namely strategic abduction and dynamic abduction. Perhaps even more importantly, a new hypothesis on the cognitive basis of design abduction is reached. While the importance of model-based abduction (and reasoning) is confirmed, the case also pinpoints the central role of verbalization and discussion in supporting design reasoning in general and especially abduction. All in all, it seems that an improved understanding of design abduction and its cognitive basis would be instrumental in promoting more effective and efficient designing.

In the product design realm, designers often use presentations to convey certain ideas about a product or a specific stage of the design process. The popular forms of presentation include verbal pitching, two-dimensional drawing, and prototyping. The clients, investigators, and other audiences rely on such presentations to evaluate an idea. Popular idea evaluation assessment tools, such as the consensual assessment technique, utilize such interactions. On the other hand, numerous pieces of literature state that the audiences are heavily influenced by the quality of presentation when evaluating the worth of the product being presented. In this study, we examine if the audience is able to discriminate between the quality of the presentation and the quality of the idea being presented. A total of 613 ideas were evaluated over a 4-year period during a specific product design class at different phases in the design process. The result shows that no matter the kind of presentation tool used, the presentation quality ratings and the idea value ratings had a very strong positive correlation despite the explicit instructions to reviewers to separate presentation quality from concept quality. Our additional analysis shows that such a pattern did not change during the different phases of the design process.

Artificial intelligence and cognitive science are two core research areas in design. Artificial intelligence shows the capability of analysing massive amounts of data which supports making predictions, uncovering patterns and generating insights in varying design activities, while cognitive science provides the advantage of revealing the inherent mental processes and mechanisms of humans in design. Both artificial intelligence and cognitive science in design research are focused on delivering more innovative and efficient design outcomes and processes. Therefore, this thematic collection on “Applications of Artificial Intelligence and Cognitive Science in Design” brings together state-of-the-art research in artificial intelligence and cognitive science to showcase the emerging trend of applying artificial intelligence techniques and neurophysiological and biometric measures in design research. Three promising future research directions: 1) human-in-the-loop AI for design, 2) multimodal measures for design, and 3) AI for design cognitive data analysis and interpretation, are suggested by analysing the research papers collected. A framework for integration of artificial intelligence and cognitive science in design, incorporating the three research directions, is proposed to inspire and guide design researchers in exploring human-centred design methods, strategies, solutions, tools and systems.

The job scheduling problem (JSP) is considered as one of the most complex combinatorial optimization problems. JSP is not an independent task, but is rather a part of a company business case. In this paper, we have studied JSPs under sudden machine breakdown scenarios that introduce a risk of not completing the jobs on time. We have first solved JSPs using an improved memetic algorithm and extended the algorithm to deal with the disruption situations, and then developed a simulation model to analyze the risk of using a job order and delivery scenario. This paper deals with job scheduling under ideal conditions and rescheduling under machine breakdown, and provides a risk analysis for a production business case. The extended algorithm provides better understanding and results than existing algorithms, the rescheduling shows a good way of recovering from disruptions, and the risk analysis shows an effective way of maximizing return under such situations.

The AI EDAM journal published its first issue in 1987. Now, amazingly, 20 years later, this issue starts the journal's third decade.

In this paper we consider a company including both a forward supply chain producing and supplying products to markets and an after-sales supply chain providing spare parts to fulfill its after-sales commitments. Uncertainty in estimating product demand in the premarkets and spare parts demands in the after-sales markets and qualified outputs of production facilities throughout these two chains are considered in this problem. Stochastic qualified outputs of these facilities are due to their imperfect productions systems. We show that uncertainties propagate and qualified flow depreciates by moving material, components, and products from upstream to the downstream of these supply chains, and these phenomena should be quantified to determine the service levels of this company in the pre- and after-sales markets. At the end, we propose a mathematical model determining the best marketing strategies for this company (i.e., price, warranty length, and service levels) in the markets and their preserving reliable flow dynamics throughout the chains’ networks. Finally, the model is tested on a test problem defined in engine industry and some managerial insights are provided by analyzing the results.

This annotated bibliography includes a small sample of sources on various aspects of research methodology from diverse disciplines that influence research on artificial intelligence techniques in engineering design analysis and manufacturing (AIEDAM). Some of these sources are extended edited volumes containing many relevant contributions and pointing to additional references. These volumes are marked by a preceding bullet (•). The bibliography is not comprehensive; it covers only several important subjects, and in each subject it lists several representative contributions ordered chronologically.

In this paper we present a formal common sense theory of the adoption of perception-based beliefs. We begin with a logical analysis of perception and then consider when perception should lead to belief change. Our theory is intended to apply to perception in humans and to perception in artificial agents at the level of the symbolic interface between a vision system and a belief system. In order to provide a context for our work we relate it to the emerging field of cognitive robotics, give an abstract architecture for an agent which is both embodied and capable of reasoning, and relate this to the concrete architectures of two vision-based surveillance systems.

Design consists of analyzing scenarios and proposing artifacts, obeying the initial set of requirements that lead from initial to goal state. Finding or creating alternative solutions, analyzing them, and selecting the best one are expected steps in the designer’s decision making process. Very often, not a sole designer, but a team of them is engaged in the design process, sharing their expertise and responsibility to achieve optimum projects. In a design team, most conflicts occur due to misunderstanding of one’s assessment of specifications and contexts. Decision explanations play a key role in teamwork success. Designers are rational agents trained to follow rational methods. Acceptable justifications include value function, requirements, constraints, and criteria. Generally, explanations are delivered in a multimedia fashion, composed of text, graphics and gestures, to provide the audience the ability to perceive what was contextually imagined. The more spatial the reasoning is, the richer the explanation channel should be. This paper presents CineADD, a design explanation generation model based on cinema techniques such as animation, scripting, editing, and camera movements. The idea is to provide designers with a tool for describing the way their projects should be visually explained, as in a movie. Designers develop their projects in an active design document environment. Rationale is captured as a design model, so explanations can be generated instead of retrieved. The captured design model serves as a base to visually reconstruct design, giving emphasis and guidance by using movie storytelling techniques. CineADD was implemented for the domain of oil pipeline layout showing the feasibility of this approach. We expect CineADD to become a commodity attachable to any intelligent CAD system.

Platform product development is a contemporary approach to agile product development for mass customization. Distinctive product variants are derived or customized from a platform that is defined as components and subsystems commonly shared across a product family. A well-organized platform is essential to connect different parties of an enterprise including soliciting customer needs through order fulfillment to field service. Hence, it is also critical to achieve the economy of scale by identifying repetitive applications of share tooling, knowledge, and other resources. In this Special Issue, we attempt to cover the different aspects of platform product development. The topics span a wider range of artificial intelligence (AI) disciplines, from knowledge representation to knowledge support systems. It identifies a fertile area not only for applying AI to contemporary issues of design and manufacturing systems but also for enriching the methodology for developing AI systems in manufacturing enterprises. Indeed, we consider that numerous successful applications in the industrial sectors highlight a future direction for productive AI applications in industry.

Most engineering design problems involve optimizing a number of often conflicting performance measures in the presence of multiple constraints. Traditional vector optimization techniques approach these problems by generating a set of Pareto-optimal solutions, where any specific objective can be further improved only at the cost of degrading one or more other objectives. The solutions obtained in this manner, however, are only single points within the space of all possible Pareto-optimal solutions and generally do not indicate to designers how small deviations from predicted design parameters settings affect the performance of the product or the process under study.

In this paper we introduce a new approach to robust design based on the concept of inductive learning with regression trees. Given a set of training examples relating to a multiobjective design problem, we demonstrate how a multivariate regression tree can utilize an information-theoretic measure of covariance complexity to capture optimal, tradeoff design surfaces. The novelty of generating design surfaces as opposed to traditional points in the design space is that now designers are able to easily determine how the responses of a product or process vary as design parameters change. This ability is of paramount importance in situations where design parameter settings need to be modified during the lifetime of a product/process due to various economic or operational constraints. As a result, designers will be able to select optimal ranges for design parameters such that the product's performance indices exhibit minimal or tolerable deviations from their target values. To highlight the advantages of our methodology, we present a multiobjective example that deals with optimum design of an electric discharge machining (EDM) process.