The task of modeling, i.e., of creating a set of equations that can be used to predict the behavior of a physical object, is a key step in engineering analysis. This paper describes a computer system, MSG, for generating mathematical models to analyze physical systems involving heat transfer behavior. MSG is motivated by the need for modeling in an automated design process. The models are sets of equations which may include algebraic equations, ordinary differential equations and partial differential equations. MSG uses the strong domain theory to guide model construction in three sequential tasks: identify regions of interests on an object, determine relevant heat transfer and energy storage processes, and transform these processes into equations. The decisions in these tasks are guided by estimates of variation in temperature and material property, and the relative strengths of heat transfer processes.

According to Simon (1983), machine learning is a process that improves the performance of an intelligent system. The performance task of a design system is to arrive at a structural description of a device given its functional description. Machine learning can occur, to improve the performance of the design system, in a number of ways. The learning can make the process of arriving at a known structure to function mapping faster, either by improving the control strategy or by learning new world knowledge needed for the structure to function mapping. It can also improve the performance of the design system by allowing it to come up with new structure to function mappings. The latter kinds of learning leads to innovative designs. The work presented in this paper, EnviroAdapt, belongs to the latter category. EnviroAdapt has the performance task of designing devices along with their operating environments. The EnviroAdapt learns about the novel environments and designs devices for these environments. This learning process is enabled by adapting the previous designs of devices along with their operating environments. This adaptation process makes use of abstracting general mechanisms from the previous designs, then instantiating them in the context of new design problem. Both of these processes are driven by the characteristics of the new design problem that requires a device to operate within a novel operating environment.

Machlup used the words alpha, beta, and gamma to identify humanities, science, and social science as three distinct fields of academic learning and knowing, in addition to general knowledge. Gilles and Paquet identified a fourth type of disciplinary knowledge and labeled it as delta. This includes the knowledge of creative disciplines such as design, law, and economy. Since the time of these road-paving works, a lot has changed. In the last two decades, various concepts and manifestations of intellectualized engineered systems have appeared. A paradigmatic feature of these systems, exemplified by smart cyber-physical systems, is that they collect, infer, or extract massive amount of synthetic system knowledge (M-SSK) based on some pre-programmed human knowledge. The amount of this type of knowledge grows continuously. It can be aggregated on system level and on system of systems level. This paper argues that this aggregated M-SSK is not covered by the abovementioned four genres of knowledge. In fact, it represents a new genre. The conducted literature study underpins this claim. Therefore, the paper suggests dealing with it as a new genre, called epsilon-knowledge. Artificial intelligence, system engineering, cyber-physical systems, and knowledge engineering are the disciplines dealing with epsilon-knowledge. The paper refers to sympérasmology as the proper conceptual framework of studying this genre of knowledge.

Recent advances in machine learning have enabled computers to converse with humans meaningfully. In this study, we propose using this technology to facilitate design conversations in large-scale urban development projects by creating chatbot systems that can automate and streamline information exchange between stakeholders and designers. To this end, we developed and evaluated a proof-of-concept chatbot system that can perform design conversations on a specific construction project and convert those conversations into a list of requirements. Next, in an experiment with 56 participants, we compared the chatbot system to a regular online survey, focusing on user satisfaction and the quality and quantity of collected information. The results revealed that, with regard to user satisfaction, the participants preferred the chatbot experience to a regular survey. However, we found that chatbot conversations produced more data than the survey, with a similar rate of novel ideas but fewer themes. Our findings provide robust evidence that chatbots can be effectively used for design discussions in large-scale design projects and offer a user-friendly experience that can help to engage people in the design process. Based on this evidence, by providing a space for meaningful conversations between stakeholders and expanding the reach of design projects, the use of chatbot systems in interactive design systems can potentially improve design processes and their outcomes.

Neuroevolution, or evolving neural networks with evolution algorithms such as genetic algorithms, is becoming one of the hottest areas in hybrid systems research. One of the areas that become under research using neuroevolutions is the controllers. In this paper, we shall present two engineering controllers based on neuroevolutions techniques. One of the controllers is used to monitor the temperature and humidity in an industry. This controller is having a linear behavior. The second controller is concerned with scheduling parts in queues in an industry. The scheduling controller is having a nonlinear behavior. The results obtained by the proposed controllers based on neuroevolution are compared with results obtained by traditional methods such as neural networks with backpropagation and ordinary simulation for the controller. The results show that the neuroevolution approaches outperform the results obtained by other methods.

The paper by Woodbury and Burrow is examined using four criteria: completeness, discrimination, alternative approaches, and combining exploration in different problem domains. Although the paper covers significant aspects of the search space literature it leaves out some relevant aspects of the cognitive approach. It fares much better in terms of discriminating important concepts and alternative approaches to the modeling of the design search space. The structure–function–behavior model is suggested as an analogy for the central parameters of the search space paradigm. The Woodbury and Burrow paper reveals more than what has been accomplished up to now in the design search space area, but its task still remains incomplete.

The presence of aerodynamics loadings makes the design of some classes of elastic structures, as, for instance, marine structures and risers, very challenging. Moreover, capturing the complex physical interaction between the structure and the fluid is challenging for both theoretical and numerical models. One of the most important phenomena that appear in these situations is vortex-induced vibrations. The picture is even more complicated when multiple elastic elements are close enough to interact by modifying the fluid flow pattern. In the present work, we show how the common design practice for these structures, which is entirely based on deterministic simulations, needs to be complemented by the uncertainty quantification analysis. The model problem is a structure constituted by two elastically mounted cylinders exposed to a two-dimensional uniform flow at Reynolds number 200. The presence of a manufacturing tolerance in the relative position of the two cylinders, which we consider to be a source of uncertainty, is addressed. The overall numerical procedure is based on a Navier–Stokes immersed boundary solver that uses a flexible moving least squares approach to compute the aerodynamics loadings on the structure, whereas the uncertainty quantification propagation is obtained by means of a nonintrusive polynomial chaos technique. A range of reduced velocities is considered, and the quantification, in a probabilistic sense, of the difference in the performances of this structure with respect to the case of an isolated cylinder is provided. The numerical investigation is also complemented by a global sensitivity analysis based on the analysis of variance.

Requirement planning is one of the most critical tasks in the product development process. Despite its significant impact on the outcomes of the design process, engineering requirement planning is often conducted in an ad hoc manner without much structure. In particular, the requirement planning phase suffers from a lack of quantifiable measures for evaluating the quality of the generated requirements and also a lack of structure and formality in representing engineering requirements. The main objective of this research is to develop a formal Web Ontology Language ontology for standard representation of engineering requirements. The proposed ontology uses explicit semantics that makes the ontology amenable to automated reasoning. To demonstrate how the proposed ontology can support requirement analysis and evaluation in engineering design, three possible services enabled by the ontology are introduced in this paper. These services are information content measurement, specificity and completeness analysis, and requirement classification. The proposed ontology and its associated algorithms and tools are validated experimentally in this work.

A selective, multiple-criteria method is proposed for handling constraint violations in well-defined design problems. First, the types of design problems upon which the method may apply are presented and a graph topology is adopted for representing the problem decomposition in the level of design parameter interrelations (design parameter graphs). Next, the problem of constraint violations for the design parameters is discussed. It is shown that these violations can be resolved by modifying the values of the primary design parameters and recalculating the values of the violated parameters. Any “blind” attempt of modifying the values of the primary design parameters for resolving occurring violations may, eventually, create additional violations. The proposed method guides the designer toward those primary design parameters that present the least possibility of creating more violations when their values are modified. This is achieved by applying multiple criteria and by producing a final, sorted list of primary design parameters. The designer may then choose the first element of this list to handle efficiently the violations of the design parameters. Two examples are given on a design space where constraint violations occur. Through these examples, the capability of the proposed method in helping the designer to handle constraint violation is shown. The concluding remarks, except for summarizing the potential of the method, determine its boundaries and include a reference on relative work currently under investigation.

Generative research in design investigates compact representations that facilitate the rapid exploration of large design spaces. It includes among other things: rule-based systems, feature structures, and genetic algorithms. Generative systems are being applied to a variety of design problems from various disciplines including engineering, product design, and architecture. The objective is to further our understanding of the design operations and manipulations to create systems that better support the designers' activity.

We describe three approaches to identify novel product affordances: affordance of absence; insights from lead users, specifically do-it-yourselfers (DIYers); and natural-language searches. While these approaches were separately pursued, we show their connection to each other in this paper. We begin by describing the affordance of absence, inspired by insights on affordances arising from a lack of resources. For example, in the absence of specialized tools, more general tools are used to accomplish similar tasks. Such absence clarifies how other tools could be modified to add relevant features and identifies critical features of the absent tool. In addition, the temporary removal of physical features and objects enables user interaction in ways that may not emerge in their presence. Affordance of absence has the potential to more fully specify affordances for a given object and to help overcome functional fixedness. For the second approach, we describe insights from DIYers obtained from the “IKEA hackers” online community. We consider DIYers lead users for seeking out and exploiting product affordances, often transforming product functions dramatically. We also discuss their projects through the lens of affordance of absence. For the third approach, we outline our natural-language approach to affordance extraction, beginning with consumer product reviews provided for Canadian Tire, a major Canadian retailer. We describe efforts toward automatically identifying less common affordances, and the use of cue phrases to highlight insightful DIY transformations from the IKEA hackers community. Finally, we comment on the potential value of this work for product design in general.

Sometime in the mid-1980s, in an urban restaurant some-where in the United States, I was sitting next to a Japanese engineer who was talking to a U.S. engineer. The following is the record of their conversation that I made with my Sony Walkman.

The concept of a function is of great importance in design. This paper describes from theory how designers should reason about functions when designing. This paper introduces the link model, showing how functions and properties link the product and its use, to the perceived value of the product. The important and useful distinction between functions and properties is made along with the distinction between “wirk functions,” which is what the product does when operating, and “use functions,” which is what the product is used for. The paper makes a novel contribution beyond previous literature, showing that not only is a product's behavior or mode of action designed but also the use activity of the end user. Based on the theoretical perspective unfolded, the authors offer nine mind-sets for both design practitioners and researchers to consider when reasoning about functions.

Universal access on equal terms to audiovisual content is a key point for the full inclusion of people with disabilities in activities of daily life. As a real challenge for the current Information Society, it has been detected but not achieved in an efficient way, due to the fact that current access solutions are mainly based in the traditional television standard and other not automated high-cost solutions. The arrival of new technologies within the hybrid television environment together with the application of different artificial intelligence techniques over the content will assure the deployment of innovative solutions for enhancing the user experience for all. In this paper, a set of different tools for image enhancement based on the combination between deep learning and computer vision algorithms will be presented. These tools will provide automatic descriptive information of the media content based on face detection for magnification and character identification. The fusion of this information will be finally used to provide a customizable description of the visual information with the aim of improving the accessibility level of the content, allowing an efficient and reduced cost solution for all.

This paper addresses an important application of machine learning (ML) in design. One of the major bottlenecks in the process of engineering analysis by using the finite-element method—a design of the finite-element mesh—was a subject of improvement. Defining an appropriate geometric mesh model that ensures low approximation errors and avoids unnecessary computational overhead is a very difficult and time-consuming task based mainly on the user's experience. A knowledge base for finite-element mesh design has been constructed using the ML techniques. Ten mesh models have been used as a source of training examples. The mesh dataset was probably the first real-world relational dataset and became one of the most widely used training set for experimenting with inductive logic programming (ILP) systems. After several experiments with different ML systems in the last few years, the ILP system CLAUDIEN was chosen to construct the rules for determining the appropriate mesh resolution values. The ILP has been found to be an effective approach to the problem of mesh design. An evaluation of the resulting knowledge base shows that the mesh design patterns are captured well by the induced rules and represent a solid basis for practical application. The aim of this paper is not only to present the real-life ML application to design, but also to describe and discuss a relation of the work being done to the topic of this special issue: the proposed “dimensions” of ML in design.

Automated support of design teams, consisting of both human and automated systems, requires an understanding of the role of trust in distributed design processes. By explicating trust, an individual designer's decisions become better understood and may be better supported. Each individual designer has his or her private goals in a cooperative design setting, in which requirement conflicts and resource competitions abound. However, there are group goals that also need to be reached. This paper presents an overview of research related to trust in the context of agents and design, a computational knowledge-level model of trust based on the seven beliefs distinguished by Castelfranchi and Falcone, and an example of the use of the trust model in a specific design process, namely, Website design from the perspective of a single designer. The results are discussed in the context of distributed design in open systems.

The paper proposes and evaluates a binary network architecture and complementary training algorithm designed for pattern classification, with applications in a variety of engineering problems. The advantages of the system are that it can always converge on zero error for a set of unambiguous training patterns (if required), converges rapidly, and circumvents the issue of how many hidden neurons to incorporate in a network. The main benefit of the proposed system over Hamming networks, its main counterpart, is that it can group patterns into different classes along any boundary. The system is shown to outperform 1) the Hamming network for a character recognition problem where the images are subject to both position change and noise; and 2) a radial-Gaussian network in a truck-type classification problem. A variant of the system, where hidden neuron thresholds are set to zero, is shown to further improve performance if a comprehensive set of noise-free input patterns are available for training.

This paper presents an expert system (called ADES, i.e. ATP Design Expert System) for the automatic design of Automatic Train Protection systems (ATP). An ATP system is a railway signalling system constituted by a set of logic circuits that control the safe movement of trains within a railway station.

AI techniques proved feasible to address the particular design problem discussed: ADES is able to rapidly design good control circuits to meet operational requirements by using a well-structured, explicitly represented, in depth knowledge of Automatic Train Protection. The use of AI techniques facilitates the maintenance and extension of ADES to face new or unplanned requirements.

Implementing both the expert system and its environment tools in the PROLOG language, by using meta-interpretation techniques, has led to the rapid prototyping of the overall system. Optimization techniques have also been developed to allow ADES to be efficiently executed.