We propose a computational method for producing novel constructs that fall within an existing design or artistic style. The method is based on evolutionary algorithms, and we discuss related knowledge representation issues. We then present an implementation of this method that we used in order to imitate the style of the Dutch painter Mondrian. Finally, we explain and give the results of a cognitive experiment designed to determine the effectiveness of the method, and provide a discussion of these results.

This study attempts to correlate the nonlinear invariants' with the changing conditions of a drilling process through a series of condition monitoring experiments on small diameter (1 mm) drill bits. Run-to-failure tests are performed on these drill bits, and vibration data are consecutively gathered at equal time intervals. Nonlinear invariants, such as the Kolmogorov entropy and correlation dimension, and statistical parameters are calculated based on the corresponding conditions of the drill bits. By intervariations of these values between two successive measurements, a drop–rise table is created. Any variation that is within a certain threshold (±20% of the measurements in this case) is assumed to be constant. Any fluctuation above or below is assumed to be either a rise or a drop. The reduct and conflict tables then help eliminate incongruous and redundant data by the use of rough sets (RSs). Inconsistent data, which by definition is the boundary region, are classified through certainty and coverage factors. By handling inconsistencies and redundancies, 11 rules are extracted from 39 experiments, representing the underlying rules. Then 22 new experiments are used to check the validity of the rule space. The RS decision frame performs best at predicting no failure cases. It is believed that RSs are superior in dealing with real-life data over fuzzy set logic in that actual measured data are never as consistent as here and may dominate the monitoring of the manufacturing processes as it becomes more widespread.

This article describes an investigation into the feasibility of using contextual reasoning to monitor and supervise the collaborative work of several knowledge workers working together on a project. Managing large and complex projects is a difficult task that requires situational awareness by the project manager to be able to be proactive when possible and to react correctly in the presence of events. In complex projects, effective oversight of the project personnel and the progress of the project are essential in ensuring that project objectives are met. This is especially true of projects that require contributions from various experts, whose interaction may be limited to a Web-based collaborative tool. Such oversight is typically the job of a project manager who is tasked with avoiding cost overruns, shipment delays, and ensuring product effectiveness. We utilize context-based reasoning and contextual graphs as the tools of choice for implementing an agent that emulates the function of a competent project manager. We use rocket design and manufacture as the domain to evaluate our technique. We use a public domain rocket design software package developed by the National Aeronautics and Space Administration as a guide to the domain. The article describes the investigation, its results, and the related works in a collaborative design project.

In this paper we present a genotype representation method for improving the performance of genetic-algorithm-based optimal design and synthesis of microelectromechanical systems. The genetic algorithm uses a hierarchical component-based genotype representation, which incorporates specific engineering knowledge into the design optimization process. Each microelectromechanical system component is represented by a gene with its own parameters defining its geometry and the way it can be modified from one generation to the next. The object-oriented genotype structures efficiently describe the hierarchical nature typical of engineering designs. They also encode knowledge-based constraints that prevent the genetic algorithm from wasting time exploring inappropriate regions of the search space. The efficiency of the hierarchical component-based genotype representation is demonstrated with surface-micromachined resonator designs.

Designers who are experts in a given design domain are well known to be able to Immediately focus on “good designs,” suggesting that they may have learned additional constraints while exploring the design space based on some functional aspects. These constraints, which are often implicit, result in a redefinition of the design space, and may be crucial for discovering chunks or interrelations among the design variables. Here we propose a machine-learning approach for discovering such constraints in supervised design tasks. We develop models for specifying design function in situations where the design has a given structure or embodiment, in terms of a set of performance metrics that evaluate a given design. The functionally feasible regions, which are those parts of the design space that demonstrate high levels of performance, can now be learned using any general purpose function approximator. We demonstrate this process using examples from the design of simple locking mechanisms, and as in human experience, we show that the quality of the constraints learned improves with greater exposure in the design space. Next, we consider changing the embodiment and suggest that similar embodiments may have similar abstractions. To explore convergence, we also investigate the variability in time and error rates where the experiential patterns are significantly different. In the process, we also consider the situation where certain functionally feasible regions may encode lower dimensional manifolds and how this may relate to cognitive chunking.

How can we prepare engineering students to work collectively on innovative design issues, involving ill-defined, “wicked” problems? Recent works have emphasized the need for students to learn to combine divergent and convergent thinking in a collaborative, controlled manner. From this perspective, teaching must help them overcome four types of obstacles or “fixation effects” (FEs) that are found in the generation of alternatives, knowledge acquisition, collaborative creativity, and creativity processes. We begin by showing that teaching based on concept–knowledge (C-K) theory can help to manage FEs because it helps to clarify them and then to overcome them by providing means of action. We show that C-K theory can provide scaffolding to improve project-based learning (PBL), in what we call project-based critical learning (PBCL). PBCL helps students be critical and give due thought to the main issues in innovative design education: FEs. We illustrate the PBCL process with several cases and show precisely where the FEs appear and how students are able to overcome them. We conclude by discussing two main criteria of any teaching method, both of which are usually difficult to address in situations of innovative design teaching. First, can the method be evaluated? Second, is the chosen case “realistic” enough? We show that C-K-based PBCL can be rigorously evaluated by teachers, and we discuss the circumstances in which a C-K-based PBCL may or may not be realistic.

Defining the aesthetic and emotional value of a product is an important consideration for its design. Furthermore, if several designers are faced with the task of creating an object that describes a certain emotion/perception (aggressive, soft, heavy, etc.), each is most likely to interpret the emotion/perception with different shapes composed of a set of different geometric features. The authors propose an automatic approach to formalize the relationships between geometric information of three-dimensional objects and the intended emotional content using fuzzy logic. In addition, the automatically generated fuzzy knowledge base was compared to the user's perceptions and to the manually constructed fuzzy knowledge base. The initial findings indicate that the approach is valid to formalize geometric information with perceptions and validate the author's manually developed fuzzy models.