Problem solving methods (PSMs) are software components that represent and encode reusable algorithms. They can be combined with representations of domain knowledge to produce intelligent application systems. A goal of research on PSMs is to provide principled methods and tools for composing and reusing algorithms in knowledge-based systems. The ultimate objective is to produce libraries of methods that can be easily adapted for use in these systems. Despite the intuitive appeal of PSMs as conceptual building blocks, in practice, these goals are largely unmet. There are no widely available tools for building applications using PSMs and no public libraries of PSMs available for reuse. This paper analyzes some of the reasons for the lack of widespread adoptions of PSM techniques and illustrate our analysis by describing our experiences developing a complex, high-throughput software system based on PSM principles. We conclude that many fundamental principles in PSM research are useful for building knowledge-based systems. In particular, the task-method decomposition process, which provides a means for structuring knowledge-based tasks, is a powerful abstraction for building systems of analytic methods. However, despite the power of PSMs in the conceptual modeling of knowledge-based systems, software engineering challenges have been seriously underestimated. The complexity of integrating control knowledge modeled by developers using PSMs with the domain knowledge that they model using ontologies creates a barrier to widespread use of PSM-based systems. Nevertheless, the surge of recent interest in ontologies has led to the production of comprehensive domain ontologies and of robust ontology-authoring tools. These developments present new opportunities to leverage the PSM approach.
Inductive learning is proposed as a tool for synthesizing domain
knowledge from data generated from a model-based simulator. To use an
inductive engine to generate decision rules, a preclassification process
is necessary in the presence of multiple competing objectives. Instead
of relying on a domain expert to perform this preclassification, a
clustering algorithm is used to eliminate the human bias involved in the
selection of a classification function for the preclassification. It is
shown that the use of a clustering algorithm for preclassification not
only further automates the process of knowledge synthesizing, but also
improves the quality of the rules generated by the inductive
This paper discusses the framework of a Knowledge Based Expert System (KBES) environment to design aerospace structures under structural and aerodynamic constraints using ASTROS (Automated Structural Optimization program). ASTROS is a synthesis tool built around the NASTRAN finite element program. The knowledge base capabilities are discussed for synthesizing in statics, normal mode, steady and unsteady aerodynamic disciplines. A description of the two ASTROS advisor modules the Editor/Bulk Data generator and Post-processor is included. Experiences and issues involved in hierarchical representation of knowledge as menu options at different levels of abstraction are presented. A brief overview of Knowledge Based Systems and the shell CLIPS (C Language Integrated Production System) used to develop the ASTROS Advisor are discussed. Illustrative examples of the advisor in designing airframe structures are also included.
The value of comprehensive rationale for documenting a design has long been recognized. However, designers rarely produce detailed rationale in practice because of the substantial time investment required. Efforts to support the acquisition of rationale information have focused on languages and tools for structuring the acquisition process, but still require substantial involvement on the part of the designer. This paper describes an experimental system, the Rationale Construction Framework (RCF), that acquires rationale information for the detailed design process without disrupting a designer's normal activities. The underlying approach involves monitoring designer interactions with a commercial CAD tool to produce a rich process history. This history is subsequently structured and interpreted relative to a background theory of design metaphors that enable explanation of certain aspects of the design process. The framework provides an environment that can acquire rich, meaningful rati...
this paper we discuss the foregoing issues in the context of an industrial cable harness design project. We shall limit the scope of our discussion to the class of design problems commonly referred to as "configuration design." Unlike novel or creative design problems, the domain knowledge is readily available and the requirements, constraints and primitive design components are defined in configuration design. However, in comparison to routine or parametric design problems, there is a large search space of solutions corresponding to different configurations, as well as variations associated with the components within each configuration. Under such circumstances, global optimization over all possible choices becomes infeasible (Welch and Dixon 1989). A practical solution is one in which routine tasks are automated, but in which engineers guide the system to explore particular parts of the solution space. The nature of configuration design also leads to the need to decompose the design process and the design model hierarchically, which permits high-level operations to be addressed somewhat 3 independently from low-level details.
: Pareto optimality is a domain-independent property that can be used to coordinate distributed engineering agents. Within a model of design called Redux, some aspects of dependency-directed backtracking can be interpreted as tracking Pareto optimality. These concepts are implemented in a framework, called Next-Link, that coordinates legacy engineering systems. This framework allows existing software tools to communicate with each other and a Redux agent over the Internet. The functionality is illustrated with examples from the domain of electrical cable harness design. Keywords:[Design Coordination], [Pareto Optimality], [Change Management], [Distributed Engineering], [Network Agents] 1 Introduction Coordination of distributed engineering agents frequently involves globally conflicting solutions to multiple local objectives. While much computer research on support of collaborative engineering concerns global metrics for optimization, decision support, and negotiation, a basic coor...
Intelligent agents must update their knowledge base as they acquire new information about their environment. The modal logic S5 n has been designed for representing knowledge bases in societies of agents. Halpern and Vardi have proposed the notion of refinement of S5 n Kripke models in order to solve multi-agent problems in which knowledge evolves. We argue that there are some problems with their proposal and attempt to solve them by moving from Kripke models to their corresponding trees. We define refinement of a tree with a formula, show some properties of the notion, and illustrate with the muddy children puzzle. We show how some diagnosis problems in engineering can be modelled as knowledge-based multi-agent systems, and hence how our approach can address them. 1 Introduction 1.1 Temporal epistemic modal logics and their potential for applications In the last few years there is been a growing trend towards applying logical theories (and MultiAgent theories in general) to the ...
Analogical reasoning plays an important role in design. In particular, cross-domain analogies appear to be important in innovative and creative design. However, making cross-domain analogies is hard and often requires abstractions common to the source and target domains. Recent work in case-based design suggests that generic mechanisms are one type of abstractions useful in adapting past designs. However, one important yet unexplored issue is where these generic mechanisms come from. We hypothesize that they are acquired incrementally from design experiences in familiar domains by generalization over patterns of regularity. Three important issues in generalization from experiences are what to generalize from an experience, how far to generalize, and what methods to use. In this paper, we describe how structure-behaviorfunction models of designs in a familiar domain provide the content, and togetherwith the problem-solving context in which learning occurs, also provide the constraints for learning generic mechanisms from design experiences. In particular, we describe the model-based learning method with a scenario of learning of feedback mechanism.
This paper suggests that science is organized in research programmes: a structure including a hard core that is not questioned and auxiliary hypotheses that guard it from negative evidence. Acknowledging that no data can confirm or refute a theory, scientists should adhere to some normative rules when revising auxiliary hypotheses. (Habermas, 1971) This book provides a critique of positivism through a study of the historical development of ideas that led to contemporary positivism. The book does not argue against science, but against "scientism:" The view that equates all knowledge with science. (Toulmin, 1972) This book argues for the necessity to bring philosophy and science together for a reappraisal of epistemology and methodology. Philosophy is to be a historical, empirical, and pragmatic enterprise that should focus on issues such as conceptual change in the sciences and human thought. (Weimer, 1979) This book develops a meta-theory of science in which positivism and logical empiricism and called justificationism and opinions such as those of Popper and Kuhn are termed non-justificationism. The book criticizes justificationist theories of science and uses the metatheory to explain the differences between positions of different contemporary non-justificatinists positions. (Knorr-Cetina, 1981) This book provides a constructivist view of science. It uses several metaphors of a scientist to study the way in which social processes make up for the lack of any rational way for advancing science. (Bunge, 1983) A part of an eight-book treatise on philosophy, this book provides a systems science perspective on epistemology and research methodology. It presents a serious study of scientific realism.
Arguing that design is a social process, we expand the meaning of modeling and analysis to include all activities facilitating continual refinement and criticism of the design requirements, process, and solutions. We do not assume any a priori methods for modeling or analysis; rather, we provide a framework and an approach to study designers and give them whatever modeling and analysis capabilities they choose. Our approach is the basis for a support tool, n-dim, currently under development. AI EDAM, 1992, 7(4):257-274 Subrahmanian et al. (1992) 1 The Objective of Modeling and Analysis Design as a social process involving designers, customers, and other participants consists of creating and refining a shared meaning of requirements and potential solutions through continual negotiations, discussions, clarifications, and evaluations. This shared meaning, crystalized as the design artifact and made persistent as shared memory forms the basis of accumulated experience upon which subse...
This paper presents a novel formulation of the configuration-design problem that achieves the benefits of the concurrent engineering (CE) design paradigm. In CE, all design concerns (manufacturability, testability, etc.) are applied to an evolving design throughout the design cycle. CE identifies conflicts early on, which avoids costly redesign and can lead to better products. Our formulation is based on a distributed, dynamic, interval constraintsatisfaction problem (DDICSP) model. Persistent catalog agents map onto DDICSP variables and constraint agents map onto DDICSP constraints. These agents use a set of operations and heuristics to navigate through the space of possible designs to rapidly eliminate sets of designs until a solution is found. Experimental results show that an architecture where each catalog agent resides on a separate computer has performance advantages over non-distributed approaches. 1 Introduction Design of large-scale artifacts involves consideration of hundr...
Numerical simulation of partial differential equations (PDEs) plays a crucial role in predicting the behavior of physical systems and in modern engineering design. However, in order to produce reliable results with a PDE simulator, a human expert must typically expend considerable time and effort in setting up the simulation. Most of this effort is spent in generating the grid, the discretization of the spatial domain which the PDE simulator requires as input. To properly design a grid, the gridder must not only consider the characteristics of the spatial domain, but also the physics of the situation and the peculiarities of the numerical simulator. This paper describes an intelligent gridder that is capable of analyzing the topology of the spatial domain and predicting approximate physical behaviors based on the geometry of the spatial domain to automatically generate grids for computational fluid dynamics simulators. Typically gridding programs are given a partitioning of the spatial...
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. 1 Introduction The task of modeling, i.e. of creating a set of equations that ca...
One of the products of engineering, besides constructed artifacts, is design documentation. To understand how design participants use documentation, we interviewed designers and typical documentation users and also took protocols of them both creating and using design documentation. Our protocols were taken from realistic projects of preliminary design for heating, ventilation and air conditioning systems (HVAC). Our studies of document creation and use revealed three important issues: (1) Design participants not only look up design facts; they frequently access documents to obtain information about the rationale for design decisions; (2) The design rationale that they seek is often missing from the documents; (3) design requirements change frequently over a project life cycle so that design documents are often inconsistent and out-of-date. Recognizing these documentation issues in design practice, we developed a new approach in which documents are no longer static records, but rather ...
Computational simulation of physical systems generally requires human experts to set up a simulation, run it, evaluate the quality of the simulation output, and repeatedly invoke the simulator with modified input until a satisfactory output quality is achieved. This reliance on human experts makes use of simulators by other programs difficult and unreliable, though invocation of simulators by other programs is critical for important tasks such as automated engineering design optimization. I present a framework for constructing intelligent controllers for computational simulators which can automatically detect a wide variety of problems which lead to low-quality simulation output, using a set of evaluation methods based on knowledge of physics and numerical analysis stored in a data/knowledge base of models and simulations. I describe an experimental implementation of this framework in an intelligent automated controller for a widely used computational fluid dynamics simulator. Computer...
Case-based design promises important advantages over rule-based design systems. However, the actual implementation of the paradigm poses many problems which put the advantages into question. In our work on CADRE, a case-based building design system, we have encountered seven fundamental problems which we think are common to most case-based design systems. We describe the problems and the ways we either solved or worked around them in the CADRE system. This leads us to conclusions about the general applicability of case-based reasoning to building design.
We describe an approach that uses causal and geometric reasoning to construct explanations for the purposes of the geometric features on the parts of a mechanical device. To identify the purpose of a feature, the device is simulated with and without the feature. The simulations are then translated into a "causal-process" representation, which allows qualitatively important differences to be identified. These differences reveal the behaviors caused and prevented by the feature and thus provide useful cues about the feature's purpose. A clear understanding of the feature's purpose, however, requires a detailed analysis of the causal connections between the caused and prevented behaviors. This presents a significant challenge because one has to understand how a behavior that normally takes place affects ~or is affected by! another behavior that is normally absent. This article describes techniques for identifying such elusive relationships. These techniques employ a set of rules that can determine if one behavior enables or disables another that is spatially and temporally far away. They do so by geometrically examining the traces of the causal processes in the device's configuration space. Using the results of this analysis, our program can automatically generate text output describing how the feature performs its function.
: The application of machine learning (ML) to solve practical problems is complex. Only recently, due to the increased promise of ML in solving real problems and the experienced difficulty of their use, has this issue started to attract attention. This difficulty arises from the complexity of learning problems and the large variety of available techniques. In order to understand this complexity and begin to overcome it, it is important to construct a characterization of learning situations. Building on previous work that dealt with the practical use of ML, a set of dimensions is developed, contrasted with another recent proposal, and illustrated with a project on the development of a decision-support system for marine propeller design. The general research opportunities that emerge from the development of the dimensions are discussed. Leading toward working systems, a simple model is presented for setting priorities in research and in selecting learning tasks within large projects. Cen...
In this paper, we propose a population-based evolutionary multiobjective optimization approach to design combinational circuits. Our results indicate that the proposed approach can significantly reduce the computational effort required by a genetic algorithm (GA) to design circuits at a gate level while generating equivalent or even better solutions (i.e., circuits with a lower number of gates) than a human designer or even other GAs. Several examples taken from the literature are used to evaluate the performance of the proposed approach.
Conflicts are likely to arise among participants in a collaborative design process as the inevitable outgrowth of the differing perspectives and viewpoints involved. The opportunities for conflict are magnified if many perspectives are brought to bear on a common artifact early in the design process, as in concurrent engineering or integrated engineering. Design advice tools can assist in the process of resolving these conflicts by making critiques and suggestions conveniently available to design participants, and by offering a fair means of evaluating and comparing suggested alternatives for compromise solution. In previous work [Bahler et al. 1994a, Bahler et al. 1994b] we introduced a protocol based on notions of economic utility by which design advice systems can recognize conflict and mediate negotiation fairly. This protocol allowed design teams to express the desire to maximize or minimize the values of design parameters over totally-ordered bounded domains of values, such as real numeric intervals. In this paper we extend this approach by allowing expressed preferences of design teams to be qualitative as well as quantitative, by allowing teams to express interest in parameters before they actually come into existence, and by relaxing many other of the earlier restrictions on the ways teams may express their preferences.
This paper 1 presents a precise market model for a well-defined class of distributed configuration design problems. Given a design problem, the model defines a computational economy to allocate basic resources to agents participating in the design. The result of running these "design economies" constitutes the market solution to the original problem. After defining the configuration design framework, I describe the mapping to computational economies and our results to date. For some simple examples, the system can produce good designs relatively quickly. However, analysis shows that the design economies are not guaranteed to find optimal designs, and we identify and discuss some of the major pitfalls. Despite known shortcomings and limited explorations thus far, the market model offers a useful conceptual viewpoint for analyzing distributed design problems. Introduction With advances in network technology and infrastructure, opportunities for the decentralization of...
With increased pressures coming from global competition and requirements for greater innovation in product development, designers are hard pressed to deliver designs of higher quality and variety using a repertoire of technological options from different disciplines. This interdisciplinary product development approach has not only removed many of the traditional constraints to design but has now given designers a much wider freedom of choice as to the best solution to a design problem. The focus of this paper is a knowledge-based design environment called Schemebuilder which is a comprehensive and integrated suite of software tools aimed at supporting the designer in the rapid development of product design models in the conceptual, through embodiment stages of design. Illustrated is the use of the software tools in the qualitative generation of alternative schemes, by application of stored working and decomposition principles in the development of a function-means tree-like information structure. With mechatronic product development as the main theme, this paper describes a closely integrated methodology that incorporates a bond graph approach to continuous-time energetic systems and high level Petri nets for the rigorous description of discrete-time information systems. Additionally, a technique is suggested for the decomposition of free format statements of need into the rigorously-defined design context and required functions which form the starting point of the function-means development process. Keywords: Conceptual design, Interdisciplinary system design, First principles, Computer support, Mechatronics. 1.
This paper focusses on how conflicts that arise during a design process and the management of conflicts can be modelled. A number of possible conflict types are distinguished and it is described how each of them can be detected during the design process, using an explicit meta-representation. Furthermore, it is shown how these conflict types can be analyzed and managed by means of strategic meta-knowledge about design processes
ence to cover more and more ground. Thus, learning is essential for creating powerful intelligent design systems. I distinguish two forms of learning in design: 1 ffl in learning for customization, the goal is to adapt a general system to a specific user, i.e. to provide a more convenient way to integrate his or her knowledge than programming ffl in learning for extending coverage, the goal is to learn new knowledge that extends the range of designs the program is able to produce. Learning for customization One aspect of learning in design is that of customization: a general design system is adapted to the specific needs and preferences of a particular user. As an example, the FAMING system (,) is a program for innovative design of mechanism part shapes. The user can provide cases of earlier devices along with interpretations which indicate the desired functions. Using techniques of qualitative physics, FAMING constructs an explanation that links the structure provided in th
Many of the design systems developed in recent years incorporate some machine learning. The number of such systems already available, and the multitude of design learning opportunities that are slowly being revealed, suggest that the time is ripe to attempt to put these developments into a systematic framework. Consequently, in this paper we present a set of dimensions for machine learning in design research. We hope that it can be used as a guide for comparing existing work, and that it may suggest new directions for future exploration in this area.
One method for making analogies is to access and instantiate abstract domain principles, and one method for acquiring knowledge of abstract principles is to discover them from experience. We view generalization over experiences in the absence of any prior knowledge of the target principle as the task of hypothesis formation, a subtask of discovery. Also, we view the use of the hypothesized principles for analogical design as the task of hypothesis testing, another subtask of discovery. In this paper, we focus on discovery of physical principles by generalization over design experiences in the domain of physical devices. Some important issues in generalization from experiences are what to generalize from an experience, how far to generalize, and what methods to use. We represent a reasoner's comprehension of specific designs in the form of structure-behavior-function (SBF) models. An SBF model provides a functional and causal explanation of the working of a device. We represe...
A temporal logic for representing and reasoning on a robotic domain is presented. Actions are represented by describing what is true while the action itself is occurring, and plans are constructed by temporally relating actions and world states. The temporal language is a member of the family of Description Logics, which are characterized by high expressivity combined with good computational properties. The logic is used to organize the domain actions and plans in a taxonomy. The classification and recognition tasks, together with the subsumption task form the basis for action management. An action/plan description can be automatically classified into a taxonomy; an action/plan instance can be recognized to take place at a certain moment from the observation of what is happening in the world during a time interval.
We applied inductive learning to a problem, engineering design optimization, for which the applicability of inductive learning is not immediately obvious. In this paper we describe how we were able to formulate two pieces of the optimization problem as inductive learning problems, and we describe some of the lessons that we learned in the process. Keywords engineering, design, decision tree induction, numerical optimization. 1 Introduction The High-Performance Computing and Design (HPCD) project has attempted to apply various advanced computing technologies to the design of complex engineering artifacts[HPCD, 1995]. As part of this project, we are exploring the application of inductive learning to numerical optimization of complex engineering artifacts. It was not immediately obvious that inductive learning would be applicable to this problem. The problem with which we were faced -- to produce a good design for a given goal -- did not easily fit into the set of classification-type p...
This paper focusses on that form of learning which relates to exploration, rather than generalization. It uses the notion of exploration as the modification of state spaces within which search and decision making occur. It demonstrates that the genetic algorithm formalism provides a computational construct to carry out this learning. The process is exemplified using a shape grammar for a beam section. A new shape grammar is learned which produces a new state space for the problem. This new state space has improved characteristics. 1 Introduction Design can be considered a purposeful, constrained, decision making, exploration and learning activity. Decision making implies a set of variables, the values of which have to be decided. Search is the common process used in decision making. Exploration here is akin to changing the problem spaces within which decision making occurs. Learning implies a restructuring of knowledge as opposed to restructuring of facts. Searching in design ...
In this paper we describe a method for improving genetic-algorithm-based optimization using search control. The idea is to utilize the sequence of points explored during a search to guide further exploration. The proposed method is particularly suitable for continuous spaces with expensive evaluation functions, such as arise in engineering design. Empirical results in several engineering design domains demonstrate that the proposed method can significantly improve the e#ciency and reliability of the GA optimizer. Keywords: genetic algorithms, design optimization, machine learning To appear in Artificial Intelligence in Engineering, Design, Analysis and Manufacturing 1 Introduction Genetic Algorithms (GAs) [ Goldberg 1989 ] are search algorithms that simulate the process of natural selection. GAs attempt to find a good solution to some problem (e.g., finding the maximum of a function) by randomly generating a collection ("population ") of potential solutions ("individuals") to t...
Gradient-based numerical optimization of complex engineering designs offers the promise of rapidly producing better designs. However, such methods generally assume that the objective function and constraint functions are continuous, smooth, and defined everywhere. Unfortunately, realistic simulators tend to violate these assumptions. We present a rule-based technique for intelligently computing gradients in the presence of such pathologies in the simulators, and show how this gradient computation method can be used as part of a gradient-based numerical optimization system. We tested the resulting system in the domain of conceptual design of supersonic transport aircraft, and found that using rule-based gradients can decrease the cost of design space search by one or more orders of magnitude. Keywords: Optimization, gradients, sequential quadratic programming, rule-based systems. 1 Introduction Automated search of a space of candidate designs seems an attractive way to improv...
The status of research methodology employed by studies on the application of AI techniques to solving problems in engineering design, analysis, and manufacturing is poor. There may be many reasons for this status including: unfortunate heritage from AI, poor educational system, and researchers' sloppiness. Understanding this status is a prerequisite for improvement. The study of research methodology can promote such understanding, but most importantly, it can assist in improving the situation. This paper introduces concepts from the philosophy of science and builds on them models of worldviews of science. These worldviews are combined with a research heuristics or research perspectives and criteria for evaluating research to create a layered model of research methodology. This layerd model can serve to organize and facilitate a better understanding of future studies of research methodologies. The paper discusses many of the issues involved in the study of AI and AIEDAM research methodo...
It is generally known that architectural practice relies heavily on the interactions between architects and other professionals. However, during their formal education, most students attending architecture schools, and engineering schools for that mat, get very little (if any) exposure to decision making in conditions that involve expertise and/or worldviews beyond thoseter, reflected and valued by their own discipline. In the past 10 years, a project-based learning initiative was developed between the University of California, Berkeley, and Stanford University in an international context involving several other universities around the world. Throughout this experience, we have identified several issues that have shown to be crucial to these interactions. This paper elaborates on three key issues: improvement of communication skills, empowerment through developing strategies of leadership, and recognition of own and others' worldviews. We also make the case to include experiential educational situations that can introduce these aspects into the academic curricula of architecture and engineering schools.
In 1997, in a farewell message in Volume 11, Issue 1, of AI EDAM I recounted how the journal came to be established in 1987 and how I became the Founding Editor. At that point I was handing over the reigns to a new Editor, Bill Birmingham. Five years later, Bill turned the enterprise over to our current Editor, Dave Brown. Now, a total of 20 years has passed. Twenty years, a goodly length of time in our current world. How have we done?
In this paper, the design of geometrical shapes of function carriers and their layout in given space is called configuration design. The constraint satisfaction problem in configuration design may be difficult to solve due to the lack of tight constraints and the countless combinations of the layout; a diversity of solutions that satisfy the constraints should be allowed. Therefore, to allow such diversity, we directed our attention to developmental processes in biology and proposed an adaptive-growth-type 3D representation based on evolutionary algorithms. Here, the adaptive-growth-type means the shape expressed in the process, which develops through interaction with an outside environment, like shape generation of a living organism in the natural world. The usefulness of the representation was verified by applying it to the component layout problem in the early stage of satellite design.
Spatial grammars are rule based, generative systems for the specification of formal languages. Set and shape grammar formulations of spatial grammars enable the definition of spatial design languages and the creation of alternative designs. Since the introduction of the underlying formalism, they have been successfully applied to different domains including visual arts, architecture, and engineering. Although many spatial grammars exist on paper, only a few, limited spatial grammar systems have been computationally implemented to date; this is especially true for three-dimensional (3-D) systems. Most spatial grammars are hard-coded, that is, once implemented, the vocabulary and rules cannot be changed without reprogramming. This article presents a new approach and prototype implementation for a 3-D spatial grammar interpreter that enables interactive, visual development and application of grammar rules. The method is based on a set grammar that uses a set of parameterized primitives and includes the definition of nonparametric and parametric rules, as well as their automatic application. A method for the automatic matching of the left hand side of a rule in a current working shape, including defining parametric relations, is outlined. A prototype implementation is presented and used to illustrate the approach through three examples: the “kindergarten grammar,” vehicle wheel rims, and cylinder cooling fins. This approach puts the creation and use of 3-D spatial grammars on a more general level and supports designers with facilitated definition and application of their own rules in a familiar computer-aided design environment without requiring programming.
In order to respond to the difficulties encountered by CAD software applications in really assisting the conceptual designer, we propose a tool that is capable of interpreting design sketches and feeding data to various project evaluators, right from the early phases in the design process. For that purpose, we use the concept of the absent interface, which is the only interface that is compatible with the cognitive process involved in sketching. In this paper, we present the principles of such an interface, illustrated by EsQUIsE, a software prototype for capturing and interpreting architectural sketches, which has been under development for several years.
Conceptual innovation in mechanical engineering design has been extremely challenging compared to the wide applications of automated design systems in digital circuits. This paper presents an automated methodology for open-ended synthesis of mechanical vibration absorbers based on genetic programming and bond graphs. It is shown that our automated design system can automatically evolve passive vibration absorbers that have performance equal to or better than the standard passive vibration absorbers invented in 1911. A variety of other vibration absorbers with competitive performance are also evolved automatically using a desktop PC in less than 10 h.
This paper claims that style, in addition to being identified by common visible physical characteristics of form, can be thought of in terms of a set of common abstract characteristics. A prototype computational design support tool is described that explores this idea in the domain of architecture. The Architect's Collaborator (TAC) supports articulation and evaluation of abstract characteristics of style (e.g., experiential characteristics such as privacy and shelter) and does so by mapping abstract characteristics to details of physical form. The implementation of TAC is described and successful experiments are reported in which abstract characteristics of Frank Lloyd Wright's Prairie houses were mapped to physical form characteristics and used to evaluate Prairie and non-Prairie houses.
Fixation prevents the associations that are bridges to new designs. The inability to see alternative solutions, or even to see how to map known solutions onto current problems, is a particularly acute problem in the design of software-intensive systems. Here, we explored two related ways of liberating fixated thinking: abstracting and rerepresenting. Although both techniques helped designers generate original ideas, not all the added ideas fit the problem constraints. We discuss ways the results might be used to generate reflective design aids that help designers to first generate original ideas and later prune them.
Abstraction and generalization of layout design cases generate new knowledge that is more widely applicable to use than specific design cases. The abstraction and generalization of design cases into hierarchical levels of abstractions provide the designer with the flexibility to apply any level of abstract and generalized knowledge for a new layout design problem. Existing case-based layout learning (CBLL) systems abstract and generalize cases into single levels of abstractions, but not into a hierarchy. In this paper, we propose a new approach, termed customizedviewpointS), which supports the generalization and abstraction of spatial layouts into hierarchies along with a supporting system, SPIDA (SPatial Intelligent Design Assistant).
The growing movement of biologically inspired design is driven in part by the need for sustainable development and in part by the recognition that nature could be a source of innovation. Biologically inspired design by definition entails cross-domain analogies from biological systems to problems in engineering and other design domains. However, the practice of biologically inspired design at present typically is ad hoc, with little systemization of either biological knowledge for the purposes of engineering design or the processes of transferring knowledge of biological designs to engineering problems. In this paper we present an intricate episode of biologically inspired engineering design that unfolded over an extended period of time. We then analyze our observations in terms of why, what, how, and when questions of analogy. This analysis contributes toward a content theory of creative analogies in the context of biologically inspired design.
Language plays at least two roles in design. First, language serves as representations of ideas and concepts through linguistic behaviors that represent the structure of thought during the design process. Second, language also performs actions and creates states of affairs. Based on these two perspectives on language use in design, we apply the computational linguistics tools of latent semantic analysis and lexical chain analysis to characterize how design teams engage in concept formation as the accumulation of knowledge represented by lexicalized concepts. The accumulation is described in a data structure comprised by a set of links between elemental lexicalized concepts. The folding together of these two perspectives on language use in design with the information processing theories of the mind afforded by the computational linguistics tools applied creates a new means to evaluate concept formation in design teams. The method suggests that analysis at a linguistic level can characterize concept formation even where process-oriented critiques were limited in their ability to uncover a formal design method that could explain the phenomenon.
When engineering content is created and applied during the product life cycle, it is often stored and forgotten. Current information retrieval approaches based on statistical methods and keyword matching are not effective in understanding the context of engineering content. They are not designed to be directly applicable to the engineering domain. Therefore, engineers have very limited means to harness and reuse past designs. The overall objective of our research is to develop an engineering ontology (EO)-based computational framework to structure unstructured engineering documents and achieve more effective information retrieval. This paper focuses on the method and process to acquire and validate the EO. The main contributions include a new, systematic, and more structured ontology development method assisted by a semiautomatic acquisition tool. This tool is integrated with Protegeontology editing environment; an engineering lexicon (EL) that represents the associated lexical knowledge of the EO to bridge the gap between the concept space of the ontology and the word space of engineering documents and queries; the first large-scale EO and EL acquired from established knowledge resources for engineering information retrieval; and a comprehensive validation strategy and its implementations to justify the quality of the acquired EO. A search system based on the EO and EL has been developed and tested. The retrieval performance test further justifies the effectiveness of the EO and EL as well as the ontology development method.
This paper presents a novel approach, which is based on integrated (automatic/interactive) knowledge acquisition, to rapidly develop knowledge-based systems. Linguistic rules compatible with heuristic expert knowledge are used to construct the knowledge base. A fuzzy inference mechanism is used to query the knowledge base for problem solving. Compared with the traditional interview-based knowledge acquisition, our approach is more flexible and requires a shorter development cycle. The traditional approach requires several rounds of interviews (both structured and unstructured). However, our method involves an optional initial interview, followed by data collection, automatic rule generation, and an optional final interview/rule verification process. The effectiveness of our approach is demonstrated through a benchmark case study and a real-life manufacturing application.
Engineering design reviews, which take place at predetermined phases of the product development process, are fundamental elements for the evaluation and control of engineering activities. These meetings are also acknowledged as unique opportunities for all the parties involved to share information about the product and related engineering processes. For product development teams, the knowledge generated during a design review is not as secondary as it may seem; key design decisions, design experiences, and associated rationale are frequently made explicit. Useful work has been carried out on the design review process itself, but little work has been undertaken about the detailed content of the meeting activity; it is argued that understanding the transactions that take place during a meeting is critical to building an effective knowledge-oriented recording strategy. To this effect, an extensive research program based on case studies in the aerospace engineering domain has been carried out. The work reported in this paper focuses on a set of tools and methods developed to characterize and analyze in depth the transactions observed during a number of case studies. The first methodology developed, the transcript coding scheme, uses an intelligent segmentation of meeting discourse transcriptions. The second approach, which bypasses the time consuming transcribing operation, is based on a meeting capture template developed to enable a meeting observer to record the transactions as the meeting takes place. A third method, the information mapping technique, has also been developed to interpret the case study data in terms of decisions, actions, rationale, and lessons learned, effectively generating qualitative measures of the information lost in the formal records of design reviews. Overall, the results generated by the set of tools presented in this paper have fostered a practical strategy for the knowledge intensive capture of the contents of design reviews. The concluding remarks also discuss possible enhancements to the meeting analysis tools presented in this paper and future work aimed at the development of a computer supported capture software for design reviews.
As manufacturing systems become more sophisticated and complicated, effective managers know how they play a crucial role in managing an enterprise and managers know how to deal with their dynamics and uncertainty. In this article, a formalism based on the computer-integrated manufacturing open-system architecture (CIMOSA) reference model is presented to specify the business processes and enterprise activities at the knowledge level. The formalism uses an integration of multiple types of knowledge, including precise, muddy, and random symbolic and numerical knowledge to systematically represent enterprise behavior and functionality. To support the modelling process, a prototype is developed and an example for a maintenance activity is presented to demonstrate the effectiveness of the proposed method.
Architects use sketching and diagramming in their design process to perform functional reasoning, formal arrangements, analogy transfer, structure mapping, and knowledge acquisition. This paper describes a research framework of the author's efforts in the studies of design drawings and the building of computational sketching tools to support the early conceptual design process in architecture. The first part of the paper discusses empirical studies conducted to determine or guess a designer's thought process from sketches and thus identifies domain-specific graphical symbols. It proposes a reasoning process framework of drawing marks, acts, and reacts. The second part of the paper illustrates how design support tools could be developed based on these concepts and describes the various applications of the study, such as indexing and retrieving of design drawings or images based on the recognition of geometric shapes and the spatial relationships among them.
Adaptation of design cases is usually the most challenging part in building any case-based reasoning design system. The success of the adaptation process in finding a solution for a new design problem determines the success of the entire case-based reasoning (CBR) system. The techniques used for generating design solutions have many common aspects among the various engineering design classes that make them amenable to be captured in a generic framework for an acceptable level of abstraction. This paper proposes a design-plan-oriented methodology for adapting design cases to produce a solution to a new design problem in the domain of engineering design. The proposed methodology uses multicase adaptation and case built-in adaptation knowledge to produce a design plan for a new design problem. We first define the model of case representation to work with the proposed methodology. We then define the overall structure of the procedural framework of this methodology and its subprocesses. The system is then demonstrated through an application from the structural engineering domain.
Ontologies are an emerging means of knowledge representation to improve information organization and management, and they are becoming more prevalent in the domain of engineering design. The task of creating new ontologies manually is not only tedious and cumbersome but also time consuming and expensive. Research aimed at addressing these problems in creating ontologies has investigated methods of automating ontology reuse mainly by extracting smaller application ontologies from larger, more general purpose ontologies. Motivated by the wide variety of existing learning algorithms, this paper describes a new approach focused on the reuse of domain-specific ontologies. The approach integrates existing software tools for natural language processing with new algorithms for pruning concepts not relevant to the new domain and extending the pruned ontology by adding relevant concepts. The approach is assessed experimentally by automatically adapting a design rationale ontology for the software engineering domain to a new one for the related domain of engineering design. The experiment produced an ontology that exhibits comparable quality to previous attempts to automate ontology creation as measured by standard content performance metrics such as coverage, accuracy, precision, and recall. However, further analysis of the ontology suggests that the automated approach should be augmented with recommendations presented to a domain expert who monitors the pruning and extending processes in order to improve the structure of the ontology.