The concept of discretization of a design space is used to make initial selection of prior designs using specification matching, and to direct redesign with evaluation and iteration. A general paradigm for routine design has been developed and implemented in a system called IDS (Initial Design Selection.) For a given design domain, certain characteristics are identified that allow all specifications and models (which represent prior designs) in that design domain to be described in terms of their values or intervals that these values may lie in. These characteristics are seen as dimensions of a design space discretized into a finite number of partitions. Each partition is represented by a model, thought of as occupying its center. Each such model is associated with a deep model, which contains sufficient information for the modeled device, process, or system to be realized. Despite the fact that the models inhabiting the space are shallow, the paradigm comprises a relatively rich mathematical structure. This paper describes in detail a computational methodology to implement this domain-independent paradigm. The IDS paradigm presents a convenient and structured framework for acquiring and representing domain knowledge. This paper also briefly discusses an enhanced version of the system, which attempts iterative redesign directed by the particular mismatch between a specification and an otherwise promising model. To date, this methodology has been applied in a variety of design domains, including mechanism design, hydraulic component selection, assembly methods, and non-destructive testing methods.

The coordination of intelligent, interacting, agents is rapidly gaining importance as such systems are deployed under diverse conditions. When robots are used in teams rather than as individuals, their coordination can become more critical for system performance than their individual capabilities. The deployment strategies and communication modes play an important role in the coordination of these teams.

This paper examines a Game Theoretic deployment approach to robotic teams in an unstructured environment. A simulation model is developed and used to compare the performance of gaming rules with a non-anticipatory deterministic deployment rule. The initial Game Theoretic rule can be enhanced to exhibit both locally and globally adaptive characteristics. The new rule outperforms both the deterministic algorithm and the straightforward game-theoretic rule. This is achieved by adapting to trends in local regions in the environment as well as anticipating global eventualities.

The process of reviewing test data for anomalies after a firing of the Space Shuttle Main Engine (SSME) is a complex, time-consuming task. A project is under way to provide the team of SSME experts with a knowledge-based system to assist in the review and diagnosis task. A model-based approach was chosen because it can be adapted to changes in engine design, is easier to maintain, and can be explained more easily. A complex thermodynamic fluid system like the SSME introduces problems during modeling, analysis, and diagnosis which have as yet been insufficiently studied. We developed a qualitative constraint-based diagnostic system inspired by existing qualitative modeling and constraint-based reasoning methods which addresses these difficulties explicitly. Our approach combines various diagnostic paradigms seamlessly, such as the model-based and heuristic association-based paradigms, in order to better approximate the reasoning process of the domain experts. The end-user interface allows expert users to actively participate in the reasoning process, both by adding their own expertise and by guiding the diagnostic search performed by the system.

A framework IPD (Iterative Parametric Design) is proposed to assist the iterative parametric mechanical design process. To effectively find a set of satisfiable values for the design parameters the key is to find good heuristics to adjust or tune the parametric values resulting from previous design iterations. We propose that heuristics can come from two aspects by both qualitative and quantitative reasoning. Qualitative reasoning, based on confluences, provides global control over the feasible directions of variable adjustments, while quantitative reasoning, based on the dependency network and perturbation analysis, can be used to propose actual quantity of local variable adjustments. We used the design of a helical compression spring as an example to illustrate the performance of IPD system. We show that IPD can often find a solution faster than those without guidance of qualitative and quantitative reasoning.

Inspection planning is a process of reasoning about inspection activities. As a result, a sequence of inspection actions is formulated, which, when performed, will achieve the desired measurements. In manufacturing, automated inspection technologies, such as Computer-Aided Inspection (CAI) or Co-ordinate Measuring Machines (CMMs), will be facilitated by inspection planning. Inspection planning involves the following four aspects: representation of inspection features; process formalization; modeling of inspection activities; and, finally, plan synthesis. This paper discusses an approach to knowledge-based inspection planning. Accordingly, a prototype inspection planning system has been developed, which is also described in this paper.

SightPlan refers to several knowledge-based systems that address construction site layout. Five different versions were implemented and their components of expertise are described here. These systems are alterations of one another, differing either in the problems they solve, the problem-solving methods they apply, or the tasks they address. Because they share either control knowledge, domain concepts, or heuristics, and such knowledge is implemented in well-defined modular knowledge bases, these systems could easily re-use parts of one another. Experiments like those presented here may clarify the role played by different types of knowledge during problem solving, enabling researchers to gain a broader understanding of the generality of the domain and task knowledge that is embedded in KBSs and of the power of their systems.

In wood engineering design, an important task is the derivation of a construct from site specific data. Human experts perform the task in two phases, first qualitatively and then quantitatively in a hierarchical fashion. COWEN (Computer Wood ENgineer) is a fully implemented research prototype expert system that performs the qualitative phase and makes two contributions to the technology of expert systems. The first contribution is a Knowledge Level specification of the task prior to considering Symbol Level implementation. This is important because expert systems have been defined as mostly symbolic processors in the literature. The second contribution is that this Knowledge Level specification has led to the conclusion that additional qualitative sciences, besides physics and geometry, are needed for an engineering task. This is an interesting discovery because qualitative reasoning research in Artificial Intelligence (AI) has approached engineering design from the viewpoints of physics and geometry only.

An approach to CAD and CAM modeling and to the design of CAD/CAM systems is presented. Models of the product and of the process are represented by logical assertions in a common logical language. CAD/CAM functions are represented by the application of logical inference rules, which correspond to the derivation of new information as well as to actions. This allows all the different kinds of model and specification used in design and manufacturing to be represented in a computer in a common form. It therefore allows the representation of constraints and rules connecting any aspects of design and manufacturing together.

This approach has all the advantages of formal specifiction, namely, ease of expression, communication, standardization and abstraction. At the same time, we demonstrate its practical implementation in an efficient form, and which is industry compatible, and we report practical experience with using this approach for CAD/CAM models and for intelligent CAD/CAM functions.

Fixtures are used in almost all manufacturing operations. They take on many different forms, ranging from simple mechanical vises to modular fixtures to specialized fixtures. For cylindrical parts or simple prismatic parts, automatic design of fixtures is feasible. However, for parts of irregular shape such as castings or forged parts, the automation of fixture design is a complex problem. In this paper we address the problem of fixture layout for parts of complicated shape. Issues related to automatic design such as completeness, soundness, and computing efficiency are first discussed. A theoretical framework based on algebraic formulations is developed which models human reasoning employed for workpiece restraint. These formulations will ensure the completeness and soundness of the design methodology. They also provide a mechanism for constraint propagation in the design space. Finally, the generality of the framework is discussed.

Currently design documentation rarely records the designer's decision process or the reasons behind those decisions. This paper describes an effort to improve design documentation by having the computer act as an intelligent apprentice to the designer to capture the rationale during the design process. The apprentice learns about the features that make a specific case different from the standard. Whenever the designer proposes a design action that differs from the apprentice's expectations, the interface will ask for the designer for justifications to explain the differences. Later queries for design rationale are answered using a combination of the apprentice's domain knowledge and the designer-supplied justifications. The apprentice model is being implemented in a prototype system called ADD (Augmenting Design Documentation). The initial focus of the work is on HVAC (Heating, Ventilation, and Air Conditioning) design. Our starting point for implementing the apprentice model is observing how people develop HVAC system designs and then explain those designs.

Process planning is the function that converts an engineering design into a manufacturing plan. One of the problems in feature-based process planning is the sequencing of features. Features must be given an order for removal. This order, or sequence, is partially dependent on the geometric relationships between the features. If the geometric relationships between features are such that they dictate a particular sequence, the features are said to have an interaction. Identifying these interactions is an important first step in creating the process plan. An approach to solve this problem using constructive solid geometry operations and the Episodal Associative Memory (EAM) is demonstrated. The EAM is an associative memory that integrates dynamic memory organization and neural computing techniques. The geometric feature relationships can be represented by a pattern. This pattern captures very qualitative information about the geometric positions fo the features. The EAM can organize these patterns into groups of similar geometric relationships. A method for dealing with exceptions, and for retrieving and storing general machining problems associated with interacting features will be described. The system implemented is shown to correctly sequence several types of feature interactions.

This paper presents a knowledge-based problem solving environment for numerical simulation of problems described by partial differential equations (PDEs). The system aims to facilitate the simulation requirements of different user groups that include engineers, mathematicians and numerical analysts. To attain this objective, a flexible multi-perspective modelling environment is proposed which incorporates three natural modelling platforms, namely; a physical model, a mathematical model and a numerical model. The modelling environment is integrated with a sophisticated numerical solver. We believe that combination of an open modelling system with a basic numerical simulator provides a powerful problem solving environment capable of meeting the needs of these different user groups. The overall system architecture is based on automatic transformation using mathematical and numerical knowledge bases between the three identified models. The knowledge bases are organized in a frame based manner to reflect the hierarchical nature of the knowledge in PDEs and numerical algorithms. The object oriented paradigm is used to bind local rule bases to each frame and for implementing a global inference mechanism which works over the hierarchical knowledge structures. Evaluation of the modelling environment has indicated that engineers can tackle PDE based engineering problems without the necessity for detailed knowledge of mathematics or numerical techniques and mathematicians can examine the mathematical properties of PDEs without the requirement of numerical expertise.