Less than a decade ago it seemed that a new paradigm of engineering–called computer-aided engineering (CAE) – was emerging. This emergence was driven in part by the success of computer support for the tasks of engineering analysis and in part by a new understanding of how computational ideas largely rooted in artificial intelligence (AI) could perhaps improve the practice of engineering, especially in the area of design synthesis. However, while this “revolution” has failed to take root or flourish as a separate discipline, it has spawned research that is very different from traditional engineering research. To the extent that such CAE research is different in style and paradigm, it must also be evaluated according to different metrics. Some of the metrics that can be used are suggested, and some of the evaluation issues that remain as open questions are pointed out.

An MPR is a deep model of a manufacturing process. It is claimed to be easier to acquire than experiential diagnostic rules, and the acquisition of an MPR can be done either by a knowledge engineer or an intelligent interrogator program. An MPR can be used for simulating processes, for centralized or distributed model-based diagnosis of problems with processes, for designing the processes themselves, for determining the need for quality control testing and sensor checks, for determining when knowledge about the process is incomplete and additional knowledge needs to be acquired, and for compiling diagnostic rules.

Research efforts to implement a Bayesian belief-network-based expert system to solve a real-world diagnostic problem – the diagnosis of integrated circuit (IC) testing machines – are described. The development of several models of the IC tester diagnostic problem in belief networks also is described, the implementation of one of these models using symbolic probabilistic inference (SPI) is outlined, and the difficulties and advantages encountered are discussed. It was observed that modeling with interdependencies in belief networks simplifies the knowledge engineering task for the IC tester diagnosis problem, by avoiding procedural knowledge and focusing on the diagnostic component’s interdependencies. Several general model frameworks evolved through knowledge engineering to capture diagnostic expertise that facilitated expanding and modifying the networks. However, model implementation was restricted to a small portion of the modeling, that of contact resistance failures, which were due to time limitations and inefficiencies in the prototype inference software we used. Further research is recommended to refine existing methods, in order to speed evaluation of the models created in this research. With this accomplished, a more complete diagnosis can be achieved.

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

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 represent domain principles as device-independent behavior-function (BF) models. We show that (1) the function of a device determines what to generalize from its SBF model, (2) the SBF model itself suggests how far to generalize, and (3) the typology of functions indicates what method to use.

In this abstract, we discuss the use of learning techniques to improve performance and solution quality in multiagent parametric design. We have implemented the L-TEAM testbed for empirical evaluation of two forms of learning (described in detail below):

We are interested in investigating the different types of knowledge and mechanisms that cause design problem-solving to become routine. We use the model of Routine Parametric Design incorporated in the language DSPL (Brown & Chandrasekaran, 1989), where both the parameters to be given values and the design knowledge needed are known in advance.

Artificial Intelligence has been very active in developing high-level symbolic reasoning paradigms that have resulted in practical expert systems. However, with a few exceptions, it has paid little attention to the automation of spatial reasoning. On the other hand, spatial reasoning has attracted the interest of several researchers in Robotics. One of the important problems that have been investigated is motion planning, and very significant results have been obtained. This paper describes an implemented system for designing pipe layouts automatically using motion planning techniques. It introduces a new approach to pipe layout design automation in which pipe routes are treated as trajectories left behind by rigid objects (‘robots’). We have implemented this approach in a basic Pipe Router that is described in detail in this paper. We have extended this router in order to make it capable of treating a variety of other constraints which are typical of practical pipe layout design problems. These constraints relate to the process carried out in the pipes, to the design of their mechanical support, and to the constructability and the ease of operation and maintenance of the designed pipe systems.

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.

The ability to reason spatially is an important skill required for engineers, particularly in engineering design and construction. One aspect of spatial reasoning is visualizing and constructing three-dimensional (3D) solid objects from two-dimensional (2D) projections. To assist in teaching this to engineering students, an instructional software system is being developed at the University of Illinois. This instructional software system is comprised of the Visual Sweeper and the Visual Teacher. The Visual Sweeper is a geometric framework for solving missing view problems. In missing view problems, students create 3D solid objects from two 2D projections by applying operations inverse to orthographic projection. The Visual Teacher, which is the focus of this article, is an intelligent critiquing and tutoring module that gives feedback to the student regarding partial solutions to missing view problems. The Visual Teacher is comprised of a Recognizer and a Critiquer. The Recognizer identifies which solution solid the student's partial solution is closest to. Based on the solution solid and a student's partial solution, the Criti-quer gives critique and advice to the student. The Recognizer is based on an algorithm for bipartite graph matching, while the Critiquer uses a rule-based approach. This paper describes the Visual Teacher, gives examples of how it can be used, presents preliminary evaluation results, and discusses the system's assumptions and limitations.

The Explorer parametric design assistant, an interactive tool that provides intelligent support for searching concurrent-engineering trade-spaces under multiple, conflicting objectives, is described. The system provides a convenient means for specifying multiple, cross-disciplinary constraints in terms of tables, formulas, and logical sentences. Based on these data, the system performs interactive constraint checking, computes feasible designs, and provides graphical analysis facilities, allowing users to compare designs based on multiple criteria. As a first application, Explorer has been used as a printed circuit board (PCB) construction design assistant. In initial tests, Explorer has helped users to find design configurations not previously considered that yield comparable performance and cost while offering better manufacturability and reliability. The capabilities and use of the Explorer system are described in detail, the underlying technologies are outlined, and an evaluation of the prototype system is presented.

In an effort to learn more about how testers test code, we observed several testers while they designed tests to check a change which had been made to code. Using a case study methodology, we gathered empirical data from the ‘real world’—professional testers, and actual software products. We found that testers do share some common work patterns. These patterns can be seen in their information gathering, their use of heuristics and their construction of mental models. This work is extremely knowledge intensive, experience appears to have a useful effect. In this paper we will discuss how we collected and analysed our data. Then we will present some of our observations about how the testers gathered information, used heuristics, formed mental models and were affected by their previous experience in the course of designing their test scenarios. Based on these observations we comment on training and tools for testers.

Artificial neural networks are finding wide application to a variety of problems in civil engineering. This paper describes how artificial neural networks can be applied in the area of construction project control. A project control system capable of predicting and monitoring project performance (e.g., cost variance and schedule variance) based on observations made from the project environment is described. This project control system has five neural network modules that allow a project manager to automatically generate revised project plans at regular intervals during the progress of the project. These five modules are similar in design and implementation. Therefore, this paper will present the main issues involved in the development of one of these five neural network modules, that is, the module for identifying schedule variance. A description of a graphical user interface integrating the neural network modules developed with project management software, and a discussion on the power and limitations of the overall system conclude the paper.