This paper discusses the framework of a knowledge-based expert system 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. Illustrative examples of the advisor in designing airframe structures are also included.

According to both cybernetics and general system theory, a subject develops and uses an adequate model of a system to widen his/her knowledge about the system. Models are then the interface between a subject and a real-world system to solve a problem and to construct knowledge. Hence, evaluating these models is crucial to ensure the quality of the constructed knowledge. We propose here an evaluation framework to assess complex models based on the intrinsic properties of these models as well as the properties of the derived knowledge. A series of 40 evaluation criteria are proposed under the four systemic axes: ontology, functioning, evolution, and teleology. Through a case study, we show how our evaluation model allows both presenting a given model and assessing it.

A critical problem with existing computer-based geometric modeling is the labor intensive task involved in specifying data input for the description of three-dimensional (3-D) objects. This paper describes a new, 3-D input system aimed at alleviating this problem. It is based on the use of a three-dimensional digitizer for the direct input of spatial coordinates, and an intelligent interactive user interface. The intent of this system is to create a high level, intelligent interface between the designer and a geometric solid modeler which would lighten the designer's burden in performing arduous 3-D geometric description tasks. The user interface is developed around the Knowledge Craft expert system building tool, using the rule-based Carnegie Representation Language OPS5 (CRL-OPS). The system uses schematic networks or frames and production rules to encode knowledge about geometric primitive digitization methods, object feature operators, solid modeler requirements, and input command functions. It also employs a forward-chaining inference strategy to direct the knowledge. This ensures that only a minimal amount of valid data entry is required by the user. However, if excessive data is entered the intelligent interface has the capability to extract the required information. As a result, the solid modeler can automatically create the appropriate object “primitive” or the specific object “feature” upon recognition by the expert system. It will be demonstrated that these capabilities can simplify the 3-D model description process.

This paper proposes a new method for dealing with geometrical layout constraints. Geometrical layout constraints are classified into three classes of dimensional, regional, and interference constraints. Dimensional constraints are handled by using an existing methodology. A method is proposed to translate the other two classes of constraints into dimensional constraints. Thus, it is possible to uniformly deal with all of those geometrical layout constraints. The method is twofold. First, it converts regional, interference constraints into a set of simple inequalities. Then each inequality is solved by a geometric gadget, which is a structured set of dimensional constraints. A prototype system is developed and applied to some layout design examples.

When developing a better understanding of the design process there are several possible approaches to choose from. Many studies are based on novice designers (e.g., students) or designers of relatively modest talents. By contrast, some studies have queried designers who are considered to have outstanding and exceptional ability in order to gain an understanding of design at the highest level that it is practiced. The study reported here adopts yet another approach by exploring how design processes are perceived by design educators. The approach is motivated by the observation that teaching design requires consciously distilling the essence of the design process for the students, observing students during their design process and guiding them through the process. As a result, design teachers tend to develop a more articulate view of design processes than most other designers. Nineteen design teachers are interviewed using general topics as discussion points. Such an approach is invaluable when exploring more abstract research questions such as the notion of design processes. This approach differs from more controlled approaches (e.g., protocol analysis) in that it accepts that the data obtained are partially driven by negotiation between the researchers and the participants, and that the discussions are largely stories or narratives about design and designing. The resulting data illustrate that design processes are interpreted, articulated, and understood in a variety of ways by different teachers. These data and subsequent results tell us in rich detail about designing and design teaching, and as a result extend our understanding of the design process.

The main function of a heavy truck is to transport goods, with ton-kilometers/year as an example of a major quantitative performance measure. Furthermore, the truck is directly operated by a driver, who has several additional functional requirements, of both ergonomic and communicative characters. Failure of these functions may be a subjective experience, differing between drivers, but the failures are still important. Today's just-in-time delivery systems rely on getting the goods on time, and this requires high availability. Availability is reduced not only by technical failures but also by subjectively experienced failures, because these also require repairs, or downtime. Product reliability is a systems property that cannot be attributed to a single component. It is in many cases related to interaction between components, or to interaction between humans and the technical system, in the case of subjectively experienced failures. Reliability assessments of systems with interactive functions require a system model that includes the interfaces between the technical system and human features that are carriers of interactive functions. This paper proposes a model of system architecture, for the purpose of reliability assessments, that integrates different and complementary representations, such as function–means diagrams and a design structure matrix. The novelty of the presented approach is that it treats and integrates the technical and the human subsystems through the human–technical system interfaces. The proposed systems reliability approach is described and verified with a component analysis case study of an extended truck cab and driver system.

A crisis is a complex situation, which actors have some difficulties to manage it. They are under stress to deal with problems that they cannot predict consequences. The human conditions (familial and life) and, the influence of the environment (politic, economic, media) pushes the actors to lose control of the crisis situation. The question we face in this paper is: “is it possible to predict the impact of the stress in this type of situation?” Our main hypothesis to answer is to represent experience feedback using knowledge management. To model the crisis management as systemic system emphasizing regulation loops, and the collaboration activity by showing the dimension of the communication, coordination, and cooperation. This modeling is illustrated in a terrorist attack situation in Algeria. To predict stress consequences, fuzzy set principle is adopted, based on experience feedback and situations modeling, as a generator of alternative states given a stress event.

This paper describes an intelligent alarm processing expert system which is integrated in a large Supervisory Control and Data Acquisition system for power distribution networks. The expert system works as an operator support tool by diagnosing network disturbances and device malfunctions. The expert system is based on a hierarchic, multi-level problem-solving architecture, integrating both model-based and heuristic techniques acting upon an object-oriented data structure. Several enhancements have been designed and implemented to enable the system to perform its task online and real-time. The expert system covers online processing of real-time data and intelligent alarm processing, as well as the automatic creation and update of the knowledge base. It consists of approximately 25000 objects (units) and 190 rules. The system uses the expert system tool KEE, runs on SUN workstations, and is integrated in the Supervisory Control and Data Acquisition system via LAN. The expert system was implemented for the Public Utilities Board Singapore controlling its 22 kV distribution network and has been online since November 1990.

Configuration and parameterization of optimization frameworks for the computational support of design exploration can become an exclusive barrier for the adoption of such systems by engineers. This work addresses the problem of defining the elements that constitute a multiple-objective design optimization problem, that is, design variables, constants, objective functions, and constraint functions. In light of this, contributions are reviewed from the field of evolutionary design optimization with respect to their concrete implementation for design exploration. Machine learning and natural language processing are supposed to facilitate feasible approaches to the support of configuration and parameterization. Hence, the authors further review promising machine learning and natural language processing methods for automatic knowledge elicitation and formalization with respect to their implementation for evolutionary design optimization. These methods come from the fields of product attribute extraction, clustering of design solutions, relationship discovery, computation of objective functions, metamodeling, and design pattern extraction.

The use of local natural and recycled feedstock is promising for sustainable construction. However, unlike versatile engineered bricks, natural and recycled feedstock involves design challenges due to their stochastic, sequential, and heterogeneous nature. For example, the practical use of stone masonry is limited, as it still relies on human experts with holistic domain knowledge to determine the sequential organization of natural stones with different sizes/shapes. Reinforcement learning (RL) is expected to address such design challenges, as it allows artificial intelligence (AI) agents to autonomously learn design policy, that is, identifying the best design decision at each time step. As a proof-of-concept RL framework for design automation involving heterogeneous feedstock, a stone masonry design framework is presented. The proposed framework is founded upon a virtual design environment, MasonTris, inspired by the analogy between stone masonry and Tetris. MasonTris provides a Tetris-like virtual environment combined with a finite element analysis (FEA), where AI agents learn effective design policies without human intervention. Also, a new data collection policy, almost-greedy policy, is designed to address the sparsity of feasible designs for faster/stable learning. As computation bottleneck occurs when parallel agents evaluate designs with different complexities, a modification of the RL framework is proposed that FEA is held until training data are retrieved for training. The feasibility and adaptability of the proposed framework are demonstrated by continuously improving stone masonry design policy in simplified design problems. The framework can be generalizable to different natural and recycled feedstock by incorporating more realistic assumptions, opening opportunities in design automation for sustainability.

Biologically inspired design can be used to aid in conceptual design. Sketching is an important ideation process in conceptual design for recording and evaluating flashing moments of inspiration. The present study aims to provide a framework for exploring the effects of biological examples on the sketching contours of products, as well as the perceptual matching degree between design ideas generated via sketching and the desired functions. Elliptic Fourier descriptors with principal component analysis and perceptual matching were used to evaluate and compare the effects of biological examples, no examples, and human-engineered examples from different product categories and within one product category on the sketches in an experiment that involved 28 participants. The application of elliptic Fourier descriptors with principal component analysis shows that there are significant differences in the third and seventh principal components. It is also found that exposure to biological examples can produce more sketches with high perceptual matching degree than the other three conditions, but there are no significant effects of the example exposure on the Pearson correlation coefficients of semantic differential evaluation value vectors between design problems and sketches. These results demonstrate that exposure to biological examples will correlate with Elliptic Fourier descriptors of sketches and will not significantly increase the perceptual matching degree between sketches and the desired function.

Methodologies have been developed and implemented in LISP and OPS-S languages which address type synthesis of mechanisms. Graph theory and separation of structure from function concepts have been integrated into an expert system called DOMES (Design Of Mechanism by an Expert System) to effectively implement the following three activities: 1. enumeration of all non-isomorphic labelled graphs; 2. identification of those graphs which satisfy structural constraints; 3. sketching of mechanisms corresponding to a given graph.

Developed theories and algorithms are applied to a robot gripper design and a variable-stroke piston engine design. The results from these two applications indicate that the automated techniques effectively identify all previously obtained solutions via manual techniques. Additional solutions are also identified and several errors of the manual process are detected. The developed methodologies and software appear to perform a complete and unbiased search of all possible candidate designs and are not prone to the errors of the manual process. Other important features of DOMES are: 1. it can learn and reason, by analogy, about a new design problem based on its experience of the problems previously solved by the system: 2. it has the capability to incrementally expand its knowledge base of rejection criteria by converting into LISP code information obtained through a query-based interactive session with a human designer; 3. it can select the set of rejection criteria relevant to a design problem from its knowledge base of rejection criteria. These procedures could become a powerful tool for design engineers, especially at the conceptual stage of design.

Although an accurate reliability assessment is essential to build a resilient infrastructure, it usually requires time-consuming computation. To reduce the computational burden, machine learning-based surrogate models have been used extensively to predict the probability of failure for structural designs. Nevertheless, the surrogate model still needs to compute and assess a certain number of training samples to achieve sufficient prediction accuracy. This paper proposes a new surrogate method for reliability analysis called Adaptive Hyperball Kriging Reliability Analysis (AHKRA). The AHKRA method revolves around using a hyperball-based sampling region. The radius of the hyperball represents the precision of reliability analysis. It is iteratively adjusted based on the number of samples required to evaluate the probability of failure with a target coefficient of variation. AHKRA adopts samples in a hyperball instead of an n-sigma rule-based sampling region to avoid the curse of dimensionality. The application of AHKRA in ten mathematical and two practical cases verifies its accuracy, efficiency, and robustness as it outperforms previous Kriging-based methods.

A fillet curve is provided at the root of the spur gear tooth, as stresses are high in this portion. The fillet curve may be a trochoid or an arc of suitable size as specified by designer. The fillet stress is influenced by the fillet geometry as well as the number of teeth, modules, and the pressure angle of the gear. Because the relationship is nonlinear and complex, an artificial neural network and a backpropagation algorithm are used in the present work to predict the fillet stresses. Training data are obtained from finite element simulations that are greatly reduced using Taguchi's design of experiments. Each simulation takes around 30 min. The 4-5-1 network and a sigmoid activation function are chosen. TRAINLM function is used for training the network with a learning rate parameter of 0.01 and a momentum constant of 0.8. The neural network is able to predict the fillet stresses in 0.03 s with reasonable accuracy for spur gears having 25–125 teeth, a 1–5 mm module, a 0.05–0.45 mm fillet radius, and a 15°–25° pressure angle.

The choice of components in industrial design involves setting design parameters that typically must reside inside permissible ranges called “design margins”. This paper proposes a novel automated method called the Margin-Based General Regression Neural Network (MB-GRNN) that classifies design errors for design parameters that are outside of permissible ranges as outliers, directly from industrial design data, using an unsupervised machine learning approach. The method is based on a modified GRNN that estimates extremal margin boundaries of design parameters by self-learning the features from datasets. These extremal permissible margin boundaries are determined by “stretching out” the upper and lower GRNN surfaces using an iterative application of stretch factors (a second kernel weighting factor). The method creates a variable insensitive band surrounding the data cloud, interlinked with the normal regression function, providing upper and lower margin boundaries. These boundaries can then be used to determine outliers and to predict a range of permissible values of design parameters during design. Pushing out extremal margin boundaries reduce the false identification of outliers. This classification technique could be used by industrial engineers to detect likely outliers and to predict a range of permissible output limits for chosen design parameters. The efficacy of this method has been validated against the widespread Parzen window method by comparing experimental results from three multivariate datasets. It was found that the two methods have different but complementary capabilities. The MB-GRNN also uses a modified algorithm for estimating the smoothing parameter using a combination of clustering, k-nearest neighbor, and localized covariance matrix.

Appropriate topology and coefficients have a great impact on their models' performances. This paper proposes an enhanced group method of data handling (GMDH) algorithm using a modified Levenberg–Marquardt (LM) method. In this work, evolutionary algorithm and LM techniques are deployed simultaneously for optimal design of both connectivity configuration and associated coefficients of each candidate solution in the evolving population combination. However, use of singular value decomposition technique with LM is considered as a novel method to overcome the problem of initial guess, which is presented for the first time in this research. In order to illustrate the benefits of the proposed algorithm, it has been applied in a Malaysian manufacturing company for forecasting in inventory control. Moreover, a comparison between the basic GMDH algorithm and the enhanced GMDH algorithm is made, and the results show that the accuracy of the proposed method is considerably high with reasonable reduction in processing time. Therefore, the enhanced GMDH method can be used to replace old techniques in an inventory control system to generate a structure when it is applied to a Kanban setting in the just in time system.

This paper presents a computational design method to analyze and synthesize representation mechanisms in structural design. The role of shape grammar schemas in analyzing parametric and grammatical structural analysis is discussed, and a set of schema to generate novel structural topology is provided.

While there are many project management tools and software packages available, these are not widely used in the design curriculum at colleges and universities. This may reflect some of the differences between conventional projects and design activities. In particular, the open-ended nature of design activities and the need to clarify the client's intention may lead to the conclusion that conventional project management tools are only useful for the most routine activities in the design process. It is suggested that there is a market for a new set of tools for teaching the management of design. These tools should incorporate the most useful of the current management tools and integrate them with some of the requirements of effective design, including support for clarification of objectives, functional analysis, and generation and evaluation of alternatives.

This paper describes EKSPRO, a knowledge-based system integrating a 3-D computer-aided design system for materials, heating, ventilation, lighting equipment, building codes and occupational health regulations, and design guidelines user-defined by architects and engineers. The system features an object-oriented predicate logic knowledge representation, and interfaces with calculation packages (CAD, thermal balance, illumination, daylight).