In recent years, the area of Product Design focusing on the Product's Life Cycle, from conception through disposal, has been an increasing area of research, in academia and industry. It provides a challenging, yet relatively unexplored, area of research for scientists and engineers from multiple disciplines. It is also an area of great interest to industry, with the refocusing of business models from increasing product performance to increasing corporate profitability while reducing expenditures. This paradigm shift has spawned multiple areas of research in Life-Cycle Design, as evidenced by the diversity in the topics of the papers submitted for this special issue of AI EDAM. We have collected five papers that present different areas of Life-Cycle Design; each provides a unique perspective on Life Cycle Design within the broad domain of Artificial Intelligence.

The AAAI Special Interest Group on AI in Manufacturing (SIGMAN) organization represents a wide array of researchers addressing fundamental scientific problems that arise in engineering design and manufacturing. The human endeavor that is design and manufacturing is rich in basic problems for researchers in Artificial Intelligence. From process planning researchers who aim to augment the abilities of human process engineers, to those who employ agents and distributed AI to model and control the factory floor—AI has found one of its most fertile and challenging proving grounds in the manufacture of products.

This issue of AIEDAM returns for the third time to the subject of evolutionary design. As in the previous two “mini” special issues (Volume 13, Numbers 3 and 5, 1999), this issue contains three papers focussing on the use of evolutionary algorithms to aid designers by automating part of the design process. These papers provide a showcase of the work of some of the original pioneers of this field as they demonstrate that their research is still at the forefront of developments in evolutionary design. As is fitting for this final special issue, the three papers all concentrate on what most designers recognize as the trickiest stage of the design process for computers: nonroutine, conceptual or innovative design.

To specify realistic tolerances and ensure acceptable product yields, a product development team must take into account the current process capability of the factory. Using historical process capability data in product development is frequently discussed in academic and industry literature. However, while many organizations have databases, the use of historical data in design is limited. This paper addresses the technical challenges of implementing a producibility analysis tool. First, a description of how data is currently collected and recorded is given. Second, the infeasibility of a “just-press-a-button” system for checking producibility is described. Finally, a new paradigm for data access is proposed, implemented in software, and tested on data used by industry.

The word “topology” is derived from the Greek word “τοπος,” which means “position” or “location.” A simplified and thus partial definition has often been used (Croom, 1989, page 2): “topology deals with geometric properties which are dependent only upon the relative positions of the components of figures and not upon such concepts as length, size, and magnitude.” Topology deals with those properties of an object that remain invariant under continuous transformations (specifically bending, stretching, and squeezing, but not breaking or tearing). Topological notions and methods have illuminated and clarified basic structural concepts in diverse branches of modern mathematics. However, the influence of topology extends to almost every other discipline that formerly was not considered amenable to mathematical handling. For example, topology supports design and representation of mechanical devices, communication and transportation networks, topographic maps, and planning and controlling of complex activities. In addition, aspects of topology are closely related to symbolic logic, which forms the foundation of artificial intelligence. In the same way that the Euclidean plane satisfies certain axioms or postulates, it can be shown that certain abstract spaces—where the relations of points to sets and continuity of functions are important—have definite properties that can be analyzed without examining these spaces individually. By approaching engineering design from this abstract point of view, it is possible to use topological methods to study collections of geometric objects or collections of entities that are of concern in design analysis or synthesis. These collections of objects and or entities can be treated as spaces, and the elements in them as points.

This paper describes an algorithm for surface reconstruction from a set of scattered three-dimensional points extracted from an image sequence. In this process, additional information (such as location of the viewpoints and the points visible from a particular viewpoint) is available and can be exploited for accurately recovering the shape of the objects portrayed in the images. Initially, the set of points is subjected to a Delaunay triangulation that fills the convex hull of the set of points with disjoint tetrahedra. The key idea of the shape recovery algorithm is to eliminate triangles that obstruct the visibility of points from certain viewpoints, whose locations are known from the image acquisition process. The major contribution of this paper is that we have been able to design an algorithm for surface reconstruction that handles a wide variety of shapes, as opposed to currently existing techniques.

The paper discusses the requirements of the engineering designer during the higher, conceptual levels of the design process in terms of search within initial predefined design spaces and subsequent exploration of transformed design spaces. Such transformation is based upon information gathered from initial search using evolutionary techniques that rapidly identify high-performance regions of complex design spaces. It is proposed that off-line processing of such information and associated design team discussion in an iterative designer/evolutionary search procedure can strengthen the knowledge base relating to the problem at hand and initiate significant change in the design environment. Research relating to appropriate evolutionary search and exploratory procedures is described and illustrated with results from simple test functions and real-world design problems. These results support discussion related to the manner in which the techniques may best support innovative and creative design activity in an interactive design team/evolutionary search environment.

This paper reports on the results of an analysis of existing ontological systems to determine which is most appropriate for the manufacturing domain. In particular, this involved the exploration of efforts that are studying both the uses of ontologies in the general sense and those that are using ontologies for domain-specific purposes. Eleven ontological systems were analyzed and, using a set of analysis criteria, it was determined that the Cyc (Cyc is a registered trademark of Cycorp Inc.) system was most appropriate for modeling concepts in the manufacturing domain. After the analysis is described, examples are given to show how manufacturing concepts could be modeled in the Cyc system. This work is part of a larger project whose objective is to move closer to the ultimate goal of seamless manufacturing systems integration using the principle behind ontological engineering to unambiguously define domain-specific concepts. The output of this work will be a taxonomy of manufacturing terms and concepts along with formal definitions of exactly what each of those terms and concepts mean and how they interrelate.

This paper presents a methodology for assessment of diagnosability of mechanical and hydraulic systems. The method is developed on the basis of relationships between system performance parameters and physical objects, that is, components of the system. These relationships are identified by system functional domain and are modeled in terms of a bipartite graph, called Diagnosability Bipartite Graph (DBG). A matrix called Diagnosability Matrix (DM) represents the DBG. Various diagnosability parameters of the system are derived from the DBG and the DM and these are useful in evaluation and comparison of design variants of the system. These parameters: are maximum number of set conflicts (MNS), maximum number of components in a set conflict (MNCS), diagnosability effort and cost (DEC), and average merit of diagnosability (AMD). The design having the lowest value of MNCS, AMD, and DEC; and highest value of MNS has the highest diagnosability. On the basis of these, a best design alternative is selected from diagnosability point of view. Moreover, components, which have poor diagnosability, are also identified. Maximum number of set conflicts (MNS) also guides in system fault diagnosis. The proposed procedure aids in the design and development of maintainable systems from diagnosability consideration. The method can also be used for evaluating and comparing the diagnosability of the systems. This method is illustrated with the help of two examples.

The problem addressed in this paper is that design decisions can have a propagation effect spanning multiple life-phases influencing life-cycle metrics such as cost, time, and quality. It introduces a computational framework of a “Knowledge of life-cycle Consequences (KC) approach” aimed at allowing designers to foresee and explore effectively unintended, solution specific life-cycle consequences (LCCs) during solution synthesis. The paper presents a phenomena model describing how LCCs are generated from two fundamentally different conditions: noninteracting and interacting synthesis decision commitments. Based on this understanding, the KC approach framework has been developed and implemented as a Knowledge-Intensive CAD (KICAD) tool named FORESEE. The framework consists of three frames: an artefact life modelling frame, an operational frame, and an LCC knowledge modelling frame. This paper focuses on the knowledge modelling frame, composed basically of synthesis elements, consequence inference knowledge, and consequence action knowledge. To evaluate the influence of design decision consequences on artefact life-phases, cost, time and quality performance measures are used within the frame. Using these metrics, the life-cycle implications of a decision can be instantly updated and fully appreciated. An evaluation of the approach was carried out by applying FORESEE to thermoplastic component design. The results provide a degree of evidence that the approach integrates the activity of component design synthesis with the activity of foreseeing artefact life issues including fluctuations in life-cycle metrics. This makes the approach fundamentally different from the conventional approach in which first a candidate design solution is generated and then, at a penalty of extra time, an analysis of the solution for conflicts with artefact life issues is carried out. The framework thus provides a significant step towards the realization of a “Design Synthesis for Multi-X” approach to component design, although further work is required to exploit practically its utilization.

This paper proposes interval constraint networks and interval propagation techniques for automatic tolerance design. To develop an intelligent automatic tolerance design mechanism, the following interrelated problems are addressed: (1) representing the relationships between the tolerances of the entities, attributes, and the functional requirements of a design component by a constraint network, (2) developing tolerance propagation techniques in the network that will satisfy the constraints between the entities, attributes and functional requirement. For the purpose of tolerance design, we propose new definitions for consistency of constraints and consistency of a constraint network. New forward and backward propagation techniques achieve worst-case tolerance analysis and synthesis, respectively. A tank design problem illustrates the use of the procedures for tolerance analysis and synthesis. The discussion and examples compare the new constraint network and propagation techniques with previous works.

The paper provides a solution to the current problem of adaptation in case-based design. The aim of this project is to develop a case-based model of design, using an evolutionary approach, for the adaptation of previously stored design solutions. It is argued that such a knowledge-lean methodology is more general in its applicability than conventional case-based design. A prototypical example in the context of 2-D spatial design of houses is used to test the efficacy and efficiency of this approach.

This paper describes a new method for generating the turning-gait of a six-legged robot using a combined genetic algorithm (GA)-Fuzzy approach. The main drawback of the traditional methods of gait generation is their high computational load. Thus, there is still a need for the development of a computationally tractable algorithm that can be implemented online to generate stable gait of a multilegged robot. In the proposed genetic-fuzzy system, the fuzzy logic controllers (FLCs) are used to generate the stable gait of a hexapod and a GA is used to improve the performance of the FLCs. The effectiveness of the proposed algorithm is tested on a number of turning-gait generation problems of a hexapod that involve translation as well as rotation of the vehicle. The hexapod will have to take a sharp circular turn (either clockwise or counter-clockwise) with minimum number of ground legs having the maximum average kinematic margin. Moreover, the stability margin should lie within a certain range to ensure static stability of the vehicle. Each leg of a six-legged robot is controlled by a separate FLC and the performance of the controllers is improved by using a GA. It is to be noted that the actual optimization is done off-line and the hexapod can use these optimized FLCs to navigate in real-world scenarios. As an FLC is computationally less expensive, the proposed algorithm will be faster compared with the traditional methods of gait-generation, which include both graphical as well as analytical methods. The GA-tuned FLCs are found to perform better than the author-defined FLCs.

In this article, an approach is presented for the representation and reasoning over qualitative spatial relations. A set-theoretic approach is used for representing the topology of objects and underlying space by retaining connectivity relationships between objects and space components in a structure, denoted, adjacency matrix. Spatial relations are represented by the intersection of components, and spatial reasoning is achieved by the application of general rules for the propagation of the intersection constraints between those components. The representation approach is general and can be adapted for different space resolutions and granularities of relations. The reasoning mechanism is simple and the spatial compositions are achieved in a finite definite number of steps, controlled by the complexity needed in the representation of objects and the granularity of the spatial relations required. The application of the method is presented over geometric structures that takes into account qualitative surface height information. It is also shown how directional relationships can be used in a hybrid approach for richer composition scenarios. The main advantage of this work is that it offers a unified platform for handling different relations in the qualitative space, which is a step toward developing general spatial reasoning engines for large spatial databases.

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 computer-assisted design (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 rationale information in a time- and cost-effective manner, with minimal disruption to the designer.

This paper describes the process planning techniques we developed for use in an Integrated Product and Process Design (IPPD) tool for the design and manufacture of microwave transmit/receive modules. Given a collection of data about the design of a microwave module, the IPPD tool uses a combination of AI planning and OR trade-off analysis to produce a collection of alternative designs and alternative process plans that have Pareto optimal values for manufacturing and purchasing lead time, process yield, cost, and number of suppliers. The IPPD tool provides facilities to enable the user to generate and examine these Pareto optimal alternatives in real time, in order to provide immediate feedback on how to modify the design to improve its cost and productivity.

In designing a state space of possible designs is implied by the representation used and the computational processes that operate on that representation. GAs are a means of effectively searching that state space which is defined by the length of the genotype's bit string. Of particular interest in design computing are processes that enlarge that state space to change the set of possible designs. This paper presents one such process based on the generalization of the genetic crossover operation. A crossover operation of genetic algorithms is reinterpreted as a random sampling of interpolating phenotypes, produced by a particular case of phenotypic interpolation. Its generalization is constructed by using a more general version of interpolation and/or by adding extrapolation to interpolation. This generalized crossover has a potential to move the current population outside of the original state space. An adaptive strategy for state space enlargement, which is based on this generalization, is designed. This strategy can be used for computational support of creative designing. An example is given.

The ability of a CAD system to perceive a three-dimensional model depicted in a single freehand sketch presents the practical possibility of bringing numerous established analysis tools into the early stages of design to institute conceptual analysis. In this article we hypothesize that the key to enabling systems to reason and communicate about conceptual design is the language of sketching. We explore this approach, outline the basic algorithms required, and provide several examples of an implemented system.

Current methods to develop standard Architecture, Engineering, Construction (AEC) product models focus on the definition of product model semantics without concurrent and formal consideration of the engineering analyses that such models must support, or formal consideration of the requirements for sharing information between applications. We present two case studies that demonstrate a service to extract data from product models and provide inputs to component analysis applications. The service was validated in a proof-of-concept application called the Internet Broker for Engineering Services (IBES) that extracts information for component analysis from product models that are external to the application and accessed across the Internet. IBES was tested for two research cases. The product model for the first case, control valve selection is based on STEP Application Protocol 227. The product model for the second case, control valve diagnosis, specifies additional semantics that support the operations and maintenance (O&M) phase of the facility life cycle. The cases offer evidence that large standard data models can support routine analyses for control valves. However, the amount of shared information between the case applications is small and is largely dependent upon the concurrence of component behaviors that are necessary to model analysis. The IBES reference model and reasoning to support information extraction was consistent for both cases. This consistency suggests that it is possible to define a general set of computational methods that integrate project information models with external component analysis applications across the product life cycle. We argue that enabling a web-based link between product models and applications requires a set of capabilities, including bi-directional communication between separated data and analysis nodes, query generation, data translation, and validation of data extracted from semistandard models. We discuss the tentative implication that minimal shared information calls into question the assumption that large core product models will work effectively in practice.

The external formation of integrated circuits based on lithographic processes is not the only possible method for manufacturing electron devices, either integrated circuits or photovoltaic cells. Planar technology, based on external formation, requires a certain sequence of interactions between the structured medium and the object being formed, in which the configuration of the region to be formed and its position are defined by the structure of the media and their alignment with the object. By contrast, in self-formation the interaction between an object to be formed and its chaotic medium is controlled by the object structure itself, and it is this interaction that changes the object's structure, leading to its increasing complexity. Three kinds of self-formation can be used in manufacturing: self-formation, based on a certain sequential interaction between an object and chaotic media; development, which requires only a single chaotic medium; and reproduction, which involves a developing object generating primary objects. All these cases represent self-formation of artificial systems. Simpler patterns of self-formation have already led to various patents and technologies, while more complex ones may be applied in the future. The following article attempts to define the necessary and sufficient conditions for self-formation.