Can artificial systems be creative? Can they be designed to be creative on their own? What are the requirements of such creative artificial systems? To be able to support humans who are expected to deliver creative solutions, or to automate part of their tasks, this paper presents a proposal for creativity requirements that provide a basis for designing creative artificial systems.

This paper presents an approach for the case adaptation, especially case repairing, in a case-based process planning system: PROCASE, for machining of rotational parts. In PROCASE, a new process plan is generated by adapting an existing similar process plan from its case library. Case adaptation is a crucial issue in achieving an automated case-based process planning system. This is because, usually, an existing process plan cannot necessarily produce an exact identical part as of the desired part. Adaptation is essential to tailor this existing plan to generate a new process plan for the new part. The case adaptation in this paper comprises case modification, case simulation, and case repairing. The modifier uses the knowledge extracted from case library to edit the retrieved similar plan. The simulator plays an important role in verifying the adapted plan as well as in directing the plan repairing. The repairing rules are indexed by the error messages obtained from the simulation. With the proposed case adaptation, the system will have the capability to repair the erroneous plans to achieve an automated and intelligent process planning system. This paper will first briefly introduce the case representation and case retrieval in PROCASE. Then the rest of the paper is dedicated to the case adaptation.

The paper describes and evaluates three methods of modelling earthquake accelerograms using artificial neural networks and linear predictors. These are a radial-Gaussian neural networking system, a linear predictor, and a hybrid of these two. Two methods of using these models to predict ground acceleration are adopted. The first is based on a direct prediction of ground acceleration at some point in time in the future from a series of ground accelerations that occurred earlier in the earthquake event. The second is a recursive approach whereby a model predicts a sequence of future ground accelerations by feeding back its predictions to its inputs. The performances of the models are tested using the 1985 Mexico earthquake and aftershock. The linear predictor and hybrid models perform best at direct prediction while none of the models perform particularly well at recursive prediction. The paper concludes with an outline of some areas for future work.

Nowadays, on the basis of significant work carried out, architectural adaption structures are considered to be intelligent entities, able to react to various internal or external influences. Their adaptive behavior can be examined in a digital or physical environment, generating a variety of alternative solutions or structural transformations. These are controlled through different computational approaches, ranging from interactive exploration ones, producing alternative emergent results, to automate optimization ones, resulting in acceptable fitting solutions. This paper examines the adaptive behavior of a kinetic structure, aiming to explore suitable solutions resulting in final appropriate shapes during the transformation process. A machine learning methodology that implements an artificial neural networks algorithm is integrated to the suggested structure. The latter is formed by units articulated together in a sequential composition consisting of primary soft mechanisms and secondary rigid components that are responsible for its reconfiguration and stiffness. A number of case studies that respond to unstructured environments are set as examples, to test the effectiveness of the proposed methodology to be used for handling a large number of input data and to optimize the complex and nonlinear transformation behavior of the kinetic system at the global level, as a result of the units’ local activation that influences nearby units in a chaotic and unpredictable manner.

Previous applications of genetic programming (GP) have been restricted to searching for algebraic approximations mapping the design parameters (e.g., geometrical parameters) to a single design objective (e.g., weight). In addition, these algebraic expressions tend to be highly complex. By adding a simple extension to the GP technique, a powerful design data analysis tool is developed. This paper significantly extends the analysis capabilities of GP by searching for multiple simple models within a single population by splitting the population into multiple islands according to the design variables used by individual members. Where members from different islands “cooperate,” simple design models can be extracted from this cooperation. This relatively simple extension to GP is shown to have powerful implications to extracting design models that can be readily interpreted and exploited by human designers. The full analysis method, GP heuristics extraction method, is described and illustrated by means of a design case study.

New methods of configuration analysis have recently emerged that are based on development trends characteristic of many technical systems. It has been found that though the development of any system aims to increase a combination of the performance, reliability and economy, actual design changes are frequently kept to a minimum to reduce the risk of failure. However, a strategy of risk reduction commits the designer to an existing configuration and an approved set of components and materials. Therefore, it is important to analyze the configurations, components, and materials of past designs so that good aspects may be reused and poor ones changed. A good configuration produces the required performance and reliability with maximum economy. These three evaluation criteria form the core of a configuration optimization tool called KATE, where known configurations are optimized producing a set of ranked trial solutions. The authors suggest that this solution set contains valuable design knowledge that can be reused. This paper briefly introduces a generic method of configuration evaluation and then describes the use of a self-organizing neural network, the Kohonen Feature Map, to analyze solution sets by performing an initial data reduction step, producing archetype solutions, and supporting qualitative clustering.

Learning is an intrinsic product of case-based reasoning. Acquiring new cases is one possible way of learning in a case-based system. These cases comprise mainly success knowledge. The successful cases are essentially used to generate new design solutions. But a case-based system also can make use of failure knowledge. In this paper we present how a case-based system can acquire failure cases for verification of the solution created by success cases. We describe IM-RECIDE, a system that uses case-based reasoning for solving design problems that are imperfectly described and explained. The learning aspect is focused and some of the machine learning dimensions in design are criticized. Experimental results in the domain of room configuration also are presented.

Literature suggests that people typically understand knowledge by induction and produce knowledge by synthesis. This paper revisits the various modes of reasoning – explanatory abduction, innovative abduction, deduction, and induction – that have been proposed by earlier researchers as crucial modes of reasoning underlying the design process. First, our paper expands earlier work on abductive reasoning – an essential mode of reasoning involved in the process of synthesis – by understanding its role with the help of the “SAPPhIRE” model of causality. The explanations of abductive reasoning in design using the SAPPhIRE model have been compared with those using existing models. Second, the paper captures and analyzes various modes of reasoning during design synthesis with the help of the “Extended Integrated Model of Designing”. The analysis of participants' verbal speech and outcomes shows the model's ability to explain the various modes of reasoning that occur in design. The results indicate the above models to provide a more extensive account of reasoning in design synthesis. Earlier empirical validation of both the models lends further support to the claim of their explanatory capacity.

This paper presents a method for automatically generating new designs from a set of existing objects of the same class using machine learning. In this particular work, we use a custom parametric chair design program to produce a large set of chairs that are tested for their physical properties using ergonomic simulations. Design schemata are found from this set of chairs and used to generate new designs by placing constraints on the generating parameters used in the program. The schemata are found by training decision trees on the chair data sets. These are automatically reverse engineered by examining the structure of the trees and creating a schema for each positive leaf. By finding a range of schemata, rather than a single solution, we maintain a diverse design space. This paper also describes how schemata for different properties can be combined to generate new designs that possess all properties required in a design brief. The method is shown to consistently produce viable designs, covering a large range of our design space, and demonstrates a significant time saving over generate and test using the same program and simulations.

Determining accurate standard time using direct measurement techniques is especially challenging in companies that do not have a proper environment for time measurement studies or that manufacture items requiring complex production schedules. New and specific time measurement techniques are required for such companies. This research developed a novel time estimation approach based on several machine learning methods. The set of collected inputs in the manufacturing environment, including a number of products, the number of welding operations, product's surface area factor, difficulty/working environment factors, and the number of metal forming processes. The data were collected from one of the largest bus manufacturing companies in Turkey. Experimental results demonstrate that when model accuracy was measured using performance measures, k-nearest neighbors outperformed other machine learning techniques in terms of prediction accuracy. “The number of welding operations” and “the number of pieces” were found to be the most effective parameters. The findings show that machine learning algorithms can estimate standard time, and the findings can be used for several purposes, including lowering production costs, increasing productivity, and ensuring efficiency in the execution of their operating processes by other companies that manufacture similar products.

The use of agent-based systems may offer significant advantages over centralized hierarchical manufacturing systems, including distribution of control/processing and data as well as adaptable automated or semiautomated problem solving. However, simply applying any agent-based paradigm to manufacturing domains may not be enough to address the various demands of these domains. Manufacturing domains require agent-based problem solving to be flexible and tolerant of faulty information (e.g., due to faulty sensors), equipments, and communication links. These issues are addressed by research on Sensible Agents, capable of 1) Dynamic Adaptive Autonomy and 2) explicit Perspective Modeling. Dynamic Adaptive Autonomy allows Sensible Agents to change problem-solving roles during system operation to address dynamic factory floor conditions, while Perspective Models internal to a respective Sensible Agent serve to maintain knowledge about the agent itself, other agents, and the environment. The application of the Sensible Agent paradigm to a shop-floor control is demonstrated.

Engineer–computer interaction (ECI) is a new subdomain of human–computer interaction that is specifically tailored to engineers' needs. ECI uses an information classification schema, provides a modular approach to task decomposition, and integrates standard engineering characteristics and working procedures into software. A software tool kit that interprets monitoring data taken from bridges was developed according to ECI guidelines. This tool kit was given to engineers for testing and evaluation. An empirical evaluation using questionnaires was performed. The results show that this ECI software corresponds to engineers' needs and the ECI approach has potential applications to other engineering tasks.

This paper presents a framework for the interactions between the processes of mapping and rerepresentation within analogy making. Analogical reasoning systems for use in design tasks require representations that are open to being reinterpreted. The framework, interpretation-driven mapping, casts the process of constructing an analogical relationship as requiring iterative, parallel interactions between mapping and interpreting. This paper argues that this interpretation-driven approach focuses research on a fundamental problem in analogy making: how do the representations that make new mappings possible emerge during the mapping process? The framework is useful for both describing existing analogy-making models and designing future ones. The paper presents a computational model informed by the framework Idiom, which learns ways to reinterpret the representations of objects as it maps between them. The results of an implementation in the domain of visual analogy are presented to demonstrate its feasibility. Analogies constructed by the system are presented as examples. The interpretation-driven mapping framework is then used to compare representational change in Idiom to that in three previously published systems.

Primary among all the activities involved in conceptual design is freehand sketching. There have been significant efforts in recent years to enable digital design methods that leverage humans’ sketching skills. Conventional sketch-based digital interfaces are built on two-dimensional touch-based devices like sketchers and drawing pads. The transition from two-dimensional to three-dimensional (3-D) digital sketch interfaces represents the latest trend in developing new interfaces that embody intuitiveness and human–human interaction characteristics. In this paper, we outline a novel screenless 3-D sketching system. The system uses a noncontact depth-sensing RGB-D camera for user input. Only depth information (no RGB information) is used in the framework. The system tracks the user's palm during the sketching process and converts the data into a 3-D sketch. As the generated data is noisy, making sense of what is sketched is facilitated through a beautification process that is suited to 3-D sketches. To evaluate the performance of the system and the beautification scheme, user studies were performed on multiple participants for both single-stroke and multistroke sketching scenarios.

A configurational method for describing shape is proposed based on two measures that gauge human experiences of moving through space: distance and changes in direction of travel. Boundary shapes from the built environment and nature are studied in a morphospace composed of two axes: one corresponding to each measure, to yield a typological classification of form. It is shown that the covariance between distance and directionality is mediated by the topological structure of embedded main circulation. Three kinds of circulation—elementary, ring, and linear—thus affect three fundamentally different balancing conditions between distance and directionality in boundary shapes. The analysis of large samples of shapes thus far demonstrates a “unique shape” status, where no two different shapes have the same pair of relative distance and directional fragmentation values.

This issue of AIEDAM is based on a workshop on Machine Learning in Design held at the 1996 Conference on Artificial Intelligence in Design, AID'96 (Gero & Sudweeks, 1996), the third of such workshops, with the previous two being held at AID'92 (Gero, 1992) and at AID'94 (Gero & Sudweeks, 1994). The first two workshops also resulted in special issues of AIEDAM (Maher et al., 1994; Duffy et al., 1996).

The subject of this paper is design intentionality. The paper is concerned with the property of the mind to hold intentional states (its capacity to represent or reflect existing and nonexisting realities) and with the way that these mental states are constructed during design tasks. The aim is to develop a mathematical theory of design intentionality, capturing the structures and processes that characterize an intentional system with the mental ability to address design tasks. The philosophical notion of intentionality is approached methodologically from a complexity theoretic perspective. More specifically, the focus is placed on the mathematical characterization of the organizational complexity of intentional states and the type of phase transitions that occur on the mental states of an intentional system during design tasks. The paper uses category theory in order to build a framework that is able to mathematically capture the meaning of these notions.

Architectural spatial design is a wicked problem that can have a multitude of solutions for any given brief. The information needed to resolve architectural design problems is often not readily available during the early conceptual stages, requiring proposals to be evaluated only after an initial solution is reached. This “solution-driven” design approach focuses on the generation of designs as a means to explore the solution space. Generative design can be achieved computationally through parametric and algorithmic processes. However, utilizing a large repertoire of organiational patterns and design precedent knowledge together with the precise criteria of spatial evaluation can present design challenges even to an experienced architect. In the implementation of a parametric design process lies an opportunity to supplement the designer's knowledge with computational decision support that provides real-time spatial feedback during conceptual design. This paper presents an approach based on a generative multiperformance framework, configured for generating and optimizing architectural designs based on a precedent design. The system is constructed using a parametric modeling environment enabling the capture of precedent designs, extraction of spatial analytics, and demonstration of how populations can be used to drive the generation and optimization of alternate spatial solutions. A pilot study implementing the complete workflow of the system is used to illustrate the benefits of coupling parametric modeling with structured precedent analysis and design generation.