Design rationale should be regarded both as a tool for the practice of design, and as a method to enable the science of design. Design rationale answers questions about why a given design takes the form that it does. Answers to these why questions represent a significant portion of the knowledge generated from design research. This knowledge, along with that from empirical studies of designs in use, contributes to what Simon called the sciences of the artificial. Most research on the nature and use of design rationale has been analytic or theoretical. In this article, we describe an empirical study of the roles that design rationale can play in the conduct of design research. We report results from an interview study with 16 design researchers investigating how they construe and carry out design as research. The results include an integrated framework of the affordances design rationale can contribute to design research. The framework and supporting qualitative data provide insight into how design rationale might be more effectively leveraged as a first-class methodology for research into the creation and use of artifacts.

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.

Computer-aided process planning has been recognized as an important tool for coordinating the different operations involved in making the product. While temporal knowledge is central to the design of efficient and reliable process plans, little attention is given to the integration of process planning and temporal processing and reasoning. To fill the void, we propose in this paper a practical approach, which is inspired by the framework of Temporal Constraint Satisfaction Problem (TCSP), to integrate process planning and temporal reasoning. We show that a TCSP formulation is a subset of a formulation using a reified temporal logic, and discuss the advantages of using such a restricted model. To reflect more realistic process planning encountered in real manufacturing environments, we present a model, called n-TCSP, which is a generalization of the TCSP framework. We envision the proposed temporal reasoning framework as one of the modules in the evolving new intelligent computer-aided process planning.

The complexity of mechanical design is reflected in the complexity of the design constraints which relate functional requirements to design parameters. Reformulations of the design constraints can significantly reduce this complexity. This is accomplished by a transformation to alternative design parameters, such as a critical ratio, a non-dimensional parameter, or a simple difference; e.g. the ratio of surface area to volume for heat transfer loss, the Reynold's number in fluid mechanics, or the velocity difference across a fluid coupling. We have developed a method by which the alternative parameters are chosen for physical significance and for the ability to create a more direct correspondence to functional behavior as determined by measures of serial and block decomposability of the constraints. Rules have been developed for the creation of physically significant new parameters from the algebraic combination of the original parameters. The rules are based on engineering principles and rely on knowledge about what a parameter physically represents rather than other qualities such as dimensions. A computer based system, called EUDOXUS, has been developed to automate this procedure. The system operates on a set of design constraints to produce sets of transformed constraints in terms of alternative design parameters. The method and its implementation have demonstrated successful results for many highly nonlinear and highly coupled parameterized designs from many mechanical engineering domains.

This paper discusses the development of an experimental software prototype that uses surrogate models for predicting the monthly energy consumption of urban-scale community design scenarios in real time. The surrogate models were prepared by training artificial neural networks on datasets of urban form and monthly energy consumption values of all zip codes in San Diego county. The surrogate models were then used as the simulation engine of a generative urban design tool, which generates hypothetical communities in San Diego following the county's existing urban typologies and then estimates the monthly energy consumption value of each generated design option. This paper and developed software prototype is part of a larger research project that evaluates the energy performance of community microgrids via their urban spatial configurations. This prototype takes the first step in introducing a new set of tools for architects and urban designers with the goal of engaging them in the development process of community microgrids.

Cold rolling involves large deformation of the workpiece leading to temperature increase due to plastic deformation. This process is highly nonlinear and leads to large computation times to fully model the process. This paper describes the use of dimension-reduced neural networks (DR-NNs) for predicting temperature changes due to plastic deformation in a two-stage cold rolling process. The main objective of these models is to reduce computational demand, error, and uncertainty in predictions. Material properties, feed velocity, sheet dimensions, and friction models are introduced as inputs for the dimensionality reduction. Different linear and nonlinear dimensionality reduction methods reduce the input space to a smaller set of principal components. The principal components are fed as inputs to the neural networks for predicting the output temperature change. The DR-NNs are compared against a standalone neural network and show improvements in terms of lower computational time and prediction uncertainty.

Automatically extracting knowledge from small datasets with a valid causal ordering is a challenge for current state-of-the-art methods in machine learning. Extracting other type of knowledge is important but challenging for multiple engineering fields where data are scarce and difficult to collect. This research aims to address this problem by presenting a machine learning-based modeling framework leveraging the knowledge available in fundamental units of the variables recorded from data samples, to develop parsimonious, explainable, and graph-based simulation models during the early design stages. The developed approach is exemplified using an engineering design case study of a spherical body moving in a fluid. For the system of interest, two types of intricated models are generated by (1) using an automated selection of variables from datasets and (2) combining the automated extraction with supplementary knowledge about functions and dimensional homogeneity associated with the variables of the system. The effect of design, data, model, and simulation specifications on model fidelity are investigated. The study discusses the interrelationships between fidelity levels, variables, functions, and the available knowledge. The research contributes to the development of a fidelity measurement theory by presenting the premises of a standardized, modeling approach for transforming data into measurable level of fidelities for the produced models. This research shows that structured model building with a focus on model fidelity can support early design reasoning and decision making using for example the dimensional analysis conceptual modeling (DACM) framework.

The predictive methods of tool wear are usually based on different algorithm predictors, different source data, and different sensing devices for remaining useful life (RUL). In general, it has challenges to model and ensure all of the cutting conditions that are suitable in the actual cutting process for sustainable manufacturing. In order to overcome the doing large amount of experimental data and predict different tool RULs, this study combines the analytical force modeling, the back-propagation neural network (BPNN) machine learning, and the current sensor which all are integrated in smart machine box (SMB) to realize the practical RUL prediction for on-line and real-time applications. The analytical model of the cutting force coefficients of shear and ploughing was established from average cutting forces, it could reduce the experimental number and predict the different cutting conditions. In general, the loading current of the cutting tool from a spindle motor is relatively easier acquired than the resultant forces. Thus, the loading currents of the spindle are used to train and predict the cutting forces using the BPNN model during intelligent manufacturing. The SMB architecture mainly performed the autonomous actions based on the edge layer, the fog layer, and the cloud layer via the TCP/IP, the MQTT protocol, and the unified communication library. Results showed that a predictive error for the ends of the tool life is about 3–10% that are based on the calculating of the cumulative current ratio.

This paper defines, for use in design, rules for propagating “distribution constraints” through relationships such as algebraic or vector equations. Distribution constraints are predicate logic statements about the values that physical system parameters may assume. The propagation rules take into account “variation source causality”: information about when and how the values are assigned during the design, manufacturing, and operation of the system.

Configuration assistants are tools for guiding the final user in simple configuration tasks, such as product assembling and customization or study plans generation. For their wide availability, web-based configuration assistants are valuable in fields such as electronic commerce and information services. We describe a general approach for building web-based configuration assistants: from a high-level description of the configuration constraints and of the basic items, given in a declarative language, the hypertext files for user guidance and the Java code for constraint checking are generated. We claim that the general approach of process-oriented configuration, where the user is guided through the configuration process by an explanatory hypertext, as opposed to product-oriented configuration, where one starts from a high-level description of the product of the configuration, is better suited for many application domains.

When developing a product, designers must decide what consumer variation will be addressed and how they will address it, because each consumer has a unique set of human factors, preferences, personal knowledge, and solution constraints. Numerous design methodologies exist to support the design of a product or set of products that address this consumer variation. However, currently there is little work supporting the selection of a design methodology, resulting in an ad hoc or a priori decision before conceptual design begins. This paper presents an affordance-based design method for use prior to conceptual design to help designers understand the consumer variation that is present. This facilitates the creation of a product or set of products that meets the demands of both the consumer(s) and the organization that is developing the product. Once consumer variation is understood, conceptual design can be performed with a more complete understanding of the overall problem.

After 20 years of personal experience in introducing advanced software into several engineering contexts (engineering consulting firms, construction companies, large diversified companies, and commercial research establishments), some observations may be of interest. Although some development efforts succeeded and software is still in use, not one development effort has met the expectations that were expressed at the beginning of the project. The least successful experiences are design applications.

Reflective actions in collaborative design can potentially improve design performance and results. This paper quantitatively reexamines the relationships between reflective activities and design performance during the collaborative design process in terms of reflection in action. Twenty sets of protocol data were encoded by a modified version of Valkenburg and Dorst's coding scheme. Using statistical testing, the relationship between the design performance and the number of activities plus the transitions was examined. A significant statistical correlation was found between the percentage of mature framing (setting up of a desired goal with sufficient follow-ups) and the overall performance. These quantitative results verify the qualitative findings of the previous study.

This article is an attempt to improve the efficiency of procedures for compositional synthesis of design solutions using building blocks. These procedures have found use in a wide range of applications, and are one of the most substantial outcomes of research into automated synthesis of design solutions. Due to their combinatorial nature, these procedures are highly inefficient in solving problems, especially when the database of building blocks for synthesis or the problem size is large. Previous literature often focuses on improving only the algorithm part of a procedure, while it is both its algorithm and database which together determine the overall efficiency of the procedure. This article uses a case study to investigate and develop a set of rules for structuring and preprocessing a database of building blocks so as to improve the efficiency of synthesis of design solutions using this database.

Self-organizing systems (SOS) are developed to perform complex tasks in unforeseen situations with adaptability. Predefining rules for self-organizing agents can be challenging, especially in tasks with high complexity and changing environments. Our previous work has introduced a multiagent reinforcement learning (RL) model as a design approach to solving the rule generation problem of SOS. A deep multiagent RL algorithm was devised to train agents to acquire the task and self-organizing knowledge. However, the simulation was based on one specific task environment. Sensitivity of SOS to reward functions and systematic evaluation of SOS designed with multiagent RL remain an issue. In this paper, we introduced a rotation reward function to regulate agent behaviors during training and tested different weights of such reward on SOS performance in two case studies: box-pushing and T-shape assembly. Additionally, we proposed three metrics to evaluate the SOS: learning stability, quality of learned knowledge, and scalability. Results show that depending on the type of tasks; designers may choose appropriate weights of rotation reward to obtain the full potential of agents’ learning capability. Good learning stability and quality of knowledge can be achieved with an optimal range of team sizes. Scaling up to larger team sizes has better performance than scaling downwards.

I present an implementation of shape grammars that is aimed at supporting designers. It has two parts: a grammar editor and a stand-alone interpreter. The editor is the modeling application Rhinoceros3d using Python scripts. The interpreter is general, is three-dimensional, and supports subshape detection. A grammar is a Rhinoceros3d model; thus users can manipulate all its parts directly and immediately. That is, they can modify any shape without selecting or invoking an editor, and they can lay out the parts of the grammar in any way they find meaningful. Using this approach, which I call a whole-grammar approach, users are shielded from most subdomain tasks, like typing text files or specifying transformations. Informal observations suggest that users of this implementation can work effectively.

Identifying failure paths and potentially hazardous scenarios resulting from component faults and interactions is a challenge in the early design process. The inherent complexity present in large engineered systems leads to nonobvious emergent behavior, which may result in unforeseen hazards. Current hazard analysis techniques focus on single hazards (fault trees), single faults (event trees), or lists of known hazards in the domain (hazard identification). Early in the design of a complex system, engineers may represent their system as a functional model. A function failure reasoning tool can then exhaustively simulate qualitative failure scenarios. Some scenarios can be identified as hazardous by hazard rules specified by the engineer, but the goal is to identify scenarios representing unknown hazards. The incidences of specific subgraphs in graph representations of known hazardous scenarios are used to train a classifier to distinguish hazard from nonhazard. The algorithm identifies the scenario most likely to be hazardous, and presents it to the engineer. After viewing the scenario and judging its safety, the engineer may have insight to produce additional hazard rules. The collaborative process of strategic presentation of scenarios by the computer and human judgment will identify previously unknown hazards. The feasibility of this methodology has been tested on a relatively simple functional model of an electrical power system with positive results. Related work applying function failure reasoning to a team of robotic rovers will provide data from a more complex system.