In this paper a unique design methodology known as 1stPRINCE (FIRST PRINciple Computational Evalualor) is developed to perform innovative design of mechanical structures from first principle knowledge. The method is based on the assumption that the creation of innovative designs of physical significance, concerning geometric and material properties, requires reasoning from first principles. The innovative designs discovered by 1stPRINCE differ from routine designs in that new primitives are created. Monotonicity analysis and computer algebra are utilized to direct design variables in a globally optimal direction relative to the goals specified. In contrast to strict constraint propagation approaches, formal qualitative optimization techniques efficiently search the solution space in an optimizing direction, eliminate infeasible and suboptimal designs, and reason with both equality and inequality constraints. Modification of the design configuration space and the creation of new primitives, in order to meet the constraints or improve the design, are achieved by manipulating mathematical quantities such as the integral. The result is a design system which requires a knowledge base only of fundamental equations of deformation with physical constraints on variables, constitutive relations, and fundamental engineering assumptions; no pre-compiled knowledge of mechanical behavior is needed. Application of this theory to the design of a beam under torsion leads to designs of a hollow tube and a composite rod exhibiting globally optimal behavior. Further, these optimally-behaved designs are described symbolically as a function of the material properties and system parameters. This method is implemented in a LISP environment as a module in a larger intelligent CAD system that integrates qualitative, functional and numerical computation for engineering applications.

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.

Function models are frequently used in engineering design to describe the technical functions that a product performs. This paper investigates the use of the functional basis, a function vocabulary developed to aid in communication and archiving of product function information, in describing consumer products that have been decomposed, analyzed, modeled functionally, and stored in a Web-based design repository. The frequency of use of function terms and phrases in 11 graphical and 110 list-based representations in the repository is examined and used to analyze the organization and expressiveness of the functional basis and function models. Within the context of reverse engineering, we determined that the modeling resolution provided by the hierarchical levels, especially the tertiary level, is inadequate for function modeling; the tertiary terms are inappropriate for capturing sufficient details desired by modelers for archiving and reuse, and there is a need for a more expressive flow terms and flow qualifiers in the vocabulary. A critical comparison is also presented of two representations in the design repository: function structures and function lists. The conclusions are used to identify new research opportunities, including the extension of the vocabulary to incorporate flow qualifiers in addition to more expressive terms.

Accessibility in immersive media is a relevant research topic, still in its infancy. This article explores the appropriateness of two rendering modes (fixed-positioned and always-visible) and two guiding methods (arrows and auto-positioning) for subtitles in 360° video. All considered conditions have been implemented and integrated in an end-to-end platform (from production to consumption) for their validation and evaluation. A pilot study with end users has been conducted with the goals of determining the preferred options by users, the options that result in a higher presence, and of gathering extra valuable feedback from the end users. The obtained results reflect that, for the considered 360° content types, always-visible subtitles were more preferred by end users and received better results in the presence questionnaire than the fixed-positioned subtitles. Regarding guiding methods, participants preferred arrows over auto-positioning because arrows were considered more intuitive and easier to follow and reported better results in the presence questionnaire.

This paper explores the role of a designer's sense of engagement in early stage design. In the field of virtual reality, presence and immersion are standard measures of an individual's sense of engagement and involvement in an activity. High levels of presence might indicate that the designer is highly focused on the work. The central research question is the following: do designers who are more engaged in design activity, as measured by presence and immersive tendency questionnaires, produce better designs? An experiment was conducted to assess presence and immersive tendencies within the context of a hands-on, open-ended design-and-build activity. The results indicated that the designers' sense of immersion and presence ranged widely as well as their sense of frustration and calmness while performing the design activity. It was found that higher levels of presence correlated with either high design performance or low design performance. Lower levels of presence correlated with average design performance. No correlations were found between immersive tendency and design performance. This study suggests that some level of presence can be linked with better design, and it implies that level of presence might serve as an indicator of performance and learning in similar design-and-build activities.

This paper presents a formalism for considering the issues of learning in design. A foundation for machine learning in design (MLinD) is defined so as to provide answers to basic questions on learning in design, such as, “What types of knowledge can be learnt?”, “How does learning occur?”, and “When does learning occur?”. Five main elements of MLinD are presented as the input knowledge, knowledge transformers, output knowledge, goals/reasons for learning, and learning triggers. Using this foundation, published systems in MLinD were reviewed. The systematic review presents a basis for validating the presented foundation. The paper concludes that there is considerable work to be carried out in order to fully formalize the foundation of MLinD.

In the course of data modelling, many models could be created. Much work has been done on formulating guidelines for model selection. However, by and large, these guidelines are conservative or too specific. Instead of using general guidelines, models could be selected for a particular task based on statistical tests. When selecting one model, others are discarded. Instead of losing potential sources of information, models could be combined to yield better performance. We review the basics of model selection and combination and discuss their differences. Two examples of opportunistic and principled combinations are presented. The first demonstrates that mediocre quality models could be combined to yield significantly better performance. The latter is the main contribution of the paper; it describes and illustrates a novel heuristic approach called the SG(k-NN) ensemble for the generation of good-quality and diverse models that can even improve excellent quality models.

This paper describes our preliminary results in applying constraint satisfaction techniques in a system we call TRANS-FORM for designing automatic automobile power transmissions. The work is being conducted in collaboration with the Ford Motor Company Advanced Transmission Design Department in Livonia, Michigan. Our current focus is on the design of the mechanical subsystem, but we anticipate extending this later to the electrical and hydraulic subsystems also. For simplicity, in the initial work reported here we restrict ourselves to the relatively well-explored class of transmissions having four forward speeds and one reverse speed, built from two planetary gearsets, cross-connected by two permanent links. Moreover, we pursue design of such transmissions only at the ‘kinematic level’. These two restrictions correspond to limiting respectively the breadth (generality) and the depth (detail or granularity) of the search space employed. We find that, at least for the restricted version of the problem pursued here, transmission design is an application very naturally formulated as a constraint satisfaction problem. Our present problem requires only 10 variables, with an average of about seven values each, and 43 constraints—making it similar in difficulty to about the 10-queens problem. So far, two of the classic transmissions, known as Axod and HydraMatic, have been rediscovered (at the kinematic level) by our program. Preliminary results also indicate that the constraint satisfaction framework will continue to remain adequate and natural even when the search space is allowed to be much broader and deeper. We expect that searches of such expanded spaces will soon lead to the discovery of totally new transmissions.

Concurrent engineering is often viewed either from a technical point of view—that is, as a problem that can be solved by creating and integrating computer-based tools—or from an organizational point of view—that is, as a problem that can be solved by creating and reorganizing teams of designers. In this paper we argue that concurrent engineering requires both technical and organizational solutions, and we call the result concurrent design. We believe that the essence of concurrent design is the myriad of interactions that occur at the interfaces among all of the members of a design team and all their tools. Solving either the technical or organizational problems by assuming away the interactions will not solve the problems of concurrent design.

In this paper we present two case studies of concurrent design in practice that have changed our assumptions about design and which have changed our research agenda. We also present the evolution of concurrent design research at the Carnegie Mellon Engineering Design Research Center. In our research, we have designed, manufactured, and used our own tools as well as observed their use by others—where the tools include mobile computers, design analysis programs, and information organization tools. Through this process, we have learned about design education and design practice, and we have uncovered new issues for design research. We see the interactions among design research, practice, and education as essential to understanding concurrent design.

Gradient-based numerical optimization of complex engineering designs offers the promise of rapidly producing better designs. However, such methods generally assume that the objective function and constraint functions are continuous, smooth, and defined everywhere. Unfortunately, realistic simulators tend to violate these assumptions, making optimization unreliable. Several decisions that need to be made in setting up an optimization, such as the choice of a starting prototype and the choice of a formulation of the search space, can make a difference in the reliability of the optimization. Machine learning can improve gradient-based methods by making these choices based on the results of previous optimizations. This paper demonstrates this idea by using machine learning for four parts of the optimization setup problem: selecting a starting prototype from a database of prototypes, synthesizing a new starting prototype, predicting which design goals are achievable, and selecting a formulation of the search space. We use standard tree-induction algorithms (C4.5 and CART). We present results in two realistic engineering domains: racing yachts and supersonic aircraft. Our experimental results show that using inductive learning to make setup decisions improves both the speed and the reliability of design optimization.

This paper develops a philosophy for the use of Artificial Intelligence (AI) techniques as aids in engineering project management.

First, we propose that traditional domain-independent, ‘means–and’ planners, may be valuable aids for planning detailed subtasks on projects, but that domain-specific planning tools are needed for work package or executive level project planning. Next, we propose that hybrid computer systems, using knowledge processing techniques in conjunction with procedural techniques such as decision analysis and network-based scheduling, can provide valuable new kinds of decision support for project objective-setting and project control, respectively. Finally we suggest that knowledge-based interactive graphics, developed for providing graphical explanations and user control in advanced knowledge processing environments, can provide powerful new kinds of decision support for project management.

The first claim is supported by a review and analysis of previous work in the area of automated AI planning techniques. Our experience with PLATFORM I, II and III, a series of prototype AI-leveraged project management systems built using the IntelliCorp Knowledge Engineering Environment (KEE™), provides the justification for the latter two claims.

Collaborative design conflicts are an important type of process “exception,” that is, a real-life contingency such as a process change, execution error, or missed opportunity that leads to suboptimal performance of a collaborative process. This paper presents an integrated computational approach to collaborative process exception handling that avoids important weaknesses in current conflict management methods through the synergistic integration of conflict, workflow, and rationale technology. The approach is based upon an inclusive dependency language plus coordination services for dependency capture, process enactment, and exception handling. An initial implementation of this method called “iDCSS” is presented and challenges for future evolution of this technology are identified.

Building performance simulation and genetic algorithms are powerful techniques for helping designers make better design decisions in architectural design optimization. However, they are very time consuming and require a significant amount of computing power. More time is needed when two techniques work together. This has become the primary impediment in applying design optimization to real-world projects. This study focuses on reducing the computing time in genetic algorithms when building simulation techniques are involved. In this study, we combine two techniques (offline simulation and divide and conquer) to effectively improve the run time in these architectural design optimization problems, utilizing architecture-specific domain knowledge. The improved methods are evaluated with a case study of a nursing unit design to minimize the nurses’ travel distance and maximize daylighting performance in patient rooms. Results show the computing time can be saved significantly during the simulation and optimization process.

A framework for a design tool based on shape grammars is presented as an effective means for supporting the early stages of design. The framework uses a shape grammar interpreter to implement parametric shape grammars, allowing the grammar to be used interactively by a designer or optimization routine. A shape grammar to design inner hood panels of vehicles is introduced as an example of a parametric engineering shape grammar, and it is used with the framework to create standard and novel designs made possible by rules that take advantage of shape emergence.

Dealing with component interactions and dependencies remains a core and fundamental aspect of engineering, where conflicts and constraints are solved on an almost daily basis. Failure to consider these interactions and dependencies can lead to costly overruns, failure to meet requirements, and lengthy redesigns. Thus, the management and monitoring of these dependencies remains a crucial activity in engineering projects and is becoming ever more challenging with the increase in the number of components, component interactions, and component dependencies, in both a structural and a functional sense. For these reasons, tools and methods to support the identification and monitoring of component interactions and dependencies continues to be an active area of research. In particular, design structure matrices (DSMs) have been extensively applied to identify and visualize product and organizational architectures across a number of engineering disciplines. However, the process of generating these DSMs has primarily used surveys, structured interviews, and/or meetings with engineers. As a consequence, there is a high cost associated with engineers' time alongside the requirement to continually update the DSM structure as a product develops. It follows that the proposition of this paper is to investigate whether an automated and continuously evolving DSM can be generated by monitoring the changes in the digital models that represent the product. This includes models that are generated from computer-aided design, finite element analysis, and computational fluid dynamics systems. The paper shows that a DSM generated from the changes in the product models corroborates with the product architecture as defined by the engineers and results from previous DSM studies. In addition, further levels of product architecture dependency were also identified. A particular affordance of automatically generating DSMs is the ability to continually generate DSMs throughout the project. This paper demonstrates the opportunity for project managers to monitor emerging product dependencies alongside changes in modes of working between the engineers. The application of this technique could be used to support existing product life cycle change management solutions, cross-company product development, and small to medium enterprises who do not have a product life cycle management solution.

This paper discusses the application of genetic programming to the synthesis of compound two-dimensional kinematic mechanisms, and benchmarks the results against one of the classical kinematic challenges of 19th century mechanical design. Considerations for selecting a representation for mechanism design are presented, and a number of human-competitive inventions are shown.

The use of tangible objects is paramount in industrial design. Throughout the design process physical prototypes are used to enable exploration, simulation, communication, and specification of designs. Although much is known about prototyping skills and technologies, the reasons why and how such models are employed in design practice are poorly understood. Advanced techniques and design media such as virtual and augmented prototyping are being introduced without insight as to their benefits. We believe that an augmented prototyping system, that is, employing augmented reality technology to combine physical and digital representations, could positively influence the design process. However, we lack knowledge on why and how it might facilitate design. This paper reports on case studies performed in different domains of industrial design. At each of three Dutch design offices, a project was followed with particular attention to physical prototyping and group activities. The projects encompassed information appliance design, automotive design, and interior design. Although the studies vary in many aspects (product domain, stakeholders, duration), the findings can be applied in conceptualizing advanced prototyping systems to support industrial design. Furthermore, the data reveal that the roles of a prototype in current practice are not necessarily utilitarian; for example, the prototype may serve as a conversation piece or as seducer. Based on so-called “hints,” bottlenecks and best practices concerning concept articulation are linked to usage scenarios for augmented tangible prototyping. The results point to modeling and communication scenarios. Detailed study of the cases indicates that communication activities, especially design reviews, would benefit most from interactive augmented prototyping.

Inductive learning is proposed as a tool for synthesizing domain knowledge from data generated by a model-based simulator. In order to use an inductive engine to generate decision rules, the pre-classification process becomes more complicated in the presence of multiple competing objectives. Instead of relying on a domain expert to perform this pre-classification task, a clustering algorithm is used to eliminate human biases involved in the selection of a classification function for pre-classification. It is shown that the use of a clustering algorithm for pre-classification not only further automates the process of knowledge by synthesizing, but also improves the quality of the rules generated by the inductive engine.

The aim of our study is to investigate how innovation is taking place through different research and development (R&D) activities and to establish a link between innovation and business sustainability in the context of Indian pharmaceutical companies. Our study is based on the secondary data. Sample data of 37 Indian pharmaceutical companies listed on the National Stock Exchange have been used based on the stratified sampling technique. For empirical analysis we have performed descriptive statistics, correlation matrix, and panel regression analysis as statistical techniques with the help of STATA 12.0 statistical package. R2 value can predict 100 and 98.20% variability in return on assets (ROA) and return on equity (ROE) in model 1 and model 2, respectively. In model 1, the value of c2 is 1.48 and its corresponding p value is 0.00 (<0.05) which means that the model is a good fit for interpretation. R&D intensity is having a positive effect on ROA and the effect is statistically significant at 1% level. Advertising and marketing intensity, capital intensity, leverage ratio and operating expenditure to the total assets ratio are having positive effect on ROA but the effect is not statistically significant. In model 2, the value of F statistics is 8025.62 and its corresponding p value is 0.00 which is <0.05. It means that the model is a good fit for study. R&D intensity is having a positive effect on ROE and the effect is statistically significant at 1% level. Advertising and marketing intensity, capital intensity and operating expenditure to the total assets ratio have positive effect on ROE and the effect is statistically significant at 1% level. Leverage ratio is having a negative effect on ROE but the effect is statically significant at 10% level.

A growing trend in requirements elicitation is the use of machine learning (ML) techniques to automate the cumbersome requirement handling process. This literature review summarizes and analyzes studies that incorporate ML and natural language processing (NLP) into demand elicitation. We answer the following research questions: (1) What requirement elicitation activities are supported by ML? (2) What data sources are used to build ML-based requirement solutions? (3) What technologies, algorithms, and tools are used to build ML-based requirement elicitation? (4) How to construct an ML-based requirements elicitation method? (5) What are the available tools to support ML-based requirements elicitation methodology? Keywords derived from these research questions led to 975 records initially retrieved from 7 scientific search engines. Finally, 86 articles were selected for inclusion in the review. As the primary research finding, we identified 15 ML-based requirement elicitation tasks and classified them into four categories. Twelve different data sources for building a data-driven model are identified and classified in this literature review. In addition, we categorized the techniques for constructing ML-based requirement elicitation methods into five parts, which are Data Cleansing and Preprocessing, Textual Feature Extraction, Learning, Evaluation, and Tools. More specifically, 3 categories of preprocessing methods, 3 different feature extraction strategies, 12 different families of learning methods, 2 different evaluation strategies, and various off-the-shelf publicly available tools were identified. Furthermore, we discussed the limitations of the current studies and proposed eight potential directions for future research.