0


Guest Editorial

J. Mech. Des. 2017;139(11):110301-110301-3. doi:10.1115/1.4037943.
FREE TO VIEW
Topics: Design
Commentary by Dr. Valentin Fuster

Research Papers: D3 Methods

J. Mech. Des. 2017;139(11):111401-111401-13. doi:10.1115/1.4037246.

With the recent advances in information gathering techniques, product performances and environment/operation conditions can be monitored, and product usage data, including time-dependent product performance feature data and field data (i.e., environmental/operational data), can be continuously collected during the product usage stage. These technologies provide opportunities to improve product design considering product functional performance degradation. The challenge lies in how to assess data of product functional performance degradation for identifying relevant field factors and changing design parameters. An integrated approach for design improvement is developed in this research to transform time-dependent usage data to design information. Many data modeling and analysis techniques such as hierarchal function model, performance feature dimension reduction method, Gaussian mixed model (GMM), and data clustering method are employed in this approach. These methods are used to extract principal features from collected performance features, assess product functional performance degradation, and group field data into meaningful data clusters. The abnormal field data causing severe and rapid product function degradation are obtained based on the field data clusters. A redesign necessity index (RNI) is defined for each design parameter related to severely degraded functions based on the relationships between this design parameter and abnormal field data. An associate relationship matrix (ARM) is constructed to calculate the RNI of each design parameter for identifying the to-be-modified design parameters with high priorities for product improvement. The effectiveness of this new approach is demonstrated through a case study for the redesign of a large tonnage crawler crane.

Topics: Design , Dimensions
Commentary by Dr. Valentin Fuster
J. Mech. Des. 2017;139(11):111402-111402-14. doi:10.1115/1.4037649.

With the advent of the big-data era, massive information stored in electronic and digital forms on the internet become valuable resources for knowledge discovery in engineering design. Traditional document retrieval method based on document indexing focuses on retrieving individual documents related to the query, but is incapable of discovering the various associations between individual knowledge concepts. Ontology-based technologies, which can extract the inherent relationships between concepts by using advanced text mining tools, can be applied to improve design information retrieval in the large-scale unstructured textual data environment. However, few of the public available ontology database stands on a design and engineering perspective to establish the relations between knowledge concepts. This paper develops a “WordNet” focusing on design and engineering associations by integrating the text mining approaches to construct an unsupervised learning ontology network. Subsequent probability and velocity network analysis are applied with different statistical behaviors to evaluate the correlation degree between concepts for design information retrieval. The validation results show that the probability and velocity analysis on our constructed ontology network can help recognize the high related complex design and engineering associations between elements. Finally, an engineering design case study demonstrates the use of our constructed semantic network in real-world project for design relations retrieval.

Commentary by Dr. Valentin Fuster
J. Mech. Des. 2017;139(11):111403-111403-9. doi:10.1115/1.4037477.

With the advances in three-dimensional (3D) scanning and sensing technologies, massive human-related data are now available and create many applications in data-driven design. Similarity identification is one of the basic problems in data-driven design and can facilitate many engineering applications and product paradigm such as quality control and mass customization. Therefore, reusing information can create unprecedented opportunities in advancing the theory, method, and practice of product design. To enable information reuse, different models must be aligned so that their similarity can be identified. This alignment is commonly known as the global registration that finds an optimal rigid transformation to align two 3D shapes (scene and model) without any assumptions on their initial positions. The Super 4-Points Congruent Sets (S4PCS) is a popular algorithm used for this shape registration. While S4PCS performs the registration using a set of four coplanar points, we find that incorporating the volumetric information of the models can improve the robustness and the efficiency of the algorithm, which are particularly important for mass customization. In this paper, we propose a novel algorithm, Volumetric 4PCS (V4PCS), to extend the four coplanar points to noncoplanar ones for global registration, and theoretically demonstrate the computational complexity is significantly reduced. Experimental tests are conducted on several models such as tooth aligner and hearing aid to compare with S4PCS. The experimental results show that the proposed V4PCS can achieve a maximum of 20 times speedup and can successfully compute the valid transformation with very limited number of sample points. An application of the proposed method in mass customization is also investigated.

Commentary by Dr. Valentin Fuster
J. Mech. Des. 2017;139(11):111404-111404-14. doi:10.1115/1.4037610.

This paper presents a systematic function recommendation process (FRP) to recommend new functions to an existing product and service. Function plays a vital role in mapping user needs to design parameters (DPs) under constraints. It is imperative for manufacturers to continuously equip an existing product/service with exciting new functions. Traditionally, functions are mostly formulated by experienced designers and senior managers based on their subjective experience, knowledge, creativity, and even heuristics. Nevertheless, against the sweeping trend of information explosion, it is increasingly inefficient and unproductive for designers to manually formulate functions. In e-commerce, recommendation systems (RS) are ubiquitously used to recommend new products to users. In this study, the practically viable recommendation approaches are integrated with the theoretically sound design methodologies to serve a new paradigm of recommending new functions to an existing product/service. The aim is to address the problem of how to estimate an unknown rating that a target user would give to a candidate function that is not carried by the target product/service yet. A systematic function → product recommendation process is prescribed, followed by a detailed case study. It is indicated that practically meaningful functional recommendations (FRs) can indeed by generated through the proposed FRP.

Commentary by Dr. Valentin Fuster
J. Mech. Des. 2017;139(11):111405-111405-10. doi:10.1115/1.4037306.

To solve a design problem, sometimes it is necessary to identify the feasible design space. For design spaces with implicit constraints, sampling methods are usually used. These methods typically bound the design space; that is, limit the range of design variables. But bounds that are too small will fail to cover all possible designs, while bounds that are too large will waste sampling budget. This paper tries to solve the problem of efficiently discovering (possibly disconnected) feasible domains in an unbounded design space. We propose a data-driven adaptive sampling technique—ε-margin sampling, which learns the domain boundary of feasible designs and also expands our knowledge on the design space as available budget increases. This technique is data-efficient, in that it makes principled probabilistic trade-offs between refining existing domain boundaries versus expanding the design space. We demonstrate that this method can better identify feasible domains on standard test functions compared to both random and active sampling (via uncertainty sampling). However, a fundamental problem when applying adaptive sampling to real world designs is that designs often have high dimensionality and thus require (in the worst case) exponentially more samples per dimension. We show how coupling design manifolds with ε-margin sampling allows us to actively expand high-dimensional design spaces without incurring this exponential penalty. We demonstrate this on real-world examples of glassware and bottle design, where our method discovers designs that have different appearance and functionality from its initial design set.

Commentary by Dr. Valentin Fuster
J. Mech. Des. 2017;139(11):111406-111406-7. doi:10.1115/1.4037476.

The objective of this work is to introduce a new method for determining preliminary design specifications related to human-artifact interaction. This new method uses data mining of large numbers of consumer reviews. User opinion on specific product features can be time-consuming or expensive to obtain through traditional methods including surveys, experiments, and observational studies. Data mining review text of already released products may be a potentially less time consuming and costly method. Previously established methods of determining design for human variability information from consumer reviews, such as the frequency and accuracy summation (FAS) number and subsequent manual analysis, are explored. The weighted phrase rating (WPR), a new metric which can be an automated tool to quickly analyze consumer reviews, is also introduced. It does not require manual parsing of the reviews, which extends its applicability to larger review pools. This new method is shown to quickly and economically provide information useful to the establishment of design specifications.

Commentary by Dr. Valentin Fuster
J. Mech. Des. 2017;139(11):111407-111407-9. doi:10.1115/1.4037817.

This paper presents a method to automatically extract function knowledge from natural language text. The extraction method uses syntactic rules to acquire subject-verb-object (SVO) triplets from parsed text. Then, the functional basis taxonomy, WordNet, and word2vec are utilized to classify the triplets as artifact-function-energy flow knowledge. For evaluation, the function definitions associated with 30 most frequent artifacts compiled in a human-constructed knowledge base, Oregon State University's design repository (DR), were compared to the definitions identified by extraction the method from 4953 Wikipedia pages classified under the category “Machines.” The method found function definitions for 66% of the test artifacts. For those artifacts found, 50% of the function definitions identified were compiled in the DR. In addition, 75% of the most frequent function definitions found by the method were also defined in the DR. The results demonstrate the potential of the current work in enabling automated construction of function knowledge repositories.

Commentary by Dr. Valentin Fuster
J. Mech. Des. 2017;139(11):111408-111408-14. doi:10.1115/1.4037309.

Quantifying the ability of a digital design concept to perform a function currently requires the use of costly and intensive solutions such as computational fluid dynamics. To mitigate these challenges, the authors of this work propose a deep learning approach based on three-dimensional (3D) convolutions that predict functional quantities of digital design concepts. This work defines the term functional quantity to mean a quantitative measure of an artifact's ability to perform a function. Several research questions are derived from this work: (i) Are learned 3D convolutions able to accurately calculate these quantities, as measured by rank, magnitude, and accuracy? (ii) What do the latent features (that is, internal values in the model) discovered by this network mean? (iii) Does this work perform better than other deep learning approaches at calculating functional quantities? In the case study, a proposed network design is tested for its ability to predict several functions (sitting, storing liquid, emitting sound, displaying images, and providing conveyance) based on test form classes distinct from training class. This study evaluates several approaches to this problem based on a common architecture, with the best approach achieving F scores of >0.9 in three of the five functions identified. Testing trained models on novel input also yields accuracy as high as 98% for estimating rank of these functional quantities. This method is also employed to differentiate between decorative and functional headwear, which yields an 84.4% accuracy and 0.786 precision.

Commentary by Dr. Valentin Fuster
J. Mech. Des. 2017;139(11):111409-111409-11. doi:10.1115/1.4037612.

The authors of this work present a model that reduces product rating biases that are a result of varying degrees of customers' optimism/pessimism. Recently, large-scale customer reviews and numerical product ratings have served as substantial criteria for new customers who make their purchasing decisions through electronic word-of-mouth. However, due to differences among reviewers' rating criteria, customer ratings are often biased. For example, a three-star rating can be considered low for an optimistic reviewer. On the other hand, the same three-star rating can be considered high for a pessimistic reviewer. Many existing studies of online customer reviews overlook the significance of reviewers' rating histories and tendencies. Considering reviewers' rating histories and tendencies is significant for identifying unbiased customer ratings and true product quality, because each reviewer has different criteria for buying and rating products. The proposed customer rating analysis model adjusts product ratings in order to provide customers with more objective and accurate feedback. The authors propose an unsupervised model aimed at mitigating customer ratings based on rating histories and tendencies, instead of human-labeled training data. A case study involving real-world customer rating data from an electronic commerce company is used to validate the method.

Commentary by Dr. Valentin Fuster

Research Papers: Variability/Uncertainty in D3

J. Mech. Des. 2017;139(11):111410-111410-8. doi:10.1115/1.4037408.

The objective of this research is to model the geometric variability of the glenoid of the scapula. The glenoid is the “socket” component of the “ball and socket” connection of the shoulder joint. The model must capture the observed variability with sufficient resolution such that it informs both operative and design decisions. Creating the model required the application of existing mathematical and statistical modeling approaches, including geometric fitting, radial basis functions (RBFs), and principal component analysis (PCA). The landmark identification process represented the glenoid in a new manner. This work was validated against existing approaches and computed tomography (CT) scans from 42 patients. Information on the range of shoulder geometries can assist with preoperative planning as well as implant design for total shoulder arthroplasty (TSA). PCA was used to quantify the variability of shape across landmarks used to represent the glenoid shape. These landmark locations could be used to generate full surface meshes of existing glenoids or new glenoid models synthesized by changing principal components (PC). The process of creation of these shoulder geometries may be useful for the study of other joints. The models created will help surgeons and engineers to understand the effects of osteoarthritis on bone geometry, as well as the range of variability present in healthy shoulders.

Commentary by Dr. Valentin Fuster
J. Mech. Des. 2017;139(11):111411-111411-11. doi:10.1115/1.4037252.

Rapid advancement of sensor technologies and computing power has led to wide availability of massive population-based shape data. In this paper, we present a Taylor expansion-based method for computing structural performance variation over its shape population. The proposed method consists of four steps: (1) learning the shape parameters and their probabilistic distributions through the statistical shape modeling (SSM), (2) deriving analytical sensitivity of structural performance over shape parameter, (3) approximating the explicit function relationship between the finite element (FE) solution and the shape parameters through Taylor expansion, and (4) computing the performance variation by the explicit function relationship. To overcome the potential inaccuracy of Taylor expansion for highly nonlinear problems, a multipoint Taylor expansion technique is proposed, where the parameter space is partitioned into different regions and multiple Taylor expansions are locally conducted. It works especially well when combined with the dimensional reduction of the principal component analysis (PCA) in the statistical shape modeling. Numerical studies illustrate the accuracy and efficiency of this method.

Topics: Shapes
Commentary by Dr. Valentin Fuster
J. Mech. Des. 2017;139(11):111412-111412-12. doi:10.1115/1.4037308.

Configuration design problems, characterized by the assembly of components into a final desired solution, are common in engineering design. Various theoretical approaches have been offered for solving configuration type problems, but few studies have examined the approach that humans naturally use to solve such problems. This work applies data-mining techniques to quantitatively study the processes that designers use to solve configuration design problems. The guiding goal is to extract beneficial design process heuristics that are generalizable to the entire class of problems. The extraction of these human problem-solving heuristics is automated through the application of hidden Markov models to the data from two behavioral studies. Results show that designers proceed through four procedural states in solving configuration design problems, roughly transitioning from topology design to shape and parameter design. High-performing designers are distinguished by their opportunistic tuning of parameters early in the process, enabling a more effective and nuanced search for solutions.

Commentary by Dr. Valentin Fuster
J. Mech. Des. 2017;139(11):111413-111413-10. doi:10.1115/1.4037348.

Previous studies conducted customer surveys based on questionnaires and interviews, and the survey data were then utilized to analyze product features. In recent years, online customer reviews on products became extremely popular, which contain rich information on customer opinions and expectations. However, previous studies failed to properly address the determination of the importance of product features and prediction of their future importance based on online reviews. Accordingly, a methodology for predicting future importance weights of product features based on online customer reviews is proposed in this paper which mainly involves opinion mining, a fuzzy inference method, and a fuzzy time series method. Opinion mining is adopted to analyze the online reviews and extract product features. A fuzzy inference method is used to determine the importance weights of product features using both frequencies and sentiment scores obtained from opinion mining. A fuzzy time series method is adopted to predict the future importance of product features. A case study on electric irons was conducted to illustrate the proposed methodology. To evaluate the effectiveness of the fuzzy time series method in predicting the future importance, the results obtained by the fuzzy time series method are compared with those obtained by the three common forecasting methods. The results of the comparison show that the prediction results based on fuzzy time series method are better than those based on exponential smoothing, simple moving average, and fuzzy moving average methods.

Commentary by Dr. Valentin Fuster

Research Papers: Team Dynamics in D3

J. Mech. Des. 2017;139(11):111414-111414-9. doi:10.1115/1.4037478.

Concept clustering is an important element of the product development process. The process of reviewing multiple concepts provides a means of communicating concepts developed by individual team members and by the team as a whole. Clustering, however, can also require arduous iterations and the resulting clusters may not always be useful to the team. In this paper, we present a machine learning approach on natural language descriptions of concepts that enables an automatic means of clustering. Using data from over 1000 concepts generated by student teams in a graduate new product development class, we provide a comparison between the concept clustering performed manually by the student teams and the work automated by a machine learning algorithm. The goal of our machine learning tool is to support design teams in identifying possible areas of “over-clustering” and/or “under-clustering” in order to enhance divergent concept generation processes.

Commentary by Dr. Valentin Fuster

Research Papers: D3 and Lifecycle

J. Mech. Des. 2017;139(11):111415-111415-19. doi:10.1115/1.4037479.

The rapid rise in technologies for data collection has created an unmatched opportunity to advance the use of data-rich tools for lifecycle decision-making. However, the usefulness of these technologies is limited by the ability to translate lifecycle data into actionable insights for human decision-makers. This is especially true in the case of sustainable lifecycle design (SLD), as the assessment of environmental impacts, and the feasibility of making corresponding design changes, often relies on human expertise and intuition. Supporting human sensemaking in SLD requires the use of both data-driven and user-driven methods while exploring lifecycle data. A promising approach for combining the two is through the use of visual analytics (VA) tools. Such tools can leverage the ability of computer-based tools to gather, process, and summarize data along with the ability of human experts to guide analyses through domain knowledge or data-driven insight. In this paper, we review previous research that has created VA tools in SLD. We also highlight existing challenges and future opportunities for such tools in different lifecycle stages—design, manufacturing, distribution and supply chain, use-phase, end-of-life (EoL), as well as life cycle assessment (LCA). Our review shows that while the number of VA tools in SLD is relatively small, researchers are increasingly focusing on the subject matter. Our review also suggests that VA tools can address existing challenges in SLD and that significant future opportunities exist.

Commentary by Dr. Valentin Fuster
J. Mech. Des. 2017;139(11):111416-111416-13. doi:10.1115/1.4037680.

Engineers and technology firms must continually explore new design opportunities and directions to sustain or thrive in technology competition. However, the related decisions are normally based on personal gut feeling or experiences. Although the analysis of user preferences and market trends may shed light on some design opportunities from a demand perspective, design opportunities are always conditioned or enabled by the technological capabilities of designers. Herein, we present a data-driven methodology for designers to analyze and identify what technologies they can design for the next, based on the principle—what a designer can currently design condition or enable what it can design next. The methodology is centered on an empirically built network map of all known technologies, whose distances are quantified using more than 5 million patent records, and various network analytics to position a designer according to the technologies that they can design, navigate technologies in the neighborhood, and identify feasible paths to far fields for novel opportunities. Furthermore, we have integrated the technology space map, and various map-based functions for designer positioning, neighborhood search, path finding, and knowledge discovery and learning, into a data-driven visual analytic system named InnoGPS. InnoGPS is a global position system (GPS) for finding innovation positions and directions in the technology space, and conceived by analogy from the GPS that we use for positioning, neighborhood search, and direction finding in the physical space.

Topics: Design , Patents
Commentary by Dr. Valentin Fuster

Research Papers: D3 Applications and Case Studies

J. Mech. Des. 2017;139(11):111417-111417-11. doi:10.1115/1.4037249.

Styling or product appearance is well known for holding great influence on its differentiation, branding, and overall success in the market. However, the styling process is difficult due to the intuitive and subjective way in which designers evaluate designs. In particular, negotiating iterations between designers and engineers is challenging since engineers have objective, data-driven approaches to rationalize decisions whereas designers rely on instinct and intuition. While the literature shows sustained interest in this issue and provides methods to analyze appearance objectively, many approaches rely on abstracted or simplified versions of a product's appearance as the basis for analyses, ignoring the holistic nature of product appearance. This article contributes by proposing an improvement employing digital shape comparison tools applied to three-dimensional (3D) geometry of products, and generating data on differentiation in product shape—that is, the holistic styling analysis (HSA). The HSA provides an objective assessment of difference in appearance to form the basis for designers to rationalize styling to other stakeholders during the design process. The HSA is tested through an automotive industry case study. Results show the method adds objectivity to decision-making by providing objective reference measures for differentiation in the styling of previous and competing products. Such measures can be used to inform styling goals and to identify intended degrees of difference in key features while highlighting areas to maintain consistency. As such, we contribute by providing a means for styling designers to use data to drive their activities in the same manner as other stakeholders.

Topics: Design , Shapes , Vehicles
Commentary by Dr. Valentin Fuster
J. Mech. Des. 2017;139(11):111418-111418-3. doi:10.1115/1.4037475.

In order to overcome the problems due to subjective judgments in the traditional product requirement acquisition techniques based on the “users’ voices,” a new data-based approach is developed in this research to identify the performance requirements for design of smartphones. The operating data are collected from smartphones and curve fitting method is used to obtain the performance distributions. The sigmoidlike function is employed to construct nonlinear customer satisfaction function (CSF) based on the performance distributions. From the CSF, customer required performance with a target satisfaction degree can be obtained. The cost-effective point for satisfaction improvement is determined to get a reasonable degree of satisfaction. A case study is conducted to identify the customer requirements on CPU performance based on the collected CPU utilization data.

Topics: Design
Commentary by Dr. Valentin Fuster
J. Mech. Des. 2017;139(11):111419-111419-10. doi:10.1115/1.4037307.

Prediction of thermoacoustic instabilities is a critical issue for both design and operation of combustion systems. Sustained high-amplitude pressure and temperature oscillations may cause stresses in structural components of the combustor, leading to thermomechanical damage. Therefore, the design of combustion systems must take into account the dynamic characteristics of thermoacoustic instabilities in the combustor. From this perspective, there needs to be a procedure, in the design process, to recognize the operating conditions (or parameters) that could lead to such thermoacoustic instabilities. However, often the available experimental data are limited and may not provide a complete map of the stability region(s) over the entire range of operations. To address this issue, a Bayesian nonparametric method has been adopted in this paper. By making use of limited experimental data, the proposed design method determines a mapping from a set of operating conditions to that of stability regions in the combustion system. This map is designed to be capable of (i) predicting the system response of the combustor at operating conditions at which experimental data are unavailable and (ii) statistically quantifying the uncertainties in the estimated parameters. With the ensemble of information thus gained about the system response at different operating points, the key design parameters of the combustor system can be identified; such a design would be statistically significant for satisfying the system specifications. The proposed method has been validated with experimental data of pressure time-series from a laboratory-scale lean-premixed swirl-stabilized combustor apparatus.

Commentary by Dr. Valentin Fuster
J. Mech. Des. 2017;139(11):111420-111420-15. doi:10.1115/1.4037613.

Data-driven engineering designers often search for design precedents in patent databases to learn about relevant prior arts, seek design inspiration, or assess the novelty of their own new inventions. However, patent retrieval relevant to the design of a specific product or technology is often unstructured and unguided, and the resultant patents do not sufficiently or accurately capture the prior design knowledge base. This paper proposes an iterative and heuristic methodology to comprehensively search for patents as precedents of the design of a specific technology or product for data-driven design. The patent retrieval methodology integrates the mining of patent texts, citation relationships, and inventor information to identify relevant patents; particularly, the search keyword set, citation network, and inventor set are expanded through the designer's heuristic learning from the patents identified in prior iterations. The method relaxes the requirement for initial search keywords while improving patent retrieval completeness and accuracy. We apply the method to identify self-propelled spherical rolling robot (SPSRRs) patents. Furthermore, we present two approaches to further integrate, systemize, visualize, and make sense of the design information in the retrieved patent data for exploring new design opportunities. Our research contributes to patent data-driven design.

Topics: Design , Patents
Commentary by Dr. Valentin Fuster

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In