scholarly journals BIKED: A Dataset for Computational Bicycle Design with Machine Learning Benchmarks

2021 ◽  
pp. 1-19
Author(s):  
Lyle Regenwetter ◽  
Brent Curry ◽  
Faez Ahmed
Keyword(s):  
Design Space ◽  
Data Driven ◽  
Design Parameters ◽  
Random Generation ◽  
Current Design ◽  
Research Questions ◽  
Class Labels ◽  
Confusion Matrices ◽  
Bicycle Design ◽  
Embedding Methods

Abstract In this paper, we present “BIKED,” a dataset comprised of 4500 individually designed bicycle models sourced from hundreds of designers. We expect BIKED to enable a variety of data-driven design applications for bicycles and support the development of data-driven design methods. The dataset is comprised of a variety of design information including assembly images, component images, numerical design parameters, and class labels. In this paper, we first discuss the processing of the dataset, then highlight some prominent research questions that BIKED can help address. Of these questions, we further explore the following in detail: 1) How can we explore, understand, and visualize the current design space of bicycles and utilize this information? We apply unsupervised embedding methods to study the design space and identify key takeaways from this analysis. 2) When designing bikes using algorithms, under what conditions can machines understand the design of a given bike? We train a multitude of classifiers to understand designs, then examine the behavior of these classifiers through confusion matrices and permutation-based interpretability analysis. 3) Can machines learn to synthesize new bicycle designs by studying existing ones? We test Variational Autoencoders on random generation, interpolation, and extrapolation tasks after training on BIKED data. The dataset and code are available at http://decode.mit.edu/projects/biked/

BIKED: A Dataset and Machine Learning Benchmarks for Data-Driven Bicycle Design

2021 ◽  
Author(s):  
Lyle Regenwetter ◽  
Brent Curry ◽  
Faez Ahmed
Keyword(s):  
Machine Learning ◽  
Design Space ◽  
Data Driven ◽  
Design Parameters ◽  
Design Data ◽  
Machine Learning Methods ◽  
Reduction Methods ◽  
Research Questions ◽  
Class Labels ◽  
Bicycle Design

Abstract In this paper, we present “BIKED,” a dataset comprised of 4500 individually designed bicycle models sourced from hundreds of designers. We expect BIKED to enable a variety of data-driven design applications for bicycles and support the development of data-driven design methods. The dataset is comprised of a variety of design information including assembly images, component images, numerical design parameters, and class labels. In this paper, we first discuss the processing of the dataset, then highlight some prominent research questions that BIKED can help address. Of these questions, we further explore the following in detail: 1) Are there prominent gaps in the current bicycle market and design space? We explore the design space using unsupervised dimensionality reduction methods. 2) How does one identify the class of a bicycle and what factors play a key role in defining it? We address the bicycle classification task by training a multitude of classifiers using different forms of design data and identifying parameters of particular significance through permutation-based interpretability analysis. 3) How does one synthesize new bicycles using different representation methods? We consider numerous machine learning methods to generate new bicycle models as well as interpolate between and extrapolate from existing models using Variational Autoencoders. The dataset is available at http://decode.mit.edu/projects/biked/ along with referenced code.

Design space optimisation of an unmanned aerial vehicle submerged inlet through the formulation of a data-fusion-based hybrid model

2021 ◽  
pp. 1-18
Author(s):  
F. Akram ◽  
H. A. Khan ◽  
T. A. Shams ◽  
D. Mavris
Keyword(s):  
Data Mining ◽  
Data Fusion ◽  
Design Space ◽  
Design Parameters ◽  
Design Variables ◽  
Current Design ◽  
Aerial Vehicle ◽  
Hybrid Data ◽  
Computational Fluid Dynamics Cfd ◽  
Cruise Flight

ABSTRACT The research focuses on the design space optimisation of National Advisory Committee for Aeronautics (NACA) submerged inlets through the formulation of a hybrid data fusion methodology. Submerged inlets have drawn considerable attention owing to their potential for good on-design performance, for example during cruise flight conditions. However, complexities due to the geometrical topology and interactions among various design variables remain a challenge. This research enhances the current design knowledge of submerged inlets through the utilisation of data mining and Computational Fluid Dynamics (CFD) methodologies, focusing on design space optimisation. A two-pronged approach is employed where the first step encompasses a low-fidelity model through data mining and surrogate modelling to predict and optimise the design parameters, while the second step uses the Design of Experiments (DOE) approach based on the CFD results for the candidate design geometry to construct a surrogate model with high fidelity for design refinement. The feasibility of the proposed methodology is demonstrated for the optimisation of the total pressure recovery of a NACA submerged inlet for the subsonic flight regime. The proposed methodology is found to provide good agreement between the surrogate and CFD-based model and reduce the optimisation processing time by half in comparison with conventional (global-based) CFD optimisation approaches.

Development of an improved design methodology and front steering design guideline for small-wheel bicycles for better stability and performance

2020 ◽  
Vol 234 (3) ◽  
pp. 227-244
Author(s):  
Milan Paudel ◽  
Fook Fah Yap
Keyword(s):  
Design Methodology ◽  
Design Guidelines ◽  
Design Approach ◽  
Design Parameters ◽  
Design Practice ◽  
Frame Design ◽  
Current Design ◽  
And Performance ◽  
Improved Design ◽  
Bicycle Design

The maneuverability and compactness of small-wheel and folding bicycles are greatly appreciated. Nonetheless, the performance of these small-wheel bicycles as compared to the big-wheel bicycles has always been questioned. They are often blamed for being less stable, wobbly, or twitchy. It is still unclear how the performance of the small-wheel bicycle designs can be improved. Both small- and big-wheel bicycles are designed with similar ergonomics; therefore, the focus has been on the front steering design. The steering design parameters of 91 big-wheel and 27 small-wheel bicycles were compared, bearing in mind the available front steering design guidelines to understand: (1) the influence of big-wheel bicycle’s frame design on small-wheel bicycles and (2) most common range of design parameters used in current bicycle designs. The analysis showed a strong influence of current big-wheel bicycle design practice on front frame parameter selection of small-wheel bicycles. Furthermore, the self-stability comparison over the most common design range confirmed the lesser stability in the current small-wheel bicycle designs at normal riding speed. However, it was also found that the lesser stability was not the result of small wheels per se, but rather owing to an inadequacy in the current design approach to addressing the complex influence of reducing wheel size and bicycle frame design on its stability and performance. Therefore, an improved design methodology was adopted by incorporating the bicycle dynamics into the current design approach and the front steering design guidelines for small-wheel bicycles have been developed. The guidelines contradict the current small-wheel bicycle design practice, as they recommend steeper headtube angles for small-wheel bicycles. The guidelines were validated with good agreement between the theoretical and experimental results on two prototype 20-inch-wheel bicycles having counter-intuitive steering geometry.

Front steering design guidelines formulation for e-scooters considering the influence of sitting and standing riders on self-stability and safety performance

2021 ◽  
pp. 095440702199217
Author(s):  
Milan Paudel ◽  
Fook Fah Yap
Keyword(s):  
Preventive Measures ◽  
Recent Trend ◽  
Dynamic Performance ◽  
Design Guidelines ◽  
Safety Performance ◽  
Design Parameters ◽  
Single Track ◽  
Standing Posture ◽  
Last Mile ◽  
Current Design

E-scooters are a recent trend and are viewed as a sustainable solution to ease the first and last mile problem in modern transportation. However, an alarming rate of accidents, injuries, and fatalities have caused a significant setback for e-scooters. Many preventive measures and legislation have been put on the e-scooters, but the number of accidents and injuries has not reduced considerably. In this paper, the current design approach of e-scooters has been analyzed, and the most common range of design parameters have been identified. Thereafter, validated mathematical models have been used to quantify the performance of e-scooters and relate them with the safety aspects. Both standing and seated riders on e-scooters have been considered, and their influence on the dynamic performance has been analyzed and compared with the standard 26-in wheel reference safety bicycle. With more than 80% of the accidents and injuries occurring from falling or colliding with obstacles, this paper tries to correlate the dynamics of uncontrolled single-track vehicles with the safety performance of e-scooters. The self-stability, handling, and braking effect have been considered as major performance matrices. The analysis has shown that the current e-scooter designs are not as stable as the reference safety bicycle. Moreover, these e-scooters have been found unstable within the most common range of legislated riding velocity. The results corroborate with the general perception that the current designs of e-scooters are less stable, easy to lose control, twitchy, or wobbly to ride. Furthermore, the standing posture of the rider on the e-scooter has been found dangerous while braking to avoid any disturbances such as potholes or obstacles. Finally, the front steering design guidelines have been proposed to help modify the current design of e-scooters to improve the dynamic performance, hence the safety of the e-scooter riders and the surroundings.

scholarly journals Evaluation of Static Mapping for Dynamic Space-Shared Multi-task Processing on FPGAs

2021 ◽  
Author(s):  
Umar Ibrahim Minhas ◽  
Roger Woods ◽  
Georgios Karakonstantis
Keyword(s):  
High Performance ◽  
Design Space Exploration ◽  
Design Space ◽  
System Throughput ◽  
Design Parameters ◽  
Temporal Constraints ◽  
Shared Resources ◽  
Task Processing ◽  
High Level ◽  
Performance Computing

AbstractWhilst FPGAs have been used in cloud ecosystems, it is still extremely challenging to achieve high compute density when mapping heterogeneous multi-tasks on shared resources at runtime. This work addresses this by treating the FPGA resource as a service and employing multi-task processing at the high level, design space exploration and static off-line partitioning in order to allow more efficient mapping of heterogeneous tasks onto the FPGA. In addition, a new, comprehensive runtime functional simulator is used to evaluate the effect of various spatial and temporal constraints on both the existing and new approaches when varying system design parameters. A comprehensive suite of real high performance computing tasks was implemented on a Nallatech 385 FPGA card and show that our approach can provide on average 2.9 × and 2.3 × higher system throughput for compute and mixed intensity tasks, while 0.2 × lower for memory intensive tasks due to external memory access latency and bandwidth limitations. The work has been extended by introducing a novel scheduling scheme to enhance temporal utilization of resources when using the proposed approach. Additional results for large queues of mixed intensity tasks (compute and memory) show that the proposed partitioning and scheduling approach can provide higher than 3 × system speedup over previous schemes.

A Systematic Function Recommendation Process for Data-Driven Product and Service Design

2017 ◽  
Vol 139 (11) ◽  
Author(s):  
Zhinan Zhang ◽  
Ling Liu ◽  
Wei Wei ◽  
Fei Tao ◽  
Tianmeng Li ◽  
...  
Keyword(s):  
Subjective Experience ◽  
Vital Role ◽  
Data Driven ◽  
Design Parameters ◽  
Sound Design ◽  
New Paradigm ◽  
Senior Managers ◽  
Product Service ◽  
Target User

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.

Adaptive Geometry Representation of Turbine Vane Frames for Use in Optimization

2021 ◽  
Author(s):  
Sebastian F. Riebl ◽  
Christian Wakelam ◽  
Reinhard Niehuis
Keyword(s):  
Design Space ◽  
Cfd Simulation ◽  
A Priori ◽  
Three Dimensional ◽  
Optimization Method ◽  
Three Dimensions ◽  
Design Parameters ◽  
Adjustment Process ◽  
Turbine Vane ◽  
Integrated Concept

Abstract Turbine Vane Frames (TVF) are a way to realize more compact jet engine designs. Located between the high pressure turbine (HPT) and the low pressure turbine (LPT), they fulfill structural and aerodynamic tasks. When used as an integrated concept with splitters located between the structural load-bearing vanes, the TVF configuration contains more than one type of airfoil with sometimes pronouncedly different properties. This system of multidisciplinary demands and mixed blading poses an interesting opportunity for optimization. Within the scope of the present work, a full geometric parameterization of a TVF with splitters is presented. The parameterization is chosen as to minimize the number of parameters required to automatically and flexibly represent all blade types involved in a TVF row in all three dimensions. Typical blade design parameters are linked to the fourth order Bézier-curve controlled camber line-thickness parameterization. Based on conventional design rules, a procedure is presented, which sets the parameters within their permissible ranges according to the imposed constraints, using a proprietary developed code. The presented workflow relies on subsequent three dimensional geometry generation by transfer of the proposed parameter set to a commercially available CAD package. The interdependencies of parameters are discussed and their respective significance for the adjustment process is detailed. Furthermore, the capability of the chosen parameterization and adjustment process to rebuild an exemplary reference TVF geometry is demonstrated. The results are verified by comparing not only geometrical profile data, but also validated CFD simulation results between the rebuilt and original geometries. Measures taken to ensure the robustness of the method are highlighted and evaluated by exploring extremes in the permissible design space. Finally, the embedding of the proposed method within the framework of an automated, gradient free numerical optimization is discussed. Herein, implications of the proposed method on response surface modeling in combination with the optimization method are highlighted. The method promises to be an option for improvement of optimization efficiency in gradient free optimization of interdependent blade geometries, by a-priori excluding unsuitable blade combinations, yet keeping restrictions to the design space as limited as possible.

scholarly journals Language change and language evolution: Cousins, siblings, twins?

2020 ◽  
Author(s):  
Stefan Hartmann
Keyword(s):  
Adaptive Systems ◽  
Language Change ◽  
Historical Linguistics ◽  
Language Evolution ◽  
Integrated Approach ◽  
Data Driven ◽  
Historical Time ◽  
Research Questions ◽  
The Relationship ◽  
Cross Fertilization

The relationship between “language change” and “language evolution” has recently become subject to some debate regarding the scope of both concepts. It has been claimed that while the latter used to refer to language origins in the first place, both terms can now, to a certain extent, be used synonymously. In this paper, I argue that this can partly be explained by parallel develop-ments both in historical linguistics and in the field of language evolution research that have led to a considerable amount of convergence between both fields. Both have adopted usage-based approaches and data-driven methods, which entails similar research questions and similar perspectives on the phenomena under investigation. This has ramifications for current models and theories of language change (or evolution). Two approaches in particular – the concept of com-plex adaptive systems and construction grammar – have been combined in integrated approaches that seek to explain both language emergence and language change over historical time. I discuss the potential and limitations of this integrated approach, and I argue that there is still some unex-plored potential for cross-fertilization.

scholarly journals Calculation features of wall panels with monolithic cement bond of layers in the stages of installation, transportation and maintenance

Vestnik MGSU ◽  
2019 ◽  
pp. 367-375 ◽  
Author(s):  
Elena A. Korol’ ◽  
Marina N. Berlinova
Keyword(s):  
Middle Layer ◽  
Structural Features ◽  
Design Parameters ◽  
Competitive Advantages ◽  
Design Standards ◽  
Wall Panels ◽  
Multilayer Wall ◽  
Current Design ◽  
Infinite Variety ◽  
Construction Practice

Introduction. When building residential, public and administrative buildings of various spatial structural designs (monolithic, precast-monolithic, precast, etc.), it is common practice to design self-sustaining (non-structural) outer walls within a storey. Developing and using new design and fabrication solutions of multilayer industrial-made wall panels in modern construction practice makes actual the issue of improving methods of their calculation in different stages of maintenance and under various sorts and combinations of loads and effects. However, there is an infinite variety of possible loading levels in practice and, therefore, the same variety of design approaches would be required. This is obviously unacceptable for engineering calculations, hence it is necessary to provide a monolithic matrix bond of layers, both technologically and structurally, which can provide a generalized approach to the calculation of multilayer enclosing structures in accordance with current design standards. Materials and methods. The article describes structural features of a multilayer wall panel made of structural concrete with the middle layer of concrete with low thermal conductivity and monolithic bond of layers. These features have an influence on creation of a design model and a calculation procedure in the stages of transportation, installation and maintenance. Results. The article has examined the structures described above in the sense of design parameters that provide their competitive advantages in strength and maintenance as compared with conventional mass-built enclosures. Conclusions. The studies demonstrate that when combining loads of force and non-force character, stresses in the considered structure do not exceed allowable values in all the stages what proves the prospects of using the multilayer panels with monolithic bond of layers for erection of various-purpose frame-panel buildings.

Innovative Six Sigma Design Using the Eigenvector Dimension-Reduction (EDR) Method

2007 ◽  
Author(s):  
Lee J. Wells ◽  
Byeng D. Youn ◽  
Zhimin Xi
Keyword(s):  
Taguchi Method ◽  
Dimension Reduction ◽  
Uncertainty Propagation ◽  
Robust Design Optimization ◽  
Design Parameters ◽  
Quality Engineering ◽  
Control Factors ◽  
Current Design ◽  
Eigenvector Dimension Reduction ◽  
Mean And Variance

This paper presents an innovative approach for quality engineering using the Eigenvector Dimension Reduction (EDR) Method. Currently industry relies heavily upon the use of the Taguchi method and Signal to Noise (S/N) ratios as quality indices. However, some disadvantages of the Taguchi method exist such as, its reliance upon samples occurring at specified levels, results to be valid at only the current design point, and its expensiveness to maintain a certain level of confidence. Recently, it has been shown that the EDR method can accurately provide an analysis of variance, similar to that of the Taguchi method, but is not hindered by the aforementioned drawbacks of the Taguchi method. This is evident because the EDR method is based upon fundamental statistics, where the statistical information for each design parameter is used to estimate the uncertainty propagation through engineering systems. Therefore, the EDR method provides much more extensive capabilities than the Taguchi method, such as the ability to estimate not only mean and standard deviation of the response, but also the skewness and kurtosis. The uniqueness of the EDR method is its ability to generate the probability density function (PDF) of system performances. This capability, known as the probabilistic “what-if” study, provides a visual representation of the effects of the design parameters (e.g., its mean and variance) upon the response. In addition, the probabilistic “what-if” study can be applied across multiple design parameters, allowing the analysis of interactions among control factors. Furthermore, the implementation of the probabilistic “what-if” study provides a basis for performing robust design optimization. Because of these advantages, it is apparent that the EDR method provides an alternative platform of quality engineering to the Taguchi method. For easy execution by field engineers, the proposed platform for quality engineering using the EDR method, known as Quick Quality Quantification (Q3), will be developed as a Microsoft EXCEL add-in.

Sign in / Sign up

Export Citation Format

Share Document