Search

Existing hybrid powertrain architectures, i.e., the connections from engine and motors to the vehicle output shaft, are designed for particular vehicle applications, e.g., passenger cars or city buses, to achieve good fuel economy. For effective electrification of new applications (e.g., heavy-duty trucks or racing cars), new architectures may need to be identified to accommodate the particular vehicle specifications and drive cycles. The exploration of feasible architectures is combinatorial in nature and is conventionally based on human intuition. We propose a mathematically rigorous algorithm to enumerate all feasible powertrain architectures, therefore enabling automated optimal powertrain design. The proposed method is general enough to account for single and multimode architectures as well as different number of planetary gears (PGs) and powertrain components. We demonstrate through case studies that our method can generate the complete sets of feasible designs, including the ones available in the market and in patents.

Quantitative preference models are used to predict customer choices among design alternatives by collecting prior purchase data or survey answers. This paper examines how to improve the prediction accuracy of such models without collecting more data or changing the model. We propose to use features as an intermediary between the original customer-linked design variables and the preference model, transforming the original variables into a feature representation that captures the underlying design preference task more effectively. We apply this idea to automobile purchase decisions using three feature learning methods (principal component analysis (PCA), low rank and sparse matrix decomposition (LSD), and exponential sparse restricted Boltzmann machine (RBM)) and show that the use of features offers improvement in prediction accuracy using over 1 million real passenger vehicle purchase data. We then show that the interpretation and visualization of these feature representations may be used to help augment data-driven design decisions.

Crowdsourced evaluation is a promising method of evaluating engineering design attributes that require human input. The challenge is to correctly estimate scores using a massive and diverse crowd, particularly when only a small subset of evaluators has the expertise to give correct evaluations. Since averaging evaluations across all evaluators will result in an inaccurate crowd evaluation, this paper benchmarks a crowd consensus model that aims to identify experts such that their evaluations may be given more weight. Simulation results indicate this crowd consensus model outperforms averaging when it correctly identifies experts in the crowd, under the assumption that only experts have consistent evaluations. However, empirical results from a real human crowd indicate this assumption may not hold even on a simple engineering design evaluation task, as clusters of consistently wrong evaluators are shown to exist along with the cluster of experts. This suggests that both averaging evaluations and a crowd consensus model that relies only on evaluations may not be adequate for engineering design tasks, accordingly calling for further research into methods of finding experts within the crowd. [DOI: 10.1115/1.4029065]

We seek to elicit individual design preferences through human-computer interaction. During an iteration of the interactive session, the computer queries the subject by presenting a set of designs from which the subject must make a choice. The computer uses this choice feedback and creates the next set of designs using knowledge accumulated from previous choices. Under the hypothesis that human responses are deterministic, we discuss how query schemes in the elicitation task can be viewed mathematically as learning or optimization algorithms. Two query schemes are defined. Query type 1 considers the subject’s binary choices as definite preferences, i.e., only preferred designs are chosen, while others are skipped; query type 2 treats choices as comparisons among a set, i.e., preferred designs are chosen relative to those in the current set but may be dropped in future iterations. We show that query type 1 can be considered as an active learning problem, while type 2 as a “black-box” optimization problem. This paper concentrates on query type 2. Two algorithms based on support vector machine and efficient global optimization search are presented and discussed. Early user tests for vehicle exterior styling preference elicitation are also presented. [DOI: 10.1115/1.4005104]