Modern design problems present both opportunities and challenges, including multifunctionality, high dimensionality, highly nonlinear multimodal responses, and multiple levels or scales. These factors are particularly important in materials design problems and make it difficult for traditional optimization algorithms to search the space effectively, and designer intuition is often insufficient in problems of this complexity. Efficient machine learning algorithms can map complex design spaces to help designers quickly identify promising regions of the design space. In particular, Bayesian network classifiers (BNCs) have been demonstrated as effective tools for top-down design of complex multilevel problems. The most common instantiations of BNCs assume that all design variables are independent. This assumption reduces computational cost, but can limit accuracy especially in engineering problems with interacting factors. The ability to learn representative network structures from data could provide accurate maps of the design space with limited computational expense. Population-based stochastic optimization techniques such as genetic algorithms (GAs) are ideal for optimizing networks because they accommodate discrete, combinatorial, and multimodal problems. Our approach utilizes GAs to identify optimal networks based on limited training sets so that future test points can be classified as accurately and efficiently as possible. This method is first tested on a common machine learning data set, and then demonstrated on a sample design problem of a composite material subjected to a planar sound wave.
more »
« less
A Comparative Evaluation of Supervised Machine Learning Classification Techniques for Engineering Design Applications
Abstract Supervised machine learning techniques have proven to be effective tools for engineering design exploration and optimization applications, in which they are especially useful for mapping promising or feasible regions of the design space. The design space mappings can be used to inform early-stage design exploration, provide reliability assessments, and aid convergence in multiobjective or multilevel problems that require collaborative design teams. However, the accuracy of the mappings can vary based on problem factors such as the number of design variables, presence of discrete variables, multimodality of the underlying response function, and amount of training data available. Additionally, there are several useful machine learning algorithms available, and each has its own set of algorithmic hyperparameters that significantly affect accuracy and computational expense. This work elucidates the use of machine learning for engineering design exploration and optimization problems by investigating the performance of popular classification algorithms on a variety of example engineering optimization problems. The results are synthesized into a set of observations to provide engineers with intuition for applying these techniques to their own problems in the future, as well as recommendations based on problem type to aid engineers in algorithm selection and utilization.
more »
« less
- Award ID(s):
- 1641078
- NSF-PAR ID:
- 10176475
- Date Published:
- Journal Name:
- Journal of Mechanical Design
- Volume:
- 141
- Issue:
- 12
- ISSN:
- 1050-0472
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Abstract Background Problem exploration includes identifying, framing, and defining design problems and bounding problem spaces. Intentional and unintentional changes in problem understanding naturally occur as designers explore design problems to create solutions. Through problem exploration, new perspectives on the problem can emerge along with new and diverse ideas for solutions. By considering multiple problem perspectives varying in scope and focus, designers position themselves to increase their understandings of the “real” problem and engage in more diverse idea generation processes leading to an increasing variety of potential solutions.
Purpose/Hypothesis The purpose of this study was to investigate systematic patterns in problem exploration in the early design phases of mechanical engineers.
Design/Method Thirty‐five senior undergraduate students and experienced designers with mechanical engineering backgrounds worked individually following a think‐aloud protocol. They explored problems and generated solutions for two of four randomly assigned design problems. After generating solutions, participants framed and rewrote problem statements to reflect their perspectives on the design problem their solutions addressed. Thematic analysis and a priori codes guided the identification of problem exploration patterns within and across problems.
Results The set of patterns in engineers' problem exploration that emerged from the analysis documents alternative strategies in exploring problems to arrive at solutions. The results provide evidence that engineering designers, working individually, apply both problem‐specific and more general strategies to explore design problems.
Conclusions Our study identified common patterns in the explorations of presented problems by individual engineering designers. The observed patterns, described as Problem Exploration Perspectives, capture alternative approaches to discovering problems and taking multiple problem perspectives during design. Learning about Problem Exploration Perspectives may be helpful in creating alternative perspectives on a design problem, potentially leading to more varied and innovative solutions. This paper concludes with an extended example illustrating the process of applying Problem Exploration Perspectives to move between problem perspectives to generate varied design outcomes.
-
Learned optimization algorithms are promising approaches to inverse problems by leveraging advanced numerical optimization schemes and deep neural network techniques in machine learning. In this paper, we propose a novel deep neural network architecture imitating an extra proximal gradient algorithm to solve a general class of inverse problems with a focus on applications in image reconstruction. The proposed network features learned regularization that incorporates adaptive sparsification mappings, robust shrinkage selections, and nonlocal operators to improve solution quality. Numerical results demonstrate the improved efficiency and accuracy of the proposed network over several state-of-the-art methods on a variety of test problems.more » « less
-
Binary classification is a fundamental machine learning task defined as correctly assigning new objects to one of two groups based on a set of training objects. Driven by the practical importance of binary classification, numerous machine learning techniques have been developed and refined over the last three decades. Among the most popular techniques are artificial neural networks, decision trees, ensemble methods, logistic regression, and support vector machines. We present here machine learning and pattern recognition algorithms that, unlike the commonly used techniques, are based on combinatorial optimization and make use of information on pairwise relations between the objects of the data set, whether training objects or not. These algorithms solve the respective problems optimally and efficiently, in contrast to the primarily heuristic approaches currently used for intractable problem models in pattern recognition and machine learning. The algorithms described solve efficiently the classification problem as a network flow problem on a graph. The technical tools used in the algorithm are the parametric cut procedure and a process called sparse computation that computes only the pairwise similarities that are “relevant.” Sparse computation enables the scalability of any algorithm that uses pairwise similarities. We present evidence on the effectiveness of the approaches, measured in terms of accuracy and running time, in pattern recognition, image segmentation, and general data mining.more » « less
-
null (Ed.)In the recent years, there is a growing interest in using quantum computers for solving combinatorial optimization problems. In this work, we developed a generic, machine learning-based framework for mapping continuous-space inverse design problems into surrogate quadratic unconstrained binary optimization (QUBO) problems by employing a binary variational autoencoder and a factorization machine. The factorization machine is trained as a low-dimensional, binary surrogate model for the continuous design space and sampled using various QUBO samplers. Using the D-Wave Advantage hybrid sampler and simulated annealing, we demonstrate that by repeated resampling and retraining of the factorization machine, our framework finds designs that exhibit figures of merit exceeding those of its training set. We showcase the framework’s performance on two inverse design problems by optimizing (i) thermal emitter topologies for thermophotovoltaic applications and (ii) diffractive meta-gratings for highly efficient beam steering. This technique can be further scaled to leverage future developments in quantum optimization to solve advanced inverse design problems for science and engineering applications.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1115/1.4044524
