The present work presents a novel approach for semi-analytic adjoint sensitivity-based design optimization for nonproportional fatigue damage. In order to apply fatigue damage in sensitivity-based design optimizations...
详细信息
The present work presents a novel approach for semi-analytic adjoint sensitivity-based design optimization for nonproportional fatigue damage. In order to apply fatigue damage in sensitivity-based design optimizations, an essential part is to calculate correct sensitivities. However, this is not straight forward since fatigue damage calculation typically include rainflow counting and critical plane search algorithms. Therefore, no derivatives are directly available for the fatigue damage calculation, only functional values given by numerical computation. In existing literature the considered fatigue damage calculation is simplified until a closed-form differentiability is satisfied. However, these simplifications are not applicable for industrial examples where accurate fatigue life estimates are required. In the present work numerical differentiation of the fatigue damage values with respect to the stress tensor is applied to calculate semi-analytical adjoint sensitivities at material points for multiple load cases. The proposed method is verified and demonstrated using different damage parameter types including critical plane analysis. Additionally, different academic and industrial numerical examples are compared to stress and stiffness optimized designs. The fatigue damage optimized designs show improved fatigue damage results for both the specific damage parameter types and when comparing to stress and stiffness optimized designs. Furthermore, it is successfully applied for different design variables (sizing, nonparametric shape and bead) as well as different optimization formulations using fatigue damage either as objective or constraint.
Programming robot behavior remains a challenging task. While it is often easy to abstractly define or even demonstrate a desired behavior, designing a controller that embodies the same behavior is difficult, time cons...
详细信息
Programming robot behavior remains a challenging task. While it is often easy to abstractly define or even demonstrate a desired behavior, designing a controller that embodies the same behavior is difficult, time consuming, and ultimately expensive. The machine learning paradigm offers the promise of enabling "programming by demonstration" for developing high-performance robotic systems. Unfortunately, many "behavioral cloning" (Bain and Sammut in Machine intelligence agents. London: Oxford University Press, 1995;Pomerleau in Advances in neural information processing systems 1, 1989;LeCun et al. in Advances in neural information processing systems 18, 2006) approaches that utilize classical tools of supervised learning (e.g. decision trees, neural networks, or support vector machines) do not fit the needs of modern robotic systems. These systems are often built atop sophisticated planning algorithms that efficiently reason far into the future;consequently, ignoring these planning algorithms in lieu of a supervised learning approach often leads to myopic and poor-quality robot performance. While planning algorithms have shown success in many real-world applications ranging from legged locomotion (Chestnutt et al. in Proceedings of the IEEE-RAS international conference on humanoid robots, 2003) to outdoor unstructured navigation (Kelly et al. in Proceedings of the international symposium on experimental robotics (ISER), 2004;Stentz et al. in AUVSI's unmanned systems, 2007), such algorithms rely on fully specified cost functions that map sensor readings and environment models to quantifiable costs. Such cost functions are usually manually designed and programmed. Recently, a set of techniques has been developed that explore learning these functions from expert human demonstration. These algorithms apply an inverse optimal control approach to find a cost function for which planned behavior mimics an expert's demonstration. The work we present extends the Maximum Margin
For approximate nearest neighbor (ANN) search in many vision-based applications, vector quantization (VQ) is an efficient compact encoding technology. A representative approach of VQ is product quantization (PQ) which...
详细信息
For approximate nearest neighbor (ANN) search in many vision-based applications, vector quantization (VQ) is an efficient compact encoding technology. A representative approach of VQ is product quantization (PQ) which quantizes subspaces separately by Cartesian product and achieves high accuracy. But its space decomposition still leads to quantization distortion. This paper presents two optimized solutions based on residual vector quantization (RVQ). Different from PQ RVQ simulates restoring quantization error by multi-stage quantizers instead of decomposing it. To further optimize codebook and space decomposition, we try to get a better discriminated space projection. Then an orthonormal matrix R is generated. The RVQ's nonparametric solution alternately optimizes R and stage-codebooks by Singular Value Decomposition (SVD) in multiple iterations. The RVQs parametric solution assumes that data are subject to Gaussian distribution and uses Eigenvalue Allocation to get each, stage-matrix (R-1} (1 <= l <= L) at once, where L is the stage number of RVQ. Compared to various optimized PQ-based methods, our methods have good superiority on restoring quantization error. (C) 2016 Elsevier B.V. All rights reserved.
暂无评论