Search

In recent years, carbon fiber reinforced plastics (CFRP) have attracted widespread attention in many industrial fields such as aerospace, automobiles, and high-speed railways. It has become a trend to replace traditional aluminum alloys and steels with CFRP in certain key components in order to achieve a better lightweight effect. However, due to the huge difference in the performance of metal materials and CFRP, problems such as unreasonable structural design and insufficient weight reduction may occur during the material replacement process. In order to solve the above problems, a progressive optimization method was proposed by this article. This progressive optimization method includes the conceptual design stage and the detailed design stage. The conceptual design stage includes modal analysis and topography optimization. The detailed design stage involves the weight reduction analysis of components, including the optimization of fiber layup angle, stacking sequence, and thickness. This article takes a CFRP key component as an example to verify the feasibility of the optimization method. Compared with the traditional method, using the optimization method, the structural stability of key components is improved. The weight reduction ratio of key components reaches 61.1%. Finally, a test sample was manufactured according to the optimized results by molding and RTM molding process, the actual weight reduction ratio is 57%, and the sample successfully passed the tests required by the relevant standards. These results indicate that the proposed progressive optimization method has great application potential in the design of CFRP lightweight structures in the aerospace field.

Feature matching is a long-standing fundamental and critical problem in computer vision and photogrammetry. The indirect matching strategy has become a popular choice because of its high precision and generality, but it finds only a limited number of correct matches, and the mismatch removal phase does not utilize the critical feature descriptors. To this end, this paper proposes a novel and effective feature matching method, named Progressive Smoothness Consensus (PSC). Our PSC designs an objective function to directly construct correct matches from two feature point sets. To optimize the objective, we introduce a stepwise strategy, where a small but reliable match set with the smooth function is used as initialization, and then the correct match set is iteratively enlarged and optimized by match expansion and smooth function estimation, respectively. In addition, the local geometric constraint is added to the compact representation with a Fourier basis, thus improving the estimation precision. We perform the match expansion as a Bayesian formulation to exploit both the spatial distribution and feature description information, thus finding feasible matches to expand the match set. Extensive experiments on feature matching, homography & fundamental matrix estimation, and image registration are conducted, which demonstrate the advantages of our PSC against state-of-the-art methods in terms of generality and effectiveness. Our code is publicly available at https://github.com/XiaYifan1999/Robust-feature-matching-via-Progressive-Smoothness-Consensus. [ABSTRACT FROM AUTHOR]

Skeleton-based action recognition is an essential yet challenging visual task, whose accuracy has been remarkably improved due to the successful application of graph convolutional networks (GCNs). However, high computation cost and memory usage hinder their deployment on resource-constrained environment. To deal with the issue, in this paper, we introduce two novel progressive binary graph convolutional network for skeleton-based action recognition PB-GCN and PB-GCN * , which can obtain significant speed-up and memory saving. In PB-GCN, the filters are binarized, and in PB-GCN * , both filters and activations are binary. Specifically, we propose a progressive optimization, i.e., employing ternary models as the initialization of binary GCNs (BGCN) to improve the representational capability of binary models. Moreover, the center loss is exploited to improve the training procedure for better performance. Experimental results on two public benchmarks (i.e., Skeleton-Kinetics and NTU RGB + D) demonstrate that the accuracy of the proposed PB-GCN and PB-GCN * are comparable to their full-precision counterparts and outperforms the state-of-the-art methods, such as BWN, XNOR-Net, and Bi-Real Net. [ABSTRACT FROM AUTHOR]

Universal Adversarial Perturbations(UAPs), which are image-agnostic adversarial perturbations, have been demonstrated to successfully deceive computer vision models. Proposed UAPs in the case of data-dependent, use the internal layers' activation or the output layer's decision values as supervision. In this paper, we use both of them to drive the supervised learning of UAP, termed as fully supervised UAP(FS-UAP), and design a progressive optimization strategy to solve the FS-UAP. Specifically, we define an internal layers supervised objective relying on multiple major internal layers' activation to estimate the deviations of adversarial examples from legitimate examples. We also define an output layer supervised objective relying on the logits of output layer to evaluate attacking degrees. In addition, we use the UAP found by previous stage as the initial solution of the next stage so as to progressively optimize the UAP stage-wise. We use seven networks and ImageNet dataset to evaluate the proposed FS-UAP, and provide an in-depth analysis for the latent factors affecting the performance of universal attacks. The experimental results show that our FS-UAP (i) has powerful capability of cheating CNNs (ii) has superior transfer-ability across models and weak data-dependent (iii) is appropriate for both untarget and target attacks. [ABSTRACT FROM AUTHOR]

Owing to the current serious environmental and climate problems, the energy industry must focus on the problem of energy utilization rates. High-temperature gas-cooled reactors (HTGRs) are fourth-generation reactors, characterized by high outlet temperatures. The combined cycle is composed of the gas turbine and steam turbine cycles, and it can realize the cascade utilization of high-quality energy. It is a highly competitive power conversion scheme for HTGRs. In this study, the matching characteristics of the combined cycle coupled with HTGRs are revealed through the progressive optimization method. In the combined cycle coupled with HTGRs, the topping and bottoming cycle are both closed cycles, therefore, the optimization for cycle efficiency is to match the topping and bottoming cycles. For a combined cycle with subcritical steam parameters, there are two extreme values of the combined cycle efficiency that have different power ratios. The characteristics revealed in this study are unique to closed combined cycle coupled with HTGRs.

Recently, convolutional neural networks (CNNs) have been successfully used for motor fault diagnosis because of its powerful feature extraction ability. However, there are still some barriers of traditional CNNs. Due to the fact of the hierarchical structure, feature resolution of CNNs will be reduced with layer growth, which can lead to the information loss. In addition, the fixed kernel size makes traditional CNNs not suitable for fault diagnosis of motors, which are widely used in nonstationary conditions. Therefore, starting from the physical characteristics of nonstationary vibration signals, a cascade CNN (C-CNN) with progressive optimization is proposed in this article. First, a cascade structure is built to avoid the information loss caused by consecutive convolution striding or pooling. Then, dilated convolution operations are implemented, which can extract the feature maps from different scales and extend the applications of CNN to nonstationary conditions. Furthermore, taking the advantage of the cascade structure, a progressive optimization algorithm is proposed for divide-and-conquer parameters optimization, which enables the C-CNN to converge to a more optimum state and improve the diagnosis performance. The proposed method is verified by two motor fault diagnosis experiments, which are conducted under constant speed and variable speed, respectively. The results show that the proposed method can achieve better performance when rotating speed is either constant or changing than exiting methods. [ABSTRACT FROM AUTHOR]

We present a novel feature matching algorithm that systematically utilizes the geometric properties of image features such as position, scale, and orientation, in addition to the conventional descriptor vectors. In challenging scenes, in which repetitive structures and large view changes are present, it is difficult to find correct correspondences using conventional approaches that only use descriptors, as the descriptor distances of correct matches may not be the least among the candidates. The feature matching problem is formulated as a Markov random field (MRF) that uses descriptor distances and relative geometric similarities together. Assuming that the layout of the nearby features does not considerably change, we propose the bidirectional transfer measure to gauge the geometric consistency between the pairs of feature correspondences. The unmatched features are explicitly modeled in the MRF to minimize their negative impact. Instead of solving the MRF on the entire features at once, we start with a small set of confident feature matches, and then progressively expand the MRF with the remaining candidate matches. The proposed progressive approach yields better feature matching performance and faster processing time. Experimental results show that the proposed algorithm provides better feature correspondences in many challenging scenes, i.e., more matches with higher inlier ratio and lower computational cost than those of the state-of-the-art algorithms. The source code of our implementation is open to the public. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Image & Graphics is the property of Editorial Office of Journal of Image & Graphics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Autonomous driving with artificial intelligence technology has been viewed as promising for autonomous vehicles hitting the road in the near future. In recent years, considerable progress has been made with Deep Reinforcement Learnings (DRLs) for realizing end-to-end autonomous driving. Still, driving safely and comfortably in real dynamic scenarios with DRL is nontrivial due to the reward functions being typically pre-defined with expertise. This paper proposes a human-in-the-loop DRL algorithm for learning personalized autonomous driving behavior in a progressive learning way. Specifically, a progressively optimized reward function (PORF) learning model is built and integrated into the Deep Deterministic Policy Gradient (DDPG) framework, which is called PORF-DDPG in this paper. PORF consists of two parts: the first part of the PORF is a pre-defined typical reward function on the system state, the second part is modeled as a Deep Neural Network (DNN) for representing driving adjusting intention by the human observer, which is the main contribution of this paper. The DNN-based reward model is progressively learned using the front-view images as the input and via active human supervision and intervention. The proposed approach is potentially useful for driving in dynamic constrained scenarios when dangerous collision events might occur frequently with classic DRLs. The experimental results show that the proposed autonomous driving behavior learning method exhibits online learning capability and environmental adaptability.

This paper presents an extraction and expansion approach for the graph coloring problem. The extraction phase transforms a large graph into a sequence of progressively smaller graphs by removing large independent sets from the graph. The expansion phase starts by generating an approximate coloring for the smallest graph in the sequence. Then it expands the smallest graph by progressively adding back the extracted independent sets and determine a coloring for each intermediate graph. To color each graph, a simple perturbation based tabu search algorithm is used. The proposed approach is evaluated on the DIMACS challenge benchmarks showing competitive results in comparison with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Abstract: Graph coloring is one of the most studied combinatorial optimization problems. This paper presents an improved extraction and expansion method (IE2COL), initially introduced in Wu and Hao (2012) . IE2COL employs a forward independent set extraction strategy to reduce the initial graph . From the reduced graph, IE2COL triggers a backward coloring process which uses extracted independent sets as new color classes for intermediate subgraph coloring. The proposed method is assessed on 20 large benchmark graphs with 900 to 4000 vertices. Computational results show that it provides new upper bounds for 6 graphs and consistently matches the current best-known results for 12 other graphs. [Copyright &y& Elsevier]

This article proposes an efficient gradient-based optimization procedure for black-box simulation codes and its application to the thermo-fluid-dynamic design optimization of a duct-burner for combined cycle and cogenerative plants. The article also provides a discussion on some criteria that should drive the design optimization of these components, almost neglected by the scientific literature. Using a widely employed commercial (black-box) code, a new enhanced-mixing duct-burner has been first devised. Before looking at its design optimization, experimental investigations have been performed to assess the reliability of the modelling and the accuracy of the numerical predictions. Then, a finite-difference gradient-based optimization procedure that can be combined with black-box analysis codes has been developed: its efficiency relies on the simultaneous convergence of the flow solution and of the optimization process, as well as on the use of nested grid levels. After its validation, the proposed progressive optimization technique has been applied to two examples of thermo-fluid-dynamic design optimization of the new duct-burner: the first application aims at minimizing the outlet temperature gradient, whereas the second application aims at reducing the near-wall temperatures and shortening the flame, so as to strengthen its anchorage, while reducing the body heating and the thermal NOx formation. [ABSTRACT FROM AUTHOR]

Autonomous driving with artificial intelligence technology has been viewed as promising for autonomous vehicles hitting the road in the near future. In recent years, considerable progress has been made with Deep Reinforcement Learnings (DRLs) for realizing end-to-end autonomous driving. Still, driving safely and comfortably in real dynamic scenarios with DRL is nontrivial due to the reward functions being typically pre-defined with expertise. This paper proposes a human-in-the-loop DRL algorithm for learning personalized autonomous driving behavior in a progressive learning way. Specifically, a progressively optimized reward function (PORF) learning model is built and integrated into the Deep Deterministic Policy Gradient (DDPG) framework, which is called PORF-DDPG in this paper. PORF consists of two parts: the first part of the PORF is a pre-defined typical reward function on the system state, the second part is modeled as a Deep Neural Network (DNN) for representing driving adjusting intention by the human observer, which is the main contribution of this paper. The DNN-based reward model is progressively learned using the front-view images as the input and via active human supervision and intervention. The proposed approach is potentially useful for driving in dynamic constrained scenarios when dangerous collision events might occur frequently with classic DRLs. The experimental results show that the proposed autonomous driving behavior learning method exhibits online learning capability and environmental adaptability. [ABSTRACT FROM AUTHOR]