Search

The air radiator had been in service for more than 30 years until a notch failure occurred. In this paper, a rare notch failure is completely investigated by means of macroscopic and microscopic observations, microstructural inspection, chemical analysis, and residual stress test. The results show that the notch failure mode of the air radiator is attributed to high-cycle fatigue fracture, due to the welded lapping surfaces near the notch on both sides of the corrugated plate trough not being put onto one plane during the welding process. Therefore, in order to prevent or reduce possible tensile stress, it is recommended that the welded lapping surfaces be put onto one plane before welding.

Aims: We aimed to examine the association of gestational hypertension and chronic hypertension at the inter-conception examination with type 2 diabetes risk among women with a history of gestational diabetes. Methods: We conducted a population-based study among 1261 women who had a history of gestational diabetes at 1-5 years after delivery in Tianjin, China. Logistic regression or Cox regression was used to assess the associations of gestational hypertension and chronic hypertension at the inter-conception examination with pre-diabetes and type 2 diabetes risks. Results: Gestational diabetic women who had a history of gestational hypertension but did not use antihypertensive drugs during pregnancy had a 3.94-fold higher risk (95% CI: 1.94-8.02) of developing type 2 diabetes compared with those who were normotensive in index pregnancy. Compared with gestational diabetic women who had normal blood pressure at the inter-conception examination, hypertensive women at the inter-conception examination were 3.38 times (95% CI: 1.66-6.87) and 2.97 times (95% CI: 1.75-5.05) more likely to develop diabetes and prediabetes, respectively. The odds ratios of type 2 diabetes and prediabetes associated with each 5 mmHg increase in systolic blood pressure were 125 (95% CI: 1.03-1.51) and 120 (95% CI: 1.06-135). Each 5 mmHg increase in diastolic blood pressure contributed to a 1.49-fold higher risk (95% CI: 1.18-1.88) for type 2 diabetes and a 1.42-fold higher risk (95% CI: 1.22-1.65) for prediabetes. Conclusions: For women with prior gestational diabetes, gestational hypertension and chronic hypertension at the inter-conception examination were risk factors for type 2 diabetes. (C) 2016 Elsevier Inc. All rights reserved.

The paper presents a failure case of an aero-engine combustor liner. Macroscopic and microscopic observations, microstructure investigation, chemical analysis and hardness measurement have been performed to investigate the damage mechanism and failure causes of notches and cracks. The results show that the failure modes of notches, axial-direction crack along the combustor liner and crack at the edge of welding spot are respectively attributed to high-temperature ablation, mixed crack of ablation and thermal fatigue crack. The bad configuration of crossover tube is the main reason for the failure of combustor liner.

The paper presents a failure analysis of components damaged in compressor vane. In order to investigate the damage mechanism and failure causes of components, macroscopic and microscopic observations, microstructural investigations, chemical analysis and hardness measurement have been performed. The results show that the damaged components are caused by fractured blades of 1st stage rotor. In all 1st stage rotor blades, 1 # blade is fractured firstly, and is troublemaker in this incident. The fracture mechanism of 1 # blade fractured from blade root is due to first order bending vibration fatigue damage. The microstructure, hardness and chemical compositions of 1 # blade fracture, all which coincide with technical requirements. The bad shot peening qualities in the surface near blade fracture have important influence on fatigue failure.

A self-calibration method to estimate a camera's intrinsic and extrinsic parameters from vertical line segments of the same height is presented. An algorithm to obtain the needed line segments by detecting the head and feet positions of a walking human in his leg-crossing phases is described. Experimental results show that the method is accurate and robust with respect to various viewing angles and subjects.

An apparatus comprises a processor configured to: process, automatically and in real time, segmentation of a video object from a portion of a video, wherein the video object is a foreground of the video, and wherein a remaining portion of the video is a background of the video; and remove the background.

To determine the root cause of through-hole cracking in a flange, detailed methods, including macroscopic and microscopic inspection, microstructural investigations, chemical analysis, hardness measurement, simulation experimentation, and analytic calculations were carried out, in this study. The results show that the cracking was due to overload which was caused by impact. The crack formed in the time period before chromic acid anodization and machining, and the impact stress originated from conveying and revolving transportations. The microstructure, hardness, and chemical compositions of intermediate casing flange all coincide with technical requirements.

Most research efforts on image classification so far have been focused on medium-scale datasets, which are often defined as datasets that can fit into the memory of a desktop (typically 4G∼48G). There are two main reasons for the limited effort on large-scale image classification. First, until the emergence of ImageNet dataset, there was almost no publicly available large-scale benchmark data for image classification. This is mostly because class labels are expensive to obtain. Second, large-scale classification is hard because it poses more challenges than its medium-scale counterparts. A key challenge is how to achieve efficiency in both feature extraction and classifier training without compromising performance. This paper is to show how we address this challenge using ImageNet dataset as an example. For feature extraction, we develop a Hadoop scheme that performs feature extraction in parallel using hundreds of mappers. This allows us to extract fairly sophisticated features (with dimensions being hundreds of thousands) on 1.2 million images within one day. For SVM training, we develop a parallel averaging stochastic gradient descent (ASGD) algorithm for training one-against-all 1000-class SVM classifiers. The ASGD algorithm is capable of dealing with terabytes of training data and converges very fast–typically 5 epochs are sufficient. As a result, we achieve state-of-the-art performance on the ImageNet 1000-class classification, i.e., 52.9% in classification accuracy and 71.8% in top 5 hit rate.

We present a framework for unsupervised image categorization in which images containing specific objects are taken as vertices in a hypergraph and the task of image clustering is formulated as the problem of hypergraph partition. First, a novel method is proposed to select the region of interest (ROI) of each image, and then hyperedges are constructed based on shape and appearance features extracted from the ROIs. Each vertex (image) and its k-nearest neighbors (based on shape or appearance descriptors) form two kinds of hyperedges. The weight of a hyperedge is computed as the sum of the pairwise affinities within the hyperedge. Through all of the hyperedges, not only the local grouping relationships among the images are described, but also the merits of the shape and appearance characteristics are integrated together to enhance the clustering performance. Finally, a generalized spectral clustering technique is used to solve the hypergraph partition problem. We compare the proposed method to several methods and its effectiveness is demonstrated by extensive experiments on three image databases.

The traditional SPM approach based on bag-of-features (BoF) requires nonlinear classifiers to achieve good image classification performance. This paper presents a simple but effective coding scheme called Locality-constrained Linear Coding (LLC) in place of the VQ coding in traditional SPM. LLC utilizes the locality constraints to project each descriptor into its local-coordinate system, and the projected coordinates are integrated by max pooling to generate the final representation. With linear classifier, the proposed approach performs remarkably better than the traditional nonlinear SPM, achieving state-of-the-art performance on several benchmarks. Compared with the sparse coding strategy [22], the objective function used by LLC has an analytical solution. In addition, the paper proposes a fast approximated LLC method by first performing a K-nearest-neighbor search and then solving a constrained least square fitting problem, bearing computational complexity of O(M + K2). Hence even with very large codebooks, our system can still process multiple frames per second. This efficiency significantly adds to the practical values of LLC for real applications.

In this paper, we investigate the detection of semantic human actions in complex scenes. Unlike conventional action recognition in well-controlled environments, action detection in complex scenes suffers from cluttered backgrounds, heavy crowds, occluded bodies, and spatial-temporal boundary ambiguities caused by imperfect human detection and tracking. Conventional algorithms are likely to fail with such spatial-temporal ambiguities. In this work, the candidate regions of an action are treated as a bag of instances. Then a novel multiple-instance learning framework, named SMILE-SVM (Simulated annealing Multiple Instance LEarning Support Vector Machines), is presented for learning human action detector based on imprecise action locations. SMILE-SVM is extensively evaluated with satisfactory performances on two tasks: 1) human action detection on a public video action database with cluttered backgrounds, and 2) a real world problem of detecting whether the customers in a shopping mall show an intention to purchase the merchandise on shelf (even if they didn't buy it eventually). In addition, the complementary nature of motion and appearance features in action detection are also validated, demonstrating a boosted performance in our experiments.

Recent years have witnessed significant progress in detection of basic human actions. However, most existing methods rely on assumptions such as known spatial locations and temporal segmentations or employ very computationally expensive approaches such as sliding window search through a spatio-temporal volume. It is difficult for such methods to scale up to handle the challenges in real applications such as video surveillance. In this paper, we present an efficient and practical approach to detecting basic human actions, such as making cell phone calls, putting down objects, and hand-pointing, which has been extensively tested on the challenging 2008 TRECVID surveillance event detection dataset . We propose a novel action representation scheme using a set of motion edge history images, which not only encodes both shape and motion patterns of actions without relying on precise alignment of human figures, but also facilitates learning of fast tree-structured boosting classifiers. Our approach is robust with respect to cluttered background as well as scale and viewpoint changes. It is also computationally efficient by taking advantage of human detection and tracking to reduce the searching space. We demonstrate promising results on the 50-hour TRECVID development set as well as two other widely-used benchmark datasets of action recognition, i.e. the KTH dataset and the Weizmann dataset.

Aero-engine blades always failure due to impact of foreign object damage in service. Damnification and consequent fracture failure of blade is one of the main failure modes for the compressor blades in aero-engine. Damage characteristic on blades caused by different kind of material are various. Observation on damaged surfaces, trace analysis and surface element analysis by means of SEM and X-ray energy spectrum are effective methods to estimate the attribute, component and outline of foreign object. In this paper, analysis on several cases of FOD are introduced. The features, principles and rules of several typical FOD modes are summarized through failure cases analysis.

Our goal is to automatically segment and recognize basic human actions, such as stand, walk and wave hands, from a sequence of joint positions or pose angles. Such recognition is difficult due to high dimensionality of the data and large spatial and temporal variations in the same action. We decompose the high dimensional 3-D joint space into a set of feature spaces where each feature corresponds to the motion of a single joint or combination of related multiple joints. For each feature, the dynamics of each action class is learned with one HMM. Given a sequence, the observation probability is computed in each HMM and a weak classifier for that feature is formed based on those probabilities. The weak classifiers with strong discriminative power are then combined by the Multi-Class AdaBoost (AdaBoost.M2) algorithm. A dynamic programming algorithm is applied to segment and recognize actions simultaneously. Results of recognizing 22 actions on a large number of motion capture sequences as well as several annotated and automatically tracked sequences show the effectiveness of the proposed algorithms.

Segmenting and tracking multiple humans is a challenging problem in complex situations in which extended occlusion, shadow and/or reflection exists. We tackle this problem with a 3D model-based approach. Our method includes two stages, segmentation (detection) and tracking. Human hypotheses are generated by shape analysis of the foreground blobs using a human shape model. The segmented human hypotheses are tracked with a Kalman filter with explicit handling of occlusion. Hypotheses are verified while being tracked for the first second or so. The verification is done by walking recognition using an articulated human walking model. We propose a new method to recognize walking using a motion template and temporal integration. Experiments show that our approach works robustly in very challenging sequences.