Influence of Flank Wear on the Microstructure Characteristics of the GH4169 Metamorphic Layer under High-Pressure Cooling.

Since the flank has an important influence on the surface of a workpiece, and as microstructure flaws of the surface metamorphic layer are a key factor that affects the service performance of a part, this work studied the influence of flank wear on the microstructure characteristics of the metamorphic layer under the conditions of high-pressure cooling. First, Third Wave AdvantEdge was used to create a simulation model of cutting GH4169 using tools with different flank wears under high-pressure cooling. The simulation findings emphasized the impact of flank wear width (VB) on the cutting force, cutting temperature, plastic strain, and strain rate. Second, an experimental platform was established for cutting GH4169 under high-pressure cooling, and the cutting force during the machining process was recorded in real time and compared with the simulation results. Finally, an optical microscope was used to observe the metallographic structure of the GH4169 workpiece section. The microstructure characteristics of the workpiece were analyzed using a scanning electron microscope (SEM) and electron backscattered diffraction (EBSD). It was discovered that, as the flank wear width increased, so did the cutting force, cutting temperature, plastic strain, strain rate, and plastic deformation depth. The relative error between the simulation results of the cutting force and the experimental results was within 15%. At the same time, near the surface of the workpiece, there was a metamorphic layer with fuzzy grain boundaries and refined grain. With an increase in flank wear width, the thickness of the metamorphic layer increased from 4.5 µm to 8.7 µm and the grain refinement intensified. The high strain rate promoted recrystallization, which caused an increase in the average grain boundary misorientation and high-angle grain boundaries, as well as a reduction in twin boundaries.

Discriminative Suprasphere Embedding for Fine-Grained Visual Categorization.

Despite the great success of the existing work in fine-grained visual categorization (FGVC), there are still several unsolved challenges, e.g., poor interpretation and vagueness contribution. To circumvent this drawback, motivated by the hypersphere embedding method, we propose a discriminative suprasphere embedding (DSE) framework, which can provide intuitive geometric interpretation and effectively extract discriminative features. Specifically, DSE consists of three modules. The first module is a suprasphere embedding (SE) block, which learns discriminative information by emphasizing weight and phase. The second module is a phase activation map (PAM) used to analyze the contribution of local descriptors to the suprasphere feature representation, which uniformly highlights the object region and exhibits remarkable object localization capability. The last module is a class contribution map (CCM), which quantitatively analyzes the network classification decision and provides insight into the domain knowledge about classified objects. Comprehensive experiments on three benchmark datasets demonstrate the effectiveness of our proposed method in comparison with state-of-the-art methods.

Prediction scale of cerebrovascular disease subtypes for high-risk population. / è„‘è¡€ç®¡ç— äºšåž‹é«˜å±äººç¾¤çš„é¢„æµ‹é‡è¡¨.

OBJECTIVES: Cerebrovascular disease can be roughly divided into 2 subtypes: Cerebral ischemia (CI) and cerebral hemorrhage (CH). No scale currently exist that can predict the subtypes of cerebrovascular diseases. This study aims to establish a prediction scale for the subtypes of cerebrovascular diseases. METHODS: A total of 1 200 cerebrovascular disease patients were included in this study, data from 1 081 (90%) patients were used to establish the CI-CH risk scale, and data from 119 (10%) patients were used to test it. Risk factors for the CI-CH risk scale were identified by 2 screens, with two-tailed student's t-test and two-tailed Fisher's exact test preliminarily and with logistic regression analysis further. The scores of each risk factor for CI-CH risk scale were determined according to the odds rate, and the cut-off point was determined by Youden index. RESULTS: Nine risk factors were ultimately selected for score system, including age (≥75 years old was -1, <75 years old was 0), BMI (<24 kg/m2 was 0, 24-28 kg/m2 was -1, >28 kg/m2 was -2), hypertension grade (grade 1 was 1, grade 2 was 2, and grade 3 was 3), diabetes status (no was 0, yes was -1), antihypertensive drug use (no was 0, yes was -2), alcohol consumption (<60 g/d was 1, ≥60 g/d was 2), uric acid (less than normal was 0, normal was -1, high than normal was -2), LDL cholesterol (<2 mmol/L was 0, 2-4 mmol/L was -1, and >4 mmol/L was -2), and HDL cholesterol (<1.55 mmol/L was 0, ≥1.55 mmol/L was 2). Patients with a score more than 0 were classified as the CH group, Conversely, they were assigned to the CI group; its sensitivity, specificity, and accuracy were 74.5%, 77.9%, and 76.4%, respectively. CONCLUSIONS: The CI-CH risk scale can help the clinician predict the subtypes of cerebrovascular diseases.

Modal-Regression-Based Structured Low-Rank Matrix Recovery for Multiview Learning.

Low-rank Multiview Subspace Learning (LMvSL) has shown great potential in cross-view classification in recent years. Despite their empirical success, existing LMvSL-based methods are incapable of handling well view discrepancy and discriminancy simultaneously, which, thus, leads to performance degradation when there is a large discrepancy among multiview data. To circumvent this drawback, motivated by the block-diagonal representation learning, we propose structured low-rank matrix recovery (SLMR), a unique method of effectively removing view discrepancy and improving discriminancy through the recovery of the structured low-rank matrix. Furthermore, recent low-rank modeling provides a satisfactory solution to address the data contaminated by the predefined assumptions of noise distribution, such as Gaussian or Laplacian distribution. However, these models are not practical, since complicated noise in practice may violate those assumptions and the distribution is generally unknown in advance. To alleviate such a limitation, modal regression is elegantly incorporated into the framework of SLMR (termed MR-SLMR). Different from previous LMvSL-based methods, our MR-SLMR can handle any zero-mode noise variable that contains a wide range of noise, such as Gaussian noise, random noise, and outliers. The alternating direction method of multipliers (ADMM) framework and half-quadratic theory are used to optimize efficiently MR-SLMR. Experimental results on four public databases demonstrate the superiority of MR-SLMR and its robustness to complicated noise.

Multiview Hybrid Embedding: A Divide-and-Conquer Approach.

We present a novel cross-view classification algorithm where the gallery and probe data come from different views. A popular approach to tackle this problem is the multiview subspace learning (MvSL) that aims to learn a latent subspace shared by multiview data. Despite promising results obtained on some applications, the performance of existing methods deteriorates dramatically when the multiview data is sampled from nonlinear manifolds or suffers from heavy outliers. To circumvent this drawback, motivated by the Divide-and-Conquer strategy, we propose multiview hybrid embedding (MvHE), a unique method of dividing the problem of cross-view classification into three subproblems and building one model for each subproblem. Specifically, the first model is designed to remove view discrepancy, whereas the second and third models attempt to discover the intrinsic nonlinear structure and to increase the discriminability in intraview and interview samples, respectively. The kernel extension is conducted to further boost the representation power of MvHE. Extensive experiments are conducted on four benchmark datasets. Our methods demonstrate the overwhelming advantages against the state-of-the-art MvSL-based cross-view classification approaches in terms of classification accuracy and robustness.