scholarly journals LETR: An End-to-End Detector of Reconstruction Area in Blade’s Adaptive Machining with Transformer

2022 ◽  
Author(s):  
Zikai Yin ◽  
Yonghou Liang ◽  
Junxue Ren ◽  
Jungang An ◽  
Famei He
Keyword(s):  
Activation Function ◽  
Aerodynamic Performance ◽  
Image Features ◽  
The Self ◽  
Test Results ◽  
Baseline Model ◽  
Trailing Edge ◽  
Reconstruction Process ◽  
Mixed Frequency ◽  
Adaptive Machining

In the leading/trailing edge’s adaptive machining of the near-net-shaped blade, a small portion of the theoretical part is retained for securing aerodynamic performance by manual work. However, this procedure is time-consuming and depends on the human experience. In this paper, we defined retained theoretical leading/trailing edge as the reconstruction area. To accelerate the reconstruction process, an anchor-free neural network model based on Transformer was proposed, named LETR (Leading/trailing Edge Transformer). LETR extracts image features from an aspect of mixed frequency and channel domain. We also integrated LETR with the newest meta-Acon activation function. We tested our model on the self-made dataset LDEG2021 on a single GPU and got an mAP of 91.9\%, which surpassed our baseline model, Deformable DETR by 1.1\%. Furthermore, we modified LETR’s convolution layer and named the new model after GLETR (Ghost Leading/trailing Edge Transformer) as a lightweight model for real-time detection. It is proved that GLETR has fewer weight parameters and converges faster than LETR with an acceptable decrease in mAP (0.1\%) by test results.

scholarly journals Optical Navigation Sensor for Runway Relative Positioning of Aircraft during Final Approach

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2203
Author(s):  
Antal Hiba ◽  
Attila Gáti ◽  
Augustin Manecy
Keyword(s):  
Optical Sensors ◽  
Inertial Sensor ◽  
Image Data ◽  
Flight Test ◽  
Image Features ◽  
Wide Field ◽  
Test Results ◽  
Wide Field Of View ◽  
Final Approach ◽  
Marker Detection

Precise navigation is often performed by sensor fusion of different sensors. Among these sensors, optical sensors use image features to obtain the position and attitude of the camera. Runway relative navigation during final approach is a special case where robust and continuous detection of the runway is required. This paper presents a robust threshold marker detection method for monocular cameras and introduces an on-board real-time implementation with flight test results. Results with narrow and wide field-of-view optics are compared. The image processing approach is also evaluated on image data captured by a different on-board system. The pure optical approach of this paper increases sensor redundancy because it does not require input from an inertial sensor as most of the robust runway detectors.

Physiotherapists are knowledgeable about sport-related concussion

2021 ◽  
pp. 1-8
Author(s):  
Wesam Saleh A. Al Attar ◽  
Mohamed A. Husain
Keyword(s):  
Preventive Measures ◽  
The Self ◽  
American Football ◽  
Average Score ◽  
Test Results ◽  
Management Guidelines ◽  
Case Identification ◽  
Bachelors Degree ◽  
Doctor Of Philosophy ◽  
Post Hoc

PURPOSE: Sport-related concussions (SRC) are common, especially in rugby (3.00 incidents per 1000 athletic exposures) and American football (0.08 per 1000 athletic exposures). Physiotherapists should be aware of how to assess and manage cases with SRC. The purpose of this study was to assess the knowledge of SRC among physiotherapists. METHODS: The self-administered survey consisted of 16 questions related to physiotherapists’ knowledge in managing SRC patients, case identification, and preventive measures. Countries were divided into regions based on World Physiotherapy regions. Data were analysed using a one-way Analysis of Variance (ANOVA) with Tamhane’s T2 post hoc test. RESULTS: A total of 276 male (53.4 %) and 241 female (46.6%) physiotherapists participated. The survey scores ranged from 40%to 100%, with an average score of 62.7%. A master’s degree was the highest educational qualification (46.4%) recorded. There was a difference in the score based on participant qualifications (Welch’s F (4, 58.37) = 15.03, p <  0.001). Participants with a Doctor of Philosophy (PhD) degree (73.8±14.6%) or a fellowship (73.0±19.5%) or a masters’ degree (MSc) (62.7±18.5%) obtained greater scores than participants holding a bachelors’ degree (56.7±13.8%, p <  0.001). Furthermore, there was no difference in the survey score based on participants’ region (Welch’s F (4, 143.3) = 0.08, p = 0.988). CONCLUSIONS: The results suggested that many physiotherapists worldwide are aware of the current SRC assessment and management guidelines.

Construction Technology Research of RC Beams Strengthened with Prestressed CFRP Plates

2011 ◽  
Vol 268-270 ◽  
pp. 659-663
Author(s):  
Hua Chen ◽  
Kan Kang ◽  
Lang Ni Deng
Keyword(s):  
Crack Resistance ◽  
Concrete Beams ◽  
High Strength ◽  
The Self ◽  
Bending Test ◽  
Construction Technology ◽  
Rc Beams ◽  
Test Results ◽  
Technology Research ◽  
Flexural Capacity

The method of applying prestress to CFRP plates can make full use of the characteristics of high-strength, enhance the force properties, prevent peeling damage and reduce the strain lag. Construction technology of prestressed CFRP plates strengthening reinforcement concrete beams was introduce in this paper, and bending test of 6 reinforcement concrete beams strengthened with prestressed CFRP plates were carried out based on the self-developed prestressed CFRP plates supporting anchorages. The test results indicate that the flexural capacity and crack resistance capacity can be increased compared with non-prestressed CFRP plates, and the construction technology can be adopted in practical projects.

APPLICATION OF SCALE ADAPTIVE SIMULATION MODEL TO STUDYING COOLING CHARACTERISTICS OF A HIGH PRESSURE TURBINE BLADE CUTBACK TRAILING EDGE WITH DIFFERENT COOLING CONFIGURATIONS

2021 ◽  
pp. 1-53
Author(s):  
Yuefeng Li ◽  
Huazhao Xu ◽  
Jianhua Wang ◽  
Wei Song ◽  
Ming Wang ◽  
...  
Keyword(s):  
High Pressure ◽  
High Pressure Turbine ◽  
Baseline Model ◽  
Trailing Edge ◽  
Cooling Effectiveness ◽  
Adaptive Simulation ◽  
Rear Part ◽  
Pin Fins ◽  
A Minor ◽  
Better Than

Abstract This paper adopted Scale Adaptive Simulation (SAS) to investigate fluid flow and cooling characteristics in detail downstream of a high pressure turbine (HPT) blade trailing edge (TE) cutback region. The effects of typical TE configurations on cutback cooling performance are investigated including three types of internal turbulators, the cutback with/without land extensions and three kinds of ejection lip profiles. The elliptic pin fins with streamwise orientation significantly improve ηaw at the rear part of the cutback surface over the baseline model with cylindrical pin fins and slightly increase Cd. However, the elliptic pin fins with spanwise orientation drastically reduce the ηaw and Cd. Downstream of the cutback, the coherent structures are strongly disturbed and become chaotic compared to the TE with cylindrical and streamwise oriented elliptic pin fins. The application of land extensions only causes an evident change to the coherent structure immediate downstream of the lip, and slightly improves ηaw and reduces Cd over the baseline model on the rear part of the cutback surface. Rounded lip shapes B and C also show an obvious increase in ηaw on the rear part of the cutback surface but only a minor increase in Cd compared to the straight lip shape A. The rounded lip helps the coolant diffuse into the TE cutback and reduce the intensity of mixing. Due to larger rounding radius of shape B, the cooling effectiveness predicted by shape B is slightly better than shape C.

Geometry and Aerodynamic Performance of Parabolic Trailing-Edge Flaps

2018 ◽  
Author(s):  
Douglas F. Hunsaker ◽  
Jackson T. Reid ◽  
Bruno Moorthamers ◽  
James J. Joo
Keyword(s):  
Aerodynamic Performance ◽  
Trailing Edge ◽  
Trailing Edge Flaps

Numerical Investigation of Pin-Fin Influences on Cooling Air Flow Characteristics in Blade Trailing Edge Region

2019 ◽  
Author(s):  
Weilong Wu ◽  
Huazhao Xu ◽  
Jianhua Wang ◽  
Xiangyu Wu ◽  
Lei Wang
Keyword(s):  
Turbine Blade ◽  
Flow Characteristics ◽  
Baseline Model ◽  
Trailing Edge ◽  
Performance Function ◽  
Pin Fin ◽  
Low Pressure Turbine ◽  
Pin Fins ◽  
Turbine Design ◽  
Cooling Air

Abstract This paper numerically investigated the influences of pin-fin size and layout on the flow characteristics of cooling air in the trailing edge of a real low pressure turbine blade. The discussion was given first for the baseline model without pin fins (denoted as M0) under a turbine design condition and two off design conditions. Then a comparison of the flow fields in the turbine blade especially in the trailing edge region was performed with three more trailing edge models, with the purpose of discovering the benefits of using pin fin configurations in a real low pressure turbine blade. The other three models (denoted as M1, M2, M3) have pin fins in different diameters and arrangements. The M1 model has a row of 13 pin fins with a diameter of 2mm, and the M2 and M3 models have two rows of pin fins arranged in a staggered pattern with a diameter of 1.2mm. Compared to the baseline model M0, it is shown that an addition of pin fin configurations helps greatly to improve cooling flow distributions and to mitigate the blockage of coolant in trailing slots. Meanwhile, the adoption of pin fins has not only affected significantly the flow field in the trailing passage but also has moderately affected flow fields in the middle and forward cooling passages. Increasing pressure ratio can increase total mass flow rate with no significant change in flow patterns. The baseline blade Model M0 shows a high value of 6 for a friction loss related performance function at the turbine design condition. However, only a moderate increase in the value of the performance function is discovered for all the three blades with pin fins.

Image super-resolution based on multi-grained cascade forests

2019 ◽  
Vol 17 (04) ◽  
pp. 1950019
Author(s):  
Yaming Wang ◽  
Zhikang Luo ◽  
Weqing Huang ◽  
Yonghua Han
Keyword(s):  
Super Resolution ◽  
Image Features ◽  
Divide And Conquer ◽  
Learning Ability ◽  
Generalization Capability ◽  
Reconstruction Process ◽  
High Quality Image ◽  
Reconstruction Quality ◽  
Image Super Resolution ◽  
The Many

Although neural networks are most commonly used in the field of image super-resolution (SR), methods based on decision trees are still discussed. These kinds of algorithm need less time to compute than others because of their simple structure but still yield high quality image SR. In this paper, we propose an SR algorithm using the multi-grained cascade forest (SRGCF) method. Our algorithm first uses multi-grained scanning to process the spatial relationships of image features, thus the representational learning ability is improved. During the reconstruction process, the image obtained by cascade forest training is used as the input of the next training, therefore, the image features are continuously emphasized. The training of the cascade forest ends when the evaluation value is optimal. Because the decision tree uses a divide-and-conquer strategy, the SR of an image is improved in an iterative manner simply and quickly. Compared with existing methods, our method not only avoids the tradeoff between reconstruction quality and run time, but also has a good generalization capability. It can be quickly applied to the many cases of image SR.

Sign in / Sign up

Export Citation Format

Share Document