JingHui Deng, Jinhe Chen and ZhengZhong Wang
The paper aims to establish a comprehensive optimization analysis model for a helicopter roll on the ground and take off based on optimal control method. The trajectory and…
Abstract
Purpose
The paper aims to establish a comprehensive optimization analysis model for a helicopter roll on the ground and take off based on optimal control method. The trajectory and control of the entire process are studied, and the key factors affecting the helicopter takeoff distance are analyzed.
Design/methodology/approach
First, based on the equivalent stiffness and damping, the landing gear model is established, and a six-degree-of-freedom helicopter model is formed. Then, the simulation of the roll-on takeoff is transformed into a nonlinear optimal control problem (NOCP). Meanwhile, a hybrid single-multiple shooting method-based transcription process is used for discretizing the problem, leading to a finite nonlinear programming model, which is solved by sequential quadratic programming. Finally, the process was calculated and compared with flight test data, which verified the feasibility of the NOCP. The influence of takeoff weight, takeoff power and liftoff airspeed on the takeoff distance of the helicopter was analyzed.
Findings
The results show that the takeoff weight can be increased by 17% under the maximum takeoff power, which is roll-on takeoff at an altitude of 0 m. When the helicopter takes off with the maximum weight at an altitude of 5000 m, the liftoff airspeed should be over 49.2 km/h.
Originality/value
The novelty of this paper lies in the comprehensive consideration of helicopter taxiing and taking-off phases, and the application of optimal control theory to establish a comprehensive analysis model, which can quickly analyze the maximum takeoff weight, takeoff distance, optimal liftoff speed and so on. Meanwhile, the method is verified based on the flight data.
Details
Keywords
Jinghui Deng, Qiyou Cheng and Xing Lu
Helicopter fuselage vibration prediction is important to keep a safety and comfortable flight process. The helicopter vibration mechanism model is difficult to meet of demand for…
Abstract
Purpose
Helicopter fuselage vibration prediction is important to keep a safety and comfortable flight process. The helicopter vibration mechanism model is difficult to meet of demand for accurate vibration prediction. Thus, the purpose of this paper is to develop an intelligent algorithm for accurate helicopter fuselage vibration analysis.
Design/methodology/approach
In this research, a novel weighted variational mode decomposition (VMD)- extreme gradient boosting (xgboost) helicopter fuselage vibration prediction model is proposed. The vibration data is decomposed and reconstructed by the signal clustering results. The vibration response is predicted by xgboost algorithm based on the reconstructed data. The information transfer order between the controllable flight data and flight attitude are analyzed.
Findings
The mean absolute percentage error (MAPE), root mean square error (RMSE) and mean absolute error (MAE) of the proposed weighted VMD-xgboost model are decreased by 6.8%, 31.5% and 32.8% compared with xgboost model. The established weighted VMD-xgboost model has the highest prediction accuracy with the lowest mean MAPE, RMSE and MAE of 4.54%, 0.0162, and 0.0131, respectively. The attitude of horizontal tail and cycle pitch are the key factors to vibration.
Originality/value
A novel weighted VMD-xgboost intelligent prediction methods is proposed. The prediction effect of xgboost model is highly improved by using the signal-weighted reconstruction technique. In addition, the data set used is collected from actual helicopter flight process.
Details
Keywords
Xiaojun Wu, Peng Li, Jinghui Zhou and Yunhui Liu
Scattered parts are laid randomly during the manufacturing process and have difficulty to recognize and manipulate. This study aims to complete the grasp of the scattered parts by…
Abstract
Purpose
Scattered parts are laid randomly during the manufacturing process and have difficulty to recognize and manipulate. This study aims to complete the grasp of the scattered parts by a manipulator with a camera and learning method.
Design/methodology/approach
In this paper, a cascaded convolutional neural network (CNN) method for robotic grasping based on monocular vision and small data set of scattered parts is proposed. This method can be divided into three steps: object detection, monocular depth estimation and keypoint estimation. In the first stage, an object detection network is improved to effectively locate the candidate parts. Then, it contains a neural network structure and corresponding training method to learn and reason high-resolution input images to obtain depth estimation. The keypoint estimation in the third step is expressed as a cumulative form of multi-scale prediction from a network to use an red green blue depth (RGBD) map that is acquired from the object detection and depth map estimation. Finally, a grasping strategy is studied to achieve successful and continuous grasping. In the experiments, different workpieces are used to validate the proposed method. The best grasping success rate is more than 80%.
Findings
By using the CNN-based method to extract the key points of the scattered parts and calculating the possibility of grasp, the successful rate is increased.
Practical implications
This method and robotic systems can be used in picking and placing of most industrial automatic manufacturing or assembly processes.
Originality/value
Unlike standard parts, scattered parts are randomly laid and have difficulty recognizing and grasping for the robot. This study uses a cascaded CNN network to extract the keypoints of the scattered parts, which are also labeled with the possibility of successful grasping. Experiments are conducted to demonstrate the grasping of those scattered parts.
Details
Keywords
Automatic segmentation of brain tumor from medical images is a challenging task because of tumor's uneven and irregular shapes. In this paper, the authors propose an…
Abstract
Purpose
Automatic segmentation of brain tumor from medical images is a challenging task because of tumor's uneven and irregular shapes. In this paper, the authors propose an attention-based nested segmentation network, named DAU-Net. In total, two types of attention mechanisms are introduced to make the U-Net network focus on the key feature regions. The proposed network has a deep supervised encoder–decoder architecture and a redesigned dense skip connection. DAU-Net introduces an attention mechanism between convolutional blocks so that the features extracted at different levels can be merged with a task-related selection.
Design/methodology/approach
In the coding layer, the authors designed a channel attention module. It marks the importance of each feature graph in the segmentation task. In the decoding layer, the authors designed a spatial attention module. It marks the importance of different regional features. And by fusing features at different scales in the same coding layer, the network can fully extract the detailed information of the original image and learn more tumor boundary information.
Findings
To verify the effectiveness of the DAU-Net, experiments were carried out on the BRATS 2018 brain tumor magnetic resonance imaging (MRI) database. The segmentation results show that the proposed method has a high accuracy, with a Dice similarity coefficient (DSC) of 89% in the complete tumor, which is an improvement of 8.04 and 4.02%, compared with fully convolutional network (FCN) and U-Net, respectively.
Originality/value
The experimental results show that the proposed method has good performance in the segmentation of brain tumors. The proposed method has potential clinical applicability.