Fault information of rotating machinery is often drowned in strong noise signals, so it is crucial to accurately identify faults from high-intensity noise signals. In this article, an end-to-end fault diagnosis model ...
Fault information of rotating machinery is often drowned in strong noise signals, so it is crucial to accurately identify faults from high-intensity noise signals. In this article, an end-to-end fault diagnosis model is developed, which consists of a multi-stage selection filter based on wavelet packet and 2D-CNN. First, the original measured mechanical signals were processed by the three-level wavelet packet decomposition to obtain eight sub-bands with coefficient matrices. Second, the signal is reconstructed using different numbers of sub-bands, where the number is increased by one at a time to obtain eight different multi-stage reconstructed signals. Third, the reconstructed signals are reorganized into 2D signal maps; and a parallel training network is constructed using signal maps and 2D-CNN to achieve fault classification. Then, guided by the training results, eight parallel classification results are compared, so as to train the best fault diagnosis model. Finally, the simulation experiment based on a bearing data set illustrates the proposed multi-stage selection filter is effective and feasible in application.
This paper presents a learning-based high-speed trajectory tracking control strategy for quadrotors, which achieves efficient learning and strong reliability by the collaboration of deep reinforcement learning (RL) an...
详细信息
ISBN:
(数字)9798350379228
ISBN:
(纸本)9798350390780
This paper presents a learning-based high-speed trajectory tracking control strategy for quadrotors, which achieves efficient learning and strong reliability by the collaboration of deep reinforcement learning (RL) and self-tuning mechanism. Different from existing methods, the proposed strategy is designed to explore optimal control performance by taking advantage of model-based self-tuning mechanism and deep reinforcement learning. Specifically, the self-tuning guided deep RL scheme is put forward for quadrotors, with superior learning efficiency and strong adaptability. Firstly, a novel self-tuning mechanism is constructed and some auxiliary variables are introduced to enhance the tracking performance. Then, based on the model-driven self-tuning design, the deep RL is proposed to achieve model-guided learning, where the tuning actions are adopted in the evaluation process during training, aiming at removing the bad explorations by the carefully designed parallel evaluation. Finally, the convergence is analyzed based on the proposed learning framework, which indicates the efficient cooperation of exploration and self-tuning mechanism. To verify the effectiveness of the proposed controller, the guided training and hardware experiments are implemented to show efficient cooperation and satisfactory high-speed trajectory tracking control of the proposed method.
robot teleoperation attracts growing attention of researchers in many domains. Plenty of factors contribute to the good performance of a smart teleoperation system, and one crucial factor is that it provides an enviro...
详细信息
For aerial swarms, formation flight has been applied in various scenes. However, most existing works do not consider balancing the conflicting requirements among keeping formation, keeping the smoothness of trajectori...
详细信息
ISBN:
(数字)9798350377705
ISBN:
(纸本)9798350377712
For aerial swarms, formation flight has been applied in various scenes. However, most existing works do not consider balancing the conflicting requirements among keeping formation, keeping the smoothness of trajectories, and obstacle avoidance within the limited time. To address this issue, we propose a decentralized trajectory planning framework for formation flight in unknown and dense environments. To ensure that feasible trajectories can be found within the limited time, the formation optimization problem is decoupled into formation affine transformation and iterative trajectory generation. Firstly, the optimization problem based on affine transformation is designed to obtain the optimal affine transformation sequence, which provides the formation reference of trajectory optimization. Secondly, the iterative optimization framework of trajectory planning is designed, which balances the conflicting requirements of formation, smooth flight, and obstacle avoidance. Besides, to escape the local minima caused by non-convex dense environments, the method of topological path planning is designed to provide distinctive initial solutions for trajectory optimization. Finally, the proposed methods are proven to be effective through the simulations and real-world experiments.
Different from the traditional model-based fault diagnosis paradigm which is established upon the well-known observer design and analysis, a novel data-driven framework is proposed by combing systems modeling with fau...
详细信息
Different from the traditional model-based fault diagnosis paradigm which is established upon the well-known observer design and analysis, a novel data-driven framework is proposed by combing systems modeling with fault detection for a class of 1-D unknown distributed parameter systems. The key idea is to transfer the on-line modeling error into the residual signal for fault detection. The proposed methodology only utilizes the I/O data and does not require extra knowledge of the system model, which increases its usability at large. Numerical simulations on a commonly used benchmark are presented for method validation.
This paper addresses the robust image-based landing control problem for a landing system, including an underactuated quadrotor and an unknown moving platform. Firstly, an image kinematics is constructed by using an im...
详细信息
Object pose estimation is a core means for robots to understand and interact with their environment. For this task, monocular category-level methods are attractive as they require only a single RGB camera. However, cu...
详细信息
controller Area Network (CAN) protocol is an efficient standard enabling communication among Electronic control Units (ECUs). However, the CAN bus is vulnerable to malicious attacks because of a lack of defense featur...
详细信息
In this paper, we propose LF-PGVIO, a visual-Inertial-Odometry (VIO) framework for large Field-of-View (FoV) cameras with a negative plane using points and geodesic segments. The purpose of our research is to unleash ...
详细信息
Local features and contextual dependencies are crucial for 3D point cloud analysis. Many works have been devoted to designing better local convolutional kernels that exploit the contextual dependencies. However, curre...
详细信息
暂无评论