检索结果-内蒙古大学图书馆

Blind Image Despeckling Using a Multiscale Attention-Guided Neural Network

学校读者我要写书评

暂无评论

IEEE Transactions on Artificial Intelligence

IEEE Transactions on Artificial Intelligence 2024年第1期5卷 205-216页

作者： Guo, Yu Lu, Yuxu Liu, Ryan Wen Zhu, Fenghua Wuhan University of Technology School of Navigation Wuhan430063 China Wuhan University of Technology Chongqing Research Institute Chongqing401151 China Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing100190 China

Coherent imaging systems have been applied in the detection of target of interest, natural resource exploration, ailment diagnosis, etc. However, it is easy to generate speckle-degraded images due to the coherent interference of reflected echoes, restricting these practical applications. Speckle noise is a granular interference that affects the observed reflectivity. It is often modeled as multiplicative noise with a negative exponential distribution. This nonlinear property makes despeckling of imaging data an intractable problem. To enhance the despeckling performance, we propose to blindly remove speckle noise using an intelligent computing-enabled multiscale attention-guided neural network (termed MSANN). In particular, we first introduce the logarithmic transformation to convert the multiplicative speckle noise model to an additive version. Our MSANN, essentially a feature pyramid network, is then exploited to restore degraded images in the logarithmic domain. To enhance the generalization ability of the MSANN, a multiscale feature enhancement attention module is incorporated into the MSANN to extract multiscale features for improving the imaging quality. A multiscale mixed loss function is further presented to increase the network robustness during training. The final despeckled images are naturally equivalent to the exponential versions of the output of the MSANN. Experimental results have shown that the MSANN has the capacity of effectively removing the speckle noise while preserving essential structures. It can achieve superior despeckling results in terms of visual quality and quantitative measures. © 2020 IEEE.

关键词： Additives

Data-Driven Multi-step Nonlinear Model Predictive control for Industrial Heavy Load Hydraulic Robot

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Dexian Zhou, Bo Key Laboratory of Measurement and Control of Complex Systems of Engineering School of Automation Southeast University Ministry of Education Nanjing210096 China

Automating complex industrial robots requires precise nonlinear control and efficient energy management. This paper introduces a data-driven nonlinear model predictive control (NMPC) framework to optimize control under multiple objectives. To enhance the prediction accuracy of the dynamic model, we design a single-shot multi-step prediction (SSMP) model based on long short-term memory (LSTM) and multilayer perceptrons (MLP), which can directly obtain the predictive horizon without iterative repetition and reduce computational pressure. Moreover, we combine offline and online models to address disturbances stemming from environmental interactions, similar to the superposition of the robot’s free and forced responses. The online model learns the system’s variations from the prediction mismatches of the offline model and updates its weights in real time. The proposed hybrid predictive model simplifies the relationship between inputs and outputs into matrix multiplication, which can quickly obtain the derivative. Therefore, the solution for the control signal sequence employs a gradient descent method with an adaptive learning rate, allowing the NMPC cost function to be formulated as a convex function incorporating critical states. The learning rate is dynamically adjusted based on state errors to counteract the inherent prediction inaccuracies of neural networks. The controller outputs the average value of the control signal sequence instead of the first value. Simulations and experiments on a 22-ton hydraulic excavator have validated the effectiveness of our method, showing that the proposed NMPC approach can be widely applied to industrial systems, including nonlinear control and energy management. Copyright © 2024, The Authors. All rights reserved.

关键词： Excavators

Real-Time Multi-View Human Pose Estimation System

学校读者我要写书评

暂无评论

Real-Time Multi-View Human Pose Estimation System

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Yuan Yang Yangang Wang School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education China

ISBN: (数字)9798350379228

ISBN: (纸本)9798350390780

We present a highly synchronized multi-view hardware acquisition system that simultaneously enables real-time multi-person pose estimation. We design a hardware synchronizer to achieve multi camera synchronous shooting, with a synchronization latency rate of only 10 −8 seconds. Based on this, we construct a multi-view hardware synchronous acquisition system. This system can be flexibly deployed in various environments to capture moving targets, such as bodies, clothing, hands, etc. Leveraging the distributed computing capabilities of the system, we further develop a multi-view multi-person pose estimation algorithm framework that fulfills real-time requirements and achieves an average frame rate of 40FPS in experimental settings while demonstrating robustness against human motion and occlusion.

关键词： Pose estimation Data acquisition Clothing Cameras Hardware Real-time systems Robustness

Rethinking Iterative Stereo Matching from Diffusion Bridge Model Perspective

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Shi, Yuguang The School of Automation Southeast University The Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

Recently, iteration-based stereo matching has shown great potential. However, these models optimize the disparity map using RNN variants. The discrete optimization process poses a challenge of information loss, which restricts the level of detail that can be expressed in the generated disparity map. In order to address these issues, we propose a novel training approach that incorporates diffusion models into the iterative optimization process. We designed a Time-based Gated Recurrent Unit (T-GRU) to correlate temporal and disparity outputs. Unlike standard recurrent units, we employ Agent Attention to generate more expressive features. We also designed an attention-based context network to capture a large amount of contextual information. Experiments on several public benchmarks show that we have achieved competitive stereo matching performance. Our model ranks first in the Scene Flow dataset, achieving over a 7% improvement compared to competing methods, and requires only 8 iterations to achieve state-of-the-art results. Copyright © 2024, The Authors. All rights reserved.

关键词： Optimization

Dynamics parameter identification of industrial robots based on immune algorithm

学校读者我要写书评

暂无评论

Dynamics parameter identification of industrial robots based...

2022 Chinese Automation Congress, CAC 2022

作者： Ma, Jianjun Gan, Yahui Dai, Xianzhong Ministry of Education School of Automation Southeast University Key Laboratorty of Measurement and Control of Complex Systems of Engineering Nanjing China

ISBN: (纸本)9781665465335

Dynamics parameter identification is a key factor and a difficult area in the development of robot motion control technology. In order to obtain accurate dynamics parameters, an integral identification method combined with the immune algorithm is studied and experimented with. Firstly, the dynamics model of the industrial robot is derived from the Newton-Euler iteration method. Then, taking the condition number of the observation matrix as the optimization index, an ideal excitation trajectory is optimized by the immune algorithm. Butterworth zero-phase low-pass filter and the weighted least square method are used to solve the minimum parameter set of dynamics. A new validation trajectory is designed using the fmincon toolbox to cross-validate the identified dynamics model. Finally, the above identification algorithm is tested with Inexbot LG-607L robot in China as the experimental object. The experimental results show that the immune algorithm can calculate the excitation trajectory with a lower matrix condition number than the fmincon method and the genetic algorithm. And the parameter identification effect of the integral method is accurate. © 2022 IEEE.

关键词： Trajectories

Calibration of 3D Single-pixel Imaging systems with a Calibration Field

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Xinyue Wang, Chenxing The School of Automation The Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

3D single-pixel imaging (SPI) is a promising imaging technique that can be flexibly applied to various wavebands. The main challenge in 3D SPI is that the calibration usually requires a large number of standard points as references, which are tricky to capture using single-pixel detectors. Conventional solutions involve sophisticated device deployment and cumbersome operations, resulting in hundreds of images needed for calibration. In our work, we construct a Calibration Field (CaliF) to efficiently generate the standard points from one single image. A high accuracy of the CaliF is guaranteed by the technique of deep learning and digital twin. We perform experiments with our new method to verify its validity and accuracy. We believe our work holds great potential in 3D SPI systems or even general imaging systems. Copyright © 2024, The Authors. All rights reserved.

关键词： Calibration

Anti-disturbance speed regulation control of PMSM at low speed by extended state observer and kalman filter

学校读者我要写书评

暂无评论

Anti-disturbance speed regulation control of PMSM at low spe...

2023 Jiangsu Annual Conference on Automation, JACA 2023

作者： Xu, Lei Mao, Linxuan Li, Shihua School of Electronic Science and Engineering Southeast University Nanjing210096 China School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

ISBN: (纸本)9781839539848

This paper presents an enhanced friction compensation anti-disturbance control strategy for improving the speed regulation control performance of a permanent magnet synchronous motor operating in low-speed mode. This is achieved via friction modelling and lumped disturbance compensation by seamlessly integrating extended state observer (ESO) and Kalman filter algorithms. Considering that nonlinear friction torque can not be ignored at low speeds, a piece-wise linearized friction model is first established based on speed estimation of Kalman filter and ESO. Then feed-forward compensation of friction torque and lumped disturbance estimation is conducted to reduce speed fluctuation during load changes at low speeds. Comparative simulation studies in the presence of measurement noises, external disturbances and nonlinear friction torque are conducted to validate the proposed algorithm with improved performance. © The Institution of Engineering & Technology 2023.

关键词： Kalman filters

A Data-Driven Modeling and Motion control of Heavy-Load Hydraulic Manipulators via Reversible Transformation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Dexian Liu, Yirong Liu, Wenbo Zhou, Bo Key Laboratory of Measurement and Control of Complex Systems of Engineering School of Automation Southeast University Ministry of Education Nanjing210096 China

This work proposes a data-driven modeling and the corresponding hybrid motion control framework for unmanned and automated operation of industrial heavy-load hydraulic manipulator. Rather than the direct use of a neural network black box, we construct a reversible nonlinear model by using multilayer perceptron to approximate dynamics in the physical integrator chain system after reversible transformations. The reversible nonlinear model is trained offline using supervised learning techniques, and the data are obtained from simulations or experiments. Entire hybrid motion control framework consists of the model inversion controller that compensates for the nonlinear dynamics and proportional-derivative controller that enhances the robustness. The stability is proved with Lyapunov theory. Co-simulation and Experiments show the effectiveness of proposed modeling and hybrid control framework. With a commercial 39-ton class hydraulic excavator for motion control tasks, the root mean square error of trajectory tracking error decreases by at least 50% compared to traditional control methods. In addition, by analyzing the system model, the proposed framework can be rapidly applied to different control plants. Copyright © 2024, The Authors. All rights reserved.

关键词： Industrial manipulators

Data-Driven Frequency Regulation Method for Multi-Terminal HVDC Grids 38

学校读者我要写书评

暂无评论

Data-Driven Frequency Regulation Method for Multi-Terminal H...

38th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2023

作者： Yong, Panxiao Jia, Yubin Guo, Jun Zhou, Jun Liu, Zhimin Southeast University School of Automation Nanjing210096 China Southeast University Key Laboratory of Measurement and Control of Complex System of Engineering Ministry of Education Nanjing210096 China

ISBN: (纸本)9798350303636

High voltage direct current (HVDC) lines allow low-loss transmission over long distances. The multi-terminal HVDC network consists of multiple terminals connected by HVDC lines, and each area shares the frequency reserve. Through secondary frequency control, the frequency of AC and DC areas can be regulated back to the set point when the system frequency has deviated. In this paper, a data-driven model predictive control (MPC) strategy is proposed. The Kooman operator is used to obtain the high-dimensional linear model of a nonlinear system, and the Deep Learning method is used to approximate the infinite-dimensional Koopman operator. The nominal MPC is used for optimization and control, and the optimal problem is solved for the Koopman linearized system. The optimal control is applied to the original nonlinear system. Simulation results show the effectiveness of the proposed method. © 2023 IEEE.

关键词： data-driven Koopman operator model predictive control Multi-terminal HVDC