检索结果-内蒙古大学图书馆

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

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

AMG: A Depression Detection Model with Autoencoder and Multi-Head Graph Convolutional Network 42

学校读者我要写书评

暂无评论

AMG: A Depression Detection Model with Autoencoder and Multi...

42nd Chinese control Conference, CCC 2023

作者： Wang, Han-Guang Meng, Qing-Hao Jin, Li-Cheng Wang, Jian-Bang Hou, Hui-Rang Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University Tianjin Key Laboratory of Process Measurement and Control Tianjin300072 China China Southern Power Grid Company Limited Guangzhou510623 China

ISBN: (纸本)9789887581543

Depression is a common chronic mental disorder characterized by high prevalence, recurrence, suicide rate, disability rate and heavy disease burden. Depression assessment based on questionnaires is subjective, therefore, a novel framework to is hereby designed to detect depression automatically and obj ectively. The framework first utilizes a two-way autoencoder to extract the hidden features from the original differential entropy features. The new features are used to generate the channel connectivity graph, using the multi-head attention mechanism. Next, the new features and graphs are input into the graph convolutional network (GCN) to aggregate spatial information. Finally, the output from GCN is passed to a fully connected layer and a soft layer to obtain the predicted label. Experiments are performed on Multimodal Open Dataset for Mental-disorder Analysis dataset. A final accuracy of 88.68% and a cross entropy loss of 2.4532 are obtained, when using ten-fold cross validation, outperforming other traditional machine learning methods including SVM, KNN, decision tree. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Decision trees

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

E-Nose-Based Domain-Generalization Recognition of Ignitable Liquids

学校读者我要写书评

暂无评论

E-Nose-Based Domain-Generalization Recognition of Ignitable ...

第43届中国控制会议

作者： Tian-Shu Song Zhen-Peng Chen Hui-Rang Hou Hong-Yue Li Qing-Hao Meng Tianjin Key Laboratory of Process Measurement and Control Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Detecting ignitable liquids(ILs) at the scene of a fire is crucial for fire investigation. The electronic nose(e-nose) is crucial for detecting ILs due to its affordability and rapid response time. Process limitations and changes in environmental conditions can cause variations in the reactions of multiple e-noses with the same sensor array to the same input gas. This can significantly reduce the accuracy of identifying ILs when deploying a model trained on one e-nose to other e-noses. In order to tackle the issue of cross-platform identification of ILs using e-noses, we developed a feature mute gated network(FMG-Net).This network is capable of maintaining consistency in the shared components of different e-noses at the low-level feature level while effectively muting the distinct low-level features. FMG-Net is comprised of a main network and multiple branch networks that are specific to different domains. Initially, a subsidiary domain-specific convolutional neural network(SDS-CNN) is trained to learn the network parameters on various e-nose platforms with known labels. Additionally, the backbone network generates low-level features of the e-nose responses. Furthermore, the SDS-CNN incorporates random input of low-level features and generates a mask using the gradient. This mask is then used to explicitly remove the non-overlapping parts of the low-level features. At last, the low-level features are sent back to the backbone network for further training once the non-overlapping parts have been removed. Experiments were conducted to identify four types of ILs(diesel, gasoline, ethanol, and thinner) using five self-made e-nose platforms with identical sensor arrays. The results indicated that the proposed FMG-Net consistently outperforms other domain-generalization algorithms in terms of recognition accuracy and parameter sizes. FMG-Net has the ability to detect volatile gases in ILs using an e-nose, even without the need for a dataset.

关键词： Electronic Nose Fire Investigation Ignitable Liquids Convolutional Neural Network Cross Platform

A Depression Level Classification Model Based on EEG and GCN Network with Domain Generalization

学校读者我要写书评

暂无评论

A Depression Level Classification Model Based on EEG and GCN...

第43届中国控制会议

作者： Zhongyi Zhang Chenyang Xu Licheng Jin Huirang Hou Qinghao Meng Tianjin Key Laboratory of Process Measurement and Control Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Electroencephalography(EEG) contains a wealth of information, including neuron activity, allowing for a partial understanding of the brain's state. As a reliable tool, EEG, combined with deep neural networks, has been increasingly utilized to assist in the detection of depression and has achieved satisfactory results. However, there are still some limitations in the current models. Firstly, it is worth noting that many existing models are binary classification models. These models can determine whether a subject is depressed or not, but they lack the capability to differentiate the severity of depression. Besides, the variations in EEG signals among various individuals have not been thoroughly taken into account, leading to subpar performance when applying the trained model to new subjects. To address the aforementioned issues, we suggest implementing a multi-classification model that utilizes a graph convolutional neural network(GCN) to identify levels of depression. Additionally,to mitigate the problem of imbalanced samples in multi-classification tasks, we introduce a penalty coefficient for the smaller categories. At the same time, the issue of signal discrepancies among subjects was taken into account, leading to the introduction of the domain generalization module. Finally, the depression level identification task on the MODMA and PRED+CT dataset achieved an accuracy of 75.47% and 77.97% respectively, surpassing the performance of the state-of-the-art(SOTA) model. In addition, numerous ablation experiments were conducted to validate the efficacy of each module.

关键词： Depression Level EEG Graph Convolution Network Domain Generalization

A Multi-Gas Detection System Based on Convolutional Neural Network

学校读者我要写书评

暂无评论

A Multi-Gas Detection System Based on Convolutional Neural N...

第43届中国控制会议

作者： Si-Wen Chen Hong-Yue Li Hui-Rang Hou Qing-Hao Meng Tianjin Key Laboratory of Process Measurement and Control Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The emission of carbon oxides（COX）, nitrogen oxides（NOX）, sulfur compounds, and volatile organic compounds（VOCs） from vehicles has significantly impacted the air quality, thus posing threats to the environmental resources and human health. This work presents the development of a non-dispersive infrared（NDIR） multi-gas detection system featuring three broadband light sources, a sealed gas chamber, and three multi-channel pyroelectric detectors with a response time shorter than 32 ms. The proposed system is used for constructing an odor dataset comprising five target gases, including carbon dioxide（CO）,carbon monoxide（CO）, nitric oxide（NO）, sulfur dioxide（SO）, and propane（CH）. We perform odor recognition experiments using the traditional machine learning methods, as well as one-dimensional convolutional neural network（1D-CNN） and depthwise separable convolutional neural network（DS-CNN）. The results show that the proposed DS-CNN model achieves an accuracy of 94.75% in recognizing different odors, thus outperforming other classification algorithms. This work demonstrates that the proposed detection system exhibits rapid response and precise recognition, thus establishing it as an effective approach for analyzing the primary components of automobile exhaust.

关键词： Non-Dispersive Infrared Multi-gas Detection System Pattern Recognition Convolutional Neural Network