检索结果-内蒙古大学图书馆

Hierarchical Energy Management Strategy of Hybrid Electric Truck Fleet under Connected Environment

学校读者我要写书评

暂无评论

Hierarchical Energy Management Strategy of Hybrid Electric T...

第43届中国控制会议

作者： Qizhe Lu Wenbin Tang Zitong Pang Yahui Zhang Xiaohong Jiao School of Electrical Engineering Yanshan University Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University School of Mechanical Engineering Yanshan University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Considering the slow-moving and energy-consuming issues that tend to occur when truck fleets drive,this paper proposes a hierarchical energy management strategy(EMS) for the hybrid electrical truck(HET) fleet,including speed planning and energy *** speed threshold range that allows the whole fleet to pass through the traffic light is computed in the upper-layer speed *** the model predictive control framework,a multi-objective optimization function is constructed for speed planning to find the optimum *** the lower-layer energy management,an offline model is established for power allocation between the Integrated Starter Generator and the Electric Motor and gear shift selection of automated manual transmission to reduce the dimensionality of the control ***,an adaptive equivalent consumption minimum strategy(A-ECMS) is designed based on the fleet's optimal speed *** the offline part,the transformation relationship between the co-state and equivalence factor is established based on Pontryagin's minimum principle(PMP),and PMP obtains the globally optimal control sequence in the historical driving cycle to train a back-propagation neural network(BPNN).The BPNN model predicts the current optimal co-state in the online part,transformed into a real-time optimal equivalence factor to guide the A-ECMS online *** simulation results indicate that the fuel economy of the proposed EMS is comparable to that of the global optimization method PMP and superior to that of Fixed EF-ECMS and ***,it enables the HET fleet to pass through traffic lights without stopping,thereby ensuring queue continuity and improving the passage efficiency of the fleet.

关键词： hybrid electric trucks equivalent consumption minimization strategy fleet speed planning back-propagation neural network model predictive control

Branch-Yolo：Efficient Object Detector for Thin Structure Objects Like Pantograph

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Li, Yaqian Han, Jiaqi Li, Haibin Zhang, Wenming College of Electrical Engineering Yanshan University Hebei Qinhuangdao066000 China Key Laboratory of Industrial Computer Control Engineering of Hebei Province Hebei Qinhuangdao066000 China

The pantograph is the key structure in the railway Pantograph-OCS system, acting as the switch for the railway traction power supply system. So it’s crucial to detect the pantograph's lifting and lowing states for production efficiently and safely. However, due to the pantograph’s special slender structure and complex application scenarios, it occupies few pixels and is susceptible to background interference, making accurate real-time detection a challenging task. In this work, we aim to propose a generalized model, designed for detecting, branch-like objects with thin structure and multi-scale size such as pantographs. To this end, we propose the Branch-YOLO based on YOLOv8, which is improved in two stages, feature extraction and feature fusion, to simultaneously enhance perception. First, we introduce BrLayer is consist of BranchConv and EFAC(Extend receptive field attention Convolution), BranchConv can adaptively capture features of thin and tortuous local structures,EFAC is able to assist in expanding the effective receptive field. Subsequently, we propose a feature fusion network (BranchNet) to integrate multilevel semantic information and multi-scale features, which significantly reduces background interference in detecting slender structure objects and enhances the ability to perceive changes in object scale. Besides, we propose the Lightweight Cross-Kernel Convolution layer (LckLayer) and introduce the Feature Decomposition module (FdM) in BranchNet for lightweight design, reducing the computational overhead and enhancing model efficiency. Our proposed Branch-YOLO not only achieves the best performance on the multi-scale pantograph datasets but also attains an outstanding 42.9% AP on the COCO val2017 datasets, with 5.9M parameters and 16.8 GFLOPs. © 2024, The Authors. All rights reserved.

关键词： Religious buildings

Fault Tolerant control for the Vibration Displacement System of a Continuous Casting Mold Based on a Fault Detection Observer

学校读者我要写书评

暂无评论

Fault Tolerant Control for the Vibration Displacement System...

第43届中国控制会议

作者： Wenqi Hao Yiming Fang Le Liu Xiaonan Liu Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Engineering Research Center of the Education Ministry for Intelligent Control System and Intelligent Equipment Yanshan University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

In this paper,a fault detection observer and an adaptive sliding mode fault-tolerant controller are designed for the vibration displacement system of a continuous casting mold with actuator faults and load torque ***,a mathematical model of a continuous casting mold vibration displacement system driven by a servo motor with actuator faults and load disturbance uncertainties are ***,a fault detection observer is designed to obtain information on actuator faults,load disturbances,and system state ***,based on the information from the fault detection observer,an adaptive sliding mode fault-tolerant controller is designed,and the stability of the designed system is proved using Lyapunov stability ***,the effectiveness of the designed adaptive sliding mode fault-tolerant controller based on fault observer is verified through simulation.

关键词： Continuous casting mold Fault detection observer Fault tolerant control Actuator fault Vibration displacement system Driven by a servo motor

Global-Local Context Enhanced Yolo for Small Object Detection in Uav Images

学校读者我要写书评

暂无评论

SSRN 2025年

作者： Wei, Lixin Han, Kangshuai Li, Xin Che, Haijun Hu, Ziyu Engineering Research Center of the Ministry of Education for Intelligent Control System and Intelligent Equipment Yanshan University Hebei Qinhuangdao066000 China Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Hebei Qinhuangdao066000 China

Object detection using Unmanned Aerial Vehicles (UAVs) has emerged as a criti cal application across diverse domains. However, the wide-angle views of drones often result in images containing a high density of small objects, posing chal lenges for object detection such as few learnable features, significant occlusion, and an imbalanced distribution of positive and negative samples. To address these issues, this paper introduces AGLC-YOLO, an enhanced version of the YOLOv7 architecture specifically designed for detecting small objects in UAV images. AGLC-YOLO integrates global and local context information through a Attention guide Global-Local Context Information Extraction (AGLC) module. This module employs parallel dilated convolutions to capture local context infor mation and a transformer-based structure to extract global dependencies, which are then fused using an improved attention mechanism. The network also adds an additional small object detection head to enrich the small object information in the model. Additionally, AGLC-YOLO utilizes an auxiliary bounding box in con junction with the Inner-Wise Intersection over Union (Inner-WIoU) loss function to accelerate the bounding box regression process and improve detection accu racy. Experimental results on the VisDrone and ManipalUav datasets demonstrate that AGLC-YOLO achieves significant improvements over the baseline YOLOv7 model, with anincrease of 3%inAP50and2.7%inAP95ontheVisDronedataset, and 1.9% in AP50 and 2% in AP95 on the ManipalUav dataset. © 2025, The Authors. All rights reserved.

关键词： Convolution

A Heterogeneous Reinforcement Learning Approach for Joint Relay Selection and Power Allocation in Time-Varying Uasns with Energy Harvesting

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Han, Song Wang, Ziyuan Li, Aijia Li, Xinbin Liu, Zhixin Yan, Lei Zhang, Tong Wei Key Lab of Industrial Computer Control Engineering of Hebei Province Institute of Electrical Engineering Yanshan University Hebei Province Qinhuangdao066004 China School of Computer and Communication Engineering Northeastern University Hebei Province Qinhuangdao066004 China Department of Technology Northeastern University Shandong Province Qingdao266237 China

In this study, we investigate the joint relay selection and power allocation problem for underwater acoustic communication networks with energy harvesting to maximize the cumulative capacity. We specially formulate a heterogeneous reinforcement learning-based framework. In the different decision layers, the Upper Confidence Bound 1 and enhanced Deep Deterministic Policy Gradient algorithms are employed to efficiently explore the discrete and continuous action spaces, respectively. Therefore, the solving difficulty of the complex hybrid discrete-continuous optimization problem can be significantly mitigated. Furthermore, a circular interaction structure is constructed to facilitate the exchange of decision-making information between the two decision layers. The strongly interdependent relationship of the different substrategies can be comprehensively considered, thereby improving the entire performance of thejoint strategy. Moreover, we propose an adaptive reward function, which can guide the user to balance the instantaneous capacity and interruptions, thereby effectively utilizing the green energy harvesting technology and enhancing long-term cumulative performance. Simulation results verify the effectiveness of our proposed algorithm. © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

EAVFormer: an end-to-end audio and visual emotion recognition network based on transformers

学校读者我要写书评

暂无评论

Multimedia Systems 2025年第3期31卷 1-22页

作者： Liu, Haoran Sun, Zijian Li, Haibin Li, Yaqian Zhang, Wenming Song, Tao School of Information Science and Engineering Yanshan University Qinhuangdao066004 China The Key Laboratory for Special Fiber and Fiber Sensor of Hebei Province Yanshan University Qinhuangdao066004 China Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao066004 China Shenzhen Research Institute of Yanshan University Shenzhen518057 China Key Lab of Measurement Technology & Instrumentation of Hebei Province School of Electrical Engineering Yanshan University Qinhuangdao066004 China

Audio-visual emotion recognition, integrating information from various sources, enhances the comprehensive understanding and analysis of human emotions. However, existing methods in this field primarily focus on feature fusion, often overlooking the equally crucial stage of feature extraction. Typically, these methods employ pre-trained models to extract features during the initial phase, complicating modality-specific feature extraction and increasing system complexity and coordination challenges, which hinder effective audio-visual feature fusion. To address these issues, we propose an end-to-end audio-visual emotion recognition model, EAVFormer. For the audio modality, we input raw audio signals along with a mix of mel spectrograms and Mel Frequency Cepstral Coefficients (MFCCs), employing a hierarchical transformer technique that facilitates both shallow local and deep global feature extraction to fully harness complementary acoustic information, significantly enhancing the acoustic modality’s contribution. For the visual modality, we input raw video frames and employ a hierarchical transformer feature extraction method that integrates three-dimensional convolution and spatio-temporal self-attention mechanisms to address spatial and temporal redundancies and dependencies, thereby enhancing the expression of dynamic visual information. In the modal fusion stage, we construct dual-modality representations and encode inter-modal information while preserving modality-specific and meaningful intra-modal features. Testing on three popular datasets RAVDESS, CREMA-D, and CMU-MOSEI demonstrates that EAVFormer surpasses existing state-of-the-art methods in audio-visual emotion recognition accuracy, achieving rates of 95.17%, 86.13%, and 78.22%, respectively. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Image coding

A TCN-Transformer Model of Acceleration Prediction for Preceding Vehicle in CACC Systems

学校读者我要写书评

暂无评论

A TCN-Transformer Model of Acceleration Prediction for Prece...

Conference on Vehicle control and Intelligence (CVCI)

作者： Wenzhao Tang Wenbin Tang Xiaohong Jiao Yahui Zhang Dongxue Zhang Hebei Key Laboratory of Industrial Computer Control Engineering Yanshan University Qinhuangdao Hebei Province China School of Mechanical Engineering Yanshan University Qinhuangdao China

ISBN: (数字)9798331504892

ISBN: (纸本)9798331504908

This study establishes an acceleration prediction model of the preceding vehicle tailored for cooperative adaptive cruise control (CACC) systems that address the common challenges posed by V2V communication delays or no communication from the preceding vehicle. The designed model integrates a temporal convolutional network (TCN) with the Transformer architecture block to create a sophisticated mechanism for temporal data analysis. This integration leverages the strengths of TCN in capturing spatial features and the multi-attention mechanism of Transformers to enhance the recognition of long-term dependencies in the time series of data. The synergy between these techniques not only effectively narrows the identification gap between short-term and long-term dependencies but also helps to process spatial information for accurate time-series prediction, significantly improving prediction accuracy. Simulations using the NGSIM dataset confirm the model's prediction performance over the traditional model. Further, the potential of the method to solve the communication delay problem is verified, highlighting the effectiveness of TCN and Transformer multi-attention mechanism in improving the CACC capability.

关键词： Adaptation models Accuracy Uncertainty Adaptive systems Time series analysis Vehicular ad hoc networks Predictive models Transformers Delays Cruise control

Decision Variable Classification-Based Evolutionary Algorithm for Dynamic Multi-Objective Optimization

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Wei, Lixin Yang, Qingshuai Guo, Zeyin Institute of Electrical Engineering Yanshan University Hebei Qinhuangdao066004 China Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Hebei Province Qinhuangdao066004 China

There are many dynamic multi-objective optimization problems (DMOPs) in real life, and such problems require the algorithms to converge quickly to a new Pareto Front and maintain the diversity of solution sets after the environment changes. To achieve these objectives, a dynamic multi-objective evolutionary algorithm (DEA) based on decision variable classification is proposed in this paper. First, the decision variables are classified into two categories using the decision variable clustering method: convergence-related variables and diversity-related variables. Then, the convergence optimization strategy and the diversity optimization strategy are used to optimize these two categories of decision variables, so that the algorithm can obtain excellent convergence and good diversity while fast tracking the Pareto front. In addition, a method for calculating the degree of environmental change, which uses the information after environmental change, is proposed to improve the algorithm’s ability to respond to environmental change. The proposed algorithm is compared with three state-of-the-art dynamic multi-objective optimization evolutionary algorithms on 16 benchmark problems. The experimental results show that the algorithm can effectively solve dynamic multi-objective optimization problems. © 2023, The Authors. All rights reserved.

关键词： Evolutionary algorithms

A Novel A-ESO Composited Non-Recursive control Methodology for Complex High-Order Disturbed Nonlinear Systems

学校读者我要写书评

暂无评论

A Novel A-ESO Composited Non-Recursive Control Methodology f...

Chinese control Conference (CCC)

作者： Cong Zhang Shiji Liu Shuang Liu School of Electrical Engineering Yanshan University Qinhuangdao Hebei China Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao Hebei China

This paper mainly focuses on a disturbance rejection control methodology for a series of mismatched and matched disturbed complex systems. Firstly, a novel finite-time arbitrary-order extended state observer (A-ESO) is proposed to accurately estimate the system states, disturbances, and their corresponding order derivatives. And then, a novel concise nonrecursive control ideology utilizing all the estimations of A-ESO is proposed to strictly guarantee finite-time stability and convergence of the whole closed-loop system. Significantly, compared with the existing nonrecursive control methods, the essential characteristic is that all the estimation information is utilized to construct the composite controller. This will be tremendously conducive to cost-saving and promoting practical implementations.

关键词：