检索结果-内蒙古大学图书馆

Deep learning network for predicting the remaining useful life of lithium-ion batteries using the positive and negative convolution perceptron model

引用

JOURNAL OF THE CHINESE INSTITUTE OF ENGINEERS 2025年

作者： Bak, Gwiman Bae, Youngchul Chonnam Natl Univ Dept Elect & Semicond Engn Yeosu South Korea Chonnam Natl Univ Div Elect & Comp Engn Yeosu South Korea

Lithium-ion batteries (LIBs) are vital in electric vehicles, portable electronic devices, and energy storage systems due to their high energy density and long lifespan. Accurately predicting LIBs remaining useful life (RUL) is critical for extending battery life, reducing costs, and enhancing system stability. In this study, we propose a positive and negative convolution perceptron (PNC) network to predict the RUL of LIBs. The PNC network integrates a PNC with a multi-layer perceptron model. This design leverages convolutional neural network (CNN) multidimensional data processing capabilities while utilizing the PNC model's unique ability to manage positive and negative data elements separately. The PNC network achieved the lowest root mean square error (RMSE) of 106.39 cycles, substantially outperforming the other models. Furthermore, when evaluated against other studies on LIB RUL prediction, the PNC network demonstrated superior accuracy. These results highlight the PNC network's ability to provide higher accuracy and efficiency in predicting LIB RUL compared to conventional deep learning models. In future research, we aim to validate the generalizability of the PNC network using various datasets and investigate strategies for improving resource efficiency, such as applying quantization and distributed processing techniques.

关键词： LIB RUL prediction PNC PNP

来源：评论

学校读者我要写书评

暂无评论

Fixed-Time Anti-synchronization and Preassigned-Time Synchronization of Discontinuous Fuzzy Inertial neural networks with Bounded distributed Time-Varying Delays

引用

neural processing LETTERS 2023年第3期55卷 3333-3353页

作者： Liu, Yang Zhang, Guodong Hu, Junhao South Cent Min Zu Univ Sch Math & Stat Minzu Ave Wuhan 430074 Peoples R China

This paper is dedicated to fixed-time anti-synchronization (FXTAS) and preassigned-time synchronization (PATS) of discontinuous fuzzy inertial neural networks with mixed time-varying delays. Different from the traditional continuous neural network model, the differential inclusion theory is utilized to deal with discontinuous systems. Then, based on Lyapunov stability theory, two operational and efficient pure power-law control schemes are designed to ensure FXTAS and PATS. PATS is more flexible than fixed-time synchronization because its settling-time can be set in advance according to the actual situation. Finally, two numerical simulations are given to confirm the consistency with the theoretical results obtained in this paper.

关键词： Fixed-time anti-synchronization Preassigned-time synchronization Fuzzy inertial neural networks Discontinuous functions Bounded distributed time-varying delays

来源：评论

学校读者我要写书评

暂无评论

Detecting local earthquakes via fiber-optic cables in telecommunication conduits under Stanford University campus using deep learning

引用

COMPUTERS & GEOSCIENCES 2024年 190卷

作者： Huot, Fantine Clapp, Robert G. Biondi, Biondo L. Stanford Univ Stanford CA USA

With fiber-optic seismic acquisition development, continuous dense seismic monitoring is becoming increasingly more accessible. Repurposing fiber cables in telecommunication conduits makes it possible to run seismic studies at low cost, even in locations where traditional seismometers are not easily installed, such as urban areas. However, due to the large volume of continuous streaming data, data collected in such a manner will go to waste unless we significantly automate the processing workflow. We train a convolutional neural network (CNN) for earthquake detection using 3000 events from a publicly available catalog and data acquired over three years by fiber cables in telecommunication conduits under the Stanford University campus. We performed a hyperparameter search both on the network architecture itself (e.g., number of layers, number of parameters) and on its training parameters, showing that CNNs with a small number of layers are sufficient for performing this detection task with high accuracy. We introduce a novel method for combining the deep learning results on fiber-optic and seismometer data to improve detection accuracy, dramatically reducing the false detection rate that is often a problem when processing large time-scale noisy continuous data. Consequently, we demonstrate that enhancing two sparse seismometer stations with an urban fiber system allows for the reliable detection of small earthquakes despite a low signal-to-noise ratio. We scale this processing method over three years of continuous data and show that this system reliably detects local small-amplitude earthquakes down to magnitudes as low as 0.5, leading to the discovery of previously uncataloged events.

关键词： Seismology distributed acoustic sensing (DAS) Acquisition Earthquake Machine learning neural network

来源：评论

学校读者我要写书评

暂无评论

A distributed Proximal Consensus Algorithm for Energy Saving in Ethylene Production

引用

IEEE TRANSACTIONS ON neural networkS AND LEARNING SYSTEMS 2024年第3期35卷 3052-3061页

作者： Nie, Rong Du, Wenli Wang, Ting Li, Zhongmei He, Shuping East China Univ Sci & Technol Minist Educ Key Lab Smart Mfg Energy Chem Proc Shanghai 200237 Peoples R China Qingyuan Innovat Lab Quanzhou 362801 Peoples R China Anhui Univ Sch Elect Engn & Automat Minist Educ Key Lab Intelligent Comp & Signal Processing Hefei 230601 Peoples R China Chengdu Univ Sch Elect Informat & Elect Engn Chengdu 610106 Peoples R China

This article presents a distributed optimization framework in order to solve the plant-wide energy-saving problem of an ethylene plant. First, the ethylene production process is abstracted into a distributed network, and then, a new distributed consensus algorithm is proposed, which is called adaptive step-size-based distributed proximal consensus algorithm (ASS-DPCA). This algorithm can dynamically adjust the step size and automatically abandon the irrational evolutionary route while eliminating the dependence of optimization algorithms on model gradient information. Moreover, the designed algorithm is able to converge to an optimal solution for any convex cost functions and approach to a convex constraint set of agents over an undirected connected graph. Finally, the results of numerical simulation and industrial experiments show that the algorithm can reduce the total energy consumption of an ethylene plant with less computing time and assured consensus.

关键词： Production Optimization Energy consumption Consensus algorithm Upper bound Petrochemicals Linear programming distributed optimization energy saving ethylene plant-wide optimization proximal consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Factorized Fourier Operator Based neural network for Fiber Nonlinearity Compensation in Coherent Optical Communication Systems

引用

JOURNAL OF LIGHTWAVE TECHNOLOGY 2025年第8期43卷 3612-3622页

作者： Yi, Anlin Fei, Jianxiong Huang, Junling Yan, Lianshan Luo, Bin He, Xingchen Jiang, Lin Pan, Wei Southwest Jiaotong Univ Ctr Informat Photon & Commun Sch Informat Sci & Technol Chengdu 610031 Peoples R China

In long-haul and high-capacity coherent optical communications systems, it is essential to reduce the complexity of the underlying algorithms in the practical implementation of digital signal processing techniques for compensation of transmission impairments. Here, we investigate a factorized Fourier operator (F-FNO) based neural network (NN) for compensation the linear and nonlinear signal distortion in fiber simultaneously. The combination of the factorized Fourier transforms and residual connection enables the F-FNO based NN to compensate fiber impairments with higher accuracy, lower computational complexity and faster convergence rate, compared with our previous Fourier operator (FNO) based NN. The time consumption is further decreased by sharing the Fourier-domain weight matrices. The feasibility of the proposed scheme is verified experimentally in 32GBaud polarization division multiplexed (PDM) uniformly distributed 16/32/64-ary quadrature amplitude modulation (PDM-16/32/64QAM) as well as probabilistically shaped 16/32/64QAM (PDM-PS-16/32/64QAM) coherent optical communication systems. The experimental results demonstrate that the Q-factor improvement is extremely close to the standard digital back propagation (DBP) with 16 steps per span (16StPS-DBP) even in the highly nonlinear region, while with much lower computational complexity and time consumption.

关键词： Artificial neural networks Optical fiber networks Fast Fourier transforms Optical fiber polarization Optical fiber dispersion Training Symbols Computational complexity Signal processing algorithms Modulation Digital back-propagation (DBP) factorized Fourier operator fiber nonlinearity compensation neural networks (NN)

来源：评论

学校读者我要写书评

暂无评论

DAS Up- and Downgoing Wavefield Separation via Radon Transform Combined With Parallel U-network

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Sun, Decheng Yao, Guijin Li, Yue Jilin Univ Coll Commun Engn Dept Informat Changchun 130012 Peoples R China

After mitigating noise pollution, the primary challenge in processing downhole distributed acoustic sensing (DAS) data is the effective separation of its wavefield. Wavefield separation networks specifically for DAS data are scarce. Existing vertical seismic profiling (VSP) wavefield separation methods include traditional techniques, establishing propagation models applied to neural networks, and using the results of traditional methods as labels. Traditional methods can lead to issues of spatial aliasing and artifacts. Using such "not-so-clean" data for network training results in suboptimal performance. In addition, constructing models under simplified conditions results in training data that are overly simplistic, leading to a loss of detailed information in modern, higher sampling frequency, and more densely sampled complex DAS data. Inspired by the Radon transform and neural networks, we propose a DAS wavefield separation framework that combines the Radon transform with parallel U-Net (RTPU-Net) to address the issue of spatial aliasing in the Radon transform. We identified two key features in wavefield separation based on Radon transform: phase-reversed spatial aliasing and high amplitude preservation. In addition to constraining the network with loss functions, we also used reconstruction loss (MSE) to associate these two features. Using the Radon transform as a preprocessing method, our approach can also synthesize a large amount of training data automatically from raw data. Applications to both synthetic and field DAS data demonstrate that RTPU-Net can be widely used for high-precision DAS wavefield separation. When comparing the MSE metric of the overlapped wavefield from separated field data, our method also consistently achieves the lowest value among all the tested methods.

关键词： Transforms Training Noise reduction Signal to noise ratio Reflection Energy loss Training data Radon Geoscience and remote sensing Data models distributed acoustic sensing (DAS) encoder-decoder multiscale radon transform wave field separation

来源：评论

学校读者我要写书评

暂无评论

Automated Graph neural network Search Under Federated Learning Framework

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2023年第10期35卷 9959-9972页

作者： Wang, Chunnan Chen, Bozhou Li, Geng Wang, Hongzhi Harbin Inst Technol Dept Comp Sci & Technol Harbin 150001 Peoples R China

Graph neural network (GNN) has achieved great success in the field of graph data processing and analysis, but the design of GNN architecture is difficult and time-consuming. To reduce the development cost of GNNs, recently, some GNN neural Architecture Search (GNN NAS) techniques are presented for the automatic design of GNN architectures. These techniques bring great convenience to the use of GNN, but cannot be applied to the federated learning scenarios. They only consider the single-source graph dataset, while failing to deal with the distributed and private graph datasets, which limits their applications. To address this shortcoming, in this paper we propose FL-AGNNS, an efficient GNN NAS algorithm which enables distributed agents to cooperatively design powerful GNN models while keeping personal information on local devices. FL-AGNNS designs a novel federated evolutionary optimization strategy. This strategy can fully consider the GNN architectures favored by each client, thus recommend GNN architectures that perform well in multiple datasets. In additions, FL-AGNNS applies the GNN super-network, a weight sharing strategy, to speed up the evaluation of GNN models during the search phase. Extensive experimental results show that FL-AGNNS can recommend better GNN models in short time under the federated learning framework, surpassing the state-of-the-arts GNN models.

关键词： Graph neural networks Federated learning Computer architecture Training Optimization Task analysis Servers Automated machine learning federated learning graph neural networks neural architecture search

来源：评论

学校读者我要写书评

暂无评论

neural-network-Based DOA Estimation in the Presence of Non-Gaussian Interference

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2024年第1期60卷 119-132页

作者： Feintuch, Stefan Tabrikian, Joseph Bilik, Igal Permuter, Haim Ben Gurion Univ Negev Sch Elect & Comp Engn IL-8410501 Beer Sheva Israel

This work addresses the problem of direction-of-arrival (DOA) estimation in the presence of non-Gaussian, heavy-tailed, and spatially-colored interference. Conventionally, the interference is considered to be Gaussian-distributed and spatially white. However, in practice, this assumption is not guaranteed, which results in degraded DOA estimation performance. Maximum likelihood DOA estimation in the presence of non-Gaussian and spatially-colored interference is computationally complex and not practical. Therefore, this work proposes a neural network (NN)-based DOA estimation approach for spatial spectrum estimation in multisource scenarios with an a priori unknown number of sources in the presence of non-Gaussian spatially-colored interference. The proposed approach utilizes a single NN instance for simultaneous source enumeration and DOA estimation. It is shown via simulations that the proposed approach significantly outperforms conventional and NN-based approaches in terms of probability of resolution, estimation accuracy, and source enumeration accuracy in conditions of low signal-to-interference ratio, small-sample support, and when the angular separation between the source DOAs and the spatially-colored interference is small.

关键词： Direction-of-arrival estimation Interference Estimation Heavily-tailed distribution Covariance matrices Thermal noise Spatial resolution Akaike information criterion (AIC) array processing deep learning direction-of-arrival (DOA) estimation machine learning minimum descriptive length (MDL) minimum-variance-distortionless-response (MVDR) neural networks (NNs) non-Gaussian interference radar source enumeration spatially-colored interference

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Cooperative LiDAR Sensing for Improved Vehicle Positioning

引用

IEEE TRANSACTIONS ON SIGNAL processing 2024年 72卷 1666-1682页

作者： Barbieri, Luca Tedeschini, Bernardo Camajori Brambilla, Mattia Nicoli, Monica Politecn Milan Dipartimento Elettron Informaz & Bioingn DEIB I-20133 Milan Italy Politecn Milan Dipartimento Ingn Gestionale DIG I-20133 Milan Italy

Accurate positioning is known to be a fundamental requirement for the deployment of Connected Automated Vehicles (CAVs). To meet this need, a new emerging trend is represented by cooperative methods where vehicles fuse information coming from navigation and imaging sensors for joint positioning and environmental perception. In line with this trend, this paper proposes a novel data-driven cooperative sensing framework, termed Cooperative LiDAR Sensing with Message Passing neural network (CLS-MPNN), where spatially-distributed vehicles collaborate in perceiving the environment via LiDAR sensors. Vehicles process their LiDAR point clouds using a Deep neural network (DNN), namely a 3D object detector, to identify and localize possible static objects in the driving environment. Data are then aggregated by a centralized infrastructure that performs Data Association (DA) using a Message Passing neural network (MPNN) and runs the Implicit Cooperative Positioning (ICP) algorithm. The proposed approach is evaluated using two realistic driving scenarios generated by a high-fidelity automated driving simulator. The results show that CLS-MPNN outperforms a conventional non-cooperative localization algorithm based on Global Navigation Satellite System (GNSS) and a state-of-the-art cooperative Simultaneous Localization and Mapping (SLAM) method while approaching the performances of an oracle system with ideal sensing and perfect association.

关键词： Connected automated vehicles cooperative LiDAR sensing data association 3D object detection message passing neural networks positioning SLAM

来源：评论

学校读者我要写书评

暂无评论

Optimal design of a 15 kW-class interior permanent magnet synchronous motor for micro-EV traction using artificial neural network models

引用

MICROSYSTEM TECHNOLOGIES-MICRO-AND NANOSYSTEMS-INFORMATION STORAGE AND processing SYSTEMS 2023年第8期29卷 1165-1179页

作者： Kim, Hyeon-Jun Baek, Soo-Whang Sangmyung Univ Dept Elect Informat Syst Engn Cheonan 31066 South Korea Sangmyung Univ Dept Human Intelligence & Robot Engn Cheonan 31066 South Korea

This study proposes an optimal design using artificial neural network models to improve the efficiency of a 15 kW-class interior permanent magnet synchronous motor (IPMSM) used in micro electric vehicles (EVs). The proposed method improves the efficiency of the initial IPMSM model by combining the number of poles and slots as well as the shape design of the rotor. The number of poles used and the combination of slots were determined according to the purpose of the micro-EV motor, the windings of the stator were changed from distributed winding to concentrated winding, and the dimensions of the rotor were selected to maximize efficiency. We realize the optimal design was performed with using a model with having a structure of a concentrated winding stator 18-slot rotor12-poles in the IPMSM having with a distributed winding stator 48-slot rotor 8-pole structure as an initial model. The objective function and constraints were determined for the optimal design and as a metamodel, we applied recurrent neural network and long short-term memory models. The optimal metamodel was selected by comparing the root-mean-square error test results according to the efficiency and cogging torque characteristics to evaluate its accuracy. We validate the optimal design result derived based on the proposed shape-optimization method through finite element analysis. An optimal model of the 15 kW-class IPMSM prototype used in micro-EVs was designed for validation. The efficiency performance improved by 1.6%, as validated through a motor dynamo test.

关键词： Stators

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：