检索结果-内蒙古大学图书馆

Prognostics and System Health Management Conference (PHM-Qingdao)

作者： Chunyu Ju Qinghua Luo Xiaozhen Yan The Guangxi Key Laboratory of Automatic Detecting technology and Instruments Guilin China The auto test and control institute Shandong institute of shipping weihai

ISBN: (数字)9781728159461

ISBN: (纸本)9781728159478

Aiming at the deficiencies in A-star algorithm and artificial potential field method, this paper proposes a fusion algorithm based on artificial potential field method and A-star algorithm. Although the A-star algorithm can obtain a relatively short path, it cannot handle dynamic obstacles, the artificial potential field method can handle dynamic obstacles but the generated path is much longer than the A-star algorithm. Artificial potential field method and A-star fusion algorithm is proposed to avoid dynamic obstacles and find a shorter path simultaneously. Then we evaluated our proposed method by comparing it with the A-star algorithm, artificial potential field method and two other reference methods. The simulation results show that our proposed method can generate a shorter path and effectively avoid dynamic obstacles.

关键词： Heuristic algorithms Simulation Real-time systems Path planning Reliability Mobile robots Prognostics and health management

来源：评论

学校读者我要写书评

暂无评论

Path Planning Using Artificial Potential Field Method and A-star Fusion Algorithm

Path Planning Using Artificial Potential Field Method and A-...

引用

2020 Global Reliability and Prognostics and Health Management, PHM-Shanghai 2020

作者： Ju, Chunyu Luo, Qinghua Yan, Xiaozhen School of Information Science and Engineering Harbin Institute of Technology weihai China Shandong Institute of Shipbuilding Technology Weihai China Shandong New Beiyang Information Technology Co. Ltd. Weihai China The Guangxi Key Laboratory of Automatic Detecting technology and Instruments Guilin China The Auto Test and Control Institute Shandong Institute of Shipping Weihai China

ISBN: (纸本)9781728159454

关键词： Stars

来源：评论

学校读者我要写书评

暂无评论

Bearing health condition prediction using deep belief network 9

Bearing health condition prediction using deep belief networ...

引用

9th Annual Conference of the Prognostics and Health Management Society, PHM 2017

作者： Zhao, Guangquan Liu, Xiaoyong Zhang, Bin Zhang, Guohui Niu, Guangxing Hu, Cong Department of Automatic Test and Control Harbin Institute of Technology Harbin Heilongjiang150080 China Department of Electrical Engineering University of South Carolina ColumbiaSC29208 United States Guangxi Key Laboratory of Automatic Detecting Technology and Instruments Guilin University of Electronic Technology Guilin Guangxi541004 China

ISBN: (纸本)9781936263264

Bearings play a critical role in maintaining safety andreliability of rotating machinery. Bearings health conditionprediction aims to prevent unexpected failures and minimizeoverall maintenance costs since it provides decision makinginformation for condition-based maintenance. This paperproposes a Deep Belief Network (DBN)-based data-drivenhealth condition prediction method for bearings. In thisprediction method, a DBN is used as the predictor, whichincludes stacked RBMs and regression output. Our maincontributions include development of a deep leaning-baseddata-driven prognosis solution that does not rely on explicitmodel equations and prognostic expertise, and providingcomprehensive prediction results on five representative runto-failure bearings. The IEEE PHM 2012 challenge datasetis used to demonstrate the effectiveness of the proposedmethod, and the results are compared with two existingmethods. The results show that the proposed method haspromising performance in terms of short-term healthcondition prediction and remaining useful life prediction forbearings. © 2017 Prognostics and Health Management Society. All rights reserved.

关键词： Condition based maintenance

来源：评论

学校读者我要写书评

暂无评论

Lithium-ion battery remaining useful life prediction with long short-term memory recurrent neural network 9

Lithium-ion battery remaining useful life prediction with lo...

引用

9th Annual Conference of the Prognostics and Health Management Society, PHM 2017

作者： Liu, Yuefeng Zhao, Guangquan Peng, Xiyuan Hu, Cong Department of Automatic Test and Control Harbin Institute of Technology Harbin Heilongjiang150001 China School of Information Engineering Inner Mongolia University of Science and Technology Baotou Inner Mongolia Autonomous region014010 China Guangxi Key Laboratory of Automatic Detecting Technology and Instruments Guilin University of Electronic Technology Guilin Guangxi541004 China

ISBN: (纸本)9781936263264

Lithium-ion batteries play critical roles in many electronicdevices. It is necessary to develop a reliable and accurateremaining useful life (RUL) prediction approach to providetimely maintenance or replacement of battery systems. Anovel RUL prediction approach based on Long Short-termMemory (LSTM) Recurrent Neural Network (RNN) isproposed in this paper. LSTM is able to capture long-termdependencies and model sequential data among the capacitydegradation of lithium-ion batteries. The advantages of ourproposed method include: 1) obtaining high predictionaccuracy without accurate physics-based model or expertiseand 2) decreasing the cumulation errors by multi-step aheadprediction each time, while traditional RUL method predictsone-step ahead once and then uses the current estimatedvalue to predict next one, which causes cumulation errorsincreased. The Center for Advanced Life Cycle Engineering(CALCE) battery datasets are used to demonstrate theeffectiveness of the proposed method. The results show that,compared with echo state networks (ESN), the proposedmethod has higher accuracy, more stable and reliableperformance for lithium-ion batteries RUL prediction. © 2017 Prognostics and Health Management Society. All rights reserved.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

F-CNN: An FPGA-based framework for training Convolutional Neural Networks

F-CNN: An FPGA-based framework for training Convolutional Ne...

引用

International Conference on Application Specific Systems (ASAP), Architectures and Processors

作者： Wenlai Zhao Haohuan Fu Wayne Luk Teng Yu Shaojun Wang Bo Feng Yuchun Ma Guangwen Yang Ministry of Education Key Laboratory for Earth System Modeling and Center for Earth System Science Tsinghua University China Tsinghua National Laboratory for Information Science and Technology China Department of Computing Imperial college London UK Department of Automatic Test and Control Harbin Institute of Technology China Department of Computer Science and Technology Tsinghua University China

ISBN: (纸本)9781509015047

This paper presents a novel reconfigurable framework for training Convolutional Neural Networks (CNNs). The proposed framework is based on reconfiguring a streaming datapath at runtime to cover the training cycle for the various layers in a CNN. The streaming datapath can support various parameterized modules which can be customized to produce implementations with different trade-offs in performance and resource usage. The modules follow the same input and output data layout, simplifying configuration scheduling. For different layers, instances of the modules contain different computation kernels in parallel, which can be customized with different layer configurations and data precision. The associated models on performance, resource and bandwidth can be used in deriving parameters for the datapath to guide the analysis of design trade-offs to meet application requirements or platform constraints. They enable estimation of the implementation specifications given different layer configurations, to maximize performance under the constraints on bandwidth and hardware resources. Experimental results indicate that the proposed module design targeting Maxeler technology can achieve a performance of 62.06 GFLOPS for 32-bit floating-point arithmetic, outperforming existing accelerators. Further evaluation based on training LeNet-5 shows that the proposed framework achieves about 4 times faster than CPU implementation of Caffe and about 7.5 times more energy efficient than the GPU implementation of Caffe.

关键词： Training Field programmable gate arrays Convolution Computational modeling Bandwidth Neural networks Runtime

来源：评论

学校读者我要写书评

暂无评论

A joint recovery algorithm for distributed sub-Nyquist sampling based on MWC

引用

Advances in Information Sciences and Service Sciences 2012年第16期4卷 233-241页

作者： Gai, Jianxin Qiao, Jiaqing Fu, Ping Fu, Ning Department of Automatic Test and Control Harbin Institute of Technology Harbin 150001 China The Higher Educational Key Laboratory for Measuring and Control Technology Instrumentations of Heilongjiang Province Harbin University of Science and Technology Harbin 150080 China

The sub-Nyquist sampling based on Modulated Wideband Converter (MWC) is an emerging sampling method. This method can perform sampling at a low rate below Nyquist frequency for sparse wideband signals using existing devices and achieve a perfect recovery. However, for some tasks, the recovery performance of a single MWC is far from satisfactory. In this paper, we present a distributed sub-Nyquist sampling method and especially a joint recovery algorithm. The proposed sampling method and recovery algorithm can significantly improve the recovery performance with the increase of signal numbers by making full use of the joint sparse structure across multiple signals and the diversity of sampling matrices. Numerical experiments show that, compared with separate recovery method, the proposed joint recovery approach enhances the recovery performance in terms of recovery rate, and it even can achieve a success when the separate recovery for each MWC fails.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

A blind recovery algorithm for spectrum-sparse signals sub-Nyquist sampling

A blind recovery algorithm for spectrum-sparse signals sub-N...

引用

6th International Forum on Strategic Technology, IFOST 2011

作者： Gai, Jianxin Tong, Ziquan Cheng, Shuang Wang, Junjie Liu, Xu Higher Educational Key Laboratory for Measuring and Control Technology Instrumentations of Heilongjiang Province Harbin University of Science and Technology Harbin China Department of Automatic Test and Control Harbin Institute of Technology Harbin China

ISBN: (纸本)9781457703966

Wideband analog signals push contemporary analog- to-digital conversion systems to their performance limits. The recent development of compressive sensing theory enables direct analog-to-information conversion of sparse (or compressible) signals at sub-Nyquist rate. In this paper, we implement spectrum-sparse signals sub-Nyquist sampling by use of Modulated Wide Converter (MWC). To overcome the drawback of requiring exact sparsity of the existing recovery algorithm, we introduce the Sparsity Adaptive Matching Pursuit (SAMP) method into reconstruction stage to search the support set of unknown signal vectors blindly. The numerical experiments demonstrate that the MWC system with the proposed recovery algorithm can implement spectrum-sparse signals sub-Nyqiust sampling and perfect reconstruction under the condition of not knowing exact sparsity. © 2011 IEEE.

关键词： Analog to digital conversion

来源：评论

学校读者我要写书评

暂无评论

A digital demodulation method for amplitude modulated signal based on sub-Nyquist sampling

A digital demodulation method for amplitude modulated signal...

引用

International Conference on Pervasive Computing, Signal Processing and Applications

作者： Gai, Jian-Xin Fu, Ping Yin, Hong-Tao Department of Automatic Test and Control Harbin Institute of Technology Harbin China Higher Educational Key Laboratory for Measuring and Control Technology Instrumentations of Heilongjiang Province Harbin University of Science and Technology Harbin China

ISBN: (纸本)9780769541808

Digital demodulation technology confronts the pressure from sampling rate due to the wide bandwidth of radio transmission. The recent development of compressive sensing theory enables sub-Nyquist sampling. In this paper, we utilize an implementation approach of sub-Nyquist sampling - Modulated Wide Converter (MWC) - to demodulate a given frequency band from multiband signal of radio transmission. The paper analyzes the behavior in frequency domain of MWC sampling and reveals the essence of sampling process as spectrum segmenting. Considering demodulation of multiband signal, we optimize the spectrum segmentation through choosing optimal parameters for MWC to reduce the impact of nonideal analog lowpass filter. The numerical experiments demonstrate that the MWC with the improved configuration can eliminate the impact of analog filters and achieve perfect demodulation performance. © 2010 IEEE.

关键词： Demodulation

来源：评论

学校读者我要写书评

暂无评论

A Digital Demodulation Method for Amplitude Modulated Signal Based on Sub-Nyquist Sampling

A Digital Demodulation Method for Amplitude Modulated Signal...

引用

International Conference on Pervasive Computing Signal Processing and Applications (PCSPA)

作者： Jian-Xin Gai Ping Fu Hong-Tao Yin Department of Automatic Test and Control Harbin Institute of Technology Harbin China Higher Educational key laboratory of Measuring & Control Technology and Instrumentations of Heilongjiang Province Harbin University of Science and Technology Harbin China

Digital demodulation technology confronts the pressure from sampling rate due to the wide bandwidth of radio transmission. The recent development of compressive sensing theory enables sub-Nyquist sampling. In this paper, we utilize an implementation approach of sub-Nyquist sampling--Modulated Wide Converter (MWC)-to demodulate a given frequency band from multiband signal of radio transmission. The paper analyzes the behavior in frequency domain of MWC sampling and reveals the essence of sampling process as spectrum segmenting. Considering demodulation of multiband signal, we optimize the spectrum segmentation through choosing optimal parameters for MWC to reduce the impact of nonideal analog lowpass filter. The numerical experiments demonstrate that the MWC with the improved configuration can eliminate the impact of analog filters and achieve perfect demodulation performance.

关键词： Baseband Demodulation Wideband Filtering theory Frequency domain analysis Frequency modulation Bismuth

来源：评论

学校读者我要写书评

暂无评论

A novel temperature-insensitive strain sensor based on tapered fiber grating

引用

Optoelectronics Letters 2007年第5期3卷 342-345页

作者： YANG Xian-hui YU Yong-sen ZHANG Qiu-hua SUN Sheng-he Department of Automatic Test and Control Harbin Institute of Technology Harbin 150001 China State Key Laboratory on Integrated Optoelectronics Jilin University Changchun 130023 China Department of Astronautic Engineering and Mechanics Harbin Institute of Technology Harbin 150001 China

A novel temperature-insensitive strain sensor based on bandwidth demodulation of the reflected light from the tapered fiber grating is presented, which is simple and low-cost and has considerable potential particularly application for strain sensing,and with the development of the interrogation system, it can demodulate both the bandwidth and the center wavelength of the reflected light from TFG to measure strain and temperature simultaneously.

关键词：光学纤维光栅传感器温度

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：