检索结果-内蒙古大学图书馆

Vibration signal demodulation and bearing fault detection: A clustering-based segmentation method

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE 2014年第11期228卷 1888-1899页

作者： Hou, Shumin Liang, Ming Zhang, Yi Li, Chuan Univ Ottawa Dept Mech Engn Ottawa ON K1N 6N5 Canada ZEC Wind Power Ottawa ON Canada Chongqing Technol & Business Univ Engn Lab Detect Control & Integrated Syst Chongqing Peoples R China

The resonance demodulation technique has been widely employed in vibration signal analysis. In order to construct a proper bandpass filter, the prior knowledge, i.e. the resonance frequency band of the mechanical system is required in the traditional demodulation method. However, as the collected vibration signal is often tainted by the background noise and interferences often with unknown frequency contents, it is difficult to identify the center frequency and the bandwidth of the filter. This paper introduces a clustering-based segmentation method to determine these parameters automatically. Envelope analysis is then applied to demodulating the vibration data. According to the simulated cases, the proposed approach is robust to Gaussian noise and interferences. Its effectiveness is further validated by applying it to detect rolling bearing faults based on experimental data.

关键词： clustering-based segmentation signal demodulation vibration signal fault detection bearings

来源：评论

学校读者我要写书评

暂无评论

Removing Smoothing Effects for Color Image segmentation

Removing Smoothing Effects for Color Image Segmentation

引用

IEEE International Conference on Systems, Man, and Cybernetics (SMC)

作者： Cheng, Wen-Chang Tseng, Hua-Hung Chaoyang Univ Technol Dept Comp Sci & Informat Engn Taichung Taiwan

ISBN: (纸本)9781479986965

In this study, we described the effects of image smoothing on image segmentation, introduced a method proposed by Yang et al. for removing smoothing effects (hereafter referred as Yang's method), and modified this method to solve image segmentation problems. The results showed that Yang's smoothing method still required further improvements;therefore, two solutions to solving problems related to this method were proposed. In Yang's method, the researchers only considered removing the effects of central pixels in a mask on mask calculation, neglecting the effects of edge pixels in a region of a mask on mask calculation. Therefore, we incorporated an edge mask calculation into Yang's method. Moreover, in Yang's method, distinct color masks are contained in the color components of a single pixel, which cause these components to yield differing adjustment results. Thus, the solution to this problem is to adopt a single-colored mask for color adjustments. The experimental results verified that the method proposed in this study effectively improved Yang's method and removed the effects of smoothing on image segmentation.

关键词： Local information adaptive mask denoising fuzzy c-mean clustering-based segmentation

来源：评论

学校读者我要写书评

暂无评论

A New Modification of Fuzzy C-Means via Particle Swarm Optimization for Noisy Image segmentation 2nd

A New Modification of Fuzzy C-Means via Particle Swarm Optim...

引用

2nd Australasian Conference on Artificial Life and Computational Intelligence (ACALCI)

作者： Mirghasemi, Saeed Rayudu, Ramesh Zhang, Mengjie Victoria Univ Wellington Sch Engn & Comp Sci Wellington New Zealand

ISBN: (纸本)9783319282701;9783319282695

This paper presents a new clustering-based algorithm for noisy image segmentation. Fuzzy C-Means (FCM), empowered with a new similarity metric, acts as the clustering method. The common Euclidean distance metric in FCM has been modified with information extracted from a local neighboring window surrounding each pixel. Having different local features extracted for each pixel, Particle Swarm Optimization (PSO) is utilized to combine them in a weighting scheme while forming the proposed similarity metric. This allows each feature to contribute to the clustering performance, resulting in more accurate segmentation results in noisy images compared to other state-of-the-art methods.

关键词： Particle swarm optimization Fuzzy C-means Noisy image segmentation clustering-based segmentation Similarity metrics

来源：评论

学校读者我要写书评

暂无评论

Estimation of the Dynamic Contact Area From a Rolling Tire Correlated to Expert Assessment

引用

IEEE ACCESS 2019年 7卷 97909-97918页

作者： Nava, Rodrigo Fehr, Duc Petry, Frank Tamisier, Thomas Luxembourg Inst Sci & Technol L-4422 Belvaux Luxembourg Goodyear Innovat Ctr Luxembourg L-7750 Colmar Berg Luxembourg

Characteristics of the tire footprint are major indicators of tire performance and provide relevant information that can be used to improve the tire design process. However, the accurate segmentation of the tire footprint requires prior training and can be a highly man-hour consuming task. In order to overcome such drawbacks, scientists have made multiple efforts to design methods for segmenting the tire footprint automatically but it is still an open problem. In this paper, we propose a novel methodology to estimate the tire footprint under dynamic conditions and conduct an extensive subjective assessment of its quality. For this aim, we designed a subjective evaluation procedure based on the ITU-R BT. 500-13 recommendation. In addition, we include a quantitative comparison of several tire contact patch segmentation methods using ray feature error and Dice index. The results of our methodology have been evaluated by expert tire engineers and will allow us to improve the tire manufacturing process.

关键词： clustering-based segmentation dynamic tire footprint fuzzy C-means K-means plus multi-thresholding quantitative evaluation ray feature error subjective assessment superpixels

来源：评论

学校读者我要写书评

暂无评论

Brain Lesion Detection in MRI with Fuzzy and Geostatistical Models

Brain Lesion Detection in MRI with Fuzzy and Geostatistical ...

引用

32nd Annual International Conference of the IEEE Engineering-in-Medicine-and-Biology-Society (EMBC 10)

作者： Pham, Tuan D. Univ New S Wales Sch Informat Technol & Engn Canberra ACT 2600 Australia

ISBN: (纸本)9781424441242

Automated image detection of white matter changes of the brain is essentially helpful in providing a quantitative measure for studying the association of white matter lesions with other types of biomedical data. Such study allows the possibility of several medical hypothesis validations which lead to therapeutic treatment and prevention. This paper presents a new clustering-based segmentation approach for detecting white matter changes in magnetic resonance imaging with particular reference to cognitive decline in the elderly. The proposed method is formulated using the principles of fuzzy.. means algorithm and geostatistics.

关键词： MRI biomedical MRI brain brain lesion detection clustering-based segmentation cognition cognition elderly fuzzy c-means algorithm fuzzy set theory geostatistical models geriatrics image segmentation magnetic resonance imaging medical image processing statistical analysis white matter lesions

来源：评论

学校读者我要写书评

暂无评论

A method using EEMD and L-Kurtosis to detect faults in roller bearings

A method using EEMD and L-Kurtosis to detect faults in rolle...

引用

Prognostics and System Health Management Conference (PHM-Chongqing)

作者： Gao, Qiang Xiang, Jiawei Wenzhou Univ Coll Mech & Elect Engn Wenzhou Peoples R China

ISBN: (纸本)9781538653807

The presence of periodical impulses in vibration signals usually indicates the occurrence of faults in roller bearings. Unfortunately, in the complex working condition with the heavy noises, fault detection in mechanical systems is often difficult. To solve this problem, a hybrid method of ensemble empirical mode decomposition (EEMD) and L-Kurtosis clustering-based segmentation is proposed. EEMD is similar to empirical mode decomposition (EMD), which can express the intrinsic essence using simple and understandable algorithm to solve the mode mixing phenomenon. L-Kurtosis is the improved version of kurtosis to recognize the impulses without the influence of outliers. Furthermore, the L-Kurtosis value is employed as an indicator in the clustering-based segmentation method to extract the fault features from the background noises. To illustrate the feasibility of utilizing the EEMD and L-Kurtosis based clustering segmentation method, benchmark data simulations and experimental investigations are performed to detect faults in bearings. The results show that the proposed method enables the efficient recognition of faults in bearings.

关键词： ensemble empirical mode decomposition L-Kurtosis clustering-based segmentation fault detection roller bearings

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：