• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文学位 >Intelligent health monitoring of structures using smart sensors, wavelet neural networks and fuzzy logic.
【24h】

Intelligent health monitoring of structures using smart sensors, wavelet neural networks and fuzzy logic.

机译：使用智能传感器，小波神经网络和模糊逻辑对结构进行智能健康监测。

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The purpose of this study is to investigate the compatibility of Self-Powered Sensors and Low-Power Wireless Protocol in a Structural Health Monitoring System. The other purpose of the project is to exploit the ever increasing computational capabilities of computers by transferring the processing burden away from complex hardware traditionally used in health monitoring. Thus the major focus of the project is to develop new sensing capabilities that use vibration as a way to detect structural damage as well as to power sensors and the ultra low-power data distribution system for information dissemination. The goal of the project is to reduce the use of expensive sensing, signal processing and data acquisition systems toward a simpler, energy-efficient, easily scalable, cost-efficient and intelligent prognostics health monitoring system.;Power Output tests were conducted on aircraft representative structural specimens using PZT Ceramics as primary strain measuring sensors. These sensors were integrated with sensor validation algorithms and sensor output prediction mathematical models to constantly monitor the sensor integrity in real-time. These sensors were further integrated with Diagnostic and Prognostic Neural Networks. The Diagnostic Neural Network (DNN) based on multi-resolution temporal signals monitor data from various sensors to recognize any potential structural flaw. Since the DNN is a parallel signal processing paradigm and since it is based on multi-resolution analysis, these systems can be easily adapted to real-time health monitoring. A Prognostic Neuro-Fuzzy System has also been developed in the project to predict the amount of life a structural member has endured.;Since the focus of the project from the start has been away from expensive sensing capabilities and toward intelligent algorithms working on simple processor cores, one can achieve better fault-tolerant capabilities. Also, since the core of the health monitoring is done by the micro-controllers, the number of potential points of failure is drastically reduced. Hence one does not require a monitoring system for a structural monitoring system.
机译：这项研究的目的是研究结构健康监测系统中自供电传感器和低功率无线协议的兼容性。该项目的另一个目的是通过将处理负担从健康监测中传统使用的复杂硬件上转移下来，从而利用计算机不断增长的计算能力。因此，该项目的主要重点是开发新的传感功能，该功能将振动用作检测结构损坏的方法，并用于功率传感器和超低功率数据分发系统以进行信息传播。该项目的目标是减少对昂贵的传感，信号处理和数据采集系统的使用，而转向更简单，节能，易于扩展，具有成本效益的智能预测健康监测系统。使用PZT陶瓷作为主要应变测量传感器的结构样本。这些传感器与传感器验证算法和传感器输出预测数学模型集成在一起，以不断地实时监控传感器的完整性。这些传感器进一步与诊断和预后神经网络集成在一起。基于多分辨率时间信号的诊断神经网络（DNN）监视来自各种传感器的数据，以识别任何潜在的结构缺陷。由于DNN是并行信号处理范例，并且由于它基于多分辨率分析，因此这些系统可以轻松地适用于实时健康状况监视。在该项目中还开发了预后神经模糊系统，以预测结构构件的寿命。由于该项目的重点从一开始就已经从昂贵的传感功能转向了在简单处理器上工作的智能算法。内核，可以实现更好的容错能力。另外，由于健康监控的核心是由微控制器完成的，因此潜在故障点的数量大大减少了。因此，不需要结构监视系统的监视系统。

著录项

  • 作者

    Sadhu, Suman.;

  • 作者单位

    University of Kansas.;

  • 授予单位 University of Kansas.;
  • 学科 Engineering Aerospace.
  • 学位 M.S.
  • 年度 2010
  • 页码 169 p.
  • 总页数 169
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号