【摘要】 随着智能化、网络化传感器技术的日益成熟,无线传感网络在人类生活以及商业等领域有着广泛的应用,无线传感器网络节点通常只携带有限的资源,容易出现因资源不足而导致的故障,对WSN节点进行准确、及时的故障诊断,能够保障获得信息可靠性,从而提高WSN可维护性并且延长WSN的使用寿命。针对该问题,提出一种使用核偏最小二乘法来预测故障原因的方法,该方法克服了传统线性回归方法的缺陷,在高维的非线性空间对数据进行分析,同时,该方法也吸收了典型相关分析和主成分分析方法的特点,为分析提供了更加深入、丰富的内容,实验结果表明,提出的方法能够有效预测到故障原因。更多还原

【Abstract】 With the development of intelligent and networked sensor technology,wireless sensor networks were widely used in human life and commercial fields,because wireless sensor network nodes usually only carry limited resources,it is prone to failures due to insufficient resources,the accurate and timely fault diagnosis of WSN nodes can ensure the reliability of information,thus improving the maintainability of WSN and prolonging the service life of WSN.A method of using kernel partial least squares has been proposed to predict the fault reasons,the method overcomes the defects of traditional linear regression method and the nonlinear high dimensional space for data analysis.Through many experiments,the method can absorb the characteristics of canonical correlation analysis and principal component analysis method,provide a more thorough and rich content analysi,that the reason of the fault can be predicted effectively.更多还原