Wu Leon Li author Columbia University. Computer Science Columbia University. Center for Computational Learning Systems Teravainen Timothy Kaleva author Columbia University. Statistics Kaiser Gail E. author Columbia University. Computer Science Anderson Roger N. author Columbia University. Center for Computational Learning Systems Boulanger Albert G. author Columbia University. Center for Computational Learning Systems Rudin Cynthia author Columbia University. Computer Science originator contributor text Technical reports New York Department of Computer Science, Columbia University 2011 An important problem in reliability engineering is to predict the failure rate, that is, the frequency with which an engineered system or component fails. This paper presents a new method of estimating failure rate using a semiparametric model with Gaussian process smoothing. The method is able to provide accurate estimation based on historical data and it does not make strong a priori assumptions of failure rate pattern (e.g., constant or monotonic). Our experiments of applying this method in power system failure data compared with other models show its efficacy and accuracy. This method can be used in estimating reliability for many other systems, such as software systems or components. Computer science CUCS-015-11 http://hdl.handle.net/10022/AC:P:10670 English NNC NNC 2011-07-08 12:08:15 -0400 2011-07-08 12:22:19 -0400 4621 eng