Particle filtering （PF） is being applied successfully in nonlinear and/or non-Gaussian system failure prognosis. However, for failure prediction of many complex systems whose dynamic state evolution models involve t...Particle filtering （PF） is being applied successfully in nonlinear and/or non-Gaussian system failure prognosis. However, for failure prediction of many complex systems whose dynamic state evolution models involve time-varying parameters, the tradi- tional PF-based prognosis framework will probably generate serious deviations in results since it implements prediction through iterative calculation using the state models. To address the problem, this paper develops a novel integrated PF-LSSVR frame- work based on PF and least squares support vector regression （LSSVR） for nonlinear system failure prognosis. This approach employs LSSVR for long-term observation series prediction and applies PF-based dual estimation to collaboratively estimate the values of system states and parameters of the corresponding future time instances. Meantime, the propagation of prediction un- certainty is emphatically taken into account. Therefore, PF-LSSVR avoids over-dependency on system state models in prediction phase. With a two-sided failure definition, the probability distribution of system remaining useful life （RUL） is accessed and the corresponding methods of calculating performance evaluation metrics are put forward. The PF-LSSVR framework is applied to a three-vessel water tank system failure prognosis and it has much higher prediction accuracy and confidence level than traditional PF-based framework.展开更多
Dynamic time-varying operational conditions pose great challenge to the estimation of system remaining useful life （RUL） for the deteriorating systems. This paper presents a method based on probabilistic and stochas...Dynamic time-varying operational conditions pose great challenge to the estimation of system remaining useful life （RUL） for the deteriorating systems. This paper presents a method based on probabilistic and stochastic approaches to estimate system RUL for periodically moni- tored degradation processes with dynamic time-varying operational conditions and condition- specific failure zones. The method assumes that the degradation rate is influenced by specific oper- ational condition and moreover, the transition between different operational conditions plays the most important role in affecting the degradation process. These operational conditioqs are assumed to evolve as a discrete-time Markov chain （DTMC）. The failure thresholds are also determined by specific operational conditions and described as different failure zones. The 2008 PHM Conference Challenge Data is utilized to illustrate our method, which contains mass sensory signals related to the degradation process of a commercial turbofan engine. The RUE estimation method using the sensor measurements of a single sensor was first developed, and then multiple vital sensors were selected through a particular optimization procedure in order to increase the prediction accuracy. The effectiveness and advantages of the proposed method are presented in a comparison with exist- ing methods for the same dataset.展开更多
基金Aeronautical Science Foundation of China (20100751010, 2010ZD11007)
文摘Particle filtering （PF） is being applied successfully in nonlinear and/or non-Gaussian system failure prognosis. However, for failure prediction of many complex systems whose dynamic state evolution models involve time-varying parameters, the tradi- tional PF-based prognosis framework will probably generate serious deviations in results since it implements prediction through iterative calculation using the state models. To address the problem, this paper develops a novel integrated PF-LSSVR frame- work based on PF and least squares support vector regression （LSSVR） for nonlinear system failure prognosis. This approach employs LSSVR for long-term observation series prediction and applies PF-based dual estimation to collaboratively estimate the values of system states and parameters of the corresponding future time instances. Meantime, the propagation of prediction un- certainty is emphatically taken into account. Therefore, PF-LSSVR avoids over-dependency on system state models in prediction phase. With a two-sided failure definition, the probability distribution of system remaining useful life （RUL） is accessed and the corresponding methods of calculating performance evaluation metrics are put forward. The PF-LSSVR framework is applied to a three-vessel water tank system failure prognosis and it has much higher prediction accuracy and confidence level than traditional PF-based framework.
基金supported by the Fundamental Research Funds for the Central Universities(No.YWF-14-ZDHXY-16)
文摘Dynamic time-varying operational conditions pose great challenge to the estimation of system remaining useful life （RUL） for the deteriorating systems. This paper presents a method based on probabilistic and stochastic approaches to estimate system RUL for periodically moni- tored degradation processes with dynamic time-varying operational conditions and condition- specific failure zones. The method assumes that the degradation rate is influenced by specific oper- ational condition and moreover, the transition between different operational conditions plays the most important role in affecting the degradation process. These operational conditioqs are assumed to evolve as a discrete-time Markov chain （DTMC）. The failure thresholds are also determined by specific operational conditions and described as different failure zones. The 2008 PHM Conference Challenge Data is utilized to illustrate our method, which contains mass sensory signals related to the degradation process of a commercial turbofan engine. The RUE estimation method using the sensor measurements of a single sensor was first developed, and then multiple vital sensors were selected through a particular optimization procedure in order to increase the prediction accuracy. The effectiveness and advantages of the proposed method are presented in a comparison with exist- ing methods for the same dataset.
