【摘要】 针对时变模型建模或大数据量情况下建模过程中的野点检测问题,提出了鲁棒递推偏最小二乘法(RRPLS).通过将递推偏最小二乘法(RPLS)与鲁棒主分量回归算法(RPPSV)相结合,实现分块野点检测算法,有效地解决了一般野点检测算法的计算量大的问题.仿真说明鲁棒递推偏最小二乘法不但能检测出数据中的野点还能大量减少建模时间,最后给出了在交流异步电力测功机系统的应用实例.更多还原

【Abstract】 A robust recursive partial least-squares algorithm(RPLS) was proposed to solve the large computation burden problem of outlier detection algorithm in regression for time-varying system or massive data.By combining PRLS and robust principal components regression based on principal sensitivity vectors(RPPSV),the block-wise outlier detection algorithm was carried out,which effectively overcame the shortcoming of large computation burden in common outlier detection algorithm.Simulation results have proved that RPPSV can find outliers efficiently and greatly reduce the recursive modeling time.At last,an application of RPPSV in the system of AC asynchronous electrical dynamometer was presented.更多还原