胎儿心电图(FECG)是反映胎儿心脏电生理活动的一项客观指标,获取的FECG受到母体心电图(MECG)的干扰,如何快捷、有效的提取FECG成为重要的研究课题。在非侵入方式下,FECG的提取算法中独立成分分析(ICA)算法被认为是效果最好的方法,但现有求解其分解矩阵的算法收敛性能都不太高。量子粒子群(QPSO)算法是一种收敛于全局的智能优化算法。因此,提出了一种结合QPSO的ICA方法。研究结果表明,与其他在非侵入方式下的主要提取算法相比,这种方法能更清晰准确地提取出有用信号,为胎儿的健康检测提供了更好的方法。 Fetal electrocardiogram (FECG) is an objective indicator of electrophysiological activity in fetal heart. Fetal ECG obtained is disturbed by maternal electrocardiogram (MECG). How to extract FECG rapidly and effectively has become an important research topic. In the non-intrusive way, the independent component analysis (ICA) algorithm of FECG extraction algorithm is considered as the best method, but the existing convergence algorithms of its decomposition matrix are not very high. Quantum Particle Swarm Optimization (QPSO) is a kind of intelligent optimization algorithm that converges to the global. Therefore, an ICA method combined with QPSO is proposed. The results show that this method can extract useful signals more clearly and accurately than other main algorithms in noninvasive mode, which provides a better method for fetal health detection.