目前消除干扰量对主传感器特性影响的研究多限于一个干扰量，本文讨论多个干扰量影响的消除方法，文中提出利用多个传感器检测影响主传感器特性的多个非目标参量，由神经网络实现融合算法。该方法可降低主传感器对非目标参量的交叉灵敏度。使主传感器系统获得高抗干扰、高稳定的输入／输出特性.以环境与供电电源波动两个干扰量为例.实验结果表明，当环境温度波动△T=48.5C，供电电源波动γ＝±3％，经神经网络融合处理后，主传感器系统在两种干扰状况下的交叉灵敏度下降一个数量级.%At present, studies on how to eliminate the factors intervening the performance of main sensors are mostly limited in the single-factor case. A method for eliminatingmultiple non-aim parameters is discussed in this paper. By virtue of this method, the cross-sensitivity of main sensors to non-aim parameters are decreased, thus the main sensor system can obtain high antiinterference ability and stable input-output characteristics. Supposed environmental temperature flux △T and the power flux γ as two interference factors, the experimental results show that for the case of △T=48.5℃ and γ=±3%, the cross-sensitivity of the main sensor system reduces for one order of magnitude after the neural-network and the data fusion method are used.
展开▼
