用于气敏传感器漂移补偿的数据选择方法

针对传感器在线漂移补偿中可能存在多种状态的样本,进而引起误判的情况,提出了一种新的数据剔除与判别方法,该方法将传感器阵列响应曲线斜率作为依据进行数据剔除,同时将输入样本与模式识别算法中的记忆知识进行对比,从而进行数据归类,以此避免识别错误的发生.实验表明:该方法配合在线漂移补偿方法后,能够自动判断当前样本所处状态.识别正确率由37.5％提升至100％.

A data selection method applied to on-line drift compensation for gas sensors

A new data culling and labeling method is proposed to avoid misleading outcomes caused by multi-state samples during drift compensation process. This method culls data by the curve slops of gas sensor array response and labels data by comparing input samples with the memories of pattern recognition algorithm to avoid occurrence of misleading results. Experiments show the method combined with on-line drift compensation algorithm can estimate sample-states automatically and increase the recognizing accuracy from 37.5% to 100%.