交叠分段拟合在热传感器线性化中的应用

A Linearization Method for Heat Sensor Calibration Based on Fitting by Overlapping Segments

分段最小二乘多项式拟合是一种常用的传感器线性化函数生成方法。针对常规分段策略下相邻分段间经常出现跳变的问题,提出交叠分段拟合方法,先按预设的交叠比逐段进行拟合;然后在交叠区中搜索距离最近的点,作为相邻段的实际分界点。实验结果表明:当交叠比取0.30时,该方法能够在总分段数略有增加的情况下,有效抑制分段处的跳变。

Segmented least squares polynomial fitting is a commonly-used method for generating a sensor lin- earization function. Aiming at the hopping appeared between adjacent segments when classical segmentation strategy was applied, a fitting method based on overlapping segments strategy was proposed, in which, imple- menting the fitting segment by segment according to a preset overlapping ratio,and then searching the nearest point in the overlap region and taking it as the actual segmented point. Experimental results show that when the overlap ratio is O. 30 and the number of segments increases slightly, the method can effectively suppress the hopping between segments at the same time.