测量仪器校准间隔的模糊范数融合预测

校准间隔的预测是解决测量仪器不足校准和过剩校准的一种主要方法。现有校准间隔预测模型仅仅关注瞬时值,而随机因素的存在导致瞬时值难以精确预测。针对这一问题,在历史校准数据为小样本条件下,提出一种模糊范数融合模型,进行测量仪器校准间隔预测。首先,通过分析历史校准数据的特征和影响因素,建立了校准数据的数学描述模型。在此基础上,采用模糊范数融合模型,预测校准数据的区间。实验表明,模糊范数融合模型更能反映校准数据序列的变化趋势,克服了其它预测模型仅仅预测瞬时值的缺点,提高了预测的可靠性。

Prediction of Calibration Interval for Measuring Instrument Using Fuzzy Norm Fusion Model

Prediction of the measuring instrument calibration interval is a main method to solve insufficient calibration and surplus calibration. Those used prediction models at present only focus on prediction of the instantaneous value. However, the instantaneous value is tough to be predicted precisely due to random factors. For these problems, a fuzzy norm fusion model is proposed to predict calibration intervals under small sample of calibration data. The mathematic model of calibration data is founded, by analyzing historical calibration data and corresponding effect factors. Base on this work, the fuzzy norm fusion model is adopted to predict calibration intervals. The fuzzy norm fusion model conquers the deficiency, which other prediction models only predict the instantaneous value. Experiments show that the fuzzy norm fusion model could reflect the change trend of the system better and have higher prediction reliability.