Fusing method of temperature compensation of humidity sensor

Abstract

The invention relates to a fusing method of temperature compensation of a humidity sensor. A characteristic function y=f(x) of the humidity sensor is given, wherein y represents the output of the humidity sensor, x represents the input of the humidity sensor, a temperature parameter is provided additionally, when t0<t1<t2<t3, according to the characteristics that a characteristic curve of the humidity sensor is linear in the middle and is nonlinear at two ends under the influence of the temperature, through a linear least square method, a linear equation f2(x, t) influenced by the temperature within a range of [t1, t2] is obtained; and when t0<t<t1 or t2<t<t3, error compensation caused by the temperature influence is carried out on f1(x, t) and f3 (x, t) through an RBF (Radial Basis Function) neutral network. The fusing method has the beneficial effect that an actual value which is closer to an output value of the humidity sensor is finally obtained.

Description

technical field [0001] The invention belongs to the technical field of sensor soft compensation, and in particular relates to the application of an adaptive fusion method combining RBF neural network and least squares in temperature compensation of humidity sensors. Background technique [0002] Air humidity is an important parameter in meteorological observation. At present, the automatic weather stations that have been put into operation by the meteorological department mostly use the HMP45D temperature and humidity integrated sensor produced by Vaisala Company of Finland to measure air humidity. The HMP45D temperature and humidity sensor is a new generation of polymer film capacitive sensor with HUMICAP technology. During the application process, the relative humidity is calculated through a linear relationship. However, in the actual business process, the measurement of humidity under high and low temperature conditions cannot Meet the problems of measurement accuracy an...

AI Technical Summary

Problems solved by technology

The hardware compensation method is affected by factors such as the drift of electronic components in the circuit, resulting in poor reliability and low precision of the entire measurement system, which cannot achieve full compensation, and its application is limited in actual use.

The software compensation method is a multidimensional regression analysis method. However, when applying the multidimensional regression analysis method for data fusion processing, it is necessary to solve a large-scale matrix equation, and even the equation is sometimes an ill-conditioned equation that cannot be solved, and the fitting accuracy is low, which often cannot meet Practical application requirements; the temperature compensation of the humidity sensor can also be realized by using the nonlinear mapping ability of the BP neural network, but there are some problems in the application process of this method, and it is easy to fall into the local extremum, which makes the training fail, and when the amount of data is large, Slower learning rate and lower fitting accuracy

Images