Neural Network, Component of Measuring Set for Error Reduction

The paper describes the use of neural network as a component of measuring set for error reduction (nonlinearity). The scope of interest is elastomagnetic sensor used for measuring of massive pressure force (of range about 200 kN). Nonlinearity and hysteresis errors are main limitations of elastomagnetic sensor use. The hysteresis causes ambiguity of transfer characteristic and with it related impossibility of exact conversion of output sensor voltage into measured force. The function of the neural network is to regulate the basic metrological characteristics of sensor in order to achieve the smallest deviation from an ideal transfer characteristic. The assumption of the use of neural network as data-conditioning block is non-linear dependency of sensor output from input quantity.