Correction of gas sensor dynamic errors by means of neural networks

The paper presents a method based on artificial neural network (ANN) technique applied for correction of dynamic error of gas concentration measuring transducer. Its response time is about 8 minutes. The results obtained in the research of this transducer were used for learning and testing ANN, which were implemented in the dynamic correction task. The described method allowed for significant reduction of the transducer’s response time – the output signal was practically fixed after a time equal to one sampling period of output signal provided that the stimulus is a step function. In addition, the use of ANN allows reducing the impact of the transducer dynamic non-linearity on the correction effectiveness.