Optimisation of the range of an optical fibre pH sensor using feed-forward artificial neural network

A broad range of optical fibre pH sensor based on immobilised bromophenol blue (BPB) immobilised on hydrophobic organic polymers Amberlite XAD 7 is presented in this paper. The reflectance spectra of the immobilised bromophenol blue were measured by using an optical fibre spectrophotometer. A back-propagation (BP) artificial neural network (ANN) model was used to analyse the optode response. The results showed that the use of ANN technique was very effective in broadening the limited dynamic response of the pH sensor (pH 2.00–5.00) to an extensive calibration response (pH 2.00–12.00). A network with 11 neurons in the hidden layer was tremendously accurate in predicting the response of the optical fibre pH sensor with an average error 0.02 pH for measuring unidentified buffer solution.