Broad-Range Optical pH Sensor Based on Binary Mixed-Indicator Doped Sol-Gel Film and Application of Artificial Neural Network

Abstract

Abstract In this article, we constructed a pH optical sensor based on m-cresol purple/bromocresol green mixed indicators. The sensor possessed different behaviors at various pH values from −1.04 to 8.70. The observed behaviors were modeled by means of a PC-feed-forward artificial neural network (ANN) with back-propagation training algorithm. The resulting ANN model was used to predict pH values of new measured spectra from unknown solutions. The results showed very good agreement between true and predicted pH values. The sensor revealed no leaching and excellent reversibility. Other advantages of the sensor include rapid response time, long-term stability, reversibility, high sensitivity, and little hysteresis effect.