Identification of Vinegar Acid, Ammonia and Alcohol using Conducting Polymer Sensors and Artificial Neural Network (ANN)

Abstract

Testing on organic solutions aims to test the system in identifying an organic solution correctly. The organic solutions tested were vinegar acid, ammonia and alcohol. The author discusses in this research how a system can identify 3 types of organic solutions based on the odor produced by the three organic solutions. Data on the smell of vinegar acid was obtained from acetic acid samples taken on the first day. Ammonia odor data was obtained from ammonia samples taken on the second day. Alcohol odor data was obtained from alcohol samples taken on the third day. In this study the author used a series of conducting polymer sensors consisting of eight sensors and used polymer materials, namely silicon DC-200, PEG-20M, 0V-101, 0V-17, DEGA, PEG-200, PEG-1540, and PEG -6000 are mixed with carbon black. A two-layer artificial neural network consisting of eight input nodes and three output neurons, was trained using the Kohonen algorithm with the training process completed in 50 iterations. Of the 20 tests, 2 tests were wrong, and 18 tests were correct, so that from this test the success rate in identifying vinegar acid, ammonia and alcohol was 90%.