Leak Detection on Air Reservoir via Acoustic Models with TensorFlow Based
Naparat Pairin and Ramil Kesvarakul
Production Engineering, King Mongkut’s University of Technology North Bangkok, Bangkok, Thailand
Abstract—Fluid, both gas and liquid, is a widely used substance which can be used in pneumatic and hydraulic system. However, the pneumatic system with compressed air system integrated has a flaw that leakage air during power transmission cost a lot of loss both resources and performance. Leak detection is one of the main solution to plug the flaw. In this research, we use acoustic signal to detect the leakage by using it as an input for model. Artificial Neural Network (ANN) is used in our model to achieve deep learning property via Tensorflow. Acoustic signal is recorded in different situation and is used as a model input. So, our model can be trained with leak data and predict the leakage in pneumatic system. We evaluate model using test data and shows the leakage prediction in probability distribution.
Index Terms—Artificial Neural Network, leak detection, Tensorflow
Cite: Naparat Pairin and Ramil Kesvarakul, "Leak Detection on Air Reservoir via Acoustic Models with TensorFlow Based," International Journal of Electronics and Electrical Engineering, Vol. 8, No. 4, pp. 88-93, December 2020. doi: 10.18178/ijeee.8.4.88-93
Index Terms—Artificial Neural Network, leak detection, Tensorflow
Cite: Naparat Pairin and Ramil Kesvarakul, "Leak Detection on Air Reservoir via Acoustic Models with TensorFlow Based," International Journal of Electronics and Electrical Engineering, Vol. 8, No. 4, pp. 88-93, December 2020. doi: 10.18178/ijeee.8.4.88-93
Array