Orifice Leak Detection in Atmospheric Vertical Cylindrical Storage Tanks Based on SVM

Leak detection in atmospheric vertical storage tanks is crucial for preventing environmental pollution, ensuring production safety, and reducing economic losses. This study investigates orifice leaks in vertical cylindrical storage tanks under atmospheric pressure using FLUENT 16.0. The simulation reveals a significant abrupt pressure change at the leak location. Based on the simulation findings, the actual acquired pressure signals during leakage are processed with wavelet threshold denoising, confirming the abrupt pressure change characteristic. Time-domain and waveform features of the denoised signals are extracted to establish a support vector machine (SVM)-based leak detection model. The performance of different kernel functions is compared, with the linear kernel achieving the highest accuracy of 96.55%.