An Intelligent Fault Diagnosis Architecture for Electrical Fused Magnesia Furnace Using Sound Spectrum Submanifold Analysis

The temperature and pressure of electrical fused magnesia furnace (EFMF) are hard to obtain because the EFMF cannot be monitored effectively. Experts familiar with EFMF can determine its status by listening to its sound. In our work, we propose an intelligent architecture that can learn the experts' knowledge. Sound waveform is first transformed into the power spectrum density (PSD), and then the Laplacian score algorithm is used to select key frequencies. Next, a one-class support vector machine (SVM) is employed to find the minimum boundary of the submanifold of normal sound PSD. The distance of the sample to the classification hyperplane in kernel feature space is proposed to indicate the magnitude of faults. Lastly, the binary SVM is used to identify fault types. We have developed an instrument to acquire the sound of EFMF; experimental results using this data have shown the effectiveness of our proposed architecture. Additionally, the proposed architecture can be performed easily on the instrument for online monitoring.