The Loosening Detection System of Prosthetic Screw in Implant Supported Denture

To solve the problem of prosthetic screws loosening in implant supported denture, a detection algorithm and detection system based on Hilbert-Huang transform (HHT) and support vector machine (SVM) was constructed. On the basis of the wavelet transform of the vibration signal sampled from the prosthetic screw, intrinsic mode functions (IMF), obtained by empirical mode decomposition (EMD) of the filtered signal, are used as the eigenvector of the vibration signal. Then, use the eigenvector as the input feature of support vector machine and train it to gain the recognition and classification model. In practical operation, the prosthetic screw looseness is detected based on the classification model obtained. The test results show that the system can effectively detect the looseness of the prosthetic screw in implant supported denture.