http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Fault Diagnosis of Bevel Gears Using Neural Pattern Recognition and MLP Neural Network Algorithms
Cemal Keleşoğlu,Haluk Küçük,Mustafa Demetgül 한국정밀공학회 2020 International Journal of Precision Engineering and Vol.21 No.5
Gear mechanisms are key components for rotating machinery ranging from automotive, hydraulic systems to aviation systems. As a more reliable, safer, economical fault diagnostic method, vibration and acoustic signatures of such systems havebeen widely studied. There are only a few numbers of studies incorporating sound and vibration monitoring together, fordiff erent working hours of the mechanism, rotating at diff erent operational parameters. A bevel gear test setup was developedin-house to observe the eff ect of diff erent operating conditions as shaft loading, shaft speed, lubrication level and abrasivecontamination along with diff erent operating hours. The system operating condition was also monitored, by obtaining visualphotographs of gear teeth. Vibration and sound signals were recorded followed by fast Fourier Transform and Power SpectrumDensity computations to extract the features used in developing a Multi-Layer Perceptron (MLP) based Neural Networkand a Neural Pattern Recognition algorithm for fault classifi cation purposes. It has been shown that sound and vibrationmeasurements can be confi dently used to predict bevel gear fault conditions.