The operation status of gear device can directly affect the working conditions of the whole machine system. Thus, it is crucial to detect the gear damage as early as possible to prevent the system from malfunction. This paper proposes an intelligent diagnosis method for gear damage using multiple classifiers of support vector machines with extracted failure feature vector. The vibration signal of gear box is employed as the analytical data in this paper. In order to illustrate the representative characters of gear conditions, statistical parameters and characteristic amplitude ratios of frequency bands are extracted from the vibration signals in time-domain and frequency-domain respectively, which are served as failure feature vector for the following diagnosis. Moreover, to reduce the dimensions of the failure feature vector, the technology of principal component analysis is adopted to transform the original failure feature vector into a new smaller set of variables as inputs to classifiers of support vector machines. In order to classify different types of gears, multiple classifiers of support vector machines based on the binary tree are designed. The validity of this approach is investigated by the experiment. Three kinds of gears, namely normal gear, spot damaged gear and pitted gear, are tested on the power circulating type gear testing machine. The vibration accelerations of gear box are measured as original data. Most of the samples are correctly classified by the provided method, which demonstrates the effectiveness of the proposed method on the application of gear damage diagnosis. IntroductionSince minor gear damage may cause serious failures of the entire equipment, early detection of gear damage is one of the important measures to prevent the machine system from malfunction. Analyzing the vibration signal adopted from the gear or gear box is one of the effective methods to diagnose gear failures. Researchers have done countless studies in this respect and have developed many methods based on the analysis of vibration signal in time domain, frequency domain and time-frequency domain. In frequency domain, it is well known that the fault condition of gears can be observed at the meshing frequency and its harmonics, together with sidebands by spectra analysis of vibration signal (Dalpiaz, et al., 2000). However, the acquired signals are always inevitably interfered by the vibration of other components in the system, or the environment disturbances. Therefore, in order to strengthen the characteristics of the useful signal, researchers have developed many other signal processing techniques for gear fault detection, such as time synchronous average method in time domain, wavelet transform and Hilber transform techniques in time-frequency domain, advanced statistical approaches and so on. These techniques have been satisfactorily applied to both fault detection and identification of the damaged gear (Houjoh, et al., 2007, Tanaka, et al., 2012, Wang, et al., 2010 Fan, Ikejo, Nagamura, Kawada and Has...

Gear is one of the most important and commonly used components in machine system. Some gear failure may lead to fatal damage of the entire system, or even huge losses in industrial production. Early detection of gear damage is crucial to prevent the machine system from malfunction. This paper provides an intelligent diagnosis method for gear damage based on techniques of empirical mode decomposition and support vector machines. By the data processing of empirical mode decomposition, the original signal are decomposed into a finite set of intrinsic mode functions with frequency bands ranging from high to low. The characteristic energy ratios of intrinsic mode functions are acquired as representative parameters of the signal. Furthermore, statistical parameters of standard deviation, root mean square value, kurtosis and skewness are extracted from the original signal. Characteristic energy ratios and statistical parameters are combined as failure feature vectors to be input to the support vector machines classifiers for gear damage diagnosis. The validity of the presented method is confirmed by the application of monitoring gear conditions during the cyclic fatigue test. The vibration accelerations of gear box are acquired to illustrate the progression of pitting damage. Most of the gear conditions are identified, indicating the effectiveness of the proposed method.

Gear failure is the main cause of machine malfunction. Therefore, it has become increasingly important to detect gear failure to ensure the normal operation of a machine. Here, we propose a gear damage detection and localization approach by studying the vibration signal of an individual gear tooth and support vector machines. Generally, it is difficult to detect a small gear failure in the total vibration signal. The waveform of an individual gear tooth was studied to investigate the vibration features of a gear in more detail. The characteristics of damaged and normal teeth were investigated by analyzing their individual waveform. Besides, the feature parameters were also extracted from both the time and frequency domains of the waveform to investigate the characteristics of each gear tooth. The difference between the damaged and normal teeth was detected by the waveform and feature parameters. Additionally, the condition of each gear tooth was diagnosed by support vector machines using the extracted feature parameters. The method was used to analyze the results of cyclic fatigue experiments. The conditions of most of the gear teeth were correctly classified, validating the proposed method.

No abstract

Gear is one of the most commonly used and important components in machine system. Mainly gear failure may cause serious damage of the whole equipment, even huge economic losses. Therefore, it is important to detect the gear damage as early as possible. This paper provides a method of diagnosis and location for gear damage based on statistical approach and discrete wavelet transform (DWT). The vibration signals of gear box and bearing box are measured as analytical data. To emphasize the failure features of the measured signal, gear motion residual signal is obtained from the raw signal and provides a better indication of the existence of failures. Additionally, the method of discrete wavelet transform is employed to reduce the noise from the residual signal and decompose the signal into several decomposition levels. Because of the good sensitivity to the altering of vibration signal, statistical parameters such as standard deviation, kurtosis and so on are extracted from the raw signal and the reconstructed signal by DWT as failure features for detecting the gear damage. For a comparison of the raw signal and the reconstructed signal, the variation of statistical parameters among different kinds of test gears is also discussed by the significance test. The validity of the presented method is testified by some experiments under different conditions. Three kinds of gears namely normal gear, spot damaged gear and pitted gear are tested on the power circulating type gear testing machine, and the vibration acceleration on both gear box and bearing box is obtained. The experimental results show the effectiveness of this method on the diagnosis of gear damage.