Search

Ye et al. [[5]] proposed a simultaneous fault diagnosis method based on hierarchical multi-label classification and a sparse Bayesian extreme learning machine to identify the single failure and simultaneous failures of the main reducer and determine the probability of each failure mode. 10.3390/app13084655 4 Gu Y., Zhang Y., Yang M., Li C. Motor On-Line Fault Diagnosis Method Research Based on 1D-CNN and Multi-Sensor Information. Gu et al. [[4]] proposed a model for motor fault diagnosis based on deep learning and multi-sensor information fusion, including the steps of data layer fusion, feature layer fusion, and fault classification, and finally realized the fast and accurate diagnosis of motor faults. [Extracted from the article]

To conduct diagnosis and prognosis of gears, this paper introduces a novel short-frequency slip fault energy distribution-based demodulation method. As an essential step of the method, the resonance-based sparse signal decomposition algorithm is firstly employed to obtain the high-resonance part from the raw gear fault signal. To deal with the difficulty in determining the resonance frequency band, we establish a multi-input signal-output model to describe the signal components acquired from a faulty gear. Based on it, the short-frequency slip fault energy distribution graph is defined to locate the center frequency. Besides, the maximum amplitude in the short-frequency slip fault energy distribution graph can be used as a health indicator for prognosis, which is named as fault-induced resonance energy ratio. The effectiveness of the proposed method is validated with both simulated signal and test data. The positive results achieved in both experiments show the perfect property of the methodology for gear fault detection with high noise, especially when the fault is incipient. In addition, by comparing the fault-induced resonance energy ratio values of faulty gears with different severity, it is proved to be a reliable health indicator for gear prognostic. [ABSTRACT FROM AUTHOR]

As one of the most important components in rotating machinery, it’s necessary and essential to monitor the rolling bearing operating condition to prevent equipment failure or accidents. However, in vibration signal processing, the bearing initial fault detection under background noise is quite difficult. Therefore, in this paper a new feature extraction method combining sparse reconstruction and Multiscale Dispersion Entropy (MDErms) is proposed. Firstly, the Sliding Matrix Sequences (SMS) truncation and sparse reconstruction by Hankel-matrix are applied to the vibration signal. Then MDErms is utilized as a characteristic index of vibration signal, which is suitable for a short time series. Additionally, the MDErms is employed in the sparse reconstructed matrix sequences to achieve the Multiscale Fusion Entropy Value Sequence (MFEVS). The MFEVS keeps the fault potential feature information in different scales and is superior in distinguishing fault periodic impulses from heavy background noise. Finally, the designed FIR bandpass filter based on the MFEVS, shows prominent features in denoising and detecting weak bearing faults, which is separately verified by simulation studies and artificial fault experiments in different cases. By comparison with traditional methods like EEMD, Wavelet Packet (WP), and fast kurtogram, it can be concluded that the proposed method has a remarkable ability in removing noise and detecting rolling bearing faint fault. [ABSTRACT FROM AUTHOR]

The failure of rolling bearings is one of the most important factors for rotating machinery breakdown. The detection of initial fault in rolling bearings is crucial for the further prevention of equipment malfunction and failure. In this study, a new rolling bearing fault diagnosis method based on the singular value decomposition, slip Hankel matrix series construction and maximum singular value energy analysis is proposed. It has been validated that the proposed method has an excellent impulse recognition capacity, which can be further applied to design the optimal band‐pass filter for rolling bearing fault diagnosis. Then, the minimum entropy deconvolution (MED) technique is introduced to improve the fault extraction ability of the proposed method. Simulated signals and artificial fault tests are used to prove the capacity of the new method for rolling bearing fault detection. Furthermore, the result of accelerated life test indicates the initial bearing fault can be recognised by the proposed method, while the envelope spectrum cannot directly distinguish the failure type because of the redundant frequency interference. It can be concluded that the proposed method has the effectiveness of initial fault identification and redundant frequency elimination for rolling bearing fault diagnosis. [ABSTRACT FROM AUTHOR]

An energy analyzing method called the Impact Energy Model (IEM) is introduced to assess and diagnose the rub–impact fault of a rotor system. The main purpose of the model is to indicate the probability of rub–impact or the severity level of the fault. Utilizing the nonlinear predictive energy, an effective quantitative evaluation index IEM is obtained from the model. Some work has been done elsewhere to partly demonstrate the IEM through experiments. In this paper we mainly discuss the variation of the IEM index with the speed ratio Ω at different levels of damping ratio ξ. The stagnation point is discussed in detail which is important to the assessment for the probability or severity of a rub–impact fault. The influence of dynamic stiffness is discussed which may affect the assessment result of the IEM. Furthermore, a sensitive area of the rotor operating system is presented. The result shows that this sensitive area provides a reference for the operation and design of a rotor system. [ABSTRACT FROM PUBLISHER]

Due to planetary movement of planet gears, the vibration signal perceived by a stationary sensor is modulated and difficult to diagnose. This paper proposed a vibration separation methodology compensated by a time-varying transfer function (TVTF-VS), which is a further development of the vibration separation (VS) method in the diagnosis of non-hunting tooth planetary gearboxes. On the basis of VS, multi-teeth VS is proposed to extract and synthesize the meshing signal of a planet gear using a single transducer. Considering the movement regularity of a planetary gearbox, the time-varying transfer function (TVTF) is represented by a generalized expression. The TVTF is constructed using a segment of healthy signal and an evaluation indicator is established to optimize the parameters of the TVTF. The constructed TVTF is applied to overcome the amplitude modulation effect and highlight fault characteristics. After that, experiments with baseline, pitting, and compound localized faults planet gears were conducted on a non-hunting tooth planetary gearbox test rig, respectively. The results demonstrate that incipient failure on a planet gear can be detected effectively, and relative location of the local faults can be determined accurately. [ABSTRACT FROM AUTHOR]