Intelligent Fault Diagnosis of Planetary Wheel Bearing Using Constrained Independent Component Analysis and Stacked Sparse Autoencoder

Industrial machinery is developing in the direction of large-scale, automation, and high precision, which brings novel troubles to mechanical equipment management and maintenance. Intelligent diagnosis of mechanical running state based on vibration signals is becoming increasingly important, and it is still a great challenge at pattern recognition. As one of the indispensable components in mechanical equipment, planetary gearboxes are widely used in wind power, aerospace, and heavy industry. However, the problem of automatically maximizing the accuracy of planetary gearbox under different working conditions has not been solved. Therefore, an intelligent diagnosis method for planetary wheel bearing based on constrained independent component analysis (CICA) and stacked sparse autoencoder (SSAE) is presented in this research. Firstly, the fault signal with obvious time-domain characteristics is extracted by constrained independent component analysis (CICA), and the fault signals and noise is separated. Then, calculating the correlation kurtosis value of the time domain signals at different iteration periods as the eigenvalue to obtain the training samples and the test samples. The parameters of the network layer, the number of hidden nodes and learning rate are determined to build the model of SSAE. In the end, the training samples are input into the model for training and the whole network is fine-tuned. The advantages and disadvantages of the model are verified by the test samples. The intelligent classification and diagnosis of the mechanical running state are completed. Experiments analysis with real datasets of planetary wheel bearing show that the proposed method can achieve higher accuracy and robustness for fault classification compared with other data-driven methods. The application of this method in other major machinery industry also has bright prospects.

An Enhanced CICA Method and Its Application to Multistage Gearbox Low-frequency Fault Feature Extraction

Background: The vibration signals acquired from multistage gearbox’s slow-speed gear with localized fault may be directly mixed with source noise and measured noise. In addition, Constrained Independent Component Analysis (CICA) method has strong immunity to the measured noise but not to the source noise. These questions cause the difficulty for applying CICA method to directly extract lowfrequency and weak fault characteristic from the gear vibration signals with source noise. Methods: In order to extract the low-frequency and weak fault feature from the multistage gearbox, the source noise and measured noise are introduced into the independent component analysis (ICA) algorithm model, and then an enhanced Constrained Independent Component Analysis (CICA) method is proposed. The proposed method is implemented by combining the traditional Wavelet Transform (WT) with Constrained Independent Component Analysis (CICA). Results: In this method, the role of a supplementary step of WT before CICA analysis is explored to effectively reduce the influence of strong noise. Conclusion: Through the simulations and experiments, the results show that the proposed method can effectively decrease noise and enhance feature extraction effect of CICA method, and extract the desired gear fault feature, especially the low-frequency and weak fault feature.

Skin Chromophore Estimation from Mobile Selfie Images using Constrained Independent Component Analysis

Human skin is made up of two primary chromophores: melanin, the pigment in the epidermis giving skin its color; and hemoglobin, the pigment in the red blood cells of the vascular network within the dermis. The relative concentrations of these chromophores provide a vital indicator for skin health and appearance. We present a technique to automatically estimate chromophore maps from RGB images of human faces captured with mobile devices such as smartphones. The ultimate goal is to provide a diagnostic aid for individuals to monitor and improve the quality of their facial skin. A previous method approaches the problem as one of blind source separation, and applies Independent Component Analysis (ICA) in camera RGB space to estimate the chromophores. We extend this technique in two important ways. First we observe that models for light transport in skin call for source separation to be performed in log spectral reflectance coordinates rather than in RGB. Thus we transform camera RGB to a spectral reflectance space prior to applying ICA. This process involves the use of a linear camera model and Principal Component Analysis to represent skin spectral reflectance as a lowdimensional manifold. The camera model requires knowledge of the incident illuminant, which we obtain via a novel technique that uses the human lip as a calibration object. Second, we address an inherent limitation with ICA that the ordering of the separated signals is random and ambiguous. We incorporate a domain-specific prior model for human chromophore spectra as a constraint in solving ICA. Results on a dataset of mobile camera images show high quality and unambiguous recovery of chromophores.

A Method for Utility Harmonic Impedance Estimation Based on Constrained Complex Independent Component Analysis

Utility harmonic impedance is an important parameter for harmonic mitigation. In this paper, a method for utility harmonic impedance estimation method based on constrained independent component analysis is proposed. The conventional impedance estimation method based on ComplexICA has two major problems: the algorithm is not suitable for separating weak and strong source mixed signals, and lots of sample data should be provided to avoid converging on a local optimum. To solve the two problems, the prior information of the utility harmonic source is added to the objective function of ComplexICA; in this paper, the measurement data at PCC when the load is shutdown are chosen as the prior information. Then the utility harmonic source signal can be recovered and the separated matrix can be obtained effectively. The connection between the utility harmonic source, utility harmonic impedance and the data at PCC are established using Norton equivalent circuit, and then the separation matrix is used to calculate utility harmonic impedance. The performance and feasibility of the proposed method are verified by the computer simulation and field test. Compared with the current ComplexICA method, the proposed method is more adaptive to changes in the background harmonic and the calculation result is more stable.