Research on Gear-box Fault Diagnosis Method Based on Adjusting-learning-rate PSO Neural Network

Based on the research of Particle Swarm Optimization (PSO) learning rate, two learning rates are changed linearly with velocity-formula evolving in order to adjust the proportion of social part and cognitional part; then the methods are applied to BP neural network training, the convergence rate is heavily accelerated and locally optional solution is avoided. According to actual data of two levels compound-box in vibration lab, signals are analyzed and their characteristic values are abstracted. By applying the trained BP neural networks to compound-box fault diagnosis, it is indicated that the methods are sound effective.

Improved CICA Algorithm Used for Single Channel Compound Fault Diagnosis of Rolling Bearings

A Compound fault signal usually contains multiple characteristic signals and strong confusion noise, which makes it difficult to separate week fault signals from them through conventional ways, such as FFT-based envelope detection, wavelet transform or empirical mode decomposition individually. In order to realize single channel compound fault diagnosis of bearings and improve the diagnosis accuracy, an improved CICA algorithm named constrained independent component analysis based on the energy method （E-CICA） is proposed. With the approach, the single channel vibration signal is firstly decomposed into several wavelet coefficients by discrete wavelet transform（DWT） method for the purpose of obtaining multichannel signals. Then the envelope signals of the reconstructed wavelet coefficients are selected as the input of E-CICA algorithm, which fulfills the requirements that the number of sensors is greater than or equal to that of the source signals and makes it more suitable to be processed by CICA strategy. The frequency energy ratio（ER） of each wavelet reconstructed signal to the total energy of the given synchronous signal is calculated, and then the synchronous signal with maximum ER value is set as the reference signal accordingly. By this way, the reference signal contains a priori knowledge of fault source signal and the influence on fault signal extraction accuracy which is caused by the initial phase angle and the duty ratio of the reference signal in the traditional CICA algorithm is avoided. Experimental results show that E-CICA algorithm can effectively separate out the outer-race defect and the rollers defect from the single channel compound fault and fulfill the needs of compound fault diagnosis of rolling bearings, and the running time is 0.12% of that of the traditional CICA algorithm and the extraction accuracy is 1.4 times of that of CICA as well. The proposed research provides a new method to separate single channel compound fault signals.

Static-deformation based fault diagnosis for damping spring of large vibrating screen

Based on the statics theory, a novel and feasible twice-suspended-mass method(TSMM) was proposed to deal with the seldom-studied issue of fault diagnosis for damping springs of large vibrating screen(LVS). With the static balance characteristic of the screen body/surface as well as the deformation compatibility relation of springs considered, static model of the screen surface under a certain load was established to calculate compression deformation of each spring. Accuracy of the model was validated by both an experiment based on the suspended mass method and the properties of the 3D deformation space in a numerical simulation. Furthermore, by adopting the Taylor formula and the control variate method, quantitative relationship between the change of damping spring deformation and the change of spring stiffness, defined as the deformation sensitive coefficient(DSC), was derived mathematically, from which principle of the TSMM for spring fault diagnosis is clarified. In the end, an experiment was carried out and results show that the TSMM is applicable for diagnosing the fault of single spring in a LVS.