Research On Fault Diagnosis System For Turbinedrill By Rolling Element Bearing

The failure of bearings is one of the foremost causes of breakdown in rotary machinery.So far,a variety of vibration-based techniques have been developed to monitor the condition of bearings;however,the role of vibration behavior is rarely considered in the proposed techniques.This thesis presents an analytical study of a healthy rotor-bearing system to gain an understanding of the different categories of bearing vibration.In this study,a two degree-of-freedom model is employed,where the contacts between the rolling elements and races are considered to be nonlinear springs.The analytical investigations confirm that the nature of the inner ring oscillation depends on the internal clearance.A fault-free bearing with a small backlash exhibits periodic behavior;however,bearings categorized as having normal clearance oscillate chaotically.The results from the numerical simulations agree with those from the experiments confirming bearing's chaotic response at various rotational speeds.Bearing faults generate periodic impacts which affect the chaotic behavior.This effect manifests itself in the phase plane,Poincare map,and chaotic quantifiers such as the Lyapunov exponent,correlation dimension,and information entropy.These quantifiers serve as useful indices for detecting bearing defects.To compare the sensitivity and robustness of chaotic indices with those of well-accepted fault detection techniques,a comprehensive investigation is conducted.The test results demonstrate that the Correlation Dimension(CD),Normalized Information Entropy(NIE),and a proposed time-frequency index,the Maximum Approximate Coefficient of Wavelet transform(MACW),are the most reliable fault indicators.A neuro-fuzzy diagnosis system is then developed,where the strength of the aforementioned indices are integrated to provide a more robust assessment of a bearing's health condition.Moreover,a prognosis scheme,based on the Adaptive Neuro Fuzzy Inference System(ANFIS),in combination with a set of logical rules,is proposed for estimating the next state of a bearing's condition.Experimental results confirm the viability of forecasting health condition under different speeds and loads.Through the research of this dissertation,the main results are summarized as follows:1)It is proven that the number of equilibrium points of a bearing's motion depends on the internal clearance.Bearings with a small clearance exhibit periodic motion with a unique equilibrium point.For larger clearances three equilibrium points exist at each time frame which divides the phase space into one unstable region and two stable regions.For high speeds,the inner ring jumps from one of the stable regions to the other,exhibiting chaotic behavior.2)The experimental results and numerical simulations confirm that the ball and cylindrical roller bearings,with a normal class of clearance,exhibit broad-band chaotic vibration at various rotational speeds.In addition,it is found that the bearing defects manifest themselves as periodic impulses,disturbing the chaotic behavior of a normal system.The experimental and simulation results reveal that faults significantly affect the chaotic quantifiers:Lyapunov exponent,correlation dimension,and information entropy.Therefore,they have the potential to be bearing fault indicator.Consequently,the sensitivity and robustness of these quantifiers are compared by well-known diagnostic methods.The experimental results pinpoint three indices as the most sensitive and robust monitoring features for fault diagnosis:Normalized Information Entropy(NIE),Correlation Dimension(CD),and Maximum of Approximated Coefficient Wavelet(MACW).Theses monitoring indices are less sensitive to load and shaft speed variations.3)To integrate the strengths of the three proposed monitoring indices,a neural-based diagnostic system is developed.The monitoring indices used as the input of the diagnostic scheme,and the output of the system corresponds to the level of bearing's health.The comparison demonstrates that the Neuro-Fuzzy Inference System(ANFIS)is more efficient to map the indices into the condition of the bearings.4)The performance of two types of viable neural networks,RNN and ANFIS,are evaluated for forecasting the next state of the monitoring indicators.It is explained that once an ANFIS system is trained with the run-to-damage vibration data of a bearing,the network can capture the damage propagation behavior accurately.Such a trained network is utilized successfully to predict future states of the same series of the bearings under different speed and load conditions.The reliability of the ANFIS system is reinforced by a logical combination of the three proposed monitoring indices.The developed prognostic structure is used to evaluate the future condition of the tested bearings in 305 cases with a success rate higher than 98 percent.