Dynamic Characteristics of Ball Bearing-Coupling-Rotor System with Angular Misalignment Fault

The rotor misalignment fault, which occurs only second to unbalance, easily occurs in the practical rotating machinery system. Rotor misalignment can be further divided into coupling misalignment and bearing misalignment. However, most of the existing references only analyze the effect of coupling misalignment on the dynamic characteristics of the rotor system, and ignore the change of bearing excitation caused by misalignment. Based on the above limitations, a five degrees of freedom nonlinear restoring force mathematical model is proposed, considering misalignment of bearing rings and clearance of cage pockets. The finite element model of the rotor is established based on the Timoshenko beam element theory. The coupling misalignment excitation force and rotor unbalance force are introduced. Finally, the dynamic model of the ball bearing-coupling-rotor system is established. The radial and axial vibration responses of the system under misalignment fault are analyzed by simulation. The results show that the bearing misalignment significantly influences the dynamic characteristics of the system in the low-speed range, so bearing misalignment should not be ignored in modeling. With the increase of rotating speed, rotor unbalance and coupling misalignment have a greater impact. Misalignment causes periodic changes in bearing contact angle, radial clearance, and ball rotational speed. It also leads to reciprocating impact and collision between the ball and cage. In addition, misalignment increases the critical speed and the axial vibration of the system. The results can provide a basis for health monitoring and misalignment fault diagnosis of the rolling bearing-rotor system.

Diagnosis of the Misaligned Faults of the Vertical Test Instrument of High-Precision Industrial Robot Reducer

High-precision reducer is the core component of industrial robots. In order to achieve the comprehensive performance testing of precision reducers, an instrument with a vertical layout and a cylindrical structure is designed. As a rotating machine, the inevitable coupling misalignment of the instrument can lead to vibration faults which lead to errors in the test. So it is pretty necessary to diagnose and monitor the coupling misalignment while the instrument is working. The causes of the coupling misaligned fault of the instrument and the relationship between the misalignment fault and torque ripple are analyzed in this paper. A method of using the torque transducer in the measurement chain of the instrument to diagnose the coupling misalignment is proposed in this paper. Many experiments have been done to test the capability of detecting the coupling misalignment using this method. Experimental results show that the amplitude of torque ripple of the shaft is linearly related to the coupling misalignment and is quadratically related to the rotation speed of the shaft when the misalignment exists in the shaft. The combination of components at the rotation frequency (fr) and the additional components can be used to diagnose faults due to coupling misalignment.

Misalignment Fault Prediction of Wind Turbines Based on Improved Artificial Fish Swarm Algorithm

A misalignment fault is a kind of potential fault in double-fed wind turbines. The reasonable and effective fault prediction models are used to predict its development trend before serious faults occur, which can take measures to repair in advance and reduce human and material losses. In this paper, the Least Squares Support Vector Machine optimized by the Improved Artificial Fish Swarm Algorithm is used to predict the misalignment index of the experiment platform. The mixed features of time domain, frequency domain, and time-frequency domain indexes of vibration or stator current signals are the inputs of the Least Squares Support Vector Machine. The kurtosis of the same signals is the output of the model, and theprinciple of the normal distribution is adopted to set the warning line of misalignment fault. Compared with other optimization algorithms, the experimental results show that the proposed prediction model can predict the development trend of the misalignment index with the least prediction error.

Study on fault diagnosis method of splitter intelligent wheelchair motor based on wavelet and energy feature

As a key component of a split-type intelligent sports wheelchair for the disabled, the reliability of the motor is related to the personal safety of the wheelchair user and the accurate realization of the wheelchair’s sports functions. This motor is actually just a rotating machine. In order to achieve detection and analysis of rotating machinery bearing vibration signal, a method based on wavelet and energy feature of rotating machinery fault diagnosis is introduced. This method applies wavelet to obtain de-noising and then uses wavelet packet energy feature extraction to diagnose faults effectively caused by rotating machinery such as rotor unbalance fault, rotor misalignment fault, and rotor-to-stator rub fault. Test results illustrate that when different faults occur to the bearing, it is viable to utilize pattern recognition to diagnose faults for the reason that discrepancies appear in sub-hand energy after wavelet packet decomposition. The main research conclusions of this paper are also directly applied to the fault diagnosis of such wheelchair motors.

Wind Turbine Generator Controller Signals Supervised Machine Learning for Shaft Misalignment Fault Detection: A Doubly Fed Induction Generator Practical Case Study

With a continued strong increase in wind generator applications, the condition monitoring of wind turbine systems has become ever more important in ensuring the availability and reduced cost of produced power. One of the key turbine conditions requiring constant monitoring is the generator shaft alignment, which if compromised and untreated can lead to catastrophic system failures. This study explores the possibility of employing supervised machine learning methods on the readily available generator controller loop signals to achieve detection of shaft misalignment condition. This could provide a highly noninvasive and low-cost solution for misalignment monitoring in comparison with the current misalignment monitoring field practice that relies on invasive and costly drivetrain vibration analysis. The study utilises signal datasets measured on a dedicated doubly fed induction generator test rig to demonstrate that high consistency and accuracy recognition of shaft angular misalignment can be achieved through the application of supervised machine learning on controller loop signals. The average recognition accuracy rate of up to 98.8% is shown to be attainable through analysis of a key feature subset of the stator flux-oriented controller signals in a range of operating speeds and loads.

Misalignment Fault Diagnosis for Wind Turbines Based on Information Fusion

Most conventional wind turbine fault diagnosis techniques only use a single type of signal as fault feature and their performance could be limited to such signal characteristics. In this paper, multiple types of signals including vibration, temperature, and stator current are used simultaneously for wind turbine misalignment diagnosis. The model is constructed by integrated methods based on Dempster–Shafer (D–S) evidence theory. First, the time domain, frequency domain, and time–frequency domain features of the collected vibration, temperature, and stator current signal are respectively taken as the inputs of the least square support vector machine (LSSVM). Then, the LSSVM outputs the posterior probabilities of the normal, parallel misalignment, angular misalignment, and integrated misalignment of the transmission systems. The posterior probabilities are used as the basic probabilities of the evidence fusion, and the fault diagnosis is completed according to the D–S synthesis and decision rules. Considering the correlation between the inputs, the vibration and current feature vectors’ dimensionalities are reduced by t-distributed stochastic neighbor embedding (t-SNE), and the improved artificial bee colony algorithm is used to optimize the parameters of the LSSVM. The results of the simulation and experimental platform demonstrate the accuracy of the proposed model and its superiority compared with other models.

Dual-rotor misalignment fault quantitative identification based on DBN and improved D-S evidence theory

Misalignment fault is the main factor that affects the normal running of dual-rotor system. Quantitative identification the misalignment fault is an important way to ensure the safe and stable service of the dual-rotor system, while the identification accuracy of traditional methods is low. Aiming at the above problems, this paper proposed a dual-rotor misalignment fault quantitative identification method based on DBN and D-S evidence theory improved by mutual information measure (MIMD-S). Seven groups experiments were conducted and several vibration signals were collected. By comparing it with the traditional methods D-S, and Pignistic improved D-S (PD-S) evidence theory, the results show that the method proposed in this paper improves the accuracy of the misalignment fault quantitative identification of the dual-rotor, the identification error rate was only 0.36%.