Search

In order to study the vibration wearing regularity and the strength failure point of stator end windings before and after static rotor eccentricity, the three-dimensional electromagnetic forces and the subsequent mechanical responses are studied in this paper. The electromagnetic force, stress, and deformation on the end winding of the QFSN-600-2YHG turbo-generator are calculated by the finite element method (FEM) through an electromagnetic-structure coupling. The radial vibration characteristics of the winding are verified by experiments. It shows that the vibration wearing in the same layer is more serious than that between two neighboring layers. For different layers, the interphase coils endure a larger wearing risk than the innerphase coils. Inside the same phase, the last coil along the rotating direction has the highest risk of insulation wearing. The occurrence of static rotor eccentricity will significantly increase the electromagnetic forces and the vibration amplitudes on some coils. The end-phase coil which is close to the minimum air-gap point is the most dangerous one due to the lasting overstresses and the intensified deformations.

This paper studies the stator winding electromagnetic force behaviors before and after rotor inter-turn short circuit (RISC) in synchronous generator. Different from other studies, this paper not only studies the electromagnetic force characteristics, but also investigates the mechanical responses, the damage regularity, and the countermeasure of the stator winding. Firstly, formulas of electromagnetic force online and end part are obtained. Then, a 3D finite element model of a 3-pair-pole simulation generator is applied to get the electromagnetic force, and the dangerous stator slot is found. Finally, the mechanical response of each end winding is acquired, and especially the directional deformations of nose part are calculated. It shows that the occurrence of RISC will bring in times of rotor rotating frequency components to electromagnetic force, but the DC component and 2p times of rotor rotating frequency components are still the main that will be decreased. Additionally, the winding insulation wear in the same layer is more serious than that in a different layer, nose fatigue fracture begins with the center, and nose insulation wear starts from the top.

This paper comparatively studies the electromagnetic force and mechanical response of the end winding before and after 3 kinds of typical electromechanical faults in turbo-generator. The analytical expression of electromagnetic force of end winding is derived under the composite fault of static eccentricity and rotor interturn short circuit. Meanwhile, the three-dimensional transient finite element simulation is carried on, and the frequency composition and amplitude variation characteristics of the radial, axial, and tangential electromagnetic force are analyzed for the end windings under static eccentricity, rotor interturn short circuit, and composite fault. Therefore, it provides a reference for the vibration wear detection and electromagnetic force control of the end winding. Moreover, the maximum stress and deformation of different positions on the end involute are obtained. And the three-directional vibration acceleration characteristics of the end winding are further analyzed. Finally, the distribution law of winding fatigue failure and vibration wear is acquired, which lays a foundation for the reverse suppression of end winding fatigue failure and insulation wear.

This paper presents a comprehensive analysis on the transient electromagnetic force behavior of the stator windings in a QFSN-600-2YHG type turbo-generator. Different from other studies, this paper investigates not only the distribution regularities of the resultant force and the force density, but also the force harmonic characteristics, and the mechanical responses which will cause sensitive impact on the insulation wearing. The whole work is generally based on a proposed simplified model and the 3D finite element coupling calculation. The simplified model contains two parts. The first part is the theoretical model that employs the approximate solution of the image current to obtain the analytic formula of the electromagnetic force on the end windings conveniently. The second part is the FEA model that employs only the end windings and one-tenth of the stator core to save the calculating memory and, meanwhile, obtain the qualified electromagnetic force as well as the mechanical response. It is shown that the nose-top, the connection point between the line part and the end part, and the middle of the involute are the three most dangerous positions of the end winding to sustain serious insulation wearing. Moreover, the winding, which endures the maximum mechanical response, is neither always consistent with the one that has the largest resultant electromagnetic force nor directly in accordance with the winding that affords the most intensive electromagnetic force density. The findings in this paper will be beneficial for the insulation monitoring and the manufacturing improvement on the stator windings.

The intent of this paper is to find out significant united electromechanical characteristics for online monitoring of stator interturn short circuit (SISC) faults. Different from other studies, this paper pays attention to neither the stator voltage and current, nor the winding inductance variation, but focuses on the faulty electromagnetic characteristics including the exciting current, the circulating current in the parallel branches (CCPB), and the electromagnetic torque (EMT). The simulation work is modeled for a QFSN-600-2YHG type turbo-generator and the experiment is taken on a MJF-30-6 fault-simulating generator to verify the theoretical analysis. The simulation result and the experiment data accord with the theoretical analysis and show that, as SISC occurs, second harmonics will be induced in the exciting current, first and third harmonics will be induced in the CCPB, and second and fourth harmonics will be produced in the EMT. Moreover, the corresponding time-domain waves will also fluct...

The intent of this paper is to investigate the effect of the interturn short circuit fault (ISCF) in rotor on the magnetic flux density (MFD) of turbo-generator. Different from other studies, this work not only pays attention to the influence of the faulty degrees on the general magnetic field, but also investigates the effect of the short circuit positions on the harmonic components of MFD. The theoretical analysis and the digital simulation through the FEM software Ansoft are performed for a QSFN-600-2YHG turbo-generator. Several significant formulas and conclusions drawn from the analysis and the simulation results are obtained to indicate the relation between the harmonic amplitude of the MFD and the faulty degree (via nm , the number of the short circuit turns), and the relation between the MFD harmonic amplitude and the faulty position (via αr , the angle of the two slots in which the interturn short circuit occurs). Also, the developing tendency of the general magnetic field intensity, the distribution of the magnetic flux lines, and the peak-to-peak value of MFD are presented.

This paper proposes a new diagnosis method based on Adaptive maximum correlated kurtosis deconvolution (AMCKD) for accurate identification of compound faults of rolling bearings. The AMCKD method combines the powerful capability of cuckoo search algorithm for global optimization with the advantage of Maximum correlated kurtosis deconvolution (MCKD) for impact signal extraction. In contrast to traditional methods, such as direct envelop spectrum, Discrete wavelet transform (DWT), and empirical mode decomposition, the proposed method extracts each fault signal related to the single failed part from the compound fault signals and effectively separates the coupled fault features. First, the original signal is processed using AMCKD method. Demodulation operation is then performed on the obtained single fault signal, and the envelope spectrum is calculated to identify the characteristic frequency information. Verification is performed on simulated and experimental signals. Results show that the proposed method is more suitable for detecting compound faults in rolling bearings compared with traditional methods. This research provides a basis for improving the monitoring and diagnosis precision of rolling bearings.

This paper investigates the radial rotor vibration characteristics under static air-gap eccentricity and stator inter-turn short circuit composite faults. The air-gap magnetic flux density is firstly deduced to obtain the unbalanced magnetic pull (UMP) on rotor. Then the rotor vibration characters, as well as the developing trend between the faulty parameters and the vibration amplitudes, are analyzed. Finally, the experiments are taken on a SDF-9 type simulating generator. It is shown that the radial deformation possibility, the 2nd, 4th, and 6th harmonic vibrations will be caused by the composite faults. Besides, the development of the inter-turn short circuit, the increment of the static eccentricity, and the rise of the exciting current will all get the deformation trend and the vibration amplitudes increased.

Electromagnetic forces on the end windings will stimulate intensive vibrations and cause insulation wearing, and the vibration wear will further induce the coil short circuit. Eventually accidents and losses will be brought. Therefore, it is of great significance to study the electromagnetic force properties of end windings. This paper studied on the electromagnetic force properties of end windings in turbo-generators. Firstly, the magnetic field in the end region was analyzed by winding MMF superposition principle and air gap magnetic conductivity method, and the electromagnetic force is got with Ampere law. Then, taking QFSN-600-2YHG turbo-generator as study object, the 3 directional electromagnetic forces and the mechanical responses on the end windings were calculate by electromagnetic-structure coupling finite element analysis method. Finally, the experiment vibrations are tested, and the acceleration data was compared with simulated result. It is shown that each directional electromagnetic force contains both the DC component and even harmonics, which will result in the winding vibration mainly at the double fundamental frequency. Meantime, the radial acceleration is the largest and the axial one is the least, so the radial vibration should be paid more attention to in daily monitoring. Moreover, the max deformation mainly occurs on the nose and middle part of the involute, and these locations should be strengthened in design and manufacture.

This paper investigates the dynamic characteristics of 600MW turbo-generator stator core, including the bending modes, the torsional modes, the elliptical modes, the axial modes and the triangular modes. The magnetic pull formula under the steady-state condition is firstly deduced, based on which the pulsating characters and the core deformation due to the pull excitation are analyzed. Then, the finite element (FE) model of the stator core is set up and imported into ANSYS Workbench to calculate the natural frequencies and the vibration modes. Finally, the calculation is verified via comparing with the experimental data in the published papers. It is shown that the first natural frequency is much larger than the excited working frequency, which means the stator core is in a safe operation condition. The calculation proposed in this paper accords well with the experimental data obtained by other researchers.

An analysis method based on Teager-Huang transform for rotor local rubbing fault diagnosis is introduced. Firstly, the original vibration signal is decomposed into some Intrinsic Mode Function (IMF) components by using Empirical Mode Decomposition (EMD) approach, secondly, Teager energy operator is applied to estimate the instantaneous amplitude and instantaneous frequency of each IMF component, so the time-frequency distribution of the signal is obtained. The rotor local rubbing fault is simulated on a rotor test rig. The analysis results show that this method compared with Hilbert-Huang transform (HHT) can track the occurrence of rotor local rubbing fault better and can extract the characteristics of rotor local rubbing fault effectively. It provides a reliable method for timely and accurate diagnostic to the rotor local rubbing fault.

One rolling bearing fault diagnosis method based on minimum entropy deconvolution (MED) and morphological filtering is proposed. Firstly, the strong background noise of rolling bearings is decreased by the MED method, then the morphological filtering which have different length of structure elements is designed and applied to the de-noised signal. Subsequently, bearing’s fault characteristic frequency is extracted by the amplitude spectrum analysis to the best morphological filtering component which have the maximum kurtosis. This method is used to analyze both a simulated bearing signal and an experimental inner ring fault signal, and the good result validated the effectiveness of this method.

There is a large widespread cavitation turbine components. By using HVOF Stellite alloy coating technology, brushing epoxy technology, epoxy-coated steel wire technology, brazed carbide block technology, repeated welding technology integrated control over the water turbine components cavitation,effectively prevent the turbine parts water cavitation in running condition, improve the reliability of hydroelectric equipment..

This paper puts forward a kind of gearbox fault diagnosis methods which based on empirical mode decomposition (EMD), Hilbert transform, Fast Fourier Transform (FFT) and spectrum refined techniques. This method is applicable to the analysis of the nonlinear unsteady signal. First of all used wavelet denoising to the acquisition of gearbox vibrate signal, again carries on the empirical mode decomposition (EMD), than get a certain number of intrinsic mode function (imf); Choose the specific imf, based on kurtosis value, after the Hilbert transform and Fast Fourier Transform is done, the corresponding power spectrum can be obtained; To refine the power spectrum and extract the gearbox fault characteristic frequency; Then in pattern recognition and diagnosis of the gearbox fault, and compared with the normal signal characteristics. The analysis results show that the proposed method can effectively detect the gearbox fault characteristics.

Because some composite insulators run certain number of years and tends to exist insulation breakdown performance degradation issues, and some even mass incidents have occurred, affecting the normal operation of the grid. First introduced X-ray inspection systems, then introduction common failure and the reason of composite insulators. And through the artificial gap between the mandrel and the jacket seams, V-shaped mandrel and an artificial scratches and other defects between the insulator strings, concluded the feasibility of X-ray diagnosis of common faults of composite insulators.

Turbine blades crack problem is widespread. Combined with the characteristics of hydropower, analyzes the causes of cracks in the turbine, materials, design and manufacturing, operation and so on. Plant No. 6 in Little Bay machine as an example, were detected by macroscopic, chemical composition analysis, crack cross-section analysis, microstructure examination, crack source electron microscopy and spectroscopy to analyze the crack, the final cause of the crack is leaves the local area resonance, the resonance of the blade in the crater formed at the source of fatigue and fatigue development along at the source, the formation of fatigue cracks.

For gearbox common type of fault, leads to common methods gear fault diagnosis, according to the various parameters of the gearbox, to give a gearbox fault frequencies. Using mat lab signal analysis, by the time domain analysis, frequency domain analysis, cestrum analysis, signal processing methods envelope spectrum consolidated results there is a fault in the gearbox countershaft. This papers they have certain significance to gear fault diagnosis.

The rolling bearings fault feature under strong background noise is very weak for reasons of environment noise impact and signal attenuation. To extract the fault features of roller bearings effectively, a new method based on Minimum entropy deconvolution (MED) and slice bi-spectrum is proposed. The paper Firstly decreases the strong background noise of rolling bearing by the MED method, and then calculates the envelope signal of the de-noised signal. Finally, analyzes the envelope signal with slice bi-spectrum and extracted the fault characteristic frequency. The effectiveness of the proposed method was validated by analysis of both a simulated faulty bearing vibration signal and the experiment measured signal of rolling bearing, and it was also compared with the method of envelope spectrum.

This paper investigates the stator vibration characteristics of turbo-generator, respectively, under normal condition and the air-gap eccentricity and rotor interturn short circuit composite fault, with the effects of the eccentricity factor and the short circuit factor on the stator vibration characteristics presented. The air-gap magnetic flux density and the unit magnetic pull under the composite fault are firstly deduced. Then three kinds of eccentricities are, respectively, considered to analyze the stator vibration characteristics. Finally, experiments are taken on a SDF-9 non-salient fault-simulating generator to verify the theoretical results. The study shows that when the composite faults occur, the eccentric kind determines the vibration components. 1st to 4th harmonic vibrations will be produced when the eccentricity is the static one, while 1st to 6th harmonic vibrations will be produced when the eccentricity is the other two. The increment of the interturn short circuit will increase the 4th harmonic vibration, but decreases the 2nd harmonic for the static eccentricity situation, and increase the 6th harmonic vibration for the other two eccentricities. However, no matter which kind of eccentricity increases, each stator vibration component will be increased. The presented work has reference value and positive meaning for the diagnosis of composite faults.

During circuit breaker risk condition assessment, the most important thing is to calculate the circuit breaker health index (HI). Aiming at the collected data for risk assessment is incomplete or it is not useful for the assessment, this paper analyzed the principle from of the health index calculation process, finding the various characteristics, which has an effect on the health, further more calculated the contribution to the health index, streamlining the data list for assessment. It has an important guiding significance for the future data collection.

The power transformer is the most important equipment in the power system, so the condition-based maintenance of the transformer has an important significance for the safe and stable operation of the power grid, and condition assessment provides an important basis for the condition-based maintenance. In this paper, the calculation principle of the reliability assessment method is analyzed, and the contribution of each feature value is calculated. It has an important guiding significance for the Power Supply Bureau to provide the condition assessment data, the data with a contribution of large degree should be collected forcibly, so that the data for transformer reliability assessment is the most simplified, improving the assessment rate.

A new method on fault diagnosis for gear based on ensemble empirical mode decomposition and slice bi-spectrum is proposed. Firstly, fault signal was decomposed into a series of intrinsic mode function components of different frequency bands by EEMD, and then calculated the envelope signal of IMF component by Hilbert demodulation method. Finally, analyzed the envelope signal by slice bi-spectrum and extracted the fault characteristic frequency. The anti-alias decomposition capacity of EEMD and capabilities of noise suppression and non-quadratic phase coupling harmonic components elimination of slice bi-spectrum were verified by analyzing the simulation signal. The analysis results of gear pitting failure signal and gear wear fault signal showed that this method could judge gear fault type accurately and has a certainly degree reliability.

A novel method of fault diagnosis for rolling bearing based on variational mode decomposition (VMD). permutation entropy (PE), and support vector machine (SVM) is put forward in this paper. Firstly, the original vibration signals of bearings are adaptively decomposed into a series of band-limited intrinsic mode function (BUMF) components using VMD. Considering the reason that the permutation entropy can quantify the complexity of the signals to some extent, then permutation entropy is used to extract the feature information of the obtained BLIMF components and the feature vectors could be constructed. Finally, the feature vectors are fed into the SVM classifier to achieve automatic condition identification. The experimental data analysis results demonstrate that the proposed method could be applied to distinguish the different working conditions of rolling bearings. Simultaneously, the comparison results showed that the performance of the proposed method outperforms that of the method based on empirical mode decomposition (EMD) and PE.

In order to extract the fault features of rolling bearing effectively, a new improved enhanced kurtogram method is proposed. Improved enhanced kurtogram is calculated based on harmonic wavelet packet composition and the node whose kurtosis value is maximum is selected after calculating the improved enhanced kurtogram of the original fault signal, then reconstruct the signal through the harmonic wavelet packet coefficient of the optimal node, the rolling bearing fault type could be judged by analyzing the envelope spectrum of the reconstructed signal. The comparison of the proposed method with the original kurtogram method and the enhanced kurtogram method are conducted to analyze the experimental signal of rolling bearing. The results show that the new method proposed in this paper could select the resonance frequency band precisely and could be applied effectively on fault diagnosis for rolling bearing.

The ability of the frequency slice wavelet transform (FSWT) to distinguish the fault feature is weak under the condition of strong background noise; in order to solve this problem, a fault feature extraction method combining the singular value decomposition (SVD) and FSWT was proposed. Firstly, the Hankel matrix was constructed using SVD, based on which the SVD order was determined according to the principle of the single side maximum value. Then, the denoised signal was further processed by the FSWT to obtain the time-frequency spectrum of the passband. Finally, the detailed analysis was carried out in the time-frequency area with concentrated energy, and the signal was reconstructed by the inverse-FSWT. The processing effect for the pitting corrosion and the tooth broken faults of the gears shows that the faulty feature can be extracted effectively from the envelope spectrum of the reconstructed signal, which means the proposed method is able to help obtain a qualified result and has the potential to be carried out for the practical engineering application.

A time-frequency analysis method based on improved variational mode decomposition and Teager energy operator (IVMD-TEO) is proposed for fault diagnosis of turbine rotor. Variational mode decomposition (VMD) can decompose a multicomponent signal into a number of band-limited monocomponent signals and can effectively avoid model mixing. To determine the number of monocomponents adaptively, VMD is improved using the correlation coefficient criterion. Firstly, IVMD algorithm is used to decompose a multicomponent signal into a number of monocompositions adaptively. Second, all the monocomponent signals’ instantaneous amplitude and instantaneous frequency are demodulated via TEO, respectively, because TEO has fast and high precision demodulation advantages to monocomponent signal. Finally, the time-frequency representation of original signal is exhibited by superposing the time-frequency representations of all the monocomponents. The analysis results of simulation signal and experimental turbine rotor in rising speed condition demonstrate that the proposed method has perfect multicomponent signal decomposition capacity and good time-frequency expression. It is a promising time-frequency analysis method for rotor fault diagnosis.

A novel method of fault diagnosis for rolling bearing, which combines the dual tree complex wavelet packet transform (DTCWPT), the improved multiscale permutation entropy (IMPE), and the linear local tangent space alignment (LLTSA) with the extreme learning machine (ELM), is put forward in this paper. In this method, in order to effectively discover the underlying feature information, DTCWPT, which has the attractive properties as nearly shift invariance and reduced aliasing, is firstly utilized to decompose the original signal into a set of subband signals. Then, IMPE, which is designed to reduce the variability of entropy measures, is applied to characterize the properties of each obtained subband signal at different scales. Furthermore, the feature vectors are constructed by combining IMPE of each subband signal. After the feature vectors construction, LLTSA is employed to compress the high dimensional vectors of the training and the testing samples into the low dimensional vectors with better distinguishability. Finally, the ELM classifier is used to automatically accomplish the condition identification with the low dimensional feature vectors. The experimental data analysis results validate the effectiveness of the presented diagnosis method and demonstrate that this method can be applied to distinguish the different fault types and fault degrees of rolling bearings.

Theoretical analysis and numerical FEM calculations, together with segmental experiment studies, are used to study the impact of the static air-gap eccentricity forms on the rotor unbalanced magnetic pull (UMP) of turbogenerator. The universal expression of the magnetic flux density under different forms of SAGE is firstly deduced, based on which the detailed UMP formulas for the normal condition and three SAGE cases are obtained, respectively. Then the exciting characteristics of the UMP for each SAGE form to generate vibrations are analyzed. Finally, numerical FEM calculations and segmental experiments are carried out to investigate the effect of SAGE forms on the rotor UMP, taking the SDF-9 type non-salient-pole fault simulating generator as the object. It is shown that, no matter what kind of SAGE occurs, amplitude increments at each even harmonic component of the UMP and the rotor vibration, especially the 2nd harmonic component, will be brought in. Meanwhile, the UMP keeps directing to the very position where the minimum radial air-gap is. Among the different SAGE forms, the rotor offset has the most sensitive effect on the rotor UMP and vibration, while the stator ellipse deformation has the weakest impact.

This paper investigates the radial stator vibration characteristics of turbogenerator under the static air-gap eccentricity (SAGE) fault, the rotor interturn short circuit (RISC) fault, and the composite faults (CFs) composed of SAGE and RISC, respectively. Firstly, the impact of the faulty types on the magnetic flux density (MFD) is analyzed, based on which the detailed expressions of the magnetic pull per unit area (MPPUA) on the stator under different performing conditions are deduced. Then, numerical FEM simulations based on Ansoft and an experimental study are carried out, taking the SDF-9 type fault simulating generator as the study object. It is shown that SAGE will increase the stator vibration at 2f(fis the electrical frequency) which already exists even in normal condition, while RISC and CF will bring in stator vibrations atf, 2f, 3f, and 4fat the same time. The vibration amplitudes under CF are larger than those under RISC. As SAGE increases, the vibration amplitudes of each harmonic component under CF will all be increased, while the development of RISC will decrease the 2nd harmonic vibration but meanwhile increase the 4th harmonic vibration. The achievements of this paper are beneficial for fault identification and condition monitoring of the turbogenerator.

Dynamic model of nonlinear rotor—bearing system is set up using the modified Capone bearing forces models. And the nonlinear dynamics behavior of unbalanced rotor—bearing systems was studied. The system state trajectories, Poincare maps, are also constructed to analyze the typical dynamic behavior of the system．Through the nonlinear dynamic numerical simulation of the system，the dynamic phenomena of the rotor—bearing system caused by oil film forces are clearly distinct. The computational results show that the rotor speed is one of the most important factors of the system dynamic behavior. It presents a periodic, period-doubling motion, quasi-periodic motion, and abundant nonlinear dynamical behavior with the changes of the speed.

In this paper, a multi-fractal algorithm for vibration signal fault diagnosis is proposed to compute the multi-fractal dimension (Dq) automatically and perform the fault diagnosis accurately. This extended G-P generalized multi-fractal dimension algorithm is based on the qth-order correlation integral and the Grassberger-Procaccia (G-P) mono fractal correlation dimension algorithm. Experiment results verify the feasibility and effectiveness of the proposed algorithm. The obtained Dq unambiguously identifies the vibration signals sampled at the various states and provides more information of the vibration signals than the mono fractal correlation dimension . Hence it should be a more effective tool for vibration signal fault diagnosis. The analysis also indicates that the fluctuation amplitude of Dq is related with the frequency component distribution of the vibration signal.

This paper designed a signal acquisition and analysis system based on the characteristics of the graphical programming language of LabVIEW. The system adopted NI USB -9234 data collection card, applied with the virtual instrument and related technology for the signal collecting and processing system. The system also has dual-channel data acquisition, real time data acquisition, signal analysis in time domain and frequency domain, FFT implementation Waterfall conversion, signal simulation capabilities. On the basis of analysis the systems functional requirements, a detailed description of the functional programming and design of the front panel is approached. At last the feasibility of system is experimental inspected and detailed. Experiments have shown that the virtual instrument is a good solution to the efficient implementation of various missions.

This paper investigates the rotor vibration differences among the rotor interturn short circuit fault, the static air-gap eccentricity fault, and the combined fault composed by the former two. The UMP (unbalanced magnetic pull) formulas of the three faults are firstly deduced. Then the rotor vibration characters, as well as the vibration difference comparison, are studied based on the formulas. Finally, the numerical calculation and the experiment of a non-salient fault simulating generator are taken to verify the theoretical analysis. It is shown that the rotor interturn short circuit fault mainly causes the rotor to vibrate at f r (the rotating frequency of the rotor), while the static air-gap eccentricity fault primarily produces vibrations at 2f r , and the combined fault generates vibrations at f r , 2f r , and 3f r at the same time. The proposed work is available for the accuracy improvement of the generator fault diagnosis.

This paper proposed a solution in view of the non-contact measurement problem. In this solution, the camera is applied in the non-contact 3D measurement. Firstly, we complete the camera calibration, and then the feature point extraction and matching in turn based on the epipolar constraint criterion and gray similarity. Finally we calculate the three-dimensional coordinates of the feature points. The experimental results show that this method has a good application prospects in the industrial testing field.

The study applies a novel neural network technique, hybrid support vector regression (SVR), to forecast values of the turbo-generator vibration in time series. The simulation experiment results showed that the hybrid model is superior to the individual models for the test. Most of the individual models evaluated showed poor ability to detect directional change. This problem can be overcome with the use of the hybrid model. Besides superior turning point detectability, the hybrid model could achieve superior predictive performance and showed promising results. Therefore, the results suggested that the proposed hybrid model is typically a reliable forecasting tool for application within the forecasting fields of time series.

Vibration problems in rotors can be extremely frustrating and may lead to greatly reduced reliability. By utilizing the proper data collection and analysis techniques, the faults because of vibration can be discovered and predicted. The time-frequency analysis by Hilbert-Huang transform (HHT) plays on a significant role in the analysis of singularities, which hide in the signal, and is an effective method for non-stationary signal. The experiment data of rubbing vibration faults signal were analyzed by the method, and the result shows that the proposed method can not only reveal the time-frequency features of vibration signal but also extrude components of low energy. Local rubbing faults can be accurately diagnosed in good time by applying HHT. Therefore, it is a very effective tool to diagnose the early faults of rotor system. And it provides new means for state detection and fault diagnosis of rotating machine.

The time-frequency analysis by Hilbert-Huang transform (HHT) plays on a significant role in the analysis of singularities, which hide in the signal, and is an effective method for non-stationary signal. Based on empirical mode decomposition (EMD), the Hilbert-Huang method can obtain a true instantaneous frequency representation of a signal. The analytical background of the HHT is introduced, and its effectiveness is experimentally evaluated using vibration signal. The experiment data of typical vibration faults signal were analyzed by the method, and the result shows that the proposed method can not only reveal the time-frequency features of vibration signal but also extrude components of low energy. Therefore, it is a very effective tool to diagnose the early faults of rotor system. And it provides new means for state detection and fault diagnosis of rotating machine.