Small Sample Gear Fault Diagnosis Method Based on Transfer Learning

Aiming at the problems of lack of fault diagnosis samples and low model generalization ability of cross-working gear based on deep transfer learning, a fault diagnosis method based on improved deep residual network and transfer learning was proposed. Firstly, one-dimensional signal is transformed into two-dimensional time-frequency image by continuous wavelet transform. Then, a deep learning model based on ResNet50 is constructed. Attention mechanism is introduced into the model to make the model pay more attention to the useful features for the current task. The network parameters trained by ResNet50 network on ImageNet dataset were used to initialize the model and applied to the fault diagnosis field. Finally, to solve the problem of gear fault diagnosis under different working conditions, a small sample training set is proposed for fault diagnosis. The method is applied to gearbox fault diagnosis, and the results show that: The proposed deep model achieves 99.7% accuracy of gear fault diagnosis, which is better than the four models such as VGG19 and MobileNetV2. In the cross-working condition fault diagnosis, only 20% target dataset is used as the training set, and the proposed method achieves 93.5% accuracy.

Model Parameter Transfer for Gear Fault Diagnosis under Varying Working Conditions

Gear fault diagnosis technologies have received rapid development and been effectively implemented in many engineering applications.However,the various working conditions would degrade the diagnostic performance and make gear fault diagnosis(GFD)more and more challenging.In this paper,a novel model parameter transfer(NMPT)is proposed to boost the performance of GFD under varying working conditions.Based on the previous transfer strategy that controls empirical risk of source domain,this method further integrates the superiorities of multi-task learning with the idea of transfer learning(TL)to acquire transferable knowledge by minimizing the discrepancies of separating hyperplanes between one specific working condition(target domain)and another(source domain),and then transferring both commonality and specialty parameters over tasks to make use of source domain samples to assist target GFD task when sufficient labeled samples from target domain are unavailable.For NMPT implementation,insufficient target domain features and abundant source domain features with supervised information are fed into NMPT model to train a robust classifier for target GFD task.Related experiments prove that NMPT is expected to be a valuable technology to boost practical GFD performance under various working conditions.The proposed methods provides a transfer learning-based framework to handle the problem of insufficient training samples in target task caused by variable operation conditions.

NEW DEMODULATION TECHNOLOGY OF OPTIMIZING ENERGY OPERATOR AND APPLICATION TO GEAR FAULT DIAGNOSIS

Although many methods have been applied to diagnose the gear thult currently, the sensitivity of them is not very good. In order to make the diagnosis methods have more excellent integrated ability in such aspects as precision, sensitivity, reliability and compact algorithm, and so on, and enlightened by the energy operator separation algorithm （EOSA）, a new demodulation method which is optimizing energy operator separation algorithm （OEOSA） is presented. In the algorithm, the non-linear differential operator is utilized to its differential equation： Choosing the unit impulse response length of filter and fixing the weighting coefficient for inportant points. The method has been applied in diagnosing tooth broden and fatiguing crack of gear faults successfully. It provides demodulation analysis of machine signal with a new approach.

Gear Fault Detection Analysis Method Based on Fractional Wavelet Transform and Back Propagation Neural Network

A gear fault detection analysis method based on Fractional Wavelet Transform(FRWT)and Back Propagation Neural Network(BPNN)is proposed.Taking the changing order as the variable,the optimal order of gear vibration signals is determined by discrete fractional Fourier transform.Under the optimal order,the fractional wavelet transform is applied to eliminate noise from gear vibration signals.In this way,useful components of vibration signals can be successfully separated from background noise.Then,a set of feature vectors obtained by calculating the characteristic parameters for the de-noised signals are used to characterize the gear vibration features.Finally,the feature vectors are divided into two groups,including training samples and testing samples,which are input into the BPNN for learning and classification.Experimental results showed that this gear fault detection analysis method could well maintain the useful signal components related to gear faults and effectively extract the weak fault feature.The accuracy rate reached 96.67%in the identification of the type of gear fault.

Detection and Diagnosis of Gear Fault By the Single Gear Tooth Analysis Technique

This paper presents a procedure of sing le gear tooth analysis for early detection and diagnosis of gear faults. The objec tive of this procedure is to develop a method for more sensitive detection of th e incipient faults and locating the faults in the gear. The main idea of the sin gle gear tooth analysis is that the vibration signals collected with a high samp ling rate are divided into a number of segments with the same time interval. The number of signal segments is equal to that of the gear teeth. The analysis of i ndividual segments reveals more sensitively the changes of the vibration signals in both time and frequency domain caused by gear faults. In addition, the locat ion of a failed tooth can be indicated in terms of the position of the segment t hat deviates from the normal segments. An experimental investigation verified th e advantages of the single gear tooth analysis.

CLASSIFICATION OF GEAR FAULTS USING HIGHER-ORDER STATISTICS AND SUPPORT VECTOR MACHINES

Gears alternately mesh and detach in driving process, and then workingconditions of gears are alternately changing, so they are easy to be spalled and worn. But becauseof the effect of additive gaussian measurement noises, the signal-to-noises ratio is low; theirfault features are difficult to extract. This study aims to propose an approach of gear faultsclassification, using the cumulants and support vector machines. The cumulants can eliminate theadditive gaussian noises, boost the signal-to-noises ratio. Generalisation of support vectormachines as classifier, which is employed structural risk minimisation principle, is superior tothat of conventional neural networks, which is employed traditional empirical risk minimisationprinciple. Support vector machines as the classifier, and the third and fourth order cumulants asinput, gears faults are successfully recognized. The experimental results show that the method offault classification combining cumulants with support vector machines is very effective.

A Fast Multi-tasking Solution: NMF-Theoretic Co-clustering for Gear Fault Diagnosis under Variable Working Conditions

Most gear fault diagnosis(GFD)approaches su er from ine ciency when facing with multiple varying working conditions at the same time.In this paper,a non-negative matrix factorization(NMF)-theoretic co-clustering strategy is proposed specially to classify more than one task at the same time using the high dimension matrix,aiming to o er a fast multi-tasking solution.The short-time Fourier transform(STFT)is first used to obtain the time-frequency features from the gear vibration signal.Then,the optimal clustering numbers are estimated using the Bayesian information criterion(BIC)theory,which possesses the simultaneous assessment capability,compared with traditional validity indexes.Subsequently,the classical/modified NMF-based co-clustering methods are carried out to obtain the classification results in both row and column tasks.Finally,the parameters involved in BIC and NMF algorithms are determined using the gradient ascent(GA)strategy in order to achieve reliable diagnostic results.The Spectra Quest’s Drivetrain Dynamics Simulator gear data sets were analyzed to verify the e ectiveness of the proposed approach.

DETECTION OF INCIPIENT LOCALIZED GEAR FAULTS IN GEARBOX BY COMPLEX CONTINUOUS WAVELET TRANSFORM

As far as the vibration signal processing is concerned, composition ofvibration signal resulting from incipient localized faults in gearbox is too weak to be detected bytraditional detecting technology available now. The method, which includes two steps: vibrationsignal from gearbox is first processed by synchronous average sampling technique and then it isanalyzed by complex continuous wavelet transform to diagnose gear fault, is introduced. Twodifferent kinds of faults in the gearbox, i.e. shaft eccentricity and initial crack in tooth fillet,are detected and distinguished from each other successfully.

A Method for Gear Fault Diagnosis Based on the Empirical Mode Decomposition

According to the characteristics of gear fault vibration signals, a methodfor gear fault diagnosis based upon the empirical mode decomposition (EMD) is proposed in thispaper. By using EMD, any complicated signal can be decomposed into a finite and often small numberof intrinsic mode functions (IMFs) , which are based upon the local characteristic time scale of thesignal. Thus, EMD is perfectly suitable for non-stationary signal processing and faultcharacteristics extracting. It is well known that a gear vibration signal consists of a number offrequency family components, each of which is a modulated signal. Thus, we can use EMD to decomposea gear fault vibration signal into a number of IMF components, some of which correspond to thefrequency families, and the others are noises. Therefore, the frequency families can be separatedand the noise can be decreased at the same time. The proposed method has been applied to gear faultdiagnosis. The results show that both the sensitivity and the reliability of this method aresatisfactory.

Analysis and Simulation for Planetary Gear Fault of Helicopter Based on Vibration Signal

Fault diagnosis for helicopter's main gearbox based on vibration signals by experiments always requires high costs. To solve this problem,a helicopter's planetary gear system is taken as an example. Firstly,a simulation model is established by McFadden,and analyzed under ideal condition. Then this model is developed and improved as the delay-time model of the vibration signal which determines the phase-change of sidebands when the system is running. The cause and change-rules of planetary gear system's vibration signal are analyzed to establish the fault diagnosis model.At the same time,the vibration signal of fault condition is simulated and analyzed. This simulation method can provide a reference for fault monitoring and diagnosis for planetary gear system.

Faults Analysis and Diagnosis of DRJ-460 Dish Centrifugal Separator′s Helical Gear

The main faults of dish centrifugal separator's helical gear are described inthis paper. In order to diagnose the DRJ-460 dish centrifugal separator correctly, the vibration istested with a helical gear under both normal and abnormal conditions. After comparing severalgeneral methods of the gear's fault feature extraction, a new convenient and effective method ispresented on the basis of analyzing the vibration spectrum under different rotary velocities.

Bispectrum Analysis in Fault Diagnosis of Gears

The application ofbispectrum analysis in fault diagnosis o f gears is studied in this paper. Bispectrum analysis is capable of removing Gau ssian or symmetric non-Gaussian noise and providing more information than power spectrum analysis.The results of the research show that normal gear sig nals, cracked gear signals and broken gear signals can be easily distinguished b y using bispectrumas the signal features. The bispectrum diagonal slice B_x(ω_1,ω_2) can be used to identifythe gear condition automatically.

Fuzzy fault tree analysis of roller oscillating tooth gear drive

Conventional fault tree and reliability analysis do not reflect the characteristics of basic events as non stationary and ergodic process. To overcome these drawbacks, theory of fuzzy sets is employed to run fault tree analysis(FTA) of roller oscillating tooth gear drive(ROTGD), the relative frequencies of basic events are considered as symmetrical normal fuzzy numbers, from the logical relationship between different events in the fault tree and fuzzy operators AND and OR, fuzzy probability of top event is solved. Finally, an example is given to demonstrate a real ROTGD system.

Research on the Comprehensive Demodulation of Gear Tooth Crack Early Fault

The component of gear vibration signal is very complex,when a localized tooth defect such as a tooth crack is pre- sent,the engagement of the cracked tooth will induce an impulsive change with comparatively low energy to the gear mesh signal and the background noise.This paper presents a new comprehensive demodulation method which combined with amplitude envelop demodulation and phase demodulation to extract gear crack early fault.A mathematical model of gear vibration signal contain crack fault is put forward.Simulation results based on this model show that the new comprehensive demodulation method is more effective in finding fault and judging fault level then conventional single amplitude demodulation at present.

Generalized Demodulation Transform for Bearing Fault Diagnosis Under Nonstationary Conditions and Gear Noise Interferences

It is a challenging issue to detect bearing fault under nonstationary conditions and gear noise interferences. Meanwhile, the application of the traditional methods is limited by their deficiencies in the aspect of computational accuracy and e ciency, or dependence on the tachometer. Hence, a new fault diagnosis strategy is proposed to remove gear interferences and spectrum smearing phenomenon without the tachometer and angular resampling technique. In this method, the instantaneous dominant meshing multiple(IDMM) is firstly extracted from the time-frequency representation(TFR) of the raw signal, which can be used to calculate the phase functions(PF) and the frequency points(FP). Next, the resonance frequency band excited by the faulty bearing is obtained by the band-pass filter. Furthermore, based on the PFs, the generalized demodulation transform(GDT) is applied to the envelope of the filtered signal. Finally, the target bearing is diagnosed by matching the peaks in the spectra of demodulated signals with the theoretical FPs. The analysis results of simulated and experimental signal demonstrate that the proposed method is an e ective and reliable tool for bearing fault diagnosis without the tachometer and the angular resampling.

Analysis of Gear Breakage and Countermeasures Based on Fault Tree

Gears are important parts of mechanical products and have been widely used in various industries.A spur gear was broken early in a transmission chain.This article starts with the breakage fault of the gear.The processes of fault analysis and improvement countermeasure were comprehensively sorted out based on fault tree,and the relevant influencing factors which affect the life of gears were examined one by one.Through detailed investigation,the abnormal high load on the gears was clarified.The gear design strength reserve did not meet the requirements for customer-specific operating conditions,and further improvements had been made.By optimizing the oil-filling characteristics and timing matching of the hydraulic system,the impact of shift shock was reduced,thereby reducing the load on the gears.At the same time,by increasing the pressure angle of the gear,the gear strength margin was increased from the design point of view.Through the fatigue test on the bench,the gears worked safely.After further verification of the actual vehicle test,the gears worked safely and normally,so the improvement measures were effective.This article provides a useful reference for trouble shooting processes and a problem solving method for similar faults through detailed analysis of factors affecting gear life.

Gear Transmission Fault Classification using Deep Neural Networks and Classifier Level Sensor Fusion

Gear transmissions are widely used in industrial drive systems.Fault diagnosis of gear transmissions is important for maintaining the system performance,reducing the maintenance cost,and providing a safe working environment.This paper presents a novel fault diagnosis approach for gear transmissions based on convolutional neural networks(CNNs)and decision-level sensor fusion.In the proposed approach,a CNN is first utilized to classify the faults of a gear transmission based on the acquired signals from each of the sensors.Raw sensory data is sent directly into the CNN models without manual feature extraction.Then,classifier level sensor fusion is carried out to achieve improved classification accuracy by fusing the classification results from the CNN models.Experimental study is conducted,which shows the superior performance of the developed method in the classification of different gear transmission conditions in an automated industrial machine.The presented approach also achieves end-to-end learning that ean be applied to the fault elassification of a gear transmission under various operating eonditions and with signals from different types of sensors.

Fault diagnosis of AMT gear shifting process based on semi-quantitative SDG model

In order to diagnose gear shifting process in automated manual transmission（AMT）,a semi-quantitative signed directed graph（SDG）model is applied.Mathematical models are built by analysis of the power train dynamic and the gear shifting control process.The SDG model is built based on related priori knowledge.By calculating the fuzzy membership degree of each compatible passway and its possible fault source,we get the possibilities of failure for each possible fault source.We begin with the nodes with the maximum possibility of failure in order to find the failed part.The diagnosis example shows that it is feasible to use the semi-quantitative SDG model for fault diagnosis of the gear shifting process in AMT.