Operating Conditions Of Bearings Research Articles

Recursive prototypical network with coordinate attention: A model for few-shot cross-condition bearing fault diagnosis

In a practical industrial scenario, the variability in bearing operating conditions complicates the collection of a sufficient number of labeled samples, thereby limiting the effectiveness of traditional deep learning-based fault diagnosis methods. In addition, the influence of abnormal samples on the prototype features also severely limits the performance of prototypical network in few-shot fault diagnosis. To address the above issues, a recursive prototypical network based on meta-learning is proposed for few-shot cross-condition bearing fault diagnosis. Firstly, a feature extractor with coordinate attention mechanism is developed, which is able to deeply extract effective features in complex vibration signals. Furthermore, a recursive prototype computation module is introduced to alleviate prototype bias arising from abnormal samples, thereby achieving a more precise representation of prototypes. Finally, a metric module is utilized to obtain the similarity between the prototypes and the query set samples to achieve an accurate classification of faults. To verify the efficacy and superiority of the proposed method, its performance was evaluated on two bearing vibration datasets. The experimental results demonstrated that the method is significantly better than other deep learning methods with high accuracy and generalization, and greater suitability for few-shot cross-condition bearing fault diagnosis tasks.

Few-shot bearing fault diagnosis method based on an EEMD parallel neural network and a relation network

Bearing fault diagnosis presents challenges, such as insufficient fault samples and significant fault data distribution variation in different bearing operating conditions. These problems cause traditional deep learning models to show poor generality and accuracy during bearing fault diagnosis. To address these challenges, this paper proposed a few-shot bearing fault diagnosis method based on an Ensemble Empirical Mode Decomposition (EEMD) parallel neural network and a relation network (RN). First, the original bearing fault vibration signal was decomposed by EEMD, while the decomposed signal components were processed via Short Time Fourier Transfor (STFT) to obtain a two-dimensional time-frequency feature map. Then, a parallel neural network was used for initial fault feature extraction, after which the extracted features were fused to construct a more accurate multi-dimensional fault feature map. A more precise fault feature vector was generated via the feature embedding module of the RN, and the fault features of the support and query sets were stitched to create a fault feature vector set. Finally, the relation module of the RN was used for the nonlinear distance determination of the fault feature vector set and to generate the relation score for the few-shot variable condition bearing fault diagnosis. In this paper, EEMD module is introduced into RN to construct multi-dimensional fault characteristics of the original fault signal. Original signal decomposition, STFT transformation and splicing effectively improve the randomness and blindness of convolution operations, improve the accuracy of fault feature extraction in RN, and thus improve the overall diagnostic performance of the model. The experimental results showed that the proposed model obtained higher diagnostic accuracy than the matching network (MN) and RN meta-learning fault diagnosis (MLFD) methods. The accuracy of fault diagnosis of the model in 5Way-Nshot is >80%, and the accuracy of fault diagnosis in 5Way-10shot is the highest at 95.2%.

STAKgram: a method for optimal demodulation band selection in bearing fault diagnosis under complex interference

Abstract Within rotating machinery, bearings constitute critical and vulnerable components. When they operate in a compromised state, they generate periodic shock pulses. While spectral kurtosis (SK) has been demonstrated as an effective tool for pulse detection, in complex operating environments, the vibration signals of damaged bearings acquired through sensors often contain a variety of interfering pulses, such as ambient background noise, episodic single pulses, which cause SK to produce poor computational results. In this paper, an innovative bearing fault diagnostic method named subband trimmed average kurtogram (STAKgram) is proposed, aiming to minimize the effect of interfering signals on signal processing results, thus ensuring reliable diagnostic results even in complex interference environments. Firstly, the signal is segmented into N sub-signals by employing a sliding window method. Following, the subband kurtosis is calculated for every sub-signal. Ultimately, the trimmed average kurtosis of the respective sub-band is computed to construct the STAKgram, indicating the optimal demodulation frequency band. It is used for squared envelope demodulation analysis. By simulation analysis and the application of test signals obtained under conditions closely resembling authentic bearing operating conditions, the STAKgram method is proven to provide more accurate results for diagnosing bearing faults in complex interference.

Review of Recent Patents on Smart Bearing

Background: Smart bearing is based on the traditional bearing, which is integrated by sensing devices and control devices, formating a unique bearing structure unit. It uses information processing, automatic control, and other technologies to achieve real-time online monitoring of bearing operating conditions, fault detection, and state control. Compared with ordinary bearings, smart bearings have the characteristics of self-awareness, self-decision, and self-regulation. By analyzing the composition of various types of smart bearings and their working principles, it is beneficial to prospect the future development direction of bearings. Objective: We analyze and organize the patents on smart bearings in recent years, summarize the problems encountered in the development of smart bearings, and propose the development direction of smart bearings in the future to provide a reference for future scientific research. Methods: This paper reviews the patents related to smart bearings and analyzes the composition and structure of smart bearings. The main smart bearings include rolling bearing, sliding bearing, magnetic bearing, and rubber bearing. The principle and structure of these bearings are analyzed. Their advantages and shortcomings are discussed. Results: Through the analysis of relevant patents and papers on smart bearings, the current development status and problems of smart bearings are summarized, the future design of smart bearings is proposed, and the research ideas and directions are proposed. Conclusion: The development of smart bearings is conducive to the timely detection of bearing conditions in the operation process. Except for detection, smart bearings have the functions of judgment, feedback, processing, etc. There are many factors that interfere with the accuracy of the smart bearing judgment and information transfer, so it is necessary to improve the structure and working principle of smart bearings through a variety of measures. In the future, more smart bearings will be invented.

A bearing RUL prediction approach of vibration fault signal denoise modeling with Gate-CNN and Conv-transformer encoder

The operating conditions of rolling bearings are complex and variable, and their vibration monitoring signals are filled with strong noise interference, resulting in a low accuracy in remaining useful life (RUL) prediction. For this issue, this paper proposes a denoising method with vibration fault signals modeling, and a novel RUL prediction method with Gate-convolutional neural networks (CNN) and Conv-Transformer encoder. Firstly, the theoretical fault signal is obtained through the vibration fault signal model, and the quality of the extracted features is improved by the wavelet threshold denoising algorithm in the process of feature extraction and selection. Moreover, the CNN is combined with the gating mechanism to construct a feature extractor with the feature evaluation function, and the convolution layers are introduced into the transformer to expand the encoder’s ability to explore local information in temporal data. By using fixed-time step temporal features as the input to the prediction module and minimizing the Huber function as the optimization objective, the relationship between temporal features and RUL is obtained. The comparison with the existing state-of-the-art RUL methods illustrates that the combination of gate control and convolutional structure proposed in this paper can not only reduce the prediction error of the model but also improve its generalization ability and robustness.

A novel numerical analysis method for predicting non-Newtonian lubricant (grease) distribution in ball bearings

Grease is a visco-elastic fluid and the most common lubricant for rolling bearings. During the churning phase (initial phase) of bearing operation, most of the grease is collected at various locations in the bearing, e.g. by the seal, at the bottom cage bar, in the cage pockets, which are then called grease reservoirs. These are formed based on bearing operating conditions, grease type, bearing geometry, bearing type. The grease reservoirs supply lubricant to the bearing contacts via bleeding: during operation the oil bleeds out of the reservoirs and lubricates the contacts. Since the distribution of grease is crucial to the bearing lubrication, the design of bearing components e.g., the cage, shall aim at an optimal grease reservoir creation during the churning phase. It is difficult to observe the effect of component design on the grease distribution through real life experiments, so CFD simulations with MPS (Moving Particle Semi-implicit) method are performed here. Flow Simulations with MPS method can help determine the factors influencing the grease distribution inside the bearing after churning, with the final aim of enhancing lubrication. For the current simulations, a CAE software based on MPS, namely Particleworks, was used. Grease consists of a base oil, a thickener, and additives. Since it is a non-Newtonian fluid, it has a nonlinear relation shear stress vs shear rate. It is a visco-elastic material, so it does not flow in the absence of a threshold force. For current simulations, the grease rheology has been modelled using the Herschel-Bulkley model. The model was fitted on in-house rheometer test data and was reduced to a single cage-ball segment. All critical kinematic properties were preserved, that is the speeds of both the inner ring and ball surfaces and the oscillation of the ball position within the pocket as it travels through the loaded and unloaded zones of the bearing. The location and the duration of grease injections resulted in different grease distributions in the model. For demonstration purposes, this document only focuses on the results obtained injecting a grease layer on the inner ring surface in front of the contact. This realistically predicted grease reservoirs to be located at the cage bottom, on the top of cage and in the cage pockets. Sensitivity study on particle size, time step, surface tension and the parametric variation of the bearing speed were also performed. This is an important milestone, as we are able for the first time to virtually simulate the onset of grease reservoirs at locations corresponding to evidence from real bearing operations. The distribution of grease observed at the cage pockets is very important for oil film replenishment. This outcome gives us confidence that the MPS method can be used to support the design of bearing components contributing to enhanced lubrication.

Hydrodynamic lubrication behavior under miscellaneous operational conditions via CGB numerical model

The current study is basically focused on investigating the possible ways to enhance the lubricating oil film performance and hence ship energy efficiency of marine journal bearings in general terms. For the intended purpose, a novel numerical Circumferential Grooved Bearing (CGB) model was developed to assess journal bearing operating conditions based on versatile simulation analyses. Prior to all conducted test trials, the model validation has been confirmed based on the conformity between numerical outcomes and those derived from experimental procedures depending on Universal Journal Bearing Test Rig. CGB performance was evaluated at slow speed variations from 25 rpm up to 125 rpm and different applied loads utilizing the two lubricant oil grades of 5W40 and 0W30. Reducing shaft rotational speed by 80% was found to incur a reduction in the maximum oil film pressure value by 1.17 bar and 0.97 bar for the two aforementioned lubricants respectively. Further, the increase of applied loads from 1079 N up to 1471 N at a constant speed of 75 rpm reduces the maximum oil film pressure ratio by 0.14 and 0.18 for the two oil grades subsequently.

Effect of DLC film on the mitigation of white etching areas (WEAs) under dynamic loading

The premature failures in wind turbine gearbox bearings are primarily caused by the decay of subsurface microstructure called white etching areas and white etching cracks. Severe operating conditions of wind turbine gearbox bearings necessitated for tribological coatings to enhance the system performance. The current study investigated the performance of hydrogenated diamond-like‑carbon (DLC) coating against white etching areas formation under sliding-dynamic conditions. The dynamic loading experiments were carried out in the dynamic pin-on-disc tribometer with Polyalphaolefin base stock oil under a boundary lubrication regime. Prior to the dynamic load tests, detailed tribological characterisation of the deposited DLC coating was carried out. The post-test analysis results were compared with the uncoated AISI 52100 bearing steel tribopair to evaluate the performance of DLC-coated bearing steel against white etching areas formation under given conditions. The results obtained show the capability of the proposed coating to delay the formation of white etching areas in the bearing steel.

Cross-domain diagnosis of roller bearing faults based on the envelope analysis adaptive features and artificial neural networks

Traditional machine learning techniques depend on both the training data and the target data having the same data distribution and feature space. The performance may be unsatisfactory if there is a discrepancy in data distribution between the training data and the target data, which is known as a cross-domain learning issue. In this study, a technique for addressing this issue based on using the envelope analysis features coded as inputs to the Artificial Neural Networks (ANN) is presented. Specifically, three major cross-domain difficulties were resolved, including defect identification of different roller bearing types, rotating speeds, and loading conditions. The envelope approach is used to extract more distinguishing features at fundamental fault frequencies from the original signal, with the benefit of derived features being independent of both roller bearing type and operating conditions of rotating machines. The diagnosis outcomes were achieved experimentally through three different types of rollers bearing. Meanwhile, for each bearing type, three data sets were obtained at three different rotational speeds with different levels of fault categories to simulate all the cross-domain tasks. Moreover, the ANN model was trained using data of a particular bearing type and a certain operating state, whereas data of other bearing types were utilized to test the cross-domain performance of the proposed technique. At the same loading condition, the results indicate a 99.5% average success rate for bearing Koyo 1205, a 98.33% average accuracy for bearing NU 205, and a 97.3% average accuracy for the defective bearing kit. Furthermore, the results indicate that the suggested technique can deliver accurate cross-domain detection. Also, the experimental results proved that the suggested technology is a potential strategy for industrial applications.

Optimized selection of fluid lubricant for cylindrical roller bearings under elastohydrodynamic lubrication

Roller bearings are widely used in machinery. Keeping the contact surfaces of bearings properly lubricated strongly mitigates wear effects, improving bearing fatigue life. Therefore, systematically selecting the lubricant fluid that satisfies bearing operation conditions allows the lubricating layer to be able to carry the applied load, the operating temperature, and the roughness on contact. The nonlinear constrained optimization method is used for lubricant selection, seeking to find the fluid that best fits the bearing operation conditions. Roller bearing lubrication is characteristically elastohydrodynamic (EHL); namely, the Hertz theory describes the load applied on the contacts of a cylindrical roller bearing, and the Stribeck condition classifies the tribological condition of the surfaces in contact. This work concludes that roughness and speed are the most important parameters to consider when choosing a fluid lubricant.

Numerical Analysis of Turbulence Effect for Coupled Journal-Thrust Water-Lubricated Bearing With Micro Grooves

Abstract The purpose of this study is to assess the role of turbulence on the lubrication performances of coupled journal-thrust water-lubricated bearing with micro grooves using a numerical model. The results of the simulation model are compared to the published experimental data to verify the validity of the numerical model. The load capacity, maximum film pressure, and local Reynolds number variations with the rotating speed, eccentricity, radial clearance, axial geometric gap, and micro groove depth for coupled journal-thrust water-lubricated bearing are examined. Furthermore, the calculated results under the turbulent flow are compared with those under laminar flow for coupled and separate bearings. The results show that the turbulence effect can improve the lubrication performances by enlarging fluid pressure and load capacity of the coupled journal-thrust bearing and the laminar flow assumption is no longer applicable to the actual operating conditions of the water-lubricated bearings at a high rotation speed. In addition, optimal micro groove depths for both journal bearing and thrust bearing exist to reach the peak of the load capacity while the optimal micro groove depths for journal bearing and thrust bearing are not the same.

A Bearing Fault Diagnosis Method Based on Wavelet Denoising and Machine Learning

There are a lot of interference factors in the operating environment of machinery, which makes it ineffective to use traditional detection methods to judge the fault location and type of fault of the machinery, and even misjudgment of the fault location and type may occur. In order to solve these problems, this paper proposes a bearing fault diagnosis method based on wavelet denoising and machine learning. We use sensors to detect the operating conditions of rolling bearings under different working conditions to obtain datasets of different types of bearing failures. On the basis of using the wavelet denoising algorithm to reduce noise, we comprehensively evaluated five machine learning models, including K-means clustering, decision tree, random forest, and support vector machine to classify bearing faults and compare their results. By designing the fault classification evaluation prediction criteria, the following conclusions are drawn. The model proposed in this paper is significantly better than other traditional diagnostic models for bearing faults. In order to solve the problem of weak signal strength and background noise interference, this paper selects a better noise reduction algorithm under different quantitative evaluation indicators for wavelet denoising, which can better restore the true characteristics of the fault signal. Using unsupervised learning and supervised machine learning classification algorithms, the evaluation indicators before and after denoising are compared to make the classification results more accurate and reliable. This article will help researchers to intelligently diagnose the faults of rolling bearing equipment in rotating machinery.

A Multi-Scale Attention Mechanism Based Domain Adversarial Neural Network Strategy for Bearing Fault Diagnosis

There are a large number of bearings in aircraft engines that are subjected to extreme operating conditions, such as high temperature, high speed, and heavy load, and their fatigue, wear, and other failure problems seriously affect the reliability of the engine. The complex and variable bearing operating conditions can lead to differences in the distribution of data between the source and target operating conditions, as well as insufficient labels. To solve the above challenges, a multi-scale attention mechanism-based domain adversarial neural network strategy for bearing fault diagnosis (MADANN) is proposed and verified using Case Western Reserve University bearing data and PT500mini mechanical bearing data in this paper. First, a multi-scale feature extractor with an attention mechanism is proposed to extract more discriminative multi-scale features of the input signal. Subsequently, the maximum mean discrepancy (MMD) is introduced to measure the difference between the distribution of the target domain and the source domain. Finally, the fault diagnosis process of the rolling is realized by minimizing the loss of the feature classifier, the loss of the MMD distance, and maximizing the loss of the domain discriminator. The verification results indicate that the proposed strategy has stronger learning ability and better diagnosis performance than shallow network, deep network, and commonly used domain adaptive models.

A novel motor bearing fault diagnosis method based on a deep sparse binary autoencoder and principal component analysis

Due to the complex and variable operating conditions of motor bearings, it is difficult for a deep autoencoder (DAE) to effectively extract valuable fault features from the raw vibration signal, which makes it difficult to identify faults. To enhance the extraction ability of the deep features of a network model and improve the accuracy of fault identification, this paper proposes a fault diagnosis method for motor bearings based on a deep sparse binary autoencoder and principal component analysis (PCA). Firstly, a deep sparse binary autoencoder is constructed by combining an autoencoder with a binary processor to improve the ability to extract deep features. Secondly, principal component analysis is used to fuse high-dimensional features to reduce dimensionality and eliminate redundant information existing in the deep features. Finally, fused deep features are input into a Softmax classifier to train the intelligent fault diagnosis model. The proposed method is validated on a rolling bearing dataset. Compared with existing methods, the experimental results show that this method can effectively extract robust features from the original vibration signals and improve the fault diagnosis results.

Simulation methodology for the identification of critical operating conditions of planetary journal bearings in wind turbines

The usage of journal bearings as planetary bearings in wind turbines instead of roller bearings has become more common in recent years. Their usage is advantageous, due to smaller installation space needed compared to roller bearings allowing for higher power densities of wind turbine drive trains. However, this technology presents a challenge since there is currently no standardized approach for the design of planetary journal bearings regarding wear. Due to varying wind speeds and dynamic operating events a large variation of loads has to be considered in the design process of a planetary journal bearing for wind turbines. Some of these loads are considered potentially critical to the journal bearing in terms of wear. Identifying these critical load areas early in the design phase supports a reliable bearing design and wind turbine operation.This paper introduces a method to identify critical operating conditions for planetary journal bearings using a simulation tool chain, which couples a multi body simulation (MBS) model of a wind turbine with an elasto-hydrodynamic (EHD) model of the planetary journal bearing. Based on the EHD results critical operating conditions are determined for the planetary bearing. Furthermore, methods are implemented to reduce the number of required EHD simulations for analysing the bearing design. The combination of the identification of critical operating conditions, while reducing the computational effort leads to a simulation methodology, which enables a faster bearing design assessment considering the wide variation of wind turbine operating conditions. The applicability of this method is demonstrated by a simplified use case.Firstly, this paper introduces the MBS model and the parameter space that describes possible combinations of bearing loads such as forces, moments and rotational speed. Due to the number of combinations and the EHD computing effort, the identified parameter space is secondly sampled statistically to reduce the simulation effort. A risk map is derived from the EHD results, to easily indicate potentially critical operating conditions for the planetary journal bearing.

Multi-source alignment domain adaptation with similarity measurement for cross-domain bearing fault diagnosis

Variations in bearing operating conditions may cause a shift in the feature distribution of fault signals, weakening the generalization ability of the fault diagnosis model. Traditional methods with domain adaptation (DA) extract invariant cross-domain fault features, but they are mostly applied to a single-source domain. In the case of multi-source cross-domain transfer, however, determining which source domain has a better transfer effect to the target domain is difficult. In this paper, we aim to combine the transferable knowledge contained in all available source domains to improve the transfer performance. Low-correlation features are often more prone to bias under variable working conditions. The contribution of high-correlation features to the model must be increased. Accordingly, a multi-source alignment DA network with similarity measurement (MADASM) is proposed for this issue. First, DA is performed for each combination of source and target domains, and similarity measurement is introduced to constrain the similarity between the input and the central features. Second, the learned features are inputted into the corresponding domain-specific classifiers, of which the classifier discrepancy loss is then introduced to minimize the difference between the outputs of each domain-specific classifier, resulting in consistent prediction results for classifiers on the target domain. Finally, the average of output probabilities from all the classifier is calculated as the diagnosis result. Experimental results show that MADASM can fully utilize fault category information in multiple source domains to extract fault features with high correlation even in challenging scenarios with unknown data labels and lacking of prior knowledge in target domain.

VMD–RP–CSRN Based Fault Diagnosis Method for Rolling Bearings

In response to the problems of low accuracy and poor noise immunity of the traditional fault diagnosis method for rolling bearing fault diagnosis due to the complex and variable operating conditions of rolling bearings and the large noise interference during bearing signal acquisition, a rolling bearing fault diagnosis model based on VMD–RP–CSRN is proposed. Firstly, the initial feature extraction of the bearing signal is carried out by variational modal decomposition (VMD), which is then converted into a two-dimensional image with fault features by recurrent plot (RP) coding, and then the feature images are input to a channel split residual network (CSRN) for feature extraction and fault classification. In order to verify the accuracy and noise immunity of the proposed method for the diagnosis of bearing faults under complex working conditions, experiments on the selection of parameters in the CSRN model were conducted on the bearing dataset of Jiangnan University, and experiments on the diagnosis of bearing faults under complex working conditions and noise immunity of CSRN were carried out and compared with other commonly used methods. The proposed bearing fault diagnosis method based on VMD–RP–CSRN combines VMD and RP to retain the fault features in the original signal to the maximum extent and stress the hidden features in the signal. The proposed channel split operation realizes the extraction of hidden features by selecting the main operating channel of the three-channel feature image, and makes more fault features participate in the feature extraction of the diagnosis model. The experimental results demonstrate that the proposed method is at least 1.2% better than the comparison method, and has better noise immunity. In addition, experiments on the fault diagnosis capability of the model with different data set sizes and the diagnosis of variable speed bearing data by the model show that the proposed method has better generalization performance and diagnosis capability.

Bearing Fault Diagnosis of Hot-Rolling Mill Utilizing Intelligent Optimized Self-Adaptive Deep Belief Network with Limited Samples.

Given the complexity of the operating conditions of rolling bearings in the actual rolling process of a hot mill and the difficulty in collecting data pertinent to fault bearings comprehensively, this paper proposes an approach that diagnoses the faults of a rolling mill bearing by employing the improved sparrow search algorithm deep belief network (ISAA-DBN) with limited data samples. First, the fast spectral kurtosis approach is adopted to convert the non-stationary original vibration signals collected by the acceleration sensors installed at the axial and radial ends of the rolling mill bearings into two-dimensional (2D) spectral kurtosis time–frequency images with higher feature recognition, and the principal component analysis (PCA) technique is used to decrease the dimension of the data in order to achieve a high diagnosis rate with a limited number of samples. Subsequently, the sparrow search algorithm (SSA) is used to realize the intelligent optimized self-adaptive function of a deep belief network (DBN). Furthermore, the firefly disturbance algorithm is employed to improve the spatial search capability and robustness of SSA-DBN in order to achieve better performance of the ISSA-DBN method. Finally, the proposed approach is experimentally compared to other approaches used for diagnosis. The results show that the proposed approach not only retains the useful features of the data through dimension reduction but also improves the efficiency of the diagnosis and achieves the highest diagnosis accuracy with limited data samples. In addition, the optimal position of the sensor for diagnosing rolling mill roll faults is identified.

A comprehensive working condition identification scheme for rolling bearings based on modified CEEMDAN as well as modified hierarchical amplitude-aware permutation entropy

As a pivotal part of a machine driven system, the health states of rolling bearings usually determine the normal operation of a whole item of equipment. Consequently, it is important to make accurate and timely judgments as to the operating conditions of rolling bearings. In this paper, a synthesized diagnosis technology, including fault pre-judgment and identification for rolling bearings is proposed. In the first section, a threshold value is defined on the basis of the sensitivity of amplitude-aware permutation entropy (AAPE) to bearing faults. Whether the bearing has defects is judged is based on this value. If a defect exists, a feature extraction scheme combining the modified complete ensemble empirical mode decomposition with adaptive noise (MCEEMDAN) and the modified hierarchical AAPE (MHAAPE) is adopted, to fully mine the hidden state features. Firstly, the scheme uses MCEEMDAN, which benefits from a good time-frequency decomposition capability, to divide the signal of trouble into a group of intrinsic mode functions (IMFs). Second, the MHAAPE of each IMF component is computed to form the candidate state features. Then, multi cluster feature selection is employed to compress the high-dimensional fault features to form the low-dimensional sensitive feature vectors required for subsequent classification. Finally, the sensitive feature vectors are input into a random forest classifier for training and classification, so as to ascertain the different fault types and severity. In addition, different contrastive methods are tested based on experimental data. The experiment results indicate that, compared to contrastive methods, the proposed scheme enjoys better performance, which can effectively judge whether the bearing is healthy and accurately identify different fault states in bearings.

Fault Diagnosis Method for Rolling Bearing Based on Sparse Principal Subspace Discriminant Analysis

Rolling bearings are omnipresent parts in industrial fields. To comprehensively reflect the status of rolling bearing and improve the classification accuracy, fusion information is widely used in various studies, which may result in high dimensionality, redundancy information of dataset, and time consumption. Thus, it is of crucial significance in extracting optimal features from high-dimensional and redundant feature space for classification. In this study, a fault diagnosis of rolling bearings model based on sparse principal subspace discriminant analysis is proposed. It extracts sparse discrimination information, meanwhile preserving the main energy of original dataset, and the sparse regularization term and sparse error term constrained by l2,1-norm are introduced to improve the performance of feature extraction and the robustness to noise and outliers. The multi-domain feature space involved a time domain, frequency domain, and time-frequency domain is first derived from the original vibration signals. Then, the intrinsic geometric features extracted by sparse principal subspace discriminant analysis are fed into a support vector machine classifier to recognize different operating conditions of bearings. The experimental results demonstrated that the feasibility and effectiveness of the proposed fault diagnosis model based on a sparse principal subspace discriminant analysis algorithm can achieve higher recognition accuracy than fisher discriminant analysis and its extensions, and it is relatively insensitive to the impact of noise and outliers owing to the sparse property.