A Hybrid Approach for Predicting the Remaining Useful Life of Bearings Based on the RReliefF Algorithm and Extreme Learning Machine

Accurately predicting the remaining useful life(RUL)of bearings in mining rotating equipment is vital for mining enterprises.This research aims to distinguish the features associated with the RUL of bearings and propose a prediction model based on these selected features.This study proposes a hybrid predictive model to assess the RUL of rolling element bearings.The proposed model begins with the pre-processing of bearing vibration signals to reconstruct sixty time-domain features.The hybrid model selects relevant features from the sixty time-domain features of the vibration signal by adopting the RReliefF feature selection algorithm.Subsequently,the extreme learning machine(ELM)approach is applied to develop a predictive model of RUL based on the optimal features.The model is trained by optimizing its parameters via the grid search approach.The training datasets are adjusted to make them most suitable for the regression model using the cross-validation method.The proposed hybrid model is analyzed and validated using the vibration data taken from the public XJTU-SY rolling element-bearing database.The comparison is constructed with other traditional models.The experimental test results demonstrated that the proposed approach can predict the RUL of bearings with a reliable degree of accuracy.

A fatigue life prediction method of rolling bearing under elliptical contact elastohydrodynamic lubrication

In order to more accurately predict the contact fatigue life of rolling bearing, a prediction method of fatigue life of rolling bearing is proposed based on elastohydrodynamic lubrication （EHL）, the 3-paameter Weibull distribution ad fatigue strength. First,the contact stress considering elliptical EHL is obtained by mapping film pressure onto the Hertz zone. Then,the basic strength model of rolling bearing based on the 3-parameter Weibull distribution is deduced by the series connection reliability theory. Considering the effect of the type of stress, variation of shape and fuctuation of load, the mathematical models of the 尸 -tS-TV curve of the minimum life and the characteristic life for rolling bearing are established, respectively, and thus the prediction model of fatigue life of rolling bearing based on the 3-paameter Weibull distribution and fatigue strength is further deduced. Finally, the contact fatigue life obtained by the proposed method ad the latest international standard （IS0281： 2007） about the fatigue life prediction of rolling bearing are compared with those obtained by the statistical method. Results show that the proposed prediction method is effective and its relative error is smaier than that of the latest international standard （IS0281： 2007） with reliability R 〉 0. 93.

WEAR AND LIFE OF PCBN TOOLS WHEN DRY-CUTTING BEARING STEEL GCr15

The wear forms and reasons of PCBN tools when dry-cutting bearing steel GCr15are studied systematically. The effect law of the workpiece hardness on PCBN tools is gained andtool wearing with the quickest speed at the workpiece critical hardness is proved. The life equationat two kinds of workpiece hardness demonstrates that the effect of the cutting speed on the PCBNtool life is less than that of carbide tools and ceramic tools.

Deep Spatiotemporal Convolutional-Neural-Network-Based Remaining Useful Life Estimation of Bearings

The remaining useful life(RUL)estimation of bearings is critical for ensuring the reliability of mechanical systems.Owing to the rapid development of deep learning methods,a multitude of data-driven RUL estimation approaches have been proposed recently.However,the following problems remain in existing methods:1)Most network models use raw data or statistical features as input,which renders it difficult to extract complex fault-related information hidden in signals;2)for current observations,the dependence between current states is emphasized,but their complex dependence on previous states is often disregarded;3)the output of neural networks is directly used as the estimated RUL in most studies,resulting in extremely volatile prediction results that lack robustness.Hence,a novel prognostics approach is proposed based on a time-frequency representation(TFR)subsequence,three-dimensional convolutional neural network(3DCNN),and Gaussian process regression(GPR).The approach primarily comprises two aspects:construction of a health indicator(HI)using the TFR-subsequence-3DCNN model,and RUL estimation based on the GPR model.The raw signals of the bearings are converted into TFR-subsequences by continuous wavelet transform and a dislocated overlapping strategy.Subsequently,the 3DCNN is applied to extract the hidden spatiotemporal features from the TFR-subsequences and construct HIs.Finally,the RUL of the bearings is estimated using the GPR model,which can also define the probability distribution of the potential function and prediction confidence.Experiments on the PRONOSTIA platform demonstrate the superiority of the proposed TFR-subsequence-3DCNN-GPR approach.The use of degradation-related spatiotemporal features in signals is proposed herein to achieve a highly accurate bearing RUL prediction with uncertainty quantification.

Remaining Useful Life Prediction of Rolling Element Bearings Based on Different Degradation Stages and Particle Filter

A method is proposed to improve the accuracy of remaining useful life prediction for rolling element bearings,based on a state space model(SSM)with different degradation stages and a particle filter.The model is improved by a method based on the Paris formula and the Foreman formula allowing the establishment of different degradation stages.The remaining useful life of rolling element bearings can be predicted by the adjusted model with inputs of physical data and operating status information.The late operating trend is predicted by the use of the particle filter algorithm.The rolling bearing full life experimental data validate the proposed method.Further,the prediction result is compared with the single SSM and the Gamma model,and the results indicate that the predicted accuracy of the proposed method is higher with better practicability.

Fatigue Life Prediction of Rolling Bearings Based on Modified SWT Mean Stress Correction

The existing engineering empirical life analysis models are not capable of considering the constitutive behavior of materials under contact loads;as a consequence,these methods may not be accurate to predict fatigue lives of roll-ing bearings.In addition,the contact stress of bearing in operation is cyclically pulsating,it also means that the bear-ing undergo non-symmetrical fatigue loadings.Since the mean stress has great effects on fatigue life,in this work,a novel fatigue life prediction model based on the modified SWT mean stress correction is proposed as a basis of which to estimate the fatigue life of rolling bearings,in which,takes sensitivity of materials and mean stress into account.A compensation factor is introduced to overcome the inaccurate predictions resulted from the Smith,Watson,and Topper(SWT)model that considers the mean stress effect and sensitivity while assuming the sensitivity coefficient of all materials to be 0.5.Moreover,the validation of the model is finalized by several practical experimental data and the comparison to the conventional SWT model.The results show the better performance of the proposed model,especially in the accuracy than the existing SWT model.This research will shed light on a new direction for predicting the fatigue life of rolling bearings.

Online residual useful life prediction of large-size slewing bearings A data fusion method

To decrease breakdown time and improve machine operation reliability,accurate residual useful life(RUL) prediction has been playing a critical role in condition based monitoring.A data fusion method was proposed to achieve online RUL prediction of slewing bearings,which consisted of a reliability based RUL prediction model and a data driven failure rate(FR) estimation model.Firstly,an RUL prediction model was developed based on modified Weibull distribution to build the relationship between RUL and FR.Secondly,principal component analysis(PCA) was introduced to process multi-dimensional life-cycle vibration signals,and continuous squared prediction error(CSPE) and its time-domain features were employed as equipment performance degradation features.Afterwards,an FR estimation model was established on basis of the degradation features and relevant FRs using simplified fuzzy adaptive resonance theory map(SFAM) neural network.Consequently,real-time FR of equipment can be obtained through FR estimation model,and then accurate RUL can be calculated through the RUL prediction model.Results of a slewing bearing life test show that CSPE is an effective indicator of performance degradation process of slewing bearings,and that by combining actual load condition and real-time monitored data,the calculation time is reduced by 87.3%and the accuracy is increased by 0.11%,which provides a potential for online RUL prediction of slewing bearings and other various machineries.

Rolling Bearing Remaining Useful Life Prediction Based on Wiener Process

Rolling bearing is the key part of mechanical system.Accurate prediction of bearing life can reduce maintenance costs,improve availability,and prevent catastrophic consequences,aiming at solving the problem of the nonlinear,random and small sample problems faced by rolling bearings in actual operating conditions.In this work,the nonlinearWiener process with random effect and unbiased estimation of unknown parameters is used to predict the remaining useful life of rolling bearings.Firstly,random effects and nonlinear parameters are added to the traditional Wiener process,and a parameter unbiased estimation method is used to estimate the positional parameters of the constructed Wiener model.Finally,the model is validated using a common set of bearing datasets.Experimental results show that compared with the traditional maximum likelihood function estimation method,the parameter unbiased estimation method can effectively improve the accuracy and stability of the parameter estimation results.The model has a good fitting effect,which can accurately predict the remaining useful life of rolling bearing.

Dense-Structured Network Based Bearing Remaining Useful Life Prediction System

This work is focused on developing an effective method for bearing remaining useful life predictions.The method is useful in accurately predicting the remaining useful life of bearings so that machine damage,production outage,and human accidents caused by unexpected bearing failure can be prevented.This study uses the bearing dataset provided by FEMTO-ST Institute,Besancon,France.This study starts with the exploration of neural networks,based on which the biaxial vibration signals are modeled and analyzed.This paper introduces pre-processing of bearing vibration signals,neural network model training and adjustment of training data.The model is trained by optimizing model parameters and verifying its performance through cross-validation.The proposed model’s superiority is also confirmed through a comparison with other traditionalmodels.In this study,the neural network model is trained with various types of bearing data and can successfully predict the remaining useful life.The algorithm proposed in this study achieves a prediction accuracy of coefficient of determination as high as 0.99.

Fatigue Life of Slewing Bearings under Combined Radial,Axial and Tilting Moment Loads

A calculation method of fatigue life for slewing bearings under combined radial, axial and tilting moment loads was proposed. Single row four-point contact ball slewing bearing being used as a case, the statics model of the slewing bearing was established and a set of equilibrium equations were obtained. By solving the equilibrium equatioas, the rolling element loads were obtained and the equivalent rolling element loads were calculated further. By using the geometrical parameters of the bearing, the rating rolling element loads were calculated, and the fa- tigue life of the bearing was calculated by using the rating rolling element loads and the equivalent rolling element loads. A calculation example shows the feasibility of the proposed method.

Remaining useful life prediction for train bearing based on an ILSTM network with adaptive hyperparameter optimization

Remaining useful life(RUL)prediction for bearing is a significant part of the maintenance of urban rail transit trains.Bearing RUL is closely linked to the reliability and safety of train running,but the current prediction accuracy makes it difficult to meet the re-quirements of high reliability operation.Aiming at the problem,a prediction model based on an improved long short-term memory(ILSTM)network is proposed.Firstly,the variational mode decomposition is used to process the signal,the intrinsic mode function with stronger representation ability is determined according to energy entropy and the degradation feature data is constructed com-bined with the time domain characteristics.Then,to improve learning ability,a rectified linear unit(ReLU)is applied to activate a fully connected layer lying after the long short-term memory(LSTM)network,and the hidden state outputs of the layer are weighted by attention mechanism.The Harris Hawks optimization algorithm is introduced to adaptively set the hyperparameters to improve the performance of the LSTM.Finally,the ILSTM is applied to predict bearing RUL.Through experimental cases,the better perfor-mance in bearing RUL prediction and the effectiveness of each improving measures of the model are validated,and its superiority of hyperparameters setting is demonstrated.

Fatigue Damage Mechanism of Oil Film Bearing Sleeve

With the rapid development of the steel industry, to keep pace with the current trend of high speed, continuous, and large-scale production that focuses on automation and high levels of efficiency, many state-owned steel companies are being equipped with oil film bearings. Through long-term on-spot inspection and research on the fatigue failure of oil film bearing, three segments of annulated fatigue breakage were found axially along the inner surface of the bearing sleeve. In order to elucidate the reason for the three-segment annulated damage under rolling load, numerical boundary element method was adopted to analyze the contact behaviors between the sleeve and rollneck. Failure mechanism was discussed in detail, the distributions of contact stress were analyzed, and the service lives of the sleeve for different positions on the inner surface were quantitatively described, which provided an effective means to decrease wear and adhesive damage of the sleeve and to increase the load capacity of oil film bearing and its service life as well.

Mechanical behaviors of cross roller bearings with raceway roundness error

Taking the raceway roundness error into account,mechanical characteristics of cross roller bearings(CRBs)were investigated.A static analysis model of CRBs considering the raceway roundness error was established.Based on this model,the rotational accuracy and load distribution of CRBs under constraints of geometry and external loads were derived.The fatigue life of CRBs with roundness error was calculated by applying Palmgren-Miner linear cumulative damage theory.The influence of inner and outer raceway roundness error on the performance of the CRBs,such as rotational accuracy,load distribution,and fatigue life,was studied through the analysis of examples.The results indicate that the influence of roundness error on the rotating inner raceway is more significant than that of roundness error on the nonrotating outer raceway.The roundness error on the rotating inner raceway always degrades the performance of CRBs.However,a proper roundness error on the nonrotating outer raceway can reduce the loads acting on the rollers and thus improve the fatigue life of CRBs.The effect of the roundness error amplitude on the bearing performance is ordinal,whereas the effect of the roundness order on the bearing performance is not in order.

Study on Oxygen Content, Inclusions and Fatigue Properties of Bearing Steels Produced by Different Processes

The metallurgical properties and fatigue life of bearing steel processed by electric furnace (EAF), ladle refining (LF-VD), continous casting (CC) and electroslag remelting (ESR) have been investigated. The main results obtained are as follows: (1) Due to low oxygen content and dispersion inclusions in steel, the fatigue Life of LF-VD-IC or CC is three times as high as that of EAF steel; (2) The oxygen content in steel produced by CC process is about 9.0x10(-6), the carbon segregation (C/C(0)) is from 0.92 to 1.10 and the fatigue life of CC steel is equal to that of ladle refining ingot casting steel; (3) Although the amount of inclusion and oxygen in ESR steel is higher than that of LF-VD-IC or CC steel, the fatigue life of ESR steel is higher than that of the latter because of its fine and well dispersed inclusions.

THE OPERATIONAL PROPERTY ANALYSES OF THE COMPOSITE ROLLING BEARING

This paper deals with the test research on noise and fatigue life of the composite rolling bearings which have been developed recently. The test results show that the-composite rolling bearings have remarkable advantages of low noise and great load-bearing capacity over plastic ones.

EFFECT OF SULFUR ON PROPERTIES OF BALL BEARING STEEL

5 heats of GCr15 bearing steel of different sulfur contents ranging from 0.009-0.092% （wt.）were smelted. The role of sulfur in bearing steel and its effect on contact fatigue properties andfracture toughness KICWere studied. It was shown that as the sulfur content increases the sulfur content dissolved in the steelsubstrate remains unchanged. The best contact fatigue property appears at the sulfur content of0.045% （wt.）, and the influence of sulfur content on the fracture toughness of bearing steel is notobvious. Finally, the mechanism of the role of sulfur was investigated.

Luster Polish Strengthening Treatment for Raceway Surface of Aeroengine Bearings

A new surface strengthening technology, luster polish strengthening treatment, was proposed to treat the raceway surface of aeroengine bearings （9Cr18Mo） with the centrifugal strengthening machine exclusively designed for luster polish strengthening treatment. The experimental results showed that luster polish strengthening treatment produced a compressive residual stress layer with a depth of over 80 μm below the surface of the bearing raceway, and thus effectively removed the metamorphic layer in the raceway surface. After luster polish strengthening treatment, the average surface hardness of the aeroengine bearing raceway was increased from 61.02 HRC to 63.01 HRC, the surface roughness was reduced from 0.06 μm to 0.03 μm, and the contact fatigue life of the aeroengine bearings was improved by about 90%, with the dispersion of fatigue life being reduced remarkably. Theoretical calculation result agrees with that obtained by experiment.

Robust Optimization Method of Cylindrical Roller Bearing by Maximizing Dynamic Capacity Using Evolutionary Algorithms

Optimization of cylindrical roller bearings(CRBs)has been performed using a robust design.It ensures that the changes in the objective function,even in the case of variations in design variables during manufacturing,have a minimum possible value and do not exceed the upper limit of a desired range of percentage variation.Also,it checks the feasibility of design outcome in presence of manufacturing tolerances in design variables.For any rolling element bearing,a long life indicates a satisfactory performance.In the present study,the dynamic load carrying capacity C,which relates to fatigue life,has been optimized using the robust design.In roller bearings,boundary dimensions(i.e.,bearing outer diameter,bore diameter and width)are standard.Hence,the performance is mainly affected by the internal dimensions and not the bearing boundary dimensions mentioned formerly.In spite of this,besides internal dimensions and their tolerances,the tolerances in boundary dimensions have also been taken into consideration for the robust optimization.The problem has been solved with the elitist non-dominating sorting genetic algorithm(NSGA-II).Finally,for the visualization and to ensure manufacturability of CRB using obtained values,radial dimensions drawing of one of the optimized CRB has been made.To check the robustness of obtained design after optimization,a sensitivity analysis has also been carried out to find out how much the variation in the objective function will be in case of variation in optimized value of design variables.Optimized bearings have been found to have improved life as compared with standard ones.

离心泵轴承疲劳寿命仿真分析及试验验证

针对工程中常出现的离心泵轴承实际寿命低于其设计寿命问题,以IS 100-80-160型离心泵为研究对象,对其进行数值仿真,将多个工况下的仿真结果与工程中校核泵轴承寿命的Steponff经验公式进行对比,发现Steponff公式计算出的径向力值偏小.为分析Steponff公式计算的轴承寿命校核误差,将径向力加载至轴承内圈进行有限元疲劳寿命仿真分析,并搭建离心泵径向力及轴承寿命试验台进行试验验证.结果表明:径向力计算误差以及工况变化将产生较大的轴承寿命偏差,该偏差在额定工况下最大,且随着径向力变大而逐步减小;与ISO寿命计算结果对比,数值仿真疲劳寿命安全系数更高;Steponff公式的计算值不够准确,将导致轴承实际寿命与其设计寿命相差极大;在大型低比转数离心泵轴承选用中,需考量Steponff公式的适用范围,同时可应用数值仿真校核其额定寿命.研究结果可为大型泵轴承寿命校核提供一定的依据.

聚脲润滑脂稠化剂对球轴承疲劳寿命的影响

采用光干涉法、动态击穿电压测试对3种聚脲润滑脂样品润滑膜厚进行了表征,同时测试了3种样品的轴承疲劳寿命和温升特性,对比研究了聚脲润滑脂稠化剂对润滑状态的影响,结果表明:聚脲润滑脂稠化剂在摩擦副表面吸附形成垫层,阻碍了润滑脂乏油润滑引起的润滑膜厚持续减小;聚脲润滑脂稠化剂的类型、含量对表面起源型剥落的轴承疲劳寿命有显著影响,合理的稠化剂配方可显著延长轴承疲劳寿命,这可能与聚脲润滑脂稠化剂的回流特性相关。