A rotating packed bed is a typical chemical process enhancement equipment that can strengthen micromixing and mass transfer.During the operation of the rotating packed bed,the nonreactants and products irregularly adh...A rotating packed bed is a typical chemical process enhancement equipment that can strengthen micromixing and mass transfer.During the operation of the rotating packed bed,the nonreactants and products irregularly adhere to the wire mesh packing in the rotor,thus resulting in an imbalance in the vibration of the rotor,which may cause serious damage to the bearing and material leakage.This study proposes a model prediction for estimating the bearing residual life of a rotating packed bed based on rotor imbalance response analysis.This method is used to determine the influence of the mass on the imbalance in the vibration of the rotor on bearing damage.The major influence on rotor vibration was found to be exerted by the imbalanced mass and its distribution radius,as revealed by the results of orthogonal experiments.Through implementing finite element analysis,the imbalance response curve for the rotating packed bed rotor was obtained,and a correlation among rotor imbalance mass,distribution radius of imbalance mass,and bearing residue life was established via data fitting.The predicted value of the bearing life can be used as the reference basis for an early safety warning of a rotating packed bed to effectively avoid accidents.展开更多
Paris law can reflect the failure mechanism of materials and is usually used to be a method to predict fatigue life or residual fatigue life.But the variable which can represent the health of machine is hardly measure...Paris law can reflect the failure mechanism of materials and is usually used to be a method to predict fatigue life or residual fatigue life.But the variable which can represent the health of machine is hardly measured on line.To a degree,the difficulty of on-line application restricts the scope of application of Paris law.The relationship between characteristic values of vibration signals and the variable in the Paris equation which can describe the health of machine is investigated by taking ball bearings as investigative objects.Based on 6205 deep groove ball bearings as a living example,historical lives and vibration signals are analyzed.The feasibility of describing that variable in the Paris equation by the characteristic value of vibration signals is inspected.After that vibration signals decomposed by empirical mode decomposition(EMD),root mean square(RMS) of intrinsic mode function(IMF) involving fault characteristic frequency has a consistent trend with the diameter of flaws.Based on the trend,two improved Paris models are proposed and the scope of application of them is inspected.These two Paris Models are validated by fatigue residual life data from tests of rolling element bearings and vibration signals monitored in the process of operation of rolling element bearings.It shows that the first improved Paris Model is simple and plain and it can be easily applied in actual conditions.The trend of the fatigue residual life predicted by the second improved Paris model is close to the actual conditions and the result of the prediction is slightly greater than the truth.In conclusion,after the appearance of detectable faults,these improved models based on RMS can predict residual fatigue life on line and a new approach to predict residual fatigue life of ball bearings on line without disturbing the machine running is provided.展开更多
Recently,deep learning(DL)has been widely used in the field of remaining useful life(RUL)prediction.Among various DL technologies,recurrent neural network(RNN)and its variant,e.g.,long short-term memory(LSTM)network,h...Recently,deep learning(DL)has been widely used in the field of remaining useful life(RUL)prediction.Among various DL technologies,recurrent neural network(RNN)and its variant,e.g.,long short-term memory(LSTM)network,have gained extensive attention for their ability to capture temporal dependence.Although existing RNN-based methods have demonstrated their RUL prediction effectiveness,they still suffer from the following two limitations:1)it is difficult for the RNN to directly extract degradation features from original monitoring data and 2)most RNN-based prognostics methods are unable to quantify RUL uncertainty.To address the aforementioned limitations,this paper proposes a new prognostics method named residual convolution LSTM(RC-LSTM)network.In the RC-LSTM,a new ResNet-based convolution LSTM(Res-ConvLSTM)layer is stacked with a convolution LSTM(ConvLSTM)layer to extract degradation representations from monitoring data.Then,under the assumption that the RUL follows a normal distribution,an appropriate output layer is constructed to quantify the uncertainty of prediction results.Finally,the effectiveness and superiority of the RC-LSTM are verified using monitoring data from accelerated bearing degradation tests.展开更多
Residual useful life(RUL)prediction is a key issue for improving efficiency of aircraft engines and reducing their maintenance cost.Owing to various failure mechanism and operating environment,the application of class...Residual useful life(RUL)prediction is a key issue for improving efficiency of aircraft engines and reducing their maintenance cost.Owing to various failure mechanism and operating environment,the application of classical models in RUL prediction of aircraft engines is fairly difficult.In this study,a novel RUL prognostics method based on using ensemble recurrent neural network to process massive sensor data is proposed.First of all,sensor data obtained from the aircraft engines are preprocessed to eliminate singular values,reduce random fluctuation and preserve degradation trend of the raw sensor data.Secondly,three kinds of recurrent neural networks(RNN),including ordinary RNN,long shortterm memory(LSTM),and gated recurrent unit(GRU),are individually constructed.Thirdly,ensemble learning mechanism is designed to merge the above RNNs for producing a more accurate RUL prediction.The effectiveness of the proposed method is validated using two characteristically different turbofan engine datasets.Experimental results show a competitive performance of the proposed method in comparison with typical methods reported in literatures.展开更多
针对动车组车载变压器油纸绝缘剩余寿命预测中单性能退化指标难以全面反映油纸绝缘退化过程的问题,考虑车载变压器油纸绝缘退化的个体差异性及两性能指标间的相关关系,提出了基于Copula函数的两性能指标相关退化的油纸绝缘剩余寿命预测...针对动车组车载变压器油纸绝缘剩余寿命预测中单性能退化指标难以全面反映油纸绝缘退化过程的问题,考虑车载变压器油纸绝缘退化的个体差异性及两性能指标间的相关关系,提出了基于Copula函数的两性能指标相关退化的油纸绝缘剩余寿命预测方法:采用具有随机效应的维纳过程建立油纸绝缘的两性能指标相关退化模型,基于赤池信息准则(Akaike Information Criterion, AIC)选择拟合效果更优的Copula函数来描述两性能指标间的相关关系,采用最大似然估计法估计初始时刻的模型参数,基于序列贝叶斯更新方法在线更新退化模型中的漂移系数,以实现油纸绝缘剩余寿命的在线预测。最后以加速热老化试验下油纸绝缘的聚合度和抗拉强度的退化数据进行实例验证。结果表明,两性能指标相关退化模型比单性能指标退化模型的剩余寿命预测值与实际值之间的平均绝对误差更小,预测的准确性更高,且随着模型参数不断更新,剩余寿命的预测值与实际值间的绝对误差在不断减小,预测结果的准确性在不断提升。展开更多
When a nonlinear fatigue damage accumulation model based on damage curve approach is used to get better residual life prediction results, it is necessary to solve the problem caused by the uncertain exponent of the mo...When a nonlinear fatigue damage accumulation model based on damage curve approach is used to get better residual life prediction results, it is necessary to solve the problem caused by the uncertain exponent of the model. Considering the effects of load interaction, the assumption that there is a linear dependence between the exponent ratio and the loading ratio is established to predict fatigue residual life of materials. Three experimental data sets are used to validate the rightness of the proposition. The comparisons of experimental data and predictions show that the predictions based on the proposed proposition are in good accordance with the experimental results as long as the parameters that represent the linear correlativity are set an appropriate value. Meanwhile, the accuracy of the proposition is approximated to that of an existing model. Therefore, the proposition proposed in this paper is reasonable for residual life prediction.展开更多
基金the High-Performance Computing Platform of Beijing University of Chemical Technology(BUCT)for supporting this papersupported by the Fundamental Research Funds for the Central Universities(JD2319)+2 种基金the CNOOC Technical Cooperation Project(ZX2022ZCTYF7612)the National Natural Science Foundation of China(51775029,52004014)the Chinese Universities Scientific Fund(XK2020-04)。
文摘A rotating packed bed is a typical chemical process enhancement equipment that can strengthen micromixing and mass transfer.During the operation of the rotating packed bed,the nonreactants and products irregularly adhere to the wire mesh packing in the rotor,thus resulting in an imbalance in the vibration of the rotor,which may cause serious damage to the bearing and material leakage.This study proposes a model prediction for estimating the bearing residual life of a rotating packed bed based on rotor imbalance response analysis.This method is used to determine the influence of the mass on the imbalance in the vibration of the rotor on bearing damage.The major influence on rotor vibration was found to be exerted by the imbalanced mass and its distribution radius,as revealed by the results of orthogonal experiments.Through implementing finite element analysis,the imbalance response curve for the rotating packed bed rotor was obtained,and a correlation among rotor imbalance mass,distribution radius of imbalance mass,and bearing residue life was established via data fitting.The predicted value of the bearing life can be used as the reference basis for an early safety warning of a rotating packed bed to effectively avoid accidents.
基金supported by National Natural Science Foundation of China (Grant No. 50705096)National Science and Technology Major Project of China(Grant No. 2009zx04014-014)
文摘Paris law can reflect the failure mechanism of materials and is usually used to be a method to predict fatigue life or residual fatigue life.But the variable which can represent the health of machine is hardly measured on line.To a degree,the difficulty of on-line application restricts the scope of application of Paris law.The relationship between characteristic values of vibration signals and the variable in the Paris equation which can describe the health of machine is investigated by taking ball bearings as investigative objects.Based on 6205 deep groove ball bearings as a living example,historical lives and vibration signals are analyzed.The feasibility of describing that variable in the Paris equation by the characteristic value of vibration signals is inspected.After that vibration signals decomposed by empirical mode decomposition(EMD),root mean square(RMS) of intrinsic mode function(IMF) involving fault characteristic frequency has a consistent trend with the diameter of flaws.Based on the trend,two improved Paris models are proposed and the scope of application of them is inspected.These two Paris Models are validated by fatigue residual life data from tests of rolling element bearings and vibration signals monitored in the process of operation of rolling element bearings.It shows that the first improved Paris Model is simple and plain and it can be easily applied in actual conditions.The trend of the fatigue residual life predicted by the second improved Paris model is close to the actual conditions and the result of the prediction is slightly greater than the truth.In conclusion,after the appearance of detectable faults,these improved models based on RMS can predict residual fatigue life on line and a new approach to predict residual fatigue life of ball bearings on line without disturbing the machine running is provided.
基金This research was supported by National Natural Science Foundation of China(52005387,52025056)Project funded by China Postdoctoral Science Foundation(2020M673380)Fundamental Research Funds for the Central Universities.
文摘Recently,deep learning(DL)has been widely used in the field of remaining useful life(RUL)prediction.Among various DL technologies,recurrent neural network(RNN)and its variant,e.g.,long short-term memory(LSTM)network,have gained extensive attention for their ability to capture temporal dependence.Although existing RNN-based methods have demonstrated their RUL prediction effectiveness,they still suffer from the following two limitations:1)it is difficult for the RNN to directly extract degradation features from original monitoring data and 2)most RNN-based prognostics methods are unable to quantify RUL uncertainty.To address the aforementioned limitations,this paper proposes a new prognostics method named residual convolution LSTM(RC-LSTM)network.In the RC-LSTM,a new ResNet-based convolution LSTM(Res-ConvLSTM)layer is stacked with a convolution LSTM(ConvLSTM)layer to extract degradation representations from monitoring data.Then,under the assumption that the RUL follows a normal distribution,an appropriate output layer is constructed to quantify the uncertainty of prediction results.Finally,the effectiveness and superiority of the RC-LSTM are verified using monitoring data from accelerated bearing degradation tests.
基金the National Natural Science Foundationof China(Nos.11672098,11502063)the Natural Science Foundation of Anhui Province(No.1608085QA07).
文摘Residual useful life(RUL)prediction is a key issue for improving efficiency of aircraft engines and reducing their maintenance cost.Owing to various failure mechanism and operating environment,the application of classical models in RUL prediction of aircraft engines is fairly difficult.In this study,a novel RUL prognostics method based on using ensemble recurrent neural network to process massive sensor data is proposed.First of all,sensor data obtained from the aircraft engines are preprocessed to eliminate singular values,reduce random fluctuation and preserve degradation trend of the raw sensor data.Secondly,three kinds of recurrent neural networks(RNN),including ordinary RNN,long shortterm memory(LSTM),and gated recurrent unit(GRU),are individually constructed.Thirdly,ensemble learning mechanism is designed to merge the above RNNs for producing a more accurate RUL prediction.The effectiveness of the proposed method is validated using two characteristically different turbofan engine datasets.Experimental results show a competitive performance of the proposed method in comparison with typical methods reported in literatures.
文摘针对动车组车载变压器油纸绝缘剩余寿命预测中单性能退化指标难以全面反映油纸绝缘退化过程的问题,考虑车载变压器油纸绝缘退化的个体差异性及两性能指标间的相关关系,提出了基于Copula函数的两性能指标相关退化的油纸绝缘剩余寿命预测方法:采用具有随机效应的维纳过程建立油纸绝缘的两性能指标相关退化模型,基于赤池信息准则(Akaike Information Criterion, AIC)选择拟合效果更优的Copula函数来描述两性能指标间的相关关系,采用最大似然估计法估计初始时刻的模型参数,基于序列贝叶斯更新方法在线更新退化模型中的漂移系数,以实现油纸绝缘剩余寿命的在线预测。最后以加速热老化试验下油纸绝缘的聚合度和抗拉强度的退化数据进行实例验证。结果表明,两性能指标相关退化模型比单性能指标退化模型的剩余寿命预测值与实际值之间的平均绝对误差更小,预测的准确性更高,且随着模型参数不断更新,剩余寿命的预测值与实际值间的绝对误差在不断减小,预测结果的准确性在不断提升。
基金the National Natural Science Foundation of China(No.11272082)
文摘When a nonlinear fatigue damage accumulation model based on damage curve approach is used to get better residual life prediction results, it is necessary to solve the problem caused by the uncertain exponent of the model. Considering the effects of load interaction, the assumption that there is a linear dependence between the exponent ratio and the loading ratio is established to predict fatigue residual life of materials. Three experimental data sets are used to validate the rightness of the proposition. The comparisons of experimental data and predictions show that the predictions based on the proposed proposition are in good accordance with the experimental results as long as the parameters that represent the linear correlativity are set an appropriate value. Meanwhile, the accuracy of the proposition is approximated to that of an existing model. Therefore, the proposition proposed in this paper is reasonable for residual life prediction.