Deep learning and fatigue life prediction remain focal research areas in rail vehicle engineering.This study addresses the vibration fatigue of wheelset lifting lug in Chengdu Metro Line 1 bogies,aiming to develop a f...Deep learning and fatigue life prediction remain focal research areas in rail vehicle engineering.This study addresses the vibration fatigue of wheelset lifting lug in Chengdu Metro Line 1 bogies,aiming to develop a fatigue life prediction method for critical bogie components using deep learning models and measured track load spectra.Extensive field tests on Chengdu Metro Line 1 were conducted to acquire acceleration and stress response data of the wheelset lifting lug,generating training samples for the neural network system.Component stress responses were calculated via time-domain track acceleration and validated against in-situ stress measurements.Results show that neural network-fitted dynamic stress values exhibit excellent consistency with measured data,with errors constrained within 5%.This study validates the proposed small-sample deep learning approach as an effective and accurate solution for fatigue life prediction of critical bogie components under operational load conditions.展开更多
Accurate prediction of remaining useful life serves as a reliable basis for maintenance strategies,effectively reducing both the frequency of failures and associated costs.As a core component of PHM,RUL prediction pla...Accurate prediction of remaining useful life serves as a reliable basis for maintenance strategies,effectively reducing both the frequency of failures and associated costs.As a core component of PHM,RUL prediction plays a crucial role in preventing equipment failures and optimizing maintenance decision-making.However,deep learning models often falter when processing raw,noisy temporal signals,fail to quantify prediction uncertainty,and face challenges in effectively capturing the nonlinear dynamics of equipment degradation.To address these issues,this study proposes a novel deep learning framework.First,a newbidirectional long short-termmemory network integrated with an attention mechanism is designed to enhance temporal feature extraction with improved noise robustness.Second,a probabilistic prediction framework based on kernel density estimation is constructed,incorporating residual connections and stochastic regularization to achieve precise RUL estimation.Finally,extensive experiments on the C-MAPSS dataset demonstrate that our method achieves competitive performance in terms of RMSE and Score metrics compared to state-of-the-artmodels.More importantly,the probabilistic output provides a quantifiablemeasure of prediction confidence,which is crucial for risk-informed maintenance planning,enabling managers to optimize maintenance strategies based on a quantifiable understanding of failure risk.展开更多
To address the challenges posed by tunnel construction in the alpine region,silica fume mixed concrete is commonly used as a construction material.The correlation between silica fume content and the lining life requir...To address the challenges posed by tunnel construction in the alpine region,silica fume mixed concrete is commonly used as a construction material.The correlation between silica fume content and the lining life requires immediate investigation.In view of this phenomenon,the durability of unit lining concrete is predicted by analyzing three key indicators:carbonation depth,relative dynamic elastic modulus,and residual quality.This prediction is achieved by integrating the Entropy Weight Method,Grey theory life prediction model and BP artificial neural networks using data from tests and predictions of these indicators.Then,the Entropy Weight-Grey theory-BP Network Model is compared with other methods to analyze the predicted life.Finally,verify the sci-entificity of this model,and the optimum silica fume content of unit concrete lining is verified.The results showed,1)The addition of silica fume will accelerate the carbonization of unit concrete lining,and slow down the freeze-thaw cycle and sulfate erosion.2)The utilization of artificial neural networks is essential for enhancing the realism of the data,as it emphasizes the significance of silica fume content.3)Silica fume content of 10%results in the longest life and is the most suitable for lining construction.4)A comparison between single-factor and multi-factor predictions indicates that the multi-factor approach yields a longer maximum life.This improvement can be attributed to the inclusion of additional factors,such as freeze-thaw cycles and carbonation,which enhance the predicted life when employing these methods.In conclusion,the Entropy Weight-Grey Theory-BP Network life prediction Model is well-suited for tunnel lining in the alpine sulfate area of northwest China.展开更多
The service load on high temperature rotating components of aero-engines generally exhibits flight mission characteristics. The general shape of the load spectrum is that Type Ⅲ/Ⅳ cyclic loading and creep loading ar...The service load on high temperature rotating components of aero-engines generally exhibits flight mission characteristics. The general shape of the load spectrum is that Type Ⅲ/Ⅳ cyclic loading and creep loading are superimposed on Type Ⅰ cyclic loading. Meanwhile, the sequence of the Type Ⅲ/Ⅳ cyclic and creep loading varies with mission. This work performed load spectrum test with this characteristic on the Ni-based alloy FGH96. Then a life prediction method was developed based on the Chaboche fatigue damage accumulation model and a modified time fraction model. Creep followed by Fatigue (C-F) test was carried out to reveal the creep-fatigue interaction and calibrate parameters. The results show that most test results fall within the 2-fold deviation band. The sequence of creep-fatigue loading within the load spectrum exhibited a limited effect on life. Finally, simplified methods were developed to improve analysis efficiency, and cases where simplified methods could replace the proposed method were discussed.展开更多
A Combined Cycle Fatigue(CCF)life prediction model considering the effect of load sequence was proposed.To account for the interaction of high and low cycle fatigue,the CCF load was divided into two different loading ...A Combined Cycle Fatigue(CCF)life prediction model considering the effect of load sequence was proposed.To account for the interaction of high and low cycle fatigue,the CCF load was divided into two different loading paths of variable stress amplitude and stress ratio.Based on the iso-damage curves,a CCF life prediction model independent of fitting parameters was proposed,agreeing well with the experimental results.Finally,the effect of load sequence on CCF was discussed according to the fracture morphology of designed blade-like specimen.The results showed that the predicted CCF life was almost located in three-fold dispersion band for the LCF-HCF(LH)and HCF-LCF(HL)loading paths,especially for the average results of both.Compared with other models,the proposed model had better predictive and generalization abilities for multiple materials and variable experimental conditions.展开更多
The fatigue characteristics of rock materials significantly impact the economy and safety of underground structures during construction.Hence,it is essential to conduct further investigation into the progressive damag...The fatigue characteristics of rock materials significantly impact the economy and safety of underground structures during construction.Hence,it is essential to conduct further investigation into the progressive damage processes of rocks under cyclic loading conditions.This research utilised both laboratory experiments and discrete element simulations to investigate how confining pressure and fatigue upper limit stress influence the mechanical behaviour and crack development of marble under low-cycle fatigue conditions.By introducing synthetic displacement and reasonable assumptions,the classical damage evolution law was updated,resulting in a fatigue life prediction formula applicable to various rock materials and loading conditions.The results indicate that lower fatigue upper limit stress can delay the accumulation of damage and extend the fatigue life of the rock,but it results in more severe ultimate failure.The damage variable’s correlation with the relative number of loading cycles for different fatigue load upper limits under the same confining pressure can be approximated by the same functional relationship.The modified damage evolution model provides an effective characterisation of this trend.The proposed fatigue life prediction method comprehensively accounts for different rock materials,confining pressures,loading frequencies,and initial damage,showing a close match with actual results.展开更多
This paper aims to experimentally and numerically probe fatigue behaviours and lifetimes of 3D4D(three-dimensional four-directional)braided composite I-beam under four-point flexure spectrum loading.New fatigue damage...This paper aims to experimentally and numerically probe fatigue behaviours and lifetimes of 3D4D(three-dimensional four-directional)braided composite I-beam under four-point flexure spectrum loading.New fatigue damage models of fibre yarn,matrix and fibre–matrix interface are proposed,and fatigue failure criteria and PFDA(Progressive Fatigue Damage Algorithm)are thus presented for meso-scale fatigue damage modelling of 3D4D braided composite I-beam.To validate the aforementioned model and algorithm,fatigue tests are conducted on the 3D4D braided composite I-beam under four-point flexure spectrum loading,and fatigue failure mechanisms are analyzed and discussed.Novel global–local FE(Finite Element)model based on the PFDA is generated for modelling progressive fatigue failure process and predicting fatigue life of 3D4D braided composite I-beam under four-point flexure spectrum loading.Good agreement has been achieved between experimental results and predictions,demonstrating the effective usage of new model.It is shown that matrix cracking and interfacial debonding initially initiates on top surface of top flange of I-beam,and then gradually propagates from the side surface of top flange to the intermediate web along the braiding angle,and considerable fiber breakage finally causes final fatigue failure of I-beam.展开更多
The corrosion behavior and life of Sn−3.0Ag−0.5Cu solder joints were investigated through fire smoke exposure experiments within the temperature range of 45−80℃.The nonlinear Wiener process and Arrhenius equation wer...The corrosion behavior and life of Sn−3.0Ag−0.5Cu solder joints were investigated through fire smoke exposure experiments within the temperature range of 45−80℃.The nonlinear Wiener process and Arrhenius equation were used to establish the probability distribution function and prediction model of the solder joint’s average life and individual remaining useful life.The results indicate that solder joint resistance shows a nonlinear growth trend with time increasing.After 24 h,the solder joint transforms from spherical to rose-like shapes.Higher temperatures accelerate solder joint failure,and the relationship between failure time and temperature conforms to the Arrhenius equation.The predicted life of the model is in good agreement with experimental results,demonstrating the effectiveness and accuracy of the model.展开更多
The performance degradation of vehicle engine cylinder heads is a complex phenomenon,and the accurate prediction of their remaining useful life is essential for maintenance planning.To address the problem of low predi...The performance degradation of vehicle engine cylinder heads is a complex phenomenon,and the accurate prediction of their remaining useful life is essential for maintenance planning.To address the problem of low prediction accuracy caused by insufficient data mining depth in current prediction models for the remaining service life of engine cylinder heads,a prediction method of dualchannel model is proposed.Firstly,the driving status data of multiple vehicles is summarized and analyzed,and the on-board network common variables related to cylinder head life are screened.Secondly,driving segments are defined,the driving state features of each driving segment are extracted,and feature correlation analysis and principal component analysis are performed.All driving state profiles of the vehicle are divided using the clustering algorithm,and the cumulative degradation factors for driving state profiles are defined and calculated.Furthermore,the mileage of each driving segment is classified into intervals by applying fuzzy set theory,and the state transfer probability matrices of driving state profiles and driving segment mileage are calculated.A new engine head life prediction model based on dual channel Markov chain(DCMC)is established.Finally,the proposed method is applied to the residual life prediction of cylinder head of seven actual vehicles,and the comparison with actual life statistics results proved the validity of the proposed method.展开更多
Dear Editor,This letter focuses on the remaining useful life(RUL)prediction task under limited labeled samples.Existing machine-learning-based RUL prediction methods for this task usually pay attention to mining degra...Dear Editor,This letter focuses on the remaining useful life(RUL)prediction task under limited labeled samples.Existing machine-learning-based RUL prediction methods for this task usually pay attention to mining degradation information to improve the prediction accuracy of degradation value or health indicator for the next epoch.However,they ignore the cumulative prediction error caused by iterations before reaching the failure point.展开更多
To overcome the challenges of limited experimental data and improve the accuracy of empirical formulas,we propose a low-cycle fatigue(LCF)life prediction model for nickel-based superalloys using a data augmentation me...To overcome the challenges of limited experimental data and improve the accuracy of empirical formulas,we propose a low-cycle fatigue(LCF)life prediction model for nickel-based superalloys using a data augmentation method.This method utilizes a variational autoencoder(VAE)to generate low-cycle fatigue data and form an augmented dataset.The Pearson correlation coefficient(PCC)is employed to verify the similarity of feature distributions between the original and augmented datasets.Six machine learning models,namely random forest(RF),artificial neural network(ANN),support vector machine(SVM),gradient-boosted decision tree(GBDT),eXtreme Gradient Boosting(XGBoost),and Categorical Boosting(CatBoost),are utilized to predict the LCF life of nickel-based superalloys.Results indicate that the proposed data augmentation method based on VAE can effectively expand the dataset,and the mean absolute error(MAE),root mean square error(RMSE),and R-squared(R^(2))values achieved using the CatBoost model,with respective values of 0.0242,0.0391,and 0.9538,are superior to those of the other models.The proposed method reduces the cost and time associated with LCF experiments and accurately establishes the relationship between fatigue characteristics and LCF life of nickel-based superalloys.展开更多
Dear Editor,This letter presents a latent-factorization-of-tensors(LFT)-incorporated battery cycle life prediction framework.Data-driven prognosis and health management(PHM)for battery pack(BP)can boost the safety and...Dear Editor,This letter presents a latent-factorization-of-tensors(LFT)-incorporated battery cycle life prediction framework.Data-driven prognosis and health management(PHM)for battery pack(BP)can boost the safety and sustainability of a battery management system(BMS),which relies heavily on the quality of the measured BP data like the voltage(V),current(I),and temperature(T).展开更多
Throughout the composite structure’s lifespan,it is subject to a range of environmental factors,including loads,vibrations,and conditions involving heat and humidity.These factors have the potential to compromise the...Throughout the composite structure’s lifespan,it is subject to a range of environmental factors,including loads,vibrations,and conditions involving heat and humidity.These factors have the potential to compromise the integrity of the structure.The estimation of the fatigue life of composite materials is imperative for ensuring the structural integrity of these materials.In this study,a methodology is proposed for predicting the fatigue life of composites that integrates ultrasonic guided waves and machine learning modeling.The method first screens the ultrasonic guided wave signal features that are significantly affected by fatigue damage.Subsequently,a covariance analysis is conducted to reduce the redundancy of the feature matrix.Furthermore,one-hot encoding is employed to incorporate boundary conditions as features,and the resulting data undergoes preprocessing to form a sample library.A composite fatigue life prediction model has been developed,employing the aforementioned sample library as the input source and utilizing remaining life as the output metric.The model synthesizes the strengths of convolutional neural networks(CNNs)and bidirectional long short-term memory networks(BiLSTMs)while leveraging Bayesian optimization(BO)to enhance the optimization of hyperparameters.The experimental results demonstrate that the proposed BO-CNN-BiLSTM model exhibits superior performance in terms of prediction accuracy and reliability in the damage regression task when compared to both the BiLSTM and CNN-BiLSTM models.展开更多
Fatigue characteristics of A7N01 aluminium alloy welded joint were investigated and a fatigue crack initiation life-based model was proposed. The difference of fatigue crack initiation life among base metal, weld meta...Fatigue characteristics of A7N01 aluminium alloy welded joint were investigated and a fatigue crack initiation life-based model was proposed. The difference of fatigue crack initiation life among base metal, weld metal and heat affected zone (HAZ) is slight. Furthermore, the ratio of fatigue crack initiation life (Ni) to fatigue life to failure(Nf) is a material dependent parameter, 26.32%, 40.21% and 60.67% for base metal, HAZ and weld metal, respectively. Total fatigue life predicted using the presented model is in good agreement with the experimental data and that using Basquin’s model. The observation results of fatigue fracture surfaces, using scanning electron microscope (SEM), demonstrate that fatigue crack initiates from smooth surface due to welding process for weld metal, blowhole in HAZ causes fatigue crack initiation, and the crushed second phase particles play an important part in fatigue crack initiation in base metal.展开更多
The lifespan models of commercial 18650-type lithium ion batteries （nominal capacity of 1150 mA-h） were presented. The lifespan was extrapolated based on this model. The results indicate that the relationship of cap...The lifespan models of commercial 18650-type lithium ion batteries （nominal capacity of 1150 mA-h） were presented. The lifespan was extrapolated based on this model. The results indicate that the relationship of capacity retention and cycle number can be expressed by Gaussian function. The selecting function and optimal precision were verified through actual match detection and a range of alternating current impedance testing. The cycle life model with high precision （〉99%） is beneficial to shortening the orediction time and cutting the prediction cost.展开更多
Transformers have achieved promising results on aeroengine remaining useful life(RUL)prediction,but they still have several limitations:1)Aeroengine domain knowledge,which contains rich information that can reflect th...Transformers have achieved promising results on aeroengine remaining useful life(RUL)prediction,but they still have several limitations:1)Aeroengine domain knowledge,which contains rich information that can reflect the aeroengine’s health statue,is largely ignored in modeling process;2)Traditional transformer ignores the valuable degradation information from other time scales.To address these issues,a novel domain knowledge-augmented multiscale transformer(DKAMFormer)is developed by integrating domain knowledge and multiscale learning to improve the prognostic performance and reliability.First,to obtain rich and professional aeroengine domain knowledge,multiple detail and complete knowledge graphs(KGs)are established based on the working principle of aeroengine,including aeroengine structure,components working characteristics and sensor parameters.Second,the domain knowledge contained in KGs is convert to embedded vector by KG representative learning,which are then utilized to strengthen and enrich the original multidimensional time-series(MTS)monitoring data,aiming to intergrade domain knowledge and monitoring data to train DKAMFormer.Third,to learn rich and complementary degradation features,a novel multiscale time scale-guided self-attention(MTSGSA)mechanism is designed,which maps original MTS into different time-scale feature spaces,and then employs multiple independent self-attention head to extract the degradation features from different time-scale spaces.Finally,through a series of comparative experiments on the public CMAPSS and NCMAPSS datasets and compared with 17 SOTA methods,the developed DKAMFormer significantly improves the RUL prediction performance under multiple operation conditions and degradation modes.展开更多
Due to abrupt changes in the intrinsic degradation mechanism or shock from external environmental pressure,degradations of some equipment are characterized by multi-phase and jumps.Meanwhile,equipment is subject to in...Due to abrupt changes in the intrinsic degradation mechanism or shock from external environmental pressure,degradations of some equipment are characterized by multi-phase and jumps.Meanwhile,equipment is subject to inherent fluctuations,limited data and imperfect measurements resulting in aleatory,epistemic and measurement uncertainties of the degradation process.This paper proposes a degradation model and remaining useful life(RUL)prediction method under triple uncertainties for a category of complex equipment with multi-phase degradation and jumps.First,a multi-phase degradation model with random jumps and measurement errors is constructed based on uncertain random processes.Afterward,the analytic expression of RUL prediction considering the heterogeneity is derived by modeling the uncertainty of degradation states at change points under the concept of first hitting time.A stochastic uncertain approach is utilized for the proposed multi-phase degradation model to identify model parameters based on historical data.Furthermore,the implied degradation features are adaptively updated in online stage using similarity-based weighted stochastic uncertain maximum likelihood estimation and Kalman filtering.Finally,the effectiveness of the method is verified by simulation example and practical case.展开更多
The theory of economic life prediction and reliability assessment of aircraft structures has a significant effect on safety of air-craft structures.It is based on the two-stage theory of fatigue process and can guaran...The theory of economic life prediction and reliability assessment of aircraft structures has a significant effect on safety of air-craft structures.It is based on the two-stage theory of fatigue process and can guarantee the safety and reliability of structures.According to the fatigue damage process,the fatigue scatter factors of crack initiation stage and crack propagation stage are given respectively.At the same time,mathematical models of fatigue life prediction are presented by utilizing the fatigue scatter factors and full scale test results of aircraft structures.Furthermore,the economic life model is put forward.The model is of sig-nificant scientific value for products to provide longer economic life,higher reliability and lower cost.The theory of economic life prediction and reliability assessment of aircraft structures has been successfully applied to determining and extending the structural life for thousands of airplanes.展开更多
Material performance of LY12CZ aluminum is greatly degraded because of corrosion and corrosion fatigue, which severely affect the integrity and safety of aircraft structure, especially those of lbe navy aircraft struc...Material performance of LY12CZ aluminum is greatly degraded because of corrosion and corrosion fatigue, which severely affect the integrity and safety of aircraft structure, especially those of lbe navy aircraft structure. The corrosion and corrosion fatigue failure process of aircraft structure are directly concerned with many factors, such as load, material characteristics, corrosive environment and so on. The damage mechanism is very complicated, and there are both randomness and fuzziness in the failure process. With consideration of the limitation of those conventional probabilistic approaches for prediction of corrosion fatigue life of aircraft structure at present, and based on the operational load spectrum obtained through investigating service status of the aircraft in naval aviation force, a fuzzy reliability approach is proposed, which is more reasonable and closer to the fact. The effects of the pit aspect ratio, the crack aspect ratio and all fuzzy factors on corrosion fatigue life of aircraft structure are discussed. The results demonstrate that the approach can be applied to predict the corrosion fatigue life of aircraft structure.展开更多
Nickel-based superalloys are easy to produce low cycle fatigue(LCF)damage when they are subjected to high temperature and mechanical stresses.Fatigue life prediction of nickel-based superalloys is of great importance ...Nickel-based superalloys are easy to produce low cycle fatigue(LCF)damage when they are subjected to high temperature and mechanical stresses.Fatigue life prediction of nickel-based superalloys is of great importance for their reliable practical application.To investigate the effects of total strain and grain size on LCF behavior,the high temperature LCF tests were carried out for a nickel-based superalloy.The results show that the fatigue lives decreased with the increase of strain amplitude and grain size.A new LCF life prediction model was established considering the effect of grain size on fatigue life.Error analyses indicate that the prediction accuracy of the new LCF life model is higher than those of Manson-Coffin relationship and Ostergren energy method.展开更多
基金supported by the CRRC Original Technology TenYear Cultivation Program(Grant No.2022CYY007)。
文摘Deep learning and fatigue life prediction remain focal research areas in rail vehicle engineering.This study addresses the vibration fatigue of wheelset lifting lug in Chengdu Metro Line 1 bogies,aiming to develop a fatigue life prediction method for critical bogie components using deep learning models and measured track load spectra.Extensive field tests on Chengdu Metro Line 1 were conducted to acquire acceleration and stress response data of the wheelset lifting lug,generating training samples for the neural network system.Component stress responses were calculated via time-domain track acceleration and validated against in-situ stress measurements.Results show that neural network-fitted dynamic stress values exhibit excellent consistency with measured data,with errors constrained within 5%.This study validates the proposed small-sample deep learning approach as an effective and accurate solution for fatigue life prediction of critical bogie components under operational load conditions.
基金funded by scientific research projects under Grant JY2024B011.
文摘Accurate prediction of remaining useful life serves as a reliable basis for maintenance strategies,effectively reducing both the frequency of failures and associated costs.As a core component of PHM,RUL prediction plays a crucial role in preventing equipment failures and optimizing maintenance decision-making.However,deep learning models often falter when processing raw,noisy temporal signals,fail to quantify prediction uncertainty,and face challenges in effectively capturing the nonlinear dynamics of equipment degradation.To address these issues,this study proposes a novel deep learning framework.First,a newbidirectional long short-termmemory network integrated with an attention mechanism is designed to enhance temporal feature extraction with improved noise robustness.Second,a probabilistic prediction framework based on kernel density estimation is constructed,incorporating residual connections and stochastic regularization to achieve precise RUL estimation.Finally,extensive experiments on the C-MAPSS dataset demonstrate that our method achieves competitive performance in terms of RMSE and Score metrics compared to state-of-the-artmodels.More importantly,the probabilistic output provides a quantifiablemeasure of prediction confidence,which is crucial for risk-informed maintenance planning,enabling managers to optimize maintenance strategies based on a quantifiable understanding of failure risk.
基金funded by the Technology Funding Scheme of China Construction Second Engineering Bureau LTD(2020ZX150002)the National Natural Science Foundation Project of China(12262018).
文摘To address the challenges posed by tunnel construction in the alpine region,silica fume mixed concrete is commonly used as a construction material.The correlation between silica fume content and the lining life requires immediate investigation.In view of this phenomenon,the durability of unit lining concrete is predicted by analyzing three key indicators:carbonation depth,relative dynamic elastic modulus,and residual quality.This prediction is achieved by integrating the Entropy Weight Method,Grey theory life prediction model and BP artificial neural networks using data from tests and predictions of these indicators.Then,the Entropy Weight-Grey theory-BP Network Model is compared with other methods to analyze the predicted life.Finally,verify the sci-entificity of this model,and the optimum silica fume content of unit concrete lining is verified.The results showed,1)The addition of silica fume will accelerate the carbonization of unit concrete lining,and slow down the freeze-thaw cycle and sulfate erosion.2)The utilization of artificial neural networks is essential for enhancing the realism of the data,as it emphasizes the significance of silica fume content.3)Silica fume content of 10%results in the longest life and is the most suitable for lining construction.4)A comparison between single-factor and multi-factor predictions indicates that the multi-factor approach yields a longer maximum life.This improvement can be attributed to the inclusion of additional factors,such as freeze-thaw cycles and carbonation,which enhance the predicted life when employing these methods.In conclusion,the Entropy Weight-Grey Theory-BP Network life prediction Model is well-suited for tunnel lining in the alpine sulfate area of northwest China.
基金supported by the National Science and Technology Major Project of China(No.J2019-IV-0017-0085)the National Natural Science Foundation of China(Nos.12172021,52205177)the Natural Science Foundation of Hunan Province,China(No.2021JJ40741).
文摘The service load on high temperature rotating components of aero-engines generally exhibits flight mission characteristics. The general shape of the load spectrum is that Type Ⅲ/Ⅳ cyclic loading and creep loading are superimposed on Type Ⅰ cyclic loading. Meanwhile, the sequence of the Type Ⅲ/Ⅳ cyclic and creep loading varies with mission. This work performed load spectrum test with this characteristic on the Ni-based alloy FGH96. Then a life prediction method was developed based on the Chaboche fatigue damage accumulation model and a modified time fraction model. Creep followed by Fatigue (C-F) test was carried out to reveal the creep-fatigue interaction and calibrate parameters. The results show that most test results fall within the 2-fold deviation band. The sequence of creep-fatigue loading within the load spectrum exhibited a limited effect on life. Finally, simplified methods were developed to improve analysis efficiency, and cases where simplified methods could replace the proposed method were discussed.
基金funding by National Natural Science Foundation of China(No.52105137)the National Science and Technology Major Project,China(No.2017-IV0012-0049)the Beijing Natural Science Foundation,China(No.3244033)。
文摘A Combined Cycle Fatigue(CCF)life prediction model considering the effect of load sequence was proposed.To account for the interaction of high and low cycle fatigue,the CCF load was divided into two different loading paths of variable stress amplitude and stress ratio.Based on the iso-damage curves,a CCF life prediction model independent of fitting parameters was proposed,agreeing well with the experimental results.Finally,the effect of load sequence on CCF was discussed according to the fracture morphology of designed blade-like specimen.The results showed that the predicted CCF life was almost located in three-fold dispersion band for the LCF-HCF(LH)and HCF-LCF(HL)loading paths,especially for the average results of both.Compared with other models,the proposed model had better predictive and generalization abilities for multiple materials and variable experimental conditions.
基金supported by the Key Supported Project of the Joint Fund of the National Natural Science Foundation of China for Geology(No.U2444220)the National Natural Science Foundation of China(Nos.52374090 and 52278351)+1 种基金the Scientific Research(on Science and Technology)Projects for Young and Middle-aged Teachers in Fujian(No.JAT220464)the Engineering Innovation Center for Urban Underground Space Exploration and Evaluation,Ministry of Natural Resources of the People’s Republic of China(No.USEEOS-2024-01)。
文摘The fatigue characteristics of rock materials significantly impact the economy and safety of underground structures during construction.Hence,it is essential to conduct further investigation into the progressive damage processes of rocks under cyclic loading conditions.This research utilised both laboratory experiments and discrete element simulations to investigate how confining pressure and fatigue upper limit stress influence the mechanical behaviour and crack development of marble under low-cycle fatigue conditions.By introducing synthetic displacement and reasonable assumptions,the classical damage evolution law was updated,resulting in a fatigue life prediction formula applicable to various rock materials and loading conditions.The results indicate that lower fatigue upper limit stress can delay the accumulation of damage and extend the fatigue life of the rock,but it results in more severe ultimate failure.The damage variable’s correlation with the relative number of loading cycles for different fatigue load upper limits under the same confining pressure can be approximated by the same functional relationship.The modified damage evolution model provides an effective characterisation of this trend.The proposed fatigue life prediction method comprehensively accounts for different rock materials,confining pressures,loading frequencies,and initial damage,showing a close match with actual results.
基金supported by the National Natural Science Foundation of China(No.12472340).
文摘This paper aims to experimentally and numerically probe fatigue behaviours and lifetimes of 3D4D(three-dimensional four-directional)braided composite I-beam under four-point flexure spectrum loading.New fatigue damage models of fibre yarn,matrix and fibre–matrix interface are proposed,and fatigue failure criteria and PFDA(Progressive Fatigue Damage Algorithm)are thus presented for meso-scale fatigue damage modelling of 3D4D braided composite I-beam.To validate the aforementioned model and algorithm,fatigue tests are conducted on the 3D4D braided composite I-beam under four-point flexure spectrum loading,and fatigue failure mechanisms are analyzed and discussed.Novel global–local FE(Finite Element)model based on the PFDA is generated for modelling progressive fatigue failure process and predicting fatigue life of 3D4D braided composite I-beam under four-point flexure spectrum loading.Good agreement has been achieved between experimental results and predictions,demonstrating the effective usage of new model.It is shown that matrix cracking and interfacial debonding initially initiates on top surface of top flange of I-beam,and then gradually propagates from the side surface of top flange to the intermediate web along the braiding angle,and considerable fiber breakage finally causes final fatigue failure of I-beam.
基金National Natural Science Foundation of China (No. 52206180)Fundamental Research Funds for the Central Universities,China (No. WK2320000050)。
文摘The corrosion behavior and life of Sn−3.0Ag−0.5Cu solder joints were investigated through fire smoke exposure experiments within the temperature range of 45−80℃.The nonlinear Wiener process and Arrhenius equation were used to establish the probability distribution function and prediction model of the solder joint’s average life and individual remaining useful life.The results indicate that solder joint resistance shows a nonlinear growth trend with time increasing.After 24 h,the solder joint transforms from spherical to rose-like shapes.Higher temperatures accelerate solder joint failure,and the relationship between failure time and temperature conforms to the Arrhenius equation.The predicted life of the model is in good agreement with experimental results,demonstrating the effectiveness and accuracy of the model.
基金Supported by the Open Project Fund of the National Key Laboratory of Internal Combustion Engine and Power System(No.skler-202102).
文摘The performance degradation of vehicle engine cylinder heads is a complex phenomenon,and the accurate prediction of their remaining useful life is essential for maintenance planning.To address the problem of low prediction accuracy caused by insufficient data mining depth in current prediction models for the remaining service life of engine cylinder heads,a prediction method of dualchannel model is proposed.Firstly,the driving status data of multiple vehicles is summarized and analyzed,and the on-board network common variables related to cylinder head life are screened.Secondly,driving segments are defined,the driving state features of each driving segment are extracted,and feature correlation analysis and principal component analysis are performed.All driving state profiles of the vehicle are divided using the clustering algorithm,and the cumulative degradation factors for driving state profiles are defined and calculated.Furthermore,the mileage of each driving segment is classified into intervals by applying fuzzy set theory,and the state transfer probability matrices of driving state profiles and driving segment mileage are calculated.A new engine head life prediction model based on dual channel Markov chain(DCMC)is established.Finally,the proposed method is applied to the residual life prediction of cylinder head of seven actual vehicles,and the comparison with actual life statistics results proved the validity of the proposed method.
基金supported in part by the National Natural Science Foundation of China(U2034209)the Postdoctoral Science Foundation of Chongqing(cstc2021jcyj-bsh X0047)+1 种基金the Fundamental Research Funds for the Central Universities(2022CDJJMRH-008)the National Natural Science Foundation of China(62203075)
文摘Dear Editor,This letter focuses on the remaining useful life(RUL)prediction task under limited labeled samples.Existing machine-learning-based RUL prediction methods for this task usually pay attention to mining degradation information to improve the prediction accuracy of degradation value or health indicator for the next epoch.However,they ignore the cumulative prediction error caused by iterations before reaching the failure point.
基金Financial support from the Fundamental Research Funds for the Central Universities(ZJ2022-003,JG2022-27,J2020-060,and J2021-060)Sichuan Province Engineering Technology Research Center of General Aircraft Maintenance(GAMRC2021YB08)the Young Scientists Fund of the National Natural Science Foundation of China(No.52105417)is acknowledged.
文摘To overcome the challenges of limited experimental data and improve the accuracy of empirical formulas,we propose a low-cycle fatigue(LCF)life prediction model for nickel-based superalloys using a data augmentation method.This method utilizes a variational autoencoder(VAE)to generate low-cycle fatigue data and form an augmented dataset.The Pearson correlation coefficient(PCC)is employed to verify the similarity of feature distributions between the original and augmented datasets.Six machine learning models,namely random forest(RF),artificial neural network(ANN),support vector machine(SVM),gradient-boosted decision tree(GBDT),eXtreme Gradient Boosting(XGBoost),and Categorical Boosting(CatBoost),are utilized to predict the LCF life of nickel-based superalloys.Results indicate that the proposed data augmentation method based on VAE can effectively expand the dataset,and the mean absolute error(MAE),root mean square error(RMSE),and R-squared(R^(2))values achieved using the CatBoost model,with respective values of 0.0242,0.0391,and 0.9538,are superior to those of the other models.The proposed method reduces the cost and time associated with LCF experiments and accurately establishes the relationship between fatigue characteristics and LCF life of nickel-based superalloys.
文摘Dear Editor,This letter presents a latent-factorization-of-tensors(LFT)-incorporated battery cycle life prediction framework.Data-driven prognosis and health management(PHM)for battery pack(BP)can boost the safety and sustainability of a battery management system(BMS),which relies heavily on the quality of the measured BP data like the voltage(V),current(I),and temperature(T).
基金funded by the Key Technologies R&D Program of CNBM(2023SJYL01)Postgraduate Research&Practice Innovation Program of Jiangsu Province(SJCX24_1356).
文摘Throughout the composite structure’s lifespan,it is subject to a range of environmental factors,including loads,vibrations,and conditions involving heat and humidity.These factors have the potential to compromise the integrity of the structure.The estimation of the fatigue life of composite materials is imperative for ensuring the structural integrity of these materials.In this study,a methodology is proposed for predicting the fatigue life of composites that integrates ultrasonic guided waves and machine learning modeling.The method first screens the ultrasonic guided wave signal features that are significantly affected by fatigue damage.Subsequently,a covariance analysis is conducted to reduce the redundancy of the feature matrix.Furthermore,one-hot encoding is employed to incorporate boundary conditions as features,and the resulting data undergoes preprocessing to form a sample library.A composite fatigue life prediction model has been developed,employing the aforementioned sample library as the input source and utilizing remaining life as the output metric.The model synthesizes the strengths of convolutional neural networks(CNNs)and bidirectional long short-term memory networks(BiLSTMs)while leveraging Bayesian optimization(BO)to enhance the optimization of hyperparameters.The experimental results demonstrate that the proposed BO-CNN-BiLSTM model exhibits superior performance in terms of prediction accuracy and reliability in the damage regression task when compared to both the BiLSTM and CNN-BiLSTM models.
文摘Fatigue characteristics of A7N01 aluminium alloy welded joint were investigated and a fatigue crack initiation life-based model was proposed. The difference of fatigue crack initiation life among base metal, weld metal and heat affected zone (HAZ) is slight. Furthermore, the ratio of fatigue crack initiation life (Ni) to fatigue life to failure(Nf) is a material dependent parameter, 26.32%, 40.21% and 60.67% for base metal, HAZ and weld metal, respectively. Total fatigue life predicted using the presented model is in good agreement with the experimental data and that using Basquin’s model. The observation results of fatigue fracture surfaces, using scanning electron microscope (SEM), demonstrate that fatigue crack initiates from smooth surface due to welding process for weld metal, blowhole in HAZ causes fatigue crack initiation, and the crushed second phase particles play an important part in fatigue crack initiation in base metal.
基金Projects(51204209,51274240)supported by the National Natural Science Foundation of ChinaProject(HNDLKJ[2012]001-1)supported by Henan Electric Power Science&Technology Supporting Program,China
文摘The lifespan models of commercial 18650-type lithium ion batteries （nominal capacity of 1150 mA-h） were presented. The lifespan was extrapolated based on this model. The results indicate that the relationship of capacity retention and cycle number can be expressed by Gaussian function. The selecting function and optimal precision were verified through actual match detection and a range of alternating current impedance testing. The cycle life model with high precision （〉99%） is beneficial to shortening the orediction time and cutting the prediction cost.
基金supported in part by the National Natural Science Foundation of China(52305570)the National Natural Science Foundation of China Key Support Project(U2133202)+2 种基金China Postdoctoral Science Foundation(2022M720955)Postdoctoral Science Foundation of Heilongjiang Province(LBH-Z22187)Outstanding Doctoral Dissertation Funding Project of Heilongjiang Province(LJYXL2022-011).
文摘Transformers have achieved promising results on aeroengine remaining useful life(RUL)prediction,but they still have several limitations:1)Aeroengine domain knowledge,which contains rich information that can reflect the aeroengine’s health statue,is largely ignored in modeling process;2)Traditional transformer ignores the valuable degradation information from other time scales.To address these issues,a novel domain knowledge-augmented multiscale transformer(DKAMFormer)is developed by integrating domain knowledge and multiscale learning to improve the prognostic performance and reliability.First,to obtain rich and professional aeroengine domain knowledge,multiple detail and complete knowledge graphs(KGs)are established based on the working principle of aeroengine,including aeroengine structure,components working characteristics and sensor parameters.Second,the domain knowledge contained in KGs is convert to embedded vector by KG representative learning,which are then utilized to strengthen and enrich the original multidimensional time-series(MTS)monitoring data,aiming to intergrade domain knowledge and monitoring data to train DKAMFormer.Third,to learn rich and complementary degradation features,a novel multiscale time scale-guided self-attention(MTSGSA)mechanism is designed,which maps original MTS into different time-scale feature spaces,and then employs multiple independent self-attention head to extract the degradation features from different time-scale spaces.Finally,through a series of comparative experiments on the public CMAPSS and NCMAPSS datasets and compared with 17 SOTA methods,the developed DKAMFormer significantly improves the RUL prediction performance under multiple operation conditions and degradation modes.
基金supported by the National Key Research and Development Program of China(2021YFB3301200)the National Natural Science Foundation of China(NSFC)(U21A20483,62373040,62203042).
文摘Due to abrupt changes in the intrinsic degradation mechanism or shock from external environmental pressure,degradations of some equipment are characterized by multi-phase and jumps.Meanwhile,equipment is subject to inherent fluctuations,limited data and imperfect measurements resulting in aleatory,epistemic and measurement uncertainties of the degradation process.This paper proposes a degradation model and remaining useful life(RUL)prediction method under triple uncertainties for a category of complex equipment with multi-phase degradation and jumps.First,a multi-phase degradation model with random jumps and measurement errors is constructed based on uncertain random processes.Afterward,the analytic expression of RUL prediction considering the heterogeneity is derived by modeling the uncertainty of degradation states at change points under the concept of first hitting time.A stochastic uncertain approach is utilized for the proposed multi-phase degradation model to identify model parameters based on historical data.Furthermore,the implied degradation features are adaptively updated in online stage using similarity-based weighted stochastic uncertain maximum likelihood estimation and Kalman filtering.Finally,the effectiveness of the method is verified by simulation example and practical case.
基金National Natural Science Foundation of China (50135010)
文摘The theory of economic life prediction and reliability assessment of aircraft structures has a significant effect on safety of air-craft structures.It is based on the two-stage theory of fatigue process and can guarantee the safety and reliability of structures.According to the fatigue damage process,the fatigue scatter factors of crack initiation stage and crack propagation stage are given respectively.At the same time,mathematical models of fatigue life prediction are presented by utilizing the fatigue scatter factors and full scale test results of aircraft structures.Furthermore,the economic life model is put forward.The model is of sig-nificant scientific value for products to provide longer economic life,higher reliability and lower cost.The theory of economic life prediction and reliability assessment of aircraft structures has been successfully applied to determining and extending the structural life for thousands of airplanes.
文摘Material performance of LY12CZ aluminum is greatly degraded because of corrosion and corrosion fatigue, which severely affect the integrity and safety of aircraft structure, especially those of lbe navy aircraft structure. The corrosion and corrosion fatigue failure process of aircraft structure are directly concerned with many factors, such as load, material characteristics, corrosive environment and so on. The damage mechanism is very complicated, and there are both randomness and fuzziness in the failure process. With consideration of the limitation of those conventional probabilistic approaches for prediction of corrosion fatigue life of aircraft structure at present, and based on the operational load spectrum obtained through investigating service status of the aircraft in naval aviation force, a fuzzy reliability approach is proposed, which is more reasonable and closer to the fact. The effects of the pit aspect ratio, the crack aspect ratio and all fuzzy factors on corrosion fatigue life of aircraft structure are discussed. The results demonstrate that the approach can be applied to predict the corrosion fatigue life of aircraft structure.
基金Project(51575129) supported by the National Natural Science Foundation of ChinaProject(J15LA51) supported by Shandong Province Higher Educational Science and Technology Program,ChinaProject(2017T100238) supported by China Postdoctoral Science Foundation
文摘Nickel-based superalloys are easy to produce low cycle fatigue(LCF)damage when they are subjected to high temperature and mechanical stresses.Fatigue life prediction of nickel-based superalloys is of great importance for their reliable practical application.To investigate the effects of total strain and grain size on LCF behavior,the high temperature LCF tests were carried out for a nickel-based superalloy.The results show that the fatigue lives decreased with the increase of strain amplitude and grain size.A new LCF life prediction model was established considering the effect of grain size on fatigue life.Error analyses indicate that the prediction accuracy of the new LCF life model is higher than those of Manson-Coffin relationship and Ostergren energy method.
