Life Prediction Method Research Articles

Tensile efficiency and fatigue life of similar and dissimilar carbon steel joints subjected to rotary friction welding

Rotary friction welding (RFW) is a solid-state welding method that can address the melting point limitation of other welding types; however, the welded area remains at risk of failure due to fatigue during operation. Fatigue failure is difficult to detect and predict, making it a critical failure mode in engineering. Although many fatigue life prediction methods are available, they do not consider the impact of RFW parameters (such as pressure, speed, and friction time) on fatigue strength. Owing to their good mechanical properties and commercial viability, carbon steel of grades C35 and C45 is commonly applied to manufacture main parts in the automotive industry. This study centers on employing RFW to join C35 and C45, representing the first-ever instance of using this technique to weld them together. The primary goal of RFW for C35 and C45 is to construct optimum parts that meet specific design requirements and have a long fatigue life. Findings showed C45–C45 joints (77 %) were more tensile-efficient than C35–C35 joints (73 %). Dissimilar C35–C45 joints reached 60 % of C45 base metal and 76 % of C35 base metal in terms of tensile efficiency. RFW welds had lower tensile strength than their base metals. Optimal results came at 35 MPa friction pressure and 8–12 s friction time for both similar and dissimilar RFW joints using the Coffin–Manson method, dissimilar C33–C45 joint fatigue life improved by over 85 %, aligning C35 and C45 engineering aspects. SEM microstructure analysis showed two regions: non-deformed (NDZ) and plastically deformed (PDZ), with broader PDZ indicating better tensile strength. These findings enhance RFW's efficiency, promoting automotive part longevity and safety.

A life prediction method of rolling bearing based on signal reconstruction and fusion dual channel network

In addressing the problem of low prediction accuracy in the remaining useful life (RUL) prediction of rolling bearings, caused by noise interference and insufficient extraction of sensitive features by deep learning models, this paper presents a life prediction method based on signal reconstruction and dual-channel network fusion. First, addressing the issue of extracting weak features from rolling bearing vibration signals, an optimized combination of variational mode decomposition (VMD) and Teager–Kaiser energy operator (TKEO) for signal reconstruction is proposed. TKEO is used to track the energy of high-frequency impulses in the original signal. The sparrow search algorithm is employed for optimizing VMD to perform high-frequency filtering, resulting in an optimized impulse energy signal. This signal is then multiplied with the original signal to enhance weak impulse features under noisy background. Next, a dual-channel network model for RUL prediction is constructed based on temporal convolutional network (TCN) and convolutional neural networks (CNNs). The one-dimensional time-series signal obtained after reconstruction and denoising serves as the input for the TCN network channel. Simultaneously, the signal obtained after reconstruction and denoising undergoes synchrosqueezed wavelet transforms to generate a two-dimensional time–frequency representation as input for the CNN network channel. This setup allows TCN and CNN to respectively extract temporal features from the vibration signal and time–frequency features from the spectrogram. By incorporating self-attention mechanisms, internal correlations between different features are fully explored, thereby enhancing prediction accuracy.

Multiaxial fatigue life prediction of notched specimens based on multidimensional grey Markov theory

It is always a challenge to accurately predict the fatigue life of notched specimens under multiaxial loading, which is a guarantee of structural integrity. Therefore, in this paper, multiple factors affecting fatigue life are considered and a multidimensional grey Markov model is used for fatigue life prediction. Firstly, the plane of maximum shear strain amplitude is determined as the critical plane. Meanwhile, the stress–strain components on the critical plane are extracted, and the relevant parameters affecting the fatigue life are calculated. Secondly, due to the defects of the grey theory itself, the prediction error is larger. Therefore, the grey model is modified with Markov theory to get the grey Markov model. The correlation degree analysis between relevant factors and fatigue life is carried out with grey theory to analyze the degree of influence of different factors on fatigue life. Finally, the grey Markov model is analyzed and verified using experimental data from Q355(D), GH4169 and Al7050 notched specimens and the results show that the grey Markov model can provide an economical and effective method for multiaxial fatigue life prediction.

Influences of fatigue stiffness degradation of in-service concrete T-beams on natural vibration frequency

ABSTRACT In order to obtain the fatigue stiffness degradation law of in-service concrete T-beam and carry out fatigue life prediction, a dual-stage stiffness degradation model considering cracks was established for T-beams and formulas for calculating the fundamental frequency of damaged concrete T-beams were deduced based on relevant theories of damage mechanics. The developed model aimed to investigate the influences of the fatigue stiffness degradation of in-service concrete T-beams on the natural vibration frequency of structures. A fatigue test was conducted for full-scale test beams to examine the crack development and fundamental frequency change law of structures during the fatigue process. Based on a full scale model of 10 m reinforced concrete T-beams, static and fatigue failure tests were carried out to obtain the evolution law of fatigue residual stiffness with load times. Fatigue damage coefficient D and stiffness degradation coefficient k were introduced to establish the fatigue life prediction model of T-beams in service. In line with the related test data and fundamental frequency formulas, stiffness updating methods were put forward for the concrete T-beam finite element models. By comparing the calculated value and test value of the natural vibration frequency of structures, the relative error was estimated to be within 6%. This verified the accuracy and reliability of the fundamental frequency calculation formulas and the updated finite element models. The research results can be used as a reference for the precise simulation of the fatigue damage finite element models of concrete T-beams. Finally, a method for life prediction of in-service reinforced concrete beam Bridges is proposed, and relevant research results can provide theoretical support for the study of life prediction of such Bridges.

A Method for Predicting the Creep Rupture Life of Small-Sample Materials Based on Parametric Models and Machine Learning Models.

In view of the differences in the applicability and prediction ability of different creep rupture life prediction models, we propose a creep rupture life prediction method in this paper. Various time-temperature parametric models, machine learning models, and a new method combining time-temperature parametric models with machine learning models are used to predict the creep rupture life of a small-sample material. The prediction accuracy of each model is quantitatively compared using model evaluation indicators (RMSE, MAPE, R2), and the output values of the most accurate model are used as the output values of the prediction method. The prediction method not only improves the applicability and accuracy of creep rupture life predictions but also quantifies the influence of each input variable on creep rupture life through the machine learning model. A new method is proposed in order to effectively take advantage of both advanced machine learning models and classical time-temperature parametric models. Parametric equations of creep rupture life, stress, and temperature are obtained using different time-temperature parametric models; then, creep rupture life data, obtained via equations under other temperature and stress conditions, are used to expand the training set data of different machine learning models. By expanding the data of different intervals, the problem of the low accuracy of the machine learning model for the small-sample material is solved.

Thermal–Fluid–Solid Coupling Analysis on the Effect of Cooling Gas Temperature on the Fatigue Life of Turbine Blades with TBCs

The application of thermal barrier coatings (TBCs) can increase the blade’s operating temperature and fatigue life. Previous studies have neglected the effects of cooling gas temperature variations on the temperature field, stress field, and fatigue life of blades and TBCs. For this reason, this paper considers the inhomogeneity of the high-temperature gas inlet temperature, the internal cooling gas temperature, the periodicity of the external flow field, etc., and establishes a finite element model of the gas turbine blade with TBCs. Then, the life of the blade and the TBCs is predicted based on the Ncode 2020R2. Finally, the effect of the cooling gas temperature on the temperature, stresses, and life of the blade and the TBCs is analyzed. The results show that the fatigue life of the TBCs is lower than that of the blade, and the low-life region of the TBCs is located at the leading edge of the blade, which is consistent with the TBCs shedding region of the real blade and verifies the accuracy of the life prediction method in this paper. The fatigue life of the blade and TBCs firstly increases and then decreases with the increase in the cooling gas temperature, and the trend of the stress changes in the opposite direction. When the cooling gas temperature is increased from 573 K to 873 K, the minimum life of the blade is increased by 358.5%, and that of the TBCs is increased by 138.7%. The conclusions can provide guidance for the design of long-life turbine blades with TBCs.

A novel machine learning method for multiaxial fatigue life prediction: Improved adaptive neuro-fuzzy inference system

In this study, a neuro-fuzzy-based machine learning method is developed to predict the multiaxial fatigue life of various metallic materials. First, the fuzzy inference system and neural network are combined to identify and capture the nonlinear mapping relationship between multiaxial fatigue damage parameters and fatigue life. Non-proportionality and phase differences are introduced to characterize different loading paths. Next, the Adam algorithm is employed to update the premise parameters of the original model to achieve fast and accurate convergence. Then, subtractive clustering is applied to extract fuzzy rules between input variables and output for more efficient prediction. Moreover, the hyperparameters in the proposed model are automatically optimized by the adaptive opposition slime mould algorithm to obtain the optimal model. The predictive performance of the proposed model is verified by fatigue experimental data for six materials in published literature, which indicates that the proposed model can effectively predict the fatigue life of various materials under different loading paths. Meanwhile, compared with six classical machine learning models, it is found that the proposed model has better predictive performance and extrapolation capability.

High-temperature high-cycle fatigue performance and machine learning-based fatigue life prediction of additively manufactured Hastelloy X

Uncertainties in fatigue life of laser powder bed fusion (L-PBF) additively manufactured parts arise from microstructural heterogeneities and randomly dispersed defects generated during the L-PBF. Stress-controlled fatigue performances of L-PBF-built Hastelloy X were examined in 400 °C and 600 °C high-temperature atmospheres. Given the inherent anisotropy of the L-PBF-built Hastelloy X, the fatigue tests were performed on the samples with distinct building orientations. Fatigue-induced damage evolution characteristics were meticulously analyzed after drawing the S-N curves with a 0.1 stress ratio, a 20 Hz loading frequency and varied stress amplitudes. We established a database of the fatigue test results with material properties of the L-PBF-built Hastelloy X to build a machine learning (ML) framework for fatigue life prediction, skipping the traditional fatigue-life mathematical models that are less applicable to L-PBF-built metals. For capturing the intricate influence of diverse factors on the fatigue life accurately, deep neural network (DNN) and support vector machine (SVM) were utilized and optimized within the ML-based framework. By comparing our ML-based approach with traditional methods for life prediction, it is indicated that ML techniques can transcend the physical limitations associated with the fatigue processes while simultaneously offering a unified depiction thereof.

Deep learning-based modeling method for probabilistic LCF life prediction of turbine blisk

Turbine blisk is one of the typical components of gas turbine engines. The fatigue life of turbine blisk directly affects the reliability and safety of both turbine blisk and aeroengine whole-body. To monitor the performance degradation of an aeroengine, an efficient deep learning-based modeling method called convolutional-deep neural network (C-DNN) method is proposed by absorbing the advantages of both convolutional neural network (CNN) and deep neural network (DNN), to perform the probabilistic low cycle fatigue (LCF) life prediction of turbine blisk regarding uncertain influencing parameters. In the C-DNN method, the CNN method is used to extract the useful features of LCF life data by adopting two convolutional layers, to ensure the precision of C-DNN modeling. The two close-connected layers in DNN are employed for the regression modeling of aeroengine turbine blisk LCF life, to keep the accuracy of LCF life prediction. Through the probabilistic analysis of turbine blisk and the comparison of methods (ANN, CNN, DNN and C-DNN), it is revealed that the proposed C-DNN method is an effective mean for turbine blisk LCF life prediction and major factors affecting the LCF life were gained, and the method holds high efficiency and accuracy in regression modeling and simulations. This study provides a promising LCF life prediction method for complex structures, which contribute to monitor health status for aeroengines operation.

Remaining Useful Life Prediction Method for High Temperature Blades of Gas Turbines Based on 3D Reconstruction and Machine Learning Techniques

Turbine blades are crucial components exposed to harsh conditions, such as high temperatures, high pressures, and high rotational speeds. It is of great significance to accurately predict the life of blades for reducing maintenance cost and improving the reliability of gas turbine systems. A rapid and accurate blade life assessment method holds significant importance in the maintenance plan of gas turbine engines. In this paper, a novel on-line remaining useful life (RUL) prediction method for high-temperature blades is proposed based on 3D reconstruction technology and data-driven surrogate mode. Firstly, the 3D reconstruction technology was employed to establish the geometric model of real turbine blades, and the fluid–thermal–solid analysis under actual operational conditions was carried out in ANSYS software. Six checkpoints were selected to estimate the RUL according to the stress–strain distribution of the blade surface. The maximum equivalent stress was 1481.51 MPa and the highest temperature was 1393.42 K. Moreover, the fatigue-creep lifetime was calculated according to the parameters of the selected checkpoints. The RUL error between the simulation model and commercial software (Control and Engine Health Management (CEHM)) was less than 0.986%. Secondly, different data-driven surrogate models (BP, DNN, and LSTM algorithms) were developed according to the results from numerical simulation. The maximum relative errors of BP, DNN, and LSTM models were 0.030%, 0.019%, and 0.014%. LSTM demonstrated the best performance in predicting the RUL of turbine blades with time-series characteristics. Finally, the LSTM model was utilized for predicting the RUL within a gas turbine real operational process that involved five start–stop cycles.

Two-Phase fatigue life prediction method based on scSE U-net algorithm for abrasive belt grinding of titanium alloy

Two-Phase fatigue life prediction method based on scSE U-net algorithm for abrasive belt grinding of titanium alloy

Creep Performance and Life Prediction of Bamboo Scrimber under Long-Term Tension in Parallel-to-Grain

Creep performance is a crucial factor that must be considered in structural design. This paper aims to investigate the creep failure mode, creep strain, creep compliance, and other creep properties of bamboo scrimber under long-term tension in parallel-to-grain. To establish a general creep life prediction method for the full stress level of the bamboo scrimber, a multi-branch Kelvin–Voigt model, a generalized Maxwell model, and a creep finite element simulation were employed. The results showed that the creep strain curve of bamboo scrimber included the unsteady creep stage and the stable creep stage, but not the accelerated creep stage. When the stress ratio was less than 0.3, the residual strength decreased gradually. Below 70% of the ultimate load capacity, the creep characteristics of the bamboo scrimber were linear viscoelastic, and the creep compliance was generally independent of the load level. The creep finite element model of bamboo scrimber could accurately calculate the creep deformation of specimens. Based on this creep finite element model and creep failure rules, a life prediction model for the full stress level of bamboo scrimber was established, which could accurately predict the creep life. This paper provides theoretical guidance for the creep design of bamboo scrimber in engineering structures.

Total stress field method for fatigue life prediction of finite residual thickness/width notched specimen under tensile load

The notch stress fields in current studies are mainly not affected by the residual thickness/width at notch root. The Theory of Critical Distances (TCD) has been widely applied in notch fatigue analysis. However, fatigue tensile experiment results show that TCD has limitation in surface-notched specimens with finite residual thickness and side-notched specimens with finite residual width. Under the assumption that the total stress field should be considered in determining the effective stress σeff, we proposed the total stress field method (TSFM). It has advantages in prediction accuracy and convenience of finite residual thickness/width notched specimen (FRT/WNS).

Statement of Retraction: Prediction Method of Fatigue Crack Growth Life of High-Strength Steel for Industry 4.0

Statement of Retraction: Prediction Method of Fatigue Crack Growth Life of High-Strength Steel for Industry 4.0

Comparison of Various Intrinsic Defect Criteria to Plot Kitagawa-Takahashi Diagrams in Additively Manufactured AlSi10Mg.

Selective laser melting is a form of additive manufacturing in which a high-power density laser is used to melt and fuse metallic powders to form the final specimen. By performing fatigue and tensile tests under various loading conditions, the study sought to establish the impact of internal defects on the specimens' fatigue life. Scanning electron microscopy and finite element simulation were conducted to determine the defect characteristics and the stress intensity factor of the specimens. Four different methods were used to determine the intrinsic defect length of the specimen, using data such as grain size, yield strength, and hardness value, among others. Kitagawa-Takahashi and El-Haddad diagrams were developed using the results. A correction factor hypothesis was established based on the deviation of measured data. Using Paris law, fatigue life was determined and compared to the experimental results later. The study aims to select one or more approaches that resemble experimental values and comprehend how internal defects and loading situations affect fatigue life. This study's findings shed light on how internal defects affect the fatigue life of selective laser-melted AlSi10Mg specimens and can aid in improving the fatigue life prediction method of additively manufactured components, provided an appropriate intrinsic crack criterion is selected.

Service life prediction of prestressed anchor cable exposed to a dry-wet cycling corrosion environment

The life of anchor cable will be shortened by corrosion in complex engineering environment, however at present there is no quantitative method available for predicting the service life of a prestressed anchor cable. Considering the key factor (dry-wet cycles) that causes the corrosion of anchor cables in an actual project, indoor dry-wet cycling corrosion test equipment and the electrolytic corrosion test device were developed in this work. Pseudo-environmental corrosion tests of the cables were performed. The variation of cable corrosion weight loss ratio with the number of dry wet cycles was revealed through the dry-wet cycling test, and based on this, a model for calculating the corrosion weight loss ratio was built. In addition, the change of the anchor force and breaking strength of the anchor cable with corrosion weight loss ratio was investigated through electrolytic corrosion tests and based on the findings an anchor force loss model and a breaking strength attenuation model were developed. On this basis, a life prediction method of anchor cable was established. The verification results of two engineering examples with anchor cable breakage show that the prediction life of this method is highly consistent with the actual life of the anchor cable, with a difference less than 1 year.

A fast fatigue life estimation method for concrete based on the energy dissipation approach

This study proposed a concrete fatigue life prediction method based on energy dissipation analysis. The fatigue life is estimated by dividing the total critical energy dissipation by the average energy dissipation per cycle. Based on a unified concrete damage model that can be applied to both monotonic and fatigue loading conditions, the total critical energy dissipation value under fatigue loading can be estimated by the stress-strain curve under monotonic loading. The average energy dissipation per cycle is obtained by calculating numerical samples with different strengths. Several numerical examples show that the proposed prediction model can rapidly estimate fatigue life under uniaxial loading with high efficiency and excellent precision.

Remaining Useful Life Prediction Method of PEM Fuel Cells Based on a Hybrid Model

To predict the remaining useful life (RUL) of the proton exchange membrane fuel cell (PEMFC) in advance, a prediction method based on the voltage recovery model and Bayesian optimization of a multi-kernel relevance vector machine (MK-RVM) is proposed in this paper. First, the empirical mode decomposition (EMD) method was used to preprocess the data, and then MK-RVM was used to train the model. Next, the Bayesian optimization algorithm was used to optimize the weight coefficient of the kernel function to complete the parameter update of the prediction model, and the voltage recovery model was added to the prediction model to realize the rapid and accurate prediction of the RUL of PEMFC. Finally, the method proposed in this paper was applied to the open data set of PEMFC provided by Fuel Cell Laboratory (FCLAB), and the prediction accuracy of RUL for PEMFC was obtained by 95.35%, indicating that this method had good generalization ability and verified the accuracy of the method when predicting the RUL of PEMFC. The realization of long-term projections for PEMFC RUL not only improves the useful life, reliability, and safety of PEMFC but also reduces operating costs and downtime.

Remaining useful life prediction method combining the life variation laws of aero-turbofan engine and auto-expandable cascaded LSTM model

The real-time status monitoring and health management of aero-turbofan engines (ATEs) can effectively reduce the risk of engine failure and ensure aircraft flight safety. Accurate prediction of the remaining useful life (RUL) of ATE is a vital tool for effectively monitoring the engine operating condition, in which long-short term memory (LSTM) networks are often applied to RUL prediction. However, because of the complex mechanical structure and operation mode of the aero-engine, the prediction accuracy of the LSTM network is not enough to meet the actual demand. This paper proposes an auto-expandable cascaded long-short term memory (ACLSTM) prediction model that incorporates the lifetime variation laws of ATE, which is mainly applied for the degradation assessment of ATEs and the accurate prediction of RUL. The ACLSTM model adopts the network structure of multiple LSTM modules connected step by step to continuously set the prediction error of the previous module as the training outputs of the latter module. This data processing method transforms the prediction process of the original data into that of the output error, effectively reducing the prediction error and improving the prediction effect. In addition, to further improve the prediction accuracy, this paper comprehensively proposes several empirical formulas for further correction of the prediction effect obtained by the ACLSTM model. In the experimental part, the prediction effectiveness of the proposed method is tested based on four subsets of the C-MAPSS dataset published by the National Aeronautics and Space Administration. The experimental results on the four datasets show that the root mean square error (RMSE) of the ACLSTM prediction model decreases by 95.44% on average compared to the traditional LSTM network. In addition, the RMSE of the model decreases by 96.48% on average after incorporating the empirical formula. The proposed method has the lowest RMSE compared to other methods with the highest prediction accuracy. The experiments thoroughly verify that the ACLSTM model and the proposed empirical formula are feasible and effective for improving the prediction accuracy of the RUL of ATE.

Response Prediction of Asphalt Pavement in Cold Region with Thermo-Hydro-Mechanical Coupling Simulation

Although the theoretical pavement structure design method (TPSDM) is widely used for designing asphalt pavements in Japan, it still exhibits certain limitations, such as not considering the variation in moduli of the base and subgrade layers due to water contents, freeze–thaw action, and stress states. This study aims to enhance Japanese TPSDM’s accuracy by considering variations in the resilient modulus of environmental impacts, pavement materials, pavement structure, and traffic load actions to accurately calculate the mechanical responses and predict pavement fatigue life. Firstly, the study develops a 3D Thermo-Hydro-Mechanical (THM) model using the finite element method (FEM) to investigate temperature and moisture distributions of the pavement with time. Then, based on the numerical results of the moisture, temperature, and stress state obtained from the THM analysis, the constant resilient modulus of the base and subgrade layers in the Japanese TPSDM is replaced with a resilient modulus that considers the stress state and the combined effects of water content fluctuations and freeze–thaw action. Finally, the fatigue life of the pavement is calculated based on the obtained mechanical response in THM analysis. The reliability and validity of the proposed fatigue life prediction method are well verified by comparing the calculated with the actual pavement fatigue life. Results indicate that the modifications improve the Japanese TPSDM by considering the environmental impacts, traffic load actions, pavement materials, and pavement structure, thereby improving the accuracy of predicting the fatigue life of asphalt pavements, particularly in cold regions.