Reliable Life Prediction Research Articles

Multi-dimensional failure risk load prediction of electric motor based on physical model and data-driven approach

Dynamic prediction of failure risk loads is a critical prerequisite for system damage monitoring and service life evaluation. As the failure mechanism of electric vehicle drive motors under multi-source load excitations is complex, and the risk load poses challenges in rapid acquisition, a physics-based and data-driven method for multi-dimensional failure risk load prediction of motors is proposed. Based on actual operational data collected from users, we analyze the failure risk loads of various components of a motor. A physical simulation model of the motor is established to extract multi-dimensional failure risk load time history, and the effectiveness of the simulation model is verified using data from bench tests. Moreover, using the physical model simulation data as a foundation, a two-stage data-driven model is constructed. In the first stage, the genetic algorithm optimized back propagation neural network (GA-BPNN) model is implemented for multi-dimensional loss prediction of the motor, and serves as the primary input for the second stage model, which integrates prediction accuracy and training efficiency. In the second stage, by comprehensively considering the spatial and temporal correlation features with the input layer reconstructed using correlation matrix weights, an improved convolutional neural network with bidirectional long short-term memory (CNN-BiLSTM) model is employed to predict multi-scale loads. Compared with traditional models, the proposed method exhibits significantly improved prediction accuracy, with R2 greater than 0.95. Furthermore, the damage error between the predicted load and the expected load is within 10%, which provides technical support for reliability evaluation and life prediction of electric motor.

Numerical Simulation of the Frequency Dependence of Fatigue Failure for a Viscoelastic Medium Considering Internal Heat Generation.

Accurately predicting fatigue failure in CFRP laminates requires an understanding of the cyclic behavior of their resin matrix, which plays a crucial role in the materials' overall performance. This study focuses on the temperature elevation during the cyclic loadings of the resin, driven by inelastic deformations that increase the dissipated energy. At low loading frequencies, the dissipated energy is effectively released as heat, preventing significant temperature rise and maintaining a consistent, balanced thermal state. However, at higher frequencies, the rate of energy dissipation exceeds the system's ability to release heat, causing temperature accumulation and accelerating damage progression. To address this issue, the study incorporates non-recoverable strain into a fatigue simulation framework, enabling the accurate modeling of the temperature-dependent fatigue behavior. At 0.1 Hz, damage accumulates rapidly due to significant inelastic deformation per cycle. As the frequency increases to around 2 Hz, the number of cycles until failure rises, indicating reduced damage per cycle. Beyond 2 Hz, higher frequencies result in accelerated temperature rises and damage progression. These findings emphasize the strong link between the loading frequency, non-recoverable strain, and temperature elevation, providing a robust tool for analyzing resin behavior. This approach represents an advancement in simulating the fatigue behavior of resin across a range of frequencies, offering insights for more reliable fatigue life predictions.

Reliability and fatigue life prediction of GFRP pipes by continuum damage mechanics-based damage elastic–plastic bridging model

Reliability and fatigue life prediction of GFRP pipes by continuum damage mechanics-based damage elastic–plastic bridging model

Fatigue life modeling for a low alloy steel after long-term thermal aging

Fatigue failure of materials has a considerable impact on the safety of equipment in service. In this study, axially tensile and low cycle fatigue tests were conducted on a low alloy steel after accelerated thermal aged at 450 °C for 10,000 h. The experimental results indicate that the ultimate and yield strengths increase moderately, while the fatigue life of specimens experience a slight decrease in this circumstance. The fracture analysis demonstrates that the bainite breaking facilitates the fatigue crack initiation and propagation after thermal aging, which is accompanied by a decrease in plastic strain amplitude. Therefore, the plastic strain amplitude is considered as an indicator of thermal aging in fatigue life modeling for the low alloy steel. Finally, a novel life model that incorporates both aging time and temperature was proposed for rapid prediction of low cycle fatigue life. It is assumed that this model promotes reliable fatigue life prediction in low alloy steels under various thermal aging circumstances, as well as the extrapolation of fatigue performance of the material in service.

Utilization of High-Temperature miniaturized testing to Assist in life management for gas turbine Blades: An Overview

Safely operating gas turbine blades in aero-engines or industrial gas turbines under severe thermo-mechanical conditions always poses a continuous challenge. There is an urgent need for more reliable life prediction tools, necessitating earlier and more rigorous assessments of in-service damage. This paper introduces a systematic examination of high-temperature miniature specimen testing method within a practical life management framework. To improve current practices in assessing the condition of service-aged gas turbine blades, a proactive utilization of miniature specimen testing is recommended for early in-service assessment within the component lifecycle and integrated into a comprehensive life assessment/management framework. The paper outlines a structured approach to life management, combining miniature specimen sampling and creep and fatigue testing methods. This forms the basis for a novel, holistic life assessment methodology, which is proposed in this paper, incorporating the innovative use of high-temperature miniature specimen testing.

A physics-informed deep learning approach for combined cycle fatigue life prediction

The prediction of the combined high and low cycle fatigue (CCF) life of welded components was valuable for the reliability of practical engineering structures. In this study, a physics-informed Grey-deep convolutional neural networks (DCNN) model was constructed and the model parameters was determined based on the fatigue behavior characteristics of CCF, which was proved perform well in the CCF life prediction of welded components. The predicted results indicated that the proposed model can realize reliable CCF life prediction with good accuracy (MAE = 0.49) and stability (RMSE = 0.44). Further, the proposed model also exhibited good prediction performance under different loading and geometry conditions, indicating the good universality of the proposed model. And the good universality represented that the proposed model had the potential to be applied in more engineering fields.

Experimental study on low-cycle fatigue performance of high-strength bolted shear connections

In strong earthquakes, low-cycle fatigue fractures may occur in the bolted connections of steel braced frames. Ensuring a high low-cycle fatigue life for high-strength bolted connections is of paramount significance in enhancing the overall safety and collapse resistance of steel structures. Despite substantial research on plate fatigue failure within bolted connections, there remains a research gap regarding low-cycle fatigue failure of high-strength bolts in these connections. This study aims to address the aforementioned shortcomings by conducting 34 sets of low-cycle fatigue tests on high-strength bolted connections. The test specimens all experienced low-cycle shear fatigue fracture at the threaded or unthreaded portion of the bolt shank as the dominant failure mode. Residual deformations were observed in the holes of connection plates. Based on the test data, ultimate shear capacity of a single shear connection is around 0.61Fy (tensile yield bearing capacity of bolt) when the shear force passes through the unthreaded portion and drops to 0.54Fy for the shear force at the thread. The untreated Q355 (minimum yield strength of 355 MPa) steel surface has an average anti-slip coefficient of around 0.37, while milling reduces it to approximately 0.30. The influence patterns of loading amplitude, bolt material, minimum plate thickness, bolt diameter, shear force position and connection type on low-cycle fatigue life are given by range analysis. Among them, variance analysis shows that loading amplitude and bolt material are the primary influencing factors. The correlation coefficient between loading amplitude and low-cycle fatigue life is −0.92, indicating a strong negative correlation. The degradation amount and rate of anti-slip capacity and shear capacity of bolted connections are also investigated. To propose reliable life prediction method, three models were used to establish the relationship between dimensionless shear deformation and low-cycle fatigue life of 10.9-grade high-strength bolted connections. It is not appropriate to use the fatigue categories defined in current standards to predict the low-cycle shear fatigue life of high-strength bolted connections.

Multiaxial creep–fatigue failure mechanism and life prediction of a turbine blade based on a unified numerical solution approach

AbstractExposure of turbine blades to cyclic torsional loading at high temperature, stemming from pre‐torque installation and the aerodynamic forces during operation, has the potential to induce substantial creep–fatigue damage, thereby contributing to the likelihood of premature failure. Investigating the deformation mechanisms and proposing a reliable life prediction method aiming at torsional loading is critical to ensure the structural integrity of turbine blades. This study conducted strain‐controlled fatigue and creep–fatigue tests on Inconel 718 superalloy, employing a multiaxial servo‐hydraulic testing machine. Electron backscattering diffraction elucidated deformation and damage mechanisms, forming a basis for subsequent constitutive modeling and life prediction. The lack of creep–fatigue mechanical behavior and microscopic failure mechanism when stress triaxiality equal to 0 is filled, which provides the theoretical basis and data support for the life design and damage assessment of this material under extreme service conditions. The unified viscoplasticity constitutive model effectively characterized macroscopic deformation under torsional loading. Prediction of creep–fatigue life under torsional loading, utilizing the multiaxial ductility factor‐modified strain energy density exhaustion model, demonstrated excellent alignment with experimental findings. Finally, parametric analyses of stress distribution and damage assessment under different conditions were carried out for the example of a turbine blade with relatively rarely considered aerodynamic loading as a variable. It is expected to be popularized and applied in life design and damage assessment of high‐temperature structures under multiaxial loading in engineering.

Research on the Prediction Method of Equipment Status in Power Transformation and Distribution Based on Grey Model

With the continuous increase in the demand for electricity in our country, the reliability requirements of the power distribution network are gradually increasing, and the difficulty of predicting the state of key equipment in the power distribution network is also increasing. In response to this issue, this paper proposes a typical reliability prediction model for key equipment in the power distribution network based on an unbiased grey correlation model. Firstly, a grey model is established to model the reliability of typical key equipment in the power distribution network, and to conduct reliability analysis and life prediction. Secondly, an unbiased grey model is introduced to avoid the problem of the grey model leading to less than ideal life prediction accuracy when the growth rate of the original data sequence is high. Finally, taking the No. 1 main transformer of the 220 kV Lanshan substation under the jurisdiction of Ningxia Shizuishan Power Supply Company as an example, the oil chromatography data is cleaned using the KNN interpolation method and input into the prediction model to analyze and predict the failure rate during actual operation. The results show that this model has certain advantages in terms of life prediction accuracy and calculation time, and can play an auxiliary role in the process of predicting the state of key equipment in the power distribution network.

Loss of Life Transformer Prediction Based on Stacking Ensemble Improved by Genetic Algorithm By IJISRT

Prediction for loss of life transfomer is very important to ensure the reliability and efficiency of the power system. In this paper, an innovative model is proposed to improve the accuracy of lost of life transfomer prediction using stacking ensembles enhanced with genetic algorithm (GA). The aim is to develop a robust model to estimate the remaining life of a transformer in order to generally increase the reliability of the electrical energy distribution system. This approach involves integrating various machine learning models as a basic model, namely Support Vector Machines (SVM) and K-Nearest Neighbor (KNN). A stacking ensemble framework is then used to combine the predictions of these base models using a meta model namely Logistic Regression (LR). The results show a significant improvement in both transformers using stacking-GA, both TR-A and TR-B, with each prediction evaluation 99% and with a minimal error rate, namely approaching 0.the developed framework presents a promising solution for accurate and reliable transformer life prediction. By integrating a variety of basic models, applying improved stacking layouts using GA, these models offer valuable insights to improve maintenance strategies and system reliability in power grids.

Uncertainty quantification in multiaxial fatigue life prediction using Bayesian neural networks

In practical engineering scenarios, unforeseen failures may result in significant costs and risks. Assessing the uncertainty related to multiaxial fatigue life prediction is crucial for engineering applications. However, establishing a reliable multiaxial fatigue life prediction model remains challenging due to uncertainties in physical models, material properties, and measurement data. This paper proposes an effective Bayesian Neural Network (BNN) model for quantifying the uncertainty in multiaxial fatigue life prediction. Fatigue parameters in the multiaxial fatigue life prediction model are used as inputs for the BNN. The BNN method utilizes No-U-turn Sampler (NUTS) and Automatic Differentiation Variational Inference (ADVI) to address the inference problem in the model and perform life predictions for unknown non-proportional loading paths and different materials. Validation using experimental data from six different materials confirms the effectiveness of the BNN model. Experiments show that the performance of BNN models is beneficial in most cases compared to classical ML models, assessed through different error standards, statistical tests, Taylor diagrams, uncertainty analysis, and scatter index analysis. The proposed method provides a clear understanding of the uncertainty in multiaxial fatigue life prediction, offering a promising approach for simulating fatigue life under multiaxial loading in engineering applications.

Stress configuration‐based classification of current research on fatigue of reinforced and prestressed concrete

AbstractThe limited understanding of the fatigue behavior of reinforced and prestressed concrete members is one of the reasons why many structures do not reach their expected service life. Without a deeper theoretical understanding of the fatigue phenomena in the various fatigue process zones, reliable fatigue life predictions are not possible. This paper provides a classification of the major fatigue process zones and mechanisms in reinforced and prestressed concrete members, accompanied by a brief review of recent developments in design rules, experimental characterization, and modeling approaches specific to each fatigue process zone and mechanism. The limitations of current approaches to fatigue characterization and modeling are also discussed, highlighting the need for further research in this area.

Reliability Analysis and Life Prediction of Solder Joints for Avionics Devices With Immersion Cooling

Reliability Analysis and Life Prediction of Solder Joints for Avionics Devices With Immersion Cooling

Review of accelerated aging methods for geotextiles

Accelerated aging methods are becoming increasingly common to evaluate geotextile properties in long-term behavior. Due to this, various manufacturers of these materials are asked to guarantee the useful life of the product, especially for components that cannot be easily inspected or may fail in service. Although the durability of geotextiles in non-demanding applications has traditionally been predicted from previous in-service experience, design for harsh environments or the long term requires a much better understanding of degradation mechanisms and the use of accelerated aging conditions to allow reliable useful life predictions to be made. Therefore, this paper aims to review accelerated aging methods according to the geotextile application environment that is commonly experienced in service and some techniques that have been developed for lifetime prediction in geotextiles according to different applications in engineering projects. The results of the review of the different papers analyzed show a clear division between conventional and non-conventional aging procedures. Moreover, characterization is defined according to the type of application of the geotextile. The review in this study, for geosynthetic design, provides general knowledge about accelerated aging methods using the main articles from the literature to evaluate the durability of geotextiles.

Measuring Strain and Crack Evolution in Reinforced Concrete under Monotonic and Fatigue Tension using Fiber Optic Sensors

For reliable service life prediction of reinforced concrete (RC) structures, a fundamental knowledge of the damage development under repeated subcritical loading is essential. Assessment of remaining service life is in practice mostly based on elaborate visual inspection of the concrete surface. To overcome this time-consuming process, it is crucial to consider continuously gained information on the damage state of the existing structure by comprehensive strain measurement.Based on this premise, the authors have developed a monitoring concept that involves the external application of two-dimensionally arranged distributed fiber optic sensors (FOS) for high-resolution strain measurement. This paper presents the first preliminary studies validating this general concept and shows how strain and crack development under monotonic and stepwise increasing fatigue tensile loading can be accurately monitored. The results clearly demonstrate that crack initiation can be predicted based on strain measurements long before the actual crack formation and that even after crack initiation, the gradual crack opening can be reliably monitored. Furthermore, several hundred cycles (before and after crack formation) have no impact on measurement quality.

Evaluating creep rupture life in austenitic and martensitic steels with soft-constrained machine learning

Machine learning is extensively utilized for predicting creep rupture of high-temperature steels. Recently, five soft-constrained machine learning algorithms (SCMLAs) have been developed to enhance the extrapolation capabilities of machine learning. These SCMLAs were applied to the austenitic steel Sanicro 25, showing their potential. To improve SCMLAs, this study has introduced new guidelines that address temperature culling within the input range and temperature extrapolation beyond the input range. Leveraging these guidelines, the SCMLAs were extended to various austenitic and martensitic stainless steels. The predicted results of TP316H, the data of which is representative of austenitic stainless steels, were validated through error estimates. Furthermore, notable agreement has been reached for temperature culling and temperature extrapolation, as demonstrated for TP91 and TP92 martensitic steels. The effects of single casts and the temperature dependence of the predictions have been analyzed for the studied materials. Consistent results can be readily achieved through systematic evaluations of SCMLAs for extrapolating up to 300,000 h or three times the maximum experimental rupture time for the studied materials. It is demonstrated that SCMLAs can provide reliable creep rupture life prediction across various high-temperature materials.

Physics-Informed Deep Learning-Based Approach for Probabilistic Modeling of Degradation

Deep learning (DL) models have gained significant popularity for the prognostics of systems experiencing degradation. However, there are two major concerns with such models. Firstly, they require a substantial amount of training data due to their large number of parameters. Secondly, they disregard the underlying physics and solely fit the available data, leading to potentially weak generalization capabilities when faced with unseen out-of-distribution data in the field. This study aims to tackle these challenges by incorporating the underlying physics of degradation into DL models. The objective is to develop a novel DL-based approach in conjunction with Bayesian filtering, enabling physics-informed probabilistic life prediction for systems subject to environmentally induced degradation. The proposed framework consists of two main components: physics discovery and degradation prediction. The former involves identifying the dominant stress agents and formulating the underlying physics of degradation. The latter predicts the degradation of the system by incorporating the discovered physics into a DL model. It is expected the results indicate that by combining data-driven DL with physics-based insights, more robust and reliable life predictions can be achieved, addressing the limitations of DL approaches. This framework holds promise for enhancing decision-making processes related to maintenance strategies in various industries.

Remaining useful life prediction of lithium-ion batteries via an EIS based deep learning approach

Reliable life prediction technology is of great significance in ensuring a safe and efficient lifetime of lithium batteries. However, the traditional health factors such as battery capacity are the effects of battery aging rather than the direct causes, which cannot directly reflect the internal degradation mechanism information of the battery, and the prediction accuracy is easily affected by the working environment of the battery. Electrochemical impedance spectroscopy (EIS) data can more directly reflect the internal mechanism information of the battery, which includes a wealth of battery aging information. In order to deeply investigate the mapping relationship between impedance spectrum and remaining useful life (RUL) of lithium batteries, EIS method is employed to obtain the impedance and phase of lithium batteries under different health states and temperatures, as well as explore the visualization and quantification of impedance frequency response of lithium battery. Furthermore, the mapping relationship between RUL and the lithium battery impedance is investigated in a full impedance spectrum at different temperatures. It is found that, as lithium battery aging, its negative imaginary parts impedance increases significantly, especially in the middle of the frequency band, and has no significant dependence on temperature. While the real part impedance shows an obvious dependence on temperature. Therefore, it is found that the negative imaginary parts impedance of impedance spectrum has a well-fit characterization ability for RUL of a lithium battery. In this paper, a fusion neural network model of Conv1d-SAM (one-dimensional convolutional neural network-self-attention mechanism) was established with negative imaginary part impedance as input factor to predict battery RUL. The predicted results show that Conv1d-SAM has improved accuracy and stability in RUL prediction, and the mean absolute error function of the proposed model is increased by 72% compared with the latest published method.

Damage of CRTS III type ballastless track-32 m simply supported girder structural system under long-term deformation effects

Until now, the CRTS (China’s Railway Track System) III type ballastless track-girder system has been gradually used in high-speed railway engineering. However, the effect of long-term deformation of prestressed box girders on the upper track structure is often overlooked. Given the strict requirements for track smoothness in high-speed railways, an in-depth study of the long-term deformation of the CRTS III type ballastless track-32 m simply supported girder system (girder-track system) is particularly important. In this study, a refined finite element model was established for a three-span CRTS III type ballastless track- simply supported box girder system. Based on the aid of the CEB-FIP 90 creep model and the UMAT (User-Material) subroutine, the long-term deformation calculations were investigated. Furthermore, an in-depth analysis of stress and damage of the CRTS III type ballastless track under the long-term deformation of the box girder was conducted by combining concrete damaged plasticity (CDP) and cohesive zone model (CZM) constitutive models. The numerical simulated results indicated that after four years of operation, the creep camber of the box girder in the girder-track system would reach to 3.41 mm. The maximum tensile and compressive longitudinal stresses of the base plate would reach to 0.537 MPa and 11.983 MPa, respectively. Meanwhile, the maximum tensile and compressive longitudinal stresses of the self-compacting concrete layer would reach to 0.958 MPa and 2.701 MPa, respectively. In the box girder mid-span, significant damage could be observed in the edge of the two base plates near the mid-span, with a maximum compressive damage rate of 0.164 and the maximum tensile damage rate of 0.304. The research of this study has achieved the prediction of long-term deformation in the girder-track system, providing an important basis for the reliability assessment and life prediction of the girder-track system.

Fatigue behavior of Al-CFRP spot-welded joints prepared by electromagnetic pulse welding

In this study, the fatigue performance of magnetic pulse welding (MPW) joints of AA5052 aluminum alloy and T300 carbon fiber reinforced polymer (CFRP) with sandwich structure was systematically investigated. Mechanical property tests and microscopic observations were used to evaluate joint performance and damage to the CFRP. The results showed that satisfactory tensile strength (up to 92.24% of the tensile strength of the base material) was obtained by optimization of discharge energy. However, the samples in the fatigue test exhibited more sensitive properties to the fatigue environment. The higher fatigue cycle life was demonstrated only when the stress amplitude Sa ≤ 20.41 MPa. The fatigue test data were analyzed by Weibull distribution to fit the S-N curves under different reliability levels, which can be used for reliability assessment and life prediction in practical applications. The CFRP surfaces in different states were studied by scanning electron microscope (SEM). It was found that MPW would not damage the surfaces, while delamination and cracking would gradually occur during the fatigue process.