Life Prediction Research Articles

Remaining useful life prediction of lithium-ion batteries based on DBO[sbnd]CNN-DSformer

In order to improve the accuracy of predicting RUL of lithium-ion batteries, a lithium-ion battery RUL prediction method based on the DBOCNN-DSformer model is proposed. Firstly, the health characteristics of the battery are extracted and the local information of health features is mined using CNN. DSformer is utilized for global information, local information, and variable correlation learning of battery aging characteristics. The DBO is used to optimize the super-parameters of the CNN-DSformer model and build the DBOCNN-DSformer model. Finally, the battery aging data set was used for verification. The results show that DBOCNN-DSformer, which sets different prediction starting points, can extract sequence information from input data and establish long-term dependencies between sequences. The maximum average MRE error in the NASA data set was 0.05, the maximum average MAE was 0.018, and the maximum average AE error was within 5. The maximum average MRE error of the CALCE data set was 0.37, the maximum average MAE was 0.014, and the maximum average AE prediction error was within 10. Compared with LSTM, RNN, and Transformer models, it was found that DBOCNN-DSformer showed high prediction accuracy and good robustness.

Predictive modeling for coiled tubing fatigue using advanced machine learning techniques

Coiled tubing CT plays Pivotal role in oil and gas well intervention operations due to its advantages such as flexibility, fast mobilization, safe, low cost and wide range of applications, including: well intervention, cleaning, stimulation, fluid displacement, cementing, and drilling. However, CT is subject of fatigue and mechanical damage caused by repeated bending cycles, internal pressure and environmental factors which can lead to a premature failure, high operational cost and production downtime. With the development of CT proprieties and application traditional fatigue life prediction methods based on analytical models integrated in tracking process showed in some cases an underestimate or overestimate of the actual fatigue life of CT particularly when complex factor like welding type, corrosive environment, and high-pressure variation are involved. This study addresses this limitation by introducing a comprehensive machine learning-based approach to improve the accuracy of CT fatigue life prediction, using a data set derived from over 350 tests both lab scale and full-scale fatigue test. The study has incorporated the impact of different parameters such as CT, grades, wall, thickness, CT diameter, internal pressure and welding types. By using advanced machine learning techniques such as artificial network (ANN), Gradient boosting regressor we got a more precise estimation of the number of cycles to failure than traditional models. The results of this study shown the importance of integration of machine learning for CT fatigue life analysis and demonstrating its capacity to enhance the prediction accuracy and reduce the uncertainty. A detailed machine Learning models is presented, emphasizing their capability to handle complex data and improve prediction under diverse operational conditions. This study contributes to more reliable, CT management and safer more cost-efficient well intervention operations.

Remaining useful life prediction of nuclear reactor control rod drive mechanism based on dynamic temporal convolutional network

The control rod drive mechanism (CRDM) is a critical equipment of the nuclear reactor, and the prediction of its remaining useful life (RUL) is important for the efficient maintenance and ensuring the safe, reliable operation of nuclear power plants. In this paper, a novel framework for the RUL prediction of CRDM is proposed, which is a dynamic temporal convolution network (DTCN) based on dynamic activation function and attention mechanism. Firstly, the temporal convolution network (TCN) is used as the backbone of the prediction model, to extract the temporal dependence of the input data. Next, the dynamic activation function DReLU is integrated into the TCN, which can dynamically activate features and capture variable degradation information. Then, introducing the attention mechanism improves the influence of important high-level features extracted by the network on RUL prediction, thereby improving the efficiency of feature extraction in the network. Finally, the DTCN outputs the predicted RUL by performing non-linear mapping on the extracted features. The CRDM accelerated life test platform is established and a series of experiments are conducted using the collected CRDM full-life vibration dataset. The results demonstrated the performance and advantages of the proposed method.

Prediction of the Remaining Useful Life of Lithium-Ion Battery Using Multilayer Perceptron

Cogitating the reliability of the supply and ensuring continuous delivery of power to the loads, especially in the growing demand for Lithium-Ion batteries in electric vehicle applications, prediction of the remaining useful life of Lithium-Ion batteries is crucial for the timely replacement. For prediction of non-linear and chaotic relationship, experience-based approach, physics-based approach and data driven approach are used among which data driven approach is a model free, accurate and reliable approach. Therefore, a driven approach in predicting remaining useful life can be implemented in the battery management system. This research uses a multilayer perceptron to predict the remaining useful life of the battery. The NASA Ames Prognostics Center of Excellence (PCoE) battery dataset is used to test the proposed methodology. The use of multilayer perceptron for remaining life prediction seems promising despite the significant number of jump points, gaps in data and a small quantity of experimental data in the National Aeronautics and Space Administration (NASA) dataset. The predicted result was obtained with 8.52 % mean absolute error and 9.59 % root mean square error. When compared with the predicted results of different literatures, proposed multilayer perceptron with sliding window approach outperforms most of the existing approach. Incorporation of optimization techniques and hybrid algorithm in proposed approach can further enhance the accuracy of the model.

Exploring machine learning to study and predict the chloride threshold level for carbon steel reinforcement

Chloride-induced corrosion of steel reinforcing bar (rebar) is the primary cause of deterioration in reinforced concrete structures, posing a significant infrastructure challenge. The chloride threshold level (CTL) of rebar, which represents the critical amount of chloride needed to initiate active corrosion, is crucial in corrosion and service life prediction models. However, substantial uncertainties and a multitude of influencing factors, along with the absence of a universally accepted testing framework, hinder the achievement of a consistent CTL range for service life models and complicate comparisons of published values. This study addresses these challenges by developing multiple machine learning models to predict CTL, considering 21 carefully selected features. A comprehensive database of 423 data points was compiled from an exhaustive literature review. Seven machine learning models—linear regression, decision tree, random forest, K-nearest neighbors, support vector machine, artificial neural network, and an ensemble model—were developed and optimized. The ensemble model achieved superior prediction performance, with a mean absolute error of 0.218 % by weight of binder, root mean square error of 0.321 %, and a coefficient of determination of 0.751 on unseen CTL data. Partial dependence plots generated using the support vector machine model quantified the effect of each feature on CTL. The random forest model identified SiO₂ binder content and exposed rebar area to chlorides as the most influential factors. The study also examined the impact of supplementary cementitious materials (SCMs), finding that only blast furnace slag positively affected CTL.

Asymmetric-Based Residual Shrinkage Encoder Bearing Health Index Construction and Remaining Life Prediction.

Predicting the remaining useful life (RUL) of bearings is crucial for maintaining the reliability and availability of mechanical systems. Constructing health indicators (HIs) is a fundamental step in the methodology for predicting the RUL of rolling bearings. Traditional HI construction often involves determining the degradation stage of the bearing by extracting time-frequency domain features from raw data using a priori knowledge and setting artificial thresholds; this approach does not fully utilize the vibration information in the bearing data. In order to address the above problems, this paper proposes an Asymmetric Residual Shrinkage Convolutional Autoencoder (ARSCAE) model. The asymmetric structure of the ARSCAE model is characterized by the soft thresholding of signal features in the encoder part to achieve noise reduction. The decoder part consists of convolutional and pooling layers for data reconstruction. This model can directly construct HIs from the original vibration signals collected, and comparisons with other models show that it constructs better HIs from the original vibration signals. Finally, experiments on the FEMTO dataset show that the results indicate that the HIS constructed by the ARSCAE model has better lifetime prediction capability compared to other methods.

Very high cycle fatigue behavior of TC4 titanium alloy: Faceting cracking mechanism and life prediction based on dislocation characterization

This research analyzes the very-high-cycle-fatigue behavior of TC4 titanium alloy through fatigue tests at R = −1, −0.3, and 0.1. The results show that the S-N curves are all bilinear and exhibit three failure modes as surface slip failure, surface cleavage failure and interior cleavage failure. Transmission electron microscopy analysis reveals the dislocation structure in interior cleavage failure and suggests that the deformation mechanism of faceting cracking involves both anti-phase boundary shearing and stacking fault shearing mechanisms. It concludes that interior failure results from cleavage fracture of α grains due to dislocation slip. Based on the stress intensity factor of the maximum defect, a slip-cleavage competitive failure model was developed by considering factors such as control volume, defect size, external loading, and grain content, with good predictive results. Additionally, on the basis of the failure mechanism and crack propagation rate model, considering the coupled effects of crack tip blunting, stress ratio, Vickers hardness, and material fracture toughness on crack propagation, the crack propagation life prediction model is constructed. The life prediction model is further modified to be more conservative and accurate in predicting life by consideration the maximum defect size, providing important theoretical support and practical guidance for engineering applications.

A closed-form continuous-depth neural-based hybrid difference features re-representation network for RUL prediction

Remaining Useful Life (RUL) prediction contributes to ensuring the reliability of mechanical systems and improving their maintenance plans. Recently, prediction methods based on deep learning have undergone rapid development. However, there are significant differences between multivariate monitoring sequences and utilizing a single model for feature extraction, which leads to reaching suboptimization. Additionally, focusing solely on a specific feature dimension usually imposes notable limitations on the model. This paper proposes a Closed-form Continuous-depth neural (CfC)-based hybrid difference Features Re-representation Network (CfC-F2RN) for RUL prediction. This method comprehensively utilizes hybrid difference features through two stages: initial feature representation and feature re-representation. In the initial feature representation stage, a Long Short-Term Memory (LSTM) is employed to capture the hidden state information of each time step in sequence data. Next, a novel attention mechanism is utilized to extract the hidden states and obtain a deep feature map. In the feature re-representation stage, the encoded features are re-represented using a decoder composed of the CfC model. Finally, the hidden state of the last LSTM unit in the encoder, serving as supplementary information, is combined with the decoded features to form a dual-latent feature representation of the mixed differential features. The prediction subnetwork is then adopted to accomplish RUL prediction. The superiority of CfC-F2RN is substantiated through benchmarking against established methods using the C-MAPSS dataset.

Fatigue reliability analysis methodology based on fatigue life and failure mechanism for carburized gear

Gears are one of the important components in mechanical products, and their fatigue reliability determines the safety performance of mechanical products. In this paper, the fatigue characteristics of carburized gears under different torque and constant rotational speed conditions are investigated by using a gear contact fatigue testing machine, and combined with the dynamic maximum contact stress distribution on the subsurface of the meshing gears, the very-high cycle fatigue P-S-N curves of carburized gears under a stress ratio of −1 is established. Local stress concentration in the surface or subsurface of carburized gears causes grain dislocation movement under the combined influence of maximum contact and residual stresses, and then causes dislocation pileup and transcrystalline rupture after being hindered by grain boundaries, ultimately leading to pitting and fatigue failure of gears. Based on the dislocation energy method and combined with the fatigue failure mechanism of gears, a life prediction model of gears with good prediction results is established by considering the interaction of factors such as dynamic load, grain size, initial crack length, residual stress, slip band length and width. A fatigue reliability analysis method of gears is established based on the life state equation of gears considering the life prediction model. Further analyses of the influence of rotational speed, grain size, residual stress, slip band width, slip band length and initial crack size on the fatigue life reliability index of the gears resulted in the conclusion that the fatigue reliability of the gears not only decreases with the increase of the above-mentioned parameters, but also shows decreasing trend with the increase of time. This is of significance for evaluating the fatigue reliability of gears under very-high cycle fatigue conditions.

Competitive Fracture Mechanism and Microstructure‐Related Life Assessment of GH4169 Superalloy in High and Very High Cycle Fatigue Regimes

ABSTRACTHigh and very high cycle fatigue tests were performed to examine the microstructure and fracture mechanism of GH4169 superalloy in combination with techniques including electron‐backscatter diffraction (EBSD). Fractographic analysis revealed that surface failures are induced by surface flaws, whereas internal failures are caused by pores, facets, and inclusions. The three‐dimensional observation shows that fracture surfaces exhibit an irregular texture due to crystallographic mismatch of grains and plastic deformation at the crack tip. Based on EBSD analysis, Euler angles exhibited a complex geometry of grain orientation at the crack tip area, hindering crack propagation as evidenced by lower values of the Schmid factor and misorientation at the crack tip. Furthermore, the threshold values of small and long cracks decrease, whereas the transformation sizes from small to long crack growth increase from surface to internal failure. Finally, a novel microstructure defect‐based life prediction model is established, and the predicted results demonstrate a close resemblance to experimental outcomes.

Bionic Optimization Design and Fatigue Life Prediction of a Honeycomb-Structured Wheel Hub.

The wheel hub is an important component of the wheel, and a good hub design can significantly improve vehicle handling, stability, and braking performance, ensuring safe driving. This article optimized the hub structure through morphological aspects, where reducing the hub weight contributed to enhanced fuel efficiency and overall vehicle performance. By referencing honeycombed structures, a bionic hub design is numerically simulated using finite element analysis and response surface optimization. The results showed that under the optimization of the response surface analytical model, the maximum stress of the optimized bionic hub was 109.34 MPa, compared to 119.77 MPa for the standard hub, representing an 8.7% reduction in maximum stress. The standard hub weighs 34.02 kg, while the optimized hub weight was reduced to 29.89 kg, a decrease of 12.13%. A fatigue analysis on the optimized hub indicated that at a stress of 109.34 MPa, the minimum load cycles were 4.217 × 105 at the connection point with the half-shaft, meeting the fatigue life requirements for commercial vehicle hubs outlined in the national standard GB/T 5334-2021.

Remaining useful life prediction of high-capacity lithium-ion batteries based on incremental capacity analysis and Gaussian kernel function optimization

Remaining useful life (RUL) is a key indicator for assessing the health status of lithium (Li)-ion batteries, and realizing accurate and reliable RUL prediction is crucial for the proper operation of battery systems. As high-capacity Li batteries have more complex chemical properties, most of the current RUL prediction methods rely mainly on a priori knowledge to make judgments. As a result, prediction accuracy is not high. In this study, we developed a health indicator-capacity (HI-C) dual Gaussian process regression (GPR) model based on incremental capacity analysis (ICA) and optimized its kernel function to achieve accurate RUL prediction for 280 Ah high-capacity Li batteries. Validation against the United States National Aeronautics and Space Administration’s four battery test datasets showed that the use of the HI-C dual GPR model resulted in a mean absolute percentage error and root mean square error of less than 0.02 and 0.04, respectively, for the four battery-rated capacity predictions. Additionally, this model achieved an absolute error of less than five battery failure turns. Compared with a single model, the HI-C dual GPR model not only had high accuracy but also solved the problem that the HI was not measurable in the actual battery operation, which made it more suitable for RUL prediction of Li batteries.

Prediction of rotational bending fatigue life of bearing steel based on damage mechanics

Based on the theory of continuous damage mechanics, this paper proposes a fatigue damage evolution model and numerical calculation method considering the influence of vacuum chemical heat treatment process, and studies the rotational bending fatigue damage analysis and life prediction method of M50NiL bearing steel. Firstly, the constitutive model, fatigue damage evolution equation and material parameter calibration method in the theoretical model are given. Secondly, based on the ABAQUS platform, the damage mechanics-finite element numerical calculation method of fatigue damage analysis considering the influence of hardened layer is realized by writing the UMAT subroutine; then, the rotational bending fatigue test of M50NiL bearing steel treated by vacuum chemical heat treatment of quenching and tempering, carburizing and carbonitriding is carried out, and the influence of heat treatment process on fatigue performance is analyzed; finally, based on the proposed fatigue damage model and numerical calculation method, the rotational bending fatigue life of M50NiL bearing steel is predicted, and the results are compared with the experimental results to verify the correctness of the proposed method.

Identifying key predictive features for live birth rate in advanced maternal age patients undergoing single vitrified-warmed blastocyst transfer

BackgroundInfertility affects one in six couples worldwide, with advanced maternal age (AMA) posing unique challenges due to diminished ovarian reserve and reduced oocyte quality. Single vitrified-warmed blastocyst transfer (SVBT) has shown promise in assisted reproductive technology (ART), but success rates in AMA patients remain suboptimal. This study aimed to identify and refine predictive factors for live birth following SVBT in AMA patients, with the goal of enhancing clinical decision-making and enabling personalized treatment strategies.MethodsThis retrospective cohort study analyzed 1,168 SVBT cycles conducted between June 2016 and December 2022 at the First Affiliated Hospital of Guangxi Medical University and Nanning Maternity and Child Health Hospital. Nineteen machine-learning models were applied to identify key predictive factors for live birth. Feature selection and 10-fold cross-validation were employed to validate the models.ResultsThe most significant predictors of live birth included inner cell mass quality, trophectoderm quality, number of oocytes retrieved, endometrial thickness, and the presence of 8-cell blastomeres on day 3. The stacking model demonstrated the best predictive performance (AUC: 0.791), followed by Extra Trees (AUC: 0.784) and Random Forest (AUC: 0.768). These models outperformed traditional methods, achieving superior accuracy, sensitivity, and specificity.ConclusionLeveraging advanced machine-learning models and identifying critical predictive factors can improve the accuracy of live birth outcome predictions for AMA patients undergoing SVBT. These findings offer valuable insights for enhancing clinical decision-making and managing patient expectations. Further research is needed to validate these results in larger, multi-center cohorts and to explore additional factors, including fresh embryo transfers, to broaden the applicability of these models in clinical practice.

A novel performance prediction method for harmonic reducers based on the trend-enhanced Fisher’s discriminant ratio-Wiener process

Abstract Harmonic reducers, as core components of industrial robots, play a critical role in maintaining robot health. Performance degradation assessment (PDA) and remaining useful life (RUL) prediction are essential for ensuring the operational reliability of such robots. To address the multistage characteristics and stochastic uncertainties in the performance degradation of harmonic reducers, a performance prediction method based on Fisher’s discriminant ratio and Wiener process is proposed. Firstly, the health indicator (HI) construction is defined as an optimization problem based on Fisher’s discriminant ratio and trend monotonicity constraints. By leveraging the sum of the multiplication of frequency amplitudes and optimized weights, precise segmentation of the multistage degradation process over the entire lifecycle is achieved. Notably, the optimized weights can automatically identify the resonance frequency bands caused by damage. Subsequently, a nonlinear Wiener process model with a drift coefficient in the form of a power function is established. The probability density function (PDF) expression for RUL is derived based on the concept of first hit time (FHT). Additionally, a logarithmic likelihood function (Log-LF) for the unknown parameters in the degradation model is constructed. The experimental results indicate that the proposed method surpasses the other two Wiener process models in terms of root mean square error (RMSE), mean absolute percentage error (MAPE), and cumulative relative accuracy (CRA). This provides robust support for preventive maintenance decision-making for harmonic reducers.

Strain response prediction of offshore wind turbine tower under free vibration

Strain monitoring of critical locations in offshore wind turbine tower is essential for fatigue life prediction and safe operation of wind turbine. This paper theoretically analyses the feasibility of predicting tower strain under free vibration using the modal superposition method. A finite element numerical model of the tower is established, and the displacement mode and strain mode parameters of the tower are extracted. The initial displacement and strain of the tower at cut-out wind speed are analyzed, and the first three modal coordinate of the tower are calculated using test points of displacement or strain separately. Subsequently, the full field strain of the tower is predicted using the modal superposition method. Comparative results demonstrate higher accuracy in modal coordinate values calculated using test points of displacement, and the accuracy and errors of strain prediction using different numbers of test points are compared, emphasizing the crucial role of selecting optimal positions and numbers of test points in improving prediction accuracy.

Maximizing efficiency in C45 steel machining: an integrated AI-based approach to coated insert optimization

AbstractMachining involves the subtraction of the material from the sample workpiece to achieve the desired shape or surface. This versatile method is capable of producing a wide range of parts, varying from simple to intricate profiles. Coating materials are increasingly being utilized in tool inserts in the production industry owing to their superior thermal properties and wear resistance. The shielding of hard coatings, with thicknesses of only a few microns, enhances performance and durability. In this study, machining of C45 steel using distinct coated inserts was explored. The experimental trials employed PVD and CVD methods for coated tungsten carbide (WC) tools/inserts and PVD-coated cermet tools/inserts with different machining parameters. Performance metrics, such as the surface finish and reliability of the tool, were considered for the evaluation. The average tool life variation between the PVD-coated cermet and PVD-coated WC was 178.86%, and 30.11% between the PVD-coated cermet and CVD-coated WC at 1 mm DOC. ANOVA was performed using Response Surface Methodology to explore the influence of input parameters on output. The results indicate that the depth of machining and spindle speed significantly influence Ra, whereas spindle speed and type of tool insert have a considerable impact on the life span of the tool. The developed mathematical model for the prediction of tool life and Ra indicates its potential for performance forecasting during C45 steel machining. Grey relation analysis was employed to optimize the process parameters. Optimal results were achieved with a spindle speed of 400 m/min, 0.5 mm depth of cut, and cermet tool inserts. PVD-coated WC inserts performed better. ANFIS was applied for the prediction and optimization of the machining parameters.

Prediction model optimization of gas turbine remaining useful life based on transfer learning and simultaneous distillation pruning algorithm

For the application of deep learning (DL) models in the field of remaining useful life (RUL) prediction and predictive maintenance (PdM) of complex equipment, the insufficient training data and large model are the two major problems. To address these issues, a model training method based on transfer learning and a simultaneous distillation pruning algorithm were proposed. By introducing prior knowledge, three transfer learning modes are devised to reduce the demand of training data. Additionally, the simultaneous distillation pruning algorithm was devised to make the model lightweight, and an iterative pruning method was adopted to trim the large neural network model. By analyzing the performance of different transfer learning modes, the effectiveness of the proposed method can be demonstrated. The number of model parameters and the performance before and after pruning were compared. The results demonstrated that, without significant alterations to the prediction performance, the proposed model exhibited the capability to markedly reduce the number of model parameters. Based on the proposed methods, the challenges of insufficient data and efficiency encountered by DL models could be effectively addressed.

Reliability Simulation of IGBT Module with Different Solders Based on the Finite Element Method

The interconnecting solder is a key control factor for the reliability of electronic power packaging because it highly affects the junction temperature of insulated-gate bipolar transistor (IGBT) modules and is prone to plasticity, creep, and other failure behaviors under temperature-change environments. In this paper, the interconnecting performance and fatigue life of five different kinds of solders such as SAC305, sintered silver, Au80Sn20, sintered copper, and pure In under direct current (DC), power cycle, and electro-thermal coupling complex environments were studied based on electro-thermal multi-physical field coupling finite element simulation method, respectively. Results show that the sintered silver owns the most outstanding thermal reliability and the DC operating junction temperature of the IGBT module after utilizing sintered silver solder is only 90.2 °C, which is nearly 15 °C lower than that of the IGBT module utilizing SAC305 solder. Furthermore, in the power cycle reliability test, the fatigue life of Au80Sn20 solder reaches a maximum of 3.26 × 107 cycles while the life of indium presents only 5.85 × 103 cycles, a difference of nearly four orders of magnitude. Finally, under the complex environment of electro-thermal coupling, the fatigue life of Au80Sn20 solder is also the largest at 1.9 × 106 cycles, while the smallest life of solder becomes SAC305 solder at 4.44 × 102 cycles. The results of this paper can provide a theoretical basis for solder selection and life prediction of the IGBT module, which is of great significance in improving the reliability of power electronic packaging.

A self-supervised assisted label-efficient method for online remaining useful life prediction

Remaining Useful Life (RUL) prediction is crucial for safe and efficient production in industrial equipment. Conventional methods struggle in online environments, facing challenges like data distribution differences across working conditions, model cold start problem under new equipment, and lack of labels in online scenarios. To address these challenges, we propose a novel framework for online RUL prediction that leverages knowledge from self-supervised tasks via metric learning. First, a label-efficient self-supervised learning method incorporating soft triplet loss is proposed to transfer degradation knowledge. Second, we develop a two-stage method to distinguish different degradation stages of the equipment for better alignment of data distribution. Third, we introduce a pseudo-label dynamic self-updating strategy and a sample entropy-based data replay strategy, fine-tuning the offline model with newly acquired data. Our method outperforms state-of-the-art unsupervised approaches, reducing RMSE and MAPE by 16.02% and 8.40%, respectively, and achieves performance comparable to supervised methods.