Life Estimation Research Articles

Improving Fatigue Life Prediction of Natural Rubber Using a Physics‐Informed Neural Network Model

ABSTRACTTraditional physical models and purely data‐driven approaches often struggle with small sample sizes and the complex effects of strain ratios. To overcome these challenges, this study integrates physical principles with machine learning techniques to improve fatigue life predictions for natural rubber (NR). A uniaxial fatigue test on NR was performed, generating data to construct a physical model. A physics‐informed neural network (PINN) model was subsequently developed, utilizing the fatigue life predicted by the physical model, along with engineering strain amplitude and strain ratio as input variables, whereas the experimentally observed fatigue life served as the output variable. The accuracy of the physical model, a data‐driven model, and the proposed PINN model was evaluated by comparing their predictions against measured fatigue life data. The findings demonstrate that the PINN model significantly enhances prediction accuracy, with its fatigue life estimates consistently falling within 1.5 times the measured values.

Service life estimation, failure mechanisms, and specifications of galvanic anodes for corroding reinforced concrete structures

Service life estimation, failure mechanisms, and specifications of galvanic anodes for corroding reinforced concrete structures

Battery Remaining Useful Life Estimation based on Particle Swarm Optimization-Neural Network

Determining the Remaining Useful Life (RUL) of a battery is essential for several purposes, including proactive maintenance planning, optimizing resource allocation, preventing unforeseen failures, improving safety, extending battery lifespan, and achieving accurate cost savings. Concerning that matter, this study proposed hybrid Particle Swarm Optimization–Neural Network (PSO-NN) for estimating battery RUL. In the evaluation of the proposed method, the effectiveness is assessed using the metrics of Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). The dataset employed for this investigation comprises eight input parameters and one output variable, representing the battery RUL. In conducting an analysis, the performance of the PSO-NN model is compared with hybrid NN with Cultural Algorithm (CA-NN) and Harmony Search Algorithm (HSA-NN), as well as the standalone Autoregressive Integrated Moving Average (ARIMA). Upon examination of the findings, it becomes evident that the PSO-NN model outperforms the alternatives with an MAE of 2.7708 and an RMSE of 4.3468, significantly lower than HSA-NN (MAE: 22.0583, RMSE: 34.5154), CA-NN (MAE: 9.1189, RMSE: 22.4646), and ARIMA (MAE: 494.6275, RMSE: 584.3098). The PSO-NN also achieves the lowest maximum error of 104.7381 compared to 490.3125 for HSA-NN, 827.0163 for CA-NN, and 1,160.0000 for ARIMA. Additionally, the low two-tail probability values (P(T≤t)), all below the significance level of 0.05, indicate that the differences between PSO-NN and the other methods (HSA-NN, CA-NN, and ARIMA) are statistically significant. These results highlight the superior accuracy and robustness of the PSO-NN model in predicting battery RUL. This study contributes to the field by presenting the PSO-NN as a highly effective tool for accurate battery RUL estimation, as evidenced by its superior performance over alternative methods.

An efficient deep learning prognostic model for remaining useful life estimation of high speed CNC milling machine cutters

CNC machines are engaged in numerous industries, including critical ones like the aerospace, automotive, and military sectors, among others. Sensor data are time-series that may suffer from complex interconnections between variables and dynamic features. Long Short Term Memory LSTM excels in dynamic feature extraction, and Autoencoder AE has great capabilities in nonlinear deep knowledge of time-series data variables. In this work, we propose a model for tool wear prediction of CNC milling machine cutters as a type of time-series data taking advantage of the LSTM and AE capabilities. The framework consists of many steps, including extracting multi-domain features and a correlation analysis to select the most correlated features to the tool wear. New features are added, such as entropy and interquartile range IQR, which proved to be highly correlated to the cutter tool wear. An LSTM`-AE model is then trained, validated, and tested on this feature map to predict the target tool wear value. The model is provided with degradation or Run-To-Failure data for CNC machine cutters, the PHM10 dataset, to predict the tool wear values. The predicted tool wear value is compared against the wear curve to estimate RUL values. The predicted RUL values mostly underestimate the real values, which helps schedule for maintenance or equipment replacement before failure. The experimental results show that the proposed framework outperforms state-of-the-art DL methods in tool wear prediction accuracy approaching %98, as well as an enhancement of MAE and RMSE in the test set by reaching 2.6 ± 0.3222E-3 and 3.1 ± 0.6146 E-3, respectively.

Morphological analysis and Shelf life estimation of Functional baked products (wheat base) enrich by Fox nut and Palm Date.

This study aims to produce and standardise baked items that have been enhanced with Fox nut (Makhana) and Palm Date by evaluating their Morphological analysis and Shelf life estimation . The Morphological characteristics of the biscuits and muffins were analysed by scanning electron microscopy (SEM). The SEM images were used to study surface morphology and microbial growth on the sample surface. The elemental composition of the food products was analysed through SEM imaging. The shelf-life of the samples were evaluated by assessing the shelf life of the products. For shelf life analysis agar plate were used and the created product’s business values were thus determined through it.

Structural analysis and fatigue prediction of harrow tines used in Canadian prairies

The Canadian prairies are renowned for their substantial agricultural contributions to the global food market. Harrow tines are indispensable in farming equipment, especially for soil preparation and weed control before planting crops. During operation, these tines are exposed to repetitive cyclic loading, which eventually causes fatigue failure. Commercially available three different harrow tines named 0.562HT, 0.625HT, and 0.500HT undergo an experimental fatigue evaluation and are validated through Finite Element Analysis (FEA). Fatigue life estimation for different deflections under various real-field deflections was carried out where 0.562HT showed groundbreaking life compared with others. The study results showed that the fatigue life is highly dependent on geometry, number of coils, pitch angle, leg length, and coil diameter. The 0.354HT model, developed to investigate the effect of wire diameter, closely resembles the 0.500HT model. The harrowing ability of the four different harrow tine models against identical deflections has been analyzed. Experimental fractured surfaces went through morphological investigation. This research has an impeccable impact on prairies’ agricultural acceleration by saving time and mitigating unpredictable fatigue failure often faced by farmers. Even the observed failure phenomena can serve as motivation to develop more reliable and durable harrow tines, which could increase agricultural efficiency.

Data-driven AI for the automated classification of the isothermal heat-treated thermal barrier coatings using pulsed infrared thermography

Abstract Development of reliable age prediction models are crucial in monitoring the formation of oxide layer and degradation of TBC at regular intervals. This study proposes an automated classification of isothermal heat-treated TBC samples using temperature data, which helps in predicting the TBC life and monitoring the TBC degradation. TBC-coated samples are isothermal heat-treated at 1000 °C, and the initial growth of thermally grown oxide is monitored using a non-destructive thermal imaging technique. The proposed study integrates data-driven AI (DAI) models and feature extraction techniques to interpret complex thermal patterns measured from the TBC coating surface. The performance of the proposed classification framework is tested using deep learning and classical machine learning models with different types and window sizes of input data. Input data used for validation are raw experiment data, logarithmic of experiment data, polynomial fit data, and thermal signal reconstruction fit coefficients. The maximum classification performance is obtained with gated recurrent unit with accuracy and F1-score of 89.2% and 89.0%, respectively with raw temperature data as input of window 300. The study demonstrates that the proposed DAI approach effectively predicts the age of thermal barrier coatings under isothermal heat-treatment conditions by correlating the thermal response with coating degradation.

A Comprehensive Review of Remaining Useful Life Estimation Approaches for Rotating Machinery

This review paper comprehensively analyzes the prognosis of rotating machines (RMs), focusing on mechanical-flaw and remaining-useful-life (RUL) estimation in industrial and renewable energy applications. It introduces common mechanical faults in rotating machinery, their causes, and their potential impacts on RM performance and longevity, particularly in wind, wave, and tidal energy systems, where reliability is crucial. The study outlines the primary procedures for RUL estimation, including data acquisition, health indicator (HI) construction, failure threshold (FT) determination, RUL estimation approaches, and evaluation metrics, through a detailed review of published work from the past six years. A detailed investigation of HI design using mechanical-signal-based, model-based, and artificial intelligence (AI)-based techniques is presented, emphasizing their relevance to condition monitoring and fault detection in offshore and hybrid renewable energy systems. The paper thoroughly explores the use of physics-based, data-driven, and hybrid models for prognosis. Additionally, the review delves into the application of advanced methods such as transfer learning and physics-informed neural networks for RUL estimation. The advantages and disadvantages of each method are discussed in detail, providing a foundation for optimizing condition-monitoring strategies. Finally, the paper identifies open challenges in prognostics of RMs and concludes with critical suggestions for future research to enhance the reliability of these technologies.

Using Explainable Artificial Intelligence to Interpret Remaining Useful Life Estimation with Gated Recurrent Unit

In engineering, prognostics can be defined as the estimation of the remaining useful life of a system given current and past health conditions. This field has drawn attention from research, industry, and government as this kind of technology can help improve efficiency and lower the costs of maintenance in a variety of technical applications. An approach to prognostics that has gained increasing attention is the use of data-driven methods. These methods typically use pattern recognition and machine learning to estimate the residual life of equipment based on historical data. Despite their promising results, a major disadvantage is that it is difficult to interpret this kind of methodologies, that is, to understand why a certain prediction of remaining useful life was made at a certain point in time. Nevertheless, the interpretability of these models could facilitate the use of data-driven prognostics in different domains such as aeronautics, manufacturing, and energy, areas where certification is critical. To help address this issue, we use Local Interpretable Model-agnostic Explanations (LIME) from the field of eXplainable Artificial Intelligence (XAI) to analyze the prognostics of a Gated Recurrent Unit (GRU) on the C-MAPSS data. We select the GRU as this is a deep learning model that a) has an explicit temporal dimension and b) has shown promising results in the field of prognostics and c) is of simplified nature compared to other recurrent networks. Our results suggest that it is possible to infer the feature importance for the GRU both globally (for the entire model) and locally (for a given RUL prediction) with LIME.

A Review of Fatigue Failure and Life Estimation Models: From Classical Methods to Innovative Approaches

This review paper encompasses a comprehensive exploration of fatigue failure and fatigue life estimation techniques which spans from the classical methods to new and innovative approaches. The paper looks into the limitations and advancements of these techniques and highlights their respective strengths and areas for improvement. Some of the models such as artificial neural networks and genetic algorithms exhibit clear advantages in terms of processing speed, accuracy, and adaptability to diverse materials and loading scenarios. For instance, in estimating fatigue life under multiaxial loading, the stress scale factor model emerges as a viable alternative to the critical plane-based approach, as this technique offers superior efficiency under both constant and variable amplitude loadings. Additionally, optimization algorithms such as artificial neural networks and genetic algorithms show promising potential in efficiently estimating fatigue life due to their rapid computational capabilities. Despite the notable successes achieved by these techniques, none of them can be ascribed as a universal model capable of accurately estimating the fatigue life of all materials across diverse operating conditions as each of the techniques possesses its unique strengths and weaknesses, thus, necessitating the study for a better understanding of their applicability. Hence, this paper serves as a valuable compilation of various fatigue analysis techniques, targeted at paving the way towards the development of a universal model capable of handling different materials and loading conditions.

An improved constitutive model for rapid fatigue properties evaluation based on fatigue damage entropy

A constitutive model, which reflects the non-linear response association between microstructural motion and thermodynamic entropy production, is improved in this study. Two critical stress amplitudes associated with two microstructural movement mechanisms are considered in the improved constitutive model. The determination procedures for the parameters of the presented model are developed. Entropy generation data from three materials computed by two calculation methodologies, collected from the experiment and literature, are used to validate the improved model. Subsequently, a rapid fatigue life estimation method is proposed by using the accumulated entropy corresponding to fatigue damage, i.e. FFE, related to irreversible inelastic microstructural motion. Fatigue tests of welded joints fabricated by Q310NQL2 and Q345NQR2 steels, Q235 steel specimens, as well as experimental data, stainless steel specimens, collected from the literature, are employed to determine the values of the parameters of the developed model. The model is then used to forecast the S–N curve of butt joints with a 50% survival probability, and on this basis, the S–N curve with a certain confidence level is well estimated by the improved statistical method. This enhanced model may offer a fast forecast of the P–S–N curve at a certain confidence level within a limited set of tested data ranges.

CTNet: Improving the non-stationary predictive ability of remaining useful life of aero-engine under multiple time-varying operating conditions

Remaining useful life (RUL) estimation has been widely studied in prognostics and health management. Multiple time-varying operating conditions explicitly influence the measured performance parameters of the aero-engine, which results in non-stationarity and impedes the predictive ability of deep learning models. Previous data-driven studies primarily ignore the causality between operating condition descriptors and measured performance parameters, which is inconsistent with practical aero-engine engineering applications. To address this issue, we propose a causality Transformer network (CTNet), which improves the prediction stability of non-stationary series under multiple operating conditions. First, a novel graph structure is used to capture the connectivity relationship between operating condition descriptors and measured sensor nodes. Then the causality attention is proposed to inject additional causality information into the self-attention module without affecting the similarity computations of query and key values within the window. The causality attention can generate distinguishable attention for operating conditions, which properly release the predictive potential for non-stationary series. Extensive experiments are performed on public datasets (CMAPSS, N-CMAPSS), showing that CTNet outperforms existing state-of-the-art methods. We have also conducted experiments on the real-world quick access recorder (QAR) data, which validates the performance of the proposed model in perceiving time-varying operating conditions.

Crack Propagation Tests for Load Sequences Developed Using Different Flight Parameters of a Trainer Aircraft

Abstract Military aircraft are subjected to highly variable and unpredictable loads due to diverse mission profiles, armament configurations, and individual piloting styles. This variability complicates the definition of precise load spectra, particularly in cases where data loss occurs due to Flight Data Recorder (FDR) malfunctions or data mishandling. This paper investigates the use of different flight parameters, such as load factor (nz ), barometric height (Hb ), and horizontal velocity (Vp ), to define load sequences for the PZL-130 “Orlik” TC-II military trainer aircraft. These sequences were then used to evaluate crack propagation using Compact Tension (CT) specimens. The results show that the incorporation of additional flight parameters improves the accuracy of crack propagation predictions when compared to direct strain measurements. This study highlights the potential of using available flight data to develop reliable load spectra for fatigue life estimation in military aircraft, even when direct load measurements are not financially feasible.

Prediction of live weight from body measurements using stepwise regresion models in Karacabey Merino lambs

Objective: The aim of this study is to determine regression models that can be used to estimate live weight from body measurements in Karacabey Merino lambs of different ages(6th, 8th, and 12th months).. Material-Method: The animal material for the study consisted of 200 Karacabey merino lambs. Some body measurements were taken from all lambs and live weights were also weighed. For live weight prediction equations with multiple linear regression analysis using some measurements according to age groups, stepwise multiple regression procedure was used in SAS (1999). DUNCAN test, one of the tests for multiple comparisons, was used to show the differences between groups. Result: The least squares means for body length (BL), withers height (HW), back height (BH), rump height (RH), breast depth (CD), breast width (CW), rump width (RW), and live weight (LW) were 71.28 cm, 69.91 cm, 70.50 cm, 71.57 cm, 30.05 cm, 87.25 cm, 21.50 cm, 23.32 cm, and 51.05 kg, respectively. It is noteworthy that the live weight estimation models for three different age groups using stepwise regression analysis(second, third, and fourth models) can be recommended for the 6th (R2:0.82), 8th (R2:0.71), and 12th (R2:0.79) months of life. The variables that can be used in the equations to estimate body weight for this breed, at these ages are HW, CW, RW, CG, CD, and BL. Conclusion: Finally, it has been demonstrated that the live weights of Karacabey merino lambs can be estimated with high accuracy using the stepwise regression method based on body measurements.

Improving turbulence modeling for gas turbine blades: A novel approach to address flow transition and stagnation point anomalies

Accurate prediction of temperature and Heat Transfer Coefficient (HTC) distributions over gas turbine blades is crucial for the design process and life assessment of these components. Numerical studies of flow over gas turbine blades face significant challenges in accurately simulating two complex phenomena: (1) the transition of flow from laminar to turbulent, and (2) stagnation point flow at the leading edge. Many turbulence models tend to overpredict the temperature on turbine blades, leading to incorrect identification of hot-spot regions and, consequently, erroneous estimations of blade life. This paper investigates the performance of various turbulence models in simulating flow and heat transfer over gas turbine vanes. The study includes three full turbulence models, i.e., Spalart-Allmaras (SA), Shear Stress Transport k−ω (SST-kw), and v2−f (V2F), as well as two transitional models, i.e., Transition SST (Trans-SST) and k−kL−ω (k-kl-w). Simulation results indicate that the v2−f, Trans-SST, and k−kL−ω models can detect flow transition. However, the transition length and onset location predicted by the Trans-SST and k−kL−ω models do not align with experimental data. Conversely, the v2−f model suffers from over-predictions at the leading edge due to stagnation point anomaly. To address these issues and due to capacities of the V2F model, this study proposes two modifications to enhance the performance of the V2F model. First, the production term of turbulent kinetic energy is redefined to mitigate the stagnation point anomaly. Second, the model is recalibrated to improve the prediction of flow transition. The new model, named the Production Modified V2F (PMV2F) model, shows promising results in predicting temperature and heat transfer coefficients.

A comment on manuscript Comparison of machine learning algorithms and multiple linear regression for live weight estimation of Akkaraman lambs.

A comment on manuscript Comparison of machine learning algorithms and multiple linear regression for live weight estimation of Akkaraman lambs.

Stress fracture of bone under physiological multiaxial cyclic loading: Activity-based predictive models

While it is known that excessive accumulation of fatigue damage from daily activities contributes to fracture, a model of bone failure under physiologically relevant multiaxial cyclic loading needs to be developed in order to develop effective management strategies for stress or fatigue fractures. The role of strain-induced damage from repetitive loading is a strong candidate for such a model, as cycles of mechanical loading leading to failure can be measured directly. However, this approach has been limited by the restrictions of uniaxial loading models, which often overestimates the fatigue life of bone and suggests that bone will only break well beyond the realistic limits of exercise. To address this gap and develop a physiologically relevant model, our study leverages the power of four commonly used engineering failure criteria as a model for multiaxial loading using a cohort of human tibiae from cadaveric donors (age range 21–85 years old). Four failure criteria (Von Mises, Tsai-Wu, Findley critical plane, and maximum shear strain) were found to be effective in vitro models of tibial fracture when age groups of donors were combined (r2 > 0.84) and stratified (younger: 21–52-years-old versus older: 57–85-years-old) (r2 > 0.83) (p < 0.001). Each failure criterion displayed distinctly lower fatigue curves for the older age group. The maximum shear strain model was used to determine the efficacy of this approach to predict fatigue fractures in humans using published in vivo data from human volunteers. Consistent with in vivo observations in general population, the model demonstrated failure at 5000 to 200,000 loading cycles depending on activities such as jumping, sprinting, and walking, with a 3-fold reduction of fatigue life in older donors. These findings dramatically improve estimates of fatigue life under repetitive loading and demonstrate how age-related changes in bone significantly increase its propensity for fatigue-induced fractures.

The influence of storage conditions on hygiene condition and eicosapentaenoic acid oxidation in Nannochloropsis algae for sustainable food supply.

Nannochloropsis algae contain approximately 20% polyunsaturated fatty acids (PUFA) and hold significant potential for high-quality eicosapentaenoic acid (EPA) food industrialization. However, EPA in Nannochloropsis sp. is prone to oxidation, and microbial growth is a critical factor affecting the shelf life of fresh food. Storage composition and temperature are primary factors influencing microbial growth, yet these aspects are not fully understood. This study investigates the effects of temperature and encapsulation on EPA content in nano-products over time. Nano-powder and nanobeads derived from Nannochloropsis sp. served as raw materials. Additionally, changes in aerobic plate counts and coliform groups were monitored. The results indicated that nanobeads, due to their more complex processing and less mature packaging, were more susceptible to coliform contamination compared to nano-powder. In terms of EPA stability, nanobeads exhibited a longer storage life than nano-powder. The oxidation rate of both nano-powder and nanobeads was faster at 37 °C than at 25 °C. These findings can inform general shelf life estimation, rapid detection of total lipid content in nano-products and macro extraction of nano-oil. Moreover, they have significant implications for delaying EPA oxidation in nano-products and improving hygienic quality control for microbial detection. © 2024 Society of Chemical Industry.

Estimates of actual and potential lives saved in the United States from the use of COVID-19 convalescent plasma

In the Spring of 2020, the United States of America (USA) deployed COVID-19 convalescent plasma (CCP) to treat hospitalized patients. Over 500,000 patients were treated with CCP during the first year of the pandemic. In this study, we estimated the number of actual inpatient lives saved by CCP treatment in the United States of America based on CCP weekly use, weekly national mortality data, and CCP mortality reduction data from meta-analyses of randomized controlled trials and real-world data. We also estimate the potential number of lives saved if CCP had been deployed for 100% of hospitalized patients or used in 15 to 75% of outpatients. Depending on the assumptions modeled in stratified analyses, we estimated that CCP saved between 16,476 and 66,296 lives. The CCP ideal use might have saved as many as 234,869 lives and prevented 1,136,133 hospitalizations. CCP deployment was a successful strategy for ameliorating the impact of the COVID-19 pandemic in the USA. This experience has important implications for convalescent plasma use in future infectious disease emergencies.

Guaranteed estimates of the gamma percent residual life of data storage equipment

Guaranteed estimates of the gamma percent residual life of data storage equipment