Deterioration Model Research Articles

A data-based and physics-informed Bayesian updating method for deterioration models of RC structures in marine environment

Deterioration models of reinforced concrete (RC) in marine environment, to be applied to existing structures, usually need to be calibrated with long-term in-situ data. The Bayesian model updating provides a framework to incorporate measured data into existing models to make them more realistic. The measured chloride concentrations of concrete at different depths are related to each other through the Fick’s second law, but they are treated as independent in existing updating methods, which affects the accuracy of model updating. To solve this issue, this paper proposes a data-based and physics-informed (DBPI) likelihood function to incorporate the physical law behind the measured data into Bayesian updating framework, whose validity is first confirmed through numerical examples, and then it is applied to the durability assessment of an existing wharf structure in marine environment. The parameters involved in the chloride ingress model and the critical chloride concentration model are updated using the data from durability inspections. The durability performance of the structure is then assessed using the updated models, which is consistent with the actual surface deterioration observed in the two inspections. Discussion of the updated results reveals that ignoring the physical law behind the measured data may result in incorrect inferences of the chloride ingress model and multi-mode distribution of the updated parameters, which is solved by using the proposed DBPI likelihood function, and the accuracy of Bayesian updating is significantly improved.

Development of predictive model for the neurological deterioration among mild traumatic brain injury patients using machine learning algorithms.

Mild traumatic brain injury (mTBI) comprises a majority of traumatic brain injury (TBI) cases. While some mTBI would suffer neurological deterioration (ND) and therefore have poorer prognosis. This study was designed to develop the predictive model for the ND among mTBI using machine learning algorithms. mTBI patients recorded in the Medical Information Mart for Intensive Care-III were selected for the study. The ND was defined as a drop of Glasgow Coma Scale ≥ 2 within the first 7day after admission. Eight machine learning algorithms were trained and validated with 5-fold cross validation including extreme gradient boosting, logistic regression, light gradient boosting machine, random forest, adaptive boosting, decision tree, complement naïve Bayes, and support vector machine. The value of eight machine learning algorithms was compared by the area under the receiver operating characteristic curve (AUC). 361 mTBI patients suffered the ND with the incidence of 30.7%. The ND group had higher 30-day mortality (p = 0.001). In the training cohort of mTBI patients, the random forest performed the best on predicting the ND with the AUC of 1.000. The XGBoost and AdaBoost had an AUC of 0.827 and 0.815, respectively. The logistic regression performed the best on predicting the ND in the validation cohort with the AUC of 0.741. The XGBoost, random forest and AdaBoost had an AUC of 0.729, 0.735, 0.736 in the validation cohort, respectively. After adjusting confounding effects, the multivariate logistic regression found only two independent risk factors for the ND including Sequential Organ Failure Assessment (SOFA) (p < 0.001) and hypertension (p = 0.001). The logistic regression predictive model composed of SOFA and hypertension had an AUC of 0.741. SOFA score and complicated hypertension are two independent risk factors for the neurological deterioration among mTBI patients. The logistic regression predictive model incorporating SOFA and hypertension is helpful to identify mTBI patients with the high risk of ND.

Insight into the dynamic tensile behavior of deep anisotropic shale reservoir after water-based working fluid cooling

During deep shale gas production, flowing water-based working fluid inevitably cools shale reservoirs around boreholes and some fractures, and possible extraction methods induce dynamic stresses. To understand the dynamic tensile behavior of deep anisotropic shale reservoir after water-based working fluid cooling, a split Hopkinson pressure bar was used for performing the dynamic Brazilian tests on shale samples with bedding angles of 0°, 30°, 45°, 60° and 90° after reservoir temperature realization (25–200 °C) and water cooling. The results illustrate that dynamic tensile strength of shale samples decreases gradually as reservoir temperature increases under the loading rates 100–1000 GPa/s. From room temperature to 200 °C the most strength deterioration appears on samples with the bedding angle of 90°. A dynamic tensile strength deterioration model for deep shale reservoirs after water-based working fluid cooling is proposed considering the influence of loading rate and bedding angle. Geometrical trajectories of the main failure cracks are separated into three types, i.e., fully central tensile failure, tensile-shear failure and fully shear failure (sliding of bedding planes). For samples with bedding angles of 30°, 45° and 60°, increasing reservoir temperature encourages tensile failure to change into shear failure. The roles that bedding planes play in interacting with failure crack growth are summarized as IP mode (intersecting propagation), TP mode (turning propagation) and PP mode (promoting propagation). Anisotropic dynamic tensile strength responses are systematically discussed by using thermal stress simulation in ABAQUS, microstructure analyses, crack interaction conditions and the one-dimensional stress wave propagation theory. Based on experimental observations, field implications in borehole stability and fracturing of deep shale reservoirs are proposed under medium and high loading rates. This work is instrumental in providing valuable information and technology assistance for real deep shale gas production projects.

Influence of the System Downtime Cost Rate on the Performance and Robustness of Periodic Inspection and Replacement and Quantitative Inspection and Replacement Maintenance Strategies Using Monte Carlo Method

Abstract This essay analyzes the crucial role of maintenance in production and service-oriented enterprises, highlighting the necessity for integrated viewpoints in contemporary corporate management. Focusing on time-based maintenance (TBM) and condition-based maintenance (CBM) techniques, the study provides a novel criteria and applies Monte Carlo simulation for assessment. The purpose is to discover ideal values for the system downtime cost rate, establishing a balance between performance and resilience. The organized parts include deterioration and failure models, maintenance assumptions, and cost models, finishing with a summary of noteworthy results and recommendations for further investigations. The study brings significant insights into the subject of maintenance strategies and analyzes the influence of the system downtime cost rate on the performance and robustness of condition-based maintenance strategies for a system with more or less stable behavior.

A risk prediction model for unexplained early neurological deterioration following intravenous thrombolysis

Background and objectivesEarly neurological deterioration (END) post-intravenous thrombolysis significantly impacts the long-term prognosis of stroke patients. This study aimed to establish a rapid risk prediction model for unexplained END following intravenous thrombolysis.MethodsThis prospective study consecutively enrolled patients with acute ischemic stroke treated with recombinant tissue plasminogen activator intravenous thrombolysis at the Department of Neurology, Third People’s Hospital of Hubei Province, and Yangluo Hospital District between June 2019 and December 2022. Unexplained END was defined as an increase of ≥ 4 points in the National Institutes of Health Stroke Scale (NIHSS) score between admission and 24 h. A nomogram was developed and assessed by calculating the area under the receiver operating characteristic curve (AUC-ROC). The calibration was assessed using the Hosmer–Lemeshow test.ResultsA total of 211 patients (130 males and 110 patients aged < 65 years) were included, with 66 experiencing unexplained END. Multivariate logistic regression analysis identified large arterial disease, transient ischemic attack, high blood glucose, high neutrophil/lymphocyte ratio, important perforator disease, and low the Alberta Stroke Program Early CT scores (APSECTS) as independent risk factors for END and established the nomogram used above indicators. The nomogram showed an AUC-ROC of 0.809 (95% CI 0.7429–0.8751), with a specificity of 0.862 and sensitivity of 0.712. The positive predictive value was 0.702, and the negative predictive value was 0.868. The Hosmer–Lemeshow goodness-of-fit test (χ2 = 1.069, P = 0.169) indicated acceptable model calibration.ConclusionThis study successfully established a risk prediction model for END following intravenous thrombolysis and the model demonstrates good stability and predictive capacity. Further validation through a prospective, multicenter study is necessary.

Force-displacement relation for lumped plasticity model of compact square concrete-filled steel tube columns

Integration of steel and concrete benefits in square concrete-filled tube columns (SCFTs) makes them be utilized extensively worldwide. To evaluate the seismic behavior of special moment frames having SCFT columns, an accurate macro-modeling tool with little complexity is necessary. Although the fiber section can consider both linear and nonlinear behavior of SCFT, it fails to allow for deterioration, which is vital in assessing a seismic resisting system. This study proposes a new deterioration tool based on the Ibarra-Krawinkler model for compact SCFT columns using artificial neural networks (ANNs) through numerical simulation. Initially, 96 specimens with variations in geometry, material, and axial loading conditions were simulated in ABAQUS and then were analyzed using displacement control loading protocol to obtain hysteretic curves, which were used to prepare the data sets for training, testing, and validating the neural networks. Finally, the performance of ANN models was evaluated by statistical relations such as regression and mean square error. Through FEMA 356 and Ibarra-Krawinkler approaches, parameters defining linear and nonlinear phases of SCFTs behavior were derived. By employing efficiently trained neural networks, equations predicting the parameters of the deterioration model were established, and the obtained results show the accuracy and efficiency of the proposed model.

A Probability-Based Likelihood Function for Bayesian Updating of a Bridge Condition Deterioration Model

A Probability-Based Likelihood Function for Bayesian Updating of a Bridge Condition Deterioration Model

Modelling bridge deterioration using long short-term memory neural networks: a deep learning-based approach

PurposeBridge deterioration is a critical risk to public safety, which mandates regular inspection and maintenance to ensure sustainable transport services. Many models have been developed to aid in understanding deterioration patterns and in planning maintenance actions and fund allocation. This study aims at developing a deep-learning model to predict the deterioration of concrete bridge decks.Design/methodology/approachThree long short-term memory (LSTM) models are formulated to predict the condition rating of bridge decks, namely vanilla LSTM (vLSTM), stacked LSTM (sLSTM), and convolutional neural networks combined with LSTM (CNN-LSTM). The models are developed by utilising the National Bridge Inventory (NBI) datasets spanning from 2001 to 2019 to predict the deck condition ratings in 2021.FindingsResults reveal that all three models have accuracies of 90% and above, with mean squared errors (MSE) between 0.81 and 0.103. Moreover, CNN-LSTM has the best performance, achieving an accuracy of 93%, coefficient of correlation of 0.91, R2 value of 0.83, and MSE of 0.081.Research limitations/implicationsThe study used the NBI bridge inventory databases to develop the bridge deterioration models. Future studies can extend the model to other bridge databases and other applications in the construction industry.Originality/valueThis study provides a detailed and extensive data cleansing process to address the shortcomings in the NBI database. This research presents a framework for implementing artificial intelligence-based models to enhance maintenance planning and a guideline for utilising the NBI or other bridge inventory databases to develop accurate bridge deterioration models. Future studies can extend the model to other bridge databases and other applications in the construction industry.

Incorporating informatively collected laboratory data from EHR in clinical prediction models

BackgroundElectronic Health Records (EHR) are widely used to develop clinical prediction models (CPMs). However, one of the challenges is that there is often a degree of informative missing data. For example, laboratory measures are typically taken when a clinician is concerned that there is a need. When data are the so-called Not Missing at Random (NMAR), analytic strategies based on other missingness mechanisms are inappropriate. In this work, we seek to compare the impact of different strategies for handling missing data on CPMs performance.MethodsWe considered a predictive model for rapid inpatient deterioration as an exemplar implementation. This model incorporated twelve laboratory measures with varying levels of missingness. Five labs had missingness rate levels around 50%, and the other seven had missingness levels around 90%. We included them based on the belief that their missingness status can be highly informational for the prediction. In our study, we explicitly compared the various missing data strategies: mean imputation, normal-value imputation, conditional imputation, categorical encoding, and missingness embeddings. Some of these were also combined with the last observation carried forward (LOCF). We implemented logistic LASSO regression, multilayer perceptron (MLP), and long short-term memory (LSTM) models as the downstream classifiers. We compared the AUROC of testing data and used bootstrapping to construct 95% confidence intervals.ResultsWe had 105,198 inpatient encounters, with 4.7% having experienced the deterioration outcome of interest. LSTM models generally outperformed other cross-sectional models, where embedding approaches and categorical encoding yielded the best results. For the cross-sectional models, normal-value imputation with LOCF generated the best results.ConclusionStrategies that accounted for the possibility of NMAR missing data yielded better model performance than those did not. The embedding method had an advantage as it did not require prior clinical knowledge. Using LOCF could enhance the performance of cross-sectional models but have countereffects in LSTM models.

2D and 3D numerical modelling for preliminary assessment of long-term deterioration in Irish glacial till geotechnical slopes

ABSTRACT Long-term geotechnical slope deterioration, influenced by weathering and meteorological factors, presents stability challenges to infrastructure. Wetting and drying cycles lead to pore water pressure variations, causing deformations and slope failure. Studies on glacial tills which investigate deterioration in geotechnical slopes focus on variables like pore water pressure, soil water retention, compaction, freeze–thaw cycles and cracking. This research conducts a preliminary assessment of an Irish glacial till-cut slope, establishing a data-driven foundation for long-term slope behaviour studies. Data analysis, geospatial modelling and numerical simulations were performed on a cut slope in Castleblayney (Ireland), considering short-term/undrained and long-term/drained conditions. FLAC/Slope and Scoops3D were used for 2D and 3D slope stability analyses, applying the First-Order Second Moment (FOSM) probabilistic approach to assess how minor soil property changes affect slope stability, including long-term deterioration scenarios. The study underscores the importance of precise instrument placement within Irish glacial till geotechnical cut slopes, particularly at the uppermost part where shallow and deep failures coincide under long-term and short-term scenarios. This informs strategic instrument positioning for accurate slope deterioration investigations. This research lays the groundwork for understanding mechanisms driving geotechnical slope deterioration and provides insights for future studies on geotechnical asset deterioration models in Irish glacial tills.

A realist evaluation protocol: assessing the effectiveness of a rapid response team model for mental state deterioration in acute hospitals.

Mental state deterioration poses significant challenges in healthcare, impacting patients and providers. Symptoms like confusion and agitation can lead to prolonged hospital stays, increased costs, and the use of restrictive interventions. Despite its prevalence, there's a lack of consensus on effective practices for managing mental state deterioration in acute hospital settings. To address this gap, a rapid response team model has been proposed as a potential intervention, aiming to provide early identification and targeted interventions. Based on realist evaluation steps, first, initial program theories are formulated to understand the logic behind the intervention. Second, literature synthesis identifies empirical evidence on contexts, mechanisms, and outcomes elements, refining initial theories. During the third step, data will be collected using qualitative methods such as field observations and interviews, as well as quantitative methods such as surveys of the staff, audits of electronic medical records, and analysis of incident records of mental state deterioration. Analysing this data informs configurations of contexts, mechanisms, and outcomes. In the fifth step, the configurations are synthesised, presenting refined, evidence-informed program theories. This study addresses the knowledge gap by evaluating the rapid response model's effectiveness in managing mental state deterioration in acute hospital settings. Realist principles guide the exploration of causal mechanisms and their interaction with specific implementation contexts. The objective is to identify what works, for whom, and under what circumstances, aiming to manage deterioration, reduce restrictive interventions, and enhance the experience for patients and staff by implementing a proactive model of care. The findings contribute to evidence-based approaches for managing mental state deterioration in hospital settings, informing policy and practice in this crucial area of healthcare.

Multistage supply chain inventory model for controllable deterioration and imperfect production with carbon emissions regulations under Stackelberg game approach

Multistage supply chain inventory model for controllable deterioration and imperfect production with carbon emissions regulations under Stackelberg game approach

A hierarchical Bayesian approach for parameter identification in structural deterioration models using probabilistic surrogate models

Most structural systems currently in operation are subjected to potentially multiple deterioration processes, for which different models exist to describe their evolution in time. The quantities of interest (QoIs) involved in them are often directly unobservable. However, advances in Structural Health Monitoring (SHM) have enabled gathering structural response data which can be used to indirectly make inferences on unobservable (state) quantities through Bayesian inference. Obtaining updated estimates of deterioration model parameters, given observed data, enables them to be used to predict future health states of interest for the structure, which constitutes a core tenet of condition-based maintenance (CBM). Key to obtaining robust parameter estimates is accounting for different uncertain quantities involved in the model that transforms unobservable quantities to observable ones, which in a Bayesian context is achieved through the likelihood function. This work presents an offline, flexible hierarchical framework to tackle this problem that employs probabilistic reduced order models (ROMs) in the construction of the likelihood function, that enable marginalizing out these uncertain quantities. The approximate likelihood function is then used within a typical Markov Chain Monte Carlo (MCMC) setting for parameter estimation. The framework is demonstrated in applications related to deterioration processes common to ship structures.

A prediction model for prehospital clinical deterioration: The use of early warning scores.

Various prognosticative approaches to assist in recognizing clinical deterioration have been proposed. To date, early warning scores (EWSs) have been evaluated in hospital with limited research investigating their suitability in the prehospital setting. This study evaluated the predictive ability of established EWSs and other clinical factors for prehospital clinical deterioration. A retrospective cohort study investigating adult patients of all etiologies attended by Queensland Ambulance Service paramedics between January 1, 2018, and December 31, 2020, was conducted. With logistic regression, several models were developed to predict adverse event outcomes. The National Early Warning Score (NEWS), Modified Early Warning Score (MEWS), Queensland Adult Deterioration Detection System (Q-ADDS), and shock index were calculated from vital signs taken by paramedics. A total of 1,422,046 incidents met the inclusion criteria. NEWS, MEWS, and Q-ADDS were found to have comparably high predictive ability with area under the receiver operating characteristic curve (AUC-ROC) between 70% and 90%, whereas shock index had relatively low AUC-ROC. Sensitivity was lower than specificity for all models. Although established EWSs performed well when predicting adverse events, these scores require complex calculations requiring multiple vital signs that may not be suitable for the prehospital setting. This study found NEWS, MEWS, and Q-ADDS all performed well in the prehospital setting. Although a simple shock index is easier for paramedics to use in the prehospital environment, it did not perform comparably to established EWSs. Further research is required to develop suitably performing parsimonious solutions until established EWSs are integrated into technological solutions to be used by prehospital clinicians in real time.

Modeling deterioration and predicting remaining useful life using stochastic differential equations

The deterioration of engineering systems might reduce the system reliability and prompt maintenance operations that may disrupt the ability of the systems to provide regular service. Estimating the Remaining Useful Life (RUL) of the system requires an understanding of the deterioration processes acting on it. Recent formulations have shifted the focus of deterioration modeling from the system as a whole to the individual, time-varying state-variables that define the characteristics of the system. These state-dependent formulations depend on the selected models for the evolution of the state-variables over time. However, most available models rely on simplifying assumptions that disregard the true nature of the processes, either by discretizing the time domain or by assuming independence among the several processes acting on the system. This paper proposes using a system of Stochastic Differential Equations (SDEs) to model the state variables' evolution. The proposed formulation captures the continuous nature of the processes and accounts for the possible interactions among them. In addition, results from stochastic calculus can be used to facilitate the simulation of the processes and to obtain closed-form solutions for the distribution of the state variables over time and the RUL of the system. Moreover, the proposed SDEs can be calibrated based on observations of the state variables, should those be obtained via testing/monitoring or simulations. A procedure for calibration is introduced, and several numerical examples are investigated to highlight the different scenarios encountered in practice. Finally, the proposed SDE formulation is used to predict the RUL of lithium-ion batteries using actual Structural Health Monitoring data.

Water quality deterioration modeling in aged distribution mains: A case study in Addis Ababa, Ethiopia

Water quality deterioration modeling in aged distribution mains: A case study in Addis Ababa, Ethiopia

Leaching-induced deterioration of shear bonding strength and micro-Vickers hardness of the ITZ modified by micro-SiO2 and nano-SiO2

The interfacial transition zone (ITZ) serves as a critical juncture between aggregate and cement paste in concrete, particularly vulnerable to calcium leaching. This study investigates the impact of water-cement (w/c) ratio and micro-SiO2 and nano-SiO2 content on the deterioration of shear bonding strength and micro-Vickers hardness of the ITZ during leaching. Analysis of ITZ micro-structure and elemental composition is conducted using backscattering electron microscope and energy dispersive spectroscopy (BSEM/EDS), and a deterioration model for the shear bonding strength of the leached ITZ is established. Results indicate that during leaching, shear bonding strength and micro-Vickers hardness of the ITZ are approximately 28 % and 67 % of those of the cement paste, respectively. A linear relationship between the shear bonding strength of the ITZ and its micro-Vickers hardness is observed when employing the same type of admixture. Mechanical properties and leaching resistance of the ITZ diminish progressively with increasing w/c ratio. Conversely, they exhibit an initial enhancement followed by decline with increasing micro-SiO2 and nano-SiO2 contents, with optimal contents of 8 % and 2 %, respectively. Micro-SiO2 and nano-SiO2 are found to enhance long- and short-term leaching resistance of cement-based materials, respectively. Additionally, the shear bonding strength of the ITZ decreases linearly with increased degree of area leaching. These findings enhance our understanding of the deterioration behavior of the ITZ and provide an important foundation for studying the durability changes of concrete subjected to calcium leaching.

Experimental investigation into corrosion effect on buckling and low-cycle fatigue performance of high-strength steel bars

The reinforcement in marine RC structures will inevitably be corroded under long-time erosion of chloride ions, which will weaken steel mechanical properties and then structural seismic resistance. The new metallurgical technology is adopted for manufacturing high-strength steel bars (HSSB), but that may affect the corrosion resistance of steel bars at the same time. This paper experimentally investigates the effects of corrosion on monotonic and low-cycle fatigue properties of HSSB HTRB600 and normal strength steel bars (NSB) HRB400E. The HRB400E and HTRB600 steel bars were corroded to different corrosion rates by electrochemical accelerated corrosion technique. The monotonic tensile and compressive, as well as low-cycle fatigue tests of corroded steel bars were conducted to investigate the effects of corrosion on steel mechanical properties, of which corrosion levels (0–20% target corrosion mass loss), slenderness ratios (L/D=6, 8, 10, 12) and strain amplitudes (2%, 4%) are considered. Test results show that, the corrosion morphology of steel bars under electrochemical accelerated corrosion is basically consistent with that observed under natural corrosion. Compared with uncorroded HRB400E and HTRB600 steel bars, 20% corrosion mass loss leads to 38% and 35% decrease in tensile strength, as well as 33% and 28% reduction in buckling stress, respectively. The HTRB600 steel bars present slightly superior monotonic tensile and compressive corrosion resistance than HRB400E steel bars. Corrosion obviously decreases the low-cycle fatigue (LCF) life of steel bars, resulting in reductions of 44% and 36% in LCF life at 20% corrosion mass loss for HTRB600 and HRB400E steel with a L/D of 6, respectively. Moreover, the HTRB600 steel bars present more significant corrosion degradation in total hysteretic dissipated energy, compared with HRB400E steel bars. The combined effect of corrosion and inelastic buckling further exacerbates the deterioration of LCF performance of steel bars. The corresponding deterioration models are proposed to determine the LCF life and energy dissipation capacity of corroded steel bars.

An Engine Deterioration Model for Predicting Fuel Consumption Impact in a Regional Aircraft

A deterioration cycle model is presented, designed to consider the turbomachinery efficiency losses that are expected during real engine in-service operations. The cycle model was developed using information from practical experience found in the literature to account for both short- and long-term deterioration effects; the former occurring during the first flight cycles, the latter due to regular in-service operation. This paper highlights the importance of analyzing the inter-turbine temperature margin (ITTM) to track engine deterioration to determine the extent of an in-service engine life. The proposed model was used to assess the ITTM and fuel consumption impact in the CRJ-700 regional aircraft (powered by two CF34-8C5B1 engines) for three representative missions: short (0.4 h), average (1.4 h), and long (2.5 h), considering different levels of engine deterioration, from the new engine level up to fully deteriorated. The fuel consumption at the new engine level (zero deterioration) was validated against a real-time engine model embedded in a Level-D flight simulator, the so-called Virtual Research Flight Simulator located at the Laboratory of Applied Research in Active Control, Avionics, and AeroServoElasticity. The errors found in this validation for the trip mission fuel consumption in the short, average, and long missions were −3.6, +0.9, and +0.6%, respectively. The cycle model predictions suggest the ITTM for a new engine is 55.2 °C, whereas for a fully deteriorated engine, it is 26.4 °C. Finally, in terms of fuel consumption, the results presented here show that an average CF34-8C5B1 engine shows an increase in the cumulative fuel consumption of 2.25% during its life in service, which translates to a 4.5% impact in aircraft fuel consumption.

Real time conditioning monitoring of MOSFET using artificial neural network regression

The metal–oxide–semiconductor field-effect transistor (MOSFET) is a critical semiconductor device widely used in electrical and electronic systems. The performance of systems depends on the component’s reliability. More than 30% of failures of electronic and electrical systems are due to MOSFET failure. Industries are paying more apprehension towards the improvement of MOSFET reliability. Temperature stress is one of the key parameters to examine the reliability performance of semiconductor devices and to predict the lifetime of the components. This article provides a quick analysis of the MOSFET degradation models. The primary failure precursor metric that reflects the level of degradation is the MOSFET on-resistance R DS(on). In this paper, a linear, non-linear, and artificial neural network (ANN) deterioration model of MOSFETs is presented with the experimental data. The coefficient of determination (R-square), and root mean square error (RMSE) are used to compare the real data. Finally, it is demonstrated that the proposed model works well with experimental data. More than 500 data were trained for the proposed model. It can therefore predict the real-time conditioning monitoring of MOSFETs to increase the reliability of electrical systems.