Reliability Prediction Method Research Articles

Synchronization-based graph spatio-temporal attention network for seizure prediction

Epilepsy is a common neurological disorder in which abnormal brain waves propagate rapidly in the brain in the form of a graph network during seizures, and seizures are extremely sudden. So, designing accurate and reliable prediction methods can provide early warning for patients, which is crucial for improving their lives. In recent years, a large number of studies have been conducted using deep learning models on epileptic open electroencephalogram (EEG) datasets with good results, but due to individual differences there are still some subjects whose seizure features cannot be accurately captured and are more difficult to differentiate, with poor prediction results. Important time-varying information may be overlooked if only graph space features during seizures are considered. To address these issues, we propose a synchronization-based graph spatio-temporal attention network (SGSTAN). This model effectively leverages the intricate information embedded within EEG recordings through spatio-temporal correlations. Experimental results on public datasets demonstrate the efficacy of our approach. On the CHB-MIT dataset, our method achieves accuracy, specificity, and sensitivity scores of 98.2%, 98.07%, and 97.85%, respectively. In the case of challenging subjects that are difficult to classify, we achieved an outstanding average classification accuracy of 97.59%, surpassing the results of previous studies.

Deep Learning Approach in Seismology: Enhancing Earthquake Forecasting using K-Means Clustering and LSTM Networks

Located in the subduction zone of four tectonic plates, the high occurrence of seismic events is a severe threat in Indonesia. Mitigating the adverse effects of such disasters is essential to forecast the likelihood of future earthquakes. Consequently, developing a robust method of forecasting future earthquakes is critical to facilitate prevention and mitigation efforts. A reliable earthquake prediction method is necessary to reduce the after-effects to the greatest extent possible. This study utilises historical seismic and proposes innovative data pre-processing methods using K-means clustering to build a Long Short-Term Memory (LSTM) model for earthquake forecasting to overcome high-disparity locations. Four LSTM layers are embedded with adjusted fine-tuned network hyperparameters to enhance forecasting accuracy. The results attain 0.379816, 0.616292, and 0.414586 for Mean Square Error (MSE), Root MSE, and Mean Absolute Error, respectively, providing significant insights into earthquake prediction. In addition, predicted seismic occurrences are plotted on a map to display their geographic location within the specified research region. This research provides significant value in facilitating the efficient distribution of resources, such as evacuating residents impacted by earthquakes or reinforcing buildings and infrastructure, for emergency responders and policymakers.

HDN-DDI: a novel framework for predicting drug-drug interactions using hierarchical molecular graphs and enhanced dual-view representation learning

BackgroundDrug–drug interactions (DDIs) especially antagonistic ones present significant risks to patient safety, underscoring the urgent need for reliable prediction methods. Recently, substructure-based DDI prediction has garnered much attention due to the dominant influence of functional groups and substructures on drug properties. However, existing approaches face challenges regarding the insufficient interpretability of identified substructures and the isolation of chemical substructures.ResultsThis study introduces a novel framework for DDI prediction termed HDN-DDI. HDN-DDI integrates an explainable substructure extraction module to decompose drug molecules and represents them using innovative hierarchical molecular graphs, which effectively incorporates information from real chemical substructures and improves molecules encoding efficiency. Furthermore, the enhanced dual-view learning method inspired by the underlying mechanisms of DDIs enables HDN-DDI to comprehensively capture both hierarchical structure and interaction information. Experimental results demonstrate that HDN-DDI has achieved state-of-the-art performance with accuracies of 97.90% and 99.38% on the two widely-used datasets in the warm-start setting. Moreover, HDN-DDI exhibits substantial improvements in the cold-start setting with boosts of 4.96% in accuracy and 7.08% in F1 score on previously unseen drugs. Real-world applications further highlight HDN-DDI’s robust generalization capabilities towards newly approved drugs.ConclusionWith its accurate predictions and robust generalization across different settings, HDN-DDI shows promise for enhancing drug safety and efficacy. Future research will focus on refining decomposition rules as well as integrating external knowledge while preserving the model’s generalization capabilities.

Research on reliability prediction method of fuel regulator based on failure rate model

Research on reliability prediction method of fuel regulator based on failure rate model

Satellite-Driven Hydrological Modelling in Ungauged Moroccan bassins: Case study Ouzoud river

Predicting streamflow is vital for flash-flood early warning systems and managing water resources under climate change. However, limited streamflow observations restrict advanced prediction techniques to gauged basins, leaving most of the world's ungauged basins at a disadvantage. Developing reliable prediction methods for ungauged basins (PUB) is therefore essential. Over the past two decades, satellite-driven products, such as ERA5, have become crucial for enhancing precipitation and meteorological measurements, especially in complex terrains and changing climatic conditions. This study focuses on Morocco's arid and semi-arid regions, where water resource management is critical for agriculture, urbanization, and economic stability. Using the ERA5 dataset, which provides high-resolution atmospheric information, the study evaluates satellite-derived precipitation against ground measurements from the Sgatt station at Bernat River on daily timescales. Various statistical metrics assess ERA5's performance in representing daily precipitation and its integration into the GR4J-CemaNeige model for flow simulation. Results highlight the potential of ERA5 in improving rainfall representation and hydrological modelling in ungauged basins, verifying its effectiveness in simulating rainfall events compared to ground-based observations. This work underscores the importance of satellite-driven products for enhancing hydrological predictions and supporting water management in data-scarce regions.

Reliability sensitivity analysis of automotive disc brake with multiple failure modes correlation

The failure of the automotive braking system may lead to brake failure and even severe traffic accidents. Traditional single failure mode reliability analysis can no longer meet current design requirements, while the Gumbel Copula model can measure the correlation between different failure modes and evaluate the risk of failure combinations. Therefore, the model is adopted in this paper. However, in engineering practice, the reliability prediction methods for thermal fatigue and complex modal multiple failure modes have encountered problems such as computational inefficiency and solution difficulties. To solve these problems, a new method, Multi-Failure Mode Reliability Sensitivity Analysis Method (MF-RSAM), is proposed. Based on friction vibration theory and control theory, a performance function is established with the damping ratio of the most unstable mode of the system as the response. Based on the Manson-Coffin model, a performance function is established with the maximum strain value of the brake disc surface as the response. Subsequently, the optimal Gumbel-Copula function is selected and introduced into the reliability analysis model. The Monte Carlo support vector regression method is adopted for the vibration-fatigue gradual reliability prediction of automotive braking systems under multiple failure modes. Finally, the reliability sensitivity under thermal fatigue and complex modal correlated failure modes is analysed. The results show a significant difference between the results of parametric reliability prediction considering correlated failure and single failure modes, with a maximum reduction of about 7.5% in reliability under correlated failure modes as the parameters are changed and a change in the parameter sensitivity order.

Real-Time Monitoring Method and Circuit Based on Built-In Reliability Prediction.

The failure of different chips under working conditions is influenced by various stress states such as different voltages, temperatures, stress durations, and stress variations. Therefore, the failure time has a great degree of dispersion, and similar chips may exhibit different failure mechanisms due to variations in their working environments. This paper proposes three system-on-chip reliability failure prediction unit circuits: the time-dependent dielectric breakdown prediction circuit, the negative bias temperature instability prediction circuit, and the hot carrier injection prediction circuit. These circuits are embedded within the main chip, enabling real-time failure prediction and reliability mechanism diagnosis in the same working environment as the main chip. The three reliability failure prediction circuits are compact and energy efficient, allowing for their integration into a system on a chip as IP cores that provide early warning signals before system-on-chip failure. Compared to traditional reliability prediction methods, this approach offers the advantages of accurately identifying failure mechanisms, predicting failure times, and enabling real-time online monitoring.

Evaluation of reserves and injection-production capacity of underground gas storage under multi-cycle operation

In order to more accurately estimate the reserves of underground gas storage under the complex operation mode of multi-period strong injection and strong production, and design a reasonable allocation scheme of injection and production gas volume. In this paper, the material balance equation is improved according to the “hollow square” shape characteristics of apparent bottom hole flow pressure and cumulative production of multi-cycle injection-production wells in gas storage. Combined with the node analysis method, a new evaluation method of multi-period reserves and injection-production capacity of underground gas storage is established by using the vertical pipe flow equation, erosion flow equation, critical liquid carrying flow equation and critical sand flow equation to constrain the gas inflow and outflow equations respectively. Then, taking the gas storage as a case, the method is compared with the field data. The results show that this method avoids the inconsistency of the existing methods in solving the reserves of underground gas storage, and provides a more scientific and relatively reliable method for reserves and capacity prediction.

Feature selection and response prediction on a suspension bridge due to wind effect by machine learning

This research introduces an efficient machine learning approach for predicting the structural health of long-span suspension bridges, focusing on their responses to dynamic environmental load like earthquakes and wind. Unlike traditional analytical methods that rely on simplifications, this study utilizes real-world data from anemometers and accelerometers to enhance prediction accuracy and efficiency. Also instead of using whole signals, the study uses fewer time frame signal. The main contribution of this paper is the application of support vector regression (SVR), optimized through Observer-Teacher-Learner-Based-Optimization (OTLBO) for parameter tuning. The optimization process is further refined using Multi-Objective Observer-Teacher-Learner-Based-Optimization (MOOTLBO), targeting feature selection and dimension reduction to improve model performance significantly. Hardanger Bridge serves as a case study, demonstrating the model's capability to accurately predict acceleration responses to wind. By inputting wind sensor data and analyzing acceleration outputs, the enhanced SVR model, through OTLBO and MOOTLBO, shows remarkable predictive accuracy, validated against six performance indices. This methodological advancement suggests that the machine learning-based model could potentially supplant traditional finite element models, offering a more adaptable, efficient, and accurate tool for structural health monitoring (SHM). This advancement addresses critical discrepancies in SHM systems, such as data gaps or sensor malfunctions, by providing a reliable prediction method that ensures the ongoing safety and integrity of bridge structures.

A novel hybrid method for predicting maglev train-induced environmental vibrations combining field measurement, 2.5D FEM modelling and multi-objective optimization

The maglev system has been developed rapidly in recently years since its advantage in mass transportation, ride comfort and energy efficiency, which also caused an increasing concern on the maglev train-induced environmental vibrations. This paper presents a novel hybrid framework for predicting high-speed maglev train-induced environmental vibrations combining field measurement, 2.5D FEM simulation and multi-objective optimization. First, a maglev train-guideway-soil coupled model considering guideway irregularities was proposed to calculate the ground vibration using 2.5D FEM. Then, the guideway irregularity spectrum and soil damping are inverted by the optimization process using the NSGA3 genetic algorithm, in which the differences of measured and calculated vertical vibrations of measuring points are chosen as objective functions. With the inverted guideway irregularity spectrum and soil damping, the ground vibrations were calculated using the 2.5D FEM model and compared with the field measurements. It was found that the inverted PSD spectrum of guideway irregularity generally decreases as the spatial frequency increases, exhibiting a similar trend as the measured ones. The results obtained by the proposed hybrid prediction method agree well with the field measurement in both time domain and frequency domain. The prediction error for the vertical vibration level of all measuring points induced by five maglev train passing are mainly less than 10 %, indicating that the proposed hybrid method provided a reliable and effective method for vibration prediction combining field measurement and numerical simulation.

Nomogram for predicting diabetes insipidus following endoscopic transsphenoidal surgery in pituitary adenomas.

Postoperative diabetes insipidus (DI) frequently complicates endoscopic transsphenoidal surgery (TSS) in pituitary adenoma (PA) patients, yet reliable predictive methods for DI risk remain lacking. This study aims to identify risk factors associated with DI following endoscopic transsphenoidal resection of PA and to develop a predictive nomogram for assessing postoperative DI risk. This study involved 600 PA patients underwent endoscopic TSS at Shandong Provincial Hospital from 2021 to 2023. Among these patients, 82 developed postoperative DI while 518 did not. The cohort was randomly divided into training (n = 360) and validation (n = 240) groups at 6:4 ratios by R software. Clinical parameters and radiographic features were evaluated using univariable and multivariable logistic regression to construct a predictive nomogram for post-endoscopic TSS DI risk. Model performance was assessed using ROC curves, calibration plots, and decision curve analysis. Subgroup analysis was used to evaluate the model's ability to discriminate between transient and permanent DI. Univariable and multivariable logistic regression analyses on the training group identified several independent risk factors for post-endoscopic TSS DI, including maximum tumor diameter, Knosp grade, Esposito grade, recurrent PA, and pituitary stalk deviation angle. A nomogram was developed based on these factors, demonstrating robust predictive accuracy with ROC areas under curve of 0.840 for the training group and 0.815 for the validation group. Calibration plots indicated excellent agreement between predicted and observed probabilities of postoperative DI. DCA curves highlighted the nomogram's efficacy in guiding clinical decision-making. Subgroup analysis showed that the model was able to discriminate between transient and permanent DI, and the AUC was 0.652 (95% CI 0.525-0.794). This study presents a nomogram designed to predict postoperative DI risk in patients undergoing endoscopic TSS for PA. Internal and external validations underscored the model's high accuracy, calibration, and clinical utility. Simultaneously, the model can also assess the development risk of permanent DI. This predictive tool offers clinicians valuable support in identifying high-risk DI patients, optimizing postoperative care strategies, and tailoring treatment plans to improve patient outcomes.

Predicting financial distress in TSX-listed firms using machine learning algorithms.

This study investigates the application of machine learning (ML) algorithms, a subset of artificial intelligence (AI), to predict financial distress in companies. Given the critical need for reliable financial health indicators, this research evaluates the predictive capabilities of various ML techniques on firm-level financial data. The dataset comprises financial ratios and firm-specific variables from 464 firms listed on the TSX. Multiple ML models were tested, including decision trees, random forests, support vector machines (SVM), and artificial neural networks (ANN). Recursive feature elimination with cross-validation (RFECV) and bootstrapped CART were also employed to enhance model stability and feature selection. The findings highlight key predictors of financial distress, such as revenue growth, dividend growth, cash-to-current liabilities, and gross profit margins. Among the models tested, the ANN classifier achieved the highest accuracy at 98%, outperforming other algorithms. The results suggest that ANN provides a robust and reliable method for financial distress prediction. The use of RFECV and bootstrapped CART contributes to the model's stability, underscoring the potential of ML tools in financial health monitoring. These insights carry valuable implications for auditors, regulators, and company management in enhancing practices around financial oversight and fraud detection.

Structural Online Damage Identification and Dynamic Reliability Prediction Method Based on Unscented Kalman Filter.

As sensor monitoring technology continues to evolve, structural online monitoring and health management have found numerous applications across various fields. However, challenges remain concerning the real-time diagnosis of structural damage and the accuracy of dynamic reliability predictions. In this paper, a structural online damage identification and dynamic reliability prediction method based on Unscented Kalman Filter (UKF) is presented. Specifically, in the Wiener degradation process with random effects on structural performance, the structural damage identification is initially realized using UKF. Following that, the EM algorithm is employed for estimating the performance model parameters. Eventually, dynamic reliability prediction is realized based on conditional probability. The simulation results indicate that the method effectively estimates the damage state during the structure's use while providing accurate, real-time, and dynamic reliability predictions for the system.

Shear wave velocity prediction based on bayesian-optimized multi-head attention mechanism and CNN-BiLSTM

Shear wave velocity (VS) is one of the fundamental geophysical parameters essential for pre-stack seismic inversion, rock mechanics evaluation, and in-situ stress assessment. However, due to the high cost of acquiring VS log data, it is impossible to carry out this logging project in all wells. Thus, it is extremely necessary to develop an efficient and reliable VS prediction method. Deep learning methods have distinct advantages in data inversion, but different neural network have their own characteristics. A single-structured neural network has inevitable limitations in VS prediction, making it challenging to effectively capture the nonlinear mapping relationships of multiple parameters. Therefore, an integrated VS prediction model was proposed based on analyzing the applicability of classical neural networks. This new model, denoted as Bo-MA-CNN-BiLSTM, combines a Bayesian-optimized and multi-head attention mechanism (Bo-MA) with a convolutional neural network (CNN) and a bidirectional long short-term memory network (BiLSTM). It can effectively capture spatio-temporal data reflecting geophysical characteristics from log data, and the integration of the multi-head attention mechanism enhances the rational allocation of weights for log data. Bayesian optimization is utilized to determine the values of hyperparameters, overcoming the subjectivity and empiricism associated with manual selection. Actual data processing demonstrates that the new model achieves higher accuracy in predicting VS than applying CNN, LSTM, BiLSTM, and CNN-LSTM individually. The application results of well log data not involved in training indicate that, compared to other classical models, this new model exhibits optimal evaluation metrics. Especially for strongly heterogeneous formations, the predicted results demonstrate significant superiority, verifying the generalization ability and robustness of the proposed model.

Study of reliability prediction method and uncertainty analysis of the pump and valve of a floating nuclear power plant

Abstract The floating nuclear power plant (FNPP) is a new type of reactor. Due to the unique marine environment, the reliability of its equipment differs significantly from that of land-based power plants, making conventional nuclear power plant databases unsuitable for direct application to FNPPs. Consequently, recognizing the need for reliability data specific to FNPP equipment, this paper proposes a framework for predicting reliability and analyzing associated uncertainties. This framework employs the parts count method and the parts stress method, as outlined in reliability prediction handbooks, to predict reliability based on different equipment categories. This paper studies the reliability of two typical types of equipment in nuclear power plants: valves and main coolant pumps. First, the reliability data for these two equipment types in land-based environments are calculated and compared with data from conventional nuclear power plant databases to validate the accuracy of the calculation results. Next, the reliability of the equipment is estimated for a marine environment, and the uncertainty distribution of these estimates is presented. The results indicate that the proposed framework effectively predicts the failure data for valves and main coolant pumps in FNPPs operating in marine conditions, serving as a reference for future reliability predictions of additional equipment.

A Reliable Prediction Method to Forecast Pile Bearing Capacity Using Classic NB Base Hybrid Schemes

A Reliable Prediction Method to Forecast Pile Bearing Capacity Using Classic NB Base Hybrid Schemes

ECG-based epileptic seizure prediction: Challenges of current data-driven models.

Up to a third of patients with epilepsy fail to achieve satisfactory seizure control. A reliable method of predicting seizures would alleviate psychological and physical impact. Dysregulation in heart rate variability (HRV) has been found to precede epileptic seizures and may serve as an extracerebral predictive biomarker. This study aims to identify the preictal HRV dynamics and unveil the factors impeding the clinical application of ECG-based seizure prediction. Thirty-nine adult patients (eight women; median age: 38, [IQR = 31, 56.5]) with 252 seizures were included. Each patient had more than three recorded epileptic seizures, each at least 2 hours apart. For each seizure, one hour of ECG prior to seizure onset was analyzed and 97 HRV features were extracted from overlapping three-minute windows with 10s stride. Two separate patient-specific experiments were performed using a support vector machine (SVM). Firstly, the separability of training data was examined in a non-causal trial. Secondly, the prediction was attempted in pseudo-prospective conditions. Finally, visualized HRV data, clinical metadata, and results were correlated. The mean receiver operating characteristic (ROC) area under the curve (AUC) for the non-causal experiment was 0.823 (±0.12), with 208 (82.5%) seizures achieving an improvement over chance (IoC) classification score (p < 0.05, Hanley & McNeil test). In pseudo-prospective classification, the ROC-AUC was 0.569 (±0.17), and 86 (49.4%) seizures were classified with IoC. Off-sample optimized SVMs failed to improve performance. Major limiting factors identified include non-stationarity, variable preictal duration and dynamics. The latter is expressed as both inter-seizure onset zone (SOZ) and intra-SOZ variability. The pseudo-prospective preictal classification achieving IoC in approximately half of tested seizures suggests the presence of genuine preictal HRV dynamics, but the overall performance does not warrant clinical application at present. The limiting factors identified are often overlooked in non-causal study designs. While current deterministic prediction methods prove inadequate, probabilistic approaches may offer a promising alternative. Many patients with epilepsy suffer from uncontrollable seizures and would greatly benefit from a reliable seizure prediction method. Currently, no such system is available to meet this need. Previous studies suggest that changes in the electrocardiogram (ECG) precede seizures by several minutes. In our work, we evaluated whether variations in heart rate could be used to predict epileptic seizures. Our findings indicate that we are still far from achieving results suitable for clinical application and highlight several limiting factors of present seizure prediction approaches.

A novel operational reliability and state prediction method based on degradation hidden Markov model with random threshold

AbstractBearings are widely used as a common mechanical component and significantly impacts the reliability and safety of various engineering equipment. In the field of large‐scale equipment such as wind turbines, statistical data for reliability and state prediction of bearings is usually limited, leading to the inapplicability of traditional statistical methods. Besides, individual differences commonly exist among bearings, and the appropriate failure threshold for a specific bearing is difficult to be determined due to the individual uncertainty, which may induce prediction errors. To address these issues, a novel operational reliability and state prediction method based on random threshold degradation hidden Markov model was proposed in the study. The traditional hidden Markov model was improved by considering the effect of performance degradation on state transition probability matrix. Moreover, random failure thresholds of performance degradation were employed to describe individual differences between bearings. The operational reliability and state of bearings was obtained by comprehensive analysis of prediction results under different failure thresholds. Verification of the proposed operational reliability and state prediction method were conducted using PHM2012 bearing operation data. The results underscored the effectiveness of the proposed method in achieving a comparatively high accuracy in operational reliability prediction without the prerequisite of an exact failure threshold, when contrasted with several established reliability and life prediction techniques.

Development and accuracy of an artificial intelligence model for predicting the progression of hip osteoarthritis using plain radiographs and clinical data: a retrospective study

BackgroundPredicting the progression of hip osteoarthritis (OA) remains challenging, and no reliable predictive method has been established. This study aimed to develop an artificial intelligence (AI) model to predict hip OA progression via plain radiographs and patient data and to determine its accuracy.MethodsThis retrospective study utilized anteroposterior pelvic radiographs of consecutive patients with hip OA who underwent primary unilateral total hip arthroplasty. Radiographs diagnosed with Kellgren–Lawrence (KL) grade 0–2 were extracted from 361 patients and 1697 images. This AI model was developed to predict whether OA would progress from KL grade 0–2 to KL grade ≥ 3 within n years (n = 3, 4, 5). A gradient-boosting decision tree approach was utilized according to feature extractions obtained by a convolutional neural network from radiographs and patient data (height, body weight, sex, age, and KL grade given by an orthopedic surgeon) with five-fold cross-validation. The model performance was assessed using accuracy, specificity, sensitivity, and the area under the receiver operating characteristic curve (AUC).ResultsThe mean accuracy, specificity, sensitivity, and AUC of our prediction model were, respectively, 81.8%, 88.0%, 66.7%, and 0.836 for 3 years; 79.8%, 85.0%, 71.6%, and 0.836 for 4 years; and 78.5%, 80.4%, 76.9%, and 0.846 for 5 years.ConclusionsThe proposed AI model performed adequately in predicting hip OA progression and may be clinically applicable with additional datasets and validation.

Multi-relation spatiotemporal graph residual network model with multi-level feature attention: A novel approach for landslide displacement prediction

Accurate prediction of landslide displacement is crucial for effective early warning of landslide disasters. While most existing prediction methods focus on time-series forecasting for individual monitoring points, there is limited research on the spatiotemporal characteristics of landslide deformation. This paper proposes a novel Multi-Relation Spatiotemporal Graph Residual Network with Multi-Level Feature Attention (MFA-MRSTGRN) that effectively improves the prediction performance of landslide displacement through spatiotemporal fusion. This model integrates internal seepage factors as data feature enhancements with external triggering factors, allowing for accurate capture of the complex spatiotemporal characteristics of landslide displacement and the construction of a multi-source heterogeneous dataset. The MFA-MRSTGRN model incorporates dynamic graph theory and four key modules: multi-level feature attention, temporal-residual decomposition, spatial multi-relational graph convolution, and spatiotemporal fusion prediction. This comprehensive approach enables the efficient analyses of multi-source heterogeneous datasets, facilitating adaptive exploration of the evolving multi-relational, multi-dimensional spatiotemporal complexities in landslides. When applying this model to predict the displacement of the Liangshuijing landslide, we demonstrate that the MFA-MRSTGRN model surpasses traditional models, such as random forest (RF), long short-term memory (LSTM), and spatial temporal graph convolutional networks (ST-GCN) models in terms of various evaluation metrics including mean absolute error (MAE = 1.27 mm), root mean square error (RMSE = 1.49 mm), mean absolute percentage error (MAPE = 0.026), and R-squared (R2 = 0.88). Furthermore, feature ablation experiments indicate that incorporating internal seepage factors improves the predictive performance of landslide displacement models. This research provides an advanced and reliable method for landslide displacement prediction.