A Distributed Inference Method Integrating Causal Analysis and Surrogate Models for Optimizing Tuned Mass Damper Parameters to Enhance Offshore Wind Turbine Safety

Reliability Engineering & System Safety, Journal Year: 2025, Volume and Issue: unknown, P. 110863 - 110863

Published: Jan. 1, 2025

Language: Английский

---

An Integrated Methodological Approach for Interpreting Used Oil Analysis in Diesel Engines

Lubricants, Journal Year: 2025, Volume and Issue: 13(4), P. 169 - 169

Published: April 8, 2025

This study develops an integrated methodological approach for interpreting used oil analysis results in diesel engines, focusing on optimizing maintenance strategies. The methodology combines a literature review with quantitative assessment of 156 lubricant reports from fleet waste collection trucks operating Cuenca, Ecuador, high-altitude city. framework includes critical limits key parameters, correlation analysis, and Principal Component Analysis (PCA) to identify dominant degradation mechanisms. Binary Segmentation (BS) algorithm is also Change-Point Detection. findings indicate four primary pathways: thermal–chemical influenced by sulfur, oxidation, soot; metallic wear base depletion, involving iron, chromium, copper; external contamination linked silica viscosity alteration due aging. Significant shifts were identified at approximately 346 444 service hours, suggesting points condition-based interventions. highlights the effectiveness multivariate statistical tools enhancing interpretation predictive integration Detection provides robust defining change intervals based condition rather than fixed time- or mileage-based criteria. offers practical benefits operations, enabling reduction operational costs, engine reliability, minimizing environmental impact unnecessary changes.

Language: Английский

---

Multiscale-attention masked autoencoder for missing data imputation of wind turbines

Knowledge-Based Systems, Journal Year: 2024, Volume and Issue: 299, P. 112114 - 112114

Published: June 19, 2024

Language: Английский

---

Application of Bayesian Statistics in Analyzing and Predicting Carburizing-Induced Dimensional Changes in Torsion Bars

Published: July 18, 2024

This paper explores the feasibility of applying Bayesian statistical methods to study distortion patterns induced by carburizing heat treatment. By establishing posterior and predictive distribution models for torsion bar dimensions, we aim accurately understand predict expansion behavior, thus enhancing control over carburizing-induced dimensional changes. allow integration prior knowledge real-time data, providing a more comprehensive understanding phenomena. approach not only improves precision predictions but also contributes optimizing overall manufacturing process, ensuring that bars meet rigorous standards required high-performance applications in demanding industrial environments.

Language: Английский

---

Investigation on the fusion reliability and cluster consistency of multivariable entropy method

Measurement Science and Technology, Journal Year: 2024, Volume and Issue: 35(8), P. 086101 - 086101

Published: April 24, 2024

Abstract Recent researches have shown that the multivariable entropy based feature extraction method can obtain better diagnosis results for fault of planetary gearbox. However, nature properties still not been deeply explored: reliability multi-source information fusion and cluster consistency same signal. These two will affect accuracy on multivariate entropy. This paper aims to reveal Firstly, a rigid-flexible coupling dynamic model gearbox is conducted establish pure test environment. Then generated vibration signals are used evaluate Additionally, new called variational embedding refined composite multiscale diversity (veRCMDE) proposed. Finally, simulation experiment show high enable extract more valuable features, proposed veRCMDE performs best in all experiments.

Language: Английский

---

Condition monitoring based on corrupted multiple time series with common trends

Reliability Engineering & System Safety, Journal Year: 2024, Volume and Issue: 251, P. 110324 - 110324

Published: July 6, 2024

Language: Английский

---

Bayesian Updating for Prediction of Scour Depth Using Natural Frequency of Monopiles

Computers and Geotechnics, Journal Year: 2024, Volume and Issue: 176, P. 106793 - 106793

Published: Sept. 28, 2024

Language: Английский

---

Abnormal behavior analysis of distribution automation system terminal based on multi-modal data fusion

International Journal of Low-Carbon Technologies, Journal Year: 2024, Volume and Issue: 19, P. 2619 - 2625

Published: Jan. 1, 2024

Abstract In distribution automation systems, detecting terminal abnormal behaviors is crucial for stability and reliability. Traditional methods struggle with insufficient feature extraction weak generalization when handling multi-modal data. Thus, an anomaly detection method based on self-attention convolutional neural network (SA-CNN) proposed, integrating the strengths of mechanisms networks to enhance capabilities. Experiments IEEE PHM dataset demonstrate superiority over traditional CNN ARIMA algorithms, achieving accuracy, recall, F1 scores 0.928, 0.936, 0.932, respectively. Future work aims improve model efficiency performance.

Language: Английский

---

Gaussian Derivative Change-point Detection for early warnings of industrial system failures

Reliability Engineering & System Safety, Journal Year: 2024, Volume and Issue: unknown, P. 110681 - 110681

Published: Nov. 1, 2024

Language: Английский

---