最新刊期
- 摘要：This study proposes a deterministic and definitive methodology for surrogate model construction based on moment quadrature design points. Different from adaptive or randomly sampling approaches, the proposed framework derives design points directly from the statistical moments of the input probability density functions, ensuring reproducibility, optimal polynomial exactness, and broad applicability to low- and high-dimensional problems involving arbitrary distributions, including nonuniform distributions and, in principle, empirical ones. It features an automatic pipeline for basis generation, coefficient regression, and optional term pruning, avoiding case-dependent tuning. Moreover, it allows direct evaluation of uncertainty metrics and global sensitivity indices to be obtained using the same set of model evaluations. Extensive numerical examples, including standard benchmark functions and engineering applications involving up to 100 random variables, demonstrate that the proposed method achieves high accuracy and computational efficiency compared with conventional surrogate modeling approaches.关键词：surrogate model;high-dimensional;moment quadrature method;design point6|0|0更新时间：2026-05-08
- 摘要：This study focuses on an accurate and reliable prediction of the remaining useful life (RUL) of the bearings. In recent times, machine learning based RUL predictions have gained traction to ensure safety, efficiency, and cost-effectiveness of industrial machinery. However, raw vibration signals acquired from run-to-failure experiments are typically noisy, non-stationary, and high-dimensional, making direct learning of degradation patterns challenging. This often undermines the reliability of the prediction due to inconsistency in the RUL predictions at a given time. This study proposes a reliable multi-stage prognostic framework that integrates robust signal pre-processing, data-driven health-state classification, and deep learning-based RUL estimation. The proposed pipeline employs a piecewise aggregate approximation for dimensionality reduction, a singular spectrum analysis for noise suppression, and a central-moment-based change point detection to automatically identify the onset of degradation. Subsequently, a health index is constructed to characterize the degradation process and useful service life. An extreme gradient boosting classifier is adopted to distinguish between healthy and degraded operating states of the bearing using vibration response. Later, a hybrid convolution with gated recurrent (CGR) neural network is proposed to predict the RUL. The method is validated using multiple run-to-failure bearing datasets with different operating conditions. The corresponding results show that the classifier achieves average F1 score of approx. 0.993 with reliability indices >2.0, indicating a clear identification of health-state. The proposed CGR network exhibits attractive performance, with high regression accuracy in RUL prediction. The efficacy of the proposed network is also evaluated against state-of-the-art methods, including bidirectional long-short-term memory recurrent neural networks, gated recurrent units, causal dilated convolution-based residual densenet with channel attention and temporal convolutional network with transformer. Overall, the results confirm that the proposed framework enables accurate, computationally efficient, and reliability-informed RUL predictions, making it suitable for real-time condition monitoring and predictive maintenance applications in rotating machinery.关键词：fault prognostics;reliability assessment of RUL predictions;vibration signal processing;deep learning7|0|0更新时间：2026-05-08
- 摘要：This paper introduces a method based on the spectral representation of exponential and power operations to tackle the complexity issues associated with dependability characteristics in Markov systems. The conventional formulas become impractical due to the exponential growth in the number of states, which becomes a significant challenge in binary component systems. In such contexts, an approximation method is proposed in a controlled mathematical framework to realize accurate reliability assessment for highly reliable systems. In this paper, formulas for computing system dependability such as reliability, failure rate, conditional survival distribution, etc. are derived and proved to be useful and accurate for the reliability assessment of non-ergodic systems, while the availability of ergodic systems is derived. The only elements needed here are the largest eigenvalues and corresponding eigenvectors of the generate or subtransition matrix, which describes the approximation of reliability. Finally, the approximate results and exact results are verified through numerical examples, proving the correctness of the proposed method.关键词：Markov process;phase-type distribution;reliability;asymptotic failure rate;spectral analysis6|0|0更新时间：2026-05-08
- 摘要：Acoustic emission shows great potential for in-situ monitoring and defect diagnosis in wire arc additive manufacturing (WAAM). However, the AE signal produced during WAAM is heavily contaminated by arc discharge noise, making it difficult to directly extract defect-related features from raw data. This study proposes a Mel spectrogram–based deep learning framework for efficient WAAM health monitoring. The method introduces an enhanced time–frequency representation strategy that captures defect-related features more effectively under the high-noise conditions inherent in WAAM processes. By leveraging Mel spectrogram representations, the framework emphasizes informative low-frequency components while suppressing high-frequency noise, thereby improving feature interpretability and robustness. Convolutional neural network and vision transformer models are employed for defect classification and performance benchmarking. Experimental results demonstrate that the proposed approach achieves high diagnostic accuracy with substantially reduced computational cost, outperforming conventional short-time Fourier transform-based methods. The findings confirm that Mel spectrogram representations offer a more efficient and generalizable solution for health monitoring in WAAM.关键词：WAAM;acoustic emission;Mel spectrogram;CNN;manufacturing quality monitoring15|29|0更新时间：2026-04-14
- 摘要：High-temperature rotating structures (HTRSs) are essential components in industries, operating under severe conditions that lead to unpredictable failure behaviors. These failures are driven by uncertainties in material properties, loading conditions, and geometric variations. This study proposes a robust computational framework for assessing probabilistic damage accumulations (PDAs) and system-level reliability of HTRS under multi-source uncertainties. The probabilistic properties of basic random variables (RVs) in spatial and temporal scale are accounted, which are used to analyze PDA across different scenarios and reliability is assessed using the cumulative damage–damage threshold interference criterion. An adaptive surrogate model is then developed to approximate the complex, nonlinear relationship between damage and RVs, ensuring efficient and accurate simulations. Numerical case studies demonstrate the high efficiency and precision of the proposed method, which is further applied to a turbine disk considering multi-source uncertainties. The proposed method significantly improves computational efficiency while maintaining high accuracy in predicting system reliability, providing new insights in the damage-driven reliability assessment upward to system-level applications.关键词：probabilistic damage accumulation;CD-DT criterion;adaptive surrogate model;reliability assessment2|5|0更新时间：2026-04-14
- 摘要：This paper provides a systematic review of how ChatGPT-like large language models (LLMs) contribute to the testing and verification of autonomous intelligent systems (AIS). Building upon recent advances in generative reasoning, this study integrates evidence from 120 peer-reviewed works to examine four key domains: test scenario generation, vulnerability detection, formal verification, and real-time monitoring. Comparative analysis across fuzz testing, symbolic execution, and reinforcement learning highlights how LLMs improve automation, semantic coverage, and adaptability while revealing limitations in benchmark completeness, interpretability, and resource efficiency. The review introduces structured tables summarizing representative datasets, domain-specific applications, and comparative insights between traditional and LLM-based testing approaches. Key challenges-including benchmarking gaps, explainability deficits, and ethical risks-are analyzed alongside emerging research directions such as hybrid verification frameworks and data quality enhancement. This work aims to bridge conceptual and practical gaps between AI safety engineering and large-model reasoning, offering a reference roadmap for integrating LLMs into future AIS verification pipelines.关键词：ChatGPT;large language models;autonomous intelligent systems;testing;verification;AI safety3|11|0更新时间：2026-04-14
- Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19
京公网安备11010802024621 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
0