Statistical and Machine Learning Approach for Progressive Stress Accelerated Life Testing Under Unified Progressive Hybrid Censoring DOI
Aman Prakash, Anil Kumar Maurya, Raj Kamal Maurya

et al.

Quality and Reliability Engineering International, Journal Year: 2025, Volume and Issue: unknown

Published: April 16, 2025

ABSTRACT This article focuses on progressive‐stress accelerated life testing (ALT) under a unified progressive hybrid censoring scheme. The study assumes that the lifetimes of test units follow Lomax distribution, with scale parameter modeled using cumulative exposure model and an inverse power law. parameters are estimated both classical Bayesian methods. approach uses maximum likelihood estimation for point estimates asymptotic confidence intervals. In contrast, employs informative noninformative priors, Metropolis–Hastings algorithm handling complex posterior computations. Extensive simulations evaluate performance various ALT, including simple multiple ramp‐stress tests. We have applied above methodology to real‐life data demonstrated its applicability. Furthermore, we introduce machine learning techniques analyze reliability model. employed three methods, such as random forest regression, decision tree multilayer perceptron estimate reliability. A comparative analysis all methods metrics has been discussed. compared statistical estimation.

Language: Английский

An advanced technique to adjust hull girder load : Part 2 = Application to ship's hull for verification DOI Creative Commons
Changhwan Jang, Do Kyun Kim

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104313 - 104313

Published: Feb. 1, 2025

Language: Английский

Citations

2

Structural safety analysis of shield tunnels based on convergent deformation DOI
Lei Zhang,

Chang Zi Qu,

Shuzhan Zhang

et al.

International Journal of Structural Integrity, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 10, 2025

Purpose Damage to the pipe structure and increased bolt stress in operating tunnels will significantly affect long-term stability of shield tunnels. However, due large number segments complex installation methods, it is difficult directly obtain conditions bolts. Convergence deformation, as an important indicator for health assessment tunnels, easy collect can reflect structural state tunnel Design/methodology/approach Taking typical sections Hangzhou Metro Line 1 3 example, current damage simulated by monitoring convergence deformation. First, based on disease data, relationship between deformation segment leakage, misalignment well longitudinal joint opening two analyzed statistically. The bolts, steel bars under different deformations Midas. Then a reinforcement measure circumferential internal tension rings proposed. Findings It found that when exceeds 85 mm, although overall force has not reached material limit, there are certain safety risks structure. After comparison, relatively significant effect controlling lateral segments. Originality/value results have guiding significance evaluation diseases, early warning control diseases at deformations.

Language: Английский

Citations

1

Analysis of adhesive mortar bonding to ceramic tiles using resonance frequencies method DOI
Janaina Salustio, Sandro Marden Torres, António C. Azevedo

et al.

International Journal of Structural Integrity, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 13, 2025

Purpose Prismatic specimens were fabricated, consisting of two ceramic tiles bonded by an intermediate adhesive mortar layer. To simulate pre-existing defects, acetate film was strategically inserted into one the mortar-ceramic interfaces, creating controlled cracks varying sizes. The subjected to low-amplitude cyclic loading, inducing simultaneous tensile and shear stresses within system. vibrational responses samples recorded, their frequency-domain amplitudes analyzed. Design/methodology/approach Ceramic tile detachment remains a significant issue in contemporary construction, despite advancements technology updates regulatory standards. majority these failures occur at interface due combined effects stresses. While this phenomenon is well-documented, experimental studies assessing adhesion integrity façade cladding systems are limited. This study aims evaluate performance mortars using non-destructive analysis technique. Findings results enabled characterization dynamic behavior specimens, identification frequency regions corresponding individual components, formulation diagnostic criteria for damage detection. Analysis resonance spectra also made it possible identify peak that can be related mortar-substrate interface. Additionally, elastic dissipated energy metrics calculated quantify system’s mechanical behavior. further investigated impact crack size, curing time type on overall structural integrity. Originality/value work Resonance measurements have been used research analyze propagation paths metallic from aircraft engines. However, widespread use techniques based frequencies assessment, application field coating seems virtually unexplored. Therefore, attempts address gap investigating bond joints, focusing material’s associated parameters.

Language: Английский

Citations

1

Comparative Analysis of Offshore Wind Resources and Optimal Wind Speed Distribution Models in China and Europe DOI Creative Commons
Yanan Chen, Ming Zhao, Zhengxian Liu

et al.

Energies, Journal Year: 2025, Volume and Issue: 18(5), P. 1108 - 1108

Published: Feb. 24, 2025

Offshore wind resources in China and Europe are systematically compared, focusing on speed characteristics the selection of optimal probability distribution models. Using 20 years data at 10 m 100 above sea level, seven unimodal models were applied. The results point out that China’s offshore exhibit high spatial temporal variability, influenced by monsoons typhoons, while European seas characterized stable patterns. Among tested, Weibull is most accurate one for fitting, Generalized Extreme Value Gamma perform better regions with higher skewness extreme events. This study highlights importance characteristics, such as kurtosis, selecting model. These findings provide valuable guidance improvement energy assessments appropriate Future research should explore advanced techniques, machine learning hybrid models, to capture complex patterns enhance model accuracy.

Language: Английский

Citations

1

Computational Fluid Dynamics Analysis of Superhydrophobic and Superhydrophilic Micro-textures for Biofouling Mitigation DOI Creative Commons
Saeed Nazari,

Ling Min,

Elisabete R. Silva

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104627 - 104627

Published: March 1, 2025

Language: Английский

Citations

1

Optimization of cable-stayed force for asymmetric single tower cable-stayed bridge formation based on improved particle swarm algorithm DOI
Huizhong Xiong, Xin Yang, Yong-Nan He

et al.

International Journal of Structural Integrity, Journal Year: 2024, Volume and Issue: 15(5), P. 873 - 901

Published: July 23, 2024

Purpose This paper aims to optimize cable-stayed force in asymmetric one-tower bridge formation using an improved particle swarm algorithm. It compares results with the traditional unconstrained minimum bending energy method. Design/methodology/approach proposes algorithm formation. formulates a quadratic programming mathematical model considering sum of energies main girder and tower as objective function. Constraints include displacements, stresses, force, uniformity. The is applied asymmetrical single-tower bridge, combining it finite element Findings study’s findings reveal significant improvements over Results show that structural displacement internal are within constraints, maximum moment decreases, resulting smoother linear shape more even distribution. Additionally, top offset change at tower-beam junction reduced. Moreover, diagonal cable increase uniformly length growth. Originality/value offers simplicity, effectiveness, practicality optimizing bridge-forming cable-staying force. eliminates need for arbitrary manual adjustments seen methods effectively addresses optimization challenge bridges.

Language: Английский

Citations

4

Adaptive estimation: Fuzzy data-driven gamma distribution via Bayesian and maximum likelihood approaches DOI Creative Commons
Abbarapu Ashok, Nadiminti Nagamani

AIMS Mathematics, Journal Year: 2025, Volume and Issue: 10(1), P. 438 - 459

Published: Jan. 1, 2025

<p>Integrating fuzzy concepts into statistical estimation offers considerable advantages by enhancing both the accuracy and reliability of parameter estimations, irrespective sample size technique used. This study specifically examined improvement when dealing with data, a focus on gamma distribution. We explored evaluated variety techniques for determining scale $ \eta shape \rho distribution, employing maximum likelihood (ML) Bayesian methods. In case ML estimates, expectation-maximization (EM) algorithm Newton-Raphson (NR) method were applied, confidence intervals constructed using Fisher information matrix. Additionally, highest posterior density (HPD) derived through Gibbs sampling. For Tierney Kadane (TK) approximation sampling used to enhance process. A thorough performance comparison was undertaken simulated dataset lifetimes rechargeable batteries assess effectiveness these The methods comparing estimated parameters their true values mean squared error (MSE) as metric. Our findings demonstrate that approach, particularly combined TK method, consistently produces more accurate reliable estimates compared traditional These results underscore potential in addressing data precision analyses.</p>

Language: Английский

Citations

0

Characterizing the role of non-stationary hurricane wind loads on nonlinear structural responses and collapse risk of steel structures DOI
Srinivasan Arunachalam, Seymour M.J. Spence

Journal of Building Engineering, Journal Year: 2025, Volume and Issue: 102, P. 111879 - 111879

Published: Jan. 23, 2025

Language: Английский

Citations

0

An improved CREAM model based on Deng entropy and evidence distance DOI Creative Commons
Xiaoyan Su,

Ziying Hong,

Zhihui Xu

et al.

Nuclear Engineering and Technology, Journal Year: 2025, Volume and Issue: unknown, P. 103485 - 103485

Published: Jan. 1, 2025

Language: Английский

Citations

0

MDRM model and its application in hybrid reliability analysis DOI
Wenxuan Wang, Tao Wang

Proceedings of the Institution of Mechanical Engineers Part O Journal of Risk and Reliability, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 26, 2025

The high-dimensional model decomposition method is an effective approach for solving the reliability of engineering structures or composite materials with a large number uncertain parameters. multiplicative dimensionality reduction technique that decomposes function into combination low-dimensional functions and approximates overall response by responses these functions. This paper begins discussing extrema based on method. Then, combining it Taylor series expansion, approximating extremum was proposed. Furthermore, method, first-order functional relationship between upper lower bounds failure probability interval variables derived. Finally, using algorithm proposed in this paper, can be calculated to solve under random-interval hybrid uncertainty. presents two numerical example demonstrate efficiency accuracy

Language: Английский

Citations

0