Search | Engineering

订阅投稿

首页工程期刊工程焦点工程成就工程前沿关于我们 English

资源类型

期刊论文 1009

年份

2023 68

2022 82

2021 63

2020 75

2019 51

2018 44

2017 48

2016 41

2015 52

2014 43

2013 43

2012 43

2011 36

2010 48

2009 47

2008 37

2007 36

2006 26

2005 26

2004 21

展开︾

关键词

数学模型 13

模型试验 9

数值模拟 8

模型 7

不确定性 5

COVID-19 4

GM(1 3

计算机模拟 3

1)模型 2

DX桩 2

D区 2

Preissmann格式 2

SARS 2

TRIZ 2

Weibull分布 2

k-ε模型 2

不确定性评估 2

临震信号 2

云模型 2

展开︾

检索范围：

排序：展示方式：

Simulation and analysis of grinding wheel based on Gaussian mixture model

Yulun CHI, Haolin LI

《机械工程前沿（英文）》 2012年第7卷第4期页码 427-432 doi: 10.1007/s11465-012-0350-3

摘要：

This article presents an application of numerical simulation technique for the generation and analysis of the grinding wheel surface topographies. The ZETA 20 imaging and metrology microscope is employed to measure the surface topographies. The Gaussian mixture model (GMM) is used to transform the measured non-Gaussian field to Gaussian fields, and the simulated topographies are generated. Some numerical examples are used to illustrate the viability of the method. It shows that the simulated grinding wheel topographies are similar with the measured and can be effective used to study the abrasive grains and grinding mechanism.

关键词： grinding wheel 3D topographies measurement Gaussian mixture model simulation

HTML PDF 收藏

Performance monitoring of non-gaussian chemical processes with modes-switching using globality-locality

Xin Peng, Yang Tang, Wenli Du, Feng Qian

《化学科学与工程前沿（英文）》 2017年第11卷第3期页码 429-439 doi: 10.1007/s11705-017-1675-6

摘要： In this paper, we propose a novel performance monitoring and fault detection method, which is based on modified structure analysis and globality and locality preserving (MSAGL) projection, for non-Gaussian processes with multiple operation conditions. By using locality preserving projection to analyze the embedding geometrical manifold and extracting the non-Gaussian features by independent component analysis, MSAGL preserves both the global and local structures of the data simultaneously. Furthermore, the tradeoff parameter of MSAGL is tuned adaptively in order to find the projection direction optimal for revealing the hidden structural information. The validity and effectiveness of this approach are illustrated by applying the proposed technique to the Tennessee Eastman process simulation under multiple operation conditions. The results demonstrate the advantages of the proposed method over conventional eigendecomposition-based monitoring methods.

关键词： non-Gaussian processes subspace projection independent component analysis locality preserving projection finite mixture model

HTML PDF 收藏

An adaptive data-driven method for accurate prediction of remaining useful life of rolling bearings

Yanfeng PENG, Junsheng CHENG, Yanfei LIU, Xuejun LI, Zhihua PENG

《机械工程前沿（英文）》 2018年第13卷第2期页码 301-310 doi: 10.1007/s11465-017-0449-7

摘要：

A novel data-driven method based on Gaussian mixture model (GMM) and distance evaluation technique (DET) is proposed to predict the remaining useful life (RUL) of rolling bearings. The data sets are clustered by GMM to divide all data sets into several health states adaptively and reasonably. The number of clusters is determined by the minimum description length principle. Thus, either the health state of the data sets or the number of the states is obtained automatically. Meanwhile, the abnormal data sets can be recognized during the clustering process and removed from the training data sets. After obtaining the health states, appropriate features are selected by DET for increasing the classification and prediction accuracy. In the prediction process, each vibration signal is decomposed into several components by empirical mode decomposition. Some common statistical parameters of the components are calculated first and then the features are clustered using GMM to divide the data sets into several health states and remove the abnormal data sets. Thereafter, appropriate statistical parameters of the generated components are selected using DET. Finally, least squares support vector machine is utilized to predict the RUL of rolling bearings. Experimental results indicate that the proposed method reliably predicts the RUL of rolling bearings.

关键词： Gaussian mixture model distance evaluation technique health state remaining useful life rolling bearing

HTML PDF 收藏

prediction method for remaining useful life of lithium-ion batteries based on a neural network and Gaussian

《能源前沿（英文）》 doi: 10.1007/s11708-023-0906-4

摘要： Lithium-ion batteries (LIBs) are widely used in transportation, energy storage, and other fields. The prediction of the remaining useful life (RUL) of lithium batteries not only provides a reference for health management but also serves as a basis for assessing the residual value of the battery. In order to improve the prediction accuracy of the RUL of LIBs, a two-phase RUL early prediction method combining neural network and Gaussian process regression (GPR) is proposed. In the initial phase, the features related to the capacity degradation of LIBs are utilized to train the neural network model, which is used to predict the initial cycle lifetime of 124 LIBs. The Pearson coefficient’s two most significant characteristic factors and the predicted normalized lifetime form a 3D space. The Euclidean distance between the test dataset and each cell in the training dataset and validation dataset is calculated, and the shortest distance is considered to have a similar degradation pattern, which is used to determine the initial Dual Exponential Model (DEM). In the second phase, GPR uses the DEM as the initial parameter to predict each test set’s early RUL (ERUL). By testing four batteries under different working conditions, the RMSE of all capacity estimation is less than 1.2%, and the accuracy percentage (AP) of remaining life prediction is more than 98%. Experiments show that the method does not need human intervention and has high prediction accuracy.

关键词： lithium-ion batteries RUL prediction double exponential model neural network Gaussian process regression (GPR)

HTML PDF 收藏

Simulation of abrasive flow machining process for 2D and 3D mixture models

Rupalika DASH,Kalipada MAITY

《机械工程前沿（英文）》 2015年第10卷第4期页码 424-432 doi: 10.1007/s11465-015-0366-6

摘要：

Improvement of surface finish and material removal has been quite a challenge in a finishing operation such as abrasive flow machining (AFM). Factors that affect the surface finish and material removal are media viscosity, extrusion pressure, piston velocity, and particle size in abrasive flow machining process. Performing experiments for all the parameters and accurately obtaining an optimized parameter in a short time are difficult to accomplish because the operation requires a precise finish. Computational fluid dynamics (CFD) simulation was employed to accurately determine optimum parameters. In the current work, a 2D model was designed, and the flow analysis, force calculation, and material removal prediction were performed and compared with the available experimental data. Another 3D model for a swaging die finishing using AFM was simulated at different viscosities of the media to study the effects on the controlling parameters. A CFD simulation was performed by using commercially available ANSYS FLUENT. Two phases were considered for the flow analysis, and multiphase mixture model was taken into account. The fluid was considered to be a Newtonian fluid and the flow laminar with no wall slip.

关键词： abrasive flow machining (AFM) computational fluid dynamics (CFD) modeling mixture model

HTML PDF 收藏

融合显著性模型和高斯网模型的视网膜血管分割方法 Research Articles

Lan-yan XUE, Jia-wen LIN, Xin-rong CAO, Shao-hua ZHENG, Lun YU

《信息与电子工程前沿（英文）》 2019年第20卷第8期页码 1075-1086 doi: 10.1631/FITEE.1700404

摘要：视网膜血管分割是眼底图像分析的一个重要问题。本文提出一种融合显著性模型和高斯网（GNET）模型的新型深度学习结构分割视网膜血管。显著性图像替代原始图像作为GNET模型的输入。GNET模型具有双边对称结构。左边结构中，在第一层进行上采样操作，在其他层进行最大池化操作；右边结构中，在第一层进行最大池化操作，在其他层进行上采样操作。利用DRIVE数据库对所提方法进行评估。实验结果表明，与UNET模型相比，GNET模型能获得更精确的特征和更精细的细节。本文所提算法能提取准确的血管网络，与其他深度学习方法相比具有更高精确度。视网膜血管分割有助于提取血管变化特征，为脑血管疾病筛查提供依据。

关键词：视网膜血管分割；显著性模型；高斯网模型（GNET）；特征学习

HTML PDF 收藏

近似高斯共轭：非线性、多模态、不确定以及约束下的参数递归滤波等 Review

Tian-cheng LI, Jin-ya SU, Wei LIU, Juan M. CORCHADO

《信息与电子工程前沿（英文）》 2017年第18卷第12期页码 1913-1939 doi: 10.1631/FITEE.1700379

摘要：自上世纪60年代作为现代估计开山之作的卡尔曼滤波器（Kalman filter）的诞生，时间序列状态空间模型应用于各类动态估计问题吸引了大量的研究关注。特别是，寻求实现闭环马尔科夫−贝叶斯递归（比如，从一个高斯先验到一个高斯后验，本文称之为高斯共轭）的解析解成为一般时间序列滤波器设计的主流思路。其面临的主要挑战包括：系统的非线性、多模态（包括机动模型）、复杂不确定性（比如未知的系统输入，非高斯噪声等）和系统约束（包括循环随机变量）等。这些挑战不断触生新的理论、算法与滤波技术，以实现所期望的参数共轭递归。本文对最新研究进行分类、系统回顾，强调了一些容易被忽略的要点。着重介绍了高精观测非线性系统、高斯后验和机动多模态、以及复杂未知系统输入与约束，以弥补当前文献介绍的不足。同时，本文提出一些新的思考：一是一阶马尔科夫转移模型的替代模型，二是有关计算复杂度的滤波器评价。

关键词：卡尔曼滤波；高斯滤波；时间序列估计；贝叶斯滤波；非线性滤波；约束滤波；高斯混合；机动；未知输入

HTML PDF 收藏

基于双层多目标分割的超高速撞击航天器损伤红外检测算法 Research Article

杨晓1,殷春1,Sara DADRAS2,雷光钰1,谭旭彤1,邱根1

《信息与电子工程前沿（英文）》 2022年第23卷第4期页码 571-586 doi: 10.1631/FITEE.2000695

摘要：针对超高速撞击引起的航天器损伤检测，提出一种先进的基于红外成像检测的航天器缺陷提取算法。采用高速混合模型对红外视频流采样数据中的温度变化特征进行分类，并重构图像，得到反映缺陷特征的红外重构图像。设计的分割目标函数用于保证图像分割结果对噪声去除和细节保留的有效性，同时考虑到红外重构图像的复杂性，即所需权衡不同。因此，引入多目标优化算法以实现细节保留和噪声去除之间的平衡，并采用基于分解的多目标进化算法（MOEA/D）进行优化，以保证损伤分割的准确性。实验结果验证了所提算法的有效性。

关键词：超高速撞击损伤；缺陷检测；高斯混合模型；图像分割

HTML PDF 收藏

一种基于高斯过程与粒子群算法的CNN超参数自动搜索混合模型优化算法 Research Article

闫涵,仲崇权,吴玉虎,张立勇,卢伟

《信息与电子工程前沿（英文）》 2023年第24卷第11期页码 1557-1573 doi: 10.1631/FITEE.2200515

摘要：卷积神经网络（CNN）在许多实际应用领域中有着快速发展。然而，CNN性能很大程度上取决于其超参数，而为CNN配置合适的超参数通常面临着以下3个挑战：（1）不同类型CNN超参数的混合变量编码问题；（2）评估候选模型的昂贵计算成本问题；（3）确保搜索过程中收敛速率和模型性能问题。针对上述问题，提出一种基于高斯过程（GP）和粒子群优化算法（PSO）的混合模型优化算法（GPPSO），用于自动搜索最优的CNN超参数配置。首先，设计一种新的编码方法高效编码CNN中不同类型的超参数。其次，提出一种混合代理辅助（HSA）模型降低评估候选模型的高计算成本。最后，设计一种新的激活函数改善模型性能并确保收敛速率。在图像分类基准数据集上进行了大量实验，验证GPPSO优于最先进的方法。以金属断口诊断为例，验证GPPSO算法在实际应用中的有效性。实验结果表明，GPPSO仅需0.04和1.70 GPU天即可在CIFAR-10和CIFAR-100数据集上实现95.26％和76.36％识别准确率。

关键词：卷积神经网络；高斯过程；混合模型；超参数优化；混合变量；粒子群优化

HTML PDF 收藏

基于带约束最大间隔的贝叶斯分类器判别学习方法 None

Ke GUO, Xia-bi LIU, Lun-hao GUO, Zong-jie LI, Zeng-min GENG

《信息与电子工程前沿（英文）》 2018年第19卷第5期页码 639-650 doi: 10.1631/FITEE.1700007

摘要：提出一种新的面向贝叶斯模式分类的判别学习方法，称作“带约束的最大间隔（CMM）方法”。通过计算正样本最小决策值和负样本最大决策值的差异，定义类别之间的类别间隔。基于该类别间隔和正确分类的约束，将间隔函数学习问题转化为最大化类别间隔问题。利用序列无约束最小化技术解决该非线性规划问题。运用CMM方法得到基于高斯混合模型的贝叶斯分类器，并在10个UCI数据集上进行实验。结果表明，利用CMM方法得到的分类器分类性能，明显优于代表性的生成式学习方法期望最大化（EM）和判别式学习方法支持向量机（SVM），并且在多个数据集上取得了相比之前最优结果更好的效果。分类实验和分类器对比实验证明，CMM方法有效，具有一定应用前景。

关键词：判别学习；统计建模；贝叶斯分类器；高斯混合模型；UCI数据集

HTML PDF 收藏

A study on quality evaluation for bituminous mixture using X-ray CT

Satoshi TANIGUCHI, Keiichiro OGAWA, Jun OTANI, Itaru NISHIZAKI

《结构与土木工程前沿（英文）》 2013年第7卷第2期页码 89-101 doi: 10.1007/s11709-013-0197-7

摘要： The objective of this paper is to propose a new quality evaluation method for asphalt concrete mixture using X-ray CT scanner. To achieve this aim, asphalt mixtures should be subjected to the X-ray CT scanning and its characteristics should be clarified. The approach employed in this study was as follows: 1) Coarse aggregate, fine aggregate, filler and bitumen were prepared; 2) dense-graded, coarse-graded and porous asphalt mixtures were made; 3) materials and mixtures were subjected to the X-ray CT scanning; 4) frequency of CT-value, threshold value, average slice CT-value, average segment CT-value were computed. In the material examination, CT-value of aggregate becomes smaller in the order of coarse aggregate, fine aggregate and filler and CT image of bitumen was nearly homogeneous. In the mixture examination, histograms of CT-value and four segmentation images made from CT images expressed the material and mixture characterization such as particle size and the difference in bitumen content and mixture type visibly and the bitumen content varies with the threshold values. In addition, the average segment CT-value without threshold value by dividing the fine aggregate from the coarse aggregate and average CT-value of the coarse aggregate, especially is highly correlated with average CT-value of the bitumen.

关键词： asphalt concrete mixture aggregate bitumen bitumen content quality evaluation X-ray CT

HTML PDF 收藏

基于混合驱动高斯过程学习的强机动多目标跟踪方法 Research Article

国强1,滕龙1,2,尹天祥3,郭云飞3,吴新良2,宋文明2

《信息与电子工程前沿（英文）》 2023年第24卷第11期页码 1647-1656 doi: 10.1631/FITEE.2300348

摘要：现有机动目标跟踪方法在杂波环境中强机动目标的跟踪性能并不令人满意。本文提出一种混合驱动方法，利用数据驱动和基于模型算法的优点跟踪多个高机动目标。将时变恒速（CV）模型集成到在线学习的高斯过程（GP）中，提高高斯过程的预测性能。进一步与广义概率数据关联（GPDA）算法相结合，实现多目标跟踪。通过仿真实验可知，与广泛使用的机动目标跟踪算法如交互式多模型（IMM）和数据驱动的高斯过程运动跟踪器（GPMT）相比，提出的混合驱动方法具有显著的性能优势。

关键词：目标跟踪；高斯过程；数据驱动；在线学习；模型驱动；概率数据关联

HTML PDF 收藏

Determination of effective stress parameter of unsaturated soils: A Gaussian process regression approach

Pijush Samui, Jagan J

《结构与土木工程前沿（英文）》 2013年第7卷第2期页码 133-136 doi: 10.1007/s11709-013-0202-1

摘要： This article examines the capability of Gaussian process regression (GPR) for prediction of effective stress parameter ( ) of unsaturated soil. GPR method proceeds by parameterising a covariance function, and then infers the parameters given the data set. Input variables of GPR are net confining pressure ( ), saturated volumetric water content ( ), residual water content ( ), bubbling pressure ( ), suction ( ) and fitting parameter ( ). A comparative study has been carried out between the developed GPR and Artificial Neural Network (ANN) models. A sensitivity analysis has been done to determine the effect of each input parameter on . The developed GPR gives the variance of predicted . The results show that the developed GPR is reliable model for prediction of of unsaturated soil.

关键词： unsaturated soil effective stress parameter Gaussian process regression (GPR) artificial neural network (ANN) variance

HTML PDF 收藏

Inverse Gaussian process-based corrosion growth modeling and its application in the reliability analysis

Hao QIN, Shenwei ZHANG, Wenxing ZHOU

《结构与土木工程前沿（英文）》 2013年第7卷第3期页码 276-287 doi: 10.1007/s11709-013-0207-9

摘要： This paper describes an inverse Gaussian process-based model to characterize the growth of metal-loss corrosion defects on energy pipelines. The model parameters are evaluated using the Bayesian methodology by combining the inspection data obtained from multiple inspections with the prior distributions. The Markov Chain Monte Carlo (MCMC) simulation techniques are employed to numerically evaluate the posterior marginal distribution of each individual parameter. The measurement errors associated with the ILI tools are considered in the Bayesian inference. The application of the growth model is illustrated using an example involving real inspection data collected from an in-service pipeline in Alberta, Canada. The results indicate that the model in general can predict the growth of corrosion defects reasonably well. Parametric analyses associated with the growth model as well as reliability assessment of the pipeline based on the growth model are also included in the example. The proposed model can be used to facilitate the development and application of reliability-based pipeline corrosion management.

关键词： pipeline metal-loss corrosion inverse Gaussian process measurement error hierarchical Bayesian Markov Chain Monte Carlo (MCMC)

HTML PDF 收藏

Fatigue of asphalt binder, mastic and mixture at low temperature

Dong WANG, Linbing WANG, Guoqing ZHOU

《结构与土木工程前沿（英文）》 2012年第6卷第2期页码 166-175 doi: 10.1007/s11709-012-0157-7

摘要： The fatigue damage is one of the most common distresses observed on the asphalt concrete pavement. To thoroughly understand the fatigue of asphalt concrete, the behaviors of the major components of asphalt concrete under cyclic loading are investigated respectively in this study. A new experiment method is developed to evaluate the performances of asphalt binder, mastic and fine aggregates mixture under cyclic tensile loading. The fatigue test results of asphalt binder show that the fatigue performance of asphalt binder is closely related with loading magnitude, temperature and loading rate. Mastic specimens with different filler content are tested and the results indicate that mastic specimens with 30% filler content show better fatigue resistance and higher permanent strain. The micro-structure analysis of mastic and mixture indicates that the fatigue resistance is closely related with the air void content of specimen. 3D digital specimens are developed to model the fatigue of the asphalt binder, mastic and mixture specimens based on the finite element method (FEM). Fatigue damage of asphalt concrete is simplified by a damage model. With proper selection of damage parameters, the simulation results agree well with laboratory test results and can be used as a basis for future fatigue research.

关键词： fatigue asphalt mixture asphalt binder mastic finite element method (FEM) X-ray tomography