Modeling and solving the bi-objective capacitated location-routing problem with probabilistic travel times

The location-routing problem (LRP) is a relatively new research area within location analysis that concerns simultaneously both the problems of location of facilities and routing of vehicles among the established facilities and the demand points. In this work, we address the capacitated LRP with probabilistic travel times, which may arise in many practical contexts in logistics and supply chain management, and present some bi-objective mathematical programming formulations to model the problem using different stochastic programming approaches. The first objective is to minimize the overall system-wide costs, while the second objective concerns minimization of the maximum delivery time to the customers. In all the cases, the deterministic equivalents of the stochastic models have been extracted. To solve the resulted models, a variable neighborhood descent-based heuristic is proposed and finally computational study is performed and numerical results are reported.     

Probabilistic dynamic distribution of wireless sensor networks with improved distribution method based on electromagnetism-like algorithm

Performance of the Wireless Sensor Networks (WSNs) depends significantly on coverage area which is determined via the effective dynamic distribution of sensors. Making mobile sensors’ dynamic distributions, which determines their positions within the network effectively, improves performances of WSNs by enabling sensors to form the coverage area more efficiently. In this paper, we initially propose the electromagnetism-like (EM) algorithm as the sensor distribution strategy to increase the coverage area of network after random distribution of sensors. Forming more effective coverage area by using mobile and stationary sensors and probabilistic detection model has been aimed by developing the Optimal Sensor Detection Algorithm that is based on the proposed EM algorithm (OSDA-EM). For this purpose, it has been thought that we would attain to more realistic results, with probabilistic detection model by forming the coverage area more effectively. Additionally, performance of the developed OSDA-EM algorithm has been compared with the Particle Swarm Optimization (PSO) and Artificial Bee Colony (ABC) algorithms which was previously used in the dynamic distribution of WSNs. Simulation results have shown that the developed OSDA-EM can be preferred in dynamic distribution of WSNs that performed with probabilistic detection model.     

Transient dynamics in structures with non-homogeneous uncertainties induced by complex joints

This paper deals with numerical models for the prediction of the transient dynamical response induced by shocks upon structures with complex joints and shows experimental comparisons. The usual numerical methods for analysing such structures in the low- and medium-frequency ranges consist in using reduced matrix models constructed with the elastic modes. The contribution of the higher modes is very sensitive to the model errors and to the data errors. In this paper, a non-parametric probabilistic method is applied to construct the random matrix model allowing model errors and data errors to be taken into account. The paper presents an extension of the non-parametric method for the case of non-homogeneous model errors through the structure. A dynamic substructuring method is then used and the non-parametric probabilistic model of random uncertainties is used in each substructure with its own level of uncertainties. This approach is applied to a dynamical system made of two plates attached by a complex joint. Experiments have been performed and are used to validate the probabilistic predictive model.     

基于支持向量机和顺序前项选择算法的PNN风电机组液压变桨的故障诊断

针对液压变桨距系统的强耦合、非线性,以及液压变桨距故障发生原因复杂、故障单一造成的定位问题,该文提出基于支持向量机和顺序前项选择算法的概率神经网络诊断方法。首先,选取SCADA数据的特征值为输入,桨距角为输出,利用支持向量机进行模型的回归,得出桨距角输出的预测值;接着,将测量值与预测值带入顺序前项选择算法,挖掘和发现特征与故障之间的关系,评估各特征之间的重要性,并选出最好的一组特征集合;最后,建立变桨距概率诊断模型,将所选的数据送到故障诊断模型进行训练,再用所选数据进行测试,定位出变桨距系统的故障原因。实验分析表明:基于支持向量机和顺序前项选择算法的概率神经网络液压变桨距故障诊断方法可以有效地分辨出不同故障,并且诊断的精确度得到了提高。     

结构可靠性分析的概率和非概率混合模型

在结构可靠性分析中需要合理地定量处理影响结构性能的诸多不确定性。不确定性的模拟既可以是概率的，也可以是非概率的。文中简要介绍结构可靠性分析的概率方法和基于区间模型的非概率可靠性方法。提出结构可靠性分析的概率和非概率混合模型。通过两级功能方程的逐次建立及可靠性分析，给出结构可靠的概率度量。实例分析说明在结构可靠性分析中，应根据不确定性的产生机理及所掌握的数据信息合理地选取分析模型。     

Probabilistic uncertainty analysis of an FRF of a structure using a Gaussian process emulator

This paper introduces methods for probabilistic uncertainty analysis of a frequency response function (FRF) of a structure obtained via a finite element (FE) model. The methods are applicable to computationally expensive FE models, making use of a Bayesian metamodel known as an emulator. The emulator produces fast predictions of the FE model output, but also accounts for the additional uncertainty induced by only having a limited number of model evaluations. Two approaches to the probabilistic uncertainty analysis of FRFs are developed. The first considers the uncertainty in the response at discrete frequencies, giving pointwise uncertainty intervals. The second considers the uncertainty in an entire FRF across a frequency range, giving an uncertainty envelope function. The methods are demonstrated and compared to alternative approaches in a practical case study.     

机构运动精度可靠性分析方法的研究

通过直接对机构独立运动方程组全微分，建立了以矩阵运算形式表达的机构运动（包括位移、速度和加速度）精度概率分析的一般模型。在概率分析的基础上，引入机构运动精度可靠性的概念，将机构运动精度可靠性定义为机构输出误差落在最大允许误差范围内的概率。提出了机构运动精度可靠性分析的随机过程方法和随机变量方法     

机械静强度可靠性设计的非概率方法

将可限界不确定参量作为区间变量,针对概率可靠性模型的一些局限性,提出一 种机械零部件静强度的非概率可靠性设计方法。该方法和概率可靠性设计具有一定 的类比性,运算简便,且对原始数据要求低。研究表明：该设计方法是实用和可行的。     

微电子封装引线键合工艺参数的概率设计

建立多组不同网格密度的二维引线键合工艺有限元模型,从中选择一种精度较高、计算速度较快的模型进行数值模拟,并在此基础上采用Ansys概率有限元分析模块,选择蒙特卡洛模拟方法对引线键合工艺进行概率可靠性分析。研究和讨论各材料层中最大应力可能的分布区域以及应力对金属球直径、铝层厚度、键合高度、钢嘴几何结构和铝、铜与层间绝缘层ILD(interlayer dielectric)材料属性的敏感度。结果表明,金属球直径、铝层厚度、键合高度对应力的影响最明显,而其他输入参数对应力没有明显影响。     

Comprehensive model for predicting surface roughness of ground workpieces considering the plowing effect

Due to the stochastic nature of grinding process, a probabilistic model is considered to be the most appropriate solution for predicting the surface roughness of ground workpiece. However, the existing probabilistic models in the literature do not systematically take into account the contribution of plowing effect. As such, this work incorporates the pile-up ridges from plowing phenomenon and their overlapping effect into a probabilistic model. When the distance between two neighboring grooves left on the workpiece surface by the abrasive grains varies, the ridges will pile upon each other or the grooves will intersect with each other. These different interaction modes of grooves or ridges are discussed in the probabilistic model to predict the surface roughness. The improved Powell method is used to perform the prediction. A series of grinding experiments were performed to validate the proposed model and the result shows that the predicted values agree very well with the measured values with an average prediction accuracy of 90.4%.     

Sensor fault diagnosis with a probabilistic decision process

In this paper a probabilistic approach to sensor fault diagnosis is presented. The proposed method is applicable to systems whose dynamic can be approximated with only few active states, especially in process control where we usually have a relatively slow dynamics. Unlike most existing probabilistic approaches to fault diagnosis, which are based on Bayesian Belief Networks, in this approach the probabilistic model is directly extracted from a parity equation. The relevant parity equation can be found using a model of the system or through principal component analysis of data measured from the system. In addition, a sensor detectability index is introduced that specifies the level of detectability of sensor faults in a set of analytically redundant sensors. This index depends only on the internal relationships of the variables of the system and noise level. The method is tested on a model of the Tennessee Eastman process and the result shows a fast and reliable prediction of fault in the detectable sensors.     

Uncertainty analysis of deep drawing using surrogate model based probabilistic method

Deep drawing is an important manufacturing process in industry. In order to obtain high-quality products produced by deep drawing, the set of design variables used in forming operation is designed through deterministic optimization. However, in real forming process, the design variables show variability and randomness which will affect the product quality. These uncertainties are an inherent characteristic of nature and cannot be avoided. This paper focuses on uncertainty analysis of deep drawing with the consideration of uncertainties in material parameters and friction. An uncertainty analysis approach which combines the finite element method (FEM) simulation, surrogate modeling, and Monte Carlo simulation (MCS) is presented in this work. The constructed surrogate models are validated and compared by cross validation and error measures. Then Monte Carlos Simulation is conducted by the use of the constructed surrogate model. The surrogate model based probabilistic method used in this paper is an approach with high-efficiency and sufficient accuracy for uncertainty analysis in deep drawing.     

A robust optimization model for p-median problem with uncertain edge lengths

In this paper, we propose a p-median problem with uncertain edge lengths where uncertainty is characterized by given intervals. The uncertainty in edge lengths may appear in transportation costs or travel times along the edges in any network location problem. Minimax regret approach is a promising tool to cope with uncertainty in network location problems. However, minimax regret algorithms normally suffer from complexity, and they are time consuming. We propose a robust optimization approach to obtain the robust linear counterpart for the same class of the nominal p-median problem. The performance of the proposed model is compared with minimax regret approach through a simple but illustrative example, and results are discussed in more details.     

Aspects Regarding the Use of Probabilistic Models for Isothermal Full Film Rough Line Contacts

This article presents a method to improve the classical probabilistic EHL models by incorporating deterministic EHL results. We first provide a review of the latest developments in the probabilistic approach for the solution of a mixed EHL problem, as well as a review of the latest deterministic EHL results that can impact the probabilistic formulations. Next, we present a probabilistic algorithm for the computations of the load supported by the fluid, the elastically deformed asperities, and the plastically deformed asperities in a mixed EHL contact. The Chang-Etsion-Bogy elastoplastic micro contact model is used together with a corresponding probabilistic fluid flow model. We also present an approach in which the elastic roughness deformation induced by the oil film can be incorporated into the probabilistic model via the use of the amplitude reduction technique.     

应变疲劳可靠性理论与方法的新进展

介绍概率应变疲劳试验法、评价模型和损伤随机演化机制方面的新进展。突破经典极大似然法在参考试验载荷之外的单试样限制，提出新的广义极大似然疲劳试验法。新发现随机循环应力—应变响应现象并建立其概率模型。新发展概率疲劳应变一寿命模型。概率模型参数由称为广义极大似然法的方法确定，在整体数据层面综合考虑数据分散性规律与样本量对概率评价的影响。考虑随机应力—应变关系反映“随机应变载荷”、随机应变—寿命关系揭示材料的“应变强度”，提出随机应变载荷—强度干涉恒幅可靠性模型，与Keciguliu的递推法结合可进行变幅和应变载荷谱下的可靠性分析，形成了应变疲劳可靠性理论和方法的新体系。进一步根据有效短裂纹准则，揭示疲劳性能随机及演化性的本质原因源于主导有效短裂纹萌生区域及其裂尖区域微观结构扩展条件的差异及演化性；随机疲劳裂纹扩展、应变—寿命和应力—应变关系是3个关联的随机疲劳关系；疲劳损伤是一个由初始混沌状态，到独立无关的随机状态，然后到史相关随机状态的演化过程。     

An overview of state‐of‐the‐art image restoration in electron microscopy

In Life Science research, electron microscopy (EM) is an essential tool for morphological analysis at the subcellular level as it allows for visualization at nanometer resolution. However, electron micrographs contain image degradations such as noise and blur caused by electromagnetic interference, electron counting errors, magnetic lens imperfections, electron diffraction, etc. These imperfections in raw image quality are inevitable and hamper subsequent image analysis and visualization. In an effort to mitigate these artefacts, many electron microscopy image restoration algorithms have been proposed in the last years. Most of these methods rely on generic assumptions on the image or degradations and are therefore outperformed by advanced methods that are based on more accurate models. Ideally, a method will accurately model the specific degradations that fit the physical acquisition settings. In this overview paper, we discuss different electron microscopy image degradation solutions and demonstrate that dedicated artefact regularisation results in higher quality restoration and is applicable through recently developed probabilistic methods.     

机构速度和加速度分析统一模型的研究

研究了适应于任意机构的通用速度和加速度的分析模型 ,研究中采用了四个有特色的技术 :(1)基于齐次变换矩阵位移方程推导统一模型 ;(2 )在速度和加速度统一模型中使用了齐次矩阵的全部位置和姿态信息 ,这样既避免了有效方程的挑选 ,又简化了模型构造过程 ;(3)采用向量标记推导模型 ,简化了模型结构 ,同时描述了模型的构成 ;(4 )通过引入变量存在系数 ,使各个环路或构件路径的速度和加速度模型的结构形式完全一致和统一。这样 ,本文得到了统一的速度和加速度模型 ,这些模型适应于任意连杆机构 ;结构精练、标准 ;可以被自动构造 ,且构造效率高。本文为通用机构分析软件开发打下了基础。     

基于小波分析与概率神经网络的化工过程故障诊断

针对复杂化工过程,提出了一种结合小波分析与概率神经网络（PNN）的故障诊断方法（HWPNN方法）,即利用Haar小波分析对过程原始数据进行消噪处理,然后将重构的逼近系数作为输入样本送入概率神经网络完成故障诊断。将HWPNN方法应用于TE过程（一个化工生产过程,由Tennessee Eastman公司控制小组提出）的15种故障进行实验,并与将原始数据直接送入概率神经网络作故障诊断的PNN方法进行了比较,实验结果表明HWPNN方法的故障诊断的准确率明显高于PNN方法。HWPNN方法的诊断准确率达到了100％,是一种可行而有效的化工过程的故障诊断方法。     

Cutting force-based real-time estimation of tool wear in face milling using a combination of signal processing techniques

In this paper, combinations of signal processing techniques for real-time estimation of tool wear in face milling using cutting force signals are presented. Three different strategies based on linear filtering, time-domain averaging and wavelet transformation techniques are adopted for extracting relevant features from the measured signals. Sensor fusion at feature level is used in search of an improved and robust tool wear model. Isotonic regression and exponential smoothing techniques are introduced to enforce monotonicity and smoothness of the extracted features. At the first stage, multiple linear regression models are developed for specific cutting conditions using the extracted features. The best features are identified on the basis of a statistical model selection criterion. At the second stage, the first-stage models are combined, in accordance with proven theory, into a single tool wear model, including the effect of cutting parameters. The three chosen strategies show improvements over those reported in the literature, in the case of training data as well as test data used for validation—for both laboratory and industrial experiments. A method for calculating the probabilistic worst-case prediction of tool wear is also developed for the final tool wear model.     

Probabilistic fatigue life prediction methodology for notched components based on simple smooth fatigue tests

The methodology of probabilistic fatigue life prediction for notched components based on smooth specimens is presented. Weakestlink theory incorporating Walker strain model has been utilized in this approach. The effects of stress ratio and stress gradient have been considered. Weibull distribution and median rank estimator are used to describe fatigue statistics. Fatigue tests under different stress ratios were conducted on smooth and notched specimens of titanium alloy TC11. The proposed procedures were checked against the test data of TC11 notched specimens. Prediction results of 50 % survival rate are all within a factor of two scatter band of the test results.