Multi-objective shape optimization of transonic airfoil sections using swarm intelligence and surrogate models

In this article, the optimization problem of designing transonic airfoil sections is solved using a framework based on a multi-objective optimizer and surrogate models for the objective functions and constraints. The computed Pareto-optimal set includes solutions that provide a trade-off between maximizing the lift-to-drag ratio during cruise and minimizing the trailing edge noise during the aircraft’s approach to landing. The optimization problem was solved using a recently developed multi-objective optimizer, which is based on swarm intelligence. Additional computational intelligence tools, e.g., artificial neural networks, were utilized to create surrogate models of the objective functions and constraints. The results demonstrate the effectiveness and efficiency of the proposed optimization framework when applied to simulation-based engineering design optimization problems.     

Design optimization with back-propagation neural networks

A methodology with back-propagation neural network models is developed to explore the artificial neural nets (ANN) technology in the new application territory of design optimization. This design methodology could go beyond the Hopfield network model, Hopfield and Tank (1985), for combinatorial optimization problems In this approach, pattern classification with back-propagation network, the most demonstrated power of neural networks applications, is utilized to identify the boundaries of the feasible and the infeasible design regions. These boundaries enclose the multi-dimensional space within which designs satisfy all design criteria. A feedforward network is then incorporated to perform function approximation of the design objective function. This approximation is performed by training the feedforward network with objective functions evaluated at selected design sets in the feasible design regions. Additional optimum design sets in the classified feasible regions are calculated and included in the successive training sets to improve the function mapping. Iteration is continued until convergent criteria are satisfied. This paper demonstrates that the artificial neural nets technology provides a global perspective of the entire design space with good and near optimal solutions. ANN can indeed be a potential technology for design optimization.     

基于支持向量机的蒙脱土悬浮液电动电位预测

应用多元线性回归、人工神经网络、支持向量机3种方法,对加入聚乙二醇、十二烷基苯磺酸钠、石油磺酸盐和部分水解聚丙烯酰胺四种处理剂的蒙脱土悬浮液的电动电位进行预测。在模型训练中,分别采用了神经网络集成和非启发式参数优化来提高人工神经网络和支持向量机模型的泛化能力。检验结果表明,参数优化的支持向量机模型预测精度最高,其平均误差率为3.88%,最大误差率为7.55%。     

Surrogate modeling approximation using a mixture of experts based on EM joint estimation

An automatic method to combine several local surrogate models is presented. This method is intended to build accurate and smooth approximation of discontinuous functions that are to be used in structural optimization problems. It strongly relies on the Expectation−Maximization (EM) algorithm for Gaussian mixture models (GMM). To the end of regression, the inputs are clustered together with their output values by means of parameter estimation of the joint distribution. A local expert is then built (linear, quadratic, artificial neural network, moving least squares) on each cluster. Lastly, the local experts are combined using the Gaussian mixture model parameters found by the EM algorithm to obtain a global model. This method is tested over both mathematical test cases and an engineering optimization problem from aeronautics and is found to improve the accuracy of the approximation.     

The integration of design of experiments, surrogate modeling and optimization for thermoscience research

This paper presents an integrated approach for the solution of complex optimization problems in thermoscience research. The cited approach is based on the design of computational experiments (DOE), surrogate modeling, and optimization. The DOE/surrogate modeling techniques under consideration include: A-optimal/classical linear regression, Latin hypercube/artificial neural networks, and Latin hypercube/Sugeno-type fuzzy models. These techniques are coupled with both local (modified Newtons method) and global (genetic algorithms) optimization methods. The proposed approach proved to be an effective, efficient and robust modeling and optimization tool in the context of a case study, and holds promise for use in larger scale optimization problems in thermoscience research.     

Forecasting daily total ozone concentration—a comparison between neurocomputing and statistical approaches

The present paper develops three predictive models for daily total ozone concentration over Arosa, Switzerland. The models are artificial neural network, multiple linear regression, and persistence forecast. Each model was judged for their predictive ability using analysis of variance, Pearson correlation study, and scatterplot analysis. Prediction errors were computed for each model. After painstaking analysis it was established that artificial neural network produces better forecasts than the statistical approaches like multiple linear regression and persistence forecast models.     

An optimization methodology for machine learning strategies and?regression problems in ballistic impact scenarios

In domains with limited data, such as ballistic impact, prior researches have proven that the optimization of artificial neural models is an efficient tool for improving the performance of a classifier based on MultiLayer Perceptron. In addition, this research aims to explore, in the ballistic domain, the optimization of other machine learning strategies and their application in regression problems. Therefore, this paper presents an optimization methodology to use with several approaches of machine learning in regression problems, maximizing the limited dataset and locating the best network topology and input vector of each network model. This methodology is tested in real regression scenarios of ballistic impact with different artificial neural models, obtaining substantial improvement in all the experiments. Furthermore, the quality stage, based on criteria of information theory, enables the determination of when the complexity of the network design does not penalize the fit over the data and thereby the selection of the best neural network model from a series of candidates. Finally, the results obtained show the relevance of this methodology and its application improves the performance and efficiency of multiple machine learning strategies in regression scenarios.     

Artificial Neural Network Approach to Data Matrix Laser Direct Part Marking

Certain applications have recently appeared in industry where a traditional bar code printed on a label will not survive because the item to be tracked has to be exposed to harsh environments. Laser direct-part marking is a manufacturing process used to create permanent marks on a substrate that could help to alleviate this problem. In this research, artificial neural networks were employed to model the laser direct-part marking process of Data Matrix symbols on carbon steel substrates. Several experiments were conducted to study the laser direct-part marking process and to generate data to serve as training, validation and testing data sets in the artificial neural networks modeling process. Two performance measures, mean squared error and correlation coefficient, were utilized to assess the performance of the artificial neural network models. Single-output artificial neural network models corresponding to four performance measures specific to the Data Matrix bar code symbology were found to have good learning and predicting capabilities. The single-output artificial neural network models were compared to equivalent multiple linear regression models for validation purposes. The prediction capability of the single-output artificial neural network models with respect to laser direct-part marking of Data Matrix symbols on carbon steel substrates was superior to that of the multiple linear regression models.     

光滑神经网络解决非李普西茨优化问题的研究

为寻求满足约束条件的优化问题的最优解,针对目标函数是非李普西茨函数,可行域由线性不等式或非线性不等式约束函数组成的区域的优化问题,构造了一种光滑神经网络模型。此模型通过引进光滑逼近技术将目标函数由非光滑函数转换成相应的光滑函数以及结合惩罚函数方法所构造而成。通过详细的理论分析证明了不论初始点在可行域内还是在可行域外,光滑神经网络的解都具有一致有界性和全局性,以及光滑神经网络的任意聚点都是原始优化问题的稳定点等结论。最后通过几个简单的仿真实验证明了理论的正确性。     

Quantile regression neural networks: Implementation in R and application to precipitation downscaling

The qrnn package for R implements the quantile regression neural network, which is an artificial neural network extension of linear quantile regression. The model formulation follows from previous work on the estimation of censored regression quantiles. The result is a nonparametric, nonlinear model suitable for making probabilistic predictions of mixed discrete-continuous variables like precipitation amounts, wind speeds, or pollutant concentrations, as well as continuous variables. A differentiable approximation to the quantile regression error function is adopted so that gradient-based optimization algorithms can be used to estimate model parameters. Weight penalty and bootstrap aggregation methods are used to avoid overfitting. For convenience, functions for quantile-based probability density, cumulative distribution, and inverse cumulative distribution functions are also provided. Package functions are demonstrated on a simple precipitation downscaling task.     

Optimum design of aerospace structural components using neural networks

The application of artificial neural networks to capture structural design expertise is demonstrated. The principal advantage of a trained neural network is that it requires a trivial computational effort to produce an acceptable new design. For the class of problems addressed, the development of a conventional expert system would be extremely difficult. In the present effort, a structural optimization code with multiple nonlinear programming algorithms and an artificial neural network code NETS were used. A set of optimum designs for a ring and two aircraft wings for static and dynamic constraints were generated using the optimization codes. The optimum design data were processed to obtain input and output pairs, which were used to develop a trained artificial neural network using the code NETS. Optimum designs for new design conditions were predicted using the trained network. Neural net prediction of optimum designs was found to be satisfactory for the majority of the output design parameters. However, results from the present study indicate that caution must be exercised to ensure that all design variables are within selected error bounds.     

A NEURAL NETWORK-BASED SYSTEM FOR PREDICTION OF COMPUTER USER COMFORT

This article proposes a neural network-based system for prediction of computer user comfort with respect to the existing settings of the workstation. In this context, anthropometric measures and the existing measures of a computer workstation were related to back-support comfort, distance comfort, keyboard comfort, monitor comfort, and seat comfort using two distinct modeling approaches—multiple linear regression and artificial neural network. The purpose of this article was to compare and contrast the resulting models. The data from 144 computer workstations were used and a total of 12 different data types such as shoulder to elbow, eye to buttock, pan height, monitor height, or distance from the chair were recorded. While multiple linear regression could not be used to adequately predict the computer workstation comfort, the neural network was deemed superior. This approach allows ergonomists to aid in the decision-making process of computer environment design and the prediction of the health risk in an occupational environment.     

Metamodeling development for reliability-based design optimization of automotive body structure

Metamodels are commonly used in reliability-based design optimization (RBDO) due to the enormously expensive computation cost of numerical simulations. However, for large-scale design optimization of automotive body structure, with the increasing number of design variable and enhanced nonlinearity degree of structural performance, polynomial response surface which is commonly used for vehicle design optimization often suffers exponentially increased computation burden and serious loss of approximation accuracy. In this paper, support vector regression, along with other four complex metamodeling techniques including moving least square, artificial neural network, radial basis function and Kriging, is investigated for approximating frontal crashworthiness performance which is one of the most highly nonlinear performances. It aims at testing support vector regression and providing advanced metamodeling technique for RBDO of automotive body structure. Approximation results are compared in both accuracy and computational efficiency. Based on the frontal crashworthiness example, it is found that support vector regression and moving least square are preferable techniques to approximate structural performances with good accuracy. But support vector regression is recommended for its computational efficiency and better approximation potential. Moreover, the ensemble of support vector regression, moving least square, Kriging and artificial neural network is an effective alternative and is proved, in the RBDO example for the lightweight design of front body structure, to outperform any other single metamodel. The remarkable predominance indicates that the ensemble of support vector regression, moving least square, Kriging and artificial neural network holds great potential in approximating highly nonlinear performances for RBDO of automotive body structure.     

Generation of optimal artificial neural networks using a pattern search algorithm: application to approximation of chemical systems

A pattern search optimization method is applied to the generation of optimal artificial neural networks (ANNs). Optimization is performed using a mixed variable extension to the generalized pattern search method. This method offers the advantage that categorical variables, such as neural transfer functions and nodal connectivities, can be used as parameters in optimization. When used together with a surrogate, the resulting algorithm is highly efficient for expensive objective functions. Results demonstrate the effectiveness of this method in optimizing an ANN for the number of neurons, the type of transfer function, and the connectivity among neurons. The optimization method is applied to a chemistry approximation of practical relevance. In this application, temperature and a chemical source term are approximated as functions of two independent parameters using optimal ANNs. Comparison of the performance of optimal ANNs with conventional tabulation methods demonstrates equivalent accuracy by considerable savings in memory storage. The architecture of the optimal ANN for the approximation of the chemical source term consists of a fully connected feedforward network having four nonlinear hidden layers and 117 synaptic weights. An equivalent representation of the chemical source term using tabulation techniques would require a 500 x 500 grid point discretization of the parameter space.     

Multipoint cubic surrogate function for sequential approximate optimization

Multipoint cubic approximations are investigated as surrogate functions for nonlinear objective and constraint functions in the context of sequential approximate optimization. The proposed surrogate functions match actual function and gradient values, including the current expansion point, thus satisfying the zero and first-order necessary conditions for global convergence to a local minimum of the original problem. Function and gradient information accumulated from multiple design points during the iteration history is used in estimating a reduced Hessian matrix and selected cubic terms in a design subspace appropriate for problems with many design variables. The resulting approximate response surface promises to accelerate convergence to an optimal design within the framework of a trust region algorithm. The hope is to realize computational savings in solving large numerical optimization problems. Numerical examples demonstrate the effectiveness of the new multipoint surrogate function in reducing errors over large changes in design variables.     

基于机器学习的机器人辅助椎弓根植钉规划

为了解决脊柱手术机器人辅助实施椎弓根植钉过程中的图像辅助定位问题,该文提出了一种基于机器学习策略的椎弓根植钉规划方法。该方法利用卷积神经网络对脊柱计算机断层扫描(CT)图像进行学习和训练,通过建立神经网络模型确定网络内各层间的调整参数,然后对样本图像进行特征提 取并分类,采用交叉验证法对样本数据进行训练,验证卷积神经网络模型的正确性。通过机器学习方法对计算机断层扫描图像中适合做椎弓根植钉手术规划的图像区域进行识别,从而快速定位到植钉安全约束区域,并通过相应的图像处理方法实现植钉操作规划。医生只需要基于安全约束区域内的植钉规划完成最终的手术任务规划,能够显著提升手术效率。     

A surrogate-based optimization method with RBF neural network enhanced by linear interpolation and hybrid infill strategy

In engineering, it is computationally prohibitive to directly employ costly models in optimization. Therefore, surrogate-based optimization is developed to replace the accurate models with cheap surrogates during optimization for efficiency. The two key issues of surrogate-based optimization are how to improve the surrogate accuracy by making the most of the available training samples, and how to sequentially augment the training set with certain infill strategy so as to gradually improve the surrogate accuracy and guarantee the convergence to the real global optimum of the accurate model. To address these two issues, a radial basis function neural network (RBFNN) based optimization method is proposed in this paper. First, a linear interpolation (LI) based RBFNN modelling method, LI-RBFNN, is developed, which can enhance the RBFNN accuracy by enforcing the gradient match between the surrogate and the trend observed from the training samples. Second, a hybrid infill strategy is proposed, which uses the surrogate prediction error based surrogate lower bound as the optimization objective to locate the promising region and meanwhile employs a linear interpolation-based sequential sampling approach to improve the surrogate accuracy globally. Finally, extensive tests are investigated and the effectiveness and efficiency of the proposed methods are demonstrated.     

基于代理模型和遗传算法的仿真优化研究

首先由已知样本建立神经网络作为代理模型，替代费时的仿真评价而快速给出近似目标值；然后基于代理模型，采用GA进行决策量寻优．为增强优化结果的可靠性和一致性，讨论了按问题信息选取样本和多模型方法.基于典型压力管设计问题的数值仿真，验证了所提出方法的可行性和有效性，其结果明显优于现有文献结果.     

An artificial neural network model for estimating crop yields using remotely sensed information

Crop yield forecasting is a very important task for researchers in remote sensing. Problems exist with traditional statistical modelling (especially regression models) of nonlinear functions with multiple factors in the cropland ecosystem. This paper describes the successful application of an artificial neural network in developing a model for crop yield forecasting using back-propagation algorithms. The model has been adapted and calibrated using on the ground survey and statistical data, and it has proven to be stable and highly accurate.     

Analysis of service satisfaction in web auction logistics service using a combination of Fruit fly optimization algorithm and general regression neural network

When constructing classification and prediction models, most researchers used genetic algorithm, particle swarm optimization algorithm, or ant colony optimization algorithm to optimize parameters of artificial neural network models in their previous studies. In this paper, a brand new approach using Fruit fly optimization algorithm (FOA) is adopted to optimize artificial neural network model. First, we carried out principal component regression on the results data of a questionnaire survey on logistics quality and service satisfaction of online auction sellers to construct our logistics quality and service satisfaction detection model. Relevant principal components in the principal component regression analysis results were selected for independent variables, and overall satisfaction level toward auction sellers’ logistics service as indicated in the questionnaire survey was selected as a dependent variable for sample data of this study. In the end, FOA-optimized general regression neural network (FOAGRNN), PSO-optimized general regression neural network (PSOGRNN), and other data mining techniques for ordinary general regression neural network were used to construct a logistics quality and service satisfaction detection model. In the study, 4–6 principal components in principal component regression analysis were selected as independent variables of the model. Analysis results of the study show that of the four data mining techniques, FOA-optimized GRNN model has the best detection capacity.