A flexible brand choice model based on neural net methodology A comparison to the linear utility multinomial logit model and its latent class extension

Brand choice models as a rule have a linear (deterministic) utility function, i.e. they conceive utility as linear combination of predictors like price, sales promotion variables, brand name and other product attributes. To discover nonlinear effects on brands' utilities in a flexible way we specify deterministic utility by means of a certain type of neural net. This feedforward multilayer perceptron is able to approximate any continuous multivariate function and its derivatives with the desired level of precision. In an empirical study the neural net based choice model leads to better out-of-sample results than homogeneous and heterogeneous versions of linear utility MNL models. On the other hand the latent class variant of the linear utility MNL model attains better fit values for estimation data than the neural net model. The neural net approach implies different choice elasticities for most predictors and identifies nonlinear effects (like interaction effects, thresholds, saturation effects). Received: November 3, 2000 / Accepted: March 7, 2002     

Research on Affordability Modeling of Aircraft Based on Effectiveness Indexes

With the cost estimation of military aircraft as the research object,this paper aims to study the contradiction between the choice of explanatory variables in index modeling and the maintaining of model validity.It analyzes and establishes a cost estimation modeling concept based on an Effectiveness Index and studies the way to construct Effectiveness Indexes for the sake of cost estimation modeling.Based on a case study,the paper establishes and analyzes the Effectiveness Index-based cost estimation models and DAPCA(Development And Procurement Costs of Aircraft)models developed by the RAND Corparation.The comparison of these models shows that the Effectiveness Index-based cost parameter models not only comprehensively consider the obvious driving parameter indexes of the cost,but reduces the variables of regressive analysis,hence giving the model a higher reliability.     

Dynamic inferential estimation using principal components regression (PCR)

Principal components regression (PCR) is applied to the dynamic inferential estimation of plant outputs from highly correlated data. A genetic algorithm (GA) approach is developed for the optimal selection of subsets from the available measurement variables, thereby providing a method of identifying nonessential elements. The theoretical link between principal components analysis (PCA) and state–space modelling is employed to identify a measurement equation involving the GA-selected subset, which is then used for inferential estimation of the omitted variables. These techniques are successfully demonstrated for the inferential estimation of outputs from a validated industrial benchmark simulation of an overheads condensor and reflux drum model (OCRD).     

Estimating Military Aircraft Cost Using Least Squares Support Vector Machines

A multi-layer adaptive optimizing parameters algorithm is developed for improving least squares support vector machines (LS-SVM), and a military aircraft life-cycle-cost (LCC) intelligent estimation model is proposed based on the improved LS-SVM. The intelligent cost estimation process is divided into three steps in the model. In the first step, a cost-drive-factor needs to be selected, which is significant for cost estimation. In the second step, military aircraft training samples within costs and cost-drive-factor set are obtained by the LS-SVM. Then the model can be used for new type aircraft cost estimation. Chinese military aircraft costs are estimated in the paper. The results show that the estimuted costs by the new model are closer to the true costs than that of the traditionally used methods.     

基于光纤应变传感器的型架定位器位置检测方法研究

针对飞机装配过程中型架定位器的位置变化,提出一种基于光纤应变传感器的定位器位置检测方法。通过光纤应变传感器对型架主体及定位器组件关键特征区域的应变和定位器位置变化量进行实时采集,对采集的数据进行分析和处理,采用BP（back propagation,反向传播）神经网络建立飞机型架不同区域应变量与定位器位置变化量之间的数学模型。在某型工艺装备上搭建型架定位器位置检测试验平台,根据试验数据分别建立了定位器在平面及空间范围受载下的位置检测神经网络模型。试验结果表明：当神经网络样本数量一定时,模型对定位器位置的预测精度与加载偏移角度有关,偏移角度越小,加载覆盖率越高,模型的预测精度越高。其中,平面内以30°间隔、空间以45°间隔加载时,建立的神经网络模型对定位器位置的预测精度满足定位要求,验证了本文方法的可行性。该方法摈弃了用数字化设备直接测量的传统方式,弥补了因视线遮挡而造成个别定位器位置无法被检测的缺陷,能对装配过程中所有定位器的位置进行检测,解决定位器位置偏差过大造成的飞机部件检测质量差的问题,提升了飞机的装配质量。     

Prediction of MOR and MOE of structural plywood board using an artificial neural network and comparison with a multivariate regression model

The structural application of plywood boards has increased considerably in recent years. In this context, determining plywood mechanical properties such as bending strength and modulus of elasticity through predictive models using more-easily obtained properties is a very useful tool for in-factory quality control. Artificial neural networks have demonstrated their high capacity for modelling complex relations between variables, considerably improving on results obtained through regression techniques. Four neural networks were developed to obtain these mechanical properties by determining board thickness, moisture content, specific gravity, bending strength and modulus of elasticity of test pieces of small dimensions. The results were compared with those of a regression model and in all cases the results of the present study were better.     

Proportional hazards modelling of aircraft cargo door complaints

Proportional hazards modelling is a powerful technique which can be used to investigate the effects of various explanatory variables on the life length of equipment. In this paper the analysis of aircraft cargo door complaints is considered, as this can cause serious delay problems. Particular attention is given to the assumptions supporting the application of the model. Consideration is given to problems in the choice of the appropriate basic metric time, definition of covariates and adapting the methodologies to this particular problem. Emphasis is placed upon the validation of the results by attempting several different structures of the dependent variables.     

Aircraft parameter estimation — A tool for development of aerodynamic databases

With the evolution of high performance modern aircraft and spiraling developmental and experimental costs, the importance of flight validated databases for flight control design applications and for flight simulators has increased significantly in the recent past. Ground-based and in-flight simulators are increasingly used not only for pilot training but also for other applications such as flight planning, envelope expansion, design and analysis of control laws, and handling qualities investigations. Most of these demand a high-fidelity aerodynamic database representing the flight vehicle. System identification methodology, evolved over the past three decades, provides a powerful and sophisticated tool to identify from flight data aerodynamic characteristics valid over the entire operational flight envelope. This paper briefly presents aircraft parameter estimation methods for both stable and unstable aircraft, highlighting the developmental work at the DLR Institute of Flight Mechanics. Various aspects of database identification and its validation are presented. Practical aspects like the proper choice of integration and optimization methods as well as limitations of gradient approximation through finite-differences are brought out. Though the paper focuses on application of system identification methods to flight vehicles, its use in other applications, like the modelling of inelastic deformations of metallic materials, is also presented. It is shown that there are many similar problems and several challenges requiring additional concepts and algorithms.     

基于神经网络混合建模的结构振动滑模控制

将神经网络和标称系统混合建模方法引入到离散滑模控制当中,得到神经网络滑模控制,然后对结构振动进行控制,振动结构为具有不确定性参数的柔性附件,并受到随机外扰作用。离散滑模控制的滑模面是以标称系统为基础,由最优二次型价值函数求解黎卡提方程确定。利用标称模型和神经网络混合建模方法来减小系统的不确定性,达到提高滑模控制在实际控制系统中的控制效果。其中利用前馈神经网络来对不确定部分进行建模。最后通过对滑模控制和神经网络滑模控制进行仿真,结果表明,本文所提出的神经网络滑模控制对具有不确定性参数和随机外扰的柔性结构系统振动的控制效果要优于滑模控制。     

Aircraft Combat Survivability Estimation and Synthetic Tradeoff Methods

A new concept is proposed that susceptibility, vulnerability, reliability, maintainability and supportability should be essential factors of aircraft combat survivability. A weight coefficient method and a synthetic method are proposed to estimate aircraft combat survivability based on the essential factors. Considering that it takes cost to enhance aircraft combat survivability, a synthetic tradeoff model between aircraft combat survivability and life cycle cost is built. The aircraft combat survivability estimation methods and synthetic tradeoff with a life cycle cost model will be helpful for aircraft combat survivability design and enhancement.     

Fractional derivatives and recurrent neural networks in rheological modelling – part I: theory

The aim of this paper was to develop a general approach based on fractional time derivatives and recurrent neural networks to model the rheological behaviour of asphalt materials. The paper focuses on elastic and viscoelastic material characteristics. It consists of two parts. In this first part, the theoretical aspects of modelling are discussed. A brief introduction into the theory of rheological elements based on fractional time derivatives is provided. The fractional differential equation of a general rheological element (base element) is developed from which a huge variety of other rheological elements can be derived, e.g. fractional Newton, Kelvin and standard solid elements. A new approach is presented for solving the fractional differential equations. Artificial neural networks are developed to compute the stress–strain–time behaviour of fractional rheological elements in a numerical efficient way. The approach is tested and verified. The second part of this work will appear later. It will be focused on applications of the new theoretical work to pavement engineering problems.     

基于长短时记忆神经网络的大跨拱桥温度-位移相关模型建立方法

建立温度-位移相关模型是开展基于位移响应的大跨桥梁性能评估的关键步骤.该文提出一种基于长短时记忆(LSTM)神经网络的多元温度-位移相关模型建立方法.充分利用LSTM神经网络能够考虑位移时滞效应和适合处理超长数据序列的优势,采用自适应矩估计方法对LSTM神经网络进行优化,并引入丢弃正则化技术提升模型的预测能力.在此基础...     

确定飞机最大抖振设计载荷的长期极值估计方法

确定飞机在抖振工况下的限制载荷是现代飞机动强度设计分析的关键步骤之一。运用次序统计和长期极值估计理论的极值Ⅰ型分布和Ⅲ型分布,在风洞试验数据基础上,分别应用最小二乘法和最大似然估计法进行极值模型的参数估计,并根据预设的重现期指标进行了某型飞机尾部结构抖振设计载荷的极值估计。探讨了极值分布概率模型、估计方法和样本数量对抖振载荷极值估计结果的影响。提出了实现准确有效极值估计的样本数量基本要求的指标,根据该指标可以确定最小振动响应采集时间,以指导测试方案和数据处理方法的制定。实例分析结果表明:极值Ⅲ型分布能够较好地估计抖振试验数据的极值(相对误差在±5%以内),且进行分布模型的参数估计时,最大似然法的精度略高于最小二乘法。对比分析的结果也表明,应用传统的3σ准则进行随机振动结构的限制载荷设计可能偏危险,不适于工程应用。     

Optimal input design for online parameter estimation for aircraft with multiple control surfaces

An optimal input design method is proposed for online parameter estimation for aircraft with multiple control surfaces. The optimal input is designed considering the input and output constraints. These constraints are constructed based on a military standard, MIL-STD-8785C, viz., the flying qualities of a piloted aircraft. The accuracy of parameter estimation using the optimal input is compared with that of parameter estimation using conventional doublet/3211 inputs. Two online parameter estimation schemes are also considered to evaluate the performance of the designed optimal input: a Bayesian method based on the time domain and an equation-error method based on the frequency domain. The recursive form of the Bayesian method is also derived. Numerical simulations are performed, and the performance, convergence, and accuracy of two online parameter estimation schemes are compared.     

Boundary defect recognition using neural networks

This research presents schemes for automated visual inspection for boundary defects and classification using neural networks. An efficient method for representing circular boundaries is proposed utilizing a curvature and circular fitting algorithm. For classification, two types of neural network modelling schemes are established. First, a multi-layer perceptron is discussed for defect classification problems. Second, a Hopfield network is modelled to be used for continuous-type variables by a minimizing energy function. Extensive tests are conducted on the casting parts, then the results of neural networks are compared with those of traditional pattern classifiers.     

基于RBF神经网络的诺西肽发酵过程菌体质量浓度软测量

针对诺西肽发酵过程中菌体质量浓度的估计问题,提出了一种基于RBF神经网络的软测量建模方法.在诺西肽发酵过程非结构模型的基础上,根据隐函数存在定理确定出辅助变量,从而使其选择有严格的理论依据;根据每批样本数据对被预测对象的预估能力,自适应地为各个批次的训练样本分配权值,并进而实施加权RBF神经网络建模.实际应用表明,所提出的软测量建模方法是有效的.     

A neural network decision-making model for job-shop scheduling

Scheduling in a job-shop system is a challenging task. Simulation modelling is a well-known approach for evaluating the scheduling plans of a job-shop system; however, it is costly and time-consuming, and developing a model and interpreting the results requires expertise. As an alternative, we have developed a neural network (NN) model focused on detailed scheduling that provides a versatile job-shop scheduling analysis framework for management to easily evaluate different possible scheduling scenarios based on internal or external constraints. A new approach is also proposed to enhance the quality of training data for better performance. Previous NN models in scheduling focus mainly on job sequencing and simple operations flow, and may not consider the complexities of real-world operations. The proposed model’s output proved statistically equivalent to the results of the simulation model. The study was accomplished using sensitivity analysis to measure the effectiveness of the input variables of the NN model and their impact on the output, revealing that the batch size variable had a significant impact on the scheduling results in comparison with other variables.     

飞机噪声计算通用模型研究

为完善和规范现行的飞机噪声计算方法,根据飞行航线的几何特点,基于“直线段”和“曲线段”这两个基本的航线元素提出了航线分解的思想,阐述了其基本原理,建立了系统的飞机噪声计算通用模型,并实例验证了该模型的可行性和实用性。该模型解决了实际噪声环境影响评价工作中的相关技术问题,规范了噪声计算方法,使整个评价工作更直观、更智能、更科学。     

Product Assembly Cost Estimation Based on Artificial Neural Networks

1　ＩｎｔｒｏｄｕｃｔｉｏｎＤｕｒｉｎｇｔｈｅｐｒｏｄｕｃｔｄｅｓｉｇｎｓｔａｇｅ ,ｉｔｉｓｎｅｃｅｓｓａｒｙｔｏｅｓｔｉｍａｔｅｐｒｏｄｕｃｔｃｏｓｔｓｏｔｈａｔｗｅｃａｎｕｓｅｔｈｉｓｉｎｆｏｒｍａｔｉｏｎｔｏｅｖａｌｕａｔｅｔｈｅｐｒｏｄｕｃｔｄｅｓｉｇｎｅｃｏｎｏｍｉｃａｌｌｙ ,ｔｏａｄｊｕｓｔｔｈｅｄｅｓｉｇｎｓｃｈｅｍｅｔｏｒｅｄｕｃｅｃｏｓｔｉｎｔｉｍｅａｎｄａｓａｃｏｎｓｅｑｕｅｎｃｅｔｏｃｏｎｔｒｏｌｔｈｅｐｒｏｄｕｃｔｃｏｓｔｅｆｆｅｃｔｉｖｅｌｙ .Ｔｈｅｐｒｏｄｕｃｔｃｏｓ…