Damage detection in structures using modified back-propagation neural networks

A nonparametric structural damage detection methodology based on neural networks method is presented for health monitoring of structure-unknown systems. In this approach appropriate neural networks are trained by use of the modal test data from a ‘healthy’ structure. The trained networks which are subsequently fed with vibration measurements from the same structure in different stages have the capability of recognizing the location and the content of structural damage and thereby can monitor the health of the structure. A modified back-propagation neural network is proposed to solve the two practical problems encountered by the traditional back-propagation method, i.e., slow learning progress and convergence to a false local minimum. Various training algorithms, types of the input layer and numbers of the nodes in the input layer are considered. Numerical example results from a 5-degree-of-freedom spring-mass structure and analyses on the experimental data of an actual 5-storey-steel-frame demonstrate that neural-networks-based method is a robust procedure and a practical tool for the detection of structural damage, and that the modified back-propagation algorithm could improve the computational efficiency as well as the accuracy of detection Project supported by the National Natural Science Foundation of China (No. 59908003) and the Natural Science Foundation of Hubei Province (No. 99J035).     

Mesh deformation based on artificial neural networks

In the article a new mesh deformation algorithm based on artificial neural networks is introduced. This method is a point-to-point method, meaning that it does not use connectivity information for calculation of the mesh deformation. Two already known point-to-point methods, based on interpolation techniques, are also presented. In contrast to the two known interpolation methods, the new method does not require a summation over all boundary nodes for one displacement calculation. The consequence of this fact is a shorter computational time of mesh deformation, which is proven by different deformation tests. The quality of the deformed meshes with all three deformation methods was also compared. Finally, the generated and the deformed three-dimensional meshes were used in the computational fluid dynamics numerical analysis of a Francis water turbine. A comparison of the analysis results was made to prove the applicability of the new method in every day computation.     

基于遗传神经网络的旋转机械故障预测方法研究

许多大型旋转机械运行工况恶劣,非平稳、非线性特征明显,以及各种突发性、偶然性因素的影响,给基于振动信号处理的状态预测和状态维护分析带来困难。神经网络以其强大的处理非线性系统的能力在故障预测中得到广泛的应用,但由于其在追求高精度训练目标时易陷入局部极值,且收敛速度慢甚至发散。针对这个问题,提出了采用遗传算法对神经网络连接权值和阈值进行优化,这样不仅发挥了神经网络广泛的映射特性也使遗传算法的全局搜索优势尽显无疑。通过组合这两种算法,在提升网络学习的准确度方面,优点尤其突出,最终提高对旋转机械故障预测和寿命估计的性能,这在某环境模拟试验系统动力风机的轴承磨损故障预测中得到了验证。     

用BP神经网络模型评价养殖区水域的富营养化——以湖州地区为例

根据养殖区水域富营养化程度主要影响因素和评价标准,用足够多的BP神经网络训练样本、检验样本和测试样本进行模拟学习,给出了区分养殖区富营养化程度的分界值,能够直观地进行不同等级富营养化程度的划分.所得到的神经网络模型具有较好的泛化能力和预测能力,减少了人为主观因素的影响,该模型有一定的客观性、通用性和实用性.实例分析表明,湖州地区养殖区外荡水域富营养化程度比较严重,处于富营养化和重富营养化状态.     

Neural Networks as a Tool for Quality Assessment of Soybean and Rapeseed Oils Analyzed by Thermogravimetry

The quality of commercial vegetable oils is usually evaluated via chemical parameters such as density, refractive index, saponification, iodine and acid values. In this paper, the applicability of thermal parameters for the quality assessment of vegetable oils is proposed. In order to achieve this goal, different back-propagation neural network architectures were trained, using chemical and thermal parameters as inputs. To avoid any accidental correlation due to the random initialization of the weights, each topology was repeated three times and three networks were chosen, with 5-3-2, 8-5-2 and 13-6-2 structures. The error function sum square error (SSE) was used as the criterion for finalization of the learning process. A model was developed for the correct classification of oils with regard to their type and quality. This revised version was published online in August 2006 with corrections to the Cover Date.     

Review of validation and reporting of non-targeted fingerprinting approaches for food authentication

Food fingerprinting approaches are expected to become a very potent tool in authentication processes aiming at a comprehensive characterization of complex food matrices. By non-targeted spectrometric or spectroscopic chemical analysis with a subsequent (multivariate) statistical evaluation of acquired data, food matrices can be investigated in terms of their geographical origin, species variety or possible adulterations. Although many successful research projects have already demonstrated the feasibility of non-targeted fingerprinting approaches, their uptake and implementation into routine analysis and food surveillance is still limited. In many proof-of-principle studies, the prediction ability of only one data set was explored, measured within a limited period of time using one instrument within one laboratory. Thorough validation strategies that guarantee reliability of the respective data basis and that allow conclusion on the applicability of the respective approaches for its fit-for-purpose have not yet been proposed. Within this review, critical steps of the fingerprinting workflow were explored to develop a generic scheme for multivariate model validation. As a result, a proposed scheme for “good practice” shall guide users through validation and reporting of non-targeted fingerprinting results. Furthermore, food fingerprinting studies were selected by a systematic search approach and reviewed with regard to (a) transparency of data processing and (b) validity of study results. Subsequently, the studies were inspected for measures of statistical model validation, analytical method validation and quality assurance measures. In this context, issues and recommendations were found that might be considered as an actual starting point for developing validation standards of non-targeted metabolomics approaches for food authentication in the future. Hence, this review intends to contribute to the harmonization and standardization of food fingerprinting, both required as a prior condition for the authentication of food in routine analysis and official control.     

Fuzzy regression analysis using neural networks

In this paper, we propose simple but powerful methods for fuzzy regression analysis using neural networks. Since neural networks have high capability as an approximator of nonlinear mappings, the proposed methods can be applied to more complex systems than the existing LP based methods. First we propose learning algorithms of neural networks for determining a nonlinear interval model from the given input-output patterns. A nonlinear interval model whose outputs approximately include all the given patterns can be determined by two neural networks. Next we show two methods for deriving nonlinear fuzzy models from the interval model determined by the proposed algorithms. Nonlinear fuzzy models whose h-level sets approximately include all the given patterns can be derived. Last we show an application of the proposed methods to a real problem.     

应用红外光谱技术快速检测月桂酸单甘油酯的品质指标

月桂酸单甘油酯是用途广泛的食品添加剂,在其制备过程中经分子蒸馏得到的制备品中会有月桂酸、甘油等杂质。用化学滴定或气相色谱等传统方法检测制备品中的月桂酸单甘油酯纯度及其杂质含量过程相当繁琐。为了对月桂酸单甘油酯制备品的品质进行快速定量,先利用气相色谱法确定不同工艺下的月桂酸单甘油酯产品中各成分的含量,再利用傅立叶红外光谱仪对月桂酸单甘油酯制备品进行分析,得到它们的光谱数据曲线,并结合主成分分析和反向传播神经网络建立回归模型。通过对实验结果的均方根误差预测值PRMSE以及相关系数r辨析,预测月桂酸单甘油酯含量的结果为PRMSE=3.6376,r=0.9950,预测甘油含量的结果为PRMSE=1.4764,r=0.9795,预测月桂酸含量的结果为PRMSE=1.2859,r=0.9247。结果表明,应用光谱分析方法能够较好检测月桂酸单甘油酯、月桂酸和甘油含量。     

非线性组合预测人民币汇率变动方法研究

本文利用神经网络中的反向传播算法 (BP算法 ) ,结合组合预测模型的思想 ,得到一种非线性组合预测方法。通过对人民币长期汇率的五种模型计算、比较分析 ,以及对一产品市场行情分析 ,说明我们提出的非线性组合预测是一种有效的预测分析工具 ,适合于象人民币汇率制定等需综合多种理论来分析的问题。