计算机模式识别在煤矿顶板分类中的应用

本文利用新兴的边缘科学——计算机模式识别技术,对煤矿井下回采工作面顶板进行分类。实践证明,这是一种非常有效的方法,使模式识别这门新学科应用于煤炭生产实际。

Numerical and experimental evaluation on methods for parameter identification of thermal response tests

Several parameter identification methods of thermal response test were evaluated through numerical and experimental study.A three-dimensional finite-volume numerical model was established under the assumption that the soil thermal conductivity had been known in the simulation of thermal response test.The thermal response curve was firstly obtained through numerical calculation.Then,the accuracy of the numerical model was verified with measured data obtained through a thermal response test.Based on the numerical and experimental thermal response curves,the thermal conductivity of the soil was calculated by different parameter identification methods.The calculated results were compared with the assumed value and then the accuracy of these methods was evaluated.Furthermore,the effects of test time,variable data quality,borehole radius,initial ground temperature,and heat injection rate were analyzed.The results show that the method based on cylinder-source model has a low precision and the identified thermal conductivity decreases with an increase in borehole radius.For parameter estimation,the measuring accuracy of the initial temperature of the deep ground soil has greater effect on identified thermal conductivity.

Offline Handwritten Characters Recognition Using Moments Features and Neural Networks

In this paper we revise the moment theory for pattern recognition designed, to extract patterns from the noisy character datas, and develop unconstrained handwritten. Amazigh character recognition method based upon orthogonal moments and neural networks classifier. We argue that, given the natural flexibility of neural network models and the extent of parallel processing that they allow, our algorithm is a step forward in character recognition. More importantly, following the approach proposed, we apply our system to two different databases, to examine the ability to recognize patterns under noise. We discover overwhelming support for different style of writing. Moreover, this basic conclusion appears to remain valid across different levels of smoothing and insensitive to the nuances of character patterns. Experiments tested the effect of set size on recognition accuracy which can reach 97.46%. The novelty of the proposed method is independence of size, slant, orientation, and translation. The performance of the proposed method is experimentally evaluated and the promising results and findings are presented. Our method is compared to K-NN （k-nearest neighbors） classifier algorithm; results show performances of our method.

EXPERIMENTAL MODELING OF MIDDLE-RISE BUILDING VIA AMBIENT MODAL IDENTIFICATION

Experimental modeling of a middle-rise office building via ambient modal identification is presented. A 200-DOF (Dimension of freedom) test model is designed to correlate with finite element mode. A newly developed frequency-spatial domain decomposition ( FSDD ) technique is used to identify modal characteristics of the full-size building by using ambient response measurements. In the interested frequency ranges of 0～4.5 Hz and 0～ 6.5 Hz altogether 9 bending and torsion modes are identified. As one of the major focuses of the project, the accurate damping estimation is conducted based on FSDD. The identified modal frequencies and mode shapes are utilized for finite element model tuning. Excellent agreement has been achieved with respect to the final tuned finite element (FE) model up to 9 modes.

An Approximated Voxel Approach for the Identification and Modelling of Ligand-Binding Sites

Most protein-ligand interactions take place on surfaces and include but not limited to factors such as chemical composition, hydrophobicity, electronegavitiy and shape complementarity. Past studies showed that protein-protein interactions occur on comparatively fiat regions whereas protein-ligand bindings involve crevices. In the search for such sites various approaches have been designed and developed each of which is algorithmically unique. The use of grid units or voxels has been demonstrated in early studies with relatively good results obtained. We present here an approximated approach comprising of the use of voxels and computer vision methods in the search for ligand-binding areas. Each test protein is modelled and analysed in 2D with all corresponding residues graphically presented for successfully identified sites. The study was carried out on 2 sets of proteins： FK506-bound proteins and heme-bound proteins with promising results obtained for all test cases.

Fuzzy finite element model updating of bridges by considering the uncertainty of the measured modal parameters

It is significant to consider the effect of uncertainty of the measured modal parameters on the updated finite element(FE) model,especially for updating the FE model of practical bridges,since the uncertainty of the measured modal parameters cannot be ignored owing to the application of output-only identification method and the existence of the measured noise.A reasonable method is to define the objective of the FE model updating as the statistical property of the measured modal parameters obtained by conducting couples of identical modal tests,however,it is usually impossible to implement repeated modal test due to the limit of practical situation and economic reason.In this study,a method based on fuzzy finite element(FFM) was proposed in order to consider the effect of the uncertainty of the measured modal parameters on the updated FE model by using the results of a single modal test.The updating parameters of bridges were deemed as fuzzy variables,and then the fuzzification of objective of the FE model updating was proposed to consider the uncertainty of the measured modal parameters.Finally,the effectiveness of the proposed method was verified by updating the FE model of a practical bridge with the measured modal parameters.