浅论认识模糊性的相对性

有人认为认识的模糊性是绝对的,精确性才是相对的。笔者认为模糊性既具有绝对性,又具有相对性,是绝对性与相对性的统一,并且认为模糊性的相对性更富有重要的实际意义。本文着重就认识的模糊性及其相对性谈些粗浅看法。 唯物辩证法认为,绝对与相对是统一不可分割的,绝对与相对的差别也是相对的。

用辨识法建立聚合物挤出功率与振动参数关系的模型

打破了传统的机理建模方式 ,用系统辨识建模方法 ,建立了在振动力场作用下挤出 L DPE料时挤出功率与振动强度参数 :振幅、频率间关系的数学模型。经理论分析和实验证明 ,该模型是合理有效的 ,为优化塑料电磁动态挤出设备的挤出加工过程提供了参考。

Wafer Defect Map Pattern Recognition Based on Improved ResNet

The defect detection of wafers is an important part of semiconductor manufacturing.The wafer defect map formed from the defects can be used to trace back the problems in the production process and make improvements in the yield of wafer manufacturing.Therefore,for the pattern recognition of wafer defects,this paper uses an improved ResNet convolutional neural network for automatic pattern recognition of seven common wafer defects.On the basis of the original ResNet,the squeeze-and-excitation(SE)attention mechanism is embedded into the network,through which the feature extraction ability of the network can be improved,key features can be found,and useless features can be suppressed.In addition,the residual structure is improved,and the depth separable convolution is added to replace the traditional convolution to reduce the computational and parametric quantities of the network.In addition,the network structure is improved and the activation function is changed.Comprehensive experiments show that the precision of the improved ResNet in this paper reaches 98.5%,while the number of parameters is greatly reduced compared with the original model,and has well results compared with the common convolutional neural network.Comprehensively,the method in this paper can be very good for pattern recognition of common wafer defect types,and has certain application value.

规模经营就是这样搞起来的——记襄樊市农机总公司轮胎分公司

襄樊市农机总公司轮胎分公司经过两年,经营已初具规模。据统计:刚成立分公司的1993年销售额不到300万元,利税只有几万元;1994年销售额上升到1663万元,利税57万元;1995年元月至9月销售额已达到2150万元,利税75万元。其销售额和利税不仅在总公司内独占鳖头,而且在全市同行业中也遥遥领先。他们的经验是三三一。

走出认识误区 增强发展信心

最近,我们对我市各审计师事务所进行了一次调查,从调查的情况来看,有的审计师事务所前景堪忧,创业时期曾经兢兢业业,大刀阔斧地开拓过社会审计事业,

自适应神经网络判决树及其在人脸识别领域的应用

提出了一种神经网络与判决树结合而成的新结构———自适应神经网络判决树（ＡｄａｐｔｉｖｅＮｅｕｒａｌＮｅｔｗｏｒｋｓＤｅｃｉｓｉｏｎＴｒｅｅ，简称ＡＮＮＤＴ）。实验表明，基于ＡＮＮＤＴ的人脸识别方法，能够综合利用多种神经网络模型和特征提取算法，不仅具有较高的识别速度、准确率、容错性和健壮性，而且基本满足开发实用化人脸识别系统的要求。

Automatic discrimination of sedimentary facies and lithologies in reef-bank reservoirs using borehole image logs

Reef-bank reservoirs are an important target for petroleum exploration in marine carbonates and also an essential supplemental area for oil and gas production in China. Due to the diversity of reservoirs and the extreme heterogeneity of reef-banks, it is very difficult to discriminate the sedimentary facies and lithologies in reef-bank reservoirs using conventional well logs. The borehole image log provides clear identification of sedimentary structures and textures and is an ideal tool for discriminating sedimentary facies and lithologies. After examining a large number of borehole images and cores, we propose nine typical patterns for borehole image interpretation and a method that uses these patterns to discriminate sedimentary facies and lithologies in reeI^bank reservoirs automatically. We also develop software with user-friendly interface. The results of applications in reef-bank reservoirs in the middle Tarim Basin and northeast Sichuan have proved that the proposed method and the corresponding software are quite effective.

Synthetical condition assessment of long span suspension bridge based on closeness degree and FAHP

Based on the theory of pattern recognition, the concept of closeness degree between fuzzy sets is brought into the condition assessment of long span bridges. Using the fuzzy analytic hierarchy process （FAHP）, a mathematical model of a multi-objective assessment of a long span suspension bridge is set up. An example is given to show the procedure in the synthetical condition assessment of the Runyang Suspension Bridge, which includes the hierarchical division, the definition of factor weights and fuzzy membership functions, and the calculation of closeness degrees, etc. The assessment combines both the data from the health monitoring system and the manual tests. The classification of evaluation items as well as the calculation of deterministic and nondeterministic items is presented. Compared with the traditional method of point rating, this method can better describe the discreteness of monitoring data and the fuzziness in the condition assessment.

DAMAGE ANALYSIS AND LOCATION OF RUNYANG BRIDGE USING MULTI-LAYER PERCEPTRON

A damage location method using multi-layer perceptron （MLP） is developed to diagnose the cable damage of a real long span cable-stayed bridge. Firstly, the damage patterns are defined based on dynamical calculation. The analysis of damage pattern reveals that the damage patterns caused by different damage locations have inherent distinctness, while the damage extent only linearly amplifies the damage pattern curves. And 4th, 6th and 7th order frequencies are canceled from the patterns because of their insensitiveness to cable damage. Then a MLP network is designed by trail-error method to describe the 7-D mapping space of damage pattern. Identification results prove that the properly organized MLP can grasp the damage pattern and identify the damage location.

Configuration knowledge modeling of customizable products based on semantic web technologies

In order to solve the problem of modeling product configuration knowledge at the semantic level to successfully implement the mass customization strategy, an approach of ontology-based configuration knowledge modeling, combining semantic web technologies, was proposed. A general configuration ontology was developed to provide a common concept structure for modeling configuration knowledge and rules of specific product domains. The OWL web ontology language and semantic web rule language （SWRL） were used to formally represent the configuration ontology, domain configuration knowledge and rules to enhance the consistency, maintainability and reusability of all the configuration knowledge. The configuration knowledge modeling of a customizable personal computer family shows that the approach can provide explicit, computerunderstandable knowledge semantics for specific product configuration domains and can efficiently support automatic configuration tasks of complex products.

Monitoring Tool Wear States in Turning Based on Wavelet Analysis

To monitor the tool wear states in turning, a new way based on the wavelet transformation to get the signal characters, which can reflect the tool wear states, was proposed. Using discrete dyadic wavelet transform, the acoustic emission(AE) signal of cutting process was decomposed; the root mean square(RMS) values of the decomposed signals at different scales were taken as the feature vector; the technique of fuzzy pattern identification was used to real time monitor the tool wear states. Based on choosing the suitable standard samples, this method can correctly identify the tool wear states. Experiments showed that the technique based on wavelet analysis is suitable for real time implementation in manufacturing application.

TONE MODELING BASED ON HIDDEN CONDITIONAL RANDOM FIELDS AND DISCRIMINATIVE MODEL WEIGHT TRAINING

The use of hidden conditional random fields （HCRFs） for tone modeling is explored. The tone recognition performance is improved using HCRFs by taking advantage of intra-syllable dynamic, inter-syllable dynamic and duration features. When the tone model is integrated into continuous speech recognition, the discriminative model weight training （DMWT） is proposed. Acoustic and tone scores are scaled by model weights discriminatively trained by the minimum phone error （MPE） criterion. Two schemes of weight training are evaluated and a smoothing technique is used to make training robust to overtraining problem. Experiments show that the accuracies of tone recognition and large vocabulary continuous speech recognition （LVCSR） can be improved by the HCRFs based tone model. Compared with the global weight scheme, continuous speech recognition can be improved by the discriminative trained weight combinations.

On similarity measures of interval-valued intuitionistic fuzzy sets and their application to pattern recognitions

The concept of the degree of similarity between interval-valued intuitionistic fuzzy sets （IVIFSs） is introduced, and some distance measures between IVIFSs are defined based on the Hamming distance, the normalized Hamming distance, the weighted Hamming distance, the Euclidean distance, the normalized Euclidean distance, and the weighted Euclidean distance, etc. Then, by combining the Hausdorff metric with the Hamming distance, the Euclidean distance and their weighted versions, two other similarity measures between IVIFSs, i. e., the weighted Hamming distance based on the Hausdorff metric and the weighted Euclidean distance based on the Hausdorff metric, are defined, and then some of their properties are studied. Finally, based on these distance measures, some similarity measures between IVIFSs are defined, and the similarity measures are applied to pattern recognitions with interval-valued intuitionistic fuzzy information.

Operational modal identification of suspension bridge based on structural health monitoring system

An output-only modal identification method by a combination use of the peak-picking method and the cross spectrum methods are presented. Meanwhile, a novel mode shape optimum method of the deck is proposed. The methods are applied to the operational modal identification system of the Runyang Suspension Bridge, which can be used to obtain the modal parameters of the bridge from out-only data sets collected by its structural health monitoring system （SHMS）. As an example, the vibration response data of the deck, cable and tower recorded during typhoon Matsa excitation are used to illustrate the program application. Some of the modal frequencies observed from deck vibration responses are also found in the vibration responses of the cable and the tower. The results show that some modal shapes of the deck are strongly coupled with the cable and the tower. By comparing the identification results from the operational modal system with those from field measurements, a good agreement between them is achieved, but some modal frequencies identified from the operational modal identification system （OMIS）, such as L1 and L2, obviously decrease compared with those from the field measurements.

Wavelet transform and gradient direction based feature extraction method for off-line handwritten Tibetan letter recognition

To improve the recognition accuracy of off-line handwritten Tibetan characters the local gradient direction histograms based on the wavelet transform are proposed as the recognition features.First for a Tibetan character sample image the first level approximation component of the Haar wavelet transform is calculated.Secondly the approximation component is partitioned into several equal-sized zones. Finally the gradient direction histograms of each zone are calculated and the local direction histograms of the approximation component are considered as the features of the character sample image.The proposed method is tested on the recently developed off-line Tibetan handwritten character sample database.The experimental results demonstrate the effectiveness and efficiency of the proposed feature extraction method.Furthermore compared with the detail components the approximation component contributes more to the recognition accuracy.

Classification of Chinese Traditional Drug-"Beimu" (Bulbus Fritillariae) by Pyrolysis High Resolution Gas Chromatography-Pattern Recognition

The combination of pyrolysis high resolution gas chromatography and pat- tern recognition techniques is a powerful tool for the classification of traditional Chinese drug.A study has been completed on 55 Beimu samples of five different geographic origins: Eastern China.Central China.South-western China,North-western China and North-eastern China.Principal component analysis and SIMCA are applied to effectively classifying the samples according to the origin of the plants.The chemical information contained in the high resolution gas chromatographic data is sufficient to characterize the geographic origin of sam- pies.

DEBRIS MONITORING AND ANALYZING SYSTEM (DMAS) AND ITS APPLICATION IN AEROENGINE

By inspecting and analyzing the debris, which is the most direct and important information units in the lubricating oil, we can monitor the machine condition to predict its failure. The debris monitoring and analyzing system (DMAS) is developed from the traditional iron spectrum technology, and has such characteristics as ease for debris separating, forecasting machine failure automatically and accurately in time and so on. The fundamental theory, components and its application in aeroengine health monitoring of DMAS are presented.

Identification of material parameters from punch stretch test

To accurately describe the mechanical properties of aluminium alloy sheet during deformation, an inverse identification was presented to deal with material parameters from the popular punch stretch test. In the identification procedure, the optimization strategy combines finite element method （FEM）, Latin hypercube sampling （LHS）, Kriging model and multi-island genetic algorithm （MIGA）. The proposed approach is used on material parameter identification of aluminium alloy sheet 2D12. The anisotropic yield criterion Hill’90 is discussed. The results show that the Hill’90 anisotropic yield criterion with identified anisotropic material parameters has a good potential in describing the anisotropic behaviours. It provides a way to obtain the material parameters for FE simulations of sheet metal forming.

Identification of constitutive model parameters for nickel aluminum bronze in machining

The material of nickel aluminum bronze (NAB) presents superior properties such as high strength, excellent wear resistance and stress corrosion resistance and is extensively used for marine propellers. In order to establish the constitutive relation of NAB under high strain rate condition, a new methodology was proposed to accurately identify the constitutive parameters of Johnson?Cook model in machining, combining SHPB tests, predictive cutting force model and orthogonal cutting experiment. Firstly, SHPB tests were carried out to obtain the true stress?strain curves at various temperatures and strain rates. Then, an objective function of the predictive and experimental flow stresses was set up, which put the identified parameters of SHPB tests as the initial value, and utilized the PSO algorithm to identify the constitutive parameters of NAB in machining. Finally, the identified parameters were verified to be sufficiently accurate by comparing the values of cutting forces calculated from the predictive model and FEM simulation.

Identification and Quantification of Non-Spherical Particles

In commercial applications of phase Doppler anemometry (PDA), the effectiveness of non sphericity of particles is present and the response of PDA system deviates from the theoretical prediction. In this paper, the statistic characteristics of PDA signal related to irregular particles is analyzed and a method of statistic classification of irregular particles is proposed.It proves that the parameter of PDA signal for irregular particles is an unbiased estimation for spherical ones, the mean of the phase difference is in direct proportion to the mean diameter of particles and the standard deviation of the phase difference increases linearly with the standard deviation of irregular particles. As an application of the identification of irregular objects, fuzzy patterns and similarities of haemocytes are used to recognize and quantify cell samples.The statistic classification of particles is more significant in practice.