期刊：
2008 INTERNATIONAL SYMPOSIUM ON INFORMATION PROCESSING AND 2008 INTERNATIONAL PACIFIC WORKSHOP ON WEB MINING AND WEB-BASED APPLICATION,2008年:373-378
摘要：
The microstructures of sesame cake under five applied pressures were measured using stereo light microscope and Image-pro software. Fractal dimensions of pore section border and pore size distribution were measured and calculated by the slit island process. Regression method was used to analyse the correlation between the fractal dimension and applied pressure. Results showed that the fractal characteristic of pore structure of sesame cake was obvious, the pore structure and its fractal dimension were significantly affected by applied pressure. There existed good linear correlations between applied pressure and fractal dimensions of the pore section border and pore size distribution. Their fractal dimension values decreased significantly with increasing applied pressure. It was concluded that with increasing applied pressure the pore section border is further twisty, the pore wall further rough, the pore shape further irregular and the pore size distribution further complicated.
摘要：
A prediction model of compression ratio for extruded oilseeds was developed based on improved BP neural networks. As an applied example, the predicted curves were successfully used to predict critical pressing pressures. Results indicated that the predicted values of compression ratios conformed to the measured values well for extruded cottonseed and castor been. There was a limiting compression for extruded oilseeds under given conditions. The compression ratios for extruded cottonseed had more rapid increase from 0 to 40 MPa of applied pressure. less increase from 40 to 80 MPa and insignificant increase over 80 MPa, and for extruded castor bean had more rapid increase from 0 to 60 MPa of applied pressure, less increase from 60 to 100 MPa and insignificant increase over 100 MPa. 80 and 100 MPa of applied pressure were identified as the critical pressing pressure for extruded cottonseed and castor bean respectively.
摘要：
Friction between rubber roller and paddy or brown rice for paddy dehulling was much characteristic compared with that between two solid bodies. Paddy or brown rice was approximately considered as a rigid body, while rubber roller was considered as complete elastic body. Mathematical simulation of friction for paddy dehulling had been developed based upon the theory of elasticity, and of adhesion and hysteresis friction. Calculation results indicated that the adhesion force had dominant influence on the frictional force, and the hysteresis force could be negligible under normal conditions. The effect of the hysteresis force on the frictional force was significance and not negligible only in case high total radial pressure. The models revealed that the frictional force and power consumed acted on the long and narrow paddy were larger than those of the short and wide paddy when the total radial stress and shear strength of husk were the same for two kinds of paddy. The models also revealed, from another point of view, why the dehulling rate would increase with the increase of the difference of velocity between fast roller and slow roller.
摘要：
By using of combining theoretical model with empirical model, the nonlinear viscoelastic-plastic constitutive equations of soybean and cottonseed were developed on the basis of the creep test. The parameter inverse problem of constitutive model was proposed using improved particles swarm optimization. Numerical simulations of creep of soybean and cottonseed were carried out. The definition of critical pressing time for oil extraction and the method for determining the critical pressing time using creep rate were proposed. The values of critical pressing time for extruded soybean and cottonseed under six applied pressures were evaluated Results indicated that the nonlinear viscoelastic-plastic constitutive model could simulate rheological behaviors of soybean and cottonseed very well. Mean relative deviations between the experimental and predicted values of soybean and cottonseed were 1.55% and 1.93%, respectively. There were significant decreases in the values for the creep rates in the early stage of pressing, and decreases to an insignificant and stabilize value in the later stage.
摘要：
Stress-strain relationship is the most important properties of physical mechanics of oilseeds during mechanical pressing. In view of the difficulty for establishing a mathematical model due to the complexity of physical mechanics performance, the stress-strain identification model for oilseeds based on BP neural network was developed to simulate the relationship. The identification results that the maximum error was less than 0.00005 and the maximum training times was less than 100 indicated that the method of stress-strain identification for cottonseed and castor bean by using artificial neural networks is both feasible and effective.
会议论文集名称：
Lecture Notes in Control and Information Sciences
摘要：
The ability to detect a new fault class can be a useful feature for an intelligent fault classification and diagnosis system. In this paper, we adopt two novelty detection methods, the support vector data description (SVDD) and the Parzen density estimation, to represent known fault class samples, and to detect new fault class samples. The experiments on real multi-class bearing fault data show that the SVDD can give both high identification rates for the prescribed ‘unknown’ fault samples and the known fault samples, which shows an advantage over the Parzen density estimation method in our experiments, via choosing the appropriate SVDD algorithm parameters.
关键词：
rolling element bearing;fault diagnosis;blind deconvolution;impulse signal
摘要：
A blind deconvolution algorithm was applied to extract or enhance the impulse impact signals in vibration signals of the localized defect bearings. The algorithm is based on maximizing the kurtosis value of the deconvolved signals. In the deconvolved signals collected from rolling bearings with inner race and outer race faults, the faulty impulse signals were adequately enhanced, and appeared regularly in the time domain. By taking two times the value of the standard deviation of the deconvolved signals as the threshold values, the "clean" faulty impulse line sequences were obtained using the threshold denoising. Computational results show that the mean impulse line repetition rate of each impulse sequence in the time.. domain matches the corresponding characteristic defect frequency of the bearing very well.
摘要：
A kernel Fisher discriminant (KFD) method is applied to the bearing fault diagnosis (i.e. classification of multiple fault classes). This paper deals with KFD for two multi-class fault recognition examples. One example is to recognize faults on different bearing elements; another is to recognize four different severities of the ball faults. The time-domain vibration signals of normal bearings, bearings with different faults have been used for feature extraction. The features are obtained from direct processing of the signal segments using simple preprocessing. The classification results demonstrate that KFD method is effective on the examples. Furthermore, in terms of classification performance, KFD method competes with support vector machines.
