Applied Mechanics and Materials Vols. 190-191

Abstract: Owing to Key parameter in Xylitol fermentation process cannot be measured on line, the soft measurement technology is used to estimate the xylitol and the xylosc concentration in this work. The RBF neutral network which is optimized by uniform design method is taken as a new soft measurement model. The genetic simulated annealing algorithm(GASA) is used to optimize the initial parameters of RBF network which is applied to xylitol fermentation process. So the xylitol and xylosc concentration can be measured in real time.

Abstract: According to the fault type and fault signal of rolling bearing is difficult to predict, the paper proposed a new method to diagnose fault of rolling bearings with the wavelet neural network optimizated by simulated annealing particle swarm optimization. And it was applied to the fault diagnosis of rolling bearing. The experiment shows that this method can reduce the iteration time and improve the accuracy of convergence.

Abstract: The paper analyses the compensation error which is caused by the probe radius of shape measurement instrument with the theory of envelope, and the model of the probe center is established. After having coordinates of envelope point corresponding to data point, actual curve equation has been obtained by using non-uniform B-spline curve. Finally, the effect is simulated and analysed by Matlab, and the result shows that the method of data processing has high precision.

Abstract: In the diagnosis of the respiratory diseases, auscultation is a non-invasive and convenient diagnostic method. In the digital auscultation analysis, what method we use to analyze the lung signals which microphone recorded will affect the results of the experiment greatly. The purpose of this study is to use frequency analysis and time-frequency analysis to analyze the six lung sound signals, which are vesicular breath sounds, bronchial breath sounds, crackle, and wheeze. Finally, the study transformed the analysis results into the characteristic images, and put them to the back propagation neural network for training. After that, the study compares the results of the two methods. We also analyze the realistic lung sound signals and simulated lung sound signals, and compare the results finally. First, we use the piezoelectric microphone and data acquisition card NI-PXI 4472B to acquire LS signals, and signals preprocessing. Then we use Visual Signal to analyze the lung sound signals by time-frequency analysis. We also analyze the lung sound signals which are from the auscultation teaching website. Finally we compare the result of two kinds of signals, and assess their similarity and accuracy by the test of back-propagation neural network. According to the result of this study, we found that time-frequency analysis provide much information about the lung signals, and are more suitable as a basis of diagnosis, and increase the recognition rate of the back-propagation neural network.

Abstract: The influence of mean stress on fatigue has to be considered by means of Haigh diagram, the actual stress range is modified to damage-equivalent range. There are three main methods for creating Haigh diagram, such as experiment and empirical relationships and six points, which has the different application field. The creating and application of Haigh diagram in GL certification for wind turbines is studied, and the solving method for the mean stress sensitivity is given.

Abstract: To grasp Complex characteristics of shortwave (HF) channel is the key and difficulty to research HF communication. On the premise of comprehending the ionosphere prediction method in the Asia Oceania region, HF frequency prediction method recommended by the International Telecommunication Union (ITU) is improved in this paper, and the engineering calculation method of predicting HF frequency in the Asia Oceania region is concluded and summarized. Comparing with the ITS (the Institute for Telecommunication Science) software’s predicting result, the method is improved to some extent in time availability and SNR in the receiving point.

Abstract: This paper rushes from unit to surge to make in the theoretical intension of function the unified theory and method that signal divides into to fold , this theory is normalized more , is clear.

Abstract: Category level object discovery is important for a number of applications such as remote sensing image classification, and data mining in images and video sequences. This paper presents a novel unsupervised learning algorithm for discovering object category and their locations in video sequences. Both appearance consistency and motion consistency of local patches across frames are exploited. Video patches are first extracted and represented by spatial-temporal context words. A dynamic topic model is then introduced to learn object categories in video sequences. The proposed dynamic model can categorize and localize multiple objects in a single video. Experimental results on the CamVid dataset and the VISATTM dataset demonstrate the effectiveness of our method.

Abstract: In general, most of stochastic age-structured system of two species with diffusion do not have explicit solutions, thus numerical approximation schemes are invaluable tools for exploring their properties. The main purpose of this paper is to develop a numerical scheme and show the convergence of the numerical approximation solution to the true solution for stochastic age-structured system of two species.

Abstract: To detect crack of nonlinear rotor in large rotating machinery, the correlation dimension is introduced, which is calculated through G-P algorithm. The optimal delay time is derived from autocorrelation function, and the pseudo-phase portrait of cracked rotor is investigated. The influence of embedding dimension and data length on the correlation dimension is studied thoroughly, and the accurate value of correlation dimension is obtained, which can provide a basis for crack identification.