Applied Mechanics and Materials Vols. 401-403

Abstract: To handle with the limitation of bag-of-features (BoF) model which ignores spatial and temporal relationships of local features in human action recognition in video, a Local Spatiotemporal Coding (LSC) is proposed. Rather than the exiting methods only uses the feature appearance information for coding, LSC encodes feature appearance and spatiotemporal positions information simultaneously with vector quantization (VQ). It can directly models the spatiotemporal relationships of local features in space time volume (STV). In implement, the local features are projected into sub-space-time-volume (sub-STV), and encoded with LSC. In addition a multi-level LSC is also provided. Then a group of sub-STV descriptors obtained from videos with multi-level LSC and Avg-pooling are used for action video classification. A sparse representation based classification method is adopted to classify action videos upon these sub-STV descriptors. The experimental results on KTH, Weizmann, and UCF sports datasets show that our method achieves better performance than the previous local spatiotemporal features based human action recognition methods.

Abstract: This paper presented a new watermarking algorithm based on 3D-DCT and chaotic neural network in order to protect three-dimensional medical images. The algorithm adopts a wealth of information grayscale image as a watermark and three-dimensional medical image as the original carrier. It utilizes chaos neural network for scrambling and encryption of watermarking image. The embedded watermark has cryptographic security significance. Experimental results show that the algorithm is simple, which is a blind watermarking algorithm; the watermark extraction process does not require the original image. It is capable of resisting shear and filtering attacks.

Abstract: In order to reduce computational complexity of modeling and improve the model's robustness and prediction accuracy, successive projections algorithm is used in the Neural Networks calibration modeling of wheat protein. Firstly, the spectral data is pretreated with first-order differential method and SNV method，and then a representative set of calibration samples are selected by SPXY algorithm. Secondly, making use of successive projections algorithm(SPA) to extract sensitive wave points of the original spectrum and the pretreated spectrum, and then the neural networks calibration model of wheat protein is established. The results show that the calibration model based on successive projections algorithm has a fast convergence speed and high accuracy, both of which are better than the calibration model established with the original data. Root mean square error of prediction(RMSEP) and prediction correlation coefficient(r) are 1.3332 and 0.94319 respectively, which can basically complete the grain reserves and the food processing profession division and the breeding preliminary generation.

Abstract: In order to track the phase of the voltage of the grid quickly and accurately in the photovoltaic grid system, a digital three-phase phase locked loop optimization method that can be completed by FPGA, which can lock the in a short time and adjust the power system voltage phase to the synchronization with the grid voltage. This design consists of three-phase phase detector, comparator and bit phase locking circuit. The principle of synchronous rotating coordinate transformation and lookup table of RAM are used to adjust the phase error more and more fine-tune. The adjustment of the phase is controlled by the waveform output of driver without analog circuit, besides the ability of anti-jamming is improved by the full digital designation and the dynamic characteristics is better. The system is simulated with MATLAB/Simulink and the given results show that this method greatly shorten the time needed for adjusting the phase difference. Obviously the precision of the system has been improved and then the effectiveness of the proposed method was verified.

Abstract: Aiming at the difficulty to building inverse model in the inverse model control system, the modeling method of inverse model based on the LS_SVM is proposed. In order to obtain better static and dynamic performance, the feed-forward compensator and self-tuning PID controller are consisted of the compound control system. As can be seen from the simulation results that the compound control system has a good ability to control nonlinear object with high tracking precision, good dynamic performance and better control effect.

Abstract: A speed controller with fuzzy sliding mode algorithm was designed by using power function instead of the traditional switch symbol function, and adjusting the approach law parameters combined with fuzzy algorithm in real time, as it was difficult to eliminate the chattering when designing a PMSM speed controller with the traditional sliding mode variable structure. The mathematical model of the PMSM was built in Matlab/Simulink with the vector control strategy. The simulation results showed that the control system of PMSM built by improved sliding mode had quick velocity response with less overshoot and significantly weakened chattering, which verified the efficiency of the improved algorithm in the simulation stage.

Abstract: The structure of machining workpiece is more and more complex, from the perspective of CNC machining, contains a lot of processing features generally. Machining feature plays an important role for production process for CNC machining programming, CNC code, as well as the analysis of clamping. Feature programming is one of the development trend of automatic CNC programming. This improve the efficiency of programming greatly.

Abstract: This article analyses the use requirement of construction machinery, introduce the main features of typical construction machinery hydraulic system, derived power control modes of hydraulic system form hydraulic power form, compares the advantages and disadvantages of each power control mode, gives the optimization solutions, at last, sum up the full text of the construction machinery hydraulic power and control modes and prospect of the hydraulic system to precision control.

Abstract: This paper addresses the nonlinear dynamics of the Sheppard-Taylor converter to explain the complex behaviour exhibited in the converter under different practical conditions. The bifurcation diagram of the converter is generated to analyze the stability of the system. Several representative waveforms are captured from simulation to illustrate the chaos control of the converter, such as time-domain waveforms, phase portraits, Poincaré section diagrams, and power spectral diagrams.

Abstract: This paper focus on analyzing and comparing the merits and faults of neural oscillators and dynamics control methods for the physical human-robot interaction. Firstly, the principles of two control modes are introduced about neural oscillators and dynamics. Secondly, their self-oscillation and synchronizatin chracteristics are analyed and compared in both without input and with input cases respectively. Lastly, based on human-robot handshaking interaction, simulation is implemented by using two control methods respctively. And the validity of two control methods are compared and analyzed according to simulation results.