Advanced Materials Research Vols. 945-949

Abstract: The abstraction of diagnostic feature from field condition monitoring data is a significant research challenge. A new dimension reduction method based on correlation coefficient matrix is proposed aimed at the high-dimension characteristic parameters in the process of pattern recognition for partial discharge in power transformer. The CCM is constructed by parameters extracted from partial discharge signature in power transformer. The parameters that have similar classification characters are reduced directed by the correlation analysis result. The reduced PD features are inputted to the pattern classifiers of probabilistic neural networks (PNN). The results show that the parameter dimension is reduced and the classifier construction is simplified, and the recognition effect is better than that of the traditional back propagation neural network (BPNN) in the condition of small samples.

Abstract: ReliefF feature selection and LogitBoost ensemble learning method are employed in the data mining procedure of 2126 fetal cardiotocograms (CTGs). Based on 10 critical features selected by ReliefF and the full 21 features, LogitBoost algorithm almost outperforms the other three ensemble learning methods of Stacking, Bagging and AdaBoostM1 in ACC (%) and AUC in classification, and the ACC (%) and AUC of LogitBoost algorithm are achieved to 94.45% and 0.977 based on the critical features from ReliefF.

Abstract: To study influence of LED light source lifetime on electricity consumption, optimization of BP neural network is adopted to establish analysis model of energy consumption for neural network, regarding environmental illumination, LED working face illumination, attenuation rates of LED lifetime as input parameters and PWM as output parameters. Under future lifetime of LED, energy consumption is predicted through the model. Results show BP neural network based on genetic algorithm can calculate energy consumption of LED light source quickly and accuracy of prediction is high. The method can be well used to predict energy consumption of short-time LED.

Abstract: The combination forecasting model based on induced ordered weighted averaging IOWA operators. First, individual forecasting model that has higher forecasting accuracy is chosen as a criterion. Then, the deviation of predictive values between other models and standard model is computed. The weights are given according to the mean value size of the absolute value sum of deviation in every individual forecasting model in every period. Finally, a new forecasting model is built in accordance with the weighted error sum of squares. And genetic algorithm is used to solve the optimal weights. Verified by an example, the improved combination forecasting method is better than the original combination forecasting method based on IOWA operator. Forecasting accuracy is improved effectively.

Abstract: The anti-collision algorithm is the key technology of RFID system. Firstly, this paper studied frame-slotted ALOHA anti-collision algorithm, in order to solve the shortcomings of ALOHA algorithm, an improved anti-collision algorithm is proposed based on grouping mechanism, and it also carried out the simulation experiences using the C# language under the .NET platform. The simulation results indicate that the improved algorithms can increase RFID system throughput.

Abstract: Voronoi-based Overlay Network (VON) has been proposed that promises to maintain high overlay topology consistency in a bandwidth-efficient manner. VoroCast constructs a spanning tree across all AOI neighbors based on Voronoi diagrams, while FiboCast dynamically adjusts the messaging range by a Fibonacci sequence. VoroCast improves the AOI scalability of P2P-based NVEs. However, one potential drawback of the schemes is that the child node degrees are only based on peers' positions, but not node capacities. Since each node in VoroCast has different capacity, packet loss will be unavoidable. VoroCast may lead to lower multicast efficiency in AOI. To these problems, an Advanced AOI-cast algorithm based on PCA is presented. In the algorithm, node capacity is related to node CPU (c), node bandwidth (b) and node memory (m), and the node capacity is calculated according to the PCA. An undirected graph is formed through all the nodes in the AOI and the edge weights are calculated by the Gaussian function. Through the prim algorithm, to generate the minimum spanning tree of the weighted undirected graph, and the minimum spanning tree is used as the final multicast tree. The message is delivered through the multicast tree. The simulation results show that the algorithm gains a greater improvement on multicast efficiency, and achieves better scalability.

Abstract: Using the characteristics of prediction model, rolling optimization and feedback correction, a AWC system based on generalized predictive control was designed, and its control performance was simulated based on a hot strip continuous mill. The results show that generalized predictive controller achieves better control effects than the normal PID on response time and steady precision with matching model; when model mismatching is caused by inaccuracy of plastic coefficient and pure delay time, the normal PID is overshot or even oscillation, but the control performance of the generalized predictive controller is not influenced by model parameter variations .

Abstract: The paper proposes a manipulation principle teaching system of the main clutch based on PLC control with a high degree of automation. It is designed combining with the working characteristics of a certain type main clutch and its purpose is to meet the training needs of armored vehicles driving manipulation skills for junior commanders in military academies. The sensor signals can be collected by the system to simulate the driving manipulation signals. The actuators are consisted of displaying lights, electromagnets and stepper motor. So the various actuators can be controlled comprehensively to imitate main clutch mechanism to show different working conditions which can be converted according to the teaching needs.

Abstract: For the non-measurable states, a control of switched fuzzy systems is presented based on observer. Using switching technique and multiple Lyapunov function method, the fuzzy observer is built to ensure that for all allowable external disturbance the relevant closed-loop system is asymptotically stable. Moreover, switching strategy achieving system global asymptotic stability of the switched fuzzy system is given. In this model, a switching state feedback controller is presented. A simulation shows the feasibility and the effectiveness of the method.

Abstract: Switching control and stability issues for discrete-time switched systems whose subsystems are all discrete-time fuzzy systems are studied and new results derived. Innovated representation models for switched fuzzy systems are proposed. The common Lyapunov function method has been adopted to study the stability of this class of switched fuzzy systems. Sufficient conditions for asymptotic stability are presented. The main conditions are given in form of linear matrix inequalities (LMIs), which are easily solvable. The elaborated illustrative examples and the respective simulation experiments demonstrate the effectiveness of the proposed method.