Earticle

A novel static decoupling control strategy based on Hammerstein model and neural network for induction motors was proposed in this paper. Hammerstein model, consisting of a static nonlinear module and a dynamic linear module, can be used to model many nonlinear systems. In the proposed method, firstly, neural network and auto-regressive moving-average (ARMA) model were employed to construct the static nonlinear module and the dynamic linear module respectively. Further, neural network inverse model of the static nonlinear module can be trained on the static dataset collected in the framework of the Hammerstein model. Finally, the inverse model was utilized to offset the nonlinear characteristic of an induction motor, decoupled into a rotor speed subsystem and a rotor flux subsystem. Simulations show that the proposed static decoupling control strategy has satisfactory decoupling performances and robustness to load disturbance in close loop control.

With the development of high technology, the complication of battle environment and the acceleration of the battle rhythm, target damage assessment playsa very important rolein the modern war. Becausethe target damage information is uncertaininformation, it is a challenge on target damage assessment problem. To the problem of airport damage assessment, anew solutionis proposed.The Fuzzy Comprehensive Evaluation method is given, and the two-levelfuzzy comprehensive evaluation model based on uncertain information is proposedin this paper. The damage effect of airport target is evaluatedbythe two-levelfuzzy comprehensive evaluation model. And the method ofairport target damage gradeis given by the compare of interval numbers. In the last, the effectiveness of this method is verified by the example.

On heavy load, the energy supplement in the starting process of Thyristor Power Supply for Parallel Resonant Induction Heating (TPSPRIH) has trouble in catching up its consumption which makes the system start more difficultly. Aimed at the puzzle, this paper proposes a starting strategy based on the analysis of parameters of heating inductor and starting circuit. Considered the process complexity in commonly used pre-charged circuit, it analyzed relationship among the parameters of heating inductor, the iron material and its filling status. Compared the supply speed with the decay characteristic of load circuit, the critical starting conditions of TPSPRIH on heavy load has been gotten, then derived the solving space of trigger angle of rectifier on energy providing. Based on the rated parameters of a typical system, the starting strategy of rectifier angle has been proposed. The simulation on different regions in the solving space has been made. The simulation result demonstrated the rationality and correctness. It probably provides a reference way for the reliable starting of TPSPRIH.

A phase coincidence phenomenon between two arbitrary frequency signals is a periodic phenomenon. One application of this phenomenon is a new method to generate a stable time signal. Using two frequency signals with a certain frequency difference and a phase coincidence detection circuit to detect the phase coincidence signal of them, one can get a periodic coincidence signal. And then moving the phases of the two frequency signals properly, one can get a coincidence signal synchronizing with a standard time signal. The advantage of the new method is the second signal generated by it is easy to transmit and comparison with high resolution.

A discriminative learning model with a rich feature set was used for extreme precipitation forecasting of a river basin to effectively use available historical observation data. Discrimination models use decision functions that are suitable for forecasting in cases where factors are complex or even unknown. In this study, we used the neural network technique that belongs to the empirical risk minimization method, and a support vector machine that belongs to the structural risk minimization method to be constructed on rich feature sets of rainfall in the Dongjiang basin. The results of forecast experiments show that our method was more effective compared with four types of traditional time series methods and the Naïve Bayes method that belongs to generative models. The support vector machine yielded the maximum F1 value.

Based on real options method to construct a petroleum exploration and development projects of integrated economic evaluation model, application mechanism real option method in oil and gas exploration and development projects around the expansion, the option value to identify and analyze the process of exploration and development projects exist. Finally, select the appropriate option pricing model, instance data analyzed by gas exploration and development projects, and its contrast with the traditional analysis, pointed out that application of real options method can effectively improve the investment project economic evaluation of science. In this paper, to build an economic evaluation method based on real options method of energy development projects, and to explore applications based on the principle of real options to develop economic evaluation method, proposed mostly for exploration stage oil and gas exploration and development project abandonment option binomial model and the development phase stop start option of partial differential equations, is determined based on the actual parameters of such projects, and to provide solutions to parameter estimation.

The development of large scale direct current (DC) transmission system with high efficiency and stability of DC grids has been studied widely. The dc circuit breaker (DCCB) is introduced to ensure the stability of DC grids. Among different types of DCCB, hybrid DCCB has gained more attention. This paper proposes a novel hybrid DCCB topology based on inverse current injecting method. The proposed DCCB topology is able to perform the operation duty of reclosing and rebreaking. In addition, this paper also considers the bidirectional topology of dc circuit breaker with bidirectional current breaking capability. The operating characteristics of the proposed DCCB topology are verified by simulations in Matlab/Simulink environment.

The core issues of RBF network design are to design the minimum structure neural networks that can meet the accuracy requirements, in order to ensure the generalization ability of the network. For the purpose of simplifying the structure of RBF network, proposes a learning method of RBF network based on improved particle swarm. The method automatically constructs frugal structure of RBF network model by the combining algorithm of regularized least squares method and D- optimal experimental design; chooses three learning parameters of the combining algorithm that can affect network generalization performance by the improved particle swarm optimization algorithm. By nonlinear time series modeling, verifies the effectiveness of the method in this paper.

This study first analyzes the features and defects of each product design evaluation method. Then radial basis function (RBF) network is used for the modeling for sowing machines. Considering the characteristics of sowing machines and the general method of design evaluation of electromechanical equipments, 7 primary evaluation indicators for sowing machines are identified, including overall design, form, human-machine interface and color. These primary evaluation indicators were subdivided into 18 secondary indicators. Survey on these indicators was performed by professionals and the scores are assigned to 18 indicators collected from 26 samples. Thus the comprehensive evaluation score of the indicators is calculated using image scale method. The scores of the evaluation indicators are taken as input and the comprehensive evaluation score as the output, then the RBF network for design evaluation is built. After training and verification using 26 samples, it is found that the RBF-based design evaluation model achieves better prediction performance than the BP-based model.