Search

This paper introduces a testing mothod about hydroturbine governing system based on dSPACE hardware-in-the-loop-simulation. PID parameters are adjusted by hardware-in-the-loop -simulation. The results of the simulation show that it can provide simple, intuitive simulation model, and make parameters adjusting more intuitive and easier. The validity of the testing platform have been testified by the results of real-time simulation and hardware-in-the-loop-simulation. The superiority of controldesk in the real-time simulation is prominent.

Support Vector Machine Recursive Feature Elimination (SVM-RFE) is a simple and efficient feature selection algorithm which has been used in many fields. Just like SVM itself, SVM-RFE was originally designed to solve binary feature selection problems. In this paper, we propose a new recursive feature elimination method based on SVM for ranking problem. As against standard approaches of treating ranking as a multiclass classification problem, our approach enables the use of standard binary SVM-RFE algorithms for ranking problems. We evaluate our algorithm on both public dataset and for a real world credit evaluating problem. The results obtained demonstrate the superiority of our algorithm over extended SVM-RFE to solve multiclass problems using ensemble techniques.

Elman neural network was one of the dynamic recurrent neural networks. In this paper, a modified Elman network was introduced first. Then we proposed a PID Elman neural network and its learning algorithms are discussed in detail. Simulation results based on ideal mathematical model and hydro-turbine governing system model show that the PID Elman network is prior to the modified Elman network in identifying nonlinear dynamic system.

The relationship between the error signal and gain parameters of PID controller is nonlinear, so fitting and constructing the nonlinear of each parameter can be used respectively for the individual tuning each part of PID controller. In this paper, it is described that based on the tuning law between the control and error, with formulating the nonlinear function of each gain parameter, the nonlinear PID controller could be optimized and constructed by adopting genetic algorithm. The simulate results of typical system shows that the dynamic and static performances of the system can be both attended to at a satisfied degree.

Based on the complicated relationships between the symptoms and the defects of hydro-generator units, An approach to diagnosing the faults in hydro-generator units via a neural networks combined with Genetic algorithm (GA) and nonlinear principal analysis neural network (NLPCA NN) is presented in this paper. At first, GA optimizes both the structure and the connection of the NLPCA NN. The so-called GA-NLPCANN is employed to extract main features from high dimension samples. And then the Bayesian neural network (BNN) is also added to test the final diagnosis performance. Finally, the proposed scheme is applied to diagnose the faults samples of hydro-generator unit and the simulation results have proved the effectiveness of this method.

Canonical genetic algorithms have the defects of pre-maturity and stagnation when applied in optimizing problems. In order to avoid the shortcomings, an adaptive niche hierarchy genetic algorithm(ANHGA) is proposed. The algorithm is based on the adaptive mutation operator and crossover operator to adjust the crossover rate and probability of mutation of each individual, whose mutation values are decided using individual gradient. This approach is used in Percy and Shubert function optimization. Comparisons between NGA and ANHGA have been done by establishing a simulation model, the results of mathematics model and actual industrial model show that ANHGA is feasible and efficient in the design of multi-extremum.

The Elman network is a well-known recurrent neural network. In this paper, an overview of the structure of the Elman neural network and its modified form are presented. Both have trainable feed-forward connections. Then, by comparing with the discrete PID control algorithm, their dynamic characteristics are fully discussed using the z transform function. Finally, we conclude that the modified Elman network has better dynamic properties.

Traditional hydroturbine governing systems are mainly based on PID regulators. Because of the indeterminacy, nonlinearity, and time-varying parameters of the controlled plant, it is difficult to obtain satisfactory system performance for all running conditions. To overcome this drawback, in this paper, we introduce an intelligent integral strategy which is realized by fuzzy logic and the output of which is used to modify the integral gain of the PID regulator. Simulation proves that the method proposed here is not only easy to implement, but also gives a good performance when the plant's key parameters change within a large range.

This paper presents a fuzzy logic strategy for the current control of a three-phase voltage source power PWM-inverter. The base of this regulator is a direct digital predictive loop which has a very good dynamic performance, but the steady state performance will heavily depend on the accuracy of the model structure and plant's parameters. To reduce the steady errors and compensate the system uncertainties, a feedforward control loop and a fuzzy logic algorithm are introduced. The direct digital predictive loop with the feedforward loop, which can be seen as a hybrid current regulator, generates the command voltage based on the nominal system conditions, guarantees the system with a very fast dynamic response and a smaller system error. The fuzzy logic algorithm, by measuring the amplitude and phase angle of the system error, generates a modifying signal to correct the gains of the direct digital predictive loop and the feedforward loop. When the difference between the reference and actual signals is larger than a given threshold, therefore it minimizes the effects of system uncertainties. Simulation results are presented to verify the effectiveness of the current regulation algorithm.

The hydro-turbine governing system is a nonlinear, nonminimum phase, time-variant system. To improve the performance of the control system, it is necessary to find a good algorithm. In this paper, the compound fuzzy neural control, which combines the advantages of fuzzy control and neural control, is introduced. The simulation and analysis show that the proposed method is effective and better than the conventional PID control system.