Search

Artificial sheep algorithm (ASA) is a novel swarm intelligence algorithm. Although ASA performs a good optimization ability, it cannot completely avoid local optimum, premature and imbalance between exploration and exploitation. To solve those problems proposed above, a hybrid improvement strategy is employed on ASA. The hybrid improvement strategy includes two parts, reconstruction strategy and competition strategy which both can not only enhance the diversity of IASA, but also improve the global search ability. Moreover, 13 benchmark functions are run on ASA and the improved ASA named IASA respectively. Test results show that IASA have significantly performed better performance than ASA.

In this paper, the controller optimization problem of the pumped-storage unit (PSU) was examined. The objectives of this paper were to identify the dynamic model of the PSU according to the deep learning model through training of the input-output data and to optimize the parameters of the controller on the basis of this identified model. To achieve the objectives, a novel pump-turbine model based on the B-spline surface was employed to precisely simulate the PSU for data measurement and identification. Next, the long short-term memory (LSTM) network architecture was applied to identify the dynamic model of the PSU. Then, gain tuning of the proportional-integral-derivative (PID) controller was conducted by applying particle swarm optimization on the basis of the identified model. To verify the effectiveness of the proposed method, a simulation platform based on the pumped-storage hydropower plant in China was chosen as the experimental object, and the comparative experiments were conducted. The results show the following: 1) the LSTM model performed better compared with the autoregressive model with exogenous variables, support vector machine, and feedforward neural network inaccuracy; 2) the PID controller tuned with the identified LSTM model has excellent control ability compared with the other identified models, and; 3) the identified LSTM model and optimized controller have very good robustness under different conditions.

A novel hybrid algorithm named HASA based on artificial sheep algorithm (ASA) and particle swarm optimization (PSO) is proposed. Three improvements are respectively employed in the initialization method and movement strategy, which include the initialization of the flock in opposition-based learning, a movement strategy inspired by PSO and a chaotic mutation operator. Sixteen benchmark functions are run on PSO, ASA and the improved ASA named HASA respectively. Test results show that the HASA has achieved significantly better performance than PSO and ASA.

The technology of laser scan range finder is researched, a line laser is used to survey the object section outlines. The system is composed of line laser, CCD camera, Frame Grabber, computer and the software. The mathematical model of the system is defined and studied, the error is analysed, the calibration method is resesrched. the system is calibrated and tested, the result showed that the survey data moved towards with the stripe shape tallies and the system achieve the accuracy requirements.