Pang Q.,Shandong Institute of Business and Technology
Dianwang Jishu/Power System Technology | Year: 2010
Due to its remarkable approximation ability, neural network is widely applied in pattern recognition, model prediction and data mining. However, the approximation error of neural network at the peak value of the approximated nonlinear function is great, especially the error is greater when the slope difference at both sides of the peak value. An improved rough set-based neural network algorithm is proposed and applied in short-term load forecasting. Taking the load in current time interval, load in prior time interval, load difference between current time interval and prior time interval and current time as the inputs of neural network forecasting model, and the forecasted load in next time interval as the output of neural network forecasting model, the forecasted load, i.e., the output of neural network forecasting model, is compensated according to rough set theory to improve the forecasted result. Simulation results show that using the proposed method the precision of load forecasting can be evidently improved.
Gong Z.,Shandong Institute of Business and Technology
Mathematics and Computers in Simulation | Year: 2010
In fed-batch fermentation of glycerol bio-dissimilation to 1,3-propanediol (1,3-PD) by Klebsiella pneumoniae, glycerol and alkali are fed into the reactor to provide nutrient and maintain a suitable environment for cells growth. Taking the feeding process as a time-continuous process, we present a nonlinear multistage dynamical system to formulate the fed-batch fermentation. In view of the big errors between experimental data and computational values, a parameter identification model is established. Finally, an improved Nelder-Mead simplex search method is developed to seek the unknown parameters in the model. Numerical simulations show that the multistage dynamical system can describe the fed-batch process better, compared with the previous results. © 2010 IMACS.
Zhang S.-X.,Shandong Institute of Business and Technology
Journal of Computers | Year: 2011
An unmanned mining technology for the fully mechanized longwall face automation production is proposed and studied. The essential technology will bring the longwall face production into visualization through the VR (Virtual Reality) and AR (Augmented Reality) combination. Based on the visual theoretical model of the longwall face, the combination of virtual and reality, the real-time interactive and the 3D registration function were realized. The 3D image of the longwall face may be scaled and viewed from free angles. Using the overall affine coordinate system, the stereoscopic impression for the longwall face was enhanced; the video image is matched to 3D characteristics; the occlusion issue is resolved with the depth information solution; and the simplification visualization interactive method is proposed. The Key technology and Alpha channel are used to the combination of the real longwall face and the virtual user. © 2011 ACADEMY PUBLISHER.
Li D.,Shandong Institute of Business and Technology
Journal of Convergence Information Technology | Year: 2011
The atmospheric turbulence is an important factor which affects the laser atmosphere communication. Particularly, the probability distribution of the light intensity fluctuation is the focus of the research when the laser transfers in the strong turbulence or long distance transmission. And the multi-beam transmission is one of the most important ways to settle the impact on the atmospheric turbulence. This paper takes the negative exponential distribution, I-K distribution as the basis to establish the distribution model of the light intensity under the weak and strong turbulence. Moreover, it uses the test result of related document s for verification. The result shows that the simulation result agrees with the test result relatively; the distribution curve is corresponded; and the degree of fitting is relatively high. With the increase of the beams, the function value for the light intensity distribution is increased; and with the increase of the receiving aperture, the function value for the light intensity distribution is increased.
Yang L.,Shandong Institute of Business and Technology
International Journal of Advancements in Computing Technology | Year: 2011
In the fault-tolerant system, there is one bottleneck problem to need to solve, the voting design when there are many fault-tolerant gyroscopes floating point input signals. A novel fuzzy voting design has been proposed based on adaptive extended Kalman filter. Through connecting EKF in the fuzzy voting mechanism, the adaptive fuzzy voting design has solved that the smaller deviated signals are unable to judge. Moreover, we have achieved the real-time adjustment of the Q covariance and R covariance matrix by designing another logical controller with extended Kalman filter and the fuzzy logic method. We can obtain the real time spaceborne apparatus's posture by simulating gyroscope, the fuzzy voting design can get the correct output, it has solved the measured noise and the gyro error.