Coal mine safety production forewarning based on improved BP neural network

Firstly, the early warning index system of coal mine safety production was given from four aspects as per- sonnel, environment, equipment and management. Then, improvement measures which are additional momentum method, adaptive learning rate, particle swarm optimization algorithm, variable weight method and asynchronous learning factor, are used to optimize BP neural network models. Further, the models are applied to a comparative study on coal mine safety warning instance. Results show that the identification precision of MPSO-BP network model is higher than GBP and PSO-BP model, and MPSO- BP model can not only effectively reduce the possibility of the network falling into a local minimum point, but also has fast convergence and high precision, which will provide the scientific basis for the forewarnin~ management of coal mine safetv production.

A Quantitative Seismic Topographic Effect Prediction Method Based upon BP Neural Network Algorithm and FEM Simulation

Topography can strongly affect ground motion,and studies of the quantification of hill surfaces’topographic effect are relatively rare.In this paper,a new quantitative seismic topographic effect prediction method based upon the BP neural network algorithm and three-dimensional finite element method(FEM)was developed.The FEM simulation results were compared with seismic records and the results show that the PGA and response spectra have a tendency to increase with increasing elevation,but the correlation between PGA amplification factors and slope is not obvious for low hills.New BP neural network models were established for the prediction of amplification factors of PGA and response spectra.Two kinds of input variables’combinations which are convenient to achieve are proposed in this paper for the prediction of amplification factors of PGA and response spectra,respectively.The absolute values of prediction errors can be mostly within 0.1 for PGA amplification factors,and they can be mostly within 0.2 for response spectra’s amplification factors.One input variables’combination can achieve better prediction performance while the other one has better expandability of the predictive region.Particularly,the BP models only employ one hidden layer with about a hundred nodes,which makes it efficient for training.

Motion Control of Underwater Vehicle Based on Least Disturbance BP Algorithm

Up to now, some technology of neural networks are developed to solve the non-linearity of researched objects and to implement the adaptive control in many engineering fields, and some good results were achieved. Though it puts some questions over to design application structure with neural networks, it is really unknowable about the study mechanism of those. But, the importance of study ratio is widely realized by many scientists now, and some methods on the modification of that are provided. The main subject is how to improve the stability and how to increase the convergent rate of networks by defining a good form of the study ratio. Here a new algorithm named LDBP (least disturbance BP algorithm) is proposed to calculate the ratio online according to the output errors, the weights of network and the input values. The algorithm is applied to the control of an autonomous underwater vehicle designed by HEU. The experimental results show that the algorithm has good performance and the controller designed based on it is fine.

Information integration research on cumulative effect of 'Siqi,Wuwei,and Guijing' in Traditional Chinese Medicine

OBJECTIVE:To study the morphological basis of the role of Siqi(cold as winter,cool as autumn,warm as spring,hot as summer),Wuwei(five flavors:sweet,pungent,salty,sour,and bitter),and Guijing(meridian tropism) through the use of information integration.METHODS:A14C-2-deoxy-glucose autoradiography method was adopted to determine the overall impact of treatment with 39 herbs on functions of various tissues and organs.Data was measured at 4hs after a single dose and following the last treatment of repeated doses for a week.Least-squares estimation was used and fitted for each herb regression effect of organs and tissues after singleand repeated treatment.The slope of the regression line represented the cumulative trend of the effect of the herbs(β),and the standard deviation of the slope(Sβ) was compared with those of the untreated animals(t 'test).All significantly cumulative effect trends were applied with an artificial neural network,which integrated the relationship among Siqi,Wuwei,and Guijing with tissues and organs.RESULTS:There is a certain relationship among the Siqi,Wuwei,Guijing and the anatomy of organs and tissues,but the different scores indicate that influence of Siqi,Wuwei,Guijing to anatomy of organs and tissues was a nonlinear state.CONCLUSION:Results demonstrated that the effects of Siqi,Wuwei,and Guijing have a morphological basis,and each concept was associated with multiple anatomical structures.