Study On Monitoring And Forecasting Method Of Saturation Line In Tailings Dam

Tailings dam is an important part of the mine enterprises.And it is a dangerous source of man-made debris flow with high potential energy.Its safety seriously affects the normal production and development of enterprises,which is a serious threat to the socio-economic and ecological environment.The saturation line is the lifeline of tailings dam.So its position is closely related to the safety of tailings.The high position of the saturation line will reduce the stability of the tailings dam,which leads to the occurrence of unsafe accidents in tailings.Therefore,it is vital important for ensuring the normal operation of the tailings to accurately control of the height of the saturation line and timely improvement of the anti-sliding stability factor of the dam.However,the height of saturation line is dynamic nonlinear system which is impacted by series of complex factors.And it brings difficulties to predict the height and trend of the saturation line accurately and effectively.Then,the prediction model of tailings dam saturation line is proposed,and the height and trend of infiltration line are predicted in time to ensure the safe operation of tailings.The construction of the prediction model of the saturation line is mainly studied in this paper.The main researches include:(1)The impacts of the height of the saturation line on the safety of the tailings dam are studied.The Swedish slice method is analyzed.And the result is that the increase of the saturation line will reduce the stability of the tailings dam.The factors affect the height of the saturation line are studied.The impacts of the reservoir water level and the dry beach length to the height of the saturation line are determined.Meanwhile,the simulation of seepage law inner the dam with different reservoir water level and different factors are carried out.The relationship of dam seepage and the change of the height of saturation line are analyzed.And it provides the theoretical basis for the reduction of the height of the infiltration line.(2)Aiming at the problem that GM(1,1)algorithm used to solve the development factor a and the gray effect b would be impacted by the background value.The identifying parameters method of avoiding background value is proposed.The problem of low prediction accuracy caused by the background value of the selected steps or improper selection is avoided.Aiming at the problem of initial condition with fixed value would affect the accuracy when GM(1,1)model predicts.The method of constructing the initial value with the variable weight is proposed.The impacts of the fixed initial value to the prediction accuracy are avoided.Through the verification,the predictive value of the optimized model is closer to the real value.And the prediction accuracy is higher.(3)Aiming at the problem of BP(Back Propagation)neural network is easy to fall into local minimum and slow convergence.The BP neural network is optimized by genetic algorithm(GA-Genetic Algorithm),and GA-BP neural network is constructed.The convergence characteristic of the BP network is optimized by using the fitness function and operator of GA.The global optimal network weights and thresholds were fast searched.The experiments show that the GA-BP network has better prediction effect than traditional BP network.Aiming at the problem of single sample type of traditional grey neural network,a new combination forecasting model is proposed,and add the GM(0,3)model.Taking full account of the impact of related factors on the main control factors,and in order to break the limitation of the traditional model to predict saturation line only rely on the data of history single,and the prediction model of saturation line based on improved grey neural network is established.The results show that the model can predict the change of the saturation line height in the short term,and it can provide reliable data to calculate the stability of the tailings dam,and ensure the safe production of mining enterprises.(4)According to the monitoring task,design the monitoring system content,composition,development the host computer program,to achieve automatic and remote collection of field data,data storage,analysis and early warning function of PC,fully integrated VB graphics display advantages and MATLAB powerful data processing function,effectively predict and display the change trend of saturation line.