Research On Evaluation Of University Laboratory Safety Based On GA-BP Neural Network

Evaluation of university laboratory safety is the weakness in the management of laboratory safety. Aiming at the present university laboratory safety evaluation is lack of more comprehensive, reasonable, efficient evaluation method, for the purposeof how toscientifically, objectively and accuratelyevaluate university laboratory safety level, on the basis of theoretical exploration on BP neural network and genetic algorithm, above tow are combined, and applied to the evaluation of university laboratory safety. Evaluation of university laboratory safety based on GA-BP neural network is researched in the paper. The research work includes the following aspects:Firstly, BP Neural Network with nonlinear mapping, learning and the adaptive ability is applied to the evaluation of university laboratory safety. An evaluation model of university laboratory safety based on BP neural network is proposed.Secondly, Aiming at the deficiency of BP evaluation model of university laboratory safety,a genetic algorithm is used to optimize the weights and thresholds of the BP neural network, and the evaluation model of university laboratory safety based on GA-BP neural network isconstructed.Thirdly,the evaluation model of BP network and GA-BP network are respectively trained, learned and tested by using the neural network toolbox of Matlab and writing GA-BP program. Conclusion that the evaluation model of GA-BP network can achieve higher precision in a shorter period of time and it is obviously better thanevaluation model of BP neural network in convergence rate, accuracy and stabilityis drawn by comparison. The rationality and the high efficiency of the genetic algorithm to optimize BP neural network is validated.Consequently, the research will raise the level of university laboratory safety management, as well as it has positive meaning to application research on the theory of BP neural network and genetic algorithm.