基于二进制蚁群时变灰模型的汛期水库安全预警模型

Reservoir Safety Early Warning Model in Flood Season Based on Binary Ant Colony Time-Varying Grey Model

针对汛期水库安全监测数据短序列、贫信息、多突变的特征,提出了采用二进制蚁群时变灰模型构建水库安全监测预警分析模型。将二进制蚁群算法引入时变灰模型的参数优化中,既克服了蚁群算法在对组合优化的缺陷,又能避免传统灰模型参数固定导致模型适应性不强的缺点;同时采用等维新信息处理,可以进一步提高模型对新信息的利用,增加模型中长期预测能力。实际工程应用表明,基于二进制蚁群的时变灰模型对水库安全预警的非线性拟合是可行的,为汛期水库的安全稳定分析评价提供了一种较为有效的新方法。

The mode of reservoir safety monitoring and early warning based on binary ant colony algorithm-time varying grey model is proposed to solve the problems on the characteristics of“Small samples,poor information,multimutation”in reservoir flood season safety monitoring data.The binary ant colony algorithm is introduced into the optimization of weights in time varying grey model,which not only overcomes the shortcomings of the ant algorithm using in the combinatorial optimization,but also avoids the disadvantages of traditional grey model's poor adaptability caused by fixed parameters.The application of equal-dimensional innovation to the grey model can further improve the utilization of innovation and increase the medium and long-term prediction ability of the model.The analysis result shows that the mode of reservoir safety monitoring and early warning based on binary ant colony algorithm-time varying grey model is feasible with high efficiency,and so provides a new method for safety and stability analysis of reservoir.