论文部分内容阅读
针对现有各种类型的浆体输送管道临界淤积流速经验公式形式不一,适用面较窄,且实测值与计算值的误差很大的问题,采用了基于改进的粒子群算法与最小二乘支持向量机相结合的新方法对临界淤积流速展开预测。所改进的粒子群算法在采用异步变化的学习因子、二次型惯性权重递减策略的同时,融合了自然选择的思想。通过实验仿真,结果显示本文采用的算法所取得的效果相比传统的方法要更优。同时,和所选的具有代表性的经验公式相比有着更高的精度。
Aiming at the problems that the empirical formula of the critical silting flow rate in slurry pipelines of various types is different in form and application, and the error between the measured value and the calculated value is very large, an improved particle swarm optimization (PSO) A new method based on support vector machines is used to predict the critical depositional velocity. The improved Particle Swarm Optimization (PSO) incorporates the idea of natural selection while adopting asynchronously changing learning factors and quadratic inertia weight decreasing strategy. The experimental results show that the proposed algorithm is superior to the traditional one. At the same time, it is more accurate than the representative empirical formula chosen.