本文已被：浏览 1360次 下载 0次
中文摘要: 提出一种基于改进粒子群算法（PSO）优化最小二乘支持向量机（LSSVM）的MEMS陀螺随机漂移的预测模型建立方法。该方法首先应用最小二乘支持向量机对MEMS陀螺随机漂移建立预测模型，然后应用改进粒子群算法对该模型进行优化，最后应用参数优化后的LSSVM预测模型对随机漂移进行预测。该方法不仅解决了支持向量机训练速度慢和所需计算资源多的问题，而且文中提出的改进的惯性权值递减策略使PSO算法在全局或局部搜索能力上的侧重具有更好的适应度。实验结果表明，该预测模型可以有效地进行陀螺随机漂移的预测，且预测效果优于基本PSO优化的最小二乘支持向量机。
Abstract:A prediction model modeling method for MEMS gyroscope’s random drift is proposed, which is based on the least squares support vetor machine optimized by modified particle swarm algorithm. Firstly, we build a forecasting model of MEMS gyroscope’s random drifts with least squares support vector machine, then the modified particle swarm algorithm is used to optimize the model. Finally, the optimized LSSVM model is used for prediction of MEMS gyroscope’s random drifts. The modeling method solve SVM’s disadvantage of slow training speed and requesting more resources, what’s more, the modified PSO have better fitness in selecting global searching capability or local searching capability. The experimental result shows that the modeling method can effectively predict MEMS gyroscope’s random drifts, and it has better effect than LSSVM optimized by PSO.
keywords: MEMS gyroscope least squares support vetor machine modified particle swarm algorithm random drifts
文章编号：cg15001165 中图分类号： 文献标志码：
基金项目:国家自然科学基金
引用文本：