基于IAEFA-LSSVM的煤与瓦斯突出预测的新方法

A New Method for Predicting Coal and Gas Outburst Based on IAEFA-LSSVM

为了在发生数据缺失和异常的情况下完成煤与瓦斯突出预测,提出基于IAEFA-LSSVM的煤与瓦斯突出预测的新方法。在缺失数据时,利用皮尔逊相关系数实时完成缺失数据的填充;当出现数据异常时,使用Pauta准则处理数据异常值;在人工电场算法初始化阶段引入透镜成像学习策略,实现初始种群多样性和个体质量的提升,采用正余弦算法改进人工电场算法最优解位置,从而提高人工电场算法的寻优能力。建立改进人工电场算法优化最小二乘支持向量机模型,并采用皮尔逊相关系数和Pauta准则完成数据实时缺失和数据异常的处理,预测结果的灵敏度为100%,准确度为97.5%。实验结果表明,该模型能够在数据缺失和数据异常情况下实时完成煤与瓦斯突出预测,可作为一种新的煤与瓦斯突出预测模型。

In order to complete the prediction of coal and gas outburst in the case of missing and abnormal data,a new method of coal and gas outburst prediction based on IAEFA-LSSVM was proposed.In case of missing data,Pearson correlation coefficient was used to fill in the missing data in real time.When data abnormality occurs,Pauta criterion was used to deal with data abnormal value.In the initialization stage of the artificial electric field algorithm,the lens imaging learning strategy was introduced to improve the initial population diversity and individual quality.The sine cosine algorithm was used to improve the optimal solution position of the artificial electric field algorithm,so as to improve the optimization ability of the artificial electric field algorithm.The improved artificial electric field algorithm was established to optimize the least squares support vector machine model,and the Pearson correlation coefficient and Pauta criterion were used to deal with the real-time missing and abnormal data.The sensitivity of the prediction results was 100%and the accuracy was 97.5%.The experimental results show that the model can complete the prediction of coal and gas outburst in real time under the condition of missing and abnormal data,and can be used as a new coal and gas outburst prediction model.