基于ISSA-SVM的钻井卡钻事故预测

为预防钻井过程中卡钻事故的发生，通过提出了一种改进麻雀搜索算法(improved sparrow search algorithm, ISSA)优化支持向量机(support vector machines, SVM)的预测模型方法(ISSA-SVM),在发现者位置更新公式中引入一种改进的自适应非线性惯性递减权重；在警戒者位置更新公式中引入莱维飞行策略。利用主成分分析法(principal component analysis, PCA)对外国某大型油田的实测钻井数据进行降维处理，并利用惩罚参数和核参数进行卡钻事故的预测。实验结果表明：ISSA-SVM的预测准确率高达85.185 2%,且收敛速度更快，可见ISSA-SVM可有效预测钻井卡钻事故。

Prediction of drilling jam accidents based on ISSA-SVM

In order to prevent the occurrence of stuck drilling accidents during drilling, an improved sparrow search al-gorithm (ISSA) predictive model method (ISSA-SVM) to optimize support vector machines (SVM) is proposed, and an improved adaptive nonlinear declining inertia weight is introduced into the finder position update for-mula. Introduced the Levy flight strategy in the alert position update formula. The principal component analysis method was used to reduce the dimensionality of the measured drilling data of a large foreign oilfield, and the penalty parameters and nuclear parameters were used to predict the stuck drilling accident. The experimental results show that the prediction accuracy of ISSA-SVM is as high as 85.185 2%, and the convergence speed is faster, which shows that ISSA-SVM can effectively predict stuck drilling accidents.