论文部分内容阅读
合理的钻井液配方是保证钻井工程能够顺利完成的必要条件,因此钻井液配方的优化设计已成为钻井工程中一个十分关注的问题。基于支持向量机建立通过钻井液性能参数反算处理剂加量的模型,即在给定钻井液性能参数的情况下,利用此模型反推各种处理的加量以达到优化钻井液配方的目的。根据某油田常用的强抑制性水基钻井液性能为要求,利用该模型计算出钻井液配方,将这些配方进行实验验证,实验结果表明,支持向量机计算出的7组配方中有5组符合该油田所使用的钻井液性能要求,模型仅经过一次训练正确率达到71.4%。该模型对钻井液的室内评价实验具有指导作用,能缩小实验时处理剂加量范围,减少实验工作量。
Reasonable drilling fluid formulation is a necessary condition to ensure the successful completion of drilling engineering. Therefore, the optimal design of drilling fluid formulation has become a very important issue in drilling engineering. Based on the support vector machine, a model for calculating the dosage of back-treatment agent through drilling fluid performance parameters is established. That is to say, given the parameters of drilling fluid, the model can be used to reverse the dosage of various treatments to achieve the purpose of optimizing drilling fluid formulation . According to the commonly used strong inhibition water-based drilling fluid performance in a certain oilfield, the drilling fluid formula is calculated by using this model and the experimental results are validated. The experimental results show that there are 5 groups of 7 formulas calculated by support vector machine The performance of the drilling fluid used in this field requires that the model be trained only once with a correct rate of 71.4%. The model can guide the laboratory evaluation of drilling fluid, reduce the dosage range of the treatment agent and reduce the experimental workload.