人工智能在储层损害诊断及预测中的应用与展望

Application and prospect of artificial intelligence in reservoir damage diagnosis and prediction

人工智能(AI)是计算机科学的一个分支,在积累、处理、运用信息方面具有独特的优势,被广泛应用于油气藏储层保护领域。本文在简要介绍人工智能及其在石油工程中的应用的基础上,重点对目前两种最为常见的人工智能方法在石油工程中的研究进展进行综述:神经网络技术可以很好地结合非线性问题,但数据量少、计算成本高;专家决策支持系统可复合专家知识,在全面性、适应性上存在一定的优势,且使用成本较低,但存在着获取知识相对困难,推理能力弱,灵活性差的缺点。最后,列举了人工智能方法在储层损害诊断与预测中的应用,并对其发展趋势进行了展望。

Artificial intelligence(AI), a branch of computer science, has unique advantages in accumulation, processing and application of information and is widely used in the field of formation protection. On the basis of a brief introduction of artificial intelligence and its application in petroleum engineering, this paper summarizes the research progress of two most common artificial intelligence methods in petroleum engineering. Neural network technology can solve the non-linear problem well, but it has less data and high computing cost. Expert decision support system can compound expert knowledge, which has certain advantages in comprehensiveness and adaptability, and lower use cost. However, it has disadvantages such as relatively difficult to acquire knowledge, weak reasoning ability and poor flexibility. Finally, the application of artificial intelligence in formation damage diagnosis and prediction is listed, and its development trend is prospected.