基于Bitmap的油水井采注优化实时推理引擎

发布时间：2018-02-13 14:47

  本文关键词： 采注优化 推理引擎 Bitmap 规则匹配 事件过滤　出处：《自动化学报》2017年06期 　论文类型：期刊论文

【摘要】：针对油田油水井采注优化业务中,油水井数据量大、地层结构复杂以及人类经验多的特点,分析了传统推理方法在油田采注实时优化处理过程中的不足,采用事件处理思想,提出了一种基于Bitmap事件编码与匹配机制的推理引擎,有效地实现了对无效事件的过滤并提升了事件与规则的匹配效率.在油田实际数据试验平台上对该方法进行了验证并与RETE算法、LFA(Linear forward-chaining)算法的性能对比,结果验证了本文方法在实时推理能力上的有效性.
[Abstract]:In view of the characteristics of large amount of data, complex formation structure and human experience in oil and water well production and injection optimization in oil field, this paper analyzes the shortcomings of traditional reasoning method in the process of real-time optimization of oilfield production and injection, and adopts the idea of event processing. A reasoning engine based on Bitmap event coding and matching mechanism is proposed. The filter of invalid events is realized effectively and the matching efficiency between event and rule is improved. The method is verified on the platform of oilfield actual data and compared with the performance of RETE algorithm. The results show that the proposed method is effective in real-time reasoning.
【作者单位】： 中国科学院沈阳自动化研究所工业控制网络与系统研究室;
【基金】：国家自然科学基金(61533015)资助~~
【分类号】：TE319
，

本文编号：1508408