计算机应用 ›› 2021, Vol. 41 ›› Issue (6): 1842-1848.DOI: 10.11772/j.issn.1001-9081.2020091429

所属专题: 前沿与综合应用

• 前沿与综合应用 • 上一篇    

基于形态流的石油钻井水流异常检测

李衍志, 范勇, 高琳   

  1. 西南科技大学 计算机科学与技术学院, 四川 绵阳 621010
  • 收稿日期:2020-09-15 修回日期:2020-11-15 出版日期:2021-06-10 发布日期:2020-11-26
  • 通讯作者: 李衍志
  • 作者简介:李衍志(1994-),男,四川西昌人,硕士研究生,主要研究方向:计算机视觉、视频异常事件检测、图像处理;范勇(1972-),男,重庆人,教授,博士,主要研究方向:计算机视觉、视觉测量、软件测试;高琳(1976-),男,四川绵阳人,讲师,博士,主要研究方向:计算机视觉、人工智能、模式识别。
  • 基金资助:
    四川省教育厅科技项目(18ZA0501)。

Anomaly detection of oil drilling water flow based on shape flow

LI Yanzhi, FAN Yong, GAO Lin   

  1. School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang Sichuan 621010, China
  • Received:2020-09-15 Revised:2020-11-15 Online:2021-06-10 Published:2020-11-26
  • Supported by:
    This work is partially supported by the Science and Technology Project of the Education Department of Sichuan Province (18ZA0501).

摘要: 针对石油钻井水流的智能监控技术,可以实现石油钻井污染气体的自动监测,并最大限度地减少人工监测成本。针对现有特征提取方法不能描述水流形态变化过程,异常样本获取困难且不能完全列举,以及没有充分利用融合层信息的问题,提出了一种水流异常数据检测算法。首先,提出了一种新特征表示方法——形态流;然后,将经典的异常检测无监督神经网络GANomaly优化为残差结构;最后,在GANomaly的基础上增加了特征融合层,从而提升神经网络的学习能力。实验结果表明,改进后的算法检测精度达到了95%,相较GANomaly算法提升了5个百分点。所提算法能适用于不同场景下的水流异常数据检测,并能克服雾气对实验结果的影响。

关键词: 视频异常事件检测, 石油钻井水流异常检测, 生成对抗网络, 水流分割

Abstract: Intelligent monitoring technology for the water flow of oil drilling can realize the automatic monitoring of gaseous pollutant from oil drilling and minimize the cost of manual monitoring to the greatest extent. The existing feature extraction methods cannot describe the change process of water flow, it is difficult to obtain abnormal samples and fully enumerate them, and the fusion layer information is not fully utilized. In order to solve the problems, a new water flow abnormal data detection algorithm was proposed. Firstly, a new feature representation method named shape flow was proposed. Then, the classic anomaly detection unsupervised neural network GANomaly was optimized into a residual structure. Finally, a feature fusion layer was added to the GANomaly to improve the learning ability of neural network. Experimental results show that, the detection accuracy of the improved algorithm reaches 95%, which is 5 percentage points higher than that of the GANomaly algorithm. The proposed algorithm can be applied to the detection of abnormal water flow data in different scenarios, and can overcome the influence of fog on the experimental results.

Key words: video abnormal event detection, oil drilling water flow anomaly detection, Generative Adversarial Network (GAN), water flow segmentation

中图分类号: