上海交通大学学报

上海交通大学学报

• • 上一篇    

融合深度学习的油田柱塞式注水泵不平衡数据故障诊断方法

  

  1. 上海交通大学 机械与动力工程学院，上海 200240
  • 作者简介:吴泽林（2000—），硕士生，从事设备衰退预测研究。
  • 基金资助:

    国家重点研发计划重点项目(2022YFF0605700)

A fusion method based on deep learning for oil field injection pump unbalanced data in fault diagnosis

  1. School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China

PDF (PC)

17

摘要： 针对油田柱塞式注水泵的故障诊断中存在的数据不平衡问题，提出了一种融合小波包分解和高效通道注意力（efficient channel attention, ECA）机制的多级Inception-长短时记忆（long short term memory, LSTM）网络模型。该模型利用小波包分解技术对振动信号的低频和高频成分进行分解，Inception模块从多个尺度提取数据特征，LSTM模块对数据的时序相关性进行捕捉，同时ECA机制进一步增强了模型对跨信道数据相关性的挖掘能力，提升了特征表示的准确性。使用某油田实际作业现场中采集的柱塞泵振动数据进行效果验证，结果表明，该模型在多个指标下的表现最优，诊断准确率可达到99.38%，证明了所提出模型的有效性和优越性。

关键词: 柱塞式注水泵, 不平衡数据, 卷积神经网络, 长短时记忆网络, 注意力机制

Abstract: Due to the data imbalance problem in the fault diagnosis of oilfield plunger injection pumps, a multilevel Inception-LSTM (long short term memory) network incorporating wavelet packet decomposition and efficient channel attention (ECA) mechanism is proposed in this paper. The wavelet packet decomposes the low-frequency and high-frequency components of the vibration signal. The Inception module extracts the data features from multiple scales. The LSTM module captures the temporal correlation of the data. The ECA mechanism further enhances the model's mining ability for cross-channel data correlation. The experiment is based on the data collected in an operation site of an oil field. The results show that the proposed model performed optimally. The fault diagnostic accuracy can reach 99.38%, which demonstrates the effectiveness and superiority of the proposed model.

Key words: plunger injection pump; imbalance data, convolutional neural networks, long short term memory（LSTM）, attention mechanisms

中图分类号: