In oil exploitation, the short maintenance period and the poor real-Time performance of dynamometer card sensors limit the timely working state diagnosis for sucker rod pumps (SRP). The motor is the power source of the SRP that provides all the energy required to lift the oil from underground to surface. The motor power output is highly associated with the working state of the entire equipment. Thus, this article proposes a new strategy to predict the working state of SRP based on motor power. First, seven novel features are extracted from motor power data to support the modeling and diagnosing processes, with the consideration of the significant parameters such as valve's working points and the operating cycle of SRP. Moreover, a custom-designed multiple hidden conditional random fields model with time window is employed as the classifier to identify different working states. At last, the proposed method is validated by a set of motor power data collected from wells by a self-developed device. The experimental result demonstrates the effectiveness of the proposed method for the working state diagnosis of SRPs.
- hidden conditional random fields (HCRFs)
- motor power data
- sucker rod pump (SRP)
ASJC Scopus subject areas
- Control and Systems Engineering
- Electrical and Electronic Engineering