Publications
Sort:
Open Access Original Paper Issue
UAV-based pipeline leakage detection via acoustics with owl auditory-inspired OPEI representation
Petroleum Science 2026, 23(9): 5908-5913
Published: 17 July 2026
Abstract PDF (6.7 MB) Collect
Downloads:0

To address the low sensitivity of visual UAV inspection in leakage detection for above-ground natural gas pipelines, an acoustic detection method inspired by the owl auditory mechanism was developed. An innovative oscillatory positional encoding imaging (OPEI) technique was proposed, through which one-dimensional acoustic signals were converted into two-dimensional image representations incorporating time-domain, frequency-domain, and amplitude information. Recognition accuracy of 97.38% for OPEI images on the testing dataset was achieved by the EfficientNetV2 cascade model. The results demonstrated that the biomimetic design enhanced acoustic signal sensitivity and enabled fine-grained recognition of pipeline leakage apertures (1/5/10 mm). This study proposes a novel acoustic signal processing method, providing a theoretical foundation for ensuring the reliability and safety of natural gas pipeline transportation.

Open Access Original Paper Issue
Dynamic plugging regulating strategy of pipeline robot based on reinforcement learning
Petroleum Science 2024, 21(1): 597-608
Published: 18 August 2023
Abstract PDF (2.8 MB) Collect
Downloads:3

Pipeline isolation plugging robot (PIPR) is an important tool in pipeline maintenance operation. During the plugging process, the violent vibration will occur by the flow field, which can cause serious damage to the pipeline and PIPR. In this paper, we propose a dynamic regulating strategy to reduce the plugging-induced vibration by regulating the spoiler angle and plugging velocity. Firstly, the dynamic plugging simulation and experiment are performed to study the flow field changes during dynamic plugging. And the pressure difference is proposed to evaluate the degree of flow field vibration. Secondly, the mathematical models of pressure difference with plugging states and spoiler angles are established based on the extreme learning machine (ELM) optimized by improved sparrow search algorithm (ISSA). Finally, a modified Q-learning algorithm based on simulated annealing is applied to determine the optimal strategy for the spoiler angle and plugging velocity in real time. The results show that the proposed method can reduce the plugging-induced vibration by 19.9% and 32.7% on average, compared with single-regulating methods. This study can effectively ensure the stability of the plugging process.

Total 2