Safe and efficient deep drilling is a fundamental requirement for the development of oil and gas resources. In this regard, the application of membrane separation technology for drilling fluid gas separation and monitoring is highly significant. In this study, several commonly used permeable membrane materials were analyzed, and a PDMS separation membrane was preliminarily selected as a suitable material for downhole gas separation. We designed an experimental setup to investigate the separation performance of PDMS membranes. The effects of the separation pressure difference, operating temperature, and membrane thickness on the performance of PDMS membranes were analyzed, and the microstructure changes in the PDMS membrane under high temperature and pressure were observed using a scanning electron microscopy. The experimental results showed that PDMS membranes with a thickness of 150–200 μm can work stably and maintain good strength and permeability at a separation pressure difference of 1.1 MPa and a temperature of 150 °C. The SEM observations revealed that the PDMS separation membrane had a smooth surface and uniform microstructure after continuous operations for 15 h under the temperature and pressure conditions, without any cracks, demonstrating high temperature and pressure resistance. These research results provide an important reference for the application of PDMS separation membranes in downhole gas separation technology.

In the petroleum industry, accurately identifying downhole fluid is crucial for understanding fluid composition and estimating crude oil contamination and other properties. Near-infrared (NIR) spectrum analysis technology has achieved successful fluid identification applications due to its non-destructive nature and high efficiency. However, for real-time downhole fluid analysis, the NIR spectrometer faces challenges such as miniaturization and cost effectiveness. To address these issues, we construct a real-time downhole fluid identification system in this work. First, we propose a lightweight and deployable fluid identification model by integrating the successive projections algorithm (SPA) and a quadratic neural network (QNN). The SPA allows for spectral feature selection, and the QNN acts as an efficient identification model. Consequently, we use only four specific wavelengths with a one-hidden-layer QNN to achieve high identification accuracy. Second, we devise a hardware deployment scheme for real-time identification. We use four laser diodes to replace conventional light sources, further saving space. The QNN is then deployed to the STM32 MCU to implement real-time identification. Computational and online experiments demonstrate that our system functions well in real-time fluid identification and can further estimate the oil contamination rate with acceptable error.