Evaluation of Fracturing Effect of Tight Reservoirs Based on Deep Learning.

The utilization of hydraulic fracturing technology is indispensable for unlocking the potential of tight oil and gas reservoirs. Understanding and accurately evaluating the impact of fracturing is pivotal in maximizing oil and gas production and optimizing wellbore performance. Currently, evaluation methods based on acoustic logging, such as orthogonal dipole anisotropy and radial tomography imaging, are widely used. However, when the fractures generated by hydraulic fracturing form a network-like pattern, orthogonal dipole anisotropy fails to accurately assess the fracturing effects. Radial tomography imaging can address this issue, but it is challenged by high manpower and time costs. This study aims to develop a more efficient and accurate method for evaluating fracturing effects in tight reservoirs using deep learning techniques. Specifically, the method utilizes dipole array acoustic logging curves recorded before and after fracturing. Manual labeling was conducted by integrating logging data interpretation results. An improved WGAN-GP was employed to generate adversarial samples for data augmentation, and fracturing effect evaluation was implemented using SE-ResNet, ResNet, and DenseNet. The experimental results demonstrated that ResNet with residual connections is more suitable for the dataset in this study, achieving higher accuracy in fracturing effect evaluation. The inclusion of the SE module further enhanced model accuracy by adaptively adjusting the weights of feature map channels, with the highest accuracy reaching 99.75%.

Deep Learning-Based Simultaneous Temperature- and Curvature-Sensitive Scatterplot Recognition.

Since light propagation in a multimode fiber (MMF) exhibits visually random and complex scattering patterns due to external interference, this study numerically models temperature and curvature through the finite element method in order to understand the complex interactions between the inputs and outputs of an optical fiber under conditions of temperature and curvature interference. The systematic analysis of the fiber's refractive index and bending loss characteristics determined its critical bending radius to be 15 mm. The temperature speckle atlas is plotted to reflect varying bending radii. An optimal end-to-end residual neural network model capable of automatically extracting highly similar scattering features is proposed and validated for the purpose of identifying temperature and curvature scattering maps of MMFs. The viability of the proposed scheme is tested through numerical simulations and experiments, the results of which demonstrate the effectiveness and robustness of the optimized network model.

A Study on Impact Force Detection Method Based on Piezoelectric Sensing.

Impact force refers to a transient phenomenon with a very short-acting time, but a large impulse. Therefore, the detection of impact vibration is critical for the reliability, stability, and overall life of mechanical parts. Accordingly, this paper proposes a method to indirectly characterize the impact force by using an impact stress wave. The LS-DYNA software is utilized to establish the model of a ball impacting the steel plate, and the impact force of the ball and the impact response of the detection point are obtained through explicit dynamic finite element analysis. In addition, on this basis, a correspondence between the impact force and the impact response is established, and finally, an experimental platform for impact force detection is built for experimental testing. The results obtained by the finite element method are in good agreement with the experimental measurement results, and it can be inferred that the detected piezoelectric signal can be used to characterize the impact force. The method proposed herein can guide the impact resistance design and safety assessment of structures in actual engineering applications.

Development of a 16-Channel Broadband Piezoelectric Micro Ultrasonic Transducer Array Probe for Pipeline Butt-Welded Defect Detection.

Butt welding is extensively applied in long-distance oil and gas pipelines, and it is of great significance to conduct non-destructive ultrasonic testing of girth welds in order to avoid leakage and safety accidents during pipeline production and operation. In view of the limitations of large transducer size, single fixed beam angle, low detection resolution and high cost of conventional ultrasonic inspection technologies, a 16-channel piezoelectric micro ultrasonic transducer (PMUT) array probe was developed through theoretical analysis and structural optimization design. After the probe impedance characterization, the experimental results show that the theoretical model can effectively guide the design of the ultrasonic transducer array, offering the maximum operating frequency deviation of less than 5%. The ultrasonic echo performance tests indicate that the average -6 dB bandwidth of the PMUT array probe can be up to 77.9%. In addition, the fabricated PMUT array probe has been used to successfully detect five common internal defects in pipeline girth welds. Due to the multiple micro array elements, flexible handling of each element, large bandwidth and high resolution of defect detection, the designed PMUT array probe can provide a good application potential in structural health monitoring and medical ultrasound imaging fields.

Monitoring of Epoxy-Grouted Bonding Strength Development between an Anchored Steel Bar and Concrete, Using PZT-Enabled Active Sensing.

Anchored steel bars have been widely used in retrofitting of existing concrete structures. The bonding strength between the anchored steel bar and the concrete is critical to the integrity of the strengthened concrete structure. This paper presents a method to monitor epoxy-grouted bonding strength development by using a piezoceramic-enabled active sensing technique. One concrete beam with an anchored steel bar was involved in the monitoring test, and two concrete beams with six anchored steel bars were used in the pull-out test. To enable the active sensing, a Lead Zirconate Titanate (PZT) patch was bonded to the surface of the exposed end, and piezoceramic smart aggregates were embedded in each concrete specimen. During the monitoring experiment, signals from PZT sensors and smart aggregates were acquired at intervals of 0, 20, 40, 60, 80, and 100 min. In addition, a pull-out test was performed on each of the remaining six anchored steel bars in the two concrete beams, while the signal was recorded in the test. Furthermore, a wavelet packet analysis was applied to analyze the received signal energies to investigate the bonding strength development between the concrete and the anchored steel bar during the epoxy solidification process. The test results demonstrate the effectiveness of the proposed method in monitoring the bonding strength development between the anchored steel bar and the concrete, using the PZT-enabled active sensing.

Concrete Infill Monitoring in Concrete-Filled FRP Tubes Using a PZT-Based Ultrasonic Time-of-Flight Method.

Concrete-filled fiber-reinforced polymer tubes (CFFTs) have attracted interest for their structural applications in corrosive environments. However, a weak interfacial strength between the fiber-reinforced polymer (FRP) tube and the concrete infill may develop due to concrete shrinkage and inadequate concrete compaction during concrete casting, which will destroy the confinement effect and thereby reduce the load bearing capacity of a CFFT. In this paper, the lead zirconate titanate (PZT)-based ultrasonic time-of-flight (TOF) method was adopted to assess the concrete infill condition of CFFTs. The basic idea of this method is that the velocity of the ultrasonic wave propagation in the FRP material is about half of that in concrete material. Any voids or debonding created along the interface between the FRP tube and the concrete will delay the arrival time between the pairs of PZT transducers. A comparison of the arrival times of the PZT pairs between the intact and the defected CFFT was made to assess the severity of the voids or the debonding. The feasibility of the methodology was analyzed using a finite-difference time-domain-based numerical simulation. Experiments were setup to validate the numerical results, which showed good agreement with the numerical findings. The results showed that the ultrasonic time-of-flight method is able to detect the concrete infill condition of CFFTs.