In the phase of oil drilling, mud filtrate penetrates into porous formations and alters the pore fluid properties. This complicates well logging exploration, and inevitably gives rise to shift in reservoir estimation. Logging engineers deem mud invasion a harm and attempt to eliminate its impact on logging data exploration. However, from our point of view, the mudcontaminated parts of the formation do also carry some valuable information, notably with regard to the key hydraulic properties. Therefore, if adequately characterized, mud invasion effects, in turn, could be utilized for reservoir estimation. Typically, the invasion depth critically depends on the formation porosity and permeability. To achieve this objective, we propose to use borehole radar to determine the mud invasion depth considering a high spatial resolution of ground-penetrating radar (GPR) compared with the conventional logging tools. We implement numerical investigations on the feasibility of this approach by coupling electromagnetic (EM) modelling with fluid flow modelling in an oil-bearing formation disturbed by mud invasion effects. The simulations imply that a time-lapse radar logging is able to extract EM reflection signals from mud invasion front, and the invasion depth and EM velocity can be obtained by a downhole antenna displacement of one source and two receivers. We find that there exists a positive correlation between the estimated invasion depth and permeability curves, and a negative correlation between the estimated velocity and porosity curves. We suggest that borehole radar has potential to estimate permeability and porosity of oil reservoirs, wherein the mud invasion effect is positively utilized. The study demonstrates a potential method of oil reservoir estimation and a novel application of GPR in oil fields @en

In hydrocarbon drilling, mud filtrate penetrates permeable formations and alters the pore fluid characteristics in the immediate vicinity of the borehole. Typically, the prevailing in situ pore fluids are displaced by the invading mud filtrate, which leads to gradually changing distributions of the fluid and electrical properties. Understanding this invasion process is crucial for the interpretation of logging data and associated reservoir evaluations. Conventional logging methods tend to be inadequate for this purpose as their resolution is too low. We find that invasion depth can be determined from borehole radar data using an optimized antenna configuration and time-lapse measurements. A series of parametric sensitivity analyses provide information about the effects of variations of the rock and fluid properties on the identification and extraction of borehole radar signals reflected from the invasion front. Our results suggest that by embedding the radar antennas in cavities filled with an absorbing dielectric material, it is possible to minimize the interference arising from the metal components of the logging tool. In the simulated reservoir scenario, a time-lapse measurement mode with a time interval of at least 6 h can reliably extract the radar signals reflected from the invasion front, and the proposed borehole radar has a lateral detection range from 0.15 to 1 m. A comprehensive range of parametric sensitivity analyses indicates that the signals reflected from the invasion front are principally influenced by oil viscosity, porosity, and mud and formation water salinity, as well as by molecular diffusion coefficient and cementation exponent. These properties and parameters should be carefully explored and assessed when applying borehole radar to evaluate mud invasion information in a reservoir environment. @en

In oil drilling, mud filtrate penetrates into porous formations and alters the compositions and properties of the pore fluids. This disturbs the logging signals and brings errors to reservoir evaluation. Drilling and logging engineers therefore deem mud invasion as undesired and attempt to eliminate its adverse effects. However, the mud-contaminated formation carries valuable information, notably with regard to its hydraulic properties. Typically, the invasion depth critically depends on the formation porosity and permeability. Therefore, if adequately characterized, mud invasion effects could be used for reservoir evaluation. To pursue this objective, we have applied borehole radar to measure mud invasion depth considering its high radial spatial resolution compared with conventional logging tools, which then allows us to estimate the reservoir permeability based on the acquired invasion depth. We investigate the feasibility of this strategy numerically through coupled electromagnetic and fluid modeling in an oil-bearing layer drilled using freshwater-based mud. Time-lapse logging is simulated to extract the signals reflected from the invasion front, and a dual-offset downhole antenna mode enables time-to-depth conversion to determine the invasion depth. Based on drilling, coring, and logging data, a quantitative interpretation chart is established, mapping the porosity, permeability, and initial water saturation into the invasion depth. The estimated permeability is in a good agreement with the actual formation permeability. Our results therefore suggest that borehole radar has significant potential to estimate permeability through mud invasion effects.@en

It is not practical to obtain a large number of labeled data to train a supervised learning network in tunnel lining nondestructive testing with ground-penetrating radar (GPR). To decrease the dependence of supervised learning on the number of labeled data, an improved self-supervised learning algorithm—self-attention dense contrastive learning (SA-DenseCL)—is proposed and incorporated with a mask region-convolution neural network (Mask R-CNN), which is trained by unlabeled and labeled GPR data. The proposed SA-DenseCL adds a self-attention-based relevant projection head to the DenseCL architecture of self-supervised learning, capturing the spatially continuing information between adjacent GPR traces. In the workflow, some unlabeled GPR images are used to pre-train the SA-DenseCL network for feature extraction and obtaining the backbone weights, which is superior to the conventional pre-training methods of supervised learning pre-trained by ImageNet images. The weights of the pre-trained backbone are then used to initialize the Mask R-CNN through transfer learning. Subsequently, a limited number of labeled GPR images are used to fine-tune the Mask R-CNN for automatically identifying the locations of the reinforcement bars and voids and estimating the secondary lining thickness. The experimental results show that the average precision reaches 96.70%, 81.04%, and 94.67% in identifying reinforcement bar locations, detecting void defects, and estimating secondary lining thickness, respectively, which outperform the conventional methods that use ImageNet-based supervised learning or GPR image-based DenseCL for initializing the Mask R-CNN backbone weights. It is observed that the improved self-supervised learning-based framework can improve the detection and estimation accuracy in GPR tunnel lining inspection.@en

This paper proposes a nondestructive evaluation method based on deep learning using combined ground-penetrating radar (GPR) and electromagnetic induction (EMI) data for autonomic and accurate estimation of the cover thickness and diameter of reinforcement bars. A real-time object detection algorithm—You Only Look Once–version 3 (YOLO v3)—is adopted to automatically identify the reinforcement bar reflected signals from radargrams, with which the range of the cover thickness is roughly predicted. Subsequently, EMI data, accompanied with the cover thickness range, are imported to a one-dimensional convolutional neural network (1D CNN), pretrained by calibrated EMI and GPR data, to simultaneously estimate the cover thickness and reinforcement bar diameter. Testing with the on-site GPR data shows that YOLO v3 is superior to Single Shot Multibox Detector method in GPR hyperbolic signal identification. Testing of 1D CNN with the EMI and GPR data collected in an in-house sand pit experiment shows that the estimation accuracy of the cover thickness and reinforcement bar diameter is, respectively, 96.8% and 90.3% with a permissible error of 1 mm. Further, an experiment with concrete specimens demonstrates that among the 22 estimated values (including the reinforcement bar diameter and cover thickness), there are 17 values accurately estimated, while the inaccurately estimated values have an error up to 2 mm. The experimental results show that the proposed method can autonomically evaluate the reinforcement bar diameter and cover thickness with a high accuracy.@en