Search Results (8)

Accurate pre-drilling mud weight window (MWW) prediction is crucial for drilling fluid design and wellbore stability in complex geological formations. Traditional physics-based approaches suffer from subjective parameter selection and inadequate handling of multi-mechanism over-pressured formations, while machine learning methods lack physical constraints and interpretability. This study develops a novel physics-guided deep learning framework integrating rock mechanics theory with deep neural networks for enhanced MWW prediction. The framework incorporates three key components: first, a physics-driven layer synthesizing intermediate variables from rock physics calculations to embed domain knowledge while preserving interpretability; second, a geological sequence-matching algorithm enabling precise stratigraphic correlation between offset and target wells, compensating for lateral geological heterogeneity; third, a long short-term memory network capturing sequential drilling characteristics and geological structure continuity. Case study results from 12 wells in northwestern China demonstrate significant improvements over traditional methods: collapse pressure prediction error reduced by 40.96%, pore pressure error decreased by 30.43%, and fracture pressure error diminished by 39.02%. The proposed method successfully captures meter-scale pressure variations undetectable by conventional approaches, providing critical technical support for wellbore design optimization, drilling fluid formulation, and operational safety enhancement in challenging geological environments. Full article

This study examines the distribution of pore pressure (PP) and fracture gradient (FG) within intervals of lost circulation encountered during drilling operations in the Ordovician reservoir (IV-3 unit) of the Tin Fouye Tabankort (TFT) field, located in the Illizi Basin, Algeria. The research further aims to determine an optimized drilling mud weight to mitigate mud losses and enhance overall operational efficiency. PP and FG models for the Ordovician reservoir were developed based on data collected from five vertical development wells. The analysis incorporated multiple datasets, including well logs, mud logging reports, downhole measurements, and Leak-Off Tests (LOTs). The findings revealed an average overburden gradient of 1.03 psi/ft for the TFT field. The generated pore pressure and fracture gradient (PPFG) models indicated a sub-normal pressure regime in the Ordovician sandstone IV-3 reservoir, with PP values ranging from 5.61 to 6.24 ppg and FG values between 7.40 and 9.14 ppg. The analysis identified reservoir depletion due to prolonged hydrocarbon production as the primary factor contributing to the reduction in fracture gradient, which significantly narrowed the mud weight window and increased the likelihood of lost circulation. Further examination of pump on/off cycles over time, coupled with shallow and deep resistivity variations with depth, confirmed that the observed mud losses were predominantly associated with induced fractures resulting from the application of excessive mud weight during drilling operations. Based on the established PP and FG profiles, a narrow mud weight window of 6.24–7.40 ppg was recommended to ensure the safe and efficient drilling of future wells in the TFT field and support the sustainability of drilling operations in the context of a depleted reservoir. Full article

The aim of this study was to propose the workflow for integrated analysis of the 3D geostress and 1D geomechanics of an exploration in a new gas field. This integrated analysis will allow for problems associated with the inaccuracy of 1D geomechanical analysis to be overcome in a region with obvious anticline/syncline structures. The 1D geomechanical analysis of the well in the exploration of a new gas field mainly included the prediction of pore pressure and calculation of the mud weight window for safe drilling. In general, this integrated workflow included both a method for pore pressure prediction and a method for the calculation of the mud weight window, with the numerical solution of 3D geostress plus the interval velocity of formations. The procedure for the calculation of the 3D geostress of a target block was also introduced. Numerical solution of the 3D geostress of the target gas field, as well as solutions of 1D geomechanical analysis, have demonstrated the efficiency and practical use of the proposed theory in the successful drilling of the LT-1 well in the Junggar Basin, Xinjiang, China. For this LT-1 well in the target TS block, there was no logging data to refer to when predicting the pore pressure of undrilled formations. Only 3D geostress could be used to calculate the mud weight window. Influences of anticline structures were considered in the calculation of 3D geostress. Since the accuracy of the numerical solution of 3D geostress is higher than the accuracy of the 1D geostress solution for a single well analysis, the results of pore pressure and the mud weight window are more accurate than those obtained with conventional 1D geostress analysis. Details of the finite element modeling of the 3D geostress field of the TS block is presented along with the solution of the 3D geostress field. With the data of the interval velocity of formations and 3D geostress solution of the TS block, pore pressure prediction was carried out for the 7000 m-deep pilot LT-1 well. Finally, calculations were performed for the values of the mud weight window of the LT-1 well. Full article

Severe wellbore stability issues were reported while drilling in laminated formation with weak planes such as beddings. To accurately determine the safe mud weight according to the changing environment is of primary importance for safety control of drilling. Considering both the elastic and strength anisotropy of bedding formation, a novel theoretical model is established and the stress and failure around wellbores are analyzed. The accuracy and applicability of the theoretical model is verified by in situ field data. For the purpose of fulfilling real-time prediction, the method flowchart of programming is also provided. The results show that the model built can be conveniently used to predict the stress distribution, failure area, and collapse and fracture pressure while drilling, and rather good predictions can be made compared to real field data. In addition, the inhomogeneity of in situ stress and elastic parameters affect the upper limit of the safe mud weight window (SMWW) greater than the lower limit. Negative SMWW may appear with the direction change of the wellbore or weak plane, especially when the azimuths of them change. As to the magnitude of SMWW, the anisotropic effects of Young’s modulus are greater than the Poisson’s ratio. The method established in this paper can greatly help with the precise prediction of wellbore stability as drilling proceeds in bedding formation. Full article

For a safe drilling operation with the of minimum borehole instability challenges, building a mechanical earth model (MEM) has proven to be extremely valuable. However, the natural complexity of reservoirs along with the lack of reliable information leads to a poor prediction of geomechanical parameters. Shear wave velocity has many applications, such as in petrophysical and geophysical as well as geomechanical studies. However, occasionally, wells lack shear wave velocity (especially in old wells), and estimating this parameter using other well logs is the optimum solution. Generally, available empirical relationships are being used, while they can only describe similar formations and their validation needs calibration. In this study, machine learning approaches for shear sonic log prediction were used. The results were then compared with each other and the empirical Greenberg–Castagna method. Results showed that the artificial neural network has the highest accuracy of the predictions over the single and multiple linear regression models. This improvement is more highlighted in hydrocarbon-bearing intervals, which is considered as a limitation of the empirical or any linear method. In the next step, rock elastic properties and in-situ stresses were calculated. Afterwards, in-situ stresses were predicted and coupled with a failure criterion to yield safe mud weight windows for wells in the field. Predicted drilling events matched quite well with the observed drilling reports. Full article

This study presents a new interface for wellbore stability analysis, which visualizes and quantifies the stress condition around a wellbore at shear and tensile failure. In the first part of this study, the Mohr–Coulomb, Mogi–Coulomb, modified Lade and Drucker–Prager shear failure criteria, and a tensile failure criterion, are applied to compare the differences in the critical wellbore pressure for three basin types with Andersonian stress states. Using traditional wellbore stability window plots, the Mohr–Coulomb criterion consistently gives the narrowest safe mud weight window, while the Drucker–Prager criterion yields the widest window. In the second part of this study, a new type of plot is introduced where the safe drilling window specifies the local magnitude and trajectories of the principal deviatoric stresses for the shear and tensile wellbore failure bounds, as determined by dimensionless variables, the Frac number ( $F$ ) and the Bi-axial Stress scalar ( $\chi$ ), in combination with failure criteria. The influence of both stress and fracture cages increases with the magnitude of the $F$ values, but reduces with depth. The extensional basin case is more prone to potential wellbore instability induced by circumferential fracture propagation, because fracture cages persists at greater depths than for the compressional and strike-slip basin cases. Full article

Due to the uncertainty of formation properties and improper wellbore stability analysis methods, the input parameters are often uncertain and the required mud weight to prevent wellbore collapse is too large, which might cause an incorrect result. However, the uncertainty evaluation of input parameters and their influence on safe mud weight window (SMWW) is seldom investigated. Therefore, the present paper aims to propose an uncertain evaluation method to evaluate the uncertainty of SMWW. The reliability assessment theory was introduced, and the uncertain SMWW model was proposed by involving the tolerable breakout, the Mogi-Coulomb (MG-C) criterion and the reliability assessment theory. The influence of uncertain parameters on wellbore collapse, wellbore fracture and SMWW were systematically simulated and investigated by utilizing Monte Carlo simulation. Finally, the field observation of well SC-101X was reported and discussed. The results indicated that the MG-C criterion and tolerable breakout is recommended for wellbore stability analysis. The higher the coefficient of variance is, the higher the level of uncertainty is, the larger the impact on SMWW will be, and the higher the risk of well kick, wellbore collapse and fracture will be. The uncertainty of basic parameters has a very significant impact on SMWW, and it cannot be ignored. For well SC-101X, the SMWW predicted by analytical solution is 0.9921–1.6020 g/cm³, compared to the SMWW estimated by the reliability assessment method, the reliability assessment method tends to give a very narrow SMWW of 1.0756–1.0935 g/cm³ and its probability is only 80%, and the field observation for well kick and wellbore fracture verified the analysis results. For narrow SMWW formation drilling, some kinds of advanced technology, such as the underbalanced drilling (UBD), managed pressure drilling (MPD), micro-flow drilling (MFD) and wider the SMWW, can be utilized to maintain drilling safety. Full article

In depleted offshore reservoirs, pore pressure declines and consequently horizontal in-situ stresses decrease as well. This causes a very limited well depth for extended-reach drilling targeting to offshore depleted reservoirs. In this paper, based on analyzing the safe mud weight window of the depleted offshore reservoirs, a model of predicting the Maximum Allowable Measured Depth (MAMD) for extended-reach drilling targeting to offshore depleted reservoirs is developed. Meanwhile, the numerical method of the model is proposed, and the key affecting factors of the MAMD are also investigated. The results show the pore pressure depletion has obvious effects on the MAMD. With the depletion of pore pressure, the safe mud weight window appears narrower and even disappears, consequently the predicted MAMD becomes shorter. For a normal regime depositional environment in the depleted reservoirs, it may be impossible to drill with conventional drilling method in the nearby directions of the maximum horizontal in-situ stress, while it may be much safer and attain a long MAMD when drilling in the directions near the minimum horizontal in-situ stress. Moreover, the MAMD will decrease with the increase of Poisson’s ratio and Biot’s parameter, and its response to Poisson’s ratio is more obvious. For a specific target depleted reservoir, the extended-reach drilling with a high borehole inclination may have a longer MAMD than that with a low borehole inclination. This paper presents a method for promoting the design of extended-reach drilling targeting to offshore depleted reservoirs. Full article