Evaluation of hydraulic fracturing of horizontal wells in tight reservoirs based on the deep neural network with physical constraints

Accurate diagnosis of fracture geometry and conductivity is of great challenge due to the complex morphology of volumetric fracture network. In this study, a DNN (deep neural network) model was proposed to predict fracture parameters for the evaluation of the fracturing effects. Field experience and the law of fracture volume conservation were incorporated as physical constraints to improve the prediction accuracy due to small amount of data. A combined neural network was adopted to input both static geological and dynamic fracturing data. The structure of the DNN was optimized and the model was validated through k-fold cross-validation. Results indicate that this DNN model is capable of predicting the fracture parameters accurately with a low relative error of under 10% and good generalization ability. The adoptions of the combined neural network, physical constraints, and k-fold cross-validation improve the model performance. Specifically, the root-mean-square error (RMSE) of the model decreases by 71.9% and 56% respectively with the combined neural network as the input model and the consideration of physical constraints. The mean square error (MRE) of fracture parameters reduces by 75% because the k-fold cross-validation improves the rationality of data set dividing. The model based on the DNN with physical constraints proposed in this study provides foundations for the optimization of fracturing design and improves the efficiency of fracture diagnosis in tight oil and gas reservoirs.

Numerical simulation and dimension reduction analysis of electromagnetic logging while drilling of horizontal wells in complex structures

Electromagnetic logging while drilling(LWD)is one of the key technologies of the geosteering and formation evaluation for high-angle and horizontal wells.In this paper,we solve the dipole source-generated magnetic/electric fields in 2D formations efficiently by the 2.5D finite diff erence method.Particularly,by leveraging the field’s rapid attenuation in spectral domain,we propose truncated Gauss–Hermite quadrature,which is several tens of times faster than traditional inverse fast Fourier transform.By applying the algorithm to the LWD modeling under complex formations,e.g.,folds,fault and sandstone pinch-outs,we analyze the feasibility of the dimension reduction from 2D to 1D.For the formations with smooth lateral changes,like folds,the simplified 1D model’s results agree well with the true responses,which indicate that the 1D simplification with sliding window is feasible.However,for the formation structures with drastic rock properties changes and sharp boundaries,for instance,faults and sandstone pinch-outs,the simplified 1D model will lead to large errors and,therefore,2.5D algorithms should be applied to ensure the accuracy.

Annual Output of Five Horizontal Wells Reaches One Million Tons

ＡｎｎｕａｌＯｕｔｐｕｔｏｆＦｉｖｅＨｏｒｉｚｏｎｔａｌＷｅｌｌｓＲｅａｃｈｅｓＯｎｅＭｉｌｌｉｏｎＴｏｎｓ￥／／ＯｎＭａｒｃｈ３，１９９６，ｔｈｅｈｏｒｉｚｏｎｔａｌｗｅｌｌＮｏ．４，ＴａｚｈｏｎｇＮｏ．４ｏｉｌｆｉｅｌｄｐｒｏｄｕｃｅｄ１１９２ｔ...

Study on temperature distribution along wellbore of fracturing horizontal wells in oil reservoir

The application of distributed temperature sensors(DTS)to monitor producing zones of horizontal well through a real-time measurement of a temperature profile is becoming increasingly popular.Those parameters,such as flow rate along wellbore,well completion method,skin factor,are potentially related to the information from DTS.Based on mass-,momentum-,and energy-balance equations,this paper established a coupled model to study on temperature distribution along wellbore of fracturing horizontal wells by considering skin factor in order to predict wellbore temperature distribution and analyze the factors influencing the wellbore temperature profile.The models presented in this paper account for heat convective,fluid expansion,heat conduction,and viscous dissipative heating.Arriving temperature and wellbore temperature curves are plotted by computer iterative calculation.The non-perforated and perforated sections show different temperature distribution along wellbore.Through the study on the sensitivity analysis of skin factor and flow rate,we come to the conclusion that the higher skin factor generates larger temperature increase near the wellbore,besides,temperature along wellbore is related to both skin factors and flow rate.Temperature response type curves show that the larger skin factor we set,the less temperature augmenter from toe to heel could be.In addition,larger flow rate may generate higher wellbore temperature.

Investigation of low water recovery based on gas-water two-phase low-velocity Non-Darcy flow model for hydraulically fractured horizontal wells in shale

Various mechanisms are employed to interpret the low water recovery during the shale-gas production period,such as extra-trapped water in the fracture network,water imbibition due to osmotic pressure and capillary pressure.These lead to the difficulty of water flow,which could be described by lowvelocity non-Darcy's law known as threshold pressure gradient(TPG).In this paper we firstly employ the low-velocity non-Darcy's law to describe the water flow and use Darcy flow accounting for slip flow and free molecular flow mechanisms to model gas flow in the shale formation.The sensitive study using numerical simulation shows that the proposed flow model could model the low fracturing liquid recovery and that large pseudo TPG leads to lower fracturing liquid recovery.Thus,the proposed model would give new insight to model the low water recovery in shale formations.

Selection of candidate wells for re-fracturing in tight gas sand reservoirs using fuzzy inference

An artificial-intelligence based decision-making protocol is developed for tight gas sands to identify re-fracturing wells and used in case studies. The methodology is based on fuzzy logic to deal with imprecision and subjectivity through mathematical representations of linguistic vagueness, and is a computing system based on the concepts of fuzzy set theory, fuzzy if-then rules, and fuzzy reasoning. Five indexes are used to characterize hydraulic fracture quality, reservoir characteristics, operational parameters, initial conditions, and production related to the selection of re-fracturing well, and each index includes 3 related parameters. The value of each index/parameter is grouped into three categories that are low, medium, and high. For each category, a trapezoidal membership function all related rules are defined. The related parameters of an index are input into the rule-based fuzzy-inference system to output value of the index. Another fuzzy-inference system is built with the reservoir index, operational index, initial condition index and production index as input parameters and re-fracturing potential index as output parameter to screen out re-fracturing wells. This approach was successfully validated using published data.

A new approach for flow simulation in complex hydraulic fracture morphology and its application:Fracture connection element method

Efficient flow simulation and optimization methods of hydraulic fracture morphology in unconventional reservoirs are effective ways to enhance oil/gas recovery.Based on the connection element method(CEM)and distribution of stimulated reservoir volume,the complex hydraulic fracture morphology was accurately described using heterogeneous node connection system.Then a new fracture connection element method(FCEM)for fluid flow in stimulated unconventional reservoirs with complex hydraulic fracture morphology was proposed.In the proposed FCEM,the arrangement of dense nodes in the stimulated area and sparse nodes in the unstimulated area ensures the calculation accuracy and efficiency.The key parameter,transmissibility,was also modified according to the strong heterogeneity of stimulated reservoirs.The finite difference and semi-analytical tracking were used to accurately solve the pressure and saturation distribution between nodes.The FCEM is validated by comparing with traditional numerical simulation method,and the results show that the bottom hole pressure simulated by the FCEM is consistent with the results from traditional numerical simulation method,and the matching rate is larger than 95%.The proposed FCEM was also used in the optimization of fracturing parameters by coupling the hydraulic fracture propagation method and intelligent optimization algorithm.The integrated intelligent optimization approach for multi-parameters,such as perforation number,perforation location,and displacement in hydraulic fracturing is proposed.The proposed approach was applied in a shale gas reservoir,and the result shows that the optimized perforation location and morphology distribution are related to the distribution of porosity/permeability.When the perforation location and displacement are optimized with the same fracture number,NPV increases by 70.58%,which greatly improves the economic benefits of unconventional reservoirs.This work provides a new way for flow simulation and optimization of hydraulic fracture morphology of multi-fractured horizontal wells in unconventional reservoirs.

Development and Application of a Production Data Analysis Model for a Shale Gas Production Well

This paper presents the development and application of a production data analysis software that can analyze and forecast the production performance and reservoir properties of shale gas wells.The theories used in the study were based on the analytical and empirical approaches.Its reliability has been confirmed through comparisons with a commercial software.Using transient data relating to multi-stage hydraulic fractured horizontal wells,it was confirmed that the accuracy of the modified hyperbolic method showed an error of approximately 4%compared to the actual estimated ultimate recovery(EUR).On the basis of the developed model,reliable productivity forecasts have been obtained by analyzing field production data relating to wells in Canada.The EUR was computed as 9.6 Bcf using the modified hyperbolic method.Employing the Pow Law Exponential method,the EUR would be 9.4 Bcf.The models developed in this study will allow in the future integration of new analytical and empirical theories in a relatively readily than commercial models.

Productivity comparison of radial lateral wells and horizontal snake wells applied to marine gas hydrate reservoir development

Development of marine gas hydrate resources presents a huge challenge to the energy industry owing to the well production complications such as wellbore collapse,sand production,and low productivity.Radial lateral wells(RLW)and horizontal snake wells(HSW)have been proposed separately to mitigate these complications.We compare the productivity potentials of these two types of wells using the recently developed analytical models and field case data from a gas hydrate reservoir in the South China Sea.It is concluded that RLW will yield slightly higher gas productivity than HSW under similar conditions.Sensitivity analysis with the well models indicates that the productivity of RLW is directly proportional to the number of laterals,length of laterals,and radius of laterals,while the productivity of HSW is directly proportional to the length and radius of the horizontal wellbore.The decision of using RLW or HSW can be made based on economic analysis of well completion and production,which should be addressed in future studies.