A population-feedback control based algorithm for well trajectory optimization using proxy model

Wellbore instability is one of the concerns in the field of drilling engineering.This phenomenon is affected by several factors such as azimuth,inclination angle,in-situ stress,mud weight,and rock strength parameters.Among these factors,azimuth,inclination angle,and mud weight are controllable.The objective of this paper is to introduce a new procedure based on elastoplastic theory in wellbore stability solution to determine the optimum well trajectory and global minimum mud pressure required(GMMPR).Genetic algorithm(GA) was applied as a main optimization engine that employs proportional feedback controller to obtain the minimum mud pressure required(MMPR).The feedback function repeatedly calculated and updated the error between the simulated and set point of normalized yielded zone area(NYZA).To reduce computation expenses,an artificial neural network(ANN) was used as a proxy(surrogate model) to approximate the behavior of the actual wellbore model.The methodology was applied to a directional well in southwestern Iranian oilfield.The results demonstrated that the error between the predicted GMMPR and practical safe mud pressure was 4%for elastoplastic method,and 22%for conventional elastic solution.

Engineering costs proxy models for China rural access network and its application

The article builds three engineering rural access network models that describe the structure of network elements and their relative engineering parameters for cable access, synchronous code division multiple access（SCDMA）, and very small aperture terminal （VSAT） access technologies in the rural areas of China. Of the three access technologies, cable access and SCDMA access are the most popular access technologies. Besides, there still exist some remote special areas such as western mountain areas, whose natural environment is so bad that VSAT becomes the unique economical access way. Fully considering rural areas＇ geographical environments＇ impact, the article introduces geographical revised factor （GRF） to the models. By substituting the network data from the operators into the models, the article obtains the integrated networking values and does further researches on different access networks.

Applications of smart proxies for subsurface modeling

Using artificial intelligence(AI) and machine learning(ML) techniques, we developed and validated the smart proxy models for history matching of reservoir simulation, sensitivity analysis, and uncertainty assessment by artificial neural network(ANN). The smart proxy models were applied on two cases, the first case study investigated the application of a proxy model for calibrating a reservoir simulation model based on historical data and predicting well production while the second case study investigated the application of an ANN-based proxy model for fast-track modeling of CO2 enhanced oil recovery, aiming at the prediction of the reservoir pressure and phase saturation distribution at injection stage and post-injection stage. The prediction effects for both cases are promising. While a single run of basic numerical simulation model takes hours to days, the smart proxy model runs in a matter of seconds, saving 98.9% of calculating time. The results of these case studies demonstrate the advantage of the proposed workflow for addressing the high run-time, computational time and computational cost of numerical simulation models. In addition, these proxy models predict the outputs of reservoir simulation models with high accuracy.

基于水动力载荷混合数据集的高精度神经网络代理模型构建

In this work,we constructed a neural network proxy model(NNPM)to estimate the hydrodynamic resistance in the ship hull structure design process,which is based on the hydrodynamic load data obtained from both the potential flow method(PFM)and the viscous flow method(VFM).Here the PFM dataset is applied for the tuning,pre-training,and the VFM dataset is applied for the fine-training.By adopting the PFM and VFM datasets simultaneously,we aim to construct an NNPM to achieve the high-accuracy prediction on hydrodynamic load on ship hull structures exerted from the viscous flow,while ensuring a moderate data-acquiring workload.The high accuracy prediction on hydrodynamic loads and the relatively low dataset establishment cost of the NNPM developed demonstrated the effectiveness and feasibility of hybrid dataset based NNPM achieving a high precision prediction of hydrodynamic loads on ship hull structures.The successful construction of the high precision hydrodynamic prediction NNPM advances the artificial intelligence-assisted design(AIAD)technology for various marine structures.

Robust M-estimate of GJR Model with High Frequency Data

In this paper, we study the GJR scaling model which embeds the intraday return processes into the daily GJR model and propose a class of robust M-estimates for it. The estimation procedures would be more efficient when high-frequency data is taken into the model. However, high-frequency data brings noises and outliers which may lead to big bias of the estimators. Therefore, robust estimates should be taken into consideration. Asymptotic results are derived from the robust M-estimates without the finite fourth moment of the innovations. A simulation study is carried out to assess the performance of the model and its estimates.Robust M-estimate of GJR model is also applied in predicting Va R for real financial time series.

Fractured reservoir history matching improved based on artificial intelligent

In this paper,a new robust approach based on Least Square Support Vector Machine(LSSVM)as a proxy model is used for an automatic fractured reservoir history matching.The proxy model is made to model the history match objective function(mismatch values)based on the history data of the field.This model is then used to minimize the objective function through Particle Swarm Optimization(PSO)and Imperialist Competitive Algorithm(ICA).In automatic history matching,sensitive analysis is often performed on full simulation model.In this work,to get new range of the uncertain parameters(matching parameters)in which the objective function has a minimum value,sensitivity analysis is also performed on the proxy model.By applying the modified ranges to the optimization methods,optimization of the objective function will be faster and outputs of the optimization methods(matching parameters)are produced in less time and with high precision.This procedure leads to matching of history of the field in which a set of reservoir parameters is used.The final sets of parameters are then applied for the full simulation model to validate the technique.The obtained results show that the present procedure in this work is effective for history matching process due to its robust dependability and fast convergence speed.Due to high speed and need for small data sets,LSSVM is the best tool to build a proxy model.Also the comparison of PSO and ICA shows that PSO is less time-consuming and more effective.