Interpretation and characterization of rate of penetration intelligent prediction model

Accurate prediction of the rate of penetration(ROP)is significant for drilling optimization.While the intelligent ROP prediction model based on fully connected neural networks(FNN)outperforms traditional ROP equations and machine learning algorithms,its lack of interpretability undermines its credibility.This study proposes a novel interpretation and characterization method for the FNN ROP prediction model using the Rectified Linear Unit(ReLU)activation function.By leveraging the derivative of the ReLU function,the FNN function calculation process is transformed into vector operations.The FNN model is linearly characterized through further simplification,enabling its interpretation and analysis.The proposed method is applied in ROP prediction scenarios using drilling data from three vertical wells in the Tarim Oilfield.The results demonstrate that the FNN ROP prediction model with ReLU as the activation function performs exceptionally well.The relative activation frequency curve of hidden layer neurons aids in analyzing the overfitting of the FNN ROP model and determining drilling data similarity.In the well sections with similar drilling data,averaging the weight parameters enables linear characterization of the FNN ROP prediction model,leading to the establishment of a corresponding linear representation equation.Furthermore,the quantitative analysis of each feature's influence on ROP facilitates the proposal of drilling parameter optimization schemes for the current well section.The established linear characterization equation exhibits high precision,strong stability,and adaptability through the application and validation across multiple well sections.

Hybrid ensemble soft computing approach for predicting penetration rate of tunnel boring machine in a rock environment

This study implements a hybrid ensemble machine learning method for forecasting the rate of penetration(ROP) of tunnel boring machine(TBM),which is becoming a prerequisite for reliable cost assessment and project scheduling in tunnelling and underground projects in a rock environment.For this purpose,a sum of 185 datasets was collected from the literature and used to predict the ROP of TBM.Initially,the main dataset was utilised to construct and validate four conventional soft computing(CSC)models,i.e.minimax probability machine regression,relevance vector machine,extreme learning machine,and functional network.Consequently,the estimated outputs of CSC models were united and trained using an artificial neural network(ANN) to construct a hybrid ensemble model(HENSM).The outcomes of the proposed HENSM are superior to other CSC models employed in this study.Based on the experimental results(training RMSE=0.0283 and testing RMSE=0.0418),the newly proposed HENSM is potential to assist engineers in predicting ROP of TBM in the design phase of tunnelling and underground projects.

Comparison of accuracy and computational performance between the machine learning algorithms for rate of penetration in directional drilling well

Oil and gas reservoirs are of the main assets of countries possessing them.Production from these reservoirs is one of the main concerns of engineers,which can be achieved by drilling oil and gas reservoirs.Construction of hydrocarbon wells is one of the most expensive operations in the oil industry.One of the most important parameters affecting drilling cost is the rate of penetration(ROP).This paper predicts the rate of penetration using artificial intelligence and hybrid models on Kaboud oil field well#7 in the directional stage.In this study,different models were constructed through various approaches based on 1878 dataset obtained from drilling operation in the well#7.Then,the accuracy of the constructed models was compared with each other.It was found that the MLP-ABC algorithm predicts the rate of penetration more accurately,by far,as compared with other methods.The MLP-ABC algorithm achieves impressive ROP prediction accuracy(RMSE=0.007211 m/h;AAPD=0.1871%;R^(2)=1.000 for the testing subset).Consequently,it can be concluded that this method is applicable to predict the drilling rate in that oilfield.

Applications and theoretical perspectives of artificial intelligence in the rate of penetration

Artificial Intelligence(AI)is becoming popular for the Rate of Penetration(ROP)estimation,hence,the need to study the best techniques and their advantages over empirical models.Various literatures were analysed to determine the prevalence of AI in ROP computation and compare the computation accuracies with empirical models.Artificial Neural Network(ANN)accounted for over 92%of the AI techniques used for ROP computation and Weight on Bit(WOB)mostly influenced the computation accuracy.The accuracy of AI algorithms is better than the empirical models thus,will improve the drilling efficiency,reduce cost and enhance the development of pad wells.

Discussion of reasonable drilling parameters in impregnated diamond bit drilling

The impregnated diamond(ID)bit drilling is one of the main rotary drilling methods in hard rock drilling and it is widely used in mineral exploration,oil and gas exploration,mining,and construction industries.In this study,the quadratic polynomial model in ID bit drilling process was proposed as a function of controllable mechanical operating parameters,such as weight on bit(WOB)and revolutions per minute(RPM).Also,artificial neural networks(ANN)model for predicting the rate of penetration(ROP)was developed using datasets acquired during the drilling operation.The relationships among mechanical operating parameters(WOB and RPM)and ROP in ID bit drilling were analyzed using estimated quadratic polynomial model and trained ANN model.The results show that ROP has an exponential relationship with WOB,whereas ROP has linear relationship with RPM.Finally,the optimal regime of mechanical drilling parameters to achieve high ROP was confirmed using proposed model in combination with rock breaking principal.

Multi-objective optimization of oil well drilling using elitist non-dominated sorting genetic algorithm

A multi-objective optimization of oil well drilling has been carried out using a binary coded elitist non-dominated sorting genetic algorithm.A Louisiana offshore field with abnormal formation pressure is considered for optimization.Several multi-objective optimization problems involving twoand three-objective functions were formulated and solved to fix optimal drilling variables.The important objectives are：（i） maximizing drilling depth,（ii） minimizing drilling time and （iii） minimizing drilling cost with fractional drill bit tooth wear as a constraint.Important time dependent decision variables are：（i） equivalent circulation mud density,（ii） drill bit rotation,（iii） weight on bit and （iv） Reynolds number function of circulating mud through drill bit nozzles.A set of non-dominated optimal Pareto frontier is obtained for the two-objective optimization problem whereas a non-dominated optimal Pareto surface is obtained for the three-objective optimization problem.Depending on the trade-offs involved,decision makers may select any point from the optimal Pareto frontier or optimal Pareto surface and hence corresponding values of the decision variables that may be selected for optimal drilling operation.For minimizing drilling time and drilling cost,the optimum values of the decision variables are needed to be kept at the higher values whereas the optimum values of decision variables are at the lower values for the maximization of drilling depth.

Experimental study of rock-breaking with an offset single cone bit

An experimental study of rock-breaking with an offset single cone bit was completed on the bit bench test equipment. Data such as transmission ratio, weight on bit （WOB）, rate of penetration （ROP） and torque on bit were acquired in the experiments. Based on analyzing the experimental results, several conclusions were drawn as follows. The transmission ratio of the offset single-cone bit changed slightly with rotary speed of bit, weight on bit and offset distance. The rate of penetration of the offset singlecone bit increased with increase of WOB and off＇set distance. The torque on bit increased with increase of offset distance under the same WOB and bit rotary speed, decreased with increase of bit rotary speed under the same WOB. The rock-breaking mechanism of the offset single-cone bit was a scraping action. This indicates that the offset single-cone bit is a chipping type bit.

Properties and testing of a hydraulic pulse jet and its application in offshore drilling

Offshore drilling has attracted more attention than ever before due to the increasing worldwide energy demand especially in China. High cost, long drilling cycles, and low rate of penetration （ROP） represent critical challenges for offshore drilling operations. The hydraulic pulse generator was specifically designed, based on China offshore drilling technologies and parameters, to overcome problems encountered during offshore drilling. Both laboratory and field tests were conducted to collect the characteristics of the hydraulic pulse generator. The relationships between flow rate and pressure amplitude, pressure loss and pulse frequency were obtained, which can be used to optimize operation parameters for hydraulic pulse jet drilling. Meanwhile a bottom hole assembly （BHA） for pulse jet drilling has been designed, combining the hydraulic pulse generator with the conventional BHA, positive displacement motor, and rotary steerable system （RSS） etc. Furthermore, the hydraulic pulse jet technique has been successfully applied in more than 10 offshore wells in China. The depth of the applied wells ranged from 2,000 m to 4,100 m with drilling bit diameters of 311 mm and 216 mm. The field application results showed that hydraulic pulse jet technique was feasible for various bit types and formations, and that ROP could be significantly increased, by more than 25%.

Numerical and experimental investigation on the depressurization capacity of a new type of depressure-dominated jet mill bit

Efficient cuttings transport and improving rate of penetration(ROP)are two major challenges in horizontal drilling and extended reach drilling.A type of jet mill bit(JMB)may provide an opportunity to catch the two birds with one stone:not only enhancing cuttings transport efficiency but also improving ROP by depressuring at the bottom hole.In this paper,the JMB is further improved and a new type of depressure-dominated JMB is presented;meanwhile,the depressurization capacity of the depressure-dominated JMB is investigated by numerical simulation and experiment.The numerical study shows that low flow-rate ratio helps to enhance the depressurization capacity of the depressure-dominated JMB;for both depressurization and bottom hole cleaning concern,the flow-rate ratio is suggested to be set at approximately 1:1.With all other parameter values being constant,lower dimensionless nozzle-to-throat-area ratio may result in higher depressurization capacity and better bottom hole cleaning,and the optimal dimensionless nozzle-to-throat-area ratio is at approximately0.15.Experiments also indicate that reducing the dimensionless flow-rate ratio may help to increase the depressurization capacity of the depressure-dominated JMB.This work provides drilling engineers with a promising tool to improve ROP.

Investigations into the coiled tubing partial underbalanced drilling (CT-PUBD)technique for drilling hard formations

To improve the rate of penetration(ROP) in drilling deep and hard formations, this paper proposes a new drilling method called coiled tubing partial underbalanced drilling(CT-PUBD). As a preliminary investigation into the new drilling method, this paper presents predictions of hole cleaning efficiency, drilling speed, cuttings migration and pressure loss in the drilling process with CT-PUBD. Based on numerical simulation and full-scale experimental studies, we conclude that using CT-PUBD, an underbalanced drilling condition can be achieved near the bit while maintaining wellbore safety at the same time. This condition can be achieved using a cuttings discharge device, a rotary packer and a backflow controller.According to the numerical simulations performed in this study, CT-PUBD can achieve high efficiency of hole cleaning.Along the cuttings migration process, the fluid velocities can reach the maximum values in the backflow holes. A full-scale laboratory experimental system was used to test the hydraulic characteristics and obtain the drilling performance of the new technology. The result shows that CT-PUBD significantly improves the ROP compared to the conventional drilling method.

DRILLING CHARACTERISTICS OF COMBINATIONS OF DIFFERENT HIGH PRESSURE JET NOZZLES

The high speed fluid jet for directly or indirectly breaking rock is one of the most effective ways to improve the deep penetration rate. In order to maximize the efficiency of energy use, the flow characteristics of different combinations of high pressure jet nozzles are analyzed through numerical simulations. According to the velocity vectors at the bottom and the bottom hole pressure diagram, the effects of the high pressure nozzle combinations on the flow structure and the penetration rate are analyzed. It is shown that the combination of three vertical edge nozzles is very efficient, but inefficient in cleaning the bottom hole and eroding the wall. The jet velocity is 400 m/s and the radius is 5 mm, with a center nozzle added, the problem can be solved, but the high-pressure fluid displacement would increase. The center nozzle＇s jet velocity is 200 m/s and the radius is 8 ram, the combination of two vertical edge nozzles and a center tilt nozzle or that of a vertical edge nozzle and a center tilt nozzle would provide a flow structure favorable for drilling. The angle of inclination is 10°. To take advantage of high pressure jet energy to improve the efficiency of drilling, it is important to select a suitable nozzle combination according real conditions.

Confined compressive strength model of rock for drilling optimization

The confined compressive strength(CCS)plays a vital role in drilling optimization.On the basis of Jizba's experimental results,a new CCS model considering the effects of the porosity and nonlinear characteristics with increasing confining pressure has been developed.Because the confining pressure plays a fundamental role in determining the CCS of bottom-hole rock and because the theory of Terzaghi's effective stress principle is founded upon soil mechanics,which is not suitable for calculating the confining pressure in rock mechanics,the double effective stress theory,which treats the porosity as a weighting factor of the formation pore pressure,is adopted in this study.The new CCS model combined with the mechanical specific energy equation is employed to optimize the drilling parameters in two practical wells located in Sichuan basin,China,and the calculated results show that they can be used to identify the inefficient drilling situations of underbalanced drilling(UBD)and overbalanced drilling(OBD).