A novel stacking-based ensemble learning model for drilling efficiency prediction in earth-rock excavation

Accurate prediction of drilling efficiency is critical for developing the earth-rock excavation schedule.The single machine learning(ML)prediction models usually suffer from problems including parameter sensitivity and overfitting.In addition,the influence of environmental and operational factors is often ignored.In response,a novel stacking-based ensemble learning method taking into account the combined effects of those factors is proposed.Through multiple comparison tests,four models,e Xtreme gradient boosting(XGBoost),random forest(RF),back propagation neural network(BPNN)as the base learners,and support vector regression(SVR)as the meta-learner,are selected for stacking.Furthermore,an improved cuckoo search optimization(ICSO)algorithm is developed for hyper-parameter optimization of the ensemble model.The application to a real-world project demonstrates that the proposed method outperforms the popular single ML method XGBoost and the ensemble model optimized by particle swarm optimization(PSO),with 16.43%and 4.88%improvements of mean absolute percentage error(MAPE),respectively.

Improving TC drill bit's efficiency and resistance to wear by graphene coating

Displaying a two-dimensional pure crystal carbon structure,Graphene is the strongest,yet thinnest substance discovered by scientists.Coating tungsten carbide(TC)drill bits with graphene to evaluate the effect of graphene on the wear,as well as the rate of penetration of the drilling bit was examined in this research.Two evaluation approaches were employed:one with employing ANSYS Software and the second by employing atomic pressure chemical vapor deposition(APCVD synthesis)in the laboratory to produce a monolayer graphene coating.The simultaneous software-based and lab-based testing were performed to increase the credibility of the results and minimize the potential errors.Conducting the simulation using ANSYS,the maximum shear elastic strain,equivalent elastic strain,equivalent(von mises)stress,total deformation and maximum shear stress were investigated prior and after the gra-phene coating was applied on TC simulated bit.Total deformation was only slightly increased,while the maximum shear elastic strain was almost doubled,reflecting that the bit's wear was significantly reduced after the coating.Lab-based APCVD synthesis results showed 34%increase in compressive strength of the coated bit,in comparison to the uncoated one.The failure occurred for uncoated bit at 35 MPa,where the coated bit experienced failure at 46.9 MPa.The Von Mises stress test conducted on the coated and uncoated samples also indicated that this stress was 41%less for the coated bit,in comparison to the uncoated one.Finally,two small-scale drilling operations,one using a 1inch graphene-coated TC bit and the other using a 1inch non-coated TC bit,were performed on a granite block,to evaluate the performance of the graphene-coated bit in practice.In a chosen 120-min time frame,27 consecutive holes could be drilled by the graphene-coated TC bit,while 19 consecutive holes could be drilled by the uncoated TC bit,in identical drilling conditions.This implies a 42%increase in ROP.