Genetic Expression Programming Model Research Articles

Modeling and analysis of hydraulic fracture complexity index in sandy conglomerate reservoirs based on genetic expression programming—A case study in Xinjiang Oilfield

The stimulation effect of oil wells is seriously affected by the complexity of hydraulic fractures, and the analysis of the factors that control the fracture complexity index has become the key to fracturing design in sandy conglomerate reservoirs. Based on the intrinsic relationship between geological engineering parameters and the fractures complexity index, a Genetic Expression Programming (GEP) method, which has broad advantages in solving multi-factor nonlinear fitting and black-box prediction problems, is proposed to analyze the hydraulic fracture complexity index. Combined with the geoengineering factors that affect the hydraulic fractures propagation, a comprehensive index calculation method is established to analyze the relative importance of these features and 18 reconstructed features were obtained by collecting the geoengineering parameter data of 118 fracturing sections in 8 fracturing wells in Jinlong oilfield. The principal component analysis was performed to eliminate the interaction between the features, and then a GEP-based fractures complexity index calculation model was developed. The partial dependence plot is used to analyze the influence of the main control feature (variable) on the hydraulic fracture complexity index. It showed that GEP model can achieve satisfactory performance (Training set: R = 0.861; Test set: R = 0.817) by statistical parameters. The results showed that the model can calculate the hydraulic fracture complexity index quickly and precisely. The influence of geological engineering control factors can be obtained. It proved that the GEP method can effectively analyze and evaluate the complexity in sandy conglomerate reservoirs.

Shale gas load recovery modeling and analysis after hydraulic fracturing based on genetic expression programming: A case study of southern Sichuan Basin shale

For shale gas reservoir, fracture network fracturing in horizontal well is the key technology to guarantee its commercial exploitation, and the load recovery is a critical parameter which determines the post-fracturing performance. It has been reported that there is a huge difference in load recovery but the control factors are not well understood. It seriously affects the stimulation effect of fracture network fracturing in shale gas wells. Therefore, it is important to analyze the main control factors affecting the load recovery to optimize the design of fracture network fracturing. Further, the load recovery is affected by many factors such as geological, engineering, and production. However, traditional methods are blind to the accurate analysis of the impact on the load recovery. Notably, machine learning (ML) technology has achieved remarkable success in solving the problems of multi-factor nonlinear fitting and black box prediction. Therefore, the genetic expression programming (GEP) is adopted to express the nonlinear relationship in a clear and precise manner in this paper. The data of 189 wells were collected in southern Sichuan, including geological and engineering factors. A feature comprehensive index calculation method was established, and the relative importance of these features analyzed, and then screened out 18 reconstructed features based on geological and engineering factors that affect flow back. The mutual influence between the features was eliminated through principal component analysis of the reconstructed features. Thus the load recovery calculation model was developed and the influence of main control features (variables) on the flow back was analyzed by using partial dependence plot. Statistical parameters showed that satisfactory performance can be obtained through GEP model (training set R = 0.835, test set R = 0.815). The research results show that the GEP calculation model can quickly and accurately calculate the load recovery, obtain the influence law of main controlling factors of geological engineering on shale gas flow back and improve the control of load recovery. Therefore, the method based on GEP can effectively study the main control factors affecting the flow back of shale gas, and hence it can be used as a fast reliable tool to effectively evaluate the load recovery.

Investigating the Bond Strength of FRP Rebars in Concrete under High Temperature Using Gene-Expression Programming Model.

In recent times, the use of fibre-reinforced plastic (FRP) has increased in reinforcing concrete structures. The bond strength of FRP rebars is one of the most significant parameters for characterising the overall efficacy of the concrete structures reinforced with FRP. However, in cases of elevated temperature, the bond of FRP-reinforced concrete can deteriorate depending on a number of factors, including the type of FRP bars used, its diameter, surface form, anchorage length, concrete strength, and cover thickness. Hence, accurate quantification of FRP rebars in concrete is of paramount importance, especially at high temperatures. In this study, an artificial intelligence (AI)-based genetic-expression programming (GEP) method was used to predict the bond strength of FRP rebars in concrete at high temperatures. In order to predict the bond strength, we used failure mode temperature, fibre type, bar surface, bar diameter, anchorage length, compressive strength, and cover-to-diameter ratio as input parameters. The experimental dataset of 146 tests at various elevated temperatures were established for training and validating the model. A total of 70% of the data was used for training the model and remaining 30% was used for validation. Various statistical indices such as correlation coefficient (R), the mean absolute error (MAE), and the root-mean-square error (RMSE) were used to assess the predictive veracity of the GEP model. After the trials, the optimum hyperparameters were 150, 8, and 4 as number of chromosomes, head size and number of genes, respectively. Different genetic factors, such as the number of chromosomes, the size of the head, and the number of genes, were evaluated in eleven separate trials. The results as obtained from the rigorous statistical analysis and parametric study show that the developed GEP model is robust and can predict the bond strength of FRP rebars in concrete under high temperature with reasonable accuracy (i.e., R, RMSE and MAE 0.941, 2.087, and 1.620, and 0.935, 2.370, and 2.046, respectively, for training and validation). More importantly, based on the FRP properties, the model has been translated into traceable mathematical formulation for easy calculations.

Power prediction formula for blade design and optimization of Dual Darrieus Wind Turbines based on Taguchi Method and Genetic Expression Programming model

This study focuses on the blade design and optimization of Dual Darrieus Wind turbines (DDWTs). Based on Genetic Expression Programming (GEP) model, a power prediction formula CP=f(Δ,β,θ), containing radius difference Δ, chord ratio β, and offset angle θ, is proposed in this study. Hence, the power coefficient of various blade layouts can be directly calculated, corresponding to their optimum TSR. Meanwhile, orthogonal array L9 (34) and Modified Additive Model (MAM) are combined to ensure the representative sample and consider the interaction effects. Additionally, each configuration in dataset requires to execute Computational Fluid Dynamics (CFD) analyses under various Tip Speed Ratios (TSRs) to figure out the highest power coefficient. The optimum layout of double-layer blades, derived from Taguchi Method and CP=f(Δ,β,θ), features the parameter combination as radius difference Δ of 0.25 m and chord ratio β of 3, which can improve the power output by 7.5%. The power prediction formula established by GEP is competent to approximate CP value of double-layer blades precisely which is verified by the correlation index R2 = 0.993 and supplementary CFD cases. The proposed methodology indicates that DDWTs deserve to be further researched and developed.

Compressive strength prediction of rice husk ash using multiphysics genetic expression programming

Rice husk ash (RHA) is obtained by burning rice husks. An advanced programming technique known as genetic expression programming (GEP) is used in this research for developing an empirical multiphysics model for predicting the compressive strength of RHA incorporated concrete. A vast database comprising of 250 data points is obtained from the extensive and consistent literature review. Different parameters such as age, RHA content, cement content, water content, amount of superplasticizer and aggregate content are used as inputs. A closed-form equation solution was obtained to predict the compressive strength of RHA based on input parameters. The performance of GEP is evaluated by comparing it with regression models. Statistical parameter R2 is used to assess the results predicted by GEP and regression models. Statistical and parametric analysis is also carried out to determine the influence of inputs on the outcome. The GEP model performed better in all terms as compared to other models.

Assessment of probable groundwater changes under representative concentration pathway (RCP) scenarios through the wavelet–GEP model

The main objective of this research was to evaluate the possible impact of climate change on groundwater levels in the Tasuj Plain, Iran. To accomplish this, the values of precipitation for a near future period was projected through four general circulation models (GCM). Then, the groundwater level variations through the genetic expression programming (GEP) model were evaluated. The projection results indicated that the average annual precipitation with 33.55 mm in the base period would decline to 20.51, 20.11, and 19.14 mm under three representative concentration pathway (RCP) scenarios, namely, RCP2.6, RCP4.5, RCP8.5, respectively. The values of the determination coefficient range from 0.92 to 0.99; the root mean square error between 0.12 and 0.61, and mean absolute error from 0.08 to 0.54 showed that in the forecasting of groundwater level through the GEP model, all models have acceptable results. The evaluation of groundwater level simulation demonstrated that the developed model through the precipitation and previous groundwater level performs better. Prediction of groundwater level for a future period based on climate change scenarios indicated that the average groundwater level in Tasuj Plain at the beginning of the period would experience a gradual reduction and would then increase very slightly to the end of the period. Overall, it was found that the declining precipitation under climate change has no significant impacts on the groundwater level in the Tasuj Plain, and other parameters like anthropogenic activities could be the primary reason for groundwater depletion.

Genetic evolutionary approach for surface roughness prediction of laser sintered Ti–6Al–4V in EDM

Abstract Additive Manufacturing (AM) methods, in the field of production, are increasing rapidly. In particular, the use of Ti alloys has an important role in AM methods. The major disadvantage of AM methods is low surface quality of the manufactured parts. Therefore, parts produced using AM methods need subsequent surface treatment. Electro Discharge Machining (EDM) is one of the nontraditional machining methods, which can be used to improve the surface quality with appropriate parameters. In this study, EDM was investigated to improve the surface quality of sintered Ti–6Al–4V alloy by using 160 different finish parameters. It was observed that Current (I) has a notable effect on surface roughness showing that best surface quality is achieved with low current values, which is under R a = 2 µm. To estimate the final result of EDM, roughness values obtained from the experiments were modeled by using the Genetic Expression Programming (GEP), and a mathematical relationship between the obtained roughness values and EDM parameters was proposed. As a result of 830,900 iterations, GEP model created can estimate the final surface roughness of the parts with 84% accuracy.

Estimation of Clear-Water Local Scour at Pile Groups Using Genetic Expression Programming and Multivariate Adaptive Regression Splines

The physical process of scour around pile groups is complex. Due to economical and geotechnical considerations, multiple pile bridge piers have become more common in bridge designs. Various empirical models have been developed to estimate scour depth at pile groups. However, these models are mostly based on the conventional statistical regression approaches and are not able to adequately capture the highly nonlinear and complex relationship between scour depth and its influential factors. In this study, genetic expression programming (GEP) and multivariate adaptive regression splines (MARS) were utilized to estimate clear-water local scour depth at pile groups using the flow, sediment, and pile characteristics. Two combinations of data were used to train the GEP and MARS models. The first combination included dimensional variables (e.g., mean flow velocity and depth, mean grain diameter, pile diameter). The second combination contained nondimensional parameters. Results indicated that GEP and MARS can accurately estimate scour depth. Both models yielded better results when the dimensional data were used. In addition, the MARS model with a root mean square error (RMSE) of 0.0220 m and correlation coefficient (R2) of 0.902 outperformed the GEP model with an RMSE of 0.0285 m and R2 of 0.834. Performance of the GEP and MARS models was compared with that of the existing equations. The comparison showed that both models perform better than the regression-based empirical equations. Finally, a sensitivity analysis showed that pile diameter has the most significant impact on equilibrium scour depth.

SOFT-COMPUTING MODEL FOR COMPRESSIVE STRENGTH OF MORTARS WITH BLENDED CEMENTS

The 90 experimental data samples previously validated in the current literature regarding the compressive strength of mortars have been collected and evaluated to develop the practical soft-computing model which is presented in this study for prediction of the compressive strength of mortars with blended cements. The presented model provides many economical, technical and environmental benefits to be swiftly implemented into the practice. It is formulated based on the soft-computing techniques of genetic expression programming (GEP) by considering the model factors including as specific weight and surface of cement, water/cement ratio, testing age, the amounts of clinker, limestone, pozzolana and gypsum. Paper explains the validity of the presented model with that randomly selected experimental sub datasets available in the current literature. The findings illustrate that the presented GEP model has a favorable potential for estimating the compressive strength of mortars with blended cements.

Daily Mean Streamflow Prediction in Perennial and Non-Perennial Rivers Using Four Data Driven Techniques

This study examines and compares the performance of four new attractive artificial intelligence techniques including artificial neural network (ANN), hybrid wavelet-artificial neural network (WANN), Genetic expression programming (GEP), and hybrid wavelet-genetic expression programming (WGEP) for daily mean streamflow prediction of perennial and non-perennial rivers located in semi-arid region of Zagros mountains in Iran. For this purpose, data of daily mean streamflow of the Behesht-Abad (perennial) and Joneghan (non-perennial) rivers as well as precipitation information of 17 meteorological stations for the period 1999–2008 were used. Coefficient of determination (R2) and root mean square error (RMSE) were used for evaluating the applicability of developed models. This study showed that although the GEP model was the most accurate in predicting peak flows, but in overall among the four mentioned models in both perennial and non-perennial rivers, WANN had the best performance. Among input patterns, flow based and coupled precipitation-flow based patterns with negligible difference to each other were determined to be the best patterns. Also this study confirmed that combining wavelet method with ANN and GEP and developing WANN and WGEP methods results in improving the performance of ANN and GEP models.

Genetic programming and gene expression programming for flyrock assessment due to mine blasting

This research is aimed to develop new practical equations to predict flyrock distance based on genetic programming (GP) and genetic expression programming (GEP) techniques. For this purpose, 97 blasting operations in Delkan iron mine, Iran were investigated and the most effective parameters on flyrock were recorded. A database comprising of five inputs (i.e. burden, spacing, stemming length, hole depth, and powder factor) and one output (flyrock) was prepared to develop flyrock distance. Several GP and GEP models were proposed to predict flyrock considering the modeling procedures of them. To compare the performance prediction of the developed models, coefficient of determination (R2), mean absolute error (MAE), root mean squared error (RMSE) and variance account for (VAF) were computed and then, the best GP and GEP models were selected. According to the obtained results, it was found that the best flyrock predictive model is the GEP based-model. As an example, considering results of RMSE, values of 2.119 and 2.511 for training and testing datasets of GEP model, respectively show higher accuracy of this model in predicting flyrock, while, these values were obtained as 5.788 and 10.062 for GP model.

Estimation of soil cation exchange capacity using Genetic Expression Programming (GEP) and Multivariate Adaptive Regression Splines (MARS)

The soil cation exchange capacity (CEC) is one of the main soil chemical properties, which is required in various fields such as environmental and agricultural engineering as well as soil science. In situ measurement of CEC is time consuming and costly. Hence, numerous studies have used traditional regression-based techniques to estimate CEC from more easily measurable soil parameters (e.g., soil texture, organic matter (OM), and pH). However, these models may not be able to adequately capture the complex and highly nonlinear relationship between CEC and its influential soil variables. In this study, Genetic Expression Programming (GEP) and Multivariate Adaptive Regression Splines (MARS) were employed to estimate CEC from more readily measurable soil physical and chemical variables (e.g., OM, clay, and pH) by developing functional relations. The GEP- and MARS-based functional relations were tested at two field sites in Iran. Results showed that GEP and MARS can provide reliable estimates of CEC. Also, it was found that the MARS model (with root-mean-square-error (RMSE) of 0.318 Cmol+ kg−1 and correlation coefficient (R2) of 0.864) generated slightly better results than the GEP model (with RMSE of 0.270 Cmol+ kg−1 and R2 of 0.807). The performance of GEP and MARS models was compared with two existing approaches, namely artificial neural network (ANN) and multiple linear regression (MLR). The comparison indicated that MARS and GEP outperformed the MLP model, but they did not perform as good as ANN. Finally, a sensitivity analysis was conducted to determine the most and the least influential variables affecting CEC. It was found that OM and pH have the most and least significant effect on CEC, respectively.

Effects of infill walls on RC buildings under time history loading using genetic programming and neuro-fuzzy

In this study, the efficiency of adaptive neuro-fuzzy inference system (ANFIS) and genetic expression programming (GEP) in predicting the effects of infill walls on base reactions and roof drift of reinforced concrete frames were investigated. Current standards generally consider weight and fundamental period of structures in predicting base reactions and roof drift of structures by neglecting numbers of floors, bays, shear walls and infilled bays. Number of stories, number of bays in x and y directions, ratio of shear wall areas to the floor area, ratio of bays with infilled walls to total number bays and existence of open story were selected as parameters in GEP and ANFIS modeling. GEP and ANFIS have been widely used as alternative approaches to model complex systems. The effects of these parameters on base reactions and roof drift of RC frames were studied using 3D finite element method on 216 building models. Results obtained from 3D FEM models were used to in training and testing ANFIS and GEP models. In ANFIS and GEP models, number of floors, number of bays, ratio of shear walls and ratio of infilled bays were selected as input parameters, and base reactions and roof drifts were selected as output parameters. Results showed that the ANFIS and GEP models are capable of accurately predicting the base reactions and roof drifts of RC frames used in the training and testing phase of the study. The GEP model results better prediction compared to ANFIS model.

Tool life model for Al2O3 particle reinforced MMCs using genetic expression programming

In the present work, the wear of cutting tools in the machining of 7075Al alloy composites reinforced with 10 and 25 wt-% and 16 μm average size Al2O3 particles was investigated. Machining tests were performed on both as cast and heat treated composites by turning process using a physical vapour deposition coated carbide tool CP500 at different cutting conditions. A new model was developed to predict the tool life by genetic expression programming. The training and validation data sets were obtained from the well established machining test results. The weight fraction of particle Pw, cutting speed V, feedrate f and heat treatment Ht were used as independent input variables, while tool life T was used as a dependent output variable. Different models for tool life were predicted on the basis of the training data set using genetic programming, and the accuracy of the best model was proved with validation data set. The test results showed that the genetic expression programming model has produced correlation coefficient R values of ∼0·958 for the training data and 0·952 for the validation data. The predicted tool life results were compared with experimental results and found to be in good agreement with the experimentally observed ones.

Modeling of transfer length of prestressing strands using genetic programming and neuro-fuzzy

In this study, the efficiency of neuro-fuzzy inference system (ANFIS) and genetic expression programming (GEP) in predicting the transfer length of prestressing strands in prestressed concrete beams was investigated. Many models suggested for the transfer length of prestressing strands usually consider one or two parameters and do not provide consistent accurate prediction. The alternative approaches such as GEP and ANFIS have been recently used to model spatially complex systems. The transfer length data from various researches have been collected to use in training and testing ANFIS and GEP models. Six basic parameters affecting the transfer length of strands were selected as input parameters. These parameters are ratio of strand cross-sectional area to concrete area, surface condition of strands, diameter of strands, percentage of debonded strands, effective prestress and concrete strength at the time of measurement. Results showed that the ANFIS and GEP models are capable of accurately predicting the transfer lengths used in the training and testing phase of the study. The GEP model results better prediction compared to ANFIS model.

Genetic expression programming for prediction of heat of hydration of the blended cements

This study presents a new approach based on Genetic Expression Programming (GEP) for modeling of variation of heat of hydration of Portland and blended cements. For that purpose, two different GEP models were developed to generate two mathematical equations. In the GEP Model 1, six input parameters such as the ground blast furnace slag replacement ratio (GBFS), ground basaltic pumice replacement ratio (GBP), clinker and gypsum ratio (CG), cement fineness (CF), grinding type (GT) and time (T) were used. In GEP Model 2, three input parameters such as cement fineness (CF), grinding type (GT) and time (T) were used. The results were highly promising in terms of training performances and prediction accuracies and revealed that the proposed GEP models can be used in the prediction of heat of hydration of blended cements. Key words: Cement, heat of hydration, genetic expression programming.

Evolutionary programming method for modeling the EDM parameters for roughness

Abstract The method of electrical discharge machining (EDM), one of the processing methods based on non-traditional manufacturing procedures, is gaining increased popularity, since it does not require cutting tools and allows machining involving hard, brittle, thin and complex geometry. By using different EDM parameters (current, pulse on-time, pulse off-time, arc voltage), the Ra (μm) roughness value as a result of application of a number of copper electrode-hardened powder metals (cold work tool steel) to a work piece has been investigated, in this study. At the same time, roughness values obtained from the experiments that have been modeled by using the genetic expression programming (GEP) method and a mathematical relationship has been suggested between the GEP model and surface roughness and parameters affecting it. Moreover, EDM has been used by applying copper, copper–tungsten (W–Cu) and graphite electrodes to the same material with experimental parameters designed in accordance with the Taguchi method. Results obtained from this study have been compared among each other and similar studies in the literature.