Proposed Gene Expression Programming Model Research Articles

Proposal and evaluation of new models for predicting the FRP contribution to shear strength in reinforced concrete beams using gene expression programming

AbstractFiber-reinforced polymers (FRP) have been widely used in shear strengthening applications of reinforced concrete (RC) beams. The accurate prediction of the FRP contribution to the shear strength of beams is essential for reliable design. Gene expression programming (GEP) has been widely utilized because it reliably expresses complex relationships between experimental variables. In this study, three new GEP models are proposed for three different strengthening configurations of FRP such as fully-wrapping, U wrapping, and side-bonding to predict the FRP contribution to shear strength. These models are developed using the most comprehensive database containing a total of 811 strengthened beams (350 fully-wrapped, 328 U-wrapped, and 133 side-bonded. Many variables have been considered in the proposed GEP models, including those that have been experimentally effective but are often neglected in existing literature equations, such as the shear span-to-effective depth ratio $$(a/d)$$ ( a / d ) and the stirrup ratio ($${\rho }_{w}$$ ρ w ). Additionally, the reliability of existing equations in the literature and the proposed GEP models for predicting the FRP contribution to shear strength was statistically evaluated. As a result of this evaluation, the proposed GEP models for each strengthening configuration of FRP yielded the most accurate statistical results, with the lowest coefficient of variation (COV), and the highest coefficient of correlation (R).

A comparative study of LightGBM, XGBoost, and GEP models in shear strength management of SFRC-SBWS

Steel fiber reinforced concrete (SFRC) was revealed to have superior mechanical properties compared to plain concrete, especially under shear loads. However, Due to a lack of prediction models for SFRC-Slender Beams without Stirrups (SFRC-SBWS) in the available literature, the application of SFRC-SBWS in reinforced concrete (RC) constructions is limited. This research aims to fill a literature gap by analyzing different Machine Learning (ML) algorithms, including Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Gene Expression Programming (GEP), to forecast the shear strength of SFRC-SBWS specimens. A database of 333 tested SFRC-SBWS specimens was collected and analyzed. The results revealed the LightGBM and XGBoost algorithms surpassed other studied algorithms with Coefficient of determination (R2) = 95.74% and 93.27%, Root Mean Square Error (RMSE) = 20.04 kN and 25.19 kN, respectively. A GEP-based closed-form model was suggested to forecast the shear strength, considering the most important factors, including beam depth effect, beam width, and longitudinal steel reinforcement ratio. The proposed GEP model has an R2 = 91.12% and RMSE = 101.44 kN, showing a slightly lower prediction accuracy. The effectiveness of the studied models was evaluated from various angles, and the results demonstrate the importance of managing new technological advancements to create reliable support methods. Engineers that use these approaches get a dependable tool for estimating shear resistance, which is crucial in guaranteeing the safety and lifespan of RC structures. The successful combination of classic engineering approaches and revolutionary ML strategies indicates the potential for improving accuracy and reducing bias in prediction-oriented investigations. As the engineering field supports technological improvements, combining robust and efficient prediction models, as described in this paper, can contribute considerably to resilient structure design and safety assurance. This leads to sustainable and robust management of structures with greater confidence in predictions.

A predictive model for determination of sand liquefaction potential based on energy method

The prediction of liquefaction potential of sand under earthquake action is a complicated problem in civil engineering. In this study, gene expression programming (GEP) was used to establish the relationship between the capacity energy required to trigger sand liquefaction and several major parameters. By collecting 85 experimental data and six main parameters, a GEP model was established and the empirical prediction equation was obtained. Three statistical indices were used to evaluate the performance of the GEP model and 11 other existing capacity energy models. The results show that the coefficient of determination (R2), mean absolute error (MAE) and root mean squared error (RMSE) values of all datasets predicted by the GEP model are 0.924, 0.061 and 0.087, respectively. While the R2, MAE and RMSE values of all datasets of the 11 existing capacity energy models are 0.510–0.777, 0.149–0.468 and 0.196–0.653, respectively. It can be concluded that the proposed GEP model has the potential to accurately predict the capacity energy required to trigger sand liquefaction.

Prediction of building energy performance using mathematical gene-expression programming for a selected region of dry-summer climate

Developing energy-efficient buildings considering building design parameters can help reduce buildings' energy consumption. The energy efficiency of residential buildings is considered a top priority for the energy policies of a country. Thus, this study utilizes gene-expression programming (GEP) to estimate the energy performance of residential buildings. The energy consumption evaluations were carried out using the Etotect energy simulation software. Eight building parameters with 768 data points were considered to generate the database for the heating load (HL) and cooling load (CL), including relative compactness, surface area, wall area, roof area, overall building height, glazing orientation, glazing area, and distribution of glazing area. Different GEP predictive models with varying parameters for building HL and CL were developed, and the best-performing prediction model was selected. In addition, several statistical indices were utilized to measure the accuracy of the proposed GEP models. The results revealed that GEP14 gives the most robust prediction model for HL having R2-value greater than 0.9 for both the training and validation set. Likewise, R2-value >0.9 is achieved for best- CL (GEP11). Furthermore, the mean absolute error (MAE) values for both the predictive HL’ and CL’ by prediction models were relatively less for both the training and testing databases. The sensitivity and parametric analysis reveal that the overall height (Ho), roof area (Af), and glazing area (Ag) were the most influential parameters for both predictive models. Thus, GEP results demonstrate the robust performance in predicting the building energy.

Comparative study of genetic programming-based algorithms for predicting the compressive strength of concrete at elevated temperature

The elevated temperature severely influences the mixed properties of concrete, causing a decrease in its strength properties. Accurate proportioning of concrete components for obtaining the required compressive strength (C-S) at elevated temperatures is a complicated and time-taking process. However, using evolutionary programming techniques such as gene expression programming (GEP) and multi-expression programming (MEP) provides the accurate prediction of concrete C-S. This article presents the genetic programming-based models (such as gene expression programming (GEP) and multi-expression programming (MEP)) for forecasting the concrete compressive strength (C-S) at elevated temperatures. In this regard, 207 C-S values at elevated temperatures were obtained from previous studies. In the model’s development, C-S was considered as the output parameter with the nine most influential input parameters, including; Nano silica, cement, fly ash, water, temperature, silica fume, superplasticizer, sand, and gravels. The efficacy and accuracy of the GEP and MEP-based models were assessed by using statistical measures such as mean absolute error (MAE), correlation coefficient (R2), and root mean square error (RMSE). Moreover, models were also evaluated for external validation using different validation criteria recommended by previous studies. In comparing GEP and MEP models, GEP gave higher R2 and lower RMSE and MAE values of 0.854, 5.331 MPa, and 0.018 MPa respectively, indicating a strong correlation between actual and anticipated outputs. Thus, the GEP-based model was used further for sensitivity analysis, which revealed that cement is the most influencing factor. In addition, the proposed GEP model provides simple mathematical expression that can be easily implemented in practice.

Synthesis of heated aluminum oxide particles impregnated with Prussian blue for cesium and natural organic matter adsorption: Experimental and machine learning modeling

Heated aluminum oxide particles impregnated with Prussian blue (HAOPs-PB) are synthesized for the first time using different molar ratios of aluminum sulfate and PB to improve the adsorption of cesium (133Cs+) and natural organic matter (NOM) from an aqueous solution. The Cs+ adsorption from various aqueous solutions, including surface, tap and deionized water by synthesized HAOPs-PB, is investigated. The influencing factors such as HAOPs-PB mixing ratio, pH and dosage are studied. In addition, pseudo 1st and 2nd order is tested for adsorption kinetics study. A machine learning model is developed using gene expression programming (GEP) to evaluate and optimize the adsorption process for Cs+ and NOM removal. Synthesized adsorbent showed maximum adsorption at a 1:1 M ratio of aluminum sulfate and PB in DI, tap, and surface water. The pseudo 2nd order kinetics model described the Cs + adsorption by HAOPs-PB more accurately that indicating physiochemical adsorption. Adsorption of Cs+ showed an increasing trend with higher HAOPs-PB concentration, while high pH also favored the adsorption. Maximum NOM adsorption is found at a higher HAOPs-PB dosage and a neutral pH value. Furthermore, the proposed GEP model shows outstanding performance for Cs+ adsorption modeling, whereas a modified-GEP model presents promising results for NOM adsorption prediction for testing dataset by learning the relationship between inputs and output with R2 values of 0.9348 and 0.889, respectively.

GEP-based models for estimating the elastic shear buckling and ultimate loads of cold-formed steel channels with staggered slotted web perforations in shear

Thermal bridging through cold-formed steel (CFS) channels can be substantially reduced by introducing staggered slots in the channels’ webs. The perforation size and pattern significantly affect the elastic shear buckling and ultimate loads of the channels in shear, which must be considered in the design. This paper proposes new models for accurate estimations of the shear buckling and ultimate loads derived from an extensive database by employing gene expression programming (GEP). The model constructions involve various dimensional parameters, types of boundary conditions, and the yield strength of the channels. The proposed GEP models, in the form of transparent mathematical expressions, provide reasonable prediction accuracy comparable to published descriptive equations. However, the GEP models are simpler than the existing equations and do not require additional advanced computations, as the existing equations do, to obtain the elastic shear buckling and ultimate shear loads. LRFD resistance and ASD safety factors for the proposed GEP model were determined in accordance with AISI S100-16 w/S2-20. Based on the presented information, the GEP models are recommended for estimating the elastic shear buckling and ultimate loads of CFS channels with staggered slotted web perforations in shear.

Computation of energy dissipation across the type-A piano key weir by using gene expression programming technique

Abstract Energy dissipation across the weir and dam structures is a vital economic and technical solution for designing the downstream morphology of any hydraulic system. Accurately estimating the energy over any hydraulic system using traditional empirical formulas is tedious and challenging. Consequently, employing new and precise techniques still in high demand is crucial. In this study, the authors developed an empirical model for estimating the residual energy downstream of the type-A piano key weir (PKW) using gene expression programming (GEP) by considering six non-dimensional parameters: headwater ratio, magnification ratio, inlet to outlet width ratio, inlet to outlet key bottom slopes, inlet to outlet overhang portions and the number of cycles. The performance of the proposed models has been compared to empirical equations using the statistical factors coefficient of determination (R2), concordance coefficient (CC), and root mean square error (RMSE). The computed relative residual energy values using the proposed models are within ±10% of the observed ones. The proposed GEP model predicted the relative residual energy satisfactorily, with coefficients of determination of R2 = 0.978 for training, 0.980 for testing and root mean square errors (RMSE) of 0.032 and 0.029 for the training and testing datasets, respectively.

Trend analysis of temperature data using innovative polygon trend analysis and modeling by gene expression programming.

Presenting temperature data using recently introduced innovative polygon trend analysis (IPTA) can improve our understanding of the effects of climate change. This method was applied to analyze temperature trends at six stations in Turkey: Istanbul (17,064), Ankara (17,131), Bursa (17,116), Iznik (17,661), Gemilik (17,663), and Sakarya (17,069). At station 17,064, there was an increasing trend in temperature data for sevenmonths, while only onemonth showed a decreasing trend, and the remainder presented no trend. For station 17,131, there was a decreasing trend for twomonths, an increasing trend for fivemonths, and no trend for the remaining months. At station 17,116, an increasing trend was present for ninemonths, with a decreasing trend for twomonths and only onemonth indicating no trend. An increasing trend over sevenmonths was noted at station 17,661, while two and threemonths showed a decreasing and no trend, respectively. For station 17,663, there was an increasing trend for ninemonths, onemonth showed no trend, and twomonths presented a decreasing trend. At station 17,069, five, four, and threemonths showed increasing, decreasing, and no trends, respectively. The gene expression programming (GEP) model was tested to predict the short-termmonthly average temperature for this dataset. The proposed GEP model presented good prediction results for all selected stations by tracing the relationship with a coefficient of determination (R-Sq) ≥ 0.90. Trend analysis by IPTA can help understand temperature trends better, aiding future decision-making, and the GEP model can effectively predict short-term values.

Estimation of local scour depth around twin piers using gene expression programming (local scour around twin piers)

Abstract The scour around the bridge piers has been estimated using conventional empirical formulae; however, these formulae are unable to predict the scour depth precisely. The present study is conducted in two parts (a) experimental investigation for evaluating the behaviour of local scour around twin piers positioned in the transverse direction of flow and (b) an empirical equation to estimating scour depth is proposed utilising new evolutionary artificial intelligence technique gene expression programming (GEP). Experimental results for the present study demonstrate the influence of the rate of flow and clear spacing between the piers on the scour depth. Additionally the results of the soft computing technique GEP during testing and training of proposed modelling, fitness function root mean square error is observed as 0.00133 and 0.00113, with the coefficient of determination as 0.950 and 0.955, respectively. Furthermore, in order to find out the role of each variable for scour depth sensitivity, analysis has been conducted. The findings of the sensitivity analysis show that the pier spacing and rate of flow play the most significant role in scour depth estimation. Results of this study demonstrate a good agreement with the proposed GEP model and conclude that it is a better approach for forecasting scour depth.

A novel model for prediction of uniaxial compressive strength of rocks

This paper presents an empirical model for predicting the uniaxial compressive strength (UCS) of rocks using gene expression programming (GEP). A total of 44 datasets collected from the literature was used to construct the GEP model. The GEP model developed is evaluated using four conventional regression models and an artificial neural network (ANN) model in terms of three statistical indices. The comparison results confirmed that the proposed GEP model has the lowest root mean square error (RMSE) and the highest coefficient of determination (R 2 ) and correlation coefficient (R) values compared to the four conventional regression models and the ANN model in the literature. It is concluded that the proposed GEP model can be applied to predict the UCS of rocks.

Optimizing slightly acidic electrolyzed water (SAEW) production through experiments and gene expression programming

Slightly acidic electrolyzed water (SAEW) was produced through hydrochloric acid (HCl) electrolysis in a lab-scale reactor equipped with titanium-coated anode and cathode, without a diaphragm. The effect of changes in the production parameters (voltage, feed water flow rate (FFR), acid flow rate (AFR), and acid concentration (AC) and feed water characteristics (pHf, temperature, organic matter (OM) content, and water hardness) on the SAEW properties was evaluated based on the available chlorine concentration (ACC), pH, and oxidation-reduction potential (ORP) of the final product. Moreover, a gene expression programming (GEP) model was developed using the experimental results as a predictive tool to optimize the process. The results indicated that variations in FFR, AC, AFR, and OM significantly affected the SAEW properties. In contrast, no substantial effect was observed by varying the feed water's temperature, pH, voltage, and hardness. Using tap water, the optimal conditions to produce SAEW were observed at an FFR of 6.5 L/min, pHf of 7.45, at 20 °C using 6% AC at an AFR of 9 mL/s with reactor operation at 3.8 V. The proposed GEP model showed an efficient correlation coefficient (CC) of 0.941 and 0.938, and coefficient of determination (R2) of 0.885 and 0.880, respectively, for the unseen testing data to predict the ACC and pH of the produced SAEW.

Sustainable use of chemically modified tyre rubber in concrete: Machine learning based novel predictive model

To encourage the consumption of crumb rubber (CR), gene expression programming (GEP) has been exercised in this paper to establish empirical models for estimation of mechanical properties of concrete made with NaOH treated CR. An extensive and reliable database of compressive strength of concrete made with NaOH treated CR is established through a comprehensive literature review. Literature review showed that compressive strength of NaOH treated CR concrete is affected by percentage of CR used as a replacement of sand (RS%), concentration of NaOH solution (NC in %), period of NaOH pre-treatment (PTP in hours), water to cement ratio (W/C), quantity of sand (S in kg/m3) and quantity of superplasticizer (SP in kg/m3). The performance of the established model is evaluated by doing parametric analysis, applying statistical checks and comparing with regression models. The R-values in the testing phase of GEP, linear and non-linear regression (LR and NLR) equations are 0.90 and 0.77 each respectively. Furthermore, objective function (OF) of GEP model is 25%, and 33% better than LR and NLR model. Thus, results reflected that the proposed GEP model is more accurate and possess a high generalization and prediction capability than LR and NLR equations with resolved overfitting issue. The results of this research can boost the re-usage of CR for expansion of green concrete leading to environmental safety and economic advantages.

Application of data-driven machine learning to predict propranolol and trimethoprim removal using a managed aquifer recharge system

Owing to their persistent nature, pharmaceutical products (PPs) are emerging as potent water pollutants. Here, experimental and data-driven modeling, specifically multilayer perceptron (MLP) neural networking and gene expression programming (GEP), was employed to predict the removal of the most common antihypertensive and antibiotic drugs, namely propranolol and trimethoprim, from reclaimed water (RW) through a managed aquifer recharge system (MARS). The characteristics of RW and soil used as the column medium, including operating time (days); pH; dissolved organic carbon; electrical conductivity; and concentration of nitrogen dioxide, nitrate, sulfate, ferrous, chloride, and manganese, were included as the input parameters and removal of the selected PPs as the model output. A dataset was created through an experimental study conducted over a year of continuous operation of MARS to predict the removal of the selected PPs. MLP and GEP models were developed for one of the selected PPs and tested for the other to determine model reliability. The developed models were assessed using statistical performance matrices. The experimental results showed over 80% propranolol and trimethoprim removal from RW through MARS. The proposed GEP predictive models for propranolol and trimethoprim removal showed higher accuracy (R2 = 0.91 and 0.87, respectively) than the MLP models (R2 = 0.827 and 0.756, respectively). Therefore, the proposed GEP models provide better predictions and mathematical relationships for future studies. Thus, data-driven machine learning models can predict the removal of specific PPs from RW through MARS and minimize the experimental workload.

Properties of self-compacted concrete incorporating basalt fibers: Experimental study and Gene Expression Programming (GEP) analysis

Inorganic basalt fiber (BF) is a novel sort of commercial concrete fiber which is made with basalt rocks. Previous studies have not sufficiently handled the behavior of self-compacted concrete, at elevated temperature, containing basalt fiber. Present endeavor covers experimental work to examine the characteristics of this material at high temperature considering different fiber content and applied temperature. Different tests were carried out to measure the mechanical properties such as compressive strength (fc), modulus of elasticity (E), Poisson's ratio, splitting tensile strength (fsplit), flexural strength (fflex), and slant shear strength (fslant) of HSC and hybrid concrete. Gene expression programming (GEP) was employed to propose new constitutive relationships depending on experimental data. It was noticed from the testing records that there is no remarkable effect of BF on the Poisson's ratio and modulus of elasticity of self-compacted concrete. The flexural strength of basalt fiber self-compacted concrete was not sensitive to temperature in comparison to other mechanical properties of concrete. Fiber volume fraction of 0.25% was found to be the optimum to some extend according to degradation of strength. The proposed GEP models were in good matching with the experimental results.

A new model for prediction of soil thermal conductivity

This study presents a gene expression programming (GEP) method for determining soil thermal conductivity (k). A large and reliable database containing 444 thermal conductivity measurements was collected and employed to develop the GEP model. Four governing parameters (i.e., porosity, saturation degree, quartz content and temperature) were selected as inputs based on a Pearson correlation analysis. Through the determination of the optimal parameter setting of GEP, a predictive equation was first proposed. Then, the proposed GEP model was evaluated and compared with several previous models. The results indicate the proposed GEP model has higher prediction precision than the other models. In addition, a monotonicity analysis was performed to validate the rationality of the proposed GEP model. According to the monotonicity analysis results, the soil thermal conductivity increases with the increase of saturation degree, quartz content and temperature, and it decreases with the increasing of the porosity. Finally, a parametric analysis was conducted to investigate the significance of the inputs. The results show that the effect rank of these four input variables on soil thermal conductivity is saturation degree > porosity > temperature > quartz content, which can provide a reference for similar projects.

Smart learning strategy for predicting viscoelastic surfactant (VES) viscosity in oil well matrix acidizing process using a rigorous mathematical approach

This piece of study attempts to accurately anticipate the apparent viscosity of the viscoelastic surfactant (VES) based self-diverting acids as a function of VES concentration, temperature, shear rate, and pH value. The focus not only is on generating computer-aided models but also on developing a straightforward and reliable explicit mathematical expression. Towards this end, Gene Expression Programming (GEP) is used to connect the aforementioned features to and the target. The GEP network is trained using a wide dataset adopted from open literature and leads to an empirical correlation for fulfilling the aim of this study. The performance of the proposed model is shown to be fair enough. The accuracy analysis indicates satisfactory Root Mean Square Error and R-squared values of 7.07 and 0.95, respectively. Additionally, the proposed GEP model is compared with literature published correlations and established itself as the superior approach for predicting the viscosity of VES-based acids. Accordingly, the GEP model can be potentially served as an efficient alternative to experimental measurements. Its obvious advantages are saving time, lowering the expenses, avoiding sophisticated experimental procedures, and accelerating the diverter design in stimulation operations.Article HighlightsThe Gene Expression Programming evolutionary algorithm is proposed for modeling the viscosity of Viscoelastic Surfactant-based self-diverting acids.The viscoelastic surfactant viscosity correlation presents high accuracy which is demonstrated through multiple analyses.The Gene Expression Programming algorithm is a reliable tool expediting the diverter design phase of each stimulation operation.

Sensitivity and Uncertainity Analysis of Flow Velocity Estimation Using Gene Expression Programming Model in Curved Channels

Prediction of velocity is an important parameter in curved channels. Recently, artificial intelligent methods are developing than the common costly and time-consuming experimental and numerical methods in estimation of flow variables. In the present study, Gene expression programming (GEP) model as developed genetic programming model is used to predict the flow velocity in the channel with a sharp 90° bend. Different input parameter combinations are examined in order to finding the optimum model then the model efficiency are evaluated in estimation of the flow velocity in training and testing phases. By comparing the results of the GEP model with experimental data, there is an acceptable accordance between results with the root mean square error (RMSE) values of 0.828 and 0.8197 in the training and testing phase. The results show that the input parameters of (r,q) (polar points coordinate and the flow discharge) are the most effective parameters in bend flow pattern surveying. With increasing the flow discharge, the model error at the end section of the bend in the outer channel wall is decreased. Also a practical and reliable relationship is proposed by the GEP model and the sensitivity of suggested equation to each of input parameter is evaluated. Furthermore, the uncertainty of the proposed GEP model in the velocity prediction is assessed and different confidence bounds are introduced.

Prediction of Concrete Cover Separation in Reinforced Concrete Beams Strengthened with FRP

Fiber-reinforced polymers (FRPs) are widely used to enhance the flexural capacity of existing concrete structures subjected to various loading actions. However, when FRPs are applied to structural elements as externally bonded flexural reinforcement, premature debonding of the FRP may occur in the form of concrete cover separation (CCS). This study explores the potential of gene expression programming (GEP) for the development of a new model for the prediction of the shear force required to induce FRP CCS failure. A comprehensive database consisting of FRP-strengthened RC beams that failed by CCS was compiled and comprised of 127 experimental data points. GEP was employed to develop an accurate prediction model for CCS failure, encapsulating all the influencing parameters into a single equation. A comparative study was also conducted to assess the performance of the new GEP model against several existing analytical models from the literature. The proposed GEP model demonstrated significantly higher correlations between predicted and actual CCS failure loads when compared with all available predictive models.

Gene-expression programming for calculating discharge in meandering compound channels

Computation of flow in natural channels is the key to the solution of numerous engineering problems particularly at the time of flood. Therefore, different approaches have been incorporated for accurate estimation of flow discharge in compound meandering channels. The present work focuses on developing an empirical model for estimating the flow of meandering compound channels using gene-expression programming (GEP) by considering four non-dimensional parameters viz Relative Depth, Sinuosity, Coherence Parameter, and Discharge Ratio (Qvdm/Qbf). The model developed for the meandering compound channels is best suited for sinuosity in the range of 1.04–2. To measure adequacy of the model, the results of the developed model are compared with various discharge estimation methods such as the Single Channel Method (SCM), Divided Channel Method (DCM), Meander Belt Method (MBM), Modified Divided Channel Method (MDCM), Interacting Divided Channel Method (IDCM), and Coherence Method (COHM). Results indicate that the proposed GEP model predicted the ratio of total discharge in compound channel (Qt) to the bank-full discharge (Qbf) in main channel satisfactorily with root mean square error of 0.15 and 0.19 for training and testing dataset, respectively. The developed model is also used to validate with higher sinuous channels having sinuosity exceeding 2.0. Finally, the model was successfully validated with natural flood conditions of River Baitarani, India (sinuosity of 1.334) giving the minimum errors in terms of mean absolute square error of 0.885 and 0.882 for the two overbank flow depths of 7.5 and 8.63 m, respectively.