Experimental Data Points Research Articles

Prediction of axial compressive capacity and interpretability analysis of web perforated Σ-shaped cold-formed steel

The Σ-shaped cold-formed steel with web opening (ΣSCFSWWO) is a critical component in modern structural systems, and accurate calculations of its axial compressive capacity are essential for ensuring the overall stability and safety of structures. However, traditional finite element analysis (FEA) and experimental methods are often inefficient and require complex modeling techniques for capacity calculations. Moreover, the interaction between section design parameters and structural capacity remains unclear. This study integrates FEA, experimental methods, and machine learning to propose a novel approach for predicting capacity and analyzing parameter interpretability. A dataset comprising 1000 numerical simulation results and 260 experimental data points was established. Machine learning techniques, including BP (Backpropagation) neural networks, RBF (Radial Basis Function) neural networks, Decision trees, Random Forests, and XGBoost algorithms, were employed to develop predictive models for capacity. The SHapley Additive exPlanation (SHAP) method was utilized for interpretability analysis. Results indicate a good correlation between FEA and experimental outcomes, effectively simulating the mechanical behavior of the components. Comparative analysis reveals that the XGBoost model demonstrates the highest predictive accuracy and generalization capability. SHAP analysis elucidates the influence of various input parameters on axial compressive capacity predictions and clarifies the interactions among these parameters. This research provides a novel reference for calculating the axial compressive capacity of ΣSCFSWWO, and the proposed methodologies can be extended to other similar components.

Bioadhesive film for the delivery of local anesthetics to the buccal mucosa: ex-vivo and in-vivo evaluation

The aim of this work was the preparation and characterization of two bioadhesive films (with different drug loadings) containing a combination of lidocaine and prilocaine hydrochloride to be applied on the buccal mucosa to reduce the pain sensation associated with needle insertion during dental procedures. The films were tested ex-vivo to determine the amount of drug permeated/retained in buccal mucosa, and, in-vivo to assess the extent and duration of anesthetic effect on the mucosa and pharmacokinetic parameters. As a reference, the commercial formulation EMLA® cream was used. Ex-vivo studies were conducted on porcine esophageal epithelium, an accepted model for buccal mucosa, and in-vivo studies on human volunteers. The ex-vivo results obtained show that the retention of both drugs into the mucosa resulted comparable after the application of the films or EMLA® cream for 10 min; on the contrary, the amounts of drug permeated from the commercial formulation was higher, suggesting the possibility to achieve systemic effect. In-vivo experiments showed that the intensity of anesthesia, evaluated by VAS during needle insertion, was much higher for EMLA® cream (the median value was zero for EMLA® and 0.15–0.3 cm for the two films); however, the film and EMLA® cream resulted equivalent in terms of duration of anesthesia, from 25 to 40 min. The pharmacokinetic study showed that both films tested produced very low plasma concentration (zero for most of experimental data point), thus guaranteeing no risk of systemic effects, whereas EMLA® cream demonstrated measurable plasma levels for both drugs (lidocaine Cmax was 4 ng/ml, prilocaine Cmax was 1.5 ng/ml). Moreover, a correlation between ex-vivo drug tissue concentration and duration of the anesthetic effect in-vivo was found. Although this correlation is limited to a small number of formulations, it supports the validity of pig esophageal epithelium in the development of formulation to be used on human buccal mucosa.

Experimental comparison and optimal machine learning technique for predicting the thermo-hydraulic performance of Low-GWP refrigerants (R1234yf, R290, and R13I1/R290) during evaporation in plate heat exchanger

In recent times, employing machine learning techniques (MLTs) to forecast the evaporation/condensation performance of refrigerants, namely the heat transfer coefficient (HTC) and frictional pressure drop (FPD), has become increasingly significant. In the current investigation, an experimental comparison of the evaporation HTC and FPD of R1234yf, R290, and R13I1/R290 was explored in an offset strip fin-plate heat exchanger. Following this, six MLTs—support vector regressor (SVR), multilayer perceptron regressor (MLPR), gradient boosting regressor (GBR), AdaBoost regressor (ABR), ridge regressor (RR), and K-nearest neighbors regressor (KNNR)—were proposed to forecast the HTC and FPD of these refrigerants. The comparative experimental analysis revealed that the evaporation-HTC of R290 was 27.8–76.2 % and 46.2–73.8 % higher than that of R1234yf and R13I1/R290, respectively, while FPD declined by up to 74.8 % and 57.2 %, respectively. Under the same working conditions, the first transition from nucleation to convective boiling occurred in the order of R1234yf, R13I1/290, and R290. In addition, nucleate boiling dominated at lower vapor quality, while convective boiling prevailed at higher vapor quality. A total of 336 experimental data points corresponding to various test conditions from existing studies and current experiments were considered for the MLT prediction analysis. According to the results, GBR (without any enhancement approaches) was the best approach for forecasting the FPD and HTC, with mean absolute errors (MAE) of 0.125 % and 0.131 %, respectively. Additionally, to enhance the forecasting efficiency of the MLTs, feature selection, analysis of principal components, and hyperparameter tuning were employed. According to feature importance, mass flux, reduced pressure, saturation temperature, heat flux, and entry vapor quality were identified as the most influential parameters on the FPD and HTC. Ultimately, the most accurate predictions of HTC and FPD, with the lowest MAE of 0.111 %, were achieved using MLPR and SVR, respectively, with feature selection.

Performance prediction of sintered NdFeB magnet using multi-head attention regression models

The preparation of sintered NdFeB magnets is complex, time-consuming, and costly. Data-driven machine learning methods can enhance the efficiency of material synthesis and performance optimization. Traditional machine learning models based on mathematical and statistical principles are effective for structured data and offer high interpretability. However, as the scale and dimensionality of the data increase, the computational complexity of models rises dramatically, making hyperparameter tuning more challenging. By contrast, neural network models possess strong nonlinear modeling capabilities for handling large-scale data, but their decision-making and inferential processes remain opaque. To enhance interpretability of neural network, we collected 1,200 high-quality experimental data points and developed a multi-head attention regression model by integrating an attention mechanism into the neural network. The model enables parallel data processing, accelerates both training and inference speed, and reduces reliance on feature engineering and hyperparameter tuning. The coefficients of determination for remanence and coercivity are 0.97 and 0.84, respectively. This study offers new insights into machine learning-based modeling of structure-property relationships in materials and has potential to advance the research of multimodal NdFeB magnet models.

Multi-feature driven seismic damage state identification for reinforced concrete shear walls using computer vision and machine learning

In this paper, an image-based methodology using machine learning algorithms is developed for earthquake-induced damage state prediction in rectangular reinforced concrete shear walls. The machine learning models are developed using a database including experimental data points of 285 surface crack maps of damaged reinforced concrete shear walls collected from the literature. Eight different machine learning algorithms are utilized to train the damage-level classification models. The damage levels are defined according to the FEMA P-58 damage categories. In addition to the structural and geometric properties of the reinforced concrete shear walls with rectangular cross-section, three image-based indices including Succolarity, Lacunarity, and generalized fractal dimensions are measured as input features of the predictive models. Nine groups of features are selected as input for the machine learning algorithms. Using the GridsearchCV function, the hyperparameters resulting in the best algorithmic performance are chosen from a set of possible parameters. A five-fold cross-validation technique is applied to evaluate the models by resampling procedure. According to the results, the predictive model that uses the Extreme Gradient Boosting (XGB) algorithm with inputs that include both structural parameters and image indices performs best in terms of both overfitting prevention and classification accuracy. The outcomes of the damage state identification can be employed for safety assessment of the reinforced concrete buildings as well as repair/demolish decision-making after an earthquake.

Experimental investigation of the heat transfer characteristics of CO2 at supercritical pressures flowing in heated vertical pipes

Supercritical CO2 shows great potential as a working fluid in power plant cycles due to its moderate critical pressure of 7.38 MPa and critical temperature of 30.98 °C, closely matching typical heat sink temperatures. Understanding the heat transfer characteristics of sCO2 is crucial for designing cycle components. This publication presents a systematic analysis of sCO2 heat transfer in two heated vertical pipes with 4 and 8 mm inner diameters, with both upward and downward flow at pressures of approximately 7.75, 8.00, and 9.50 MPa, and flow inlet temperatures between 5 and 40 °C, based on 196 experiments. The study investigates a range of mass fluxes from 400 to 2000 kg/m2s and heat fluxes from 10 to 195 kW/m2, resulting in a heat to mass flux ratio of 6 to 275 J/kg. The findings reveal enhanced, normal, and deteriorated heat transfer within the experimental dataset. Buoyancy effects are identified as the main cause of deteriorated heat transfer in the investigated parameter range, with flow acceleration showing no significant influence on heat transfer. A new proposed dimensional criterion categorises 36 out of 119 experiments with upward flow in the deteriorated heat transfer regime, accompanied by temperature peaks rising to 47 K. Thermal inflow lengths range from 0 to 480 inner pipe diameters, with some experiments not achieving a thermally fully developed flow over the entire pipe length. Based on a comparison with approximately 8950 experimental data points, two Nusselt correlations are found, capable of reproducing the experimental results with a mean absolute deviation of around 30 %. This publication provides valuable data for validating numerical models and developing correlations to predict the heat transfer of supercritical fluids.

Machine Learning Prediction of Recycled Concrete Powder with Experimental validation and Life Cycle Assessment study

The environmental effect of the construction sector has recently drawn attention, leading to research which promotes sustainability [1,2]. Therefore, different researcher recommends different alternative materials such as fly ash [3], waste glass [4], red mud [5] and solid waste [6]. Environmental sustainability and mechanical performance are two major concerns in the construction industry. Furthermore, the complex internal relationships between the components of such concrete determine the mix design, which is crucial for attaining the required compressive strength. This study addresses two key issues associated with the current concrete production. First, it uses recycled concrete powder (RCP) as a cement replacement (0%, 5%, 10%, and 15%) to promote sustainability and the undesirable impact of cement on the environment. Secondly, it proposes a predictive model based on machine learning for the compressive strength of RCP based concrete. A comprehensive dataset containing 270 experimental data points was compiled to train and test various machine learning (ML) models. The experimental results indicated that the optimum RCP mix with 10% replacement, achieved a compressive strength that was 15.8% higher than that of the reference concrete without RCP. Furthermore, scanning electronic microscopy indicates that internal structure improved with RCP due to filling and pozzolanic reaction. ML models indicate that Gradient Boosting was found to be the most precise, exhibiting the highest coefficient of determination with the lowest values for root mean squared error and mean absolute error. These findings provide valuable insights for engineers, contractors, and stakeholders, facilitating enhanced design optimization and promoting the efficient use of resources in concrete construction projects.

Apparent kinetics study and efficient continuous-flow synthesis of tert-butyl hydroperoxide & tert-butyl peroxybenzoate in a microreaction system

This study advances the synthesis of tert-butyl hydroperoxide (TBHP) and tert-butyl peroxybenzoate (TBPB) using a continuous microreaction system, meticulously detailing kinetic behavior and optimization processes through over 1250 experimental data points. We have developed a platform capable of high-throughput kinetic experiments and precise reaction quenching, determining kinetic parameters and optimal conditions that significantly improve reaction efficiency and safety. Tailored microreaction strategies, including micro-mixers, plate microreactors, and micro-packed beds, were employed to manage exothermic reactions and enhance mass transfer for each peroxide. For TBHP, conditions were optimized to achieve a 99% conversion rate of tert-butanol and an 82% conversion of hydrogen peroxide, with product selectivity reaching 92%. For TBPB, under optimal conditions, benzoyl chloride conversion reached 99.5%, and TBHP conversion was 80%, with a product selectivity of 94%. The integration of the TBHP and TBPB synthesis processes into a single continuous-flow system demonstrates scalable, safe, and efficient production, highlighting significant potential for advancements in organic peroxide manufacturing.

ECBD: European chemical biology database.

The European Chemical Biology Database (ECBD, https://ecbd.eu) serves as the central repository for data generated by the EU-OPENSCREEN research infrastructure consortium. It is developed according to FAIR principles, which emphasize findability, accessibility, interoperabilityand reusability of data. This data is made available to the scientific community following open access principles. The ECBD stores both positive and negative results from the entire chemical biology project pipeline, including data from primary or counter-screening assays. The assays utilize a defined and diverse library of over 107000 compounds, the annotations of which are continuously enriched by external user supported screening projects and by internal EU-OPENSCREEN bioprofiling efforts. These compounds were screened in 89 currently deposited datasets (assays), with 48 already being publicly accessible, while the remaining will be published after a publication embargo period of up to 3 years. Together these datasets encompass ∼4.3 million experimental data points. All public data within ECBD can be accessed through its user interface, API or by database dump under the CC-BY 4.0 license.

A robust approach for bond strength prediction of mortar using machine learning with SHAP interpretability

Application of machine learning (ML) in predicting mortars bond strength contributes to low experimental cost and high accuracy. This study explores the performance of four ML models—Back Propagation Neural Network (BPNN), Support Vector Regression (SVR), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost)—using 304 experimental data points for training and 76 results for testing. Among these, the XGBoost model demonstrated the highest predictive accuracy, with R², MAE, and RMSE values of 0.95, 0.06, and 0.13 in the training set, and 0.94, 0.08, and 0.16 in the testing set, respectively. Compared with traditional models, ML approaches, particularly XGBoost, were more effective in providing reliable predictions of bond strength. SHapley Additive exPlanation (SHAP) show that substrate type, ethylene-vinyl acetate (EVA) content and water to binder ratio W/C have the most remarkable effect on bond strength, while the type of cement and admixture shows the least effect. These findings highlight the potential of ML models in optimizing mortar formulations and improving prediction reliability.

Determination of heat transfer characteristics of tube bundles over heating plate by machine learning

In this study machine learning is used with the aid of a deep neural network algorithm to predict convective heat transfer characteristics for inline and staggered tube bundles, and correlation equations for Nusselt number and friction factor are derived. Machine learning algorithm's data were obtained from experimental work for various transverse pitch of the tube bundles, longitudinal pitch of the tube bundles and Reynolds number. 276 experimental data points were taken for both inline and staggered tube bundles. However, considering that the data obtained from the experimental study may be insufficient for training, a two-step data augmentation method and retraining with cross-validation was used to prevent data deficiency in the deep neural network structure. Thus, the unseen data in the experimental work were also predicted. The coefficient of determination for the DNN model predictions was obtained greater than 0.96. One correlation equation for Nusselt Number and three correlation equations for friction factor were proposed from the augmented data with machine learning. The R2 values of the correlation equations varied between 89 % and 99 %. As a result, machine learning methods successfully applied to predict the Nusselt number and friction factor of tube bundles consistent with the experimental data.

Gas liquid flow pattern prediction in horizontal and slightly inclined pipes: From mechanistic modelling to machine learning

This paper investigates the prediction of two-phase gas-liquid flow regimes in both horizontal and slightly inclined pipes. For this purpose, the mechanistic model of Taitel et al. (1976) and the machine learning approach have been adopted. First, the mechanistic model was implemented, tested and optimised by introducing factors in the transition equations to determine the configuration that gives the highest prediction accuracy for a specific two-phase system for which experimental data points are available. Second, several machine learning models are trained, tested and additionally validated. This is done by splitting the experimental data set corresponding to the pipe inclination range (−10∘ to 10∘) into training, test and validation sets. The best classifier achieved an accuracy of 95.5% after the test step and up to 98.9% after the validation step. Finally, the Taitel et al. model with the optimal configuration and the best machine learning classifier (XGB classifier) are used to generate the two-dimensional flow regime map.

A generalized machine learning framework to estimate fatigue life across materials with minimal data

In this research, a generalized machine learning (ML) framework is proposed to estimate the fatigue life of epoxy polymers and additively manufactured AlSi10Mg alloy materials, leveraging their failure surface void characteristics. An extreme gradient boosting algorithm-based ML framework encompassing Synthetic Minority Over-sampling TEchnique (SMOTE), categorical data encoding, and external loop cross-validation is developed to evaluate the fatigue life across materials. The influence of different training strategies based on materials, input features, encoding method, and data standardization on the model performance is explored. Additionally, the importance of anti-data-leakage and anti-overfitting measures over the ML model performance is addressed. The result shows that the data-leakage-free, external loop cross-validated model can estimate the fatigue life of selective epoxy polymers and metal alloys with an average R2 of 0.71 ± 0.06 using a mere 12 to 27 experimental data points per material category. Whereas the model trained with data-leakage and overfitting results in high R2 of 0.9.

Predicting the Compressive Strength of Sustainable Portland Cement-Fly Ash Mortar Using Explainable Boosting Machine Learning Techniques.

Unconfined compressive strength (UCS) is a critical property for assessing the engineering performances of sustainable materials, such as cement-fly ash mortar (CFAM), in the design of construction engineering projects. The experimental determination of UCS is time-consuming and expensive. Therefore, the present study aims to model the UCS of CFAM with boosting machine learning methods. First, an extensive database consisting of 395 experimental data points derived from the literature was developed. Then, three typical boosting machine learning models were employed to model the UCS based on the database, including gradient boosting regressor (GBR), light gradient boosting machine (LGBM), and Ada-Boost regressor (ABR). Additionally, the importance of different input parameters was quantitatively analyzed using the SHapley Additive exPlanations (SHAP) approach. Finally, the best boosting machine learning model's prediction accuracy was compared to ten other commonly used machine learning models. The results indicate that the GBR model outperformed the LGBM and ABR models in predicting the UCS of the CFAM. The GBR model demonstrated significant accuracy, with no significant difference between the measured and predicted UCS values. The SHAP interpretations revealed that the curing time (T) was the most critical feature influencing the UCS values. At the same time, the chemical composition of the fly ash, particularly Al2O3, was more influential than the fly-ash dosage (FAD) or water-to-binder ratio (W/B) in determining the UCS values. Overall, this study demonstrates that SHAP boosting machine learning technology can be a useful tool for modeling and predicting UCS values of CFAM with good accuracy. It could also be helpful for CFAM design by saving time and costs on experimental tests.

Fracture failure analysis of plastic fiber based on thermodynamic strength theory and experiment

In order to analyze the mechanical behavior of plastic fiber bundle, a theoretical model considering elastic and plastic behavior of single fiber is established. Based on uniaxial tensile tests of polythene single fiber, elastoplastic mechanical properties, such as elastic modulus and plastic modulus, are obtained. Moreover, distributions of yield strength and breaking strength of single fiber are determined. The stress–strain curve of polythene fiber bundle is predicted by theoretical model. The correctness of this theoretical model is verified by uniaxial tensile test of polythene fiber bundle. All experimental data points are within the range predicted by theoretical model. Some key parameters which regulate mechanical behavior of single fiber are investigated theoretically. Results show that Weibull parameters of yield strength and breaking strength of single fiber have great effect on mechanical performance of fiber bundle. The concentration of distribution area of breaking strength can improve the overall fracture strength of fiber bundle. Results and conclusions in this investigation can extend and perfect fiber bundle model in terms of plastic behavior.

Classification of expansive soils among problematic soils in the brazilian semiarid from artificial neural networks

The climatological and geomorphological conditions of the Brazilian semiarid region favor the formation of potentially expansive soils. The development of neural networks to identify and classify expansive soils in Pernambuco, and the need to export to soils across the semiarid region of Brazil is investigated in this study using a Multi-Layer Perceptron (backpropagation). The neural network was developed using 87 experimental data points, divided into three groups. The Training Group, consisting of 53 samples, using data inputs: sand percentage, clay percentage, plasticity index, activity index, and geological, pedological, and climatological classification. Selection Group, made up of 17 samples, was used to select the best network architecture, genetics algorithms formed of 7 inputs and 3 hidden nodes. The Test Group used 17 samples to evaluate the predictive accuracy of the expansion potential, obtaining an accuracy rate of 88,2%. This network was validated by applying it to 67 samples of problematic soils of the collapsible, expansive, and soft type from the Brazilian semiarid region, reaching an accuracy of 76,1%. Probabilistic Neural Networks were found to be efficient in evaluating the behavior of expansive soils, with the ability to deal with the absence of sample input data, demonstrating the ability to capture movement trends in the expansion of the soil surface, indicating the functions that introduce the effects of the composition potential on the expansion behavior, and determining the limit values of each of the input variables for the samples from the database used.

Thermodynamic modelling of gas hydrate dissociation conditions in porous medium in the presence of NaCl/methanol aqueous solution

AbstractDue to the growing significance of the existence of gas hydrates in natural media like the ocean floor/permafrost regions and the extraction of natural gas from hydrate reservoirs using thermodynamic hydrate inhibitors, investigating the dissociation of gas hydrates in porous media in the presence of inhibitors is crucial. This work examines a broad range of laboratory data on the dissociation conditions of gas hydrates in the porous mediums when salt/alcohol aqueous solutions are present. The temperature of gas hydrate dissociation in the presence of pure water is calculated using the van der Waals–Platteeuw solid solution theory. The water activity in the porous medium is then calculated by taking into account a number of variables, including the radius of the porous medium, molar volume, shape factor, wetting angle, and surface tension. The Pitzer and Margules activity coefficient models are used to determine the water activity in the presence of salt and alcohol, respectively. Lastly, the gas hydrate dissociation temperature in a porous medium in the presence of salt and/or alcohol aqueous solution is determined by combining Piereon's model with an enthalpy‐based correlation that was proposed by Azimi et al. The selected package can consistently correlate the gas hydrate dissociation conditions in a porous medium in the presence of alcohol or salt aqueous solution. The average absolute deviation (AAD) of 0.67 K for the whole data bank (90 experimental data points) shows the precision of the model.

An optimized hybrid finite element analyses - Artificial neural networks technique for estimating in-plane orthotropic mechanical properties of printed circuit boards

Explicitly modeling Printed Circuit Boards (PCBs) in Finite Element Analysis (FEA) is not practical due to the complex multi-component structure of PCBs. To overcome this complication, a PCB can be simplified and modeled as an orthotropic plate with equivalent mechanical properties that result in the same natural frequencies as the actual PCB. This research introduces an optimized hybrid technique combining FEA and Artificial Neural Networks (ANNs) to accurately estimate the equivalent in-plane orthotropic mechanical properties of PCBs. This study presents a systematic approach where natural frequencies obtained from FEA are used to train ANNs for predicting the equivalent representative mechanical properties. The research employs a rigorous optimization procedure involving various ANN configurations (i.e., different learning algorithms, activation functions, and number of hidden neurons) and training dataset sizes. To further ensure the reliability of the results, 10 cross-validation are carried out for each ANN configuration by employing dynamic data-splitting strategy, and all measures used for assessing the accuracy of the ANN predictions are based on averaged results for the 10 cross-validations. The accuracy of the ANN predictions is tested against both simulated and experimental data. The Mean Absolute Percentage Error (MAPE) is found to be about 4 % based on material properties against the simulated data, and about 1.2 % based on natural frequencies against the experimental data point. The results demonstrate superior predictive accuracy and efficiency compared to existing models, highlighting the potential of the proposed approach in advancing the reliability and performance of PCB mechanical property estimations.

Stress-strain modelling of circular concrete-filled FRP–steel composite tube columns under axial compression load

Concrete filled-circular steel tube (CFCST) columns, when externally confined with carbon or glass fiber-reinforced polymers (FRP) sheets and subjected to axial load, exhibit improved strength and ductility compared to unconfined cases. The mechanical properties of the confinement materials are crucial in determining the stress-strain relationship of the confined concrete. This study presents an in-depth analysis of the stress-strain behavior of FRP-confined CFST columns, based on data from 252 specimens. It examines a range of factors, including various infill concrete grades from 14.15 to 140.39 MPa, two types of carbon steel outer tubes with yield strengths (fy) from 226 to 466.5 MPa, and two types of FRP (CFRP and GFRP) with tensile strengths from 1260 to 4900 MPa. The complete axial stress-strain curve is divided into four phases according to a mathematical expression by Wu and Wei (2015): the elastic phase, nonlinear transition phase, linear softening phase, and residual phase. New formulas for ultimate stress, based on confinement stress, were proposed by Hassanin et al. (2023), while the ultimate strain was calculated using the classical formula by Richart et al. Peak stress and strain were determined through statistical linear regression analysis using SPSS software, based on 252 experimental data points and involved using a combined factor of steel contribution (Elsfco) and FRP contribution (Elffco). Eight specimens were specifically used to validate the models through Finite Element Method (FEM) simulations. The accuracy of the predicted analysis results was also assessed by comparing them to existing models. The evaluation showed that the models successfully simulated the complete stress-strain curve of FRP-wrapped CFST columns under axial load, producing satisfactory results. These four models provide reliable results for calculating ultimate stress, ultimate strain, peak stress, peak strain, and the complete stress-strain behavior of these columns.

Optimizing pervious concrete with machine learning: Predicting permeability and compressive strength using artificial neural networks

This study makes a significant contribution to the field of pervious concrete by using machine learning to innovatively predict both mechanical and hydraulic performance. Unlike existing methods that rely on labor-intensive trial-and-error experiments, our proposed approach leverages a multilayer perceptron network. To develop this approach, we compiled a comprehensive dataset comprising 271 sets and 3,252 experimental data points. Our methodology involved evaluating 22,246 network configurations, employing Monte Carlo cross-validation over 20 iterations, and using 4 training algorithms, resulting in a total of 1,779,680 training iterations. This results in an optimized model that integrates diverse mix design parameters, enabling accurate predictions of permeability and compressive strength even in the absence of experimental data, achieving R² values of 0.97 and 0.98, respectively. Sensitivity analyses validate the model's alignment with established principles of pervious concrete behavior. By demonstrating the efficacy of machine learning as a complementary tool for optimizing pervious concrete mix designs, this research not only addresses current methodological limitations but also lays the groundwork for more efficient and effective approaches in the field.