Tensile Strength Model Research Articles

Predictive Modeling and Experimental Validation for Assessing the Mechanical Properties of Cementitious Composites Made with Silica Fume and Ground Granulated Blast Furnace Slag

Using sustainable cement-based alternatives, such as secondary cementitious raw materials (SCMs), could be a viable option to decrease CO2 emissions resulting from cement production. Previously conducted studies to determine the optimal mix designs of concrete primarily focused on either experimental approaches or empirical modeling techniques. However, in these experimental approaches, few tests could be performed for optimization due to time restrictions and lack of resources, and empirical modeling methods cannot be relied on without external validation. The machine learning-based approaches are further characterized by certain shortcomings, including a smaller number of data points, a less robust connection among the controlling factors, and a lack of comparative analyses among machine learning models. Furthermore, the literature on predicting the performance of concrete utilizing binary SCMs (silica fume (SF) and ground granulated blast furnace slag (GGBS)) is not available. Therefore, to address these drawbacks, this research aimed to integrate ML-based models with experimental validations for accurate predictions of the compressive strength (CS) and tensile strength (TS) of concrete that includes SF and GGBS as SCMs. Three soft computing techniques, namely the ANN, ANFIS, and GEP methods, were used for prediction purposes. Eight major input parameters, including the W/B ratio, cement, GGBS, SF, coarse aggregates, fine aggregates, superplasticizer, and the age of the specimens, were considered for modeling. The validity of the established models was assessed by using external experimental validation criteria, statistical metrics, and performance measures. In addition, sensitivity and parametric analyses were performed. Based on statistical measures, the ANFIS models outperformed other models with higher correlation and lower statistical error values. However, the GEP models exhibited superior performance compared to ANFIS and ANN with respect to the closeness of the RMSE, MAE, RSE, and R2 values between the training, validation, and testing sets for both the CS and TS models. Experimental validation showed strong evidence for the applicability of the proposed models with an R2 of 0.88 and error percentages of less than 10%. Sensitivity and parametric investigations demonstrated that the input variables exhibited the patterns described in the experimental dataset and the available literature. Hence, the proposed models are accurate, have better prediction performance, and can be used for design purposes.

Performance evaluation of concrete made with plastic waste using multi-expression programming

The immense production of plastic waste due to its non-biodegradable nature has become a major issue for the world. Several researchers have recently tried to incorporate plastic waste in building materials, particularly as a substitute for cement in concrete, using conventional experimental testing. However, it is difficult to examine the optimal mix design in experimental investigations due to time and resource constraints. Therefore, this study aims to provide robust multi-expression programming (MEP) based predictive equations to evaluate the compressive strength (CS) and tensile strength (TS) of concrete containing plastic waste. Based on the literature, a comprehensive data record of 276 and 235 samples of the CS and TS of plastic concrete was generated for model development. The models' prediction capabilities were assessed by evaluating the various statistical indicators and comparing the results with a multi-linear regression (MLR) model. Furthermore, a sensitivity analysis was conducted to find out the contribution of each parameter to the CS and TS of plastic concrete. According to the statistical findings, the MEP model demonstrated higher efficacy in prediction, with an R2 value of 0.87 and 0.89 for the CS and TS models. In addition, MEP generates a simple mathematical formula, which can be employed as a design tool for estimating the CS and TS of plastic concrete. In sensitivity analysis, age demonstrated the highest sensitivity (24.8% and 31%), demonstrating its substantial impact on the model's outputs. Cement (17.63% and 17.3%) and plastic (17.4% and 15.3%) have similar contributions to the CS and TS. These results are consistent with previous research, highlighting the agreement between the results of this study and the literature. Therefore, this study can be employed for sustainable construction practices.

Recycled rubber wastes-based polymer composites with flame retardancy and electrical conductivity: Rational design, modeling and optimization

Polymer recycling techniques experience a maturity period of design and application. Rubbers comprise a high proportion of polymer wastes, highly flammable and impossible to re-melt. Polymer composites based on ground tire rubber (GTR) and ethylene-vinyl acetate copolymer (EVA) containing carbon black (CB) (1–50 phr), with variable EVA/GTR weight composition (10/90, 25/75, 50/50, 75/25 and 90/10), and processing temperature (Low: 100 °C and High: 200 °C) were designed applying Design of Experiments (DOE) approach of Optimal Design. The properties and performance features were experimentally evaluated. The tensile strength (TS) and elongation at break (EB) were optimized using Desirability Function (DF) approach. A wide fluidity window (Labeled POOR, GOOD, and EXCELLENT) and mechanical properties were observed. Overall, higher values of EB were assigned to samples processed at 200 °C. Cubic regression modeling and DF optimization of TS and EB indicated unlikely that one expect a TS ≥ 3 MPa, while EB values more than 500% were likely regardless of CB content for EVA-rich composites. The electrical properties of CB/EVA/GTR samples were examined by impedance spectroscopy technique. An interesting relationship was observed between the DC conductivity and the EVA/GTR ratio and processing temperature. GTR-rich samples showed much higher conductivity than EVA-dominated samples, attributed to the presence of CB in the rubber waste, which, together with the added CB, was able to create conduction paths for the transported electrons. Higher processing temperature of 200 °C improved dispersion of the added CB, i.e. a more even distribution of the conductive phase in the matrix. The uniform and evenly dispersed domains of particles were detected by SEM images for highly CB loaded composites. Surprisingly, 50/50 EVA/GTR composites were resilient against flame, while thermally stable ones in TGA measurements were highly CB loaded ones.

Optimization of welding parameters for BCTW-GIA single-pass welding using RSM

ABSTRACTBypass coupling triple-wire indirect arc (BCTW-GIA) welding technology was applied to single-pass welding for medium and thick plates. The regression models between process variables and target responses were built with response surface methodology (RSM) based on central composite design (CCD). The effect of significant process variables namely bypass current, groove gap, plate thickness, and welding speed on penetration-to-width ratio (P/W) of weld joint and tensile strength (TS) was evaluated. Guiding process parameters were determined with numerical optimization for BCTW-GIA single-pass welding of 8 mm, 10 mm, and 12 mm thickness steel plates. With the advice parameters, the average tensile strength of the weldments with three thickness were 558 MPa, 539 MPa, and 547 MPa. The true P/W of butt joints was also in desirable range. That the error between predicated value and experiment value was no more than 10% emphasized the positive effect of regression model of TS and P/W.

Machine Learning Approach to Predict Physical Properties of Polypropylene Composites: Application of MLR, DNN, and Random Forest to Industrial Data.

Manufacturing polypropylene (PP) composites to meet customers’ needs is difficult, time-consuming, and costly, owing to the ever-increasing diversity and complexity of the corresponding specifications and the trial-and-error method currently used to satisfy the required physical properties. To address this issue, we developed three models for predicting the physical properties of PP composites using three machine learning (ML) methods: multiple linear regression (MLR), deep neural network (DNN), and random forest (RF). Further, the industrial data of 811 recipes were acquired to verify the developed models. Data categorization was performed to account for the differences between data and the fact that different recipes require different materials. The three models were then deployed to predict the flexural strength (FS), melting index (MI), and tensile strength (TS) of the PP composites in nine case studies. The predictive performance results differed according to the physical properties of the composites. The FS and MI prediction models with MLR exhibited the highest R2 values of 0.9291 and 0.9406. The TS model with DNN exhibited the highest R2 value of 0.9587. The proposed models and study findings are useful for predicting the physical properties of PP composites for recipes and the development of new recipes with specific physical properties.

Investigating the correlation between soil tensile strength curve and soil water retention curve via modeling

Soil water retention curve (SWRC) is a crucial soil property required for solving many soil and water management problems. But, its direct measurement needs a lot of time, effort and money. The aim of this study was to develop pedotransfer functions (PTFs) for estimating water content through the van Genuchten (1980) model by employing tensile strength (TS) models. One hundred forty eight samples were gathered from five provinces in Iran. Bulk density, TS curve, SWRC and particle size distribution were measured. Four empirical TS models were fitted to the experimental soil mechanical data. Also, three physically based equations were used to estimate soil water content. In order to develop PTFs to estimate the parameters of van Genuchten (1980) model, artificial neural networks (ANNs) and regression (MLR) methods were used. In nine PTFs, the parameters of the empirical TS models and other soil properties were used as predictors for estimating SWRC. In developing the PTFs, ANNs were superior to MLR. Using the parameters of the TS models as predictors improved the estimation of water content between 2.8 and 6.9%. The SWRC was estimated better by using the parameters of the developed model of TS along with texture fractions and bulk density as predictors. The result showed the high capability of three physically based equations in the estimation of water content. Lu et al. equation had the highest accuracy in the SWRC estimation, in comparison with other physically based equations. The results showed the significance of TS in the estimation of SWRC.

EVALUATION OF FACTORS AFFECTING BARRIER, MECHANICAL AND OPTICAL PROPERTIES OF PECTIN‐BASED FILMS USING RESPONSE SURFACE METHODOLOGY

ABSTRACT Emulsion coatings were formulated and films were developed using pectin as the basic structural component. Preliminary experiments were carried out to determine the proper type and concentration of pectin, lipid and plasticizers in the film. The effects of pectin, beeswax and sorbitol concentration on water vapor permeability (WVP), mechanical properties and opacity of the films were evaluated using the response surface methodology. WVP increased by pectin and sorbitol concentration and was decreased by beeswax concentration. Mechanical properties were mainly affected by pectin and sorbitol concentration. Increasing the amount of pectin and decreasing the sorbitol concentration increased tensile strength (TS) and modulus of elasticity (EM), while elongation at break (EB) increased by increasing both pectin and sorbitol concentration. Beeswax was the most influential factor that affected opacity, which increased with increasing beeswax concentration. Models developed for WVP, EB, EM and opacity had high coefficient of multiple determination (R2) values (>0.87) and significant F values. The model for TS had a slightly lower R2 of 0.81.PRACTICAL APPLICATIONSThis research examined the preparation of pectin‐based edible films, providing an understanding of the main functionalities of these coatings. This film can help retain moisture and restrict its movement. Moisture levels in foods are critical for maintaining freshness, controlling microbial growth and providing texture. This film can control water activity, preventing either moisture loss or uptake. It can protect food from physical injuries. Since so many formulations were designed, based on the use of the film one can select each type of formulation that works best for the specific application. It can potentially limit fat migration, provide a barrier to gas, help to trap flavor and aroma, and carry and present antioxidants or antimicrobials. This article will be of value to anyone working with products where edible films have potential applications and particularly to technical personnel and product developers who wish to understand the potential of edible film and coating technology.

Prediction of mechanical properties in steel heat treatment process using neural networks

The present paper describes the application of a neural network technique for the prediction of tensile strength (TS) test results for steels heat treated using a batch heat treatment process. Industrial process data often contain outlying points, some of which can be spurious for a number of reasons. A data cleaning technique has been used to ensure that spurious data points are not present in the final neural model, which would otherwise hinder the model's representation of the true process. The effectiveness of this technique is demonstrated by comparison of the TS model trained on cleaned and uncleaned data. A model trained on cleaned data is generated for the prediction of TS in the form of an ensemble network, which was found to provide more reliable predictions and give a better representation of the degree of uncertainty in the network predictions. The performance of the model is evaluated from a metallurgical perspective. Application areas for the model are examined with particular attention being drawn to the need for caution when entering inputs into the neural model. An assessment of the model's ability to generalise to new treatment sites and new steel compositions is made, together with experimentation to determine the effect of measurement tolerances on the predicted values from the model.

Prediction of mechanical properties in steel heat treatment process using neural networks

The present paper describes the application of a neural network technique for the prediction of tensile strength (TS) test results for steels heat treated using a batch heat treatment process. Industrial process data often contain outlying points, some of which can be spurious for a number of reasons. A data cleaning technique has been used to ensure that spurious data points are not present in the final neural model, which would otherwise hinder the model's representation of the true process. The effectiveness of this technique is demonstrated by comparison of the TS model trained on cleaned and uncleaned data. A model trained on cleaned data is generated for the prediction of TS in the form of an ensemble network, which was found to provide more reliable predictions and give a better representation of the degree of uncertainty in the network predictions. The performance of the model is evaluated from a metallurgical perspective. Application areas for the model are examined with particular attention being drawn to the need for caution when entering inputs into the neural model. An assessment of the model's ability to generalise to new treatment sites and new steel compositions is made, together with experimentation to determine the effect of measurement tolerances on the predicted values from the model.