Prediction Of Strength Properties Research Articles

Comparative analysis of various machine learning algorithms to predict strength properties of sustainable green concrete containing waste foundry sand

The use of waste foundry sand (WFS) in concrete production has gained attention as an eco-friendly approach to waste reduction and enhancing cementitious materials. However, testing the impact of WFS in concrete through experiments is costly and time-consuming. Therefore, this study employs machine learning (ML) models, including support vector regression (SVR), decision tree (DT), and AdaBoost regressor (AR) ensemble model to predict concrete properties accurately. Moreover, SVR was employed in conjunction with three robust optimization algorithms: the firefly algorithm (FFA), particle swarm optimization (PSO), and grey wolf optimization (GWO), to construct hybrid models. Using 397 experimental data points for compressive strength (CS), 146 for elastic modulus (E), and 242 for split tensile strength (STS), the models were evaluated with statistical metrics and interpreted using the SHapley Additive exPlanation (SHAP) technique. The SVR-GWO hybrid model demonstrated exceptional accuracy in predicting waste foundry sand concrete (WFSC) strength characteristics. The SVR-GWO hybrid model exhibited correlation coefficient values (R) of 0.999 for CS and E, and 0.998 for STS. Age was found to be a significant factor influencing WFSC properties. The ensemble model (AR) also exhibited comparable prediction accuracy to the SVR-GWO model. In addition, SHAP analysis revealed an optimal content of input variables in the concrete mix. Overall, the hybrid and ensemble models showed exceptional prediction accuracy compared to individual models. The application of these sophisticated soft computing prediction techniques holds the potential to stimulate the widespread adoption of WFS in sustainable concrete production, thereby fostering waste reduction and bolstering the adoption of environmentally conscious construction practices.

Optimal boosting method of HPC concrete compressive and tensile strength prediction

AbstractThe evaluation of fly ash (FA) and micro‐silica (MS) effects on the mechanical properties of concrete at various ages prompts the search for efficient factors in forecasting the compressive strength (CS) and tensile strength (TS), which are extendable for future investigation as well as practical use. The main aim of this article is to overcome the complexity caused by nonlinearity, which is rooted in the relationship between input variables and outputs. Also, the nonlinearity is getting worse through the existence of admixtures. The Adaptive Boosting (ADA) approach was utilized in the related study as a hybrid model to provide an optimal relation between the ingredients and the mechanical strengths for evaluating the parameters most useful in predicting the CS and TS of high‐performance concrete. Furthermore, model boosting is applied using the starling murmuration optimization (SMO), termite queen algorithm (TQO), and gannet optimization algorithm (GOA) algorithms to reach the highest convergence. As a result of assessing the related models, the ADA‐SMO obtained a coefficient correlation of 0.9981 and 0.9825 for the predictions of CS and TS, respectively. Considering the adaptive framework provided to have the best compatibility with the complex physics of the problem, the ADA‐SMO earned the highest level of accuracy in estimating CS and TS among other hybrid models and was introduced as a trustable model in the prediction of strength properties.

Predicting Strength Properties of High-Performance Concrete Modified with Natural Aggregates and Ferroslag under Varied Curing Conditions

High-performance concrete (HPC) is obtained by inclusion of mineral admixtures like silica fumes and fly ash to the normal concrete. Consumption of natural materials such as sand, natural aggregates, and limestone produces environmental degradation. Similarly, industrial by-products such as fly ash, silica fume, and ferro slag need to be safely disposed of without negatively impacting the environment. The problem being addressed in this study is the need to develop high-performance concrete (HPC) that is durable and environmentally friendly. In recent years, the use of natural aggregates and ferro slag as partial replacements for traditional aggregates has gained attention as a sustainable alternative in the production of concrete. However, there is limited research on the effect of these materials on the mechanical and durability properties of HPC under varied curing conditions. In this current research, high-performance concrete of M60 grade with partial substitution of coarse aggregate with ferro slag aggregate was formed as per the recommendations of the American Concrete Institute with the inclusion of fly ash and silica fume. Natural coarse aggregate was partly substituted by ferro slag aggregate in proportions from 0% to 40%. Partial substitution of cement was made with 15% of fly ash and 10% of silica fumes. Specimens of normal concrete mix (MF0) and modified ferro slag aggregate concrete mix (MF20, MF30, and MF40) were prepared and subjected to acid test, sulphate test, and alternate wet and drying tests to assess the compressive strength of the concrete mixes. Central composite design (CCD) of RSM modelling was adopted to recommend a regression model to forecast the compressive strength of concrete under wetting drying test, acid test, and sulphate attack. Further, natural aggregate, ferro slag, and duration of curing were considered as basic variables to suggest the model. Regression models for response data were evaluated using analysis of variance (ANOVA) and Pareto charts. The results show that the mix MF30 (30% substitution of natural aggregate by ferro slag aggregate) had higher compressive strength. The residual compressive strength at 270 days under alternate wetting and drying, acid attack, and sulphate attack was obtained as 62 MPa, 62.50 MPa, and 66.50 MPa, respectively. Similarly, the percentage loss of weight was obtained as 12.92%, 12.22%, and 6.60% for alternate wetting and drying, acid attack, and sulphate attack, respectively. The findings of the analysis of variance (ANOVA) indicate that the most significant factors influencing the variables C S W D , C S A T , and C S S T are natural aggregate, ferro slag, and curing period. The regression models for C S W D , C S A T , and C S S T are extremely significant, as shown by the ANOVA and Pareto chart analyses.

PREDICTION OF THE PROPERTIES OF FINE-GRAINED CONCRETE BY THE DISSOCIATIVE-STEP OPTIMIZATION METHOD

The article is devoted to the problem of using ash and slag waste. The prediction of strength properties in different periods of hardening of fine-grained concrete was carried out by the dissociative-step optimization method. The prediction of strength properties in different periods of hardening of fine-grained concrete was carried out by the dissociative-step optimization method. It is shown that the required strength of fine-grained concrete on low-grade cement using ash and slag waste is provided only when it is combined with grinding for 1.5 hours.

Evolutionary Algorithm-Based Modeling of Split Tensile Strength of Foundry Sand-Based Concrete

Foundry sand (FS) is produced as a waste material by metal casting foundries. It is being utilized as an alternative to fine aggregates for developing sustainable concrete. In this paper, an artificial intelligence technique, i.e., gene expression programming (GEP) has been implemented to empirically formulate prediction models for split tensile strength (ST) of concrete containing FS. For this purpose, an extensive experimental database has been collated from the literature and split up into training, validation, and testing sets for modeling purposes. ST is modeled as a function of water-to-cement ratio, percentage of FS, and FS-to-cement content ratio. The reliability of the proposed expression is validated by conducting several statistical and parametric analyses. The modeling results depicted that the prediction model is robust and accurate with a high generalization capability. The availability of reliable formulation to predict strength properties can promote the utilization of foundry industry waste in the construction sector, promoting green construction and saving time and cost incurred during experimental testing.

Methodology to evaluate strength properties of steel by single instrumented indentation test

The instrumented indentation test (IIT) is an attractive non-destructive testing technique. Determining accurate strength properties of steel using IIT is still challenging. In this paper, a new methodology is proposed to acquire the yield and ultimate tensile strength from a single IIT. This method extracts true stress-strain curves from IIT results. Acquired stress-strain curves indicate that the initial yield stress is not repeatable. This is caused by the inhomogeneous deformation of IIT specimens. Based on the obtained true stress-stain curves, corresponding yield strength, and ultimate tensile strength are calculated through theoretical derivation. The results show that the strength has a convergent tendency. On basis of this phenomenon, the strength is determined with an extrapolating method. Finally, the strength properties of Q345R are investigated to verify the reliability of this method. It is found that the strength determined from IIT and conventional tensile tests shows good agreement. The proposed method is effective in predicting strength properties from a single instrumented indentation test.

A procedure for predicting strength properties using small punch test and finite element simulation

Developing a universal approach for acquiring yield strength and ultimate tensile strength by small punch test (SPT) is a long-standing challenge. In this paper, a methodology is proposed to obtain strength properties of bulk materials from SPT results. It involves extracting true stress–strain curves from SPT data using iterative finite element simulation. Acquired curves show that initial yield stress cannot be reproduced. This is attributed to the inhomogeneous deformation of SPT specimens. Finite element simulations were then conducted on tensile tests with the extracted true stress–strain curves to obtain strength. Results indicate that predicted strength shows a convergent tendency with the times of iterative finite element simulation. An approach is proposed to process the predicted strength, based on data analysis. The acquired strength properties are in good agreement with those obtained by standard tensile testing. This is an entirely novel procedure that predicts reliable tensile properties via a single SPT run. It can be employed with confidence to cases for which standard tensile testing is impractical.

Round robin exercise on ball indentation technique in India: Indian nuclear reactor materials

This paper presents outcome of round robin exercise on usage of ball indentation technique to predict strength properties of three different materials which are used in Indian nuclear reactors. The main objectives were to evolve a standardized procedure of determining the mechanical properties by the Ball Indentation technique and quantification of the variation in strength and fracture properties due to ageing through such tests. Standard uniaxial tensile tests were also carried out to quantify the differences between strength properties predicted by ball indentation and those determined using conventional tests. Three different materials studied were, carbon-manganese steel (Grade: SA 333Gr.6), stainless steel (SA312 Type 304LN) and zirconium alloy (Zr-2.5Nb). The carbon-manganese steel and stainless steel materials were drawn from extruded pipes while Zr-2.5Nb was drawn from pressure tubes, used in Indian Pressurized Heavy Water Reactors. Ball indentation tests were carried out on materials in as received and in aged conditions. The ageing was simulated artificially. The carbon-manganese steel and stainless steels were subjected to cold work while Zr-2.5Nb alloy was subjected to heat treatment at different temperatures with varying hold times and in some cases with charged hydrogen. The round robin exercise was conducted within different research centers of Department of Atomic Energy (DAE), India. This was a blind exercise in which all the conventional tests were carried out by a group (who was not involved in Ball Indentation tests) after the completion of ball indentation tests by participants.The paper presents the prediction of strength properties, using ball indentation, by different participants. The reasons of scatter in the results among the various participants and differences with respect to conventional test results are discussed in the paper.

Predictive models for determination of compressive and split-tensile strengths of steel slag aggregate concrete

The current study adopts the results of completed laboratory experiments for modelling the strength properties of steel slag aggregate concrete using artificial neural network (ANN) technique. Note worthily, the considered experiments reported that strength properties increased with increasing curing age. The variation of factors for building the network includes: ground granulated blast furnace slag (GGBS) as partial replacement for granite at 20, 40, 60, 80 and 100%; water-cement ratio (w/c) at 0.5, 0.55 and 0.6; curing age at 7, 14 and 28 days. Other factors, such as cement and sand were kept constant. The input data were trained, learned and validated using the feed-forward back propagation algorithm. From the various trial and errors performed, the optimal ANN model which yielded the minimum mean square error and maximum absolute variance was 6-10-2. Therefore, based on the high confidence level of the model predictions, the models are recommended for predicting strength properties of steel slag aggregate concrete that falls within the limit of this study.

Empirical correlations for predicting strength properties of rocks – United Arab Emirates

In United Arab Emirates (UAE) and the Arabian Peninsula, most of the rocks are sedimentary in nature and mainly consist of sandstone, mudstone and crystalline gypsum. The identification of rock properties is beneficial for the construction work and design projects. Unconfined compressive strength (UCS) is the most frequently used method and is usually determined from laboratory tests, among the different strength parameters. A study was undertaken to assess estimating strength parameters from empirical correlations of such rocks and to develop the governing predictive equations. In order to conduct this study, 420 soil samples were collected from various locations in the UAE and were tested for various observations including point load test (Is(50)) and ultrasonic velocity (USV) through its pulse velocity. The results indicated that the nomographs could predict well the unconfined compressive strength within ± 10% confidence interval for both Is(50) and USV. The accumulating experience over many years of rock testing in our laboratories and other geotechnical investigation laboratories in the area suggested that there exists an underlying trend that governs the strength characteristics of such rocks.

Prediction and experimental validation of composite strength by applying modified micromechanics for composites containing multiple distinct heterogeneities

Abstract The mechanical properties, such as strength and stiffness, of epoxy-based composites containing MWCNTs were experimentally and theoretically investigated. The classical analytic homogenization approach, called the Mori-Tanaka model, was firstly modified and reported to predict strength properties for composites containing multiple heterogeneities. In the modified Mori-Tanaka micromechanical strength modeling, the composites were considered as a two-phase simple model, as well as multiple heterogeneity case. The values obtained here were compared to experimentally measured data. The specimens reinforced with heterogeneities such as multi-walled carbon nanotubes (MWCNTs) were mainly fabricated and tested to measure the strength and stiffness of epoxy-based composites. When comparing the experimentally measured data of those composites with the predicted values obtained from the modified micromechanics models, it was confirmed that the developed approach successfully captures the effect of different types of heterogeneity on the resulting strength and stiffness of composites containing different geometrized nanofillers.

Empirical Correlations for Predicting Strength Properties of Rocks from P-Wave Velocity Under Different Degrees of Saturation

Determination of P-wave velocity (V p), which is closely related to intact rock properties both in laboratory and in situ conditions, is a non-destructive, easy and less complicated procedure. Due to these advantages, there is an increasing trend to predict the physico-mechanical properties of rocks from V p. By considering that no attempt on the estimation of mechanical properties of rocks from V p under different degrees of saturation has been made, in this study, it was aimed to correlate strength properties (uniaxial compressive and tensile strengths) with V p of various rock types under different degrees of saturation. For this purpose, fourteen different rock types were collected from several parts of Turkey and a comprehensive laboratory testing program was conducted. Experimental results indicated that strength and deformability properties of the rocks decreased with increasing degree of saturation, while V p showed increasing and decreasing trends depending on degree of saturation. Simple regression analysis results indicated that although prediction of the strength properties of rocks directly from V p at different degrees of saturation was possible, the equations developed would yield some under- or over-predictions. In the second stage of statistical analyses, a series of different prediction relationships were developed by using independent variables such as V p, degree of saturation and effective clay content (ECC). The statistical tests suggested that the resultant multivariate equations had very high prediction performances and were very useful tools to estimate the strength properties from V p determined at any degree of saturation. In addition, the comparisons between the theoretical Gassmann–Biot velocities, which were calculated at different degrees of saturation, and the experimental results suggest that the theoretical Gassmann–Biot velocities show inconsistencies with the experimental results obtained from the investigated rock types with high ECC. Therefore, it was concluded that the use of theoretical velocities is not suitable for rock types with high ECC.

DEM Model of Wheat Grains in Storage Considering the Effect of Moisture Content in Direct Shear Test

Discrete Element Method (DEM) modeling was conducted for predicting strength properties of stored wheat grains in different levels of moisture contents, to extend the knowledge of grain storage beyond current experimental studies in the future. The main features of agricultural and food materials that make them different from mineral materials are strong influence of Moisture Content (MC) on mechanical behavior. Published data on grain and bulk properties of wheat relevant to DEM modeling were reviewed by considering the effect of MC. The shape of grains was modeled by Multi Sphere Method (MSM) and the interaction between grains was represented by linear and nonlinear frictional elastic contact models. The effect of MC was considered in simulation through an innovative procedure. The initial test was performed to choose the best models to perform the simulation. Statistical comparisons with relevant experimental result were conducted on simulation data. It has been proved that the DEM is able to capture the variation of strength properties of wheat with MC of grains. It is observed the simplest shape of grain models would allow us to obtain quite closely prediction of wheat strength parameters. Also the linear elastic contact model has more capability in representing the form of strength properties variation with MC. This suggests that the modeling is a useful tool in the study of mechanical behavior of wheat and other cereal grains during storage processes as well as provision of data necessary in the future design of appropriate machinery and structure.

Development of a neural network programming module for predicting the strength properties of solid fuel

A method is considered for modeling the strength of solid fuel specimens used in structures for intensifying oil recovery. This method is based on artificial neural networks and makes it possible to predict strength properties with an accuracy up to 5% on the basis of data introduced into the program about solid fuel composition (percentage content of components, density) and production parameters (moisture content, temperature of the environment).

A technique for predicting strength properties of an aircraft wing

A technique for evaluating and predicting flexural stiffness of an aircraft wing in the process of operation based on measuring the first tone of flexural wing vibrations in flight is proposed.

Chaos and scaling of the main crack

We propose a generation model for the main crack surface profile and parameterization of the chaotic regime of crack development. Chaos parameters allow predicting strength properties and can be used for the informal theory of fracture.

HPC Strength Prediction Using Artificial Neural Network

An artificial neural network of the fuzzy-ARTMAP type was applied for predicting strength properties of high-performance concrete (HPC) mixes. Composition of HPC was assumed simplified, as a mixture of six components (cement, silica, superplasticizer, water, fine aggregate, and coarse aggregate). The 28-day compressive strength value was considered as the only aim of the prediction. Data on about 340 mixes were taken from various recent publications. The system was trained based on 200 training pairs chosen randomly from the data set, and then tested using remaining 140 examples. A significant enough correlation between the actual strength values and the values predicted by the neural network was observed. Obtained results suggest that the problem of concrete properties prediction can be effectively modeled in a neural system, in spite of data complexity, incompleteness, and incoherence. It is demonstrated that the approach can be used in multicriterial search for optimal concrete mixes.

Strength Properties of Cotton Blend Yarns

This paper discusses two methods of predicting strength properties of ring spun cotton blend yams produced using a normal technological process. Another facet of the research is the application of fiber parameters obtained on a high volume instrument ( HVI ) to the predictions. Fiber strength as measured by breaking individual fibers is higher than that measured on the HVI line using the bundle method, and the mean and mean ratio of these values is 1.34. The experimental results and the strength predictions are compared.

A New Approach for Predicting Strength Properties of Yarn

We present a new approach to yarn characterization and yarn tensile response based on fiber parameters such as strength and strain-at-break, length, and fineness. Yarn characterization is concerned with twist, linear density, and the ratio of experimental yarn unevenness to the Martindale's limit characteristic for spinning mills. Experimental strength results are compared with predicted ones on the basis of theory.

基本物性による手すきシートの強度的性質の評価 重回帰分析による実用的拡張Ｃｌａｒｋ式の決定

It is useful to have some practical formulas describing a particular strength property of paper as a function of a few easily measurable fundamental sheet and fiber properties. Such formulas will be helpful for designing paper and predicting strength properties of paper before it is made.In this study, the author tried to determine statistically optimal formulas for tensile breaking length, MIT double folds, burst index and tear index of handsheets based on the extended Clark type formula.First, eighteen kinds of abaca handsheets were prepared with varying fiber length, beating degree, fiber strength and wet pressing pressure. Multiple regression analysis and Akaike Information Criterion (AIC) were applied to a linear function given by taking logarithm of the extended Clark type formula so as to construct the optimal extended Clark formula for each strength property of abaca as a function of weighted average fiber length, bulk, zero-span breaking length and Z-directional tensile strength. Correlation coefficient of over 0.97 between observed and calculated values was found for each strength property.Secondarily, modifications of the formulas for abaca by introduction of fiber coarseness as an additional fundamental property were carried out so that the formulas would be applicable to handsheets made of other fibers than abaca fiber. As the result, the generalized formulas for breaking length and burst index were obtained, both of which showed correlation coefficients of over 0.94 between observed and calculated values.The formulas for abaca and the generalized formulas are expected to be used as the Paper Design Functions.