Study of Applying Macroevolutionary Genetic Programming to Concrete Strength Estimation

This technical note is aimed at demonstrating a mixture-proportioning problem, which uses the macroevolutionary algorithm (MA) combined with genetic programming (GP) to estimate the compressive strength of high-performance concrete (HPC). GP provides system identification in a transparent and structured way; a fittest function type of experimental results will be obtained automatically from this method. MA is a new concept of species evolution at the higher level. It could improve the capability of searching global optima and avoid premature convergence during the selection process of GP. In the study, two appropriate functions have been found to represent the relationships between different ingredients and the compressive strength. The results show that this new model, MAGP, is better than the traditional proportional selection GP for HPC strength estimation.     

Genetic-Fuzzy Approach for Modeling Complex Systems with an Example Application in Masonry Bond Strength Prediction

A genetic-fuzzy learning from examples (GFLFE) approach is presented for determining fuzzy rule bases generated from input/output data sets. The method is less computationally intensive than existing fuzzy rule base learning algorithms as the optimization variables are limited to the membership function widths of a single rule, which is equal to the number of input variables to the fuzzy rule base. This is accomplished by primary width optimization of a fuzzy learning from examples algorithm. The approach is demonstrated by a case study in masonry bond strength prediction. This example is appropriate as theoretical models to predict masonry bond strength are not available. The GFLFE method is compared to a similar learning method using constrained nonlinear optimization. The writers’ results indicate that the use of a genetic optimization strategy as opposed to constrained nonlinear optimization provides significant improvement in the fuzzy rule base as indicated by a reduced fitness (objective) function and reduced root-mean-squared error of an evaluation data set.     

Testing of Strength of Recycled Waste Concrete and Its Applicability

This paper gives results of studies undertaken to assess suitability of construction demolition as coarse aggregate in new concrete production. Three sets of concrete materials considered are fresh concrete (FCM), waste concrete (WCM), and waste concrete strengthened with admixtures (SWCM). Various mixes were prepared for carrying out the research by varying the proportions of cement, sand, and aggregates. All mixes were designed for characteristic strength (fck) of M20. The compressive strength of concretes was tested in laboratory after 3, 7, and 28 days. The specimens used for testing include cubes, cylinders, and flexural beams. The influence of admixtures on the strength of waste concrete was examined. The compressive strengths of FCM, WCM, and SWCM are compared and the results show that there is not much difference in the strengths of FCM and SWCM after 28 days. For this reason, this study recommends the recycling of waste concrete as an aggregate material in the production of new concrete.     

Parameters Controlling Tensile and Compressive Strength of Artificially Cemented Sand

The enhancement of local soils with cement for the construction of stabilized pavement bases, canal lining, and support layer for shallow foundations shows great economical and environmental advantages, avoiding the use of borrow materials from elsewhere, as well as the need of a spoil area. The present research aims to quantify the influence of the amount of cement, the porosity, and the voids/cement ratio in the assessment of unconfined compressive strength (qu) and splitting tensile strength (qt) of an artificially cemented sand, as well as in the evaluation of qt/qu relationship. A program of splitting tensile tests and unconfined compression tests considering three distinct voids ratio and seven cement contents, varying from 1 to 12%, was carried out in the present study. The results show that a power function adapts well qt and qu values with increasing cement content and with reducing porosity of the compacted mixture. The voids/cement ratio is demonstrated to be an appropriate parameter to assess both qt and qu of the sand-cement mixture studied. Finally, the qt/qu relationship is unique for the sand-cement studied, being independent of the voids/cement ratio.     

Effect of Wetting on Unconfined Compressive Strength of Cemented Sands

A weakly cemented sand and gravel has been partly or entirely used in the construction of earth structures such as dams and retaining walls. Such cemented soils that are usually highly permeable can undergo repetitive wetting and drying during curing due to temporary rainfall or a change in the groundwater table. In this study, weakly cemented sand specimens with four different cement ratios were compacted at optimum water content and cured for 28 days. When the cemented sand specimens were exposed to repetitive wetting and drying during curing, their 28-day unconfined compressive strength was evaluated. Wetting for one day on the last day was found to decrease the unconfined compressive strength of cemented sand, whereas wetting for one day in the middle of curing resulted in an increase in strength. The strength reduction due to wetting on the last day decreases as the cement ratio increases. For a specimen under repetitive wetting and drying over 28-day curing, the strength increases as the number of wetting increases up to three cycles. After three cycles of wetting and drying, the strength either becomes constant or slightly decreases due to insufficient water for hydration and/or washing cementitious materials.     

Prediction of Sewer Condition Grade Using Support Vector Machines

Assessing the condition of sewer networks is an important asset management approach. However, because of high inspection costs and limited budget, only a small proportion of sewer systems may be inspected. Tools are therefore required to help target inspection efforts and to extract maximum value from the condition data collected. Owing to the difficulty in modeling the complexities of sewer condition deterioration, there has been interest in the application of artificial intelligence-based techniques such as artificial neural networks to develop models that can infer an unknown structural condition based on data from sewers that have been inspected. To this end, this study investigates the use of support vector machine (SVM) models to predict the condition of sewers. The results of model testing showed that the SVM achieves good predictive performance. With access to a representative set of training data, the SVM modeling approach can therefore be used to allocate a condition grade to sewer assets with reasonable confidence and thus identify high risk sewer assets for subsequent inspection.     

Prediction of the Failure Time of Glass Fiber Reinforced Plastic Reinforced Concrete Beams under Fire Conditions

A model is proposed to predict the time to failure of reinforced concrete beams in a fire. The model is developed specifically to predict the lifetime of beams reinforced with glass fiber reinforced plastic rebar, but is applicable to beams with any form of reinforcement. The model is based on the calculations for flexural capacity and shear capacity of beams embedded within ACI design codes where time and temperature dependent values for rebar modulus and strength and concrete strength replace the static design values. The base equations are modified to remove safety factors and where necessary the temperature induced reductions in strength for concrete and steel are derived using the equations presented by EUROCODE 2. In order to validate the model it was used to predict the failure times of steel rebar reinforced beams that had been documented in the literature. There was excellent agreement between the model and the reported lifetimes for these conventional beams. The model was applied to predict the lifetimes of two beams that had been manufactured and tested for destruction in a fire by the research group. The model predicted that the failure mode of the beams would be because of rebar rupture as opposed to the design condition of concrete crushing and this was confirmed by the experimental test results. The model provided reasonable agreement with experimental results with a lifetime of 108?min predicted based on flexural failure and 94 and 128?min observed in the experiments.     

OCR Prediction Using Support Vector Machine Based on Piezocone Data

The determination of the overconsolidation ratio (OCR) of clay deposits is an important task in geotechnical engineering practice. This paper examines the potential of a support vector machine (SVM) for predicting the OCR of clays from piezocone penetration test data. SVM is a statistical learning theory based on a structural risk minimization principle that minimizes both error and weight terms. The five input variables used for the SVM model for prediction of OCR are the corrected cone resistance (qt), vertical total stress (σv), hydrostatic pore pressure (u0), pore pressure at the cone tip (u1), and the pore pressure just above the cone base (u2). Sensitivity analysis has been performed to investigate the relative importance of each of the input parameters. From the sensitivity analysis, it is clear that qt=primary in situ data influenced by OCR followed by σv, u0, u2, and u1. Comparison between SVM and some of the traditional interpretation methods is also presented. The results of this study have shown that the SVM approach has the potential to be a practical tool for determination of OCR.     

Variability of the Compressive Strength of Parallel Strand Lumber

Measurement of the compressive strength of parallel strand lumber (PSL) is conducted on specimens of varying size with nominally identical mesostructure. The mean of the compressive strength is found to vary inversely with the specimen size, and the coefficient of variation of the strength is found to decrease with increasing specimen size, and to be smaller than the coefficient of variation of strength for solid lumber. The correlation length of the compressive strength is approximately 0.5 m, and this correlation length leads to significant specimen-to-specimen variation in mean strength. A computational model is developed that includes the following properties of the PSL mesostructure: the strand length, the grain angle, the elastic constants, and the parameters of the Tsai-Hill failure surface. The computational model predicts the mean strength and coefficient of variation reasonably well, and predicts the correct form of correlation decay, but overpredicts the correlation length for compressive strength, likely because of sensitivity to the distribution of strand length used in the model. The estimates of the statistics of the PSL compressive strength are useful for reliability analysis of PSL structures, and the computational model, although still in need of further development, can be used in evaluating the effect of mesostructural parameters on PSL compressive strength.     

Techniques for Predicting Cracking Pattern of Masonry Wallet Using Artificial Neural Networks and Cellular Automata

This paper introduces innovative artificial intelligent techniques for directly predicting the cracking patterns of masonry wallets, subjected to vertical loading. The von Neumann neighborhood model and the Moore neighborhood model of cellular automata (CA) are used to establish the CA numerical model for masonry wallets. Two new methods—(1) the modified initial value method and (2) the virtual wall panel method—that assist the CA model are introduced to describe the property of masonry wallets. For practical purposes, techniques for the analysis of wallets whose bed courses have different angles with the horizontal bottom edges are also introduced. In this study, two criteria are used to match zone similarity between a “base wallet” and any new “unseen” wallets. This zone similarity information is used to predict the cracks in unseen wallets. This study also uses a back-propagation neural network for predicting the cracking pattern of a wallet based on the proposed CA model of the wallet and some data of recorded cracking at zones. These techniques, once validated on a number of unseen wallets, can provide practical innovative tool for analyzing structural behavior and also help to reduce the number of expensive laboratory test samples.     

Evaluation of Softened Truss Model for Strength Prediction of Reinforced Concrete Squat Walls

This paper evaluates the softened truss model and the softened strut-and-tie model for predicting shear strength of reinforced concrete squat walls. The prediction accuracy of analytical solutions is examined using the experimental data of 62 test shear walls available in the literature. It was found that the analytical solutions, which utilize the softening laws of cracked reinforced concrete under compression, can yield better estimations of shear strength. Further, the state of stresses in the web of a squat wall may be better assumed to be concentrated rather than uniformly distributed. The assumption of uniform distribution of stress of the softened truss model for squat walls causes some drawbacks. The upper bound solution of the softened truss model is found to generate unreasonably large horizontal clamping stresses, whereas the estimation of the lower bound solution is governed mainly by the yield of reinforcement, which is not the actual failure behavior of squat walls.     

Effect of Contact Pressure on Bond Strength of Fiber-Reinforced Polymer to Concrete

In this technical note, the importance of contact pressure (0.03 N/mm2) during curing of adhesive between fiber reinforced polymer (FRP) and concrete is addressed. The shortcoming of fast-curing epoxy resin is pointed out. Different pressures and an ordinary epoxy resin were chosen to assess the effectiveness of contact pressure on FRP-to-concrete bond strength. The test results showed that the bond quality could be significantly improved by exerting a contact pressure ≥ 0.01 N/mm2. A simple and easy site-operation method for exerting contact pressure is also introduced.     

Conceptual Model for Prediction of FRP-Concrete Bond Strength under Moisture Cycles

Fiber-reinforced polymer (FRP) retrofit systems for concrete structural members such as beams, columns, slabs, and bridge decks have become increasingly popular as a result of extensive studies on short-term debonding behavior. Nevertheless, long-term performance and durability issues regarding debonding behavior in such strengthening systems still remain largely uncertain and unanswered. Because of its composite nature, the effectiveness of the strengthening system depends on the properties of the interfaces between the three constituent materials; namely, concrete, epoxy, and FRP. Certain factors, including those related to environmental exposures, can cause degradation of the interface properties during service life. This is particularly critical when predicting service life and planning maintenance of FRP-strengthened concrete structures. In this study, effect of moisture on an FRP-concrete bond system is characterized by means of the tri-layer fracture toughness, which can be obtained experimentally from peel and shear fracture tests. Fracture specimens were conditioned under various durations and numbers of wet-dry cycles at room temperature and 50°C. An irreversible weakening in bond strength was observed in fracture specimens under moisture cyclic condition. A conceptual model is developed based on the experimental results of the fracture specimens under variable cyclic moisture conditions for the bond strength prediction of the FRP-concrete bond system. A numerical study of a precracked FRP-strengthened reinforced concrete beam is then performed to show potential application of the proposed predictive model.     

Influence of Portland Cement Type on Unconfined Compressive Strength and Linear Expansion of Cement-Stabilized Phosphogypsum

This technical note summarizes the results of a laboratory-testing program aimed at evaluating the engineering properties of cement-stabilized phosphogypsum mixtures for road base and subbase construction. Phosphogypsum is a solid byproduct of the production of phosphoric acid, a major constituent of many fertilizers that has chemical and radioactive properties may cause environmental problems. For every ton of phosphoric acid produced, approximately 5.0 tons of phosphogypsum are generated. This magnifies the problem of dealing with growing phosphogypsum stockpiles. The research program described herein, covered the physical characterization of phosphogypsum, and tests that uncovered the influence of cement type and content, curing time, and compaction energy on its unconfined compressive strength and expansion. The laboratory results indicate that cement-stabilized phosphogypsum mixtures have potential applications as road base and subbase materials.     

Prediction of Soil Composition from CPT Data Using General Regression Neural Network

Soil type is typically inferred from the information collected during a cone penetration test (CPT) using one of the many available soil classification methods. In this study, a general regression neural network (GRNN) was developed for predicting soil composition from CPT data. Measured values of cone resistance and sleeve friction obtained from CPT soundings, together with grain-size distribution results of soil samples retrieved from adjacent standard penetration test boreholes, were used to train and test the network. The trained GRNN model was tested by presenting it with new, previously unseen CPT data, and the model predictions were compared with the reference particle-size distribution and the results of two existing CPT soil classification methods. The profiles of soil composition estimated by the GRNN generally compare very well with the actual grain-size distribution profiles, and overall the neural network had an 86% success rate at classifying soils as coarse grained or fine grained.     

Dynamic Prediction of Project Success Using Artificial Intelligence

The purpose of construction management is to successfully accomplish projects, which requires a continuous monitoring and control procedure. To dynamically predict project success, this research proposes an evolutionary project success prediction model (EPSPM). The model is developed based on a hybrid approach that fuses genetic algorithms (GAs), fuzzy logic (FL), and neural networks (NNs). In EPSPM, GAs are primarily used for optimization, FL for approximate reasoning, and NNs for input-output mapping. Furthermore, the model integrates the process of continuous assessment of project performance to dynamically select factors that influence project success. The validation results show that the proposed EPSPM, driven by a hybrid artificial intelligence technique, could be used as an intelligent decision support system, for project managers, to control projects in a real time base.     

Bond Strength of Fiber Reinforced Polymer Rebars in Normal Strength Concrete

The bond behavior of reinforcing bars in concrete is a critical issue in the design of reinforced concrete structures. This study focuses on the bond strength of fiber reinforced polymer (FRP) rebars in normal strength concrete. Four different types of rebars were tested using the pullout method: aramid FRP (AFRP); carbon FRP (CFRP); glass FRP (GFRP), and steel. This involved a total of 151 specimens containing 6, 8, 10, 16, and 19?mm rebars embedded in a 203?mm concrete cube. The test embedment lengths were five, seven, and nine times the rebar diameter (db). For each rebar, the test results include the bond stress–slip response and the mode of failure. The test results showed that the bond strength of an FRP rebar is, on average, 40–100% the bond strength on a steel rebar for pullout failure mode. Based on this research, a proposal for the average bond strength of straight FRP rebars in normal strength concrete is made, which verifies an existing bond strength relationship (GFRP) and extends its application to AFRP and CFRP. It is an expression that is a function of the rebar diameter, and the concrete compressive strength.     

Quantifying the Effect of Rock Strength Criteria on Minimum Drilling Mud Weight Prediction Using Polyaxial Rock Strength Test Data

In engineering practice, a linear poroelasticity stress model in combination with a rock strength criterion is commonly used to determine a minimum mud weight for stable well drilling. Rock strength criterion therefore plays a key role in minimum mud weight prediction. There are a variety of rock strength criteria available in the literature. It is well known that all those criteria fall into two categories: intermediate principal stress dependent (σ2 dependent) criteria and intermediate principal stress independent (σ2 independent) criteria. To identify if a specific rock failure is σ2 dependent or σ2 independent, a polyaxial (true triaxial) rock strength test is essential. Similarly, to study the effect of rock strength criteria on wellbore stability and minimum drilling mud weight prediction, polyaxial rock strength test data are most useful. In this paper, we present a systematic approach to quantify the effect of three most commonly used rock strength criteria on minimum drilling mud weight prediction using polyaxial rock strength test data for Yuubari shale and Dunham dolomite.     

Prediction Models for Debonding Failure Loads of Carbon Fiber Reinforced Polymer Retrofitted Reinforced Concrete Beams

This study focuses on debonding failure in reinforced concrete beams with carbon fiber reinforced polymer composite bonded on the soffit using the wet lay-up method. An experimental study, which involved 26 tests, was carried out. The experiments showed two failure modes: Intermediate span debond and end debond. The first failure is the result of the high bond stress near the tip of a flexure-shear crack, whereas the second type of failure is due to the high shear stress developed in the weakest concrete layer at the tension reinforcement level. The experiments have shown that U-straps can be effective in preventing intermediate span and end debond. Based on experimental observations, two simple and practical theoretical models were developed and verified with the experimental data, together with a large database of other existing tests.     

Effect of Severe Environmental Exposures on CFRP Wrapped Concrete Columns

Deterioration of concrete structures caused by corrosion of reinforcing steel, aging, and weathering is a major problem in harsh environments such as coastal areas and cold regions. In addition, a hot environment, such as in the Arabian Gulf, is recognized as one of the most severe and aggressive environments that affects concrete durability. The purpose of this study is to investigate the effectiveness of strengthening plain concrete cylinders, subjected to extreme temperature variations, by wrapping with two layers of unidirectional carbon fiber-reinforced polymer (CFRP) sheets. Thirty-six plain concrete cylinders (150×300?mm) were tested. Nine specimens served as unstrengthened controls and the remaining cylinders were strengthened with two layers of CFRP sheets. Cylinders were subjected to high temperatures (45°C), to heating and cooling cycles (23 to 45°C), and to prolonged heat exposure (45°C). Some of the cylinders that were subjected to heating and cooling, were later subjected to freezing and thawing cycles, while others were submerged in fresh water or salt water. The specimens were loaded to failure under uniaxial compressive load and the axial and lateral deformations were monitored. High temperature exposure was not found to decrease the strength of the wrapped concrete cylinders.