Digital Vision Based Concrete Compressive Strength Evaluating Model Using Deep Convolutional Neural Network

Compressive strength of concrete is a significant factor to assess building structure health and safety.Therefore,various methods have been developed to evaluate the compressive strength of concrete structures.However,previous methods have several challenges in costly,time-consuming,and unsafety.To address these drawbacks,this paper proposed a digital vision based concrete compressive strength evaluating model using deep convolutional neural network(DCNN).The proposed model presented an alternative approach to evaluating the concrete strength and contributed to improving efficiency and accuracy.The model was developed with 4,000 digital images and 61,996 images extracted from video recordings collected from concrete samples.The experimental results indicated a root mean square error(RMSE)value of 3.56(MPa),demonstrating a strong feasibility that the proposed model can be utilized to predict the concrete strength with digital images of their surfaces and advantages to overcome the previous limitations.This experiment contributed to provide the basis that could be extended to future research with image analysis technique and artificial neural network in the diagnosis of concrete building structures.

Predicting Concrete Compressive Strength Using Deep Convolutional Neural Network Based on Image Characteristics

In this study,we examined the efficacy of a deep convolutional neural network(DCNN)in recognizing concrete surface images and predicting the compressive strength of concrete.A digital single-lens reflex(DSLR)camera and microscope were simultaneously used to obtain concrete surface images used as the input data for the DCNN.Thereafter,training,validation,and testing of the DCNNs were performed based on the DSLR camera and microscope image data.Results of the analysis indicated that the DCNN employing DSLR image data achieved a relatively higher accuracy.The accuracy of the DSLR-derived image data was attributed to the relatively wider range of the DSLR camera,which was beneficial for extracting a larger number of features.Moreover,the DSLR camera procured more realistic images than the microscope.Thus,when the compressive strength of concrete was evaluated using the DCNN employing a DSLR camera,time and cost were reduced,whereas the usefulness increased.Furthermore,an indirect comparison of the accuracy of the DCNN with that of existing non-destructive methods for evaluating the strength of concrete proved the reliability of DCNN-derived concrete strength predictions.In addition,it was determined that the DCNN used for concrete strength evaluations in this study can be further expanded to detect and evaluate various deteriorative factors that affect the durability of structures,such as salt damage,carbonation,sulfation,corrosion,and freezing-thawing.

Artificial Neural Network(ANN)Approach for Predicting Concrete Compressive Strength by SonReb

The compressive strength of concrete is one of most important mechanical parameters in the performance assessment of existing reinforced concrete structures.According to various international codes,core samples are drilled and tested to obtain the concrete compressive strengths.Non-destructive testing is an important alternative when destructive testing is not feasible without damaging the structure.The commonly used non-destructive testing(NDT)methods to estimate the in-situ values include the Rebound hammer test and the Ultrasonic Pulse Velocity test.The poor reliability of these tests due to different aspects could be partially contrasted by using both methods together,as proposed.in the SonReb method.There are three techniques that are commonly used to predict the compressive strength of concrete based on the SonReb measurements:computational modeling,artificial intelligence,and parametric multi-variable regression models.In a previous study the accuracy of the correlation formulas deduced from the last technique has been investigated in comparison with the effective compressive strengths based on destructive test results on core drilled in adjacent locations.The aim of this study is to verify the accuracy of Artificial Neural Approach comparing the estimated compressive strengths based on NDT measured parameters with the same effective compressive strengths.The comparisons show the best performance of ANN approach.

Effect of Steel Fiber on Concrete’s Compressive Strength

The general goal of this research is to investigate whether steel fiber has a significant “positive” or “negative” influence on concrete compressive strength, as well as the optimal steel fiber ratio that delivers best result. Manually, cement, fine aggregates, coarse aggregates, steel fibers, and water were mixed together properly. A slump test was carried on the mixed concrete. After determining the workability, the mixed concrete was poured into cubes dimension 150 mm × 150 mm × 150 mm and left for 24 hours. After 24 hours, the samples were removed from the mold and placed in a water tank to cure for 7 to 28 days. The cube was tested for compressive and flexural strength in a universal testing machine after the samples had cured for the required 7 - 28 days. This study focuses on how to obtain high strength concrete using with steel fiber in the Conventional mix ratio to enhance concrete strength. Concrete reinforcement using steel fibers alters the characteristics of the concrete, allowing it to withstand fracture and hence improve its mechanical qualities. This study reports on an experimental study that reveals the effect of steel fiber on concrete compressive strength and the optimal steel fiber ratio that produces the best results. Steel fiber reinforcing improved the compressive strength of concrete. The average compressive strength of normal M25 concrete with 0% steel fibers and curing ages of 7 and 28 days was determined to be 22.97 N/mm2 and 25.78 N/mm2, respectively. The steel fibers are then added in various concentrations, such as 1%, 2%, and 3%, with aspect ratios of 70. The compressive strength of concrete with 1%, 2%, and 3% steel fiber with an aspect ratio of 70 was examined at 7 days and found to be 23.96, 24.80, and 26.14 N/mm2 correspondingly.

Use of Plant-Based Accelerator to Enhance Rate of Gain of Strength of Kenyan Blended Cement

Concrete is the most widely used construction material in the world. The situation in the country is not an exception as most of the infrastructures in Kenya such as buildings, bridges, concrete drainage among others, are constructed using concrete. Sadly, the failure of buildings and other concrete structures is very common in Kenya. Blended Portland cement type 32.5 N/mm2 is the most widely used concrete binder material and is found in all parts of the country. Despite blended cement CEM 32.5 being the most commonly used cement type in construction industry in Kenya and most developing countries as a result of its low price and availability locally, its strength gain has been proven to be lower compared to when other types of cement are used due to quantity of pozzolanic material added to the blend. This paper outlines findings of an experimental investigation on the use of cypress tree extract as an accelerator to enhance rate of gain of strength on Kenyan blended cements. Six different blended cement brands locally available were used during the study. Cement chemical analysis was done using X-ray diffraction method while for the cypress extract, Atomic Absorption Spectrometer machine was used. Physical and mechanical properties were checked based on the British standards. The generation of the concrete mix design was done using the British DOE method and concrete was tested for the compressive strength at 7, 14, 21, 28, 56 and 90 days. It was observed that 15% dosage of the extract expressed as a mass percentage of the cement content gives the most improved compressive strength of concrete, 10.4% at 7 days and 9.5% at 28 days hence the optimum. It was further noted that when Cypress tree extract is used as an accelerator in the mix, the blended cement concrete achieves the design strength at 27 days saving 10 days of the project duration compared to when no accelerator is used while the ultimate strength is achieved at 67 days. The study therefore recommends the use of the cypress tree bark extract at a dosage of 15%, by mass, of the cement content as an accelerator when the structure is to be loaded at 28 days and waiting up to 39 days before loading the structure if no accelerator is used for blended cement concrete.

Mechanical Properties and ITZ Microstructure of Recycled Aggregate Concrete Using Carbonated Recycled Coarse Aggregate

The effect of carbonation treatment and mixing method on the mechanical properties and interfacial transition zone（ITZ） properties of recycled aggregate concrete（RAC） was investigated. Properties of recycled concrete aggregate（RCA） were tested firstly. Then, five types of concretes were made and slump of fresh concrete was measured immediately after mixing. Compressive strength and splitting tensile strength of hardened concrete were measured at 28 d. Meanwhile, the microstructure of RAC was analyzed by backscattered electron（BSE） image. It was found that the water absorption ratio of carbonated recycled concrete aggregate（CRCA） was much lower when compared to the untreated RCA. Comparatively, the apparent density of CRCA was not significantly modified. The concrete strength results indicate that the mix CRAC-2 prepared with CRCA by adopting two-stage mixing approach shows the highest compressive strength value compared to the other mixes. The microstructural analysis demonstrate that the mix CRAC-2 has a much denser old ITZ than the untreated RAC because of the chemical reaction between CO2 and the hydration products of RCA. This study confirms that the ITZ microstructure of RAC can be efficiently modified by carbonation treatment of RCA and encourages broadening the application of construction and demolition wastes.

Performance Degradation of the Repeated Recycled Aggregate Concrete with 70% Replacement of Three-generation Recycled Coarse Aggregate

The feasibility of using different generations recycled coarse aggregate（RCA） on structural concrete was fully evaluated by studying the performance of the recycled coarse aggregates and their corresponding concretes, the different generations of RCA were recycled by following the repeated mode of ‘concrete-waste concrete-coarse aggregate-concrete＇. Moreover, the focus was on ‘three generations＇ of repeated RCAs, the RCA was produced by crushing and regenerating the artificial accelerated degraded concrete, the process was designed to follow the nature degradation of the concrete with a coupling action of accelerated carbonation and bending load. The properties of x-generation（x=1, 2 or 3） of repeated RCA were systematically investigated and the compressive and splitting tensile strengths of relating structural concretes（with 70% replacement of x-generation of RCA） were studied accordingly. The results show a competent compressive and splitting tensile strength of 30 MPa at 28 th day of structural concretes with all generations of repeated RAC. And the gradual degraded performance of the repeated RCAs was observed with an increased numbers of repetition（1〉2〉3 generations）, the overall performances of all repeated RCAs fulfill the Class Ⅲ according to Chinese Standards GB25177-2010. Our gained insight demonstrates a feasibility of using at least 3 generations of repeated RCA for the production of normal structural concrete.

A Simple Mix Proportion Design Method Based on Frost Durability for Recycled High Performance Concrete Using Fully Coarse Recycled Aggregate

Durability design of recycled high performance concrete（RHPC） is fundamental for improving the use rate and level of concrete waste as coarse recycled aggregate（CRA）. We discussed a frostdurability-based mix proportion design method for RHPC using 100 % CRA and natural sand. Five groups of RHPC mixes with five strength grades（40, 50, 60, 70 and 80 MPa） were produced using CRA with four quality classes, and their workability, 28 d compressive strengths and frost resistances（measured by the compressive strength loss ratio and the relative dynamic modulus of elasticity） were tested. Relationships between the 28 d compressive strength, the frost resistance and the CRA quality characteristic parameter, water absorption, were then developed. The criterion of a CRA maximum water absorption limit value for RHPC was suggested, independent of its source and quality class. The results show that all RHPC mixes achieve the expected target workability, strength, and frost durability. The research results demonstrate that the application of the proposed method does not require trial testing prior to use.