Investigation on the Sensitivity of Ultrasonic Test Applied to Reinforced Concrete Beams Using Neural Network

Abstract

An experiment on reinforced concrete beams using four-point bending test during an ultrasonic test was conducted. Three beam specimens were considered for each water/cement ratio (WC) of 40% and 60%, with three reinforcement schedules named design A (comprising two top bars and two bottom bars), design B (with two bottom bars), and design C (with one bottom bar). The concrete beam had a size of 100 mm × 100 mm × 400 mm in length with a plain reinforcement bar of 9 mm in diameter. An ultrasonic test with pitch-catch configuration was conducted at each loading with the transducers oriented in direct transmission across the beams' length with recordings of 68 datasets per beam specimen. Recordings of ultrasonic test results and strains at the top and bottom surfaces subjected to multiple step loads in the experiment were done. After the collection of the data, feed-forward backpropagation artificial neural network (ANN) was used to investigate the sensitivity of the ultrasonic parameters to the mechanical load applied. Five input parameters were examined, as follows: neutral axis (NA), fundamental harmonic amplitude (A1), second harmonic amplitude (A2), third harmonic amplitude (A3), and peak-to-peak amplitude (PPA), while the output parameter was the percentage of ultimate load. Optimum models were chosen after training, validating, and testing 60 ANN models. The optimum model was chosen on the basis of the highest Pearson's Correlation Coefficient (R) and soundness, confirming that it exhibited good behavior in agreement with theories. A classification of sensitivity was performed using simulations based on the developed optimum models. It was found that A2 and NA were sensitive to all WC and reinforcements used in the ANN simulation. In addition, the range of sensitivity of A2 and NA was inversely and directly proportional to the reinforcing bars, respectively. This study can be used as a guide in the selection of ultrasonic parameters to assess damage in concrete with low or high WC and varying reinforcement content.

Using Waste in Producing Bio-Composite Mycelium Bricks

“…To further investigate the damage of the bio-composite bricks, an additional non-destructive test is recommended. Using acoustic emission [13,14] and ultrasonic test [15,16] for damage assessment of construction materials without breaking the test specimens can be practiced with respect to the age and growth of mycelium in the bricks.…”

Scalar Damage Modeling of Reinforced Concrete Beam Under Polarized Monotonic Stress Field Using Ultrasonic Pulses

“…Moreover, the latest trends in ultrasonic wave studies, such as Chen et al [25] and Ongpeng et al [26], both conducted in 2018, incorporated Artificial Neural Network (ANN), a computer algorithm capable of modeling a nonlinear system in concrete under applied stresses. ANN is a data mining tool that serves as a brain with a neural structure that can learn from its own data set.…”

Evaluation of the Adhesion between Overlays and Substrates in Concrete Floors: Literature Survey, Recent Non-Destructive and Semi-Destructive Testing Methods, and Research Gaps

“…The following limitations should be taken into consideration during the analysis: age of test specimens; surface and internal moisture conditions; the size, shape, and rigidity of the specimens; smoothness of test surface; type of coarse aggregate; type of cement; and carbonation of the concrete surface [23][24][25][26][27]. The hammer has recently also been used together with other non-destructive and semi-destructive testing methods to assess the compressive strength of concrete [27][28][29][30][31][32].…”