Determination of coarse aggregate content of concrete specimens by wave propagation and Artificial Neural Network

Santos, Danilo Pereira dos; Haach, Vladimir Guilherme

doi:10.1590/S1983-41952024000600012

Danilo Pereira dos Santos

conceptualization

methodology

validation

data curation

formal analysis

writing original draft

Instituto Federal de Educação, Ciência e Tecnologia da Bahia, Vitória da Conquista, BA, Brasil

http://orcid.org/0000-0003-3807-2272

Vladimir Guilherme Haach

conceptualization

methodology

project administration

supervision

writing review and editing

Universidade de São Paulo, Escola de Engenharia de São Carlos, São Carlos, SP, Brasil

http://orcid.org/0000-0002-9501-4450

Corresponding author: Danilo Pereira dos Santos. E-mail: danilo.pereira@engenharia.ufjf.br

Conflict of interest: Nothing to declare.

Editors: Yury Andrés Villagrán Zaccardi, Daniel Carlos Taissum Cardoso.

Thumbnail

Figure 1
Influence of heterogeneities on the travel-times of ultrasonic pulses.

Thumbnail

Figure 2
Concept of the adopted geometry.

Thumbnail

Figure 3
Geometric variables: aggregate Positions and rotated local axes

Thumbnail

Figure 4
Artificial neuron: basic architecture.

Thumbnail

Figure 5
Measurements configurations in 100 x 200 m² specimens: (a) 13 paths, (b) 22 paths.

Thumbnail

Figure 6
Architecture of ANN 1.

Thumbnail

Figure 7
Architecture of ANN 2.

Thumbnail

Figure 8
Architecture of ANN 3.

Thumbnail

Figure 9
Specimen divided into 200 elements that form 231 nodes at their edges.

Thumbnail

Figure 10
Straight paths for 22 measurements at 49.9% coarse aggregate content.

Thumbnail

Figure 11
Updated paths for 22 measurements at 49.9% coarse aggregate content.

Thumbnail

Figure 4
Artificial neuron: basic architecture.

Thumbnail

Figure 5
Measurements configurations in 100 x 200 m² specimens: (a) 13 paths, (b) 22 paths.

Thumbnail

Figure 6
Architecture of ANN 1.

Thumbnail

Figure 7
Architecture of ANN 2.

Thumbnail

Figure 8
Architecture of ANN 3.

Thumbnail

Figure 6
Architecture of ANN 1.

Thumbnail

Figure 7
Architecture of ANN 2.

Thumbnail

Figure 8
Architecture of ANN 3.

Thumbnail

Figure 9
Specimen divided into 200 elements that form 231 nodes at their edges.

Thumbnail

Figure 10
Straight paths for 22 measurements at 49.9% coarse aggregate content.

Thumbnail

Figure 11
Updated paths for 22 measurements at 49.9% coarse aggregate content.

Thumbnail

Figure 12
Absolute difference for ANN 1 in the samples with 18.6%, 18.6%, 24.4%, 37.8%, and 45.7% contents.

Thumbnail

Figure 13
Absolute difference for ANN 2 in the samples with 18.6%, 18.6%, 24.4%, 37.8%, and 45.7% contents.

Thumbnail

Figure 14
Comparison between the regressions performed by ANN 3 and the regression algorithms evaluated: differences between sample averages and real content.

Thumbnail

Figure 15
Comparison between the regressions performed by ANN 3 and the regression algorithms evaluated: standard deviation of sample averages.

Thumbnail

Figure 16
Comparison between ANNs´ performances.

Thumbnail

Figure 17
ANN 3 response for (a) straight paths and (b) updated paths.

Thumbnail

Figure 18
Parabolic trend for the error estimate between straight and non-straight paths.

Thumbnail

Table 1
Coarse aggregate contents for the classification problems.

Thumbnail

Table 2
ANN 1 training evaluation.

Thumbnail

Table 3
ANN 2 training evaluation.

Thumbnail

Table 4
Coarse aggregate contents for the regression problem.

Thumbnail

Table 5
ANN 3 training evaluation.

Thumbnail

Table 6
Global view of ANN 1 results.

Thumbnail

Table 7
Global view of ANN 2 results.

Thumbnail

Table 8
Basic parameters for XGB Regressor and Randon Forest.

Thumbnail

Table 9
XGB Regressor, Random Forest, and OLS training set performances.

Thumbnail

Table 10
XGB Regressor, Random Forest, and OLS testing set performances.

Thumbnail

Table 11
Correction of the ANN3 response for updated paths.

(1)

(2)

(3)

(4)

(5)

(6)

(7)

(8)

(9)

(10)

(11)

(12)

(13)

Specimen area (mm²)	Coarse aggregate area (mm²)	Number of coarse aggregates	Coarse aggregate contents (%)
20000	391.87	5	10.9
		9	21.4
		12	30.7
		15	41.6
		17	49.9

Epochs	Accuracy (%)
10	56
100	71
1000	67
2000	77
3000	74

Epochs	Accuracy (%)
10	65
50	92
100	82
1000	91

Specimen area (mm²)	Coarse aggregate area (mm²)	Number of coarse aggregates	Coarse aggregate contents (%)
20000	391.87	0	0.0
		1	2.0
		2	4.1
		3	6.2
		4	8.5
		5	10.9
		6	13.3
		7	15.9
		8	18.6
		9	21.4
		10	24.4
		11	27.5
		12	30.7
		13	34.2
		14	37.8
		15	41.6
		16	45.7
		17	49.9

Epochs	MAE
10	0.02224
50	0.01796
100	0.02512
1000	0.01988
2000	0.01895

Real content (%)	Average reached content (%)	Standard deviation (%)	CV (%)
18.6	21.09	2.76	13.1
24.4	25.44	3.39	13.3
37.8	40.43	5.50	13.6
45.7	44.42	3.85	8.67

Real content (%)	Average reached content (%)	Standard deviation (%)	CV (%)
18.6	20.28	1.62	7.99
24.4	23.48	2.42	10.3
37.8	38.37	3.68	9.59
45.7	44.41	2.33	5.25

XGB Regressor		Randon Forest
Booster	Tree base model	Number of trees in the forest	100
Number of gradients boosted trees	100	Minimum number of samples	2
Subsample ratio of columns (per tree, per level, per node)	1	Minimum number of samples to be a leaf node	1
Balance of positive and negative weights	1	Minimum weighted fraction	0
Importance type	Gain	Bootstrap samples are used	True
Maximum tree depth	3
Minimum loss reduction (γ)	0
L1 regularization (α)	0
L2 regularization (λ)	1
Learning rate (η)	0.1
Minimum child weight	1
Subsample ratio	1
Initial prediction score	0.5

Regression Method	MAE
ANN 3	0.01705
XGB Regressor	0.01082
Randon Forest	0.00883
OLS	0.02224

Regression Method	MAE
ANN 3	0.01796
XGB Regressor	0.02123
Random Forest	0.02348
OLS	0.02123

Real coarse aggregate content (CaC)	ANN 3 response (CaC_ANN3)	Corrected value (CaC*)
2.0%	2.9%	2.1%
10.9%	20.6%	10.3%
21.4%	37.9%	20.4%
34.2%	52.6%	33.4%
49.9%	61.1%	50.0%

[1] Corresponding author: Danilo Pereira dos Santos. E-mail: danilo.pereira@engenharia.ufjf.br

Brasil

Brasil

Determination of coarse aggregate content of concrete specimens by wave propagation and Artificial Neural Network

Determinação do teor de agregado graúdo em amostras de concreto por propagação de ondas e Redes Neurais Artificiais

Abstract