Open Access

ARTICLE

Deep Learning Model for Identifying Internal Flaws Based on Image Quadtree SBFEM and Deep Neural Networks

Hanyu Tao^1,2, Dongye Sun^1,2, Tao Fang^1,2, Wenhu Zhao^1,2,*

1 School of Infrastructure Engineering, Nanchang University, Nanchang, 330031, China
2 Jiangxi Provincial Key Laboratory of Intelligent Systems and Human-Machine Interaction, Nanchang, 330031, China

* Corresponding Author: Wenhu Zhao. Email:

Computer Modeling in Engineering & Sciences 2025, 145(1), 521-536. https://doi.org/10.32604/cmes.2025.072089

Received 19 August 2025; Accepted 22 September 2025; Issue published 30 October 2025

Abstract

Structural internal flaws often weaken the performance and integral stability, while traditional nondestructive testing or inversion methods face challenges of high cost and low efficiency in quantitative flaw identification. To quickly identify internal flaws within structures, a deep learning model for flaw detection is proposed based on the image quadtree scaled boundary finite element method (SBFEM) combined with a deep neural network (DNN). The training dataset is generated from the numerical simulations using the balanced quadtree algorithm and SBFEM, where the structural domain is discretized based on recursive decomposition principles and mesh refinement is automatically performed in the flaw boundary regions. The model contains only six types of elements and hanging nodes don’t affect the solution accuracy, resulting in a high degree of automation and significantly reducing the cost of the training dataset. The deep artificial neural network for flaw detection is constructed using DNN as the learning framework, effectively mitigating the risk of the objective function converging to local optima during training. Statistical methods are employed to evaluate the accuracy of the inversion model, and the influences of flaw size and the number of training samples on the performance are examined. In statistical results of single flaw, the 95% confidence intervals of the relative error for (x, y, r) are [2.16%, 2.76%], [1.53%, 1.96%] and [1.49%, 1.91%], respectively. The 95% confidence interval of the comprehensive relative error for double flaws is [3.06%, 3.62%]. The results demonstrate that the predicted flaw parameters align closely with the reserved clean data, indicating that the model can accurately quantify both the location and size of structural flaws.

---

Keywords

---