Open Access

ARTICLE

BearFusionNet: A Multi-Stream Attention-Based Deep Learning Framework with Explainable AI for Accurate Detection of Bearing Casting Defects

Md. Ehsanul Haque¹, Md. Nurul Absur², Fahmid Al Farid³, Md Kamrul Siam⁴, Jia Uddin^5,*, Hezerul Abdul Karim^3,*

1 Department of Computer Science and Engineering, East West University, Dhaka, 1212, Bangladesh
2 Department of Computer Science, City University of New York, New York, NY 10016, USA
3 Centre for Image and Vision Computing (CIVC), COE for Artificial Intelligence, Faculty of Artificial Intelligence and Engineering (FAIE), Multimedia University, Cyberjaya, 63100, Malaysia
4 Department of Computer Science, New York Institute of Technology, New York, NY 10023, USA
5 AI and Big Data Department, Endicott College, Woosong University, Daejeon, 34606, Republic of Korea

* Corresponding Authors: Jia Uddin. Email: ; Hezerul Abdul Karim. Email:

Computers, Materials & Continua 2026, 86(3), 33 https://doi.org/10.32604/cmc.2025.071771

Received 12 August 2025; Accepted 13 October 2025; Issue published 12 January 2026

Abstract

Manual inspection of onba earing casting defects is not realistic and unreliable, particularly in the case of some micro-level anomalies which lead to major defects on a large scale. To address these challenges, we propose BearFusionNet, an attention-based deep learning architecture with multi-stream, which merges both DenseNet201 and MobileNetV2 for feature extraction with a classification head inspired by VGG19. This hybrid design, figuratively beaming from one layer to another, extracts the enormity of representations on different scales, backed by a pre-preprocessing pipeline that brings defect saliency to the fore through contrast adjustment, denoising, and edge detection. The use of multi-head self-attention enhances feature fusion, enabling the model to capture both large and small spatial features. BearFusionNet achieves an accuracy of 99.66% and Cohen’s kappa score of 0.9929 in Kaggle’s Real-life Industrial Casting Defects dataset. Both McNemar’s and Wilcoxon signed-rank statistical tests, as well as five-fold cross-validation, are employed to assess the robustness of our proposed model. To interpret the model, we adopt Grad-Cam visualizations, which are the state of the art standard. Furthermore, we deploy BearFusionNet as a web-based system for near real-time inference (5–6 s per prediction), which enables the quickest yet accurate detection with visual explanations. Overall, BearFusionNet is an interpretable, accurate, and deployable solution that can automatically detect casting defects, leading to significant advances in the innovative industrial environment.

---

Keywords

---