Mr. Mohammad Hossein Nahani, Dr. Gholam Reza Molaeimanesh, Dr. Masoud Dahmardeh,
Volume 14, Issue 4 (12-2024)
Abstract
The transition from traditional internal combustion engine vehicles to electric vehicles is in progress. With their high energy density, low self-discharge rates, long cycle life, and absence of memory effects, lithium-ion batteries have become the primary power source for alternative vehicles. Throughout the battery's lifespan, its performance or health gradually deteriorates due to irreversible physical and chemical changes. Depending on the specific aging mechanisms, a battery may lose capacity or face increased internal resistance. Growing awareness of the importance of environmental protection and the potential implications associated with products and services has spurred interest in developing methods to better understand and address these impacts. Life cycle assessment is a method used to examine the environmental effects associated with all stages of product production. This study compares the operational conditions of an electric vehicle equipped with both new and old battery packs. The performance difference indicates that the vehicle with the aged battery has 17% less capacity, operates over 20% weaker in range, and its ohmic resistance increases by up to 150%. From a well-to-wheel perspective, using an electric vehicle with an old battery could result in a 2% increase in carbon dioxide emissions, reaching 56.638 g CO₂ equivalent per kilometer.
Dr Mansour Baghaeian, Mr Ehsan Abbasi,
Volume 16, Issue 1 (3-2026)
Abstract
In metal casting, detecting defects like pores and cracks in X-ray images is crucial for product quality and safety. This study presents an advanced U-Net architecture for semantic segmentation of defects in the GDXray dataset, achieving superior accuracy. By formulating defect detection as an inverse problem reconstructing material density from X-ray projections the method integrates transfer learning, data augmentation, and Convolutional Block Attention Modules (CBAM) to address low contrast-to-noise ratios and limited data. Pretrained on synthetic Radon transform projections, the U-Net, enhanced with CBAM, sharpens focus on defect regions, improving boundary precision by 5%. Data augmentation, including rotations, flips, and noise injection, generates 5,000 synthetic images to overcome data scarcity. Experiments on 2,727 grayscale GDXray images demonstrate a mean Intersection over :union: (mIoU) of 0.85, a 15% improvement over baseline U-Net models, with 97.8% accuracy for pores and 94.5% for cracks. The inverse problem approach reduces false negatives by 12%, excelling in noisy conditions. Compared to methods like Mask R-CNN, this approach advances non-destructive evaluation (NDE) for casting applications, ensuring reliability and safety. Validated on laboratory X-ray data, the model offers a scalable solution for industrial defect detection. Future work will optimize computational efficiency and explore multi-modal data to enhance robustness.
