Despite the growing popularity of rice husk ash (RHA) in various applications, limited research has been devoted to identify the influence of silica content in RHA on the intumescent properties. The present work aims to introduce a novel and economical geopolymer hybrid fire retardant coating by utilizing the use of RHA. The silica from Rice husk (RH) was extracted using distilled water and hydrochloric acid as leaching agents and subjected to pyrolysis treatment. X-ray fluorescence (XRF) analysis indicated that RH that underwent HCl pre-treatment at 600 °C for one hour produced a high purity amorphous silica content of 93.92%. XRD measurements revealed that HCl pretreatment increased the crystallization temperature of RHA to 1000 °C and retained the amorphous state of silica for 2 h. In a fire resistance test, temperature at the equilibrium and time taken to reach 200 °C for sample S3 (93.92% wt. silica) showed 5.83% and 3.48% improvement compared to sample S1 (87.49% wt. silica). The microstructure analysis showed that sample S1 possessed bigger pores on the coating surface while an increment in silica content in sample S3 produced a dense foam structure. Results from a fire resistance test were supported by the Energy dispersive X-ray (EDX) analysis of the sample. The oxygen-to-carbon ratio of S1 and S3 coating samples were 1.695 and 1.622 respectively, which indicated that lower oxygen–to-carbon ratio in sample S3 coating resulted in better anti-oxidant properties. Interestingly, the increment of SiO₂ content in RHA efficiently improved the compactness of the char layer, which resulted in a relatively higher fire-retardant efficiency. RHA proved to be a promising environmentally friendly strategy to replace halogenated fire retardant materials.

This study aims to develop suitable formulations of geopolymer concrete (GPC) by varying the percentages of the geopolymer with aggregates and evaluating the performances in thermal and mechanical properties of palm kernel shell ash (PKSA)-GPC compared to rice husk ash (RHA)-GPC and ordinary Portland cement concrete (OPCC). Preliminary tests were conducted to select the best mix design ratios before casting the specimens. Then, the performance of the PKSA-GPC, RHA-GPC and OPCC specimens was evaluated based on their thermal performance and drying shrinkage. The mix designs of PKSA-GPC 70:30, PKSA-GPC 60:40, PKSA-GPC 50:50 and PKSA-GPC 66.6:33.3 were found to produce an acceptable consistency, rheological and thixotropic behaviour for the development of the GPC. PKSA-GPC showed a better thermal performance than the RHA-GPC and OPCC due to their strong and dense intumescent layers and slow temperature increment upon exposure to a high flame temperature from ambient temperature to 169 °C. The low molar ratio of the Si/Al present in the PKSA-GPC created a thermally stable intumescent layer. In the drying shrinkage test, PKSA-GPC 60:40 and RHA-GPC 60:40 shared an equal drying shrinkage performance (5.040%) compared to the OPCC (8.996%). It was observed that microcrack formation could significantly contribute to the high shrinkage in the PKSA-GPC 50:50 and RHA-GPC 70:30 specimens. The findings of this study show that PKSA could be incorporated into GPC as a fire-retardant material due to its capability of prolonging the spread of fire upon ignition and acting as an alternative to the conventional OPCC.

The detection of impact and depth defects in Glass Fiber Reinforced Polymer (GFRP) composites has been extensively studied to develop effective, reliable, and cost-efficient assessment methods through various Non-Destructive Testing (NDT) techniques. Challenges in detecting these defects arise from varying responses based on the geometrical shape, thickness, and defect types. Long Pulse Thermography (LPT), utilizing an uncooled microbolometer and a low-resolution infrared (IR) camera, presents a promising solution for detecting both depth and impact defects in GFRP materials with a single setup and minimal tools at an economical cost. Despite its potential, the application of LPT has been limited due to susceptibility to noise from environmental radiation and reflections, leading to blurry images. This study focuses on optimizing LPT parameters to achieve accurate defect detection. Specifically, we investigated 11 flat-bottom hole (FBH) depth defects and impact defects ranging from 8 J to 15 J in GFRP materials. The key parameters examined include the environmental temperature, background reflection, background color reflection, and surface emissivity. Additionally, we employed image processing techniques to classify composite defects and automatically highlight defective areas. The Tanimoto Criterion (TC) was used to evaluate the accuracy of LPT both for raw images and post-processed images. The results demonstrate that through parameter optimization, the depth defects in GFRP materials were successfully detected. The TC success rate reached 0.91 for detecting FBH depth defects in raw images, which improved significantly after post-processing using Canny edge detection and Hough circle detection algorithms. This study underscores the potential of optimized LPT as a cost-effective and reliable method for detecting defects in GFRP composites.

Rotor imbalance in quadrotor UAVs poses a critical challenge, compromising flight stability, increasing maintenance demands, and reducing overall operational efficiency. Traditional vibration analysis methods, such as Fast Fourier Transform (FFT) and wavelet analysis, often struggle with non-stationary signals and real-time data processing, limiting their effectiveness under dynamic UAV operating conditions. To address these challenges, this study develops a machine learning-based vibration analysis system using a Multi-Layer Perceptron (MLP) neural network for real-time rotor imbalance detection. The system integrates Micro-Electro-Mechanical Systems (MEMS) sensors for vibration data acquisition, preprocessing techniques for noise reduction and feature extraction, and an optimized MLP architecture tailored to high-dimensional vibration data. Experimental validation was conducted under controlled flight scenarios, collecting a comprehensive dataset of 800 samples representing both balanced and imbalanced rotor conditions. The optimized MLP model, featuring five hidden layers, achieved a Root Mean Squared Error (RMSE) of 0.1414 and a correlation coefficient (R²) of 0.9224 on the test dataset, demonstrating high accuracy and reliability. This study highlights the potential of MLP-based diagnostics to enhance UAV reliability, safety, and operational efficiency, providing a scalable and effective solution for rotor imbalance detection in dynamic environments. The findings offer significant implications for improving UAV performance in addition to minimizing downtime in various industrial and commercial applications.

Corrosion in metallic materials is a critical challenge in maintenance and safety, and traditional visual inspection methods are often time-consuming, labor-intensive, and dependent on human expertise, highlighting the need for more efficient and reliable solutions. Deep learning, particularly convolutional neural networks (CNNs), provides a promising approach by enabling automated and accurate image-based classification. This study investigates binary image classification of corrosion using four pre-trained CNN architectures, namely ResNet50, MobileNetV2, NASNetMobile, and EfficientNetV2B0, and integrates explainable artificial intelligence (XAI) techniques to provide interpretability and insight into each model’s decision-making process. A curated dataset of 4012 images, divided between corroded and non-corroded surfaces, was pre-processed, and augmented images resulted in a total of 9636 images used to train and evaluate the models. Performance was assessed through accuracy, confusion matrices, computational timing, receiver operating characteristic curves, precision–recall curves, and Cohen’s Kappa. In this paper, Gradient-weighted Class Activation Mapping (Grad-CAM) visualizations are incorporated as an XAI technique to provide interpretable insight into the model’s reasoning process, enabling clear identification of corrosion regions and offering justification for each prediction produced by the system. A key contribution of this work is the integration of Grad-CAM to enhance explainability. The results showed that EfficientNetV2B0 demonstrates stable training with minimal sign overfitting compared to other models. MobileNetV2 achieved the lowest time to train with the datasets given, and ResNet50 achieved the highest classification performance in terms of confusion matrix, with an accuracy of 96.58%. Through Grad-CAM reasoning, EfficientNetV2B0 shows a specific high activation towards corroded regions compared to the other three models that were evaluated.