This work presents machine learning (ML) algorithm development and testing for internal corrosion rate prediction in oil and gas (O&G) piping systems. The ML models were trained using TWI’s dataset of environmental and fluid parameters, operational and flow parameters, as well as pipeline and material parameters at 35000+ condition monitoring locations (CMLs). We have trained two ML models based on different artificial intelligence (AI) approaches: model 1, a direct regression model, and model 2, a composite classification-regression model. The ML models were created using data that posed remarkable challenges, such as biasedness, skewness, and duplicate values. We observed better statistical metrics for predicting using model 2 compared to prediction using model 1. Systematic parameter selection, power transformation, and hyperparameter optimization using the grid search technique were employed in the model development. Although the model 2 predicted well for lower corrosion rate (0.05mm/year), it fell short in predicting accurately for higher corrosion rates (>0.2mm/year) as the uncertainty increases at higher corrosion rates. We have also provided a discussion on the uncertainty in the model, targeted performance metrics, use of correction factors, improving model accuracy through model refinement, and reducing bias nature of the dataset by adding more diverse values at higher corrosion rates.

This paper proposes a classification model based on a corrosion and salt damage dataset of civil structures: ViT is used as the teacher model, while MobileNetV2 and MobileNetV3 are used as student models. The second-best model is obtained by improving the classifier and setting different ratios of fine-tuning layers under frozen versus non-frozen classification layers. This model is added with an improved attention mechanism to get the optimal model. The final results show that using ViT with the second weight and MobileNetV2 gives higher Accuracy and Weighted-f1 value, where heat maps generated by applying Grad-CAM reflect that it can generally identify the damage location. The optimal model obtained by choosing a fine-tuning strategy that freezes the classification layers and retrains 15% of the top feature layers can achieve an Accuracy and Weighted-f1 score of above 0.94, better than many advanced deep learning architectures using pre-trained weights.

Automated corrosion classification is crucial for industrial inspection. However, existing methods face severe class imbalance and strict computational constraints on edge devices. This study proposes a stepwise self-training framework for six-category corrosion classification. Leveraging a Vision Transformer and XGBoost classifier, this study proposes a class-aware proportional screening strategy that expands a small, labelled dataset with 19,964 unlabeled images to create a more balanced training set. Progressive training and knowledge distillation are then integrated to train a lightweight MobileNetV2 student model. The optimal fine-tuned model achieves a peak classification accuracy of 87.52%, improving upon the baseline MobileNetV2 by over 5%. Grad-CAM analysis confirms accurate focus on corroded regions, while mask-based fine-tuning demonstrates robustness, maintaining over 83% accuracy under 10% visual interference. This approach minimizes computational overhead without sacrificing accuracy, thereby offering a practical solution for real-world monitoring on resource-constrained devices.

Accurate detection of oil palm trees is required for routine plantation monitoring, particularly in large agricultural areas where field inspection is time-consuming. In this study, we examine the influence of simple color-space preprocessing based on hue, saturation, and brightness (HSB) on the performance of YOLOv5 object detection models using UAV imagery. Two lightweight variants, YOLOv5s and YOLOv5n, were tested at input resolutions of 416, 640, and 736 pixels. During experimentation, it was observed that moderate HSB adjustment improved image clarity under uneven lighting conditions and supported more consistent detection results. Among the tested configurations, YOLOv5s performed best at a resolution of 640 × 640 pixels, achieving a precision of 95.7

Undersea pipelines are susceptible to corrosion, leading to resource loss and significant harm to the natural ecosystem. Hence, it is necessary to construct a corrosion model for detection and maintenance. This research primarily examines the existing literature on data-driven models utilising Machine Learning (ML) methods, particularly Artificial Neural Networks (NN’s) and also considers the models based on other theories to provide references for corrosion models. An initial stage involves analysing the main cause of corrosion and identifying the key factors contributing to this structural failure. Then, the review highlights the benefits of ML by listing their composition and current applications. Furthermore, the article analyses corrosion modelling using other methods and examines the potential avenues for optimisation that may provide to ML. Additionally, it considers the cost aspect and provides potential methods and suggestions for reducing costs. This review can serve as a valuable reference for researchers studying corrosive pipeline modelling.

A sudden increase in the area of a duct or at the blunt base of the projectile leads to flow separation and reattachment. In the flow separation process, the base pressure at the blunt base is sub-atmospheric, leading to significant drag, which can be around sixty to seventy percent. This study is undertaken to regulate the base pressure in the recirculation zone and the flow field of the duct. This paper focuses on the effectiveness of quarter ribs of various radii in the range from 1 mm to mm and nozzle pressure ratio ranging from 3 to 11 at Mach M = 1.48 for a duct diameter of 22 mm and its sizes ranging from 1D to 6D. Some oscillations are observed for the rib location of 11 mm from the exit of the nozzle. Due to the proximity to the nozzle exit, these oscillations are observed. With a progressive shift of passive control along the more significant length, a continued rise in the pressure in the base region for rib radii in the range from 2 mm to 4 mm and an extreme increase in the base pressure is achieved for 4 mm rib radii placed at 66 mm inside the duct. Nevertheless, despite the maximum enhancement in pressure for duct size L = 4D, a negligible reduction in base pressure and ambient pressure cannot affect the flow contained by the duct for a more considerable duct length. However, using a quarter rib radii of 1mm is inadequate, and base pressure values are identical with and without rib except for the nozzle pressure ratio (NPR) = 3, where the nozzle at NPR = 3 is over-expanded. Except at NPR = 3, the nozzles are under-expanded, and the control mechanism becomes efficient, resulting in a significant base pressure increase. One can make a final decision based on the mission requirements about the radius of the rib, rib location, and level of expansion to meet the user's requirements.

The study of base pressure and its control is an important research area in the transonic speed when the flow undergoes a sudden change in area. The turbulent flow in a separated region is still a crucial area of research due to the advent of space shuttles and high-performance military aircraft, and turbulent flow in transonic and supersonic flow is a thrust area for researchers. This paper focuses on base pressure control with sudden expansion at Mach 1.3 for an area ratio of 4.84. The flow field inside the duct is controlled through a passive control in the form of quarter ribs of radii 1 mm, 2 mm, 3 mm, and 4 mm for various duct lengths in the range from L = 1D to 6D for nozzle pressure ratios in the range from 3 to 11. Results show that a 1 mm rib is not adequate, and rib radii 2 mm, 3 mm, and 4 mm are effective in raising the base pressure values, and this rise in the base pressure continues till the duct length L = 1D to 4D. There is a marginal reduction in base pressure for the duct lengths L = 5D and 6D due to the ineffectiveness of the back pressure.

This study presents a comparative analysis of an integer order and fractional order differential equation models describing the cancer immune system interactions. Incorporating quantum pressure and memory effects via Caputo fractional derivatives, the models represent tumor, immune, mutant, and suppressor cell populations. Fundamental properties including non-negativity, boundedness, and solution existence along with uniqueness are established for both formulations. The fractional model consistently predicts higher cell population levels. Immune cells show the largest deviation, with a 37.5% increase in maximum population and a 37.6% higher equilibrium compared to the integer model. Tumor and suppressor cells also exhibit increases of up to 18.5% and 25.4%, respectively. Both immune and suppressor cells exceed their respective carrying capacities K2 and K4 by 18.1% and 76.7% under the fractional model. Scenario-based comparison indicates a strong agreement under robust immune responses (differences below 0.5%), but in marked divergence tumor resistance conditions, the fractional model predicts 15.5% higher tumor equilibrium and 25.6% lower mutant cell populations. Two neural network validation studies support these findings. The first, comparing Caputo and integer models, shows significant performance gains, including a 72.6% reduction in RMSE. The second evaluates multiple fractional formulations, thereby identifying Hilfer derivatives as the most accurate (50.6% RMSE improvement), while Caputo derivatives demonstrate a superior robustness under parameter variation. These results highlight the value of memory-based modeling in capturing complex cancer immune dynamics and suggest potential applications in the personalized treatment optimization.

This study investigates the application of YOLOv8 object detection models for identifying and counting oil palm trees in plantation management, with a focus on deployment on edge devices. Various YOLOv8 architectures were trained and evaluated using drone-captured images of palm oil plantations. The YOLOv8 nano model delivered superior performance, achieving 95.6% precision, 93.3% recall, and 98% mAP @0.5. The optimized model was deployed on a Raspberry Pi 4B (RPi) equipped with an Intel Neural Compute Stick 1 (NCS1) accelerator, enabling real-time detection under field conditions. Post-deployment performance analysis indicated an average inference time of 0.4 s per image (2.4 FPS) with minimal accuracy reduction (97% mAP @0.5). The system demonstrated low power consumption (1.6W peak) and efficient memory usage (450 MB RAM), emphasizing its suitability for edge computing in precision agriculture. This research demonstrates the feasibility of employing compact, efficient deep-learning models on resource-constrained devices like the RPi for palm oil tree detection and counting. The proposed system provides a portable and energy-efficient solution for real-time monitoring of palm oil plantations, offering significant potential to enhance plantation management by enabling data analysis and decision-making in remote or challenging environments. Despite promising results, the system's performance was evaluated under specific environmental conditions, potentially limiting its generalizability across diverse plantation landscapes. Future research should aim to expand detection capabilities to include disease identification and yield estimation. Graphical abstract

The turbulent flow in a separated region is still a fundamental area of research due to the advent of space shuttles and high-performance military aircraft, and turbulent flow in transonic and supersonic flow is a thrust area for researchers. Whenever the flow experiences an abrupt increase in the area of the enlarged duct, the flow gets significant relief to separate and expand. When the shear layer comes out, it gets divided into two regions: main flow and separated flow. The divided stream line gets reattached with the duct and forms a recirculation zone where the pressure is lower than ambient pressure, resulting in significant drag. This study focuses on base pressure control through quarter-circle rib as a passive control mechanism. Accordingly, a comprehensive numerical simulation was carried out at screech-prone Mach number M = 1.6 for various radii 1 mm, 2 mm, 3 mm, and 4 mm for duct lengths in the range from L = 1D to 6D and nozzle pressure ratios from 3 to 11. Results indicate that for the same range of the rib radius, duct lengths, and level of expansion, there is a progressive increase in the base pressure when rib locations are moved downstream from 0.5D to 3D. The maximum rise in the base pressure is achieved when the rib is located at 66 mm from the base region. A rib with a radius of 1 mm is inadequate for the entire range of rib placement in the present study except when the rib is 11 mm from the base. It can be concluded that a rib of a 1.5 mm radius will be sufficient to neutralize the suction created due to the flow separation. The user can decide on the rib dimension, location, and nozzle pressure ratio based on their requirements.

Considering that corrosion is a widespread problem in tropical countries, this study proposes a progressive optimization of EfficientNetV2 for images of corroded objects (corrosion dataset) that can effectively target small and medium-sized corrosion datasets for detection. Compared to other models, the proposed model first adopts EfficientNetV2 as the basic architecture, focusing on the use of only MBConv blocks and MBConv with Fused-MBConv blocks in the hidden layers, as well as the effect of the number of these layers on the model’s classification results. To further improve the performance, this paper attempts to replace the convolutional modules in the input layer with LazyConv, utilizing FReLU and Dy-ReLU as an activation functions in both the input and output layers. The simulation results show that for the medium-sized corrosion dataset in this paper which uses only MBConv blocks for EfficientNetV2 can achieve higher accuracy but lower computational efficiency. Setting a smaller number of layers and replacing the convolutional block in the input layer with LazyConv can significantly reduce the total size of the model and make it more flexible, where the total size of the obtained M2 model being only 58.98 MB, and capable of automatically determining the number of input channels. Using FReLU in the input and output layers can achieve greater stability, with standard deviations of F1-score and Accuracy under five cycles of only 0.0099 and 0.0126, respectively. In addition, the optimized M2 model also offers advantages in terms of both light weight and stability compared to other classic deep learning models. These findings from this study may serve as a foundation for future innovations in the design of corrosion classification models.

Currently, fossil fuels—specifically, coal, natural gas, and occasionally oil—are the primary fuel source for power plants in Southeast Asia. In several Southeast Asian nations, including the Philippines, Vietnam, and Indonesia, coal is the most common fuel used to generate electricity. Due to its economic advantages, coal has been favored by Indonesia's domestic energy strategy, and the country is a significant producer and exporter of coal. To fulfil its increasing energy needs, Vietnam has also made significant investments in coal-fired power facilities. Southeast Asia's energy industry is one of the fastest-growing sources of greenhouse gas emissions due to the usage of fossil fuels, which puts global climate goals at risk. With major environmental and financial advantages, biomass fuel—especially agricultural waste like rice husks, wood pellets, and palm oil biomass—is becoming more widely acknowledged as a competitive alternative to fossil fuels for power generation. For instance, palm oil residues can be co-fired with coal to achieve higher boiler efficiencies while reducing net carbon emissions. Government initiatives like Malaysia’s National Biomass Strategy 2020, along with regional cooperation, are driving the adoption of biomass across Southeast Asia. Despite challenges such as supply chain issues and technological constraints, biomass holds significant potential to contribute to renewable energy targets and support sustainability goals. The aim of this paper is to examine the current state of biomass co-firing in Malaysia's power plants, focusing on the operational challenges it poses to boiler integrity and discussing practical mitigation strategies to support sustainable energy generation.

Occurrence of sudden expansion is widespread in the defense and automobile industry. At the blunt base of the fuselage, missiles, projectiles, and aircraft bombs, the flow gets separated at the base and forms low-pressure recirculation, leading to a significant increase in the base drag. This paper addresses how this low base pressure at the base can be controlled. A detailed numerical study was conducted to assess the impact of the quarter circle as a passive control mechanism in a suddenly expanded flow for an area ratio of 4.84 at Mach M = 2.0 for various rib radii ranging from 1 mm to 4 mm, the different duct lengths from L = 1D to 6D at different nozzle pressure ratio ranging from 3 to 11. The findings of this study show that a 1 mm rib is inadequate to impact the flow field inside the duct. Passive control in the form of a quarter circle rib seems to become effective once the nozzle flows under a favorable pressure gradient. However, the remaining rib radii effectively reduce the suction created at the base of the recirculation zone. It is found that the rib radius of 4 mm when placed at 66 mm at the base, results in a maximum rise in the base pressure, and the base pressure ratio attains a value of 3.4. These results are case sensitive; hence, one has to make a final decision about the rib radius, rib location, and the level of expansion based on the end user requirement.

This study assesses the effectiveness of passive control as a quarter circle at Mach M = 1 for a duct of diameter 22 mm of length L = 1D to 6D. The study was conducted for a nozzle pressure ratio of 1.5 to 5. At sonic Mach M = 1, when the passive control is placed at various locations in the duct, the optimum location and radius of the rib seem to be 1D, 1.5D, 2D, and 4 mm, resulting in a base pressure almost double the ambient pressure for orientation1 of the rib where flow from the Nozzle sees curved part of the rib. The base pressure equals the ambient pressure for a 3 mm rib radius at 1D, 1.5D, and 2D. When the rib is located at 0.5D, there is an increase in the base pressure due to the presence of the rib. However, the base pressure magnitude is lower than attained for 1D, 1.5D, 2D, and 3D rib locations. The best options for orientation 2 of the rib locations are 1.5D and 2D. No appreciable results are obtained when the rib is placed at 3D for both orientations.

Heavy metals such as cadmium, lead, arsenic, mercury, and chromium are harmful to human health, even in a trace amount. Despite existing guidelines and regulations for handling these toxic substances, mortality cases among wild animals due to heavy metal poisoning continue to occur. To effectively investigate the sources of heavy metal contaminants in the environment, it is essential to establish real-time monitoring systems across affected areas. This paper presents the design and development of a potentiostat device (HMstat) with the capability to perform a square wave anodic stripping voltammetry (SWASV). The HMstat was realized using a two-board type potentiostat design, incorporating through-hole technology for the analog component and the myRIO platform for the digital component. Performance evaluations indicated that the HMstat is capable of performing the SWASV method. The results demonstrated that the HMstat achieved an accuracy of 99.014%, remained within the tolerance range of components used and surpassed the existing solution.

Pulmonary tuberculosis (PTB) is a worldwide health problem; hence, accurate, fast, and economical diagnostic methods are needed. Expert interpretation, expensive expenses, and long turnaround times are typical of conventional diagnostic methods. This research proposes an Intelligent Tuberculosis Diagnostic Support System (ITDSS) that leverages ML, AI, and IoT to address these constraints. Using a cloud-based multi-agent decision support system, ITDSS allows seamless data exchange and real-time diagnosis, optimizing healthcare operations. CNNs evaluate chest X-rays, and NLP interprets clinical data in the system. According to experiments, the ITDSS software helps doctors make quicker, more accurate diagnoses and streamline the identification process. Intelligent computing improves TB detection accuracy and reach, according to the findings. The ITDSS is a smart, scalable system that improves healthcare delivery in resource-limited locations and early illness detection.

The primary goal of this study is to use CFD analysis to investigate the impact that a cavity has on the pressure at the base of a structure. In this analysis, we took into account the NPR, the cavity aspect ratio, and the cavity position. In this case, the area ratio is 3.24 and the Mach number is 2.0. Simulations were run with L/D ratios between 1 and 6, and NPRs of 3, 5, 7.8, 9, and 12. The 2-dimensional model was developed using ANSYS Fluent's Design Modeler. The nozzle is operating at Mach 2.0. Base pressure and wall pressure in the duct were the primary research foci. The C-D nozzle was created for this research. ANSYS Fluent was used to verify the CFD findings. When the nozzles are under-expanded and the cavity is at 0.5D, passive control as a cavity is shown to be effective. It appears that 1D is the bare minimum for duct length. Because the shear layer gets reattached to the duct wall at 1D and the boundary layer grows after reattachment, passive control is not observed in the flow process regardless of whether the cavity is located at 1D, 1.5D, 2D, or 3D. An oscillating base pressure is seen at shorter duct lengths. This phenomenon does not occur at longer duct lengths. Whether or not there are cavities in the duct, the flow field is the same.

This paper discusses the control of base pressure by passive means, where the jet is issued from a converging nozzle at sonic Mach number under a favorable pressure gradient. The effect of employing annular ribs on the enlarged duct and its impact on the flow field, as the passive control mechanism from a converging nozzle at the sonic Mach number, is investigated numerically in this study. The velocity distribution and base pressure changes are analyzed using a numerical compressible turbulence flow model. Initially, the rib is positioned at 16 mm (1D) from the base of the duct. Later, the rib position is shifted from 1D to 2D and then to 3D and 4D. The effect of variation of the rib positions, as well as its height from 1 mm to 3 mm, keeping the width of the rib fixed to 3 mm, is studied. The nozzle pressure ratio varies from 1.5 to 5, and the rib location is 1D and 2D. The velocity variation in the duct with and without rib placement is also analyzed. The results revealed comprehensive spread observations from the positive analysis of base pressure variation in ducts with no ribs and ribs with heights of 1 mm and 2 mm. The base pressure increased significantly with increasing nozzle pressure ratio for both rib heights compared to a smooth duct. It is also deduced that the highest base pressure is achieved at an aspect ratio of 3:1 when placed at 4D.

Asphalt pavement materials are susceptible to cracking when exposed to the traffic and environmental conditions. The crack in asphalt pavement is therefore considered as one of the main type of distresses. The use of reinforcement grids is one of the possible solutions against crack propagation. An analysis of crack propagation of asphalt mixtures reinforced with grid interface in comparison with unreinforced specimens has been performed using a 4-point bending beam test setup at low temperature. The image analysis method was used to analysis the number of cycles required to reach the specimen failure against cyclic loading. The 4-point bending beam crack propagation test was found an interesting approach to identify the low-temperature performance of the reinforced asphalt composite layer system. The results showed that the specimen with a reinforced grid interface has higher resistance against the crack propagation compared to specimens without reinforcement.

Corrosion is one of the key factors leading to material failure, which can occur in facilities and equipment closely related to people's lives, causing structural damage and thus affecting the safety of people's lives and property. To identify corrosion more effectively across multiple facilities and equipment, this paper utilizes a corrosion binary classification dataset containing various materials to develop a CNN classification model for better detection and distinction of material corrosion, using a methodological paradigm of transfer learning and fine-tuning. The proposed model implementation initially uses data augmentation to enhance the dataset and employs different sizes of EfficientNetV2 for training, evaluated using Confusion Matrix, ROC curve, and the values of Precision, Recall, and F1-score. To further enhance the testing results, this paper focuses on the impact of using the Global Average Pooling layer versus the Global Max Pooling layer, as well as the number of fine-tuning layers. The results show that the Global Average Pooling layer performs better, and EfficientNetV2B0 with a fine-tuning rate of 20%, and EfficientNetV2S with a fine-tuning rate of 15%, achieve the highest testing accuracy of 0.9176, an ROC-AUC value of 0.97, and Precision, Recall, and F1-Score values exceeding 0.9. These findings can be served as a reference for other corrosion classification models which uses EfficientNetV2.