Ponjesly College of Engineering

Pipeline infrastructure is increasingly vulnerable to complex, multi-stage corrosion defects that compromise structural integrity, operational reliability, regulatory compliance, and long-term cost-effectiveness. Conventional periodic maintenance strategies often lack adaptability to real-time degradation dynamics and environmental variability, resulting in inefficient resource utilization and elevated failure risks. This paper introduces ARPC-DOX (Advanced Risk-Informed ABCDE prioritization and evolutionary cost-optimal framework for intelligent Corrosion Maintenance in Pipelines), a novel AI-driven decision-support framework that integrates predictive modeling, dynamic risk assessment, and cost-aware optimization for intelligent pipeline maintenance. ARPC-DOX fuses a cross-Bayesian network, augmented with cross-attention mechanisms, to capture complex spatiotemporal dependencies in corrosion progression and detect evolving multi-stage defect patterns with high precision. The framework consolidates heterogeneous data sources including inspection logs, sensor telemetry, operational parameters, material characteristics, and environmental stressors into a unified, context-aware predictive engine. Maintenance prioritization is performed through an enhanced ABCDE framework, which is embedded with a dynamic weight adjustment layer that adaptively recalibrates risk weights based on current degradation trends and uncertainty profiles. To optimize the trade-off between maintenance cost and failure risk, the system employs the ADDAX algorithm, a robust, adaptive differential evolution-based metaheuristic designed for dynamic, high-dimensional optimization tasks. Extensive simulation studies conducted on a 100-segment synthetic pipeline network demonstrate the framework’s effectiveness in reducing failure probability, enhancing risk responsiveness, and achieving superior resource allocation. ARPC-DOX represents a scalable, intelligent, and real-time corrosion management paradigm that significantly enhances the safety, resilience, and sustainability of modern pipeline systems.

Effective crop yield prediction is critical in an effort of maximizing the use of irrigation, resource distribution and sustainable agricultural planning. Nonetheless, traditional methods tend to lack the ability to reflect temporal variations, agro-environmental complex interdependencies, and dynamism to the field conditions. In order to overcome these issues, this paper develops a novel Reinforcement Learning-Enhanced Clustering and Contrastive Decision Optimization in Agriculture framework (RLCCDOA). This is aimed at enhancing the idea of prediction of crop yield, the efficiency of irrigation, and the use of water resources in agricultural IoT settings. Three important components may be found in the proposed approach. To start with, Context-Aware Temporal-Adaptive Clustering Generative Adversarial Networks (CATACGAN) learn to organize multi-source agricultural data into time-sensitive clusters, which are useful to capture crop-related and environmental dynamics. Second, Contrastive Adaptive Multi-Channel Graph Attention Networks (CAMC-GAT) model interactions among the soil, climate, and crop factors through contrastive learning to allow a better discriminatory ability of optimal and suboptimal yield conditions. Third, Hierarchical Action Space Proximal Policy Optimization (HAS-PPO) allows real-time multi-level decision-making, so that the irrigation schedule and resource allocation can be optimized using adaptive policies depending on real-time sensor measurements. It is shown in experimental results that predictive performance is improved, with 99.4

Wireless sensor network (WSN) is an advanced technology in the current scenario owing to its broad range of research. Due to constraints such as restricted bandwidth and ever-changing network structures, WSNs are inherently exposed to a wide range of security vulnerabilities. This inherent fragility has sparked a significant surge in research efforts focused on enhancing the security mechanisms of WSNs in recent years. Thus, the research on WSN security has been growing for the past few years. In terms of security, the less infrastructure and self-reliant nature of WSN is considered a difficult concern. A wormhole (WH) attack detection system on Networked Control Systems (NCSs) is developed to conquer this issue by employing the Secretary Pufferfish Optimization Algorithm enabled Dense ResNeXt fused Deep Stacked Autoencoder (SPOA_DResNeXt-DSAE). Firstly, WSN simulation is performed and routing is executed using Low Energy Adaptive Clustering Hierarchy (LEACH). In order to perform WH attack detection, three processes, like Neighbour Ratio Threshold (NRT), out-of-band and in-band WH detection, are conducted. In the final phase, detection of the WH attack is effectively carried out through the application of the ResNeXt-DSAE framework. Additionally, the attack mitigation is done by means of DResNeXt-DSAE, which is trained using the Secretary-Pufferfish Optimisation Algorithm (SPOA). The effectiveness of DResNeXt-DSAE is evaluated using throughput, delay and Packet Delivery Ratio (PDR), which observed better values of 0.570 sec, 0.704 Mbps and 0.882.

This study presents an enhanced performance strategy for a Hybrid Renewable Energy System (HRES) connected to grid by using a Triple-Stage Interleaved Boost-SEPIC-Luo (TSIBSL) converter controlled by a Puffer Fish Optimized Proportional Integral (PFO-PI) controller. The system combines wind energy sources based on Photovoltaic (PV) and Doubly Fed Induction Generators (DFIG), stabilized by an advanced control mechanism to provide ideal voltage regulation. The proposed converter architecture provides high voltage gain, increased efficiency, and minimized ripple, rendering it appropriate for varying renewable energy outputs. The Puffer Fish Optimization (PFO) algorithm is employed to fine-tune the Proportional-Integral (PI) controller parameters, resulting in superior dynamic response and minimized steady-state error. A bidirectional converter is incorporated to manage battery energy storage, enabling efficient charging and discharging based on system demands. Grid integration is achieved through a three phase Voltage Source Inverter (VSI) to ensure power quality compliance. The MATLAB simulation platform and hardware prototype are utilized for confirming the efficacy of entire developed system. The attained results validate that the proposed approach significantly enhances system stability, maintains voltage regulation and ensures efficient energy transfer under changing load and ecological circumstances. The proposed converter efficiency is attained as 98.4

There have been several efforts on designing hybrid polymer composites using both natural and synthetic reinforcements to harness the potential of combining sustainable aspects of natural fibers and engineering properties of synthetic materials. In this research work, hybrid epoxy composites were fabricated by adding constant amounts of calcium carbonate and coconut shell fillers along with hemp, carbon, and basalt fibers. For testing the effect of fiber hybridization on mechanical properties, moisture resistance and erosive wear behavior, nine different hybrid epoxy composites having variable reinforcement proportions were fabricated. Mechanical properties including tensile strength, flexural strength, and impact strength were evaluated following standard ASTM testing procedures to find the optimal reinforcement arrangement. In the fabricated specimens, hybrid composite containing 20 wt