Journal of Industrial Mechanics

Integrated Parcel Management System with ML-based Resource Analysis for Goods Transport

Amol More — Wed, 18 Mar 2026 00:00:00 +0000

The rapid growth of e-commerce and logistics services has increased the demand for efficient parcel transportation systems. However, the logistics sector continues to face challenges such as inefficient capacity utilization, poor financial planning, suboptimal route management, high operational costs, and limited scalability. The absence of predictive analytics further reduces operational efficiency and decision-making capabilities. This study proposes an integrated parcel management system (IPMS) powered by machine learning (ML)-based resource analysis to enhance logistics performance. The system integrates predictive demand forecasting, capacity optimization, expense monitoring, fleet tracking, and route optimization within a unified framework. Real-time data processing enables intelligent resource allocation and operational automation. The proposed architecture improves vehicle utilization, reduces transportation costs, enhances supply chain coordination, and supports scalable logistics operations. Experimental analysis using simulated logistics datasets demonstrates improvements in route efficiency, cost reduction, and service reliability. The proposed IPMS offers a data-driven decision-support system for modern logistics and goods transportation, aligned with Industry 4.0 principles.

Application of SAP Plant Maintenance (SAP PM) Techniques to Evaluate and Compare Effectiveness of Various Maintenance Strategies on Industrial Machines

IKEGWURU OKACHI, O. E. Isaac, ZOR-OL, Collins Burabari, Tasie Martins Chizi — Thu, 29 Jan 2026 00:00:00 +0000

In this study, a novel maintenance approach known as SAP plant maintenance (SAP PM) technique is used to evaluate and compare various maintenance strategies effectiveness used in industrial machinery. Most modern industries rely on reactive, preventive, predictive, and condition-based maintenance approaches for operational cost reduction, and increase equipment reliability. At present, selecting the strategy that is most efficient remains a problem without data-driven tools for evaluation. The SAP PM technique collected, managed, and analyzed maintenance data such as equipment downtime, maintenance cost, mean time between failures (MTBF), mean time to repair (MTTR) and entire equipment effectiveness (EEE). The aforementioned maintenance strategies were implemented within SAP PM framework, and the study systematically compared their performance across industrial machines. By conducting quantitative analysis using reliable maintenance records and SAP-generated reports to ascertain equipment improvements in reliability, availability, and cost efficiency. The result proved that SAP PM guaranteed standardized maintenance planning, real-time monitoring, and performance evaluation, for which end users can identify the most maintenance strategy that is effective for a specific type of machine under specific operating condition. The key findings provide practical knowledge for maintenance managers and engineers, highlighting the key role of SAP PM as a decision-support tool for maintenance optimization.

AI-driven Optimization Models for Managing Gas Cylinder Supply Shortages during Geopolitical Conflicts

P. Sivasankaran — Mon, 23 Mar 2026 00:00:00 +0000

Liquefied Petroleum Gas (LPG) plays a critical role in meeting the domestic energy needs of millions of households in India. The country relies heavily on imported LPG, primarily transported through strategic maritime routes such as the Strait of Hormuz. Geopolitical tensions in the Middle East—particularly conflicts involving Iran and the United States—can significantly disrupt global energy supply chains, leading to shortages, transportation delays, and increased costs in LPG distribution. Such disruptions pose significant challenges to ensuring an uninterrupted household fuel supply, especially during crises. This study proposes an optimization-based framework to address challenges in LPG cylinder distribution under scenarios of supply disruption. A mathematical supply chain model is developed to optimize the allocation and transportation of LPG cylinders from bottling plants to distributors and household clusters. Advanced metaheuristic optimization techniques, including Genetic Algorithm (GA), Tabu Search (TS), and a hybrid GA–Tabu approach, are employed to minimize supply shortages, transportation costs, and delivery delays while maximizing demand satisfaction. Simulation experiments are conducted using representative LPG demand datasets to evaluate the performance of the proposed optimization framework. Results demonstrate that the hybrid GA–Tabu model significantly improves distribution efficiency and reduces cylinder shortages compared with conventional allocation methods. The findings highlight the potential of intelligent optimization techniques for enhancing resilience and sustainability in LPG supply chains during geopolitical disruptions. The proposed model provides a strategic decision-support tool for policymakers and energy logistics planners to ensure reliable household LPG distribution under crisis conditions.

Application of Multi-queuing Network Systems for Warehouse Logistics and AGVs Scheduling Using Ant Colony and SIMULINK

Omah Iheanyi, Ikpe M. L. — Mon, 16 Feb 2026 00:00:00 +0000

This research addresses efficiency challenges in large-scale distribution centers by developing an integrated multi-queuing network model optimized with an ant colony optimization (ACO) algorithm for dynamic automated guided vehicle (AGV) scheduling. Traditional scheduling methods often lead to congestion, long cycle times, and underutilized resources in multi-tier warehouse systems. The proposed methodology models warehouse zones as interconnected service nodes and employs ACO with adaptive parameter control for real-time path planning. Simulations conducted in MATLAB/SIMULINK under varied configurations demonstrated substantial performance gains over conventional methods. Key results include a 16.1% increase in throughput (to 176.8 tasks/hour), a 24.7% reduction in cycle time (to 6.7 minutes), a 32.4% decrease in daily travel distance, and a 64.3% reduction in queue wait time. The ACO algorithm converged efficiently, and an optimal configuration using 12 AGVs in a mixed layout was identified. All improvements were statistically significant (p < 0.001). The study concludes that the integrated ACO multi-queuing system significantly enhances warehouse operational efficiency and provides a robust framework for dynamic AGV coordination. Future research should explore machine learning integration for predictive scheduling and model validation in diverse industrial environments.

Energy Efficiency Improvement in Industrial Electrical Systems

Ritesh G Upadhyay — Fri, 02 Jan 2026 00:00:00 +0000

The study concludes that energy storage systems (ESS) offer an effective and increasingly important solution for managing high electricity demand in modern power systems. Improving energy efficiency in industrial electrical systems is a critical strategy for reducing operating costs, enhancing equipment reliability, and minimizing environmental impact, particularly in energy-intensive sectors such as the paper industry. This study investigates practical methods for enhancing electrical energy efficiency in paper manufacturing facilities through systematic energy auditing, performance evaluation of electrical equipment, and implementation of targeted improvement measures. Major energy-consuming components, including motors, pumps, fans, compressed air systems, and lighting, were analyzed to identify inefficiencies related to partial loading, poor power factor, and outdated control mechanisms. The study evaluates the effectiveness of high-efficiency motors, variable frequency drives (VFDs), power factor correction, process optimization, and energy monitoring systems in reducing electrical energy consumption. Results indicate that the combined application of these measures can achieve overall electricity savings ranging from 15 to 25%, with significant reductions in peak demand and operating costs. Additional benefits include improved power quality, reduced mechanical stress on equipment, enhanced system reliability, and lower maintenance requirements. The findings demonstrate that a structured, data-driven approach to electrical energy management enables paper industries to achieve substantial economic and environmental benefits. The study provides a practical framework for industries seeking to improve energy performance while supporting long-term sustainability and compliance with modern energy management standards.