Journal of Advanced Research in Mechanical Engineering and Technology

Context-Aware Adaptive Wheelchair: AI-Driven Terrain Detection for Mobility Assistance

2026-05-05T10:33:13+00:00

The lack of economical assistive devices limits people with lower limb disabilities in terms of mobility, autonomy, and overall life satisfaction. Powered wheelchairs do offer advanced wheelchair functions for users but are very expensive and rely on sophisticated technologies to supplement their usage. Due to this, many use manual wheelchairs, which require a significant amount of effort to self-propel, especially on uneven surfaces. This paper presents an augmentation of a standard manual wheelchair with context-aware assistance that helps in difficult terrains. The system uses EfficientNet, a lightweight and accurate deep learning model for classification which improves the accuracy of classification by up to 2.5% compared to single scaling methods. To try out our method, we test EfficientNet against ResNet50 and MobileNetV3 to compare accuracy, inference speed, and computational efficiency. Depending on the classified terrain, which includes ramps, side slopes, or rough pavements, the system suggests whether powered assistance to help with the rotation of the wheelchair wheels should be provided or not, thus reducing physical exertion while allowing the user to use their arms. This method meets the user’s needs by providing an optimum combination of ease of use, efficiency, and reasonable cost.

DOI: https://doi.org/10.24321/2454.8650.202601

Grey-wolf Optimization based vibration Control system for 7-degree of freedom structure: A case study on railway vehicle

2026-05-19T04:39:32+00:00

In this modern era, vibration control of tall structures has been becoming extensively important. To extend the life of any structure, continuous monitoring and control of structural bodies play an important role. This paper investigates a 7-degree-of-freedom (DOF) dynamic model of a railway vehicle by considering the equations related to the translational and rotational motions of the car body. A control structure with Fractional Order Proportional Integral Derivative (FOPID) controllers is used to suppress the vibration of the car body. Vertical profile type random track irregularities are treated as the inputs to evaluate control performance. A metaheuristic optimisation technique named Cuckoo-Catfish Optimisation (CCO) is proposed to optimise the active force for the suspension system. Next, the tuning parameters of the proposed model have been compared with the passive system. The results show that the proposed metaheuristic algorithm performs outstandingly in decreasing the vehicle vibration using an active system. The percentage reductions of the vertical, lateral and pitch accelerations are found to be 40.76%, 43.75% and 32.35%, which ensure a better ride comfort of the car body.

Localized Human Thermal and Respiratory Impact of AC Condenser Exhaust in Semi- Enclosed Urban Spaces

2026-05-26T04:28:03+00:00

Topology Optimization of Engineering Structures Using Hybrid Metaheuristic Algorithms

2026-06-09T07:37:50+00:00

Topology optimization has proven to be an efficient design approach to identify the best distribution of material over a given design space. But the classical optimizations have challenges for nonlinear multi-objective and large-scale engineering problems. Hybrid metaheuristic algorithms are a solid option because they combine sections of different metaheuristics. Reference document How to do topology optimization with hybrid metaheuristic: methodology, literature review, applications and performance analyse Topology Optimization (TO) is a powerful design tool that performs size/shape/topology optimization of structural systems. It shows that hybrid methods have important features towards making improvement on convergence speed, solution diversification and precision of optimization in the case of complex problems in mechanical engineering design.

A Review of Multi-Objective Optimization: Methods and Algorithms in Mechanical Engineering Problems

2026-06-09T07:58:58+00:00

Modern mechanical engineering problems often involve multiple conflicting objectives such as minimizing cost while maximizing performance, strength, and efficiency. Traditional optimization approaches, which focus on a single objective, are no longer sufficient to address such complex design challenges. Multi-objective optimization (MOO) provides a systematic framework to handle trade-offs among competing objectives and identify optimal design solutions. This review paper presents a comprehensive overview of various multi-objective optimization methods and algorithms widely used in mechanical engineering applications. Classical techniques, evolutionary algorithms, swarm intelligence approaches, and hybrid optimization strategies are discussed in detail. The paper also highlights practical applications in design optimization, thermal systems, manufacturing, and structural engineering. Finally, current challenges and future research directions in the field are outlined.