International Journal of Artificial Intelligence in Mechanical Engineering

Prompt Engineering: A Critical Discipline for Maximizing Utility and Ethical Deployment of Modern AI Systems

2026-01-21T05:14:00+00:00

Artificial intelligence (AI) has become a transformative technology, with large language models (LLMs) and multimodal systems increasingly rivaling human capabilities. The performance of these systems is critically dependent on prompt engineering, the discipline of designing, structuring, and refining textual and multimodal inputs to guide AI models to desired outputs. This paper provides a comprehensive exploration of prompt engineering across leading AI tools, including ChatGPT, Gemini, Claude, and Midjourney. Using a comparative case study methodology, the research examines the efficacy of techniques like chain-of-thought and role-based prompting in influencing accuracy, creativity, and ethical alignment. The results confirm that prompt engineering is essential for effective AI use, demonstrating tool-specific strengths: ChatGPT in structured reasoning, Gemini in technical precision, Claude in ethical framing, and Midjourney in visual aesthetics. The study highlights the trade-off between creative flexibility and factual precision, underscoring the significant ethical and educational implications of responsible prompting. It concludes that prompt engineering is a foundational skill for the AI era, essential for unlocking new possibilities and ensuring the responsible advancement of artificial intelligence.

Development of an Intelligent Crash Helmet with Accident Detection Technology

2026-01-05T06:19:48+00:00

This research entails the development of an intelligent crash helmet with accident detection technology. For motorcyclists who prioritize their safety when riding, a helmet is a vital piece of protective equipment. This helmet’s primary goal is to increase rider safety by incorporating state-of-the-art technologies. It transforms a regular bike into an intelligent one and improves the capabilities of a traditional helmet. This cutting-edge headgear efficiently serves as a hands-free gadget by smoothly integrating features including alcohol detection, accident recognition, overspeeding and fall detection. Information and commands can be shared between the bike and the helmet unit through the wireless module’s smooth communication. Crucially, the rider must wear the smart helmet for the bike to start. The smart helmet has a great feature that can check if someone has consumed alcohol. If the rider is too drunk, the bike’s starting system stops working, so they cannot ride while under the influence. In tests that mimicked crashes, the helmet correctly detected high-speed forces (25.73 m/s²), fast spinning (298.16 rad/s), and sudden changes in movement (157.3 m/s³), which all set off emergency signals. A vibration part was also checked for impacts, and the GPS and GSM parts worked well to send the rider’s location within 10 seconds after an incident. The whole system runs smoothly with 50 millisecond response times and can last for 4.4 hours on a 7.4V, 2200mAh lithium-ion battery. Overall, this smart helmet brings together advanced technology and safety tools to keep riders safe, making biking a more secure and enjoyable experience.

AI-driven Smart Precision Farming Using Autonomous Drones and IoT Sensor Networks: A Case Study for Agriculture Automation

2026-02-07T09:32:35+00:00

Escalating global food demand, increasing climatic variability, and constraints on arable land and water resources necessitate the adoption of sustainable, data-driven agricultural systems. This study proposes a novel Smart Precision Farming 4.0 framework that synergistically integrates autonomous unmanned aerial vehicles (UAVs) with ground-based Internet of Things (IoT) sensor networks to enable high-resolution crop monitoring and intelligent decision support. The proposed architecture combines multispectral and thermal UAV imaging with distributed soil and environmental sensing, while artificial intelligence and machine learning (AI/ML) algorithms are employed for real-time analytics, crop-status classification, and predictive assessment of agronomic conditions. The methodology further incorporates mathematical models for soil-moisture estimation and crop-health indexing, alongside a comprehensive performance evaluation using quantitative metrics including detection accuracy, spatial coverage efficiency, and resource utilization effectiveness. Comparative assessment against conventional manual and semi-automated practices demonstrates substantial performance gains, including a 35–50% improvement in irrigation water-use efficiency, a 20–30% reduction in agrochemical inputs (fertilizers and pesticides), and approximately a 25% enhancement in early-stage detection of crop stress and disease onset. The findings validate that the proposed UAV–IoT–AI integrated approach significantly improves operational efficiency, sustainability, and responsiveness, thereby offering a scalable solution for next-generation precision agriculture.

Artificial Intelligence Applications in Industrial Engineering: A Structured Framework for Decision Support and Optimization

2026-01-13T05:22:55+00:00

Artificial intelligence is increasingly influencing how industrial systems are planned, optimized, and managed. Industrial engineering has traditionally relied on analytical models, optimization techniques, and deterministic assumptions to support decision-making. As industrial systems grow in scale, complexity, and uncertainty, these approaches often face limitations in adaptability and robustness. Data-driven and learning-based methods offer new opportunities to address these challenges, yet their adoption in Industrial Engineering remains uneven due to fragmented methodologies, limited interpretability, and insufficient validation. This study presents a structured framework for applying artificial intelligence to industrial engineering decision support and optimization. The methods used in this study integrate disciplined problem definition, systematic data preparation, appropriate model selection, and rigorous validation within a unified methodological process. The framework is designed to support core industrial engineering activities, including prioritization, planning, optimization, and system evaluation, while maintaining alignment with established engineering decision processes and systems engineering principles. The key findings indicate that artificial intelligence enhances decision quality and operational relevance most effectively when employed as a decision support mechanism rather than as an automated replacement for engineering judgment. Structured integration improves transparency, traceability, and consistency, enabling artificial intelligence outputs to remain explainable, reproducible, and suitable for real industrial environments. The novelty of this work lies in providing a clear, methodologically grounded, and practically applicable framework that bridges data-driven techniques with disciplined engineering decision logic. The contributions of this study include formalizing a repeatable integration structure that supports responsible artificial intelligence adoption while preserving engineering rigor, accountability, and decision confidence in complex industrial engineering systems.