Machine Learning

A significant barrier to preserving factual accuracy and dependability in AI-generated outputs is hallucination in large language models. Using a benchmark Kaggle dataset, this work provides a comprehensive evaluation of both advanced transformer-based architectures and traditional machine learning classifiers for hallucination identification. They compared refined transformer models, such as DistilBERT, RoBERTa, and DeBERTa, with baseline models, including Random Forest, SVM, and Logistic Regression. The results show that transformer-based models were more robust and better at understanding context; however, more conventional models, such as Random Forest, achieved a high overall accuracy of 94.10%. DistilBERT struck a wonderful balance between precision and readability. The confusion matrix analysis demonstrated that the models helped reduce false alarms for non-hallucination outputs. The ROC-AUC ratings confirmed the transformers’ precision and capability for identifying a slight rate of semantic discrepancies. Other studies provided supporting evidence that deeper context modeling will provide real benefits to the reliability of detection rates, demonstrated by the reduced hallucinations and assessments of the frequency of errors made. In conclusion, this research shows that combining traditional and modern approaches is beneficial and that tuning with transformer models holds promise for reducing hallucinations. This research provides an example of early steps of increasing trustworthiness and human-like models as AI models.

Additive manufacturing (AM) has advanced considerably as a disruptive technology that addresses the increasing demand for multi-functional, multi-material, and geometrically complex components and has begun to reshape areas of both product development and production methods. However, significant challenges related to incompatible material properties, defective parts made from AM processes, and inconsistent use of product build quality still exist. The ability to achieve highly precise AM processes is heavily reliant on monitoring, controlling, and utilizing multiple process variables effectively. In recent years, more advanced methods, including machine learning (ML), big data analytics, and design for additive manufacturing (DfAM), have become more available to address these limitations. Although these methods have been studied significantly, their use in aerospace-specific settings has been limited. In this review, study first provides an in-depth discussion on recent trends in DfAM. The review also considers simulation and modeling tools as enablers to obtain improved geometric fidelity in AM and to increase predictability of AM processes. Other trends include improved automation through the IoT, as well as knowledge-based process planning, also for multi-part cases of production. Lastly, review summarize many of the on-going issues and some future directions for algorithm-driven AM in aerospace and relate to industry 4.0 trends that emphasize intelligent automation, adaptive process control and lifecycle management, which will improve efficiency, reliability, and scale-up of AM technologies in aerospace and other advanced engineering applications.