The utilization of Machine Learning (ML) techniques in the analysis of the mechanical behavior of fiber-reinforced polymers (FRP) has been increasingly applied in composite materials. The ability to achieve high levels of accuracy, coupled with a reduction in computational cost once the ML models are trained, presents a powerful tool for optimization and in-depth analysis of laminated FRP. This review paper aims to provide insight into the emergence of this trend, offer an overview of various ML algorithms and related subtopics, and demonstrate different implementations of ML from recent studies with a specific focus on the design and optimization of FRP composites. The reviewed studies have exhibited high levels of prediction accuracy and have effectively employed ML to optimize the mechanical properties of composite materials. It was also highlighted that selecting the appropriate ML algorithm and neural network structure is crucial for various problems and data. While the studies reviewed have shown promising results, further research is needed to fully realize the potential of ML in this field.

The increasing adoption of machine learning (ML) in fiber-reinforced polymer (FRP) composite design has led to a reliance on black-box models, which achieve high predictive accuracy but lack interpretability. Python symbolic regression (PySR) offers a solution by deriving explicit equations that reveal the governing mechanics of composite structures. This study focuses on hybrid FRP bolted connections, which are rapidly adopted in the industry but remain insufficiently addressed in academic research. To address this gap, a framework was developed to identify key design parameters and predict damage initiation loads by integrating experimental testing, finite element modeling (FEM), and ML. Feature selection and ML models analyzed the dataset, providing insights that guided PySR in deriving interpretable equations. Hybrid L-joint specimens were fabricated and tested to determine damage initiation loads, with results validating FEM models in ABAQUS. A design of experiments approach structured the dataset, and feature selection identified key factors influencing joint performance. ML models assessed dataset quality, with Huber regression emerging as the best-performing model. Based on insights from feature analysis and ML models, PySR derived a compact, interpretable equation that provided greater accuracy and deeper physical insights than the Huber model. This equation aids hybrid L-joint design by improving the understanding of damage initiation mechanics. Beyond predictive accuracy, the findings highlight the model’s scalability to different bolt sizes, equally spaced row of bolts, and stacking sequences. This study demonstrates the potential of interpretable ML in structural engineering applications, particularly for hybrid composite-metal joints, where transparent models are essential for design optimization and predictive accuracy.

Large language models (LLMs) are attracting growing attention in robotics, mechanical engineering, and mechatronic systems. This review shows that, in most engineering settings, their value is not that they replace simulation, control, or numerical analysis tools, but that they help engineers work across documents, data sources, software environments, and natural-language instructions more efficiently. The review surveys recent studies across robotics and embodied systems, fault diagnosis and maintenance, design and simulation, industrial knowledge workflows, manufacturing knowledge systems, and selected adjacent engineering applications only where they provide transferable methodological insight for intelligent manufacturing. Across these areas, the evidence shows a movement away from prompt-only demonstrations and toward retrieval-augmented generation (RAG), multimodal, tool-connected, and agent-based systems that are more tightly grounded in engineering evidence and operational context. The review further shows that the strongest results generally come from hybrid architectures that combine LLMs with RAG, knowledge graphs, multimodal perception, digital twins, validation modules, or downstream engineering tools. Even so, important limitations remain, including weak grounding in cluttered or ambiguous settings, limited numerical and spatial reliability, poor long-horizon robustness, fragmented benchmarks, and incomplete integration with trusted engineering software. Overall, the evidence indicates that LLMs are becoming useful semantic and coordination layers in engineering workflows, but not dependable engineering substitutes. Their most credible near-term role is in human-in-the-loop, evidence-grounded systems where retrieval, validation, tool use, and structured knowledge help keep outputs useful and bounded in safety-relevant tasks.

Industrial safety question answering requires access to the exact source material that supports an answer, not merely a related document. This study evaluates the retrieval stage of a local retrieval-augmented generation (RAG) system at the source page level. Eighteen documents on lockout/tagout, machine guarding, and personal protective equipment were prepared in raw, cleaned, and metadata-enriched forms. Best Matching 25 (BM25), latent semantic analysis (LSA), and reciprocal rank fusion (RRF) hybrid retrieval were tested on 54 questions: 36 answerable, 12 safety-related but unsupported, and 6 outside the covered topics. Raw BM25 achieved the highest mean reciprocal rank (0.492) and Hit@5 (0.722), cleaned BM25 achieved the highest Hit@3 (0.556) and answerability AUROC (0.765), and metadata-enriched BM25 achieved the highest Hit@10 (0.833). For raw text, the retrieval method affected reciprocal rank (Friedman χ² = 7.13, p = 0.028). Hybrid retrieval exceeded LSA after Holm correction (p = 0.011), whereas BM25 and hybrid retrieval did not differ (p = 0.302). Text preparation had no overall effect within BM25 (p = 0.220). The results show that document-level evaluation can overstate access to exact evidence. The study provides a repeatable procedure for source tracking, page-level relevance labeling, separate retrieval and generation evaluation, and refusal analysis. These design principles are also relevant to construction safety knowledge systems that combine regulations, accident reports, project data, and BIM-linked information. Because the relevance set is a model-assisted silver standard, the findings remain exploratory rather than expert-certified absolute retrieval accuracy. A controlled same-run extension with all MiniLM L6 v2 and BM25 + MiniLM RRF is reported separately; its observed fusion gains did not reach statistical significance on the 36 answerable questions. The work is intended to support safety engineers, researchers, and developers designing evidence-grounded industrial and construction safety information systems.