Automated food safety inspection systems rely heavily on the visual detection of contamination, spoilage, and foreign objects in food products. Current approaches typically require extensive labeled training data for each specific hazard type, limiting generalizability to novel or rare safety issues. We propose a zero-shot detection framework for visual food safety hazards that enables the identification of previously unseen contamination types without requiring explicit training examples. Our approach adapts and extends the Knowledge-Enhanced Feature Synthesizer (KEFS) methodology to the food safety domain by constructing a specialized knowledge graph that encodes visual safety attributes and their correlations with food categories. We introduce a Food Safety Knowledge Graph (FSKG) that models the relationships between 26 food categories and 48 visual safety attributes (e.g., discoloration, mold patterns, foreign material characteristics) extracted from food safety databases and expert knowledge. Using this graph as the prior knowledge, our system synthesizes discriminative visual features for unseen hazard classes through a multi-source graph fusion module and region feature diffusion model. Experiments on our newly constructed Food Safety Visual Hazards (FSVH) dataset demonstrate that our approach achieves 63.7% mAP in zero-shot hazard detection, outperforming state-of-the-art general zero-shot detection methods by 6.9%. Furthermore, our framework demonstrates robust generalization to fine-grained novel hazard categories while maintaining high detection performance (59.8% harmonic mean) in generalized zero-shot scenarios where both seen and unseen hazards may occur simultaneously. This work represents a significant advancement toward automated, generalizable food safety inspection systems capable of adapting to emerging visual hazards without a costly retraining process.

Cold chain temperature management is crucial for preserving product quality and safety across various industries. While Computational Fluid Dynamics (CFD) provides detailed insights into thermal analysis and fluid dynamics, its computational intensity limits practical applications. This study presents a novel hybrid approach combining CFD and machine learning to enhance both computational efficiency and prediction accuracy in cold storage temperature management. A validated 3D CFD model was developed to analyze temperature distribution and airflow patterns in a refrigerated container with multiple storage boxes. Taking advantage of the cold room’s symmetrical design along its longitudinal axis significantly reduced computational requirements while maintaining model accuracy. Over 200 cases were simulated by varying key process parameters to generate training data for machine learning models. Random Forest (RF) and Neural Network (NN) models were developed and compared, with RF demonstrating consistently superior performance across all storage locations. Feature importance analysis revealed cold air temperature as the dominant control variable, while SHAP analysis identified optimal operational ranges for air velocity and heat transfer coefficients that balance product quality with energy efficiency. This research work also revealed distinct patterns in the influence of process parameters, with cold air and ambient temperatures showing hierarchical impacts on system performance. The hybrid methodology successfully addresses the computational limitations of traditional CFD approaches while maintaining high prediction accuracy, offering a practical solution for sustainable temperature management in cold storage applications. Finally, this research provides valuable insights for optimizing cold chain operations and demonstrates the potential of hybrid modeling approaches in thermal management systems.

The design of materials with programmable degradation profiles presents a fundamental challenge in pattern recognition across molecular space, requiring the identification of complex structure–property relationships within an exponentially large chemical domain. This paper introduces a novel physics-informed deep learning framework that integrates multi-scale molecular sensing data with reinforcement learning algorithms to enable intelligent characterization and prediction of polymer degradation dynamics. Our method combines three key innovations: (1) a dual-channel sensing architecture that fuses spectroscopic signatures from Graph Isomorphism Networks with temporal degradation patterns captured by transformer-based models, enabling comprehensive molecular state detection across multiple scales; (2) a physics-constrained policy network that ensures sensor measurements adhere to thermodynamic principles while optimizing the exploration of degradation pathways; and (3) a hierarchical signal processing system that balances multiple sensing modalities through adaptive weighting schemes learned from experimental feedback. The framework employs curriculum-based training that progressively increases molecular complexity, enabling robust detection of degradation markers linking polymer architectures to enzymatic breakdown kinetics. Experimental validation through automated synthesis and in situ characterization of 847 novel polymers demonstrates the framework’s sensing capabilities, achieving a 73.2% synthesis success rate and identifying 42 structures with precisely monitored degradation profiles spanning 6 to 24 months. Learned molecular patterns reveal previously undetected correlations between specific spectroscopic signatures and degradation susceptibility, validated through accelerated aging studies with continuous sensor monitoring. Our results establish that physics-informed constraints significantly improve both the validity (94.7%) and diversity (0.82 Tanimoto distance) of generated molecular structures compared with unconstrained baselines. This work advances the convergence of intelligent sensing technologies and materials science, demonstrating how physics-informed machine learning can enhance real-time monitoring capabilities for next-generation sustainable materials.