Vanillin-based flame retardant enables polylactic acid high-efficiency fireproof, anti-UV and oxygen barrier for food packaging.

Polylactic acid (PLA) is widely known for its biocompatibility, biodegradability, and high transparency. However, it still has varied limitations such as flammability, UV sensitivity, and poor oxygen barrier properties. To address these issues, a bio-based compound, hexasubstituted cyclotriphosphazene (HVP), was synthesized by using vanillin and hexachlorocyclotriphosphazene to enhance the overall performance of PLA. The resulting PLA/HVP composites demonstrated improved mechanical strength and UV resistance. Specifically, PLA/3HVP, with a 3 wt% HVP loading, achieved a UL-94 V-0 rating and a high limiting oxygen index of 26.5 %. Cone calorimeter tests revealed that PLA/3HVP possessed a significantly longer ignition time and a lower peak heat release rate compared to pure PLA. These burning testing results indicated the enhanced fire resistance. Additionally, the oxygen transmission rate of PLA/3HVP was reduced by 81.1 % compared to pure PLA. When used as food packaging, the weight loss of mangoes covered with PLA/3HVP film was 2.2 % after 7 days, compared to 2.5 % with pure PLA film, highlighting its potential for food preservation applications.

A hybrid neural network model for noisy data regression.

A hybrid neural network model, based on the fusion of fuzzy adaptive resonance theory (FA ART) and the general regression neural network (GRNN), is proposed in this paper. Both FA and the GRNN are incremental learning systems and are very fast in network training. The proposed hybrid model, denoted as GRNNFA, is able to retain these advantages and, at the same time, to reduce the computational requirements in calculating and storing information of the kernels. A clustering version of the GRNN is designed with data compression by FA for noise removal. An adaptive gradient-based kernel width optimization algorithm has also been devised. Convergence of the gradient descent algorithm can be accelerated by the geometric incremental growth of the updating factor. A series of experiments with four benchmark datasets have been conducted to assess and compare effectiveness of GRNNFA with other approaches. The GRNNFA model is also employed in a novel application task for predicting the evacuation time of patrons at typical karaoke centers in Hong Kong in the event of fire. The results positively demonstrate the applicability of GRNNFA in noisy data regression problems.