Jingpin Materials (China)

In recent years, HRRP-based radar automatic target recognition (RATR) using deep neural networks (DNNs) has garnered increasing attention. In real-world scenarios, test target categories frequently include both known and unknown classes, which is referred to as the open set recognition (OSR). Existing DNN-based classifiers tend to classify all captured HRRPs as known classes, presenting significant challenges for the practical application of HRRP-based RATR technology. Besides, extracting HRRP features at the optimal scale within DNNs is also essential for improving the HRRP-based OSR performance. To address these issues, we propose a systematic OSR solution named open set full-scale model (OSFSM). Firstly, OSFSM utilizes a set of convolutional kernels with prime-number lengths to efficiently extract HRRP features across all scales. Meanwhile, the learnable vectors are used to weight and filter the features at each scale. Secondly, we attribute the root cause of overconfidence in DNNs to the unconstrained magnitude of the logits. Therefore, OSFSM designs a parameter weight constraint (PWC) loss to implicitly suppress excessive growth in logits magnitude. Additionally, the prototype-based orientational (PBO) loss is proposed to reduce class cluster overlap. We validate the performance of OSFSM using two measured HRRP datasets and one simulated HRRP dataset. The OSFSM method achieved the optimal classification performance among the implemented methods.

Abstract A novel filling antioxidant (Lig‐g‐RT) to improve the mechanical properties and antiaging performance of styrene‐butadiene rubber (SBR) composites was prepared by grafting antioxidant intermediate p‐aminodiphenylamine (RT) on the surface of lignin via the linkage of silane coupling agent. Fourier transform infrared (FTIR) and thermogravimetric analysis (TGA) measurements confirmed that RT was successfully grafted on the surface of lignin to produce the functionalized Lig‐g‐RT which shows a better thermal stability than lignin. Compared with SBR/lignin composite, the SBR/Lig‐g‐RT composite using latex co‐precipitation method exhibits a much better filler dispersion, which contributes to the maintain of the physical mechanical properties of SBR vulcanizates. Moreover, the SBR/Lig‐g‐RT vulcanizate exhibits less chemical crosslink concentration and higher entanglement density than SBR/lignin vulcanizate according to the Mooney–Rivlin model analysis. In addition, the stabilizing effect of lignin/Lig‐g‐RT on the carbon‐black filled SBR vulcanizates is comparable with that of commercial antioxidant N‐1,3‐dimethylbutyl‐N′‐phenyl‐p‐phenylenediamine (4020), especially the SBR vulcanizate filled with 10 phr Lig‐g‐RT obtains the optimum thermo‐oxidative aging properties. This functionalized Lig‐g‐RT not only provides an intramolecular synergistic antiaging effect for SBR vulcanizates and an improvement of filler dispersion, but greatly extends the comprehensive utilization of industrial lignin.