This SAE Recommended Practice SAE J2847-6 establishes requirements and specifications for communications messages between wirelessly charged electric vehicles and the wireless charger. Where relevant, this document notes, but does not formally specify, interactions between the vehicle and vehicle operator. This is the 1st version of this document and captures the initial objectives of the SAE task force. The intent of step 1 is to record as much information on “what we think works” and publish. The effort continues however, to step 2 that allows public review for additional comments and viewpoints, while the task force also continues additional testing and early implementation. Results of step 2 effort will then be incorporated into updates of this document and lead to a republished version. The next revision will address the harmonization between SAE J2847-6 and ISO/IEC 15118-7 to ensure interoperability

ISO standards for Road vehicles — Cybersecurity engineering

原版支持中文不大好，会乱码。 现在原版基础上修改支持 新浪云主机 sina SAE 上运行支持中文的版本。 SAE 上只支持4种中文字体 宋体、楷体、文泉驿正黑、文泉驿微米黑。 调用方式： $graph->title->SetFont(FF_UMING, FS_BOLD);//宋体 $graph->title->SetFont(FF_UKAI, FS_BOLD);//楷体 $graph->title->SetFont(FF_ZENHEI, FS_NORMAL);//文泉驿正黑 $graph->title->SetFont(FF_MICROHEI, FS_NORMAL);//文泉驿微米黑

ISO SAE 21434-2021中文 道路车辆 - 网络安全工程.pdf

本文介绍了国际标准ISO/SAE 21434第一版2021-08，该标准是针对道路车辆网络安全工程的参考号。本文提供了ISO/SAE 21434:2021(E)的中英文对照翻译，版权受保护。该标准旨在为车辆制造商、供应商和其他相关方提供指导，以确保车辆网络安全性能的可靠性和安全性。

改文档为美国汽车协会发布的通信网络物理层的协议

SAE J1939_14_2022 Physical Layer, 500 kbit-s.pdf

SAE J3187-2022 System Theoretic Process Analysis (STPA) Recommended Practices for Evaluations of Automotive Related Safety-Criti.pdf

基于pytorch实现的堆叠自编码神经网络，包含网络模型构造、训练、测试 主要包含训练与测试数据（.mat文件）、模型（AE_ModelConstruction.py、AE_Train.py）以及测试例子（AE_Test.py） 其中ae_D_temp为训练数据，ae_Kobs3_temp为正常测试数据，ae_ver_temp为磨煤机堵煤故障数据，数据集包含风粉混合物温度等14个变量 在程序中神经网络的层数和每层神经元个数没有固定，可根据使用者的输入值来构造神经网络，方便调试 autoencoder类在初始化时有三个参数，第一个是网络输入值，第二个是SAE编码过程的层数(编码、解码过程层数相同)，第三个是是否添加BN层 这里为了构造方便，给每层神经元的个数与层数建立一个关系：第一层神经元的个数为2^(layer数+2)，之后逐层为上一层的1/2

Existing zero-shot learning (ZSL) models typically learn a projection function from a visual feature space to a semantic embedding space (e.g.~attribute space). However, such a projection function is only concerned with predicting the training seen class semantic representation (e.g.~attribute prediction) or classification. When applied to test data, which in the context of ZSL contains different (unseen) classes without training data, a ZSL model typically suffers from the project domain shift