-
公开(公告)号：US5745653A
公开(公告)日：1998-04-28
申请号：US596535
申请日：1996-02-05
CPC分类号： F02D41/1405 , F02D41/2406 , F02D2041/1423 , F02D2041/1429 , F02D2041/1433
摘要： A electronic engine control (EEC) module executes a generic neural network processing program to perform one or more neural network control funtions. Each neural network funtion is defined by a unitary data structure which defines the network architecture, including the number of node layers, the number of nodes per layer, and the interconnections between nodes. In addition, the data structure holds weight values which determine the manner in which network signals are combined. The network definition data structures are created by a network training system which utilizes an external training processor which employs gradient methods to derive network weight values in accordance with a cost function which quantitatively defines system objectives and an identification network which is pretrained to provide gradient signals representative the behavior of the physical plant. The training processor executes training cycles asynchronously with the operation of the EEC module in a representative test vehicle.
摘要翻译： 电子引擎控制（EEC）模块执行通用神经网络处理程序来执行一个或多个神经网络控制功能。 每个神经网络功能由定义网络架构的单一数据结构定义，包括节点层的数量，每层节点的数量以及节点之间的互连。 此外，数据结构保存了确定网络信号组合方式的权重值。 网络定义数据结构由网络训练系统创建，网络训练系统利用外部训练处理器，该外部训练处理器采用梯度方法根据量化定义系统目标的成本函数和预培训的识别网络来提供梯度信号， 物理植物的行为。 训练处理器在代表性测试车辆中与EEC模块的操作异步执行训练周期。
-
2.发明授权Method of applying an anisotropic hardening rule of plasticity to sheet metal forming processes 失效将可塑性各向异性硬化规则应用于钣金成型工艺的方法
公开(公告)号：US6009378A
公开(公告)日：1999-12-28
申请号：US950085
申请日：1997-10-14
摘要： A method is disclosed for developing a sheet metal forming process prediction method which is based on the application of an anisotropic hardening rule of plasticity in the mathematic theory.
摘要翻译： 公开了一种用于开发基于在数学理论中应用各向异性硬化可塑性规则的钣金成形工艺预测方法的方法。
-
搜索结果
2 条记录 (耗时 0.025 秒)
