设计了基于BP神经网络的PID控制器，实现PID控制器参数自学习、自整定。
The PID controller based on BP neural networks is designed to realize control parameter self-learning and self-adjusting.
在定义了数据结构和变量数组的基础上，给出了参数自学习过程算法，改善了模型样机对不同规格样本工件的适应性。
A parameter self-learning algorithm is presented after defining data structure and variable array to improve the prototype's adaptability to different size of workpieces.
提出了对随机事件概率分布参数进行自学习的方法，把知识化制造单元中的不确定因素纳入任务控制的数学模型。
The uncertain factors of the knowledgeable manufacturing cell were included in the task control model by utilizing a self-study method of probability distribution parameters of stochastic events.
应用推荐