摘要
提出了将一种改进的人工神经网络联想记忆模型应用于计算机数控机床的故障诊断方法。介绍了基于联想记忆模型的诊断算法 ,总结出数控机床的故障模式及故障分析表 ,然后将该样本向量进行 HADAMARD预处理、存储记忆后 ,可据此模型进行样本和非样本的并行联想回忆 ,实现诊断功能。最后进行了数字仿真研究 。
A modified associative memory model of Artificial Neural Network (ANN) is introduced into the fault diagnosis of computer numerical control machine tool. Firstly, the diagnosis algorithm is derived and the fault table is concluded. Secondly, the fault sample vectors are preprocessed by HADAMARD transform, and learned by the model. Finally, the samples and non-samples are parallel associatively recalled based on this network. Furthermore, the digital simulation results demonstrate that the novel strategy is reliable. Additionally, a hardware implementation method is presented, which uses large-scaled Field Programmable Gate Array (FPGA) circuits.
出处
《中国机械工程》
EI
CAS
CSCD
北大核心
2003年第15期1275-1277,1286,共4页
China Mechanical Engineering
基金
江苏省自然科学基金资助项目 ( BK2 0 0 2 0 13 )
关键词
人工神经网络
数控机床
故障诊断
现场可编程逻辑门阵列
artificial neural network numerical control machine tool fault diagnosis field programmable gate array (FPGA)
