论文部分内容阅读
针对旋转机械故障所具有的层次性、相关性和模糊性的特点 ,提出1种基于组合式模糊神经网络的旋转机械故障诊断模型。它由第 1层的决策模糊神经网络和第 2层的多个诊断模糊神经网络组合构成 ,依据大隶属度优先为真原则进行推理 ,按推理的过程和隶属度的大小给出可能的故障结果及相应的隶属度值 ,供现场工程技术人员结合辅助故障特征参数等进行进一步的联想推理 ,得到最终的故障诊断结果。实验研究结果表明 ,该系统可以有效地对具有模糊性的单一故障和复合故障进行诊断。详细讨论了模型建立、隶属度函数定义和模型推理过程 ,并给出实验结果。
Aiming at the characteristics of hierarchical, correlation and fuzziness of rotating machinery faults, a kind of rotating machinery fault diagnosis model based on combined fuzzy neural network is proposed. It is composed of the first layer of fuzzy neural network decision-making and the second layer of a combination of multiple diagnostic fuzzy neural network composition, according to the principle of priority is true of large membership reasoning, according to the process of reasoning and the size of membership gives the possible failure results And the corresponding membership value for field engineering and technical personnel with auxiliary fault characteristics parameters for further associative reasoning to get the final fault diagnosis results. The experimental results show that the system can effectively diagnose single and compound faults with ambiguity. Discusses in detail the model establishment, membership function definition and model inference process, and gives the experimental results.