何鹏飞,黄国勇,阮爱国.基于连续小波变换和模型无关元学习的压燃式活塞发动机气门故障诊断研究[J].内燃机工程,2024,45(1):57-63.
基于连续小波变换和模型无关元学习的压燃式活塞发动机气门故障诊断研究
Study on Valve Fault Diagnosis of Compression Ignition Piston Engine Based on Continuous Wavelet Transform and Model Agnostic Meta Learning
DOI：10.13949/j.cnki.nrjgc.2024.01.007
关键词:压燃式活塞发动机  故障诊断  连续小波变换  元学习
Key Words:compression ignition piston engine  fault diagnosis  continuous wavelet transform（CWT）  meta-learning
基金项目:南通常测机电设备有限公司科技项目（KKF0202165365）
作者单位邮编
何鹏飞 昆明理工大学 民航与航空学院，昆明 650500 650500
黄国勇 昆明理工大学 民航与航空学院，昆明 650500 650500
阮爱国 中国广核新能源投资有限公司云南分公司，昆明 650200 650200
摘要点击次数: 324
全文下载次数: 214
摘要:针对压燃式活塞发动机缸盖表面振动信号样本少及传统故障诊断方法特征提取和选择困难的问题，提出了一种基于连续小波变换（continuous wavelet transform， CWT）和模型无关元学习（model agnostic meta learning， MAML）的压燃式活塞发动机气门间隙异常故障诊断方法。通过将CWT的特征提取能力和MAML的快速学习能力相结合搭建故障诊断模型。试验结果表明该方法能有效识别气门间隙故障，并且其准确率高于传统基于CWT和卷积神经网络（convolutional neural network， CNN）的故障诊断方法。通过跨域故障对比试验，研究了不同气门故障类型对模型诊断能力的影响，验证了该方法在解决小样本和跨域故障问题时具有更高的准确率和泛化能力。
Abstract:Aiming at the problems of few samples of vibration signals on the cylinder head surface of compression-ignition piston engine and the difficulty of feature extraction and selection in traditional fault diagnosis methods， a fault diagnosis method for valve lash abnormality in compression-ignition piston engine based on continuous wavelet transform（CWT） and model agnostic meta learning（MAML） was proposed. By combining the feature extraction capability of CWT and the fast learning capability of MAML， a fault diagnosis model was constructed. The experimental results show that the method can effectively identify valve lash faults， and its accuracy is higher than that of the traditional fault diagnosis method based on CWT and convolutional neural network（CNN）. The effects of different valve fault types on the diagnostic capability of the model were studied through the cross-domain fault comparison experiments， and the method’s performance in solving small samples and cross-domain faults was verified. The method has higher accuracy and generalization ability in solving small samples and cross-domain fault problems.
查看全文  HTML   查看/发表评论