分形技術與概率神經(jīng)網(wǎng)絡在船舶柴油機故障診斷中的應用
發(fā)布時間：2018-09-12 12:29
【摘要】：船舶自動化程度的提高對能源的需求也日益增長,而船舶的柴油機系統(tǒng)作為能源的主要來源,其重要性也越來越明顯。為提高柴油機的穩(wěn)定性能,降低故障發(fā)生率,本文提出一種基于分形技術和神經(jīng)網(wǎng)絡算法的故障診斷模型。該模型中的分形理論能夠甄別出故障的非線性特征,精確鎖定故障的來源;然后利用神經(jīng)網(wǎng)絡算法對柴油機故障的診斷進行深度訓練。最后利用LabVIEW仿真平臺和Matlab軟件進行故障診斷能力仿真驗證,本文提出的綜合診斷方法能夠有效識別故障來源和類型。
[Abstract]:With the improvement of ship automation, the demand for energy is increasing, and the importance of marine diesel engine system as the main source of energy is becoming more and more obvious. In order to improve the stability of diesel engine and reduce the fault rate, this paper presents a fault diagnosis model based on fractal technology and neural network algorithm. The fractal theory in the model can identify the nonlinear characteristics of the fault and accurately lock the source of the fault, and then use the neural network algorithm to train the diesel engine fault diagnosis in depth. Finally, the LabVIEW simulation platform and Matlab software are used to verify the ability of fault diagnosis. The comprehensive diagnosis method proposed in this paper can effectively identify the source and type of fault.
【作者單位】： 杭州科技職業(yè)技術學院機電工程學院;
【分類號】：U672
，
本文編號：2239012
[Abstract]:With the improvement of ship automation, the demand for energy is increasing, and the importance of marine diesel engine system as the main source of energy is becoming more and more obvious. In order to improve the stability of diesel engine and reduce the fault rate, this paper presents a fault diagnosis model based on fractal technology and neural network algorithm. The fractal theory in the model can identify the nonlinear characteristics of the fault and accurately lock the source of the fault, and then use the neural network algorithm to train the diesel engine fault diagnosis in depth. Finally, the LabVIEW simulation platform and Matlab software are used to verify the ability of fault diagnosis. The comprehensive diagnosis method proposed in this paper can effectively identify the source and type of fault.
【作者單位】： 杭州科技職業(yè)技術學院機電工程學院;
【分類號】：U672
，
本文編號：2239012
本文鏈接：http://www.wukwdryxk.cn/kejilunwen/chuanbolw/2239012.html
