本文關鍵詞： 機械密封 狀態(tài)監(jiān)測 小波包 聲發(fā)射特征 Elman神經(jīng)網(wǎng)絡 PSO　出處：《西南交通大學》2015年碩士論文　論文類型：學位論文

【摘要】：機械密封是旋轉機械中最常用的軸封形式之一,因其可靠性高、泄漏量少、工作壽命長和適用性強等特點,被廣泛地用于石油化工、航天航空和核電能源等領域。因此,機械密封件的使用性能將直接對機械生產(chǎn)設備的安全性、生產(chǎn)過程的效率和生產(chǎn)成本產(chǎn)生影響。為此,對機械密封件采取實時狀態(tài)監(jiān)測,獲取有用的特征信息,分析機械密封在啟動過程中的端面摩擦狀態(tài),將是十分必要的。可以在密封件失效前及時發(fā)現(xiàn)并維修,避免因過早更換密封件造成的資源浪費、成本提高,或是延遲更換造成的安全事故。通過機械密封開啟過程監(jiān)測實驗的設計,選取電渦流和聲發(fā)射法對密封端面的膜厚信息進行監(jiān)測。實驗采集了機械密封在開啟全過程中的電渦流和聲發(fā)射信號,通過對電渦流信號的分析,建立起信號的變化與端面接觸狀態(tài)和摩擦狀態(tài)改變的對應關系。將密封的開啟過程分為干摩擦、混合摩擦和流體摩擦三種摩擦狀態(tài),采集的信號在這三個狀態(tài)中均有明顯的特征體現(xiàn)。然后對開啟過程中的聲發(fā)射信號進行分析,聲發(fā)射信號的變化情況也能與三種摩擦狀態(tài)進行對應,采用小波包分析法對信號進行降噪處理。在設計的有無密封環(huán)對比實驗中,分析得到中高頻信號包含更多的與機械密封有關的信息的結論,選取聲發(fā)射信號中的高頻信息,根據(jù)機械密封端面的摩擦特性選擇適合的特征指標,進行時頻域特征提取,篩選得到有效的聲發(fā)射信號特征。篩選得到的特征進行歸一化處理后,分析特征對三種摩擦狀態(tài)具有較好的可識別性。將歸一化后的特征值作為Elman神經(jīng)網(wǎng)絡的輸入向量,構建含反饋層的四層網(wǎng)絡模型。利用訓練樣本進行訓練后,對測試樣本進行識別,得到較好的識別效果。之后選取不同的訓練樣本和測試樣本,建立不同的網(wǎng)絡模型進行模式識別,發(fā)現(xiàn)均能很好地將不同的摩擦狀態(tài)數(shù)據(jù)進行分類。結果證明,選取的聲發(fā)射特征能有效地識別機械密封開啟過程中的端面情況。基于PSO算法實現(xiàn)對神經(jīng)網(wǎng)絡的優(yōu)化,通過加慣性權重因子和矩陣化設計實現(xiàn)了對PSO算法的改進,提高了算法的運行效率同時提升了算法的收斂速度。對比優(yōu)化前后神經(jīng)網(wǎng)絡的輸出結果證實,PSO算法對神經(jīng)網(wǎng)絡的訓練速度和精度、收斂速度和狀態(tài)識別精度等方面,均有明顯的優(yōu)化效果。
[Abstract]:Mechanical seal is one of the most commonly used shaft seals in rotating machinery, because of its high reliability, less leakage, long working life and strong applicability, it is widely used in petrochemical, aerospace and nuclear energy fields. The performance of mechanical seals will have a direct impact on the safety of mechanical production equipment, the efficiency of production process and production cost. Therefore, real-time monitoring of mechanical seals is adopted to obtain useful feature information. It will be very necessary to analyze the friction state of the end face of the mechanical seal in the starting process. It can be found and repaired in time before the failure of the seal, so as to avoid the waste of resources and increase the cost caused by the premature replacement of the seal. Or a safety accident caused by a delay in replacement. The design of the monitoring experiment through the mechanical seal opening process, Eddy current and acoustic emission methods are selected to monitor the film thickness information of the seal end face. The eddy current and acoustic emission signals of the mechanical seal during the whole process of opening are collected experimentally, and the eddy current signal is analyzed. The relationship between the signal change and the change of the contact state and the friction state is established. The opening process of the seal is divided into three kinds of friction states: dry friction, mixed friction and fluid friction. The collected signals have obvious characteristics in these three states. Then the acoustic emission signals in the process of opening are analyzed, and the changes of the acoustic emission signals can also correspond to the three friction states. The wavelet packet analysis method is used to reduce the noise of the signal. In the contrast experiment with or without the seal ring, the conclusion that the middle and high frequency signal contains more information related to mechanical seal is obtained, and the high frequency information of the acoustic emission signal is selected. According to the friction characteristics of the mechanical seal face, the suitable feature index is selected, and the feature extraction in time-frequency domain is carried out, and the effective acoustic emission signal feature is obtained. After normalized processing, the selected features are normalized. The normalized eigenvalue is used as the input vector of Elman neural network, and a four-layer network model with feedback layer is constructed. After different training samples and test samples are selected, different network models are established for pattern recognition. The results show that the selected acoustic emission features can effectively identify the end face in the process of mechanical seal opening. The neural network is optimized based on PSO algorithm. The improvement of PSO algorithm is realized by adding inertia weight factor and matrix design. Compared with the output results of neural network before and after optimization, the training speed and precision, convergence speed and state recognition accuracy of PSO algorithm for neural network are proved. All of them have obvious optimization effect.
【學位授予單位】：西南交通大學
【學位級別】：碩士
【學位授予年份】：2015
【分類號】：TH136

【參考文獻】

相關期刊論文 前6條

1 彭旭東;劉鑫;孟祥鎧;李紀云;盛頌恩;;疏水表面的自密封性對機械密封性能的影響[J];化工學報;2011年05期

2 ;中華人民共和國機械工業(yè)部部標準 機械密封分類方法(報批稿)[J];流體工程;1986年11期

3 黃莉;彭旭東;白少先;李紀云;盛頌恩;;不同型槽端面干氣密封的性能對比研究[J];流體機械;2010年08期

4 孫見君,魏龍,顧伯勤;機械密封的發(fā)展歷程與研究動向[J];潤滑與密封;2004年04期

5 王和順,陳次昌,黃澤沛,王新霖;機械密封端面接觸狀態(tài)測控技術[J];潤滑與密封;2005年03期

6 鄭海泉,陳汝灼;機械密封機理的探討[J];化工煉油機械;1981年03期

，

本文編號：1495743