本文選題：故障預(yù)測　切入點：設(shè)備健康狀態(tài)評估　出處：《中國礦業(yè)大學(xué)》2015年碩士論文　論文類型：學(xué)位論文

【摘要】：井下機械機電設(shè)備復(fù)雜度較高,導(dǎo)致其故障特征呈現(xiàn)非線性、時變性、并發(fā)性、不確定性等特征,而且井下噪聲干擾大、設(shè)備數(shù)量多、分布時而分散時而聚集等,給設(shè)備的故障預(yù)測帶來了很大的麻煩。本文在前人信號處理、分類算法、故障預(yù)測、機器學(xué)習(xí)的基礎(chǔ)上,針對井下設(shè)備健康狀態(tài)評估準(zhǔn)確度、適用范圍、實用性等問題進行了研究。主要內(nèi)容如下:(1)設(shè)備健康狀態(tài)預(yù)測與評估。井下的復(fù)雜環(huán)境導(dǎo)致通過直接預(yù)測其故障類型變得非常困難,而且對于突發(fā)故障來說,預(yù)測設(shè)備的故障類型意義不大,因此提出通過健康狀態(tài)評價設(shè)備的運行狀況。實驗表明,對于出現(xiàn)漸變故障的設(shè)備該方法具有很高的應(yīng)用價值。(2)基于特征提取的井下設(shè)備特性研究。設(shè)備的運行聲音能夠反映出當(dāng)前設(shè)備的健康狀態(tài),研究了聲音對設(shè)備健康狀態(tài)的敏感度,提出了對所提取聲音進行分幀、去噪等預(yù)處理,并且對信號的短時能量、倒頻譜、Mel倒譜系數(shù)特征進行對比分析。實驗表明,基于特征提取的設(shè)備健康狀態(tài)預(yù)測與評估是可行的,而且對于同一信號,提取不同的特征,其預(yù)測精度也有所不同。(3)機器學(xué)習(xí)理論在健康狀態(tài)預(yù)測中的應(yīng)用研究。支持向量機(Support Vector Machine,SVM)有唯一的全局最優(yōu)解與出色的機器學(xué)習(xí)能力,能夠很好的解決小樣本、非線性、高維化等問題。本文將評價設(shè)備健康狀態(tài)的問題轉(zhuǎn)化為對設(shè)備特征分類的模型進行處理,提出了基于特征提取和SVM的設(shè)備健康狀態(tài)預(yù)測與評估方法。(4)設(shè)備健康狀態(tài)評估研究及實驗分析。提出了設(shè)備健康度的概念,通過在井下水泵處安裝的拾音器(或振動傳感器)獲得設(shè)備運行的聲音信號,驗證所提方法的合理性與準(zhǔn)確度。結(jié)合設(shè)備健康度,實驗研究了本文所述方法的預(yù)測精度影響因素。實驗結(jié)果表明,基于Mel倒譜系數(shù)特征提取和SVM的設(shè)備健康狀態(tài)預(yù)測方法具有更高的預(yù)測精度。
[Abstract]:The complexity of underground mechanical and electrical equipment is high, which results in its fault features being nonlinear, time-varying, concurrency, uncertainty and so on. Moreover, the downhole noise interference is large, the number of equipment is large, the distribution is sometimes scattered and sometimes aggregated, etc. On the basis of previous signal processing, classification algorithm, fault prediction and machine learning, this paper aims at the accuracy and scope of application for evaluating the health status of underground equipment. The main contents are as follows: 1) Prediction and evaluation of equipment health status. The complex underground environment makes it very difficult to predict the type of failure directly, and for sudden failure, It is of little significance to predict the fault type of the equipment, so it is proposed to evaluate the operation condition of the equipment through the health condition. This method has high application value for equipment with gradual fault. It has high application value. (2) the characteristic of underground equipment based on feature extraction is studied. The sound of equipment running can reflect the health state of current equipment. In this paper, the sensitivity of sound to the health state of the equipment is studied, and the preprocessing of the extracted sound, such as framing and de-noising, is proposed. The characteristics of the short time energy of the signal and the Mel cepstrum coefficient of the cepstrum are compared and analyzed. The experimental results show that, It is feasible to predict and evaluate the health status of equipment based on feature extraction, and different features are extracted for the same signal. The application of machine learning theory in health state prediction is also different. The support vector machine support Vector machine has a unique global optimal solution and excellent machine learning ability, which can solve the problem of small sample size and nonlinearity. In this paper, the problem of evaluating the health status of equipment is transformed into a model of equipment feature classification. Based on feature extraction and SVM, the research and experimental analysis of equipment health state evaluation are presented, and the concept of equipment health degree is put forward. The sound signal of the equipment running is obtained by the pick-up (or vibration sensor) installed in the underground water pump, and the rationality and accuracy of the proposed method are verified. The experimental results show that the method based on Mel cepstrum coefficient feature extraction and SVM has higher prediction accuracy.
【學(xué)位授予單位】：中國礦業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2015
【分類號】：TD611

【參考文獻】

相關(guān)期刊論文 前10條

1 徐啟華,師軍;基于支持向量機的航空發(fā)動機故障診斷[J];航空動力學(xué)報;2005年02期

2 張宏國;張波;邱鐵;;煤礦機電設(shè)備故障維修[J];黑龍江科技信息;2012年01期

3 高宏力;劉慶杰;黃柏權(quán);趙敏;吳希曦;壽云;;數(shù)控機床故障預(yù)測與健康管理系統(tǒng)關(guān)鍵技術(shù)[J];計算機集成制造系統(tǒng);2010年10期

4 王樹西;夏增艷;;一種區(qū)分索引與信息的網(wǎng)頁分類數(shù)學(xué)模型及證明[J];計算機科學(xué);2014年S2期

5 張懷禮;張洪軍;;聽聲音判斷機器故障[J];農(nóng)村百事通;2006年04期

6 張浩然,韓正之;回歸支持向量機的改進序列最小優(yōu)化學(xué)習(xí)算法[J];軟件學(xué)報;2003年12期

7 陸朝榮,施毅;設(shè)備故障率和設(shè)備維修策略[J];石油化工技術(shù)經(jīng)濟;2004年03期

8 李曉虎,賈民平,許飛云;頻譜分析法在齒輪箱故障診斷中的應(yīng)用[J];振動、測試與診斷;2003年03期

9 杜培軍;柳思聰;鄭輝;;基于支持向量機的礦區(qū)土地覆蓋變化檢測[J];中國礦業(yè)大學(xué)學(xué)報;2012年02期

10 何正嘉,張涵W，

本文編號：1561718