本文選題：離散Hopfield網(wǎng)絡(luò) + 聯(lián)想記憶　； 參考：《燕山大學(xué)》2012年碩士論文

【摘要】：工業(yè)生產(chǎn)、工程機(jī)械、航天、船舶中因某一關(guān)鍵設(shè)備發(fā)生故障，常常造成巨大的經(jīng)濟(jì)損失甚至災(zāi)難性事故，故障識別技術(shù)可以分析故障，防患于未然，減少損失。液壓泵是液壓系統(tǒng)的一個(gè)重要組成部分，其性能好壞直接影響著液壓系統(tǒng)工作的可靠性和穩(wěn)定性，所以對其進(jìn)行故障識別的研究具有很重要的現(xiàn)實(shí)意義。本文對具有聯(lián)想記憶功能的神經(jīng)網(wǎng)絡(luò)技術(shù)進(jìn)行研究，并對軸向柱塞泵的故障進(jìn)行識別。 首先，研究了離散Hopfield神經(jīng)網(wǎng)絡(luò)，對結(jié)構(gòu)和有關(guān)收斂穩(wěn)定性的理論進(jìn)行了詳細(xì)的探討；另一方面對聯(lián)想記憶的功能實(shí)現(xiàn)和概念進(jìn)行了具體描述，在應(yīng)用中探討了輸入信號必須是二值型的弊端，從而結(jié)合BP網(wǎng)絡(luò)強(qiáng)非線性處理的優(yōu)點(diǎn)，對網(wǎng)絡(luò)結(jié)構(gòu)進(jìn)行合理的擬合，在實(shí)際中可以得到普遍應(yīng)用。 其次，針對聯(lián)想記憶神經(jīng)網(wǎng)絡(luò)易陷入局部極小值的特點(diǎn)，引入粒子群算法對網(wǎng)絡(luò)權(quán)值進(jìn)行了優(yōu)化，得到了收斂性能較高的網(wǎng)絡(luò)。在聯(lián)想記憶神經(jīng)網(wǎng)絡(luò)故障識別之前，對網(wǎng)絡(luò)中參數(shù)：層數(shù)，隱層神經(jīng)元個(gè)數(shù)，學(xué)習(xí)速率，慣性權(quán)重，加速因子等進(jìn)行了試探性的確定。 最后應(yīng)用本文提出的聯(lián)想記憶神經(jīng)網(wǎng)絡(luò)BP-HNN和BP-HNN-PSO對液壓泵的各種故障進(jìn)行識別和分析比較，驗(yàn)證了方法的有效性，，并發(fā)現(xiàn)加入粒子群算法的聯(lián)想記憶神經(jīng)網(wǎng)絡(luò)的識別結(jié)果值較高，識別率較高，較可靠。為了減少故障識別中的“錯(cuò)分”現(xiàn)象，利用艾賓浩斯記憶遺忘曲線對學(xué)習(xí)樣本進(jìn)行交叉循環(huán)安排，提高了學(xué)習(xí)的記憶效果，一定程度上達(dá)到了減少“錯(cuò)分”的目的。
[Abstract]:In industrial production, construction machinery, spaceflight and ship, the failure of a certain key equipment often results in huge economic loss or even catastrophic accident. The fault identification technology can analyze the fault, prevent the trouble from happening, and reduce the loss. Hydraulic pump is an important part of hydraulic system. Its performance directly affects the reliability and stability of hydraulic system. In this paper, the neural network technology with associative memory is studied, and the fault of axial piston pump is identified. Firstly, the discrete Hopfield neural network is studied, the structure and the theory of convergence stability are discussed in detail, on the other hand, the functional realization and concept of associative memory are described in detail. This paper discusses the disadvantage that the input signal must be a binary type in application, thus combining the advantages of strong nonlinear processing of BP network, the network structure is fitted reasonably, which can be widely used in practice. Secondly, aiming at the characteristic that associative memory neural networks are prone to fall into local minima, particle swarm optimization algorithm is introduced to optimize the weights of the networks, and a network with high convergence performance is obtained. Before the fault identification of associative memory neural network, the parameters of the network, such as the number of layers, the number of hidden layer neurons, the learning rate, the inertia weight, the acceleration factor and so on, are determined tentatively. Finally, using the associative memory neural network BP-HNN and BP-HNN-PSO presented in this paper to identify and compare the various faults of hydraulic pump, the validity of the method is verified, and it is found that the recognition result of associative memory neural network with particle swarm optimization algorithm is higher. The recognition rate is high and reliable. In order to reduce the phenomenon of "wrong points" in fault identification, the learning samples are arranged by using the Albinhaus memory forgetting curve, which improves the memory effect of learning and to some extent achieves the purpose of reducing the "wrong scores".
【學(xué)位授予單位】：燕山大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2012
【分類號】：TH165.3;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 趙四軍;王少萍;尚耀星;;航空液壓泵柱塞游隙增大故障診斷[J];北京航空航天大學(xué)學(xué)報(bào);2010年03期

2 賈嶸;徐其惠;李輝;劉偉;;基于鄰域粒子群優(yōu)化神經(jīng)網(wǎng)絡(luò)的變壓器故障診斷[J];高壓電器;2008年01期

3 明廷濤;張永祥;孫云嶺;;液壓伺服系統(tǒng)的H_∞觀測器設(shè)計(jì)[J];海軍工程大學(xué)學(xué)報(bào);2009年06期

4 陸雪梅;尚群立;;動態(tài)控制系統(tǒng)的故障診斷方法綜述[J];機(jī)電工程;2008年06期

5 倪遠(yuǎn)平,李一民,周建華,楊劍;自適應(yīng)遺傳神經(jīng)算法及故障識別[J];計(jì)算機(jī)工程與應(yīng)用;2003年35期

6 陳季萍,楊瑞軍;利用倒頻譜診斷液壓泵早期故障[J];機(jī)械設(shè)計(jì)與制造;2005年09期

7 賀尚紅,鐘掘;基于調(diào)制函數(shù)法的線性連續(xù)動力學(xué)系統(tǒng)參數(shù)模型估計(jì)[J];機(jī)械工程學(xué)報(bào);2003年12期

8 袁靜;何正嘉;訾艷陽;;基于提升多小波的機(jī)電設(shè)備復(fù)合故障分離和提取[J];機(jī)械工程學(xué)報(bào);2010年01期

9 周東華,席裕庚,張鐘俊;故障檢測與診斷技術(shù)[J];控制理論與應(yīng)用;1991年01期

10 李渭華;蕭德云;方崇智;;基于數(shù)學(xué)模型的故障檢測與分離技術(shù)[J];控制與決策;1992年06期

相關(guān)博士學(xué)位論文 前1條

1 吳勝強(qiáng);核主元分析及證據(jù)理論的多域特征故障診斷新方法研究[D];燕山大學(xué);2011年

相關(guān)碩士學(xué)位論文 前2條

1 鄒會榮;基于TMS320F2812的數(shù)據(jù)采集及電力電纜故障識別[D];西安科技大學(xué);2008年

2 李進(jìn)如;基于改進(jìn)小波神經(jīng)網(wǎng)絡(luò)的故障識別方法研究[D];華北電力大學(xué)（北京）;2008年

本文編號：1874310