資源描述：
《淺議基于遺傳神經(jīng)網(wǎng)絡(luò)的汽車故障率預(yù)測(cè)》由會(huì)員上傳分享，免費(fèi)在線閱讀，更多相關(guān)內(nèi)容在學(xué)術(shù)論文-天天文庫(kù)。
1、上海交通大學(xué)碩士學(xué)位論文基于遺傳神經(jīng)網(wǎng)絡(luò)的汽車故障率預(yù)測(cè)姓名：楊婷申請(qǐng)學(xué)位級(jí)別：碩士專業(yè)：控制理論與控制工程指導(dǎo)教師：楊根科20080101上海交通大學(xué)碩士學(xué)位論文i基于遺傳神經(jīng)網(wǎng)絡(luò)的汽車故障率預(yù)測(cè)摘要汽車在使用過(guò)程中總會(huì)有故障出現(xiàn)，對(duì)于汽車生產(chǎn)商來(lái)說(shuō)，了解到汽車在一定行駛條件下的故障率，可以減少相應(yīng)的時(shí)間成本和庫(kù)存成本。有鑒于此，本文首先通過(guò)對(duì)汽車整體性能的分析，找出可能引起整體性能指標(biāo)降低而導(dǎo)致汽車故障的因素：汽車不同零件的易損度不同，零件本身質(zhì)量差異，汽車維修頻率，汽車消耗品種類，汽車行駛環(huán)境，駕駛因素，行駛距離
2、等，開(kāi)拓了汽車故障模型建模的新途徑；并對(duì)每個(gè)不同的故障因素影響導(dǎo)致汽車故障的權(quán)重進(jìn)行了分析評(píng)估，得出汽車故障率的控制模型。其次，本文采用了GA-BP神經(jīng)網(wǎng)絡(luò)處理問(wèn)題。在描述了傳統(tǒng)BP網(wǎng)絡(luò)的基本模型的基礎(chǔ)上，介紹了用于BP網(wǎng)絡(luò)中的常見(jiàn)的幾種改進(jìn)算法：附加動(dòng)量和學(xué)習(xí)率自適應(yīng)調(diào)整的改進(jìn)BP算法(BPX)、Levenberg-Marquardt優(yōu)化方法(LM)、Bayes規(guī)范化BP算法。并利用遺傳算法對(duì)神經(jīng)網(wǎng)絡(luò)的權(quán)值和閾值進(jìn)行優(yōu)化，在MATLAB上分別對(duì)這幾種算法對(duì)模型進(jìn)行了訓(xùn)練，利用神經(jīng)網(wǎng)絡(luò)的泛化能力，得到我們所需要的預(yù)測(cè)數(shù)
3、據(jù)。關(guān)鍵字：BP神經(jīng)網(wǎng)絡(luò)、遺傳算法、優(yōu)化、汽車故障率、預(yù)測(cè)i上海交通大學(xué)碩士學(xué)位論文iFORECASTTHECARFAILUREBASEDONBPNEURALNETWORKABSTRACTIngeneral,theautomobilehasthebreakdownappearanceintheuseprocess.Regardingtheautomobileproducer,itwouldreducethecorrespondingtimecostandinventorycostafterknowingtheautom
4、obilefailurerateundercertaintravelcondition.Astothis,firstly,throughtheautomobileoverallperformanceanalysis,thearticlefindsthepossiblecausestoreducetheautomobilebreakdown,suchastheautomobileeachinstallmentbuckle,thecomponentsqualitydifferences,theautomobileservi
5、cefrequency,theautomobilefueloil,theautomobiletravelenvironment,thedrivingtechnologyandthedrivingmethod,thetravelcourseandsoonandetc.Allofthesehavedevelopedtheautomobilebreakdownmodelinthenewway,andanalysistheweighofthedifferentbreakdownfactorsinfluence,thenthea
6、utomobilefailureratecontrolmodelhasbeengot.Next,thisarticlehasusedtheGA-BPneuralnetworktosolvethequestion.OnthefoundationofthetraditionalBPnetworkbasicmodel,itintroducestheseveralcommonkindsofimprovementalgorithmintheBPnetwork:Additionalmomentumandlearningrateau
7、to-adaptedi上海交通大學(xué)碩士學(xué)位論文iiadjustmentimprovementBPalgorithm(BPX),Levenberg-Marquardtoptimizedalgorithm(LM),BayesstandardizedBPalgorithm,andcarriesontheoptimizationontheneuralnetworkweightandbiasusingthegeneticalgorithm.IthasseparatelycarriedonthetrainingmodelbyMAT
8、LABonthebasisofthesealgorithms,andforecastthedatawhichweneedthroughregressionabilityusingtheneuralnetwork.KEYWORDS:Back-PropagationNeuralNetwork,GeneticAlgorithm,CarF
