شماره مدرك :
4185
شماره راهنما :
3956
پديد آورنده :
درويش، نصرت اله
عنوان :

تشخسص بد سوزي در موتورهاي اشتعال جرقه اي با استفاده از شبكه عصبي

مقطع تحصيلي :
كارشناسي ارشد
گرايش تحصيلي :
كنترل
محل تحصيل :
اصفهان : دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر
سال دفاع :
1387
صفحه شمار :
سيزده، 83، [II] ص. : مصور، نمودار
يادداشت :
ص. ع. به : فارسي و انگليسي
استاد راهنما :
فريد شيخ الاسلام، يداله ذاكري
توصيفگر ها :
استاندارد OBD , فرآيند احتراق موتور , شبكه هاي عصبي مصنوعي
تاريخ نمايه سازي :
22/7/1387
استاد داور :
جواد عسگري، احمد صابونچي
دانشكده :
مهندسي برق و كامپيوتر
كد ايرانداك :
ID3956
چكيده فارسي :
به فارسي و انگليسي : قابل رويت در نسخه ديجيتال
چكيده انگليسي :
AbstractBy progress of electronic technology and its vast use in automotive industry automotivesuppliers and other related organizations have agreed on OBD standard to reach morecoordination in diagnosis Engine misfire monitoring is one of the most difficult rules inthis standard Since misfire causes severe pollution of engines and it causes mechanicaldamages to engine parts so preventing it is very important According to standards attention to misfire detection mechanisms should be provided in motor controllers tosatisfy the OBD II rules In this thesis engine combustion process has been modeled as anonlinear discrete dynamic system In this model the event of normal firing or misfire isconsidered as an input to it and the crankshaft speed fluctuation as a system outputresponse The current crankshaft speed is related to the current and previous firing eventsand also the previous speed Once an inverse model from the crankshaft speed fluctuationsignal to the firing event signal to be identified the engine misfire can be detected moreaccurately because the output signal has a higher signal to noise ratio for the misfiresignature than its input signal For system identification a two layer dynamic neuralnetwork is used and since the previous firing events have influence on current firing eventsignal a feedback path is described from output to input A backpropagation learning ruleis used for the network s training Low sampling rate of data is the advantage of thismethod that is one data point per firing event This means one data point for a 180 degreerotation of the crankshaft in a 4 cylinder engine that easily acquire from engine controlunit The data consist of the firing event signal the crankshaft speed fluctuation theaverage of crankshaft speed and the average of manifold absolute pressure are acquired indifferent engine running condition and according to this data training of network is done According to the results that have been obtained in simulations the network could detectmisfire well In comparison with other strategies that need to high sampling rate this is asuitable method for misfire detection
استاد راهنما :
فريد شيخ الاسلام، يداله ذاكري
استاد داور :
جواد عسگري، احمد صابونچي
لينک به اين مدرک :

بازگشت