4964

4668

كارشناسي ارشد

ساخت و توليد

اصفهان: دانشگاه صنعتي اصفهان، دانشكده مكانيك

1388

هفت،[115]ص: مصور،جدول، نمودار، عكس

ص.ع. به: فارسي و انگليسي

عليرضا فدائي تهراني

محمد دانش

28/10/88

محسن اصفهانيان، محمد فروزان

مهندسي مكانيك

ID4668

به فارسي و انگليسي: قابل رويت در نسخه ديجيتال

Department of Mechanical Engineering Isfahan University of TechnologyDegree M Sc Language FarsiSupervisor Dr Ali Reza Fadai Tehrani Assoc Prof mcjafft@cc iut ac irAbstractSurface quality of finished parts is one the most considerable factors in the field of quality control Surfaceroughness however is the major parameter among various surface parameters which affects directly onfriction fatigue erosion and corrosion forces and final appearance of the surface The traditional mean formeasurement of surface roughness is the stylus instrument which contacts with surface and scans the surfaceprofile The traditional stylus has several disadvantages One the most important disadvantage of stylus isthat the surface roughness must be checked off line and surface roughness control during the manufacturingprocess is impossible Therefore many researches have been done on non contact methods which are able tomeasure surface roughness on line In the present study a new optical and non contact approach for surface roughness measurement is presented In this method several correlation surface parameters are extracted using laser light scattering and imageprocessing technique by mean of artificial neural networks the surface roughness is estimated with desirableaccuracy Despite of extreme simple setup and requirement of low cost equipments this method has shownreasonable accuracy which is comparable with traditional stylus instrument In addition because this methodis non contact it can be applied on line for continuous production lines In the presented approach laser light is radiated to various surfaces with various roughnesses and itsreflection is sensed by a CCD camera The reflection differs from incident laser light which is due to surfaceroughness By using image processing technique several correlated factors are extracted from laser reflectionimages Artificial neural networks are used to estimate the relationship between surface roughness andextracted parameters By having adequate samples an appropriate ANN can be trained the trained networkcan estimate surface roughness of new samples properly accurate The results of this method and stylus instrument have been presented to be compared It can be seen that byhaving suitable imaging instruments this approach can surpass traditional stylus technique Having nocontact with surface roughness full automation feasibility quick results and on line production control areother advantages of this method Keywords Surface Roughness Laser Optical Measurement Image Artificial NeuralNetwork Back Propagation

عليرضا فدائي تهراني

محمد دانش

محسن اصفهانيان، محمد فروزان