طراحي سيستم تشخيص عيوب گيربكس خودروي تندر 09 با استفاده از آناليز موجك سيگنال صوتي

Design of the L90 automobile gearbox fault detection system using the audio signal analysis

گيربكس ‌ها در طول فرايند ساخت، مونتاژ و يا بهره ‌برداري ممكن است دچار عيب گردند در كارخانه ‌هاي توليد گيربكس، تعيين گيربكس‌ هاي معيوب جهت جلوگيري از ورود آن‌ها به چرخه مصرف اهميت فراواني دارد. در اين پژوهش به عيب ‌يابي هوشمند گيربكس خودرو تندر90 با استفاده از آناليز سيگنال ‌هاي صوتي پرداخته شده است. ابتدا استخراج ويژگي، از سيگنال ‌هاي پردازش ‌شده در هر سه حوزه انجام گرفت؛ و پس از آن با استفاده از روش آزمون و خطا و همچنين روش استنباط آماري تي ويژگي‌ هاي مطلوب جهت استفاده در طبقه ‌بندي انتخاب شد. سپس با استفاده از روش‌ هاي مختلف طبقه ‌بندي شبكه عصبي مصنوعي و ماشين بردار پشتيبان، روند هوشمند ­سازي عيب ‌يابي انجام گرفت. نتايج نشان داد كه روش كلاس ­بندي ماشين بردار پشتيبان با تبديل گسسته موجك، روي داده ­هاي پردازش شده، داراي خطاي متوسط كمتر از 9درصد هست. كه اين خطا نسبت به خطاي ساير روش ­ها در اين آزمايش كمتر هست.

Gearboxes may be defective during the manufacturing, assembly or operation process. In gearbox manufacturing factories, it is important to identify defective gearboxes to prevent them from entering the consumption cycle. Audio signals indicate the operation of the gearbox and the condition of its internal components. Therefore, this system is a powerful method to diagnose the gearbox healthy or defective in different gears. In this study, intelligent gearbox troubleshooting using audio signals has been done. After receiving the audio signals, suitable algorithms for troubleshooting were proposed and based on that, the troubleshooting process was performed. In this test, the gearbox of the Thunder 90 passenger car in the assembly line was checked for the health or defect. The received audio signals are first processed in the time, frequency (fast Fourier transform) and time-frequency (discrete wavelet transform) domains. Then the feature was extracted from the processed signals in all three domains of time, frequency and time-frequency; Then, using the error test method and statistical inference method, the desired characteristics were selected for use in classification. Then, using various methods of artificial neural network classification and support vector machine, the intelligent diagnostic process was performed. The results showed that the backup machine classification method on data processed with discrete wavelet transform has an average error of less than 9%. This error is less than the error of other signal processing and classification methods in this experiment.