Katta rulmanli isitgich
Yuqori harorat, yuqori shovqin, chang, tebranish va boshqalar kabi og'ir ekologik sharoitlarda sinov o'tkazilganda, bu nafaqat inspektorning jismoniy va ruhiy holatiga katta zarar etkazadi, balki inspektorni odatda normal ishlay olmaydi. Shu sababli, katta rulmanli isitgichlarning rulman halqalarining sirt kamchiliklarini aniqlash bo'yicha tadqiqotlar so'nggi yillarda eng qizg'in nuqtaga aylandi. Raqamli tasvirni qayta ishlash texnologiyasiga asoslanib, bizning kafedra katta rulmanli isitgichlarning rulman halqalarining sirt kamchiliklarini aniqlash bo'yicha tadqiqotlar o'tkazdi. Asosiy tarkib quyidagilar:
1. Typical performance type and defect area analysis of surface defects of bearing rings of large bearing heaters.
2. Analysis of image edge detection algorithm. A variety of classic edge detection operators are used to compare and detect the surface defect images of bearing rings of large bearing heaters, and an improved Sobel edge detection operator is proposed.
3. Extraction and selection of defect features. Hu defect invariant features, morphological features, and texture features were extracted from the defect image, and systematic analysis and demonstration were carried out to determine the Hu moment invariant features required for classification recognition.
4. Research on classification and recognition algorithm based on BP neural network.
Issiqlik tashuvchisi aybi bilan audio diagnostika usulini o'rganish
(1) Rulmanli rulmanning ovozli signalida uning ishlash holati haqida muhim ma'lumotlar mavjud. Ushbu ma'lumotni tahlil qilish orqali rulmanli isitgich rulmanining nosozlik tashxisi samarali bajarilishi mumkin va ovozli signal foydalanish uchun qulay va arzon narxlardagi - aloqa bo'lmagan usulda to'planishi mumkin.
(2) According to the advantage that all parameters in the Discrete Hidden Markov Model (DHMM) are discrete values, we propose a new method for audio diagnosis of bearing faults based on DHMM, which has simple modeling, fast calculation speed and diagnostic accuracy Advanced features.
(3) uzluksiz Gaussian aralashmasi zichligi funktsiyasidan chiqish ehtimolini tasvirlash uchun foydalanish mumkinligi sababli, hujjat uzluksiz Gaussian aralashmasining zichligi HMM (uzluksiz Gaussian aralash aralashmasi yashirilgan Markov modeli, CGHMM) asosida xato ovozini aniqlashning yangi usulini taklif qiladi. . Shu bilan birga, mashqlar va tashxis algoritmi - klaster parametrlari asosida modellashtirish usuli bo'yicha boshlang'ich usuli va oldinga - oldinga qarab kalibrlash koeffitsienti yordamida yaxshilanadi.
(4) conducted a comparative analysis of the diagnostic test results of DHMM and CGHMM methods. The DHMM algorithm is better than the general CGHMM algorithm in speed, but the diagnostic accuracy is lower than the CGHMM algorithm.