Veliki grelnik ležajev
Pri preskušanju v težkih okoljskih pogojih, kot so visoka temperatura, visok hrup, prah, vibracije itd., Ne bo samo škodoval inšpektorju, temveč tudi inšpektorju pogosto ne more normalno delati. Zato so raziskave o odkrivanju površinskih napak nosilnih obročev velikih ležajnih grelcev v zadnjih letih postale vroča točka. Na podlagi tehnologije za digitalno obdelavo slik je naš oddelek izvedel raziskave odkrivanja površinskih napak nosilnih obročev velikih grelnikov ležajev. Glavne vsebine so naslednje:
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.
Študija avdio diagnostične metode napake ležaja grelca
(1) Zvočni signal ležaja grelnika ležaja vsebuje pomembne podatke o njegovem stanju delovanja. Z analizo teh informacij je mogoče učinkovito diagnosticirati napako ležajev grelnika ležajev in zvočni signal zbrati na - kontaktni način, kar je priročno za uporabo in ima nizko cenovno ugodnost.
(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) Ker lahko funkcijo neprekinjene gostote zmesi Gaussa uporabimo za bolj razumno opisovanje izhodne verjetnosti, je v prispevku predlagano novo metodo zvočne diagnostike napak, ki temelji na neprekinjeni gostoti mešanice Gaussove mešanice HMM (Continnuous Gaussova mešanica, skriti Markov model, CGHMM) . Hkrati se algoritem za usposabljanje in diagnozo izboljša z uporabo metode inicializacije parametra na osnovi grozda - in kalibracijskega koeficienta naprej - nazaj algoritma.
(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.