Papers by Author: H.I. Liu

Abstract: High Speed Centrifugal Hydrogen Compressors are big and critical equipments which are widely used in chemical enterprises. It is very important to monitor their condition on-line and diagnose their failure. Based on the research of EMD (empirical mode decomposition) and correlation dimension and experimental simulation, the vibration signals of a High Speed Centrifugal Hydrogen Compressor’s main spindle are collected when working. Then the signals are decomposed by EMD, their correlation dimensions are calculated and taken as fault feature. Finally, using BP algorithm of a neural network in which there are 3 lays, a satisfied effect of fault diagnosis of a High Speed Centrifugal Hydrogen Compressor has been got. The experiment has confirmed that the method is advanced, reliable and practical. A new method is provided for High Speed Centrifugal Hydrogen Compressors’ fault diagnosis.

Abstract: High Speed Brushes Aeration Mechanics are the effective aeration equipments which are widely used in the environmental protection. Because of the big span of main spindle and its high speed when it is working, the breakdown sometimes occurs. It is very importance to monitor its condition and diagnose its breakdowns. Turbulent Flow Displacement Sensors are the non-contact types which are based on eddy current effect. It has many advantages, such as good linearity, wide frequency response scope, convenience installment and so on. So it is very suitable for the main spindle’s vibration signals of a high speed brushes aeration mechanic are monitored. With the development of Artificial Neural Networks technology, the equipment breakdown diagnosis has realized intellectualization. The recognition of equipment failure types is one of the most important studying domains of Artificial Neural Networks at present. Based on the research of eddy current effect and Artificial Neural Networks, we build up a test system which can monitor condition and diagnose breakdown to a GSB-12 high speed brushes aeration mechanic. With the help of it, the vibration signals of the measurement points on the main spindle are measured at two mutually vertical positions. The signals’ base frequency and multiplicative frequency are taken as characteristic value. Six common breakdowns are selected and to be taken as the standard sample and there are 3 lays in the neural network. Using FBP algorithm, we get a satisfied effect. The experiment has confirmed that this method is advanced, reliable and practical. It provides a new method about intelligent monitor and breakdown diagnosis to high speed brushes aeration mechanics’ condition.