Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Stephan Heyns
  • Room 10-7
    Engineering 1 Building
    Department of Mechanical and Aeronautical Engineering
    University of Pretoria
    Pretoria
  • +2712 420 2432
  • Stephan Heyns received his BSc degree in mechanical engineering in 1978 (cum Laude) and his PhD in 1988 from the Univ... moreedit
The effect of the rotational speed and axial torque on the diagnostics of tapered rolling element bearing defects was investigated. The accelerometer was mounted on the bearing housing and connected to Sound and Vibration Analyzer (SVAN... more
The effect of the rotational speed and axial torque on the diagnostics of tapered rolling element bearing defects was investigated. The accelerometer was mounted on the bearing housing and connected to Sound and Vibration Analyzer (SVAN 958) and was used to measure the accelerations from the bearing housing. The data obtained from the bearing was processed to detect damage of the bearing using statistical tools and the results were subsequently analyzed to see if bearing damage had been captured. From this study it can be seen that damage is more evident when the bearing is loaded. Also, at the incipient stage of damage the crest factor and kurtosis values are high but as time progresses the crest factors and kurtosis values decrease whereas the peak and RMS values are low at the incipient stage but increase with damage. Keywords—crest factor, damage detection, kurtosis, RMS, tapered roller bearing.
Abstract: The angular accelerometer is a versatile inertial instrument, with applications ranging from vehicle stabilization to navigation and satellite pointing. A novel angular accelerometer is proposed, which is able to improve on... more
Abstract: The angular accelerometer is a versatile inertial instrument, with applications ranging from vehicle stabilization to navigation and satellite pointing. A novel angular accelerometer is proposed, which is able to improve on contemporary angular accelerometers and ...
ABSTRACT This paper compares two neural network input selection schemes, the Principal Component Analysis (PCA) and the Automatic Relevance Determination (ARD) based on Mac- Kay's evidence framework. The PCA takes all the input... more
ABSTRACT This paper compares two neural network input selection schemes, the Principal Component Analysis (PCA) and the Automatic Relevance Determination (ARD) based on Mac- Kay's evidence framework. The PCA takes all the input data and projects it onto a lower dimension space, thereby reduc- ing the dimension of the input space. This input reduction method often results with parameters that have significant influence on the dynamics of the data being diluted by those that do not influence the dynamics of the data. The ARD selects the most relevant input parameters and discards those that do not contribute significantly to the dynamics of the data being modelled. The ARD sometimes results with important input parameters being discarded thereby compromising the dynamics of the data. The PCA and ARD methods are implemented together with a Multi- Layer-Perceptron (MLP) network for fault identification in structures and the performance of the two methods is as- sessed. It is observed that ARD and PCA give similar accu- racy levels when used as input-selection schemes. There- fore, the choice of input-selection scheme is dependent on the nature of the data being processed.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:

And 8 more