Application of a Novel Method for Machine Performance Degradation Assessment Based on Gaussian Mixture Model and Logistic Regression

The currently prevalent machine performance degradation assessment techniques involve estimating a machine＇s current condition based upon the recognition of indications of failure features,which entail complete data collected in different conditions.However,failure data are always hard to acquire,thus making those techniques hard to be applied.In this paper,a novel method which does not need failure history data is introduced.Wavelet packet decomposition（WPD） is used to extract features from raw signals,principal component analysis（PCA） is utilized to reduce feature dimensions,and Gaussian mixture model（GMM） is then applied to approximate the feature space distributions.Single-channel confidence value（SCV） is calculated by the overlap between GMM of the monitoring condition and that of the normal condition,which can indicate the performance of single-channel.Furthermore,multi-channel confidence value（MCV）,which can be deemed as the overall performance index of multi-channel,is calculated via logistic regression（LR） and that the task of decision-level sensor fusion is also completed.Both SCV and MCV can serve as the basis on which proactive maintenance measures can be taken,thus preventing machine breakdown.The method has been adopted to assess the performance of the turbine of a centrifugal compressor in a factory of Petro-China,and the result shows that it can effectively complete this task.The proposed method has engineering significance for machine performance degradation assessment.

Artificial woodland degradation in semi-arid agro-pastoral transitional area： conceptual model and status assessment

Planting trees was used as one of cost-effective measures for desertification control in add and semi-add areas of China. Woodland degradation, however, is becoming an inevitable issue in these areas. In this paper, a typical county, Ejin Holo County, Inner Mongolia, China was selected for its assessment of artificial woodland degradation. A conceptual model for woodland degradation was delineated qualitatively based on field sampling survey, and four model-based indicators as humidity index （HI）, vegetation index （NDVI）, soil type （ST） and soil erosion modulus （EM） were screened out and used to a GIS-based method for artificial woodland degradation assessment in this semi-add agro-pastoral transitional area. All the indicator layers were overlaid and desertification assessed using simplified equation with equal weights for each indicators. The assessment results showed that in 336. 09 km^2 of total woodland area, 311.35 km^2 woodland were under degradation, and the area for slight, medium, severe degradation was 78.97, 119.73 and 112.65 km^2, respectively. It was suggested that much attention should be paid on woodland improvement and plant species selection, especially shrub species, before revegetation in similar areas.

Research of Step-down Stress Accelerated Degradation Data Assessment Method of a Certain Type of Missile Tank

The performance degradation rates of the missile tank are generally time-varying functions uneasily evaluated by general classical evaluation methods. This paper develops a segmented nonlinear accelerated degradation model （SNADM） based on the equivalent method of accumulative damage theory, which tackles the problem that product life is difficult to be determined with degradation rate being a function of the variable of time. A segmented expression of the function of population accumulative degradation is derived. And combined with nonlinear function, an accelerated degradation function, i.e., SNADM is obtained. The parameters of the SNADM are identified by numerical iteration, and the statistical function of degradation track is extrapolated. The reliability function is determined through the type of random process of the degradation distribution. Then an evaluation of product storage life is undertaken by combining the statistical function of degradation track, reliability function and threshold. An example of a missile tank undergoes a step-down stress accelerated degradation test （SDSADT）, in which the results with the SNADM and the classical method are evaluated and compared. The technology introduced is validated with the resultant coincidence of both evaluated and field storage lives.