Extraction of Principal Components from Multiple Statistical Features for Slurry Pump Performance Degradation Assessment

2015 ◽  
pp. 131-141 ◽  
Author(s):  
Peter W. Tse ◽  
Dong Wang
Keyword(s):  
Principal Components ◽  
Performance Degradation ◽  
Statistical Features ◽  
Pump Performance

Evaluating the Performance Degradation of Centrifugal Pumps Using the Principal Component Analysis

2021 ◽  
Author(s):  
Andrew Eaton ◽  
Wael Ahmed ◽  
Marwan A. Hassan
Keyword(s):  
Principal Component Analysis ◽  
Distribution Systems ◽  
Water Distribution ◽  
Principal Component ◽  
Component Analysis ◽  
Performance Degradation ◽  
Centrifugal Pumps ◽  
Pump Performance ◽  
Hydraulic Machines ◽  
Wide Range

Abstract Centrifugal pumps are used in a variety of engineering applications, such as power production, heating, cooling, and water distribution systems. Although centrifugal pumps are considered to be highly reliable hydraulic machines, they are susceptible to a wide range of damage due to several degradation mechanisms, which make them operate away from their best efficiency range. Therefore, evaluating the energy efficiency and performance degradation of pumps is an important consideration to the operation of these systems. In the present study, the hydraulic performance along with the vibration response of an industrial scale centrifugal pump (7.5KW) subjected to different levels of impeller unbalance were experimentally investigated. Extensive testing of pump performance along with vibration measurements were carried. Both time and frequency domain techniques coupled with principal component analysis (PCA) were used in this evaluation. The effect of unbalance on the pump performance was found to be mainly on the shaft power, while no change in the flow rate and the pump head were observed. As the level of unbalance increased, the power required to operate the pump at the designated speed increased by as much as 12%. The PCA found to be a useful tool in comparing the pump vibrations in the field in order to determine the presence of unbalance as well as the degree of damage. The results of this work can be used to evaluate and monitor pump performance under prescribed degradation in order to enhance preventative maintenance programs.

scholarly journals Investigation on centrifugal pump performance degradation under air-water inlet two-phase flow conditions

2018 ◽  
pp. 41-48 ◽  
Author(s):  
Qiaorui Si ◽  
Qianglei Cui ◽  
Keyu Zhang ◽  
Jianping Yuan ◽  
Gérard Bois
Keyword(s):  
Centrifugal Pump ◽  
Pressure Pulsation ◽  
Flow Characteristics ◽  
Performance Degradation ◽  
Inlet Pressure ◽  
Pulsation Frequency ◽  
Centrifugal Pumps ◽  
Two Phase ◽  
Flow Rates ◽  
Pump Performance

In order to study the flow characteristics of centrifugal pumps when transporting the gas-liquid mixture, water and air were chosen as the working medium. Both numerical simulation and experimental tests were conducted on a centrifugal pump under different conditions of inlet air volume fraction (IAVF). The calculation used URANS k-epsilon turbulence model combined with the Euler-Euler inhomogeneous two-phase model. The air distribution and velocity streamline inside the impeller were obtained to discuss the flow characteristics of the pump. The results show that air concentration is high at the inlet pressure side of the blade, where the vortex will exist, indicating that the gas concentration have a great relationship with the vortex aggregation in the impeller passages. In the experimental works, pump performances were measured at different IAVF and compared with numerical results. Contributions to the centrifugal pump performance degradations were analyzed under different air-water inlet flow condition such as IAVF, bubble size, inlet pressure. Results show that pump performance degradation is more pronounced for low flow rates compared to high flow rates. Finally, pressure pulsation and vibration experiments of the pump model under different IAVF were also conducted. Inlet and outlet transient pressure signals under four IAVF were investigated and pressure pulsation frequency of the monitors is near the blade passing frequency at different IAVF, and when IAVF increased, the lower frequency signal is more and more obvious. Vibration signals at five measuring points were also obtained under different IAVF for various flow rates.

scholarly journals Experimental Investigations on the Inner Flow Behavior of Centrifugal Pumps under Inlet Air-Water Two-Phase Conditions

Energies ◽  
2019 ◽  
Vol 12 (22) ◽  
pp. 4377 ◽  
Author(s):  
Si ◽  
Zhang ◽  
Bois ◽  
Zhang ◽  
Cui ◽  
...  
Keyword(s):  
Two Phase Flow ◽  
Flow Behavior ◽  
Bubbly Flow ◽  
Performance Degradation ◽  
Phase Flow ◽  
Centrifugal Pumps ◽  
Two Phase ◽  
Impeller Blade ◽  
Pump Performance ◽  
Starting Point

Centrifugal pumps are widely used and are known to be sensitive to inlet air-water two-phase flow conditions. The pump performance degradation mainly depends on the changes in the two-phase flow behavior inside the pump. In the present paper, experimental overall pump performance tests were performed for two different rotational speeds and several inlet air void fractions (αi) up to pump shut-off condition. Visualizations were also performed on the flow patterns of a whole impeller passage and the volute tongue area to physically understand pump performance degradation. The results showed that liquid flow modification does not follow head modification as described by affinity laws, which are only valid for homogeneous bubbly flow regimes. Three-dimensional effects were more pronounced when inlet void fraction increased up to 3%. Bubbly flow with low mean velocities were observed close to the volute tongue for all αi, and returned back to the impeller blade passages. The starting point of pump break down was related to a strong inward reverse flow that occurred in the vicinity of the shroud gap between the impeller and volute tongue area.

scholarly journals An Enhanced Factor Analysis of Performance Degradation Assessment on Slurry Pump Impellers

2017 ◽  
Vol 2017 ◽  
pp. 1-13 ◽  
Author(s):  
Shilong Sun ◽  
Peter W. Tse ◽  
Y. L. Tse
Keyword(s):  
Factor Analysis ◽  
Health Condition ◽  
Performance Degradation ◽  
Statistical Features ◽  
Oil Sand ◽  
Pump Impeller ◽  
Pass Filter ◽  
Low Pass Filter ◽  
Vibration Signals ◽  
Current Health

Slurry pumps, such as oil sand pumps, are widely used in industry to convert electrical energy to slurry potential and kinetic energy. Because of adverse working conditions, slurry pump impellers are prone to suffer wear, which may result in slurry pump breakdowns. To prevent any unexpected breakdowns, slurry pump impeller performance degradation assessment should be immediately conducted to monitor the current health condition and to ensure the safety and reliability of slurry pumps. In this paper, to provide an alternative to the impeller health indicator, an enhanced factor analysis based impeller indicator (EFABII) is proposed. Firstly, a low-pass filter is employed to improve the signal to noise ratios of slurry pump vibration signals. Secondly, redundant statistical features are extracted from the filtered vibration signals. To reduce the redundancy of the statistic features, the enhanced factor analysis is performed to generate new statistical features. Moreover, the statistic features can be automatically grouped and developed a new indicator called EFABII. Data collected from industrial oil sand pumps are used to validate the effectiveness of the proposed method. The results show that the proposed method is able to track the current health condition of slurry pump impellers.

scholarly journals Exploring the distribution of statistical feature parameters for natural sound textures

2020 ◽  
Author(s):  
Ambika P. Mishra ◽  
Nicol S. Harper ◽  
Jan W.H. Schnupp
Keyword(s):  
Principal Components ◽  
Ecological Validity ◽  
Principal Component ◽  
Future Research ◽  
Statistical Features ◽  
Running Water ◽  
Acoustic Environment ◽  
Acoustic Stimuli ◽  
Texture Parameters ◽  
Correlation Parameters

AbstractSounds like “running water” and “buzzing bees” are classes of sounds which are a collective result of many similar acoustic events and are known as “sound textures”. Recent psychoacoustic study using sound textures by [1] reported that natural sounding textures can be synthesized from white noise by imposing statistical features such as marginals and correlations computed from the outputs of cochlear models responding to the textures. The outputs being the envelopes of bandpass filter responses, the ‘cochlear envelope’. This suggests that the perceptual qualities of many natural sounds derive directly from such statistical features, and raises the question of how these statistical features are distributed in the acoustic environment. To address this question, we collected a corpus of 200 sound textures from public online sources and analyzed the distributions of the textures’ marginal statistics (mean, variance, skew, and kurtosis), cross-frequency correlations and modulation power statistics. A principal component analysis of these parameters revealed a great deal of redundancy in the texture parameters. For example, just two marginal principal components, which can be thought of as measuring the sparseness or burstiness of a texture, capture as much as 66% of the variance of the 128 dimensional marginal parameter space, while the first two principal components of cochlear correlations capture as much as 90% of the variance in over 1000 correlation parameters. Knowledge of the statistical distributions documented here may help guide the choice of acoustic stimuli with high ecological validity in future research.

scholarly journals Exploring the distribution of statistical feature parameters for natural sound textures

PLoS ONE ◽  
2021 ◽  
Vol 16 (6) ◽  
pp. e0238960
Author(s):  
Ambika P. Mishra ◽  
Nicol S. Harper ◽  
Jan W. H. Schnupp
Keyword(s):  
Principal Components ◽  
Ecological Validity ◽  
Principal Component ◽  
Future Research ◽  
Statistical Features ◽  
Running Water ◽  
Acoustic Environment ◽  
Acoustic Stimuli ◽  
Texture Parameters ◽  
Correlation Parameters

Sounds like “running water” and “buzzing bees” are classes of sounds which are a collective result of many similar acoustic events and are known as “sound textures”. A recent psychoacoustic study using sound textures has reported that natural sounding textures can be synthesized from white noise by imposing statistical features such as marginals and correlations computed from the outputs of cochlear models responding to the textures. The outputs being the envelopes of bandpass filter responses, the ‘cochlear envelope’. This suggests that the perceptual qualities of many natural sounds derive directly from such statistical features, and raises the question of how these statistical features are distributed in the acoustic environment. To address this question, we collected a corpus of 200 sound textures from public online sources and analyzed the distributions of the textures’ marginal statistics (mean, variance, skew, and kurtosis), cross-frequency correlations and modulation power statistics. A principal component analysis of these parameters revealed a great deal of redundancy in the texture parameters. For example, just two marginal principal components, which can be thought of as measuring the sparseness or burstiness of a texture, capture as much as 64% of the variance of the 128 dimensional marginal parameter space, while the first two principal components of cochlear correlations capture as much as 88% of the variance in the 496 correlation parameters. Knowledge of the statistical distributions documented here may help guide the choice of acoustic stimuli with high ecological validity in future research.

Structuring Assessments of Psychopathology

2006 ◽  
Vol 27 (2) ◽  
pp. 87-92 ◽  
Author(s):  
Willem K.B. Hofstee ◽  
Dick P.H. Barelds ◽  
Jos M.F. Ten Berge
Keyword(s):  
Principal Components ◽  
Personality Assessment ◽  
Clinical Sample ◽  
Principal Component ◽  
Normal Sample ◽  
Normative Sample ◽  
Assessment Data ◽  
Obsessive Compulsive ◽  
Oblique Rotation ◽  
Two Samples

Hofstee and Ten Berge (2004a) have proposed a new look at personality assessment data, based on a bipolar proportional (-1, .. . 0, .. . +1) scale, a corresponding coefficient of raw-scores likeness L = ΢XY/N, and raw-scores principal component analysis. In a normal sample, the approach resulted in a structure dominated by a first principal component, according to which most people are faintly to mildly socially desirable. We hypothesized that a more differentiated structure would arise in a clinical sample. We analyzed the scores of 775 psychiatric clients on the 132 items of the Dutch Personality Questionnaire (NPV). In comparison to a normative sample (N = 3140), the eigenvalue for the first principal component appeared to be 1.7 times as small, indicating that such clients have less personality (social desirability) in common. Still, the match between the structures in the two samples was excellent after oblique rotation of the loadings. We applied the abridged m-dimensional circumplex design, by which persons are typed by their two highest scores on the principal components, to the scores on the first four principal components. We identified five types: Indignant (1-), Resilient (1-2+), Nervous (1-2-), Obsessive-Compulsive (1-3-), and Introverted (1-4-), covering 40% of the psychiatric sample. Some 26% of the individuals had negligible scores on all type vectors. We discuss the potential and the limitations of our approach in a clinical context.

Comparison of Principal Component Solutions in Two Populations

Methodology ◽  
2016 ◽  
Vol 12 (1) ◽  
pp. 11-20 ◽  
Author(s):  
Gregor Sočan
Keyword(s):  
Simulation Study ◽  
Principal Components ◽  
Common Factor ◽  
Principal Component ◽  
Component Model ◽  
Bootstrap Procedure ◽  
Factor Loadings ◽  
Component Loadings ◽  
Principal Component Model ◽  
Two Populations

Abstract. When principal component solutions are compared across two groups, a question arises whether the extracted components have the same interpretation in both populations. The problem can be approached by testing null hypotheses stating that the congruence coefficients between pairs of vectors of component loadings are equal to 1. Chan, Leung, Chan, Ho, and Yung (1999) proposed a bootstrap procedure for testing the hypothesis of perfect congruence between vectors of common factor loadings. We demonstrate that the procedure by Chan et al. is both theoretically and empirically inadequate for the application on principal components. We propose a modification of their procedure, which constructs the resampling space according to the characteristics of the principal component model. The results of a simulation study show satisfactory empirical properties of the modified procedure.

Sign in / Sign up

Export Citation Format

Share Document