Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

The CPM with FFT DAQ System.

More »

Fig 1 Expand

Fig 2.

The Basic architecture of the model.

More »

Fig 2 Expand

Fig 3.

EDA architecture for CPM Dataset.

More »

Fig 3 Expand

Table 1.

The 5-point summary of CPM dataset.

More »

Table 1 Expand

Fig 4.

Hypothesis testing of CPM dataset.

More »

Fig 4 Expand

Fig 5.

Boxplot analysis of casing, impeller & bearing vibration.

More »

Fig 5 Expand

Fig 6.

Pie chart of dependent variables.

More »

Fig 6 Expand

Fig 7.

Bivariate analysis using line plot for casing, bearing & impeller vs pressure.

More »

Fig 7 Expand

Fig 8.

Bivariate analysis using bar plot for pressure, current & voltage vs condition.

More »

Fig 8 Expand

Fig 9.

Heatmap of CPM dataset.

More »

Fig 9 Expand

Fig 10.

Impeller vs casing with bearing scatter.

More »

Fig 10 Expand

Fig 11.

K-means clustering of bearing vs c_temp vs casing.

More »

Fig 11 Expand

Fig 12.

Logistic Classifier Confusion Matrix.

More »

Fig 12 Expand

Table 2.

Statistic Result of Logistic Regression Classifier.

More »

Table 2 Expand

Fig 13.

Naïve Bayes Classifier Confusion Matrix.

More »

Fig 13 Expand

Table 3.

Statistic Result of Naïve Bayes Classifier.

More »

Table 3 Expand

Fig 14.

Confusion Matrix for Support Vector Classifier.

More »

Fig 14 Expand

Table 4.

Statistic Result of Support Vector Classifier.

More »

Table 4 Expand

Fig 15.

RF Tree and Confusion Matrix for Random Forest.

More »

Fig 15 Expand

Table 5.

Statistic Result of Random Forest Classifier.

More »

Table 5 Expand

Table 6.

Performance Table for ML Models.

More »

Table 6 Expand

Fig 16.

Performance & computational efficiency comparison of ML models.

More »

Fig 16 Expand

Fig 17.

Training -validation accuracy & lost for ANN.

More »

Fig 17 Expand