Artificial Neural Networks and Advanced Fuzzy Techniques for Predicting Noise Level in the Industrial Embroidery Workrooms

Figures & data

TABLE 1 Descriptive Statistics of Final Features of Embroidery Workrooms for Developing Noise Prediction Techniques

Features Type	Symbol	Unit	Minimum	Maximum	Mean	Std. Deviation
Workroom Acoustic Features
Average absorption coefficient		−	0.04	0.14	0.06	0.02
Room absorption constant	R	m^2	4.10	26.09	12.25	6.11
Reverberation time	RT	s	0.94	4.21	2.70	0.89
Embroidery Process Features
Number of embroideries	NE	−	1	4	1.24	0.53
Number of embroidery heads	NH	−	6	40	14.31	5.70
Embroidery lifetime	EL	Year	1	20	11.40	5.34
Embroidery speed	ES	Stitches/Min	690	850	747	39.24
Fabric type^a	FT	−	1	7	−	−
Machine-maker type^b	MT	−	1	2	−	−
Target Feature
Noise equivalent level	Leq	dB	79.40	88.70	85.20	1.96

^aThis feature was based on ordinal scale.

^bThis feature was based on nominal scale.

FIGURE 1 Histogram of noise-level distribution in embroidery workrooms.

FIGURE 2 Structure of typical adaptive neurofuzzy inference system.

TABLE 2 Comparison of Best ANN Prediction Models in the Training and Test phases

Model Developing Phase	Train		Test
Evaluation Criteria	RMSE (dB)	R^2	RMSE (dB)	R^2
ANNs with PCA	0.67	0.90	0.69	0.88
ANNs without PCA	0.79	0.84	0.84	0.79

FIGURE 3 Prediction errors of neural network structures in terms of the number of neurons for test data.

FIGURE 4 Comparison between measured and predicted Leq using ANNs with PCA for test data.

TABLE 3 Comparison of Advanced Fuzzy Prediction Models in the Training and Test Phases

Model Developing Phase	Train		Test
Evaluation Criteria	RMSE (dB)	R^2	RMSE (dB)	R^2
GENFIS	0.00	1	0.55	0.87
ANFIS	0.017	0.99	0.53	0.88

FIGURE 5 Comparison between measured and predicted Leq using ANNs without PCA for test data.

FIGURE 6 Comparison between the measured and the predicted Leq using GENFIS for the test data.

FIGURE 7 Comparison between the measured and the predicted Leq using ANFIS for the test data.

FIGURE 8 Membership functions related to embroidery speed.

FIGURE 9 Membership functions related to number of embroideries.

FIGURE 10 Typical rules graph of developed GENFIS for predicting noise level based on Sugeno approach.

FIGURE 11 Output in the form of 3D representation with embroidery machine speed and number of embroidery heads.

FIGURE 12 Output in the form of 3D representation with embroidery machine speed and embroidery machine-maker type.

FIGURE 13 Output in the form of 3D representation with embroidery lifetime and number of embroidery heads.

FIGURE 14 Output in the form of 3D representation with embroidery speed and number of embroideries.

FIGURE 15 Output in the form of 3D representation with number of embroidery heads and number of embroideries.

FIGURE 16 Graphical user interface based on the best ANN.