AI Powered Anomaly Detection and IoT Automation for Improving Textile Manufacturing Quality Management and Productivity Levels

S. Jayaraman; Kishore Kunal; Vairavel Madeshwaren; M. Kathiravan

doi:10.2478/ftee-2026-0005

.blurhash-client-img { display: none !important; }

AI Powered Anomaly Detection and IoT Automation for Improving Textile Manufacturing Quality Management and Productivity Levels

Fibres & Textiles in Eastern Europe

Volume 34 (2026): Issue 1 (February 2026)

By: S. Jayaraman, Kishore Kunal, Vairavel Madeshwaren and M. Kathiravan

Open Access

|Jun 2026

Figures & Tables

Table 1.

Data collection

Location	No. of Textile Units	Duration (Months)	Textile Process	Data Collected & Measurement Details
Tiruppur	12	6	Yarn Spinning	Yarn tension (measured on 100% cotton ring-spun yarn during winding) and dye consistency (color strength during dyeing of knitted fabric)
Coimbatore	10	6	Fabric Formation & Finishing	Fabric density (weft and warp density of grey woven cotton fabric) and humidity levels (in finishing hall)
Surat	8	6	Weaving	Machine vibration (loom vibration during shuttleless weaving) and fiber strength (cotton fiber tensile test before weaving)
Ludhiana	10	6	Knitting & Inspection	Temperature (knitting hall) and defect detection (visual inspection of knitted fabric for holes, uneven loops)
Bhilwara	10	6	Dyeing & Finishing	Moisture content (post-dyeing fabric) and thread elasticity (tested during weaving preparation)

Experimental setup of IoT for detecting fabric quality

Table 2.

Sensor Data Collected from Textile Manufacturing Units

Location	Fabric Type	Yarn Tension (N/m)	Moisture Content (%)	Dye Absorption (%)	Fabric Density (GSM)	Machine Vibration (Hz)	Defect Rate (%)	Temperature (°C)	Humidity (%)	Machine Speed (rpm)
Tiruppur	Cotton	11.5	6.2	85.4	180	55.3	3.2	28.5	65	1200
Coimbatore	Polyester	9.8	4.7	92.1	220	48.7	2.9	27.8	60	1100
Surat	Silk	13.2	7.4	87.8	140	59.8	4.1	29.2	70	1300
Ludhiana	Wool	10.9	5.5	89.6	200	52.1	3.5	26.7	55	1150
Bhilwara	Rayon	12.0	6.1	91.2	175	57.4	3.7	27.5	58	1250

Table 3.

Correlation between Machine Vibration and Defect Rate

Machine Type	Vibration (Hz)	Defect Rate (%)	Correlation Coefficient (R)	Thread Tension (N/m)	Power Consumption (kW)	Efficiency (%)
Spinning	55.3	3.2	0.87	11.2	7.5	92.4
Weaving	48.7	2.9	0.81	9.9	6.8	91.2
Dyeing	59.8	4.1	0.92	13.5	8.2	89.7
Finishing	52.1	3.5	0.85	10.8	7.1	90.5
Mixed Process	57.4	3.7	0.88	12.1	7.8	91.0

Table 4.

Machine downtime analysis before and after IoT implementation

Machine Type	Failure Rate Before (per month)	Failure Rate After (per month)	Reduction (%)	Maintenance Cost Before (USD)	Maintenance Cost After (USD)	Savings (%)
Spinning	12	4	66.7%	2,500	900	64.0%
Weaving	10	3	70.0%	2,000	750	62.5%
Dyeing	15	6	60.0%	3,200	1,400	56.3%
Finishing	8	2	75.0%	1,800	600	66.7%
Combined	11	4	63.6%	2,700	1,000	63.0%

Table 5.

AI-based defect detection accuracy

Fabric Type	Yarn Breakage (%)	Dye Mismatch (%)	Fabric Density Variance (%)	Detection Accuracy (%)	Processing Time (ms)	False Positives (%)	Model Efficiency (%)
Cotton	3.2	2.5	4.1	98.3	120	1.2	95.5
Polyester	2.9	2.1	3.7	97.6	115	1.5	94.8
Silk	4.1	3.8	5.2	96.9	130	2.1	93.9
Wool	3.5	2.9	4.5	97.2	125	1.8	94.2
Rayon	3.7	3.2	4.8	97.8	118	1.6	94.6

Table 6.

Digital twin optimization impact

Machine Parameter	Before Optimization	After Optimization	Improvement (%)	Quality Defects Before (%)	Quality Defects After (%)	Yield Improvement (%)
Yarn Tension (N/m)	11.2	12.8	14.3%	4.8	2.9	39.6%
Moisture Content (%)	5.8	6.5	12.1%	5.1	3.2	37.3%
Dye Absorption (%)	88.3	92.1	4.3%	6.2	4.1	33.9%
Fabric Density (GSM)	175	190	8.6%	5.7	3.5	38.6%

Table 7.

First-pass yield improvement

Production Stage	FPY Before IoT (%)	FPY After IoT (%)	Improvement (%)
Spinning	85.2	92.1	8.1
Weaving	82.7	90.4	9.3
Dyeing	78.5	88.0	12.1
Finishing	80.1	89.2	11.4

Table 8.

Yarn tension stability

Fabric Type	Standard Deviation of Yarn Tension		Improvement (%)
Fabric Type	Before IoT (N/m)	After IoT (N/m)	Improvement (%)
Cotton	2.8	1.5	46.4
Polyester	2.5	1.4	44.0
Wool	3.2	1.8	43.8
Silk	3.6	2.1	41.7
Rayon	3.0	1.7	43.3
Denim	2.4	1.3	45.8

Table 9.

Moisture content optimization

Fabric Type	Moisture Content		Optimization (%)
Fabric Type	Before IoT (%)	After IoT (%)	Optimization (%)
Cotton	7.2	6.4	11.1
Polyester	6.5	5.8	10.8
Wool	8.9	7.6	14.6
Silk	9.4	8.2	12.8
Rayon	7.8	6.9	11.5
Denim	6.1	5.5	9.8

Table 10.

Process-wise performance evaluation in textile manufacturing

Process	Avg. Production Time (hrs)	Defect Rate (%)	Resource Utilization (%)	Energy Consumption (kWh)
Knitting	11.5	5.2%	87.3%	230
Dyeing	14.2	7.8%	82.5%	280
Printing	12.7	6.3%	85.2%	250
Cutting	9.8	4.9%	89.7%	210
Sewing	13.4	5.6%	86.1%	240
Finishing	10.9	4.1%	90.2%	200
Packaging	8.6	3.5%	91.3%	180

Table 11.

Overall quality improvement index

Quality Metric	Before IoT (%)	After IoT (%)	Improvement (%)
Overall Defect Rate	8.3	5.6	32.5
First-Pass Yield	81.6	90.1	10.4
Production Efficiency	74.8	85.2	14.0

Table 12.

Environmental impact metrics

Environmental Metric	Before IoT	After IoT	Improvement (%)
Energy Consumption (kWh/batch)	1250	940	24.8
Water Usage (L/100 m² fabric)	850	620	27.1
CO₂ Emissions (kg CO₂/unit)	12.5	9.3	25.6
Fabric Waste (%)	8.1	5.2	35.8

Table 13.

ROI Analysis for different production scales

Production Scale	Installation Cost (USD)	Annual Savings (USD)	Payback Period (Months)	Productivity Gain (%)	Energy & Waste Savings (%)
Small (≤ 3,000 m²/month)	30,000	14,800	22	20.5	18–20
Medium (3,000–10,000 m²/month)	45,000	24,800	20	28.0	24–26
Large (≥ 10,000 m²/month)	60,000	38,500	18	33.5	27–29

Table 14.

Comparative AI performance

Algorithm	Accuracy (%)	Precision (%)	Recall (%)	F1-Score (%)	Processing Time (ms)	False Positives (%)
SVM	91.2	90.5	89.7	90.1	175	2.5
Random Forest	92.8	92.0	91.5	91.7	160	2.1
Deep Autoencoder	96.5	95.8	96.2	96.0	135	1.7
LSTM Forecasting	97.1	96.5	96.8	96.6	140	1.5
Hybrid IoT–AI (HIAF)	98.3	97.9	98.1	98.0	120	1.2

References

Authors

Metrics

Articles in this issue

DOI: https://doi.org/10.2478/ftee-2026-0005 | Journal eISSN: 2300-7354 | Journal ISSN: 1230-3666

Journal RSS Feed

Language: English

Page range: 49 - 63

Published on: Jun 11, 2026

Published by: Łukasiewicz Research Network-Łódź Institute of Technology

In partnership with: Paradigm Publishing Services

Publication frequency: Volume open

Keywords:

IoT-driven monitoring,

Smart textile manufacturing,

Quality control,

AI anomaly detection,

Digital twin,

Industry 4.0 automation

Related subjects:

Business and economics,

Business management,

Business informatics,

Process management,

Industrial chemistry,

Cellulose, paper and textiles,

Polymer science and technology,

Materials sciences,

Biomaterials and natural materials

© 2026 S. Jayaraman, Kishore Kunal, Vairavel Madeshwaren, M. Kathiravan, published by Łukasiewicz Research Network-Łódź Institute of Technology
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Volume 34 (2026): Issue 1 (February 2026)

AI Powered Anomaly Detection and IoT Automation for Improving Textile Manufacturing Quality Management and Productivity Levels

Figures & Tables

Fig. 1.

Fig. 2.

Table 1.

Fig. 3.

Fig. 4.

Fig. 5.

Table 2.

Table 3.

Table 4.

Table 5.

Table 6.

Fig. 6.

Fig. 7.

Fig. 8.

Table 7.

Fig. 9.

Table 8.

Table 9.

Table 10.

Table 11.

Table 12.

Table 13.

Table 14.

Paradigm

My account