An Industrial Dyeing Recipe Recommendation System for Textile Fabrics Based on Data-Mining and Modular Architecture Design

Qin, Xianan; Zhang, Xiaoming John

doi:10.1109/access.2021.3117261

Cited by 10 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The multivariate linear regression modeling is conducted on an industrial dyeing dataset which has been reported in the earlier report [14]. The dataset is consisted of 810 industrial dyeing records for rayon fabrics using a combination of three reactive dyes (CRD-red, CRD-Navy blue and CRD-yellow).…”

Section: Data Collection and The Settings For Regression Modelingmentioning

confidence: 99%

“…where ݇ is the i-th model parameter (݇ stands for the constant term); R, G and B stand for the RGB values; L, a and b stand for the CIELAB values. The complete dataset is randomly divided into two parts for model training and testing under a ratio of 60% to 40%, which is under the same setting as in reference [14]. Mean absolute error (MAE), mean absolute percent error (MAPE) and weighted absolute percent error (WAPE) are used to quantify the model performance.…”

Section: Data Collection and The Settings For Regression Modelingmentioning

confidence: 99%

“…Mean absolute error (MAE), mean absolute percent error (MAPE) and weighted absolute percent error (WAPE) are used to quantify the model performance. The definitions of these metrics are shown as below [14], [20]:…”

Section: Data Collection and The Settings For Regression Modelingmentioning

confidence: 99%

“…Thanks to the development of modern industrial big-data techniques [9][10][11][12][13], it is now feasible to build such recommenders based on industrial manufacturing records from the dyeing manufacturers. In our earlier work, we have reported the building of such a recommender based on a modular architecture structured system, in which individual gradient boosting regression trees (GBRT) are trained from dyeing manufacturing records for single types of fabric versus dye combinations [14]. GBRT can predict dye concentrations with prediction errors as good as ~7-10% [14], and have also been successfully applied into other applications with great model performance [15][16][17][18].…”

Section: Introductionmentioning

confidence: 99%

“…Despite the success of using GBRT, the earlier report lacks baselines for comparison [14]. It is thus helpful to conduct the model training on simpler regression models, e.g.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Improving the Performance of Industrial Dyeing Recipe Models by Taking Log-Transform in the Data Pre-Processing

Song²,

Qin

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Recent research advances on fabric dyeing have focused on modeling the relationship between dye concentrations and the final color on fabrics. The emerging techniques in related studies have great potential to evolve the traditional dyeing industry to manufacture much more smartly. Given that dyeing is a complex process regulated by many factors, one of the challenging problems in the aforementioned techniques is to maintain the modeling accuracy at acceptable level. Other than developing high-performance algorithms and model architectures, it is also important to include effective data pre-processing techniques in modeling. In this paper, we show that conducting log-transform to the industrial dyeing data can greatly improve the performance of industrial dyeing recipe models. Such observations are confirmed on modeling tasks using different formats of color as input and different types of loss function in the model training. These findings may provide useful implications for related studies for the dyeing industry.

show abstract

Section: Data Collection and The Settings For Regression Modelingmentioning

confidence: 99%

Section: Data Collection and The Settings For Regression Modelingmentioning

confidence: 99%

Section: Data Collection and The Settings For Regression Modelingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Despite the success of using GBRT, the earlier report lacks baselines for comparison [14]. It is thus helpful to conduct the model training on simpler regression models, e.g.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Improving the Performance of Industrial Dyeing Recipe Models by Taking Log-Transform in the Data Pre-Processing

Song²,

Qin

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

show abstract

A Data-Driven Approach for Predicting Industrial Dyeing Recipes of Polyester Fabrics

Xie,

Zhang,

Zhang

et al. 2024

Fibers Polym

View full text Add to dashboard Cite

Adaptive Information Fusion Using Evidence Theory and Uncertainty Quantification

Arévalo,

Alison,

Ibrahim

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Fault detection systems support the operator, providing insight during the decision-making while having an (unknown) fault. Data-based models are a common option for a detection system. However, systems that rely purely on data-based models are normally trained with a specific set of data, which cannot necessarily prevent data drift. Thus, an anomaly or unknown condition detection mechanism is required to handle data with new fault cases. Besides, the model's capability to adapt to the unknown condition is equally important to anomaly detection-in other words, its capability to update itself automatically. Alternatively, expert-centered models are powered by the knowledge of operators, which provides the models with production context and expert domain knowledge. The challenge lies in combining both systems and which framework can be used to achieve this fusion. We propose an adaptive information fusion methodology to define fault detection systems using evidence theory and uncertainty quantification. The main contribution of this paper is providing a general framework for the fusion of n number of information sources using the evidence theory. The fusion provides a more robust prediction and an associated uncertainty that can be used to assess the prediction likeliness. Moreover, we provide a methodology for the information fusion of two primary sources: an ensemble classifier based on machine data and an expert-centered model. We demonstrate the information fusion approach using data from an industrial setup, which rounds up the application part of this research. Furthermore, we address the problem of data drift by proposing a methodology to update the data-based models using an evidence theory approach. We validate the approach using the Benchmark Tennessee Eastman while doing an ablation study of the model update parameters.

show abstract

An Industrial Dyeing Recipe Recommendation System for Textile Fabrics Based on Data-Mining and Modular Architecture Design

Abstract: for very helpful discussion regarding the design of the system framework, Ms. Yaguang Wang for performing data cleaning for the industrial dataset used in this work, Mr. Zhiwen Tu for regression model training, and Miss Yawen Yin for the proof-reading.

Cited by 10 publications

References 16 publications

Improving the Performance of Industrial Dyeing Recipe Models by Taking Log-Transform in the Data Pre-Processing

Improving the Performance of Industrial Dyeing Recipe Models by Taking Log-Transform in the Data Pre-Processing

A Data-Driven Approach for Predicting Industrial Dyeing Recipes of Polyester Fabrics

Adaptive Information Fusion Using Evidence Theory and Uncertainty Quantification

Contact Info

Product

Resources

About