Predicting the Tear Strength of Woven Fabrics Via Automated Machine Learning: An Application of the CRISP-DM Methodology

Abstract

Textile and clothing is an important world industry that is currently being transformed by the adoption of the Industry 4.0 concept. In this paper, we use Data Mining (DM) technology and the CRoss-Industry Standard Process for DM (CRISP-DM) methodology to model the textile testing process, which assures that products are safe and comply with regulations and client needs. Real-world data were collected from a Portuguese textile company, which has the goal to reduce the number of attempts they take in order to produce a woven fabric. Thus, predicting the outcome of a given test is beneficial to the company because it can reduce the number of physical samples that are needed to be produced when designing new fabrics. In particular, we target two important textile regression tasks: the tear strength in warp and weft directions. To better focus on feature engineering and data transformations, we adopt an Automated Machine Learning (AutoML) during the modeling stage of the CRISP-DM. Several iterations of the CRISP-DM methodology were employed, using different data preprocessing procedures (e.g., removal of outliers). The best predictive models were achieved after 2 (for warp) and 3 (for weft) CRISP-DM iterations.

Promoting knowledge sharing performance in a knowledge management system: do knowledge workers’ behavior patterns matter?

“…For doing this research, we use the cross-industry standard process for data mining (CRISP-DM) methodology to model the knowledge workers’ behavior patterns testing process based on a hierarchical process model. This process model is defined at four levels of concept, namely, phase, generic task, specialized task and process instance (Ribeiro et al , 2020). Generally, we can summarize the life cycle of a data mining project throughout the CRISP-DM methodology.…”

Industry 4.0 in textile and apparel sector: a systematic literature review

“…Some opportunities for IoT application in the textile and apparel area are: Planning, control and management of the production chain : through the use of IoT, CPS, RFID and Machine-to-Machine (M2M) technologies, information regarding the customer, the product and the process is obtained in time real, providing an “optimal” scenario for the planning and management of the textile chain, allowing the production control, stock control, demand analysis, purchasing and logistics systems to act autonomously (Lee et al , 2018; Tsai, 2018; Hidayatno et al , 2019; Cui et al , 2019; Manglani et al , 2019; Pal and Yasar, 2020); Areas of creation and development : through the use of IoT technologies (RFID, M2M, networked sensors), it is possible to collect data generated throughout the life of the product, and use this information to increase the efficiency of its processes or the improvement of the products themselves (Surjit et al , 2016); Monitoring and maintenance : textile machines connected to the network through the IoT allow remote monitoring, maintenance and updating of equipment, whether performed by the owner or the supplier (Tsai, 2018; Ribeiro et al , 2020); Wearables : innovative textile products that, through the introduction of sensors and communication modules, connect clothing to the internet network, where, through IoT, they incorporate benefits that go beyond traditional comfort and style in their confection. This type of clothing can collect and transfer the user’s vital signs to a database, which stores, processes and analyzes them, formulating a diagnosis that can be sent to any intelligent device (Song et al , 2018; Chen et al , 2017; Fernández-Caramés and Fraga-Lamas, 2018; Bertola and Teunissen, 2018; Hidayatno et al , 2019; Carnevale et al , 2020; Corchia et al , 2020).…”

“…Monitoring and maintenance : textile machines connected to the network through the IoT allow remote monitoring, maintenance and updating of equipment, whether performed by the owner or the supplier (Tsai, 2018; Ribeiro et al , 2020);…”

Image-based textile decoding

“…Near-infrared spectroscopy revealed the material of yarns [36]. Machine learning also contributed to estimate the kinematic behavior of yarns [37]. In this paper, we aimed to analyze different patterns in a fabric.…”