Scholarlink

To reduce human intervention during the laundry process and achieve intelligent control of washing machines, this paper proposes a novel design model for intelligent washing machines. A Near-Infrared (NIR) spectroscopic sensor is installed inside the washing machine to collect data on the clothes to be laundered. Machine learning algorithms are then applied to analyze the data and determine the clothing materials, such as woolen or cotton/linen fabrics. The innovations and contributions of this study are as follows: (1) A specific application scenario integrating machine learning and intelligent washing machines is proposed, including a complete workflow description and transforming the problem into a classification task in the machine learning domain. (2) Multiple NIR sensors are compared, with comprehensive analysis of their advantages and disadvantages. (3) A KNN-based intelligent washing machine system service framework is constructed. (4) It is verified that machine learning algorithms can enable accurate material identification for washing machines, achieving an identification rate of up to 96.8%.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Analysis of Clothing Materials Using Near-Infrared Light Based on Machine Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Xinyuan Zhang,
  • Xiaoming Zhang,
  • Xiaolin Wang

摘要

To reduce human intervention during the laundry process and achieve intelligent control of washing machines, this paper proposes a novel design model for intelligent washing machines. A Near-Infrared (NIR) spectroscopic sensor is installed inside the washing machine to collect data on the clothes to be laundered. Machine learning algorithms are then applied to analyze the data and determine the clothing materials, such as woolen or cotton/linen fabrics. The innovations and contributions of this study are as follows: (1) A specific application scenario integrating machine learning and intelligent washing machines is proposed, including a complete workflow description and transforming the problem into a classification task in the machine learning domain. (2) Multiple NIR sensors are compared, with comprehensive analysis of their advantages and disadvantages. (3) A KNN-based intelligent washing machine system service framework is constructed. (4) It is verified that machine learning algorithms can enable accurate material identification for washing machines, achieving an identification rate of up to 96.8%.