K均值改进留一校验法在煤炭近红外光谱异常样本剔除中的应用研究

基金项目:

江苏省自然科学基金资助项目（BK20140215）

详细信息

Application research of improved K-means leave one out method in rejecting of abnormal samples of coal near infrared spectrum

Wangzhuang Coal Mine, Lu''an Environmental Protection and Energy Development Co., Ltd., Changzhi 046031, China

摘要: 针对现有留一校验法存在剔除异常样本耗时长、误判的缺陷，提出一种K均值改进留一校验法，并将其用于煤质分析中异常样本的检测与剔除。该方法首先利用K均值聚类法对样本进行聚类，得到可疑样本；然后将可疑样本作为验证集，通过留一校验法进行二次判别，剔除异常样本。实验结果表明，K均值改进留一校验法能快速、准确剔除异常样本，提高了模型的预测精度。
- 煤质 /
- 近红外光谱分析 /
- 异常样品 /
- K均值聚类 /
- 留一校验法
Abstract: In view of problems of time-consuming, misjudgment of rejecting abnormal sample existed in current leave one out method, an improved K-means leave one out method was put forward for detecting and eliminating abnormal sample in coal quality analysis. Firstly, the method uses K-means clustering method to cluster samples, and gets suspicious samples; then it takes suspicious samples as a validation set, adopts leave one out method to do quadratic distinguishing, so as to eliminate abnormal samples. The experimental results show that the K-means leave one out method can eliminate abnormal samples quickly and accurately, and improves prediction accuracy of models.
- coal quality /
- near infrared spectral analysis /
- abnormal samples /
- K-means clustering /
- leave one out method

1.	李旭，杨位，史云，李杰，董博. 基于千眼智能分析系统的综采设备联动控制方法. 煤矿安全. 2025(01): 237-243 . 百度学术
2.	党正伟. 智能工作面中采煤机与液压支架的协同控制分析. 能源与节能. 2025(01): 333-336 . 百度学术
3.	赵瑞峰. 综采工作面智能化系统设计与实践. 江西煤炭科技. 2025(02): 186-189 . 百度学术
4.	张顺. 改进双向A~*算法的矿井火灾逃生实时动态路径规划研究. 煤矿机电. 2024(01): 1-5 . 百度学术
5.	戴伟强，黄毅，黄庭，张维昊，张小龙，朱鹏飞，曹红亮. 探索城市生态及生态红线智能化监测监管体系建设——以深圳市为例. 环境生态学. 2024(11): 134-144+150 . 百度学术
6.	任远林. 基于NB-IoT和ZigBee的物联网智能建筑环境监控方法. 齐齐哈尔大学学报(自然科学版). 2023(02): 1-5+24 . 百度学术
7.	蔡治华，罗一民，刘聪，张启志，郑祝平. 基于温差发电的采煤机摇臂传感器供电技术研究. 煤炭工程. 2023(04): 129-134 . 百度学术
8.	严策. 智能化综采工作面采煤机与支架协同控制技术研究. 科技创新与生产力. 2023(08): 94-97 . 百度学术