【作者】 邵景峰； 贺兴时； 王进富； 白晓波； 雷霞； 刘聪颖；

【Author】 SHAO Jingfeng;HE Xingshi;WANG Jinfu;BAI Xiaobo;LEI Xia;LIU Congying;School of Management Xi’an Polytechnic University;

【机构】 西安工程大学管理学院；

【摘要】 为解决纺织制造过程中的系统集成与数据管理问题,首先,依据纺织制造过程工艺流程,对各工序产生的海量数据进行了分析,对计划层与车间制造层之间信息无法衔接的问题进行了研究;然后,在原有系统数据,以及文本类型的原料、传感器,纱疵检测图像数据的基础上,构架了一种基于Hadoop的三层纺织大数据存储体系;其次,利用D-S证据、增量聚类理论方法,对多源纺织数据融合技术难点进行了设计,提出了相应的算法与模型,进而对系统功能进行了设计。通过测试,结果表明该系统通过数据间的相关性实现了计划层与制造层之间信息的有效衔接,解决了信息"孤岛"问题,并为大数据环境下织物质量的实时在线检测提供了新方法。更多还原

【Abstract】 To solve system integration and data management problems in the textile manufacturing process, firstly, through the textile manufacturing technology process, the massive data of each process was analyzed, and the inefficient convergence phenomenon of textile information between production planning layer and workshop manufacturing layer was studied. Secondly, on the basis of the original system data, and text data of raw materials, sensor, yarn defect detection image data, and so on, a three layer textile big data storage system based on Hadoop was built. Thirdly, through using theoretical methods of D-S evidence and incremental clustering, the technical difficulties that was multi-source textile data fusion was designed, the appropriate algorithms and models were proposed, and then functions of the system were designed. Through the test, the results showed that the system we designed have realized the effective information link between planning layer and production layer by the correlation between data, solved the ‘information island’ problem, and provided a new method for real-time online detection of fabric quality in big data environment.更多还原