基于交互可视分析的多规格厚板板形质量异常诊断与回溯  

Interactive visual analytics-based diagnosis and traceback of shape quality anomalies in multi-category heavy plates

作　　者：张同康 王睿博 曾诚 丁进良 ZHANG TongKang;WANG RuiBo;ZENG Cheng;DING JinLiang(State Key Laboratory of Synthetical Automation for Process Industries,Northeastern University,Shenyang 110819,China)

机构地区：[1]东北大学流程工业综合自动化国家重点实验室,沈阳110819

出　　处：《中国科学：技术科学》2024年第9期1693-1706,共14页Scientia Sinica(Technologica)

基　　金：国家重点研发计划(编号:2022YFB3304700);国家自然科学基金(批准号:61988101);辽宁省中央引导地方科技发展专项(编号:2022JH6/100100055)资助项目。

摘　　要：厚板的板形质量对于产品的使用性能和市场竞争力至关重要.由于厚板生产过程的复杂性和生产数据的高维、多源、异构以及规模大等特征,有效地分析诊断板形质量的异常及其原因是一项极具挑战性的任务.采用数据可视化与人机交互技术,本文提出了一种基于交互式可视分析的多规格厚板板形质量异常诊断与回溯方法及系统.以多视角、多层次的数据呈现方式,为用户提供了一个直观且深入的工业大数据分析探索环境,能够通过人机交互协助快速识别板型质量异常,并分析生产过程数据与板形质量变化的内在关联,进而回溯板形异常的潜在原因.采用国内某钢铁企业的实际厚板生产数据进行的集成实验,验证了所提方法和系统的有效性和实用性.The quality of the shape of heavy plates is crucial for the product’s performance and market competitiveness.Due to the complexity of the heavy plate production process and the characteristics of the production data,which are high-dimensional,multi-source,heterogeneous,and large-scale,effectively analyzing,diagnosing,and tracing the causes of shape quality anomalies is a highly challenging task.Based on data visualization and human-computer interaction technologies,this paper proposes an interactive visual analytics-based approach and system for diagnosing and tracing shape quality anomalies in multi-specification heavy plates.The system provides users with an intuitive and in-depth industrial big data analysis and exploration environment through multiple perspectives and multi-level data presentation methods.It enables rapid identification of shape quality anomalies through humancomputer interaction,analyzes the inherent association between production process data and shape quality changes,and traces back to the potential causes of shape anomalies.Integrated experiments conducted with actual heavy plate production data from a domestic steel company confirm the effectiveness and practicality of the proposed approach and system.

关 键 词：板形质量 质量异常 诊断与回溯 可视分析 人机交互 工业大数据 

分 类 号：TG115[金属学及工艺—物理冶金]