基于静−动态特性协同感知的复杂工业过程运行状态评价

针对当前过程监测和运行状态评价方法等对工况信息感知不全面、漏报和误报现象严重等问题, 在深入研究工业现场数据静−动态特性协同感知方法的基础上, 提出关键性能指标(Key performance indicators, KPI)驱动的慢特征分析(Slow feature analysis, SFA)算法. 将关键性能指标信息融入到慢特征分析中, 协同感知复杂工业过程的静−动态特性变化, 并进一步通过计算潜变量之间的相似度及其一阶差分间的相似度实现对过程稳态和过渡的评价. 在此基础上, 建立基于静−动态特性协同感知的过程运行状态评价统一框架. 针对非优状态, 提出基于稀疏学习的非优因素识别方法, 实现对非优因素变量的准确识别. 最后, 通过重介质选煤过程实际生产数据和田纳西·伊斯曼(Tennessee Eastman, TE)过程数据验证了该方法的有效性.

Evaluation of Complex Industrial Process Operating State Based on Static-dynamic Cooperative Perception

Current process monitoring and operation performance evaluation methods suffer from inadequate capturing of process information as well as severe missed and false alarms. By performing in-depth analysis of methods for concurrent monitoring static-dynamic characteristic of industrial data, this paper proposes a key performance indicators (KPI)-driven slow feature analysis (SFA) algorithm. It integrates KPI information into SFA model in order to concurrently capture static-dynamic characteristic changes of complex industrial processes. The similarity between latent variables and that between first-order differences are computed to evaluate the optimality of static and transitional operations. On this basis, a unified framework for process operation performance assessment is established based on an integrated perception of static-dynamic characteristics. A sparse learning-based non-optimal factor identification method is proposed to effectively highlight root-cause variables that cause unsatisfactory performance. The feasibility and effectiveness of the proposed method are validated based on data collected from a real-world dense medium coal preparation process and the Tennessee Eastman (TE) process.