欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
位置：立项数据库 > 立项详情页
中文摘要：
针对工业反应过程的特点与在线监测的要求，基于多元统计技术，通过"完备"的多尺度样本数据与"完备"、"动态"更新的工业反应状况特征库的构造、优化（或最佳）特征（或原始）变量（个数）的确定、不同统计量判别性能的分析，提出一类具有高灵敏度、快捷、可靠的反应状况多尺度在线监测技术；提出一类混合建模与参数优化估计相结合的工业反应过程动态建模技术，基于已知机理模型框架、嵌入集总参数数学模型、融合生产数据中隐含的特征信息，并通过系统偏差校正，建立具有自适应性、能深刻刻画反应状况内部特征的动态机理数学模型；基于在线模拟残差分析、以及滑动时间窗口样本数据与参数优化估计法，实现工业反应状况快速、可靠的多尺度在线监测、趋势预测、以及故障预警与诊断；通过两类监测的优势与信息互补、相互解释，实现监测结果的决策层融合，最终实现快速、灵敏、全面、可靠的反应状况多尺度在线监测。该研究将保证工业反应过程安全、高效与稳定。
英文摘要：
industrial reaction；online monitoring；hybrid model；multivariate statistical analysis；visual monitoring
结论摘要：
反应是化工和工业生物过程的核心，反应状况关系着整个过程的运行品质。项目针对复杂工业反应状况在线监测，研究（1）基于特征成分或原始变量优选的多元统计在线监测技术。构建监测统计量，系统分析各成分或原始变量对监测性能的影响，发现传统的各类成分提取和保留算法存在有用信息分散和淹没问题、以及不同故障检测时存在无益信息的原始变量，分别提出基于故障敏感主成分、主元空间实时重构、故障相关独立元、重要独立元加权、集成学习等成分优选策略、以及基于原始变量智能优选的过程在线监测方法，显著提升在线监测性能。（2）复杂反应过程混合建模技术。系统分析已知的反应过程机理知识，结合参数优化技术，提出基于神经网络反应速率模型、支持向量回归反应速率常数模型、双神经网络与机理模型混联的混合动力学模型、以及基于实验室混合动力学模型非线性校正的工业混合动力学模型，通过融合已知机理和各数据源信息，建立深刻刻画反应状况内部特征的混合动力学模型。（3）融合数据驱动和解析模型的过程在线监测技术。基于数据驱动的方法描述多模态特征，克服解析模型在模态识别上的不足、以及难以同时精确描述多个模态空间特性的缺点；利用子空间辨识技术获取状态空间模型；利用未知输入观测器理论，为各个操作模态开发对应的基于观测器设计的故障检测与诊断方法，克服统计过程监测缺乏有效描述过程动态性的缺点，融合技术实现两类方法的互补，提升了在线监测性能。（4）过程可视化在线监测技术。提出融合分类相关成分分析、Fisher判别分析、规范变量分析、以及统计量模式分析，基于自组织映射网络的可视化在线监测技术，获得各运行状况的清晰分割映射平面；在TE过程应用中，可视化区分达到目前文献报到的最好结果。相关算法在连续搅拌釜式反应器、TE过程、对二甲苯氧化反应过程、葡萄糖酸钠发酵过程、青霉素发酵过程等中应用，实现相关过程工业反应状况快速、灵敏、全面、可靠、直观的在线监测。研究成果发表学术论文70篇，其中SCI收录68篇，EI收录53篇，中科院SCI一区论文22篇、二区论文20篇，3篇AIChE Journal，10篇Industrial & Engineering Chemistry Research；培养毕业博士6名、硕士12名，1名博士获洪堡基金；获上海市优秀硕士论文2篇，华东理工大学优秀硕士论文4篇。
成果综合统计
期刊论文
会议论文
专利
获奖
著作
期刊论文
Self-adaptive Co-evolution differential evolution algorithm for optimal design of water distribution
Chemical process dynamic optimization based on hybrid differential evolution algorithm integrated wi
Fault Diagnosis in Chemical Process Based on Self-organizing Map Integrated with Fisher Discriminant
Transforming input variables for RBFN based on PCA-ASH multivariate correlation analysis and its app
Selection and transformation of input variables for RVM based on MIPCAMI and 4-CBA concentration mod
Simulation and analysis of dehydration distillation column based on distillation mechanism integrate
Distributed Statistical Process Monitoring Based on Four-Subspace Construction and Bayesian Inferenc
Optimization of RBF Neural Networks Using a Rough K-Means Algorithm and Application to Naphtha Dry P
Multi-Block Independent Component Analysis Integrated with Hellinger Distance and Bayesian Inference
Self-adaptive Differential Evolution Algorithm with Zoning Evolution ofControl Parameters and Adapti
Multi-objective modified differential evolution algorithm with archive-base mutation for solving mul
Optimization of a Multilayer Neural Network by Using Minimal Redundancy Maximal Relevance-Partial Mu
Double-step Block Division Plant-Wide Fault Detection and Diagnosis Based on Variable Distribution a
Batch Process Monitoring Based on Multisubspace Multiway Principal Component Analysis and Time-Serie
Batch process monitoring based on just-in-time learning and multiple-subspace principal component an
Modified Radial Basis Function Neural Network Integrated with Multiple Regression Analysis And Its A
Global best harmony search algorithm with control parameters co-evolution based on PSO and its appli
Statistical process monitoring based on improved principal component analysis and its application to
Hybrid Model of Industrial p-Xylene Oxidation Incorporated Fractional Kinetic Model with Intelligent
Weighted kernel principal component analysis based on probability density estimation and moving wind
Chemical process dynamic optimization based on the differential evolution algorithm with an adaptive
Independent component analysis-based non-Gaussian process monitoring with preselecting optimal compo
Reservoir Computing with Sensitivity Analysis Input Scaling Regulation and Redundant Unit Pruning fo
Fault detection and isolation in hybrid process systems using a combined data-driven and observer-de
Improved simple deterministically constructed Cycle Reservoir Network with Sensitive Iterative Pruni
Fault detection and identification using a Kullback-Leibler divergence based multi-block principal c
Chaotic Differential Evolution Algorithm Based on Competitive Coevolution and Its Application to Dyn
Fault detection in non-Gaussian processes based on mutual information weighted independent component
Modified kerenel regression integrated with monotonicity knowledge and its application to chemical e
Burning side reaction model of the INVISTA oxidation process using a radial basis function neural ne
Differential evolution algorithm with self-adaptive strategy and control parameters for P-xylene oxi
Harmony search algorithm with differential evolution based control parameter co-evolution and its ap
Nonlinear plant-wide process monitoring using MI-spectral clustering and Bayesian inference-based mu
Fault diagnosis and process monitoring using a statistical pattern framework based on a self-organiz
A comparative study of hybrid models combining various kinetic and regression models for p-xylene ox
Estimating the chemical reaction kinetics of p-xylene oxidation using artificial neural network with
Joint probability density and double weighted independent component analysis for Multimode Non-Gauss
Dynamic process fault detection and diagnosis based on dynamic principal component analysis, dynamic
Fault detection in nonlinear chemical processes based on kernel entropy component analysis and angul
Hybrid model for main and side reactions of p-xylene oxidation with prior knowledge based monotone a
Probabilistic monitoring of chemical processes using adaptively weighted factor analysis and its app
Non-Gaussian chemical process monitoring with adaptively weighted independent component analysis and
相关项目
颜学峰的项目