Xiuxi Li

An expert system for real-time fault diagnosis of complex chemical processes

Abstract This paper presents the development and implementation of an expert system for real-time fault diagnosis of chemical processes. The expert system is applied as a real-time computer aided decision support system, providing operation suggestions to help field operators when abnormal situations occur. The knowledge base structure, representation of knowledge, and access to expertise are technically considered. Industrial applications to the fluid catalystic cracking process in refinery indicate that the expert system diagnoses abnormal events efficiently and promptly.

Nonlinear dynamic principal component analysis for on-line process monitoring and diagnosis

Abstract A nonlinear dynamic principal component analysis (ND-PCA) approach is developed in this paper based on dynamic PCA and the sigmoid basis function feed forward neural network (SBFN). Through ND-PCA an integrated framework for on-line monitoring and root-cause diagnosis is developed. The approach is verified and illustrated on the Tennessee Eastman benchmark process as a case study while noises were added on sensor readings. Results show that the proposed ND-PCA approach performs good incipient diagnosis capability and overall diagnosis correctness rate.

LUBRES: An expert system development and implementation for real-time fault diagnosis of a lubricating oil refining process

An expert system LUBRES (LUBricating oil Refining Expert System) is introduced in this paper. It helps plant operators in monitoring and diagnosing of abnormal situations in refining process of lubricating oil. The LUBRES structure, the knowledge base, and the inference machine are presented in detail. A new strategy is proposed for conflicts resolution - the sorting strategy of antecedents, and a selection strategy of knowledge rules in the memory knowledge base. Knowledge acquisition mechanism is based on an empirical knowledge table, while knowledge verification is carried out based on the directed graph approach. C++Builder and SQL Server 2000 have been used in developing the proposed system. LUBRES has been successfully implemented in Microsoft Windows Server environment. For 1 year, LUBRES has been used for monitoring and diagnosing of refining process of the lubricating oil. The industrial application of LUBRES proved its high reliability and accuracy.

Implementation of knowledge maintenance modules in an expert system for fault diagnosis of chemical process operation

Based on the authors previous work of developing an expert system for fault diagnosis of chemical processes, this paper presents principles and approaches of the knowledge base maintenance in the expert system. Development and implementation of maintenance modules for the knowledge base in the expert system for fault diagnosis of fluid catalytic cracking unit (FCCU) are reported in detail. Algorithms are proposed for integrality verification of five inconsistencies among heuristic rules: contradiction, redundancy, subsumption, circulation, and reclusion. The modules ensure the knowledge base and the expert system to work stably and efficiently. DELPHI and SQL SERVER are adopted in developing the modules. Application in FCCU fault diagnosis expert system shows that the modules work rationally and efficiently with user-friendly interface, besides its strong interactive feature and better performance of the expert system. The modules have been in continuous use in the expert system of fault diagnosis of FCCU installation in a refinery for the last two years.

An object/agent based environment for the Computer Integrated Process Operation System

Abstract This paper outlines an object/agent based system model for the Computer Integrated Process Operation System (CIPOS). Most previous studies have focused on the Computer Aided Process Operation system (CAPO), while they are standalone and not good at communication with each other. The system model proposed in this work can solve some key integrated problems in CIPOS, which are problem integration, task integration, tools integration and personnel involvement. An instantiated system, TE_CIPOS, is implemented to give further explanation and verification of the proposed object/agent based system model and its integrating environment.

A description of chemical processes based on state space

Abstract Status of chemical process can be specifically described in a state space. This paper presents a criterion for the state space of chemical processes and a concept describing a chemical process in state space. A case study is presented to explore the static and dynamic description based on the concept and a semi-quantitative optimization is found.

Systematic Analysis and Design of the Poly-Production Process for Power and Olefin from Natural Gas

Abstract A novel polygeneration system for olefin and power production from natural gas is proposed. Technological-economical evaluation is based on the internal rate of return (IRR) and exergy efficiency analysis. The proposed polygeneration system for simultaneous production of ethylene and propylene and electricity is energy integrated and thus more thermodynamically efficient and economically viable. IRR and exergy efficiency of the proposed polygeneration system are higher than that of GSMTO system 18.9% and 49.9%, respectively. The biggest exergy destruction segments and possible measures for improvement are investigated through simulation and thermodynamic analysis.

A web service based online optimization and monitoring system for chemical processing systems

Abstract Many information integration systems implemented in the process industry are based on Agent or CORBA technology. There are limitations in these schemes in terms of real time, security and stabilization in information communication. For a rational and better scheme, a novel web service based optimization and monitoring system is implemented, in which some professional software such as Matlab, G2, GAMS are described as web services by web service wrapper and registered in the UDDI register centre. Finally the practicability and validity of the online optimization and monitoring system are verified through the application in the product development of Nipagin ester.

Process Monitoring based on Nonlinear Wavelet Packet Principal Component Analysis

Abstract For using process operational data to realize process monitoring, kinds of improved Principal Components Analysis (PCA) have been applied to cope with complex industrial processes. In this paper, a novel nonlinear wavelet packet PCA (NLWPPCA) method, which combines input training network with wavelet packet PCA, is proposed. Wavelet packet PCA integrates ability of PCA to de-correlate the variables by extracting a linear relationship with what of wavelet packet analysis to extract auto-correlated measurements. Then methodology of process monitoring based on NLWPPCA is presented. Finally, the proposed approach is successfully applied to two case studies: process monitoring of an eight variables nonlinear process with noise and Tennessee Eastman process.

Comparative Analysis between Coal-to-Olefins with CCS and Methanol-to-Olefins

Abstract Development of the coal-to-olefins (CTO) is favourable in the context of increasingly severe oil supply shortage in China. However, it suffers the problem of high CO2 emissions. CTO processes therefore face increasing challenges from another alternative process, methanol-to-olefins (MTO). This paper models the CTO process with CCS, conducts a techno-economic comparison between the CTO process with CCS and MTO. The CTO process with CCS is slightly less thermodynamically efficient than the conventional CTO process. The corresponding mitigation cost of the process is 150 RMB/t, which is roughly equivalent to the current carbon tax. In comparison to the MTO process, the CTO process with CCS is competitive in product cost when considering carbon tax.