Gang Rong

Hybrid fuzzy modeling of chemical processes

Fuzzy models have been proved to have the ability of modeling all plants without any priori information. However, the performance of conventional fuzzy models can be very poor in the case of insufficient training data due to their poor extrapolation capacity. In order to overcome this problem, a hybrid grey-box fuzzy modeling approach is proposed in this paper to combine expert experience, local linear models and historical data into a uniform framework. It consists of two layers. The expert fuzzy model constructed from linguistic information, the local linear model and the T-S type fuzzy model constructed from data are all put in the first layer. Layer 2 is a fuzzy decision module that is used to decide which model in the first layer should be employed to make the final prediction. The output of the second layer is the output of the hybrid fuzzy model. With the help of the linguistic information, the poor extrapolation capacity problem caused by sparse training data for conventional fuzzy models can be overcome. Simulation result for pH neutralization process demonstrates its modeling ability over the linear models, the expert fuzzy model and the conventional fuzzy model.

Simulation platform in the virtual factory laboratory system

Abstract A process simulation platform of a virtual factory laboratory system and its application to investigation of PCS and MES for process industries are introduced in this paper. Based on a dynamic simulation of a crude oil distillation process, we provide a detailed analysis of the development of dynamic-static hybrid simulation platform, which combines dynamic simulation of key units with static simulation of the whole industrial process and would help solve the problem of simulation efficiency. A hardware-in-the-loop (HIL) simulation is also presented by replacing the distillation unit with a real pilot distillation tower in the virtual factory laboratory system.

Virtual plant laboratory system of process industries for education

Abstract A kind of virtual plant laboratory system for process systems engineering education and research is developed, which is deemed an effective and applicable tool. The proposed system consists of pilot tanks, package simulation software of unit operation and a real enterprise information system including DCS, management database and MES (manufacturing execution system). Particularly, positive effects of customizing the virtual education systems to satisfy the needs of specific engineering education and research domain such as modeling, optimization and control of industrial plant, and development and implementation of enterprise information systems are highlighted.

VIRTUAL FACTORY LABORATORY SYSTEM AND ITS APPLICATION

Abstract This paper proposes a novel virtual factory laboratory system which includes enterprise applications and process modeling and simulation. The virtual factory is an enterprise-wide reference model for process industry which can simulate the production and the enterprise operation in many situations. Process simulation platform in the virtual factory is an open environment for modeling and simulating different processes, while enterprise application platform supports operation management research. User interface of this system, which presents physical model and information of enterprise, is built with virtual reality (VR) and visualization technique.

Industrial application of data reconciliation for hybrid systems

Abstract For hybrid systems which incorporate both dynamical and discrete event models in process industries, the mass balance models will be changed because of discrete scheduling events. The redundancy degree of whole sensor network is time variant so that the conventional data reconciliation is very difficult to be implemented. In this paper a new approach of data reconciliation for hybrid system is proposed and its industrial application is discussed. The whole process includes 15 units and more than 100 tanks. Comparing with AspenTech Advisor, the application results demonstrate the efficiency and consistency of the proposed approach.

Modelling and Advanced Process Control (APC) for Distillation Columns of Linear Alkylbenzene Plant

Abstract This paper introduces industrial application of model predictive control (MPC) for the series of columns in a linear alkylbenzene (LAB) complex. The APC system that is consisted of twelve controlled variables, twelve manipulated variables and eight disturbance variables is used to deal with the constrained multivariable control problem of the distillation columns. Firstly, process modelling that includes experimental test and process identification is presented. Then, the construction and implementation of the APC system for the distillation columns are discussed. Industrial application results show that the APC system can maintain the best operation for a long time and realize ultimate operating potential of the distillation columns.

Integration Optimization of Production and Utility System for Refinery-wide Planning

Abstract Traditional optimization of production system and utility system is carried out separately which cannot ensure that the entire refinery system is optimized globally. In this paper, a novel integrated approach is proposed to optimize process production planning and utility system operation simultaneously. A refinery-wide mixed integer nonlinear programming model is proposed and the traditional method and improved integrated method are compared. A real industrial example is conducted to demonstrate the effect of the proposed mathematical model. The results suggest that the integrated approach can provide not only significant benefits but also better energy utilization.

Virtual Factory Integrated Manufacturing System for Process Simulation and Monitoring

Abstract A virtual factory integrated manufacturing system combined with system simulation and virtual reality is introduced in this paper. We describe the system architecture and development methodology, provide the working principle of process simulation and monitoring in virtual factory, and then explain the detailed applications of virtual factory integrated manufacturing system. With the visualization and three-dimensional human-computer interaction about process and production data, this platform can provide effective supports on monitoring, control and operation of manufacturing system.

Model Management for Refinery Multi-Level Simulation and Optimization

Abstract A comprehensive simulation and optimization platform which offers a lot of functions such as decision analysis, production scheduling optimization and process dynamic simulation is urgently required for todays process industry. But this will generate a series of model management problems because models integrated in the platform belong to different classifications and interact with each other in some special applications. In this paper, a model management platform for refinery multi-level simulation and optimization is introduced. The platform, referring to a classical model management framework in decision supporting area, integrates different refinery models for different users and can coordinate computational tasks between models for multi-level application.

Optimizing Crude Oil Operations under Uncertainty

Abstract This paper presents a novel approach for refinery crude oil operations under uncertainty. Due to the flexibility of the crude oil scheduling, decisions made by deterministic optimizations are often conservative or lack of robustness or even infeasible, so in this paper future uncertainties are considered to improve feasibility and robustness of the schedule. To handle fluctuating product demand and uncertain ship arrival time, deterministic formulation is replaced by chance constrained programming. Through a series of examples, it proves that by using probabilistic programming, the solution of the problem provides a more robust scheduling under a comprehensive confidence level. The relationship between the probability and reliability of a planned operation is also discussed.