针对复杂化工过程故障分析和理解困难的问题,应用计算机领域中的EFSM切片技术和知识库方法,提出一种新的应用于化工过程故障诊断的解决方案。本文基于前人建立的扩展有限状态机(Extended Finite State Machine,EFSM)模型,选取系统操作流程中的异常对象作为切片准则。然后,利用邻接依赖图EFSM切片算法,给出求解故障对象相关变量数据依赖图的过程,通过宽度优先搜索变量数据依赖图考查各节点是否为故障源,建立故障诊断所需知识库。最后,列出基于EFSM切片的故障诊断推理的具体过程,以及根据构建的知识库进行的诊断工作。以双容水槽液位控制系统为例,计算EFSM切片,其规模有效约减为原模型的70%左右;进而得到相关变量数据依赖图,分析异常状态和故障源,使得基于EFSM切片的化工过程故障诊断方法的可行性得以验证,为化工过程故障诊断提供新的思路。
In chemical processes, fault diagnosis is relatively difficult due to the incomplete prior-knowledge and unpredictable production changes. To solve the problem, a case-based extension fault diagnosis (CEFD) method is proposed combining with extension theory, in which the basic-element model is used for the unified and deep fault description, the distance concept is applied to quantify the correlation degree between the new fault and the original fault cases, and the extension transformation is used to expand and obtain the solution of unknown faults. With the application in Tennessee Eastman process, the result indicates that CEFD method has a flexible fault representation, objective fault retrieve performance and good ability for fault study, providing a new way for diagnosing production faults accurately.
New approaches for facility distribution in chemical plants are proposed including an improved non-overlapping constraint based on projection relationships of facilities and a novel toxic gas dispersion constraint. In consideration of the large number of variables in the plant layout model, our new method can significantly reduce the number of variables with their own projection relationships. Also, as toxic gas dispersion is a usual incident in a chemical plant, a simple approach to describe the gas leakage is proposed, which can clearly represent the constraints of potential emission source and sitting facilities. For solving the plant layout model, an improved genetic algorithm (GA) based on infeasible solution fix technique is proposed, which improves the globe search ability of GA. The case study and experiment show that a better layout plan can be obtained with our method, and the safety factors such as gas dispersion and minimum distances can be well handled in the solution.
To explore the problems of dynamic change in production demand and operating contradiction in production process, a new extension theory-based production operation method is proposed. The core is the demand requisition, contradiction resolution and operation classification. For the demand requisition, the deep and comprehensive demand elements are collected by the conjugating analysis. For the contradiction resolution, the conflict between the demand and operating elements are solved by the extension reasoning, extension transformation and consistency judgment. For the operating classification, the operating importance among the operating elements is calculated by the extension clustering so as to guide the production operation and ensure the production safety. Through the actual application in the cascade reaction process of high-density polyethylene (HDPE) of a chemical plant, cases study and comparison show that the proposed extension theory-based production operation method is significantly better than the traditional experience-based operation method in actual production process, which exploits a new way to the research on the production operating methods for industrial process.
Chemical processes are complex, for which traditional neural network models usually can not lead to satisfactory accuracy. Selective neural network ensemble is an effective way to enhance the generalization accuracy of networks, but there are some problems, e.g., lacking of unified definition of diversity among component neural networks and difficult to improve the accuracy by selecting if the diversities of available networks are small. In this study, the output errors of networks are vectorized, the diversity of networks is defined based on the error vectors, and the size of ensemble is analyzed. Then an error vectorization based selective neural network ensemble (EVSNE) is proposed, in which the error vector of each network can offset that of the other networks by training the component networks orderly. Thus the component networks have large diversity. Experiments and comparisons over standard data sets and actual chemical process data set for production of high-density polyethylene demonstrate that EVSNE performs better in generalization ability.
