基于定性趋势分析的SDG故障诊断方法及其工业应用研究
|
摘要
随着生产技术的不断发展进步,现代石油炼制过程,变得越来越自动化和大型化,但同时也日益复杂化。由于人为误操作、传感器故障、控制器故障、工艺参数变动等原因,异常工况或故障时有发生,给企业造成巨大的经济损失和人员伤亡。因此当异常工况发生时,如何及时准确地确定故障源,避免更加重大的损失和更加严重的事故成为必须要解决的重大问题。
SDG(符号有向图)模型是一种定性模型,能够从本质上描述故障传播的潜在路径,基于SDG的故障诊断方法具有完备性高、鲁棒性强、能够解释故障剧情等优点,近些年来,成为一个研究热点。
然而基于SDG方法存在的一些问题,限制了其在实际工业上的应用。建模方面,目前的SDG建模方法很多,各有优缺点,缺乏种统一的方法；SDG模型属于定性模型,只通过“+”(增量影响)和“-”(减量影响)来确定节点之间的关系,难以比较详细地描述节点当前的状态以及节点之间的关系，而且绝大部分模型都是初始响应模型。使得模型只能反映初始响应阶段变量之间的关系,难以反映故障发生后不同阶段变量关系。
以上述SDG模型的基础上,在SDG故障诊断方法也存在不足。如：节点状态难以反应节点的变化过程,难以在故障发生早期及时诊断出故障；初始响应模型导致在故障发生后不同阶段诊断结论不—致,遗漏真正故障；多故障发生时,各个节点之间互相影响,节点状态可能随时变化,传统方法难以找到真正的故障；诊断的分辨率较低等等。
除此之外,之前的研究大都是集中于对SDG故障诊断某些方面的改进,如改进阈值设置方法、提高分辨率等,缺乏一个基于SDG的故障诊断框架,统一解决目前SDG故障诊断方法存在的不足,使其能够应用于实际工业过程故障诊断中。
针对目前SDG故障诊断方法存在的问题以及在实际的应用中遇到的其它问题,本文展开了研究。主要的工作如下：
(1)研究SDG建模问题。在前人方法的基础上,提出了基于节点之间定性趋势关系的建模方法。此方法包括了变量之间定性趋势关系模式定义以及整个的建模流程。采用代数、微分方程以及经验相结合方式,将节点之间关系通过趋势模式或者模式的组合来描述,并建立到SDG模型中,代替传统的增量、减量影响,形成了一种新的SDG模型。使得模型不再只是初始响应模型,而能够更加完备地、详细地表达节点变量之间在故障发生后各个阶段的关系。为之后的故障诊断打下基础。
(2)提出了基于SDG的故障诊断框架。该框架以基于节点之间定性趋势关系的SDG模型为基础。主要分为数据预处理、异常状态监测以及故障诊断3部分。数据预处理部分采用了提升小波与中值法对采集的数据进行预处理,去除其中的随机误差与粗大误差,为框架提供更为可靠的数据。
异常状态监测部分负责对系统进行监测,一旦发现异常或者故障及时通知诊断部分进行诊断。采用了基于节点定性趋势片段与传统阈值相结合的方法。基于定性趋势片段的方法采用“上升”、“下降”与“不变”来代表节点的状态,负责在故障发生早期及时发现故障,为故障的早期诊断创造条件。当节点进入稳态之后,采用传统阈值的方法,即采用“+”、“-”以及“0”来代表节点状态,保证在故障发生后的各个阶段,都能有效地、准确地监测到异常节点。
诊断部分采用了SDG与定性趋势分析结合的故障诊断方法。提出了基于滑动窗口的双向拟合的趋势提取、识别算法,将节点趋势提取并识别为“上升”、“下降”或者“不变”。然后根据提出的转换规则,将节点定性趋势转换为定性趋势关系,接着根据提出的合并规则,将定性趋势片段合并,最终得到节点之间的定性趋势关系。采用反向推理方法,将获取节点之间的定性趋势关系与模型中的关系相比较,根据提出的相容规则进行判断,找到可能的故障,最后对诊断的结果进行排序,提高诊断的分辨率。
该框架能够实现故障的早期诊断、不同时刻诊断出真正的故障、多故障诊断,具有较高的诊断分辨率,以及很强的鲁棒性。统一解决了目前SDG方法存在的一些不足,为之后SDG方法在实际工业故障诊断中的应用打下了良好基础。
(3)在SDG故障诊断框架的基础上,研究、开发了异常工况信息指导系统并将其应用于哈尔滨炼油厂常压蒸馏装置故障诊断中。该系统提供了全流程图形化SDG建模与组态环境、异常工况在线实时信息指导、多种数据采集方式以及多种去噪方式等功能。为SDG故障诊断方法的实际工业应用提供了保证。同时针对实际应用中碰到的具体情况,如数据采集方式、去噪方式、趋势分析的窗口大小、采样率问题、生产方案切换以及验证方式等问题,进行了研究,并解决了问题。
(4)通过案例分析以及实际中应用的情况,表明了异常工况信息指导系统能够实现早期诊断、不同时刻的结果都会包含真正的故障,不遗漏故障、多故障诊断且具有较高的分辨率,具有实用性、有效性以及可靠性等特点,能够应用于实际工业故障诊断中。
As the development of production technology, the chemical industry becomes more and more automatic and the scale becomes larger, but at the same time the complexity is increasing. Abnormal situations or faults occur due to sensor drifts、equipment failures、changes in process parameters or manual misoperation, leading to heavy economic lost and casualties. So it is an essential problem to find fault causes timely and avoid more heavy lost and serious accident.
SDG based fault diagnosis is one of methods based on qualitative model. SDG based fault diagnosis can arrive at completeness、good robustness、explanation facility and so on.So in recent years, it becomes a focus in the research area.
However, there are still some disadvantages in fault diagnosis based on SDG model, which restrict its application in real chemical industry. There are several methods of building SDG model. All of them have advantages and disadvantages. It is lack of a unified method for building SDG model; SDG model is a kind of qualitative models. In the model, the relationships between nodes are determined by "+" and "-". So the model can not represent the states of nodes and relationships between nodes in detail. In addition, most of the SDG models are based on initial response. They can only reveal the relationships between nodes during the range of initial response and can not reveal the relationships at different ranges after fault occurs.
There are also disadvantages in fault diagnosis based on above SDG model. For example:The states can not reveal the trends of nodes, so it can not do early fault diagnosis. The SDG model based on initial response makes the fault diagnosis method get different results at different ranges and miss the real fault cause. When multiple faults occur, the nodes influence each other and the states of nodes may change at any time. It makes the traditional SDG based fault diagnosis can not find the real fault causes; diagnosis resolution is poor.
In addition, the research about SDG based fault diagnosis focus on improving in some aspects such as the thresholds setting、improving the resolution and so on. There are few frameworks which can overcome the disadvantages and make it applicable in chemical industry.
For these disadvantages and other problems in the application of SDG base fault diagnosis in the real chemical industry, the research is carried out in the thesis. The main contributions of the thesis are as follows:
(1) The research is carried out on building SDG model. The method of SDG modeling based on qualitative trends relationships between nodes is proposed based on previous methods. The method includes the definition of basic patterns describing qualitative trends relationships between nodes and the whole procedures of modeling. Using algebraic equations、differential equations and experience, the relations between nodes are represented by patterns or the combination of patterns. The relations are stored in the SDG model in stead of incremental effect and reduction effect. The SDG model is not only based on initial response but can also represent the relationships between nodes at different ranges after fault occurs. The model makes preparation for fault diagnosis.
(2) The SDG based fault diagnosis framework is proposed. This framework is based on SDG model which is based on qualitative trends relationships between nodes. There are three parts of the framework:data preprocessing、abnormal state monitoring and fault diagnosis. In the data preprocessing unit lifting scheme and median method are used to eliminating the random and gross error and supply more reliable data.
Abnormal state monitoring unit is used to monitoring the state of system. Once abnormal situation or fault occurs, the unit will notice the fault diagnosis unit. In the abnormal state monitoring unit, the method based on qualitative trend segment and threshold is used. Qualitative trend segments used "Increasing"、"Decreasing "and "Steady" to represent the states of nodes instead of "+"、"-" and "0". The method of qualitative trend segments is used to find abnormal nodes in the early stage. When the variables are in steady state, the method of threshold is used to find abnormal nodes to make the abnormal nodes found in every stages.
In the fault diagnosis unit, SDG and qualitative trend analysis based fault diagnosis is used. The method based on a sliding window and bidirectional fitting is used to extract and identify the qualitative trends of nodes. The qualitative trends of nodes are identified as "Increasing"、"Decreasing" and "Steady". And then the qualitative trends of nodes are transformed into qualitative trends relationships between nodes and after segments merging, the final qualitative trends relationships between nodes are identified. The qualitative trends relationships between nodes are compared with these in the SDG model to determine whether consistent and find the real fault cause. At last the method will sort the results to improve the resolution.
The framework can do early fault diagnosis、avoid missing the real fault cause、can do multiple fault diagnosis and have good diagnosis resolution. The framework solves the problems of SDG based fault diagnosis and makes good preparation for application in the real industry.
(3) Based on the SDG fault diagnosis framework, the abnormal situation information guidance system is studied and developed. And the system is applied in fault diagnosis of an atmospheric distillation unit of Harbin refining plant. The system provides SDG modeling and configuration environment for the whole process、on-line consulting for abnormal situation、kinds of data acquiring methods and kinds of denosing methods. The other problems in the application, such as data acquiring、denosing、window width of qualitative trend extracting、sample rate、switch between different production programmes and verificaiton are all studied and solved.
(4) The results of case study and application prove that the abnormal situation information guidance system can do early fault diagnosis、avoid missing the real fault cause、can do multiple fault diagnosis and have good diagnosis resolution. It obtains the practicability、effectiveness and reliability and can be applied in the fault diagnosis of real industry.
SDG(符号有向图)模型是一种定性模型,能够从本质上描述故障传播的潜在路径,基于SDG的故障诊断方法具有完备性高、鲁棒性强、能够解释故障剧情等优点,近些年来,成为一个研究热点。
然而基于SDG方法存在的一些问题,限制了其在实际工业上的应用。建模方面,目前的SDG建模方法很多,各有优缺点,缺乏种统一的方法；SDG模型属于定性模型,只通过“+”(增量影响)和“-”(减量影响)来确定节点之间的关系,难以比较详细地描述节点当前的状态以及节点之间的关系，而且绝大部分模型都是初始响应模型。使得模型只能反映初始响应阶段变量之间的关系,难以反映故障发生后不同阶段变量关系。
以上述SDG模型的基础上,在SDG故障诊断方法也存在不足。如：节点状态难以反应节点的变化过程,难以在故障发生早期及时诊断出故障；初始响应模型导致在故障发生后不同阶段诊断结论不—致,遗漏真正故障；多故障发生时,各个节点之间互相影响,节点状态可能随时变化,传统方法难以找到真正的故障；诊断的分辨率较低等等。
除此之外,之前的研究大都是集中于对SDG故障诊断某些方面的改进,如改进阈值设置方法、提高分辨率等,缺乏一个基于SDG的故障诊断框架,统一解决目前SDG故障诊断方法存在的不足,使其能够应用于实际工业过程故障诊断中。
针对目前SDG故障诊断方法存在的问题以及在实际的应用中遇到的其它问题,本文展开了研究。主要的工作如下：
(1)研究SDG建模问题。在前人方法的基础上,提出了基于节点之间定性趋势关系的建模方法。此方法包括了变量之间定性趋势关系模式定义以及整个的建模流程。采用代数、微分方程以及经验相结合方式,将节点之间关系通过趋势模式或者模式的组合来描述,并建立到SDG模型中,代替传统的增量、减量影响,形成了一种新的SDG模型。使得模型不再只是初始响应模型,而能够更加完备地、详细地表达节点变量之间在故障发生后各个阶段的关系。为之后的故障诊断打下基础。
(2)提出了基于SDG的故障诊断框架。该框架以基于节点之间定性趋势关系的SDG模型为基础。主要分为数据预处理、异常状态监测以及故障诊断3部分。数据预处理部分采用了提升小波与中值法对采集的数据进行预处理,去除其中的随机误差与粗大误差,为框架提供更为可靠的数据。
异常状态监测部分负责对系统进行监测,一旦发现异常或者故障及时通知诊断部分进行诊断。采用了基于节点定性趋势片段与传统阈值相结合的方法。基于定性趋势片段的方法采用“上升”、“下降”与“不变”来代表节点的状态,负责在故障发生早期及时发现故障,为故障的早期诊断创造条件。当节点进入稳态之后,采用传统阈值的方法,即采用“+”、“-”以及“0”来代表节点状态,保证在故障发生后的各个阶段,都能有效地、准确地监测到异常节点。
诊断部分采用了SDG与定性趋势分析结合的故障诊断方法。提出了基于滑动窗口的双向拟合的趋势提取、识别算法,将节点趋势提取并识别为“上升”、“下降”或者“不变”。然后根据提出的转换规则,将节点定性趋势转换为定性趋势关系,接着根据提出的合并规则,将定性趋势片段合并,最终得到节点之间的定性趋势关系。采用反向推理方法,将获取节点之间的定性趋势关系与模型中的关系相比较,根据提出的相容规则进行判断,找到可能的故障,最后对诊断的结果进行排序,提高诊断的分辨率。
该框架能够实现故障的早期诊断、不同时刻诊断出真正的故障、多故障诊断,具有较高的诊断分辨率,以及很强的鲁棒性。统一解决了目前SDG方法存在的一些不足,为之后SDG方法在实际工业故障诊断中的应用打下了良好基础。
(3)在SDG故障诊断框架的基础上,研究、开发了异常工况信息指导系统并将其应用于哈尔滨炼油厂常压蒸馏装置故障诊断中。该系统提供了全流程图形化SDG建模与组态环境、异常工况在线实时信息指导、多种数据采集方式以及多种去噪方式等功能。为SDG故障诊断方法的实际工业应用提供了保证。同时针对实际应用中碰到的具体情况,如数据采集方式、去噪方式、趋势分析的窗口大小、采样率问题、生产方案切换以及验证方式等问题,进行了研究,并解决了问题。
(4)通过案例分析以及实际中应用的情况,表明了异常工况信息指导系统能够实现早期诊断、不同时刻的结果都会包含真正的故障,不遗漏故障、多故障诊断且具有较高的分辨率,具有实用性、有效性以及可靠性等特点,能够应用于实际工业故障诊断中。
As the development of production technology, the chemical industry becomes more and more automatic and the scale becomes larger, but at the same time the complexity is increasing. Abnormal situations or faults occur due to sensor drifts、equipment failures、changes in process parameters or manual misoperation, leading to heavy economic lost and casualties. So it is an essential problem to find fault causes timely and avoid more heavy lost and serious accident.
SDG based fault diagnosis is one of methods based on qualitative model. SDG based fault diagnosis can arrive at completeness、good robustness、explanation facility and so on.So in recent years, it becomes a focus in the research area.
However, there are still some disadvantages in fault diagnosis based on SDG model, which restrict its application in real chemical industry. There are several methods of building SDG model. All of them have advantages and disadvantages. It is lack of a unified method for building SDG model; SDG model is a kind of qualitative models. In the model, the relationships between nodes are determined by "+" and "-". So the model can not represent the states of nodes and relationships between nodes in detail. In addition, most of the SDG models are based on initial response. They can only reveal the relationships between nodes during the range of initial response and can not reveal the relationships at different ranges after fault occurs.
There are also disadvantages in fault diagnosis based on above SDG model. For example:The states can not reveal the trends of nodes, so it can not do early fault diagnosis. The SDG model based on initial response makes the fault diagnosis method get different results at different ranges and miss the real fault cause. When multiple faults occur, the nodes influence each other and the states of nodes may change at any time. It makes the traditional SDG based fault diagnosis can not find the real fault causes; diagnosis resolution is poor.
In addition, the research about SDG based fault diagnosis focus on improving in some aspects such as the thresholds setting、improving the resolution and so on. There are few frameworks which can overcome the disadvantages and make it applicable in chemical industry.
For these disadvantages and other problems in the application of SDG base fault diagnosis in the real chemical industry, the research is carried out in the thesis. The main contributions of the thesis are as follows:
(1) The research is carried out on building SDG model. The method of SDG modeling based on qualitative trends relationships between nodes is proposed based on previous methods. The method includes the definition of basic patterns describing qualitative trends relationships between nodes and the whole procedures of modeling. Using algebraic equations、differential equations and experience, the relations between nodes are represented by patterns or the combination of patterns. The relations are stored in the SDG model in stead of incremental effect and reduction effect. The SDG model is not only based on initial response but can also represent the relationships between nodes at different ranges after fault occurs. The model makes preparation for fault diagnosis.
(2) The SDG based fault diagnosis framework is proposed. This framework is based on SDG model which is based on qualitative trends relationships between nodes. There are three parts of the framework:data preprocessing、abnormal state monitoring and fault diagnosis. In the data preprocessing unit lifting scheme and median method are used to eliminating the random and gross error and supply more reliable data.
Abnormal state monitoring unit is used to monitoring the state of system. Once abnormal situation or fault occurs, the unit will notice the fault diagnosis unit. In the abnormal state monitoring unit, the method based on qualitative trend segment and threshold is used. Qualitative trend segments used "Increasing"、"Decreasing "and "Steady" to represent the states of nodes instead of "+"、"-" and "0". The method of qualitative trend segments is used to find abnormal nodes in the early stage. When the variables are in steady state, the method of threshold is used to find abnormal nodes to make the abnormal nodes found in every stages.
In the fault diagnosis unit, SDG and qualitative trend analysis based fault diagnosis is used. The method based on a sliding window and bidirectional fitting is used to extract and identify the qualitative trends of nodes. The qualitative trends of nodes are identified as "Increasing"、"Decreasing" and "Steady". And then the qualitative trends of nodes are transformed into qualitative trends relationships between nodes and after segments merging, the final qualitative trends relationships between nodes are identified. The qualitative trends relationships between nodes are compared with these in the SDG model to determine whether consistent and find the real fault cause. At last the method will sort the results to improve the resolution.
The framework can do early fault diagnosis、avoid missing the real fault cause、can do multiple fault diagnosis and have good diagnosis resolution. The framework solves the problems of SDG based fault diagnosis and makes good preparation for application in the real industry.
(3) Based on the SDG fault diagnosis framework, the abnormal situation information guidance system is studied and developed. And the system is applied in fault diagnosis of an atmospheric distillation unit of Harbin refining plant. The system provides SDG modeling and configuration environment for the whole process、on-line consulting for abnormal situation、kinds of data acquiring methods and kinds of denosing methods. The other problems in the application, such as data acquiring、denosing、window width of qualitative trend extracting、sample rate、switch between different production programmes and verificaiton are all studied and solved.
(4) The results of case study and application prove that the abnormal situation information guidance system can do early fault diagnosis、avoid missing the real fault cause、can do multiple fault diagnosis and have good diagnosis resolution. It obtains the practicability、effectiveness and reliability and can be applied in the fault diagnosis of real industry.
引文
[1]Venkatasubramanian V, Rengaswamy R, Kavuri S N, Yin K. A review of process fault detection and diagnosis part Ⅰ:quantitative model based methods [DB/OL]. Comput. Chem. Eng.,2003,27:293-311.
[2]Venkatasubramanian V, Rengaswamy R, Kavuri S N, Yin K. A review of process fault detection and diagnosis part Ⅱ:qualitative models and search strategies [DB/OL]. Comput. Chem. Eng.,2003,27:313-326.
[3]Venkatasubramanian V, Rengaswamy R, Kavuri S N, Yin K.A review of process fault detection and diagnosis part Ⅲ:process history based methods [DB/OL]. Comput. Chem. Eng.,2003,27:327-346.
[4]Himmelblau D M. Fault detection and diagnosis in chemical and petrochemical processes [M] Amsterdam:Elsevier press,1978.13.
[5]Lapp S A, Powers G J. Computer-aided Synthesis of Fault-trees [J]. IEEE Transactions on Reliability,1977,26(2):2-12.
[6]Iri M, Aoki K, O'shima E, Matsuyama H. An Algorithm for Diagnosis of System Failures in the Chemical Process [J].Computers and Chemical Engineering,1979,3(1-4):489-493.
[7]Umeda T, Kuriyama T. A graphical approach to cause and effect analysis of chemical processing systems [J]. Chemical Engineering Science.1980,35:2379-2388.
[8]Kokawa M, Miyazaki S, Shingai S. Fault location using digraph and inverse direction search with application [J]. Automatica.1983,19(6):729-735
[9]Shiozaki J, Matsuyama H, O'shima E. An improved algorithm for diagnosis of system failure in the chemical process [J]. Comput. Chem. Eng.1985,9(3):285-293
[10]Tsuge Y, Shiozaki J, Matsuyama H, O'shima E. Fault diagnosis algorithms based on signed directed graphs and its modifications [J]. Int. Chem. Engng.1985.
[11]Shiozaki J, Matsuyama H, Tano K, O'shima E. Fault diagnosis of chemical processes by the use of signed, directed graphs. Extension to five-range patterns of abnormality [J]. Int. Chem. Engng.1985,25(4),651-659.
[12]Tsuge Y, Shiozaki J, Matsuyama H, O'shima E, Iguchi Y, Fuchigami M, Matsushita M. Fesibility study of a fault diagnosis system for chemical plants [J]. Int. Chem. Engng. 1985,25(4):660-667.
[13]Kramer M A, Palowitch B L. A rule-based approach to fault diagnosis using the signed directed graph [J]. AIChE J.1987,33(7):1078-607. Shiozaki J, Shibata B, Matsuyama H, O'shima E. Fault diagnosis of chemical processes
[14]utilizing signed directed graphs-improvement by using temporal information. IEEE Trans. Ind. Electr.1989,36(4):469-74.
[15]Oyeleye O O, Kramer M A. Qualitative simulation of chemical process systems: steady-state analysis [J]. AIChEJ.1988,34 (9):1441-1454.
[16]Chang CC, Yu CC. On-line fault diagnosis using the signed directed graph [J]. Ind. Engng. Chem. Res.1990,29(7):1290-1299.
[17]Rostein G E, Lavie R, Lewin D R. Automated synthesis of chemical batch plant procedures-A qualitative process-centered approach for chemical plant operations [A]. In: IFAC Symposium On-Line Fault Detection and Supervision in the Chemical Process Industries[C]. Newark:Delaware,1992,22-24,1992.
[18]Rostein G E, Lavie R, Lewin D R. A qualitative process-oriented approach for chemical plant operation-The generation of feasible operating procedures [J]. Comput. Chem. Eng. 1992,16(Supp1):S22-S28.
[19]Wilcox NA, Himmmelblau H M. The possible cause and effect graphs (PCEG) model for fault diagnosis-Ⅰ. Methodology [J]. Comput. Chem. Eng.1994,18(2):103-116.
[20]Wilcox NA, Himmmelblau H M. The possible cause and effect graphs (PCEG) model for fault diagnosis-Ⅱ.Applications, Comput. Chem. Eng.1994,18(2):117-127.
[21]Han C C, Shih R F, Lee L S. Quantifying signed directed graphs with the fuzzy set for fault diagnosis resolution improvement [J]. Ind. Eng. Chem. Res.1994,1943-1954.
[22]Shih R F, Lee L S. Use of Fuzzy Cause-Effect Digraph for Resolution Fault Diagnosis for Process Plants.1. Fuzzy Cause-Effect Digraph[J]. Ind. Eng. Chem. Res.1995,34(5); 1688-1702.
[23]Shih R F, Lee L S. Use of Fuzzy Cause-Effect Digraph for Resolution Fault Diagnosis for Process Plants.2. Diagnostic Algorithm and Applications [J]. Ind. Eng. Chem. Res.1995, 34(5):1703-1717.
[24]Wang X Z, Yang S A, Veloso E, Lu M L, McGreavy C. Qualitative process modeling-a fuzzy signed directed graph method [J]. Computers and Chemical Engineering.1995, 19:s735-s740.
[25]Wang X Z, Yang S A, Yang S H, Mcgreavy C. The application of fuzzy qualitative in safety and operability assessment of process plants. Computers and Chemical Engineering.1996,671-676.
[26]Tarifa E E, Scenna N J. Fault diagnosis, directed graphs, and fuzzy logic[J]. Computers and Chemical Engineering.1997,21:207-214.
[27]Tarifa E E, Scenna N J. Fault diagnosis for a MSF using a SDG and fuzzy logic[J] Desalination,2003,207-214.
[28]刘敏华,萧德云.基于SDG模型和模糊融合的故障诊断方法[J].控制工程.2006,13(1)：10-14
[29]Vaidhyanathan R, Venkatasubramanian V. Experience with an Expert System for Automated HAZOP Analysis [J]. Computers Chem. Engng.1996,20:1589-1594.
[30]Mylaraswamy D, Venkatasubramanian V. A Hybrid Framework for Large Scale Process Fault Diagnosis [J]. Computers Chem. Engng.1997,21:935-940.
[31]Dash S, Venkatasubramanian V. Challenges in the Industrial Applications of Fault Diagnostic Systems [J]. Computers Chem. Engng.2000,24:785-791.
[32]Venkatasubramanian V, Zhao J, Viswanathan S. Intelligent System for HAZOP Analysis of Complex Process Plants [J]. Computers Chem. Engng.,2000,24:2291-2302.
[33]Vedam H, Venkatasubramanian V, Signed digraph based multiple fault diagnosis [J]. Comput. Chem. Eng.1997,21(6):655-660.
[34]Zhang Z Q,Wu C G,Zhang B K, Xia T,Li A F, SDG multiple fault diagnosis by real-time inverse inference. Reliab. Eng. Syst. Saf.,2005,87:173-189.
[35]Gao D, Zhang B.K., Ma X, Wu C.C.SDG multiple fault diagnosis by fuzzy logic and real-time bidirectional inference [A]. In:2009 international conference on information engineering and computer science[C].2009,118-125.
[36]Chen J, Howell J, A self-validating control system based approach to plant fault detection and diagnosis. Comput. Chem. Eng.2001,25:337-358.
[37]Maurya M R, Rengaswamy R, Venkatasubramanian V. Consistent malfunction diagnosis inside control loops using signed directed graphs [A]. In:European symposium on computer aided process engineering-13:36th uropean symposium of the working party on computer aided process engineering, Turunen, I., ed., Elsevier Science Ltd, Europe,2003, 473-479.
[38]Maurya M R, Rengaswamy R, Venkatasubramanian V. A signed directed graph-based systematic framework for steady-state malfunction diagnosis inside control loops [J]. Chem. Eng. Sci.2006,61:1790-1810.
[39]李安峰,夏涛,张贝克,张钊谦,吴重光.化工过程SDG建模方法[J].系统仿真学报.2003,15(10)：1364-1368.
[40]杨帆,萧德云.控制系统的SDG模型描述及故障传播分析[J].控制与决策.2009：24(7)：1001-1006
[41]Yang F, Shah S, Xiao D Y. SDG model-based analysis of fault propagation in control systems [A]. In:2009 Canadian Conference on Electrical and Computer Engineering[C]. 2009,1152-1157.
[42]卢炳南,张贝克,马昕,许昕,高东.基于SDG模型的控制系统故障诊断方法[J].化工学报.2009,60：2243-2251.
[43]高东,张贝克,马昕,吴重光.基于SDG和定性趋势分析的控制系统故障诊断[J].北京理工大学学报.2010,30(增刊1)：155-160.
[44]Ning N, Zhang J, Gao X Y, Xue J. Formal Verification of SDG via Symbolic Model Checking[A].2009 2nd International Conference on Intelligent Computing Technology and Automation[C].2009,4:p521-524.
[45]Ning N, Zhang J, Gao X Y, Xue J. Formal verification for quality analysis of SDG fault diagnosis model via symbolic model checking[A].2010 International Conference on Measuring Technology and Mechatronics Automation.2010,2:305-308.
[46]黄信林,高建民,高智勇,吕延庆.应用变量因果序分析的符号有向图建模方法[J].计算机应用.2010.44(5)：85-90.
[47]Vedam, H., Venkatasubramanian, V., PCA-SDG based process monitoring and fault diagnosis, Control Eng. Pract.1999,7(7):903-917.
[48]黄道平,龚婷婷,曾辉.基于非线性主元分析和符号有向图的故障诊断方法[J].化工学报.2009.60(12)：3058-3062.
[49]Wang H, Song Z H, Wang H. Statistical process monitoring using improved PCA with optimized sensor locations. Journal of Process Control,2002,12:735-744.
[50]曹文亮,王兵树,马良玉,张冀.基于SDG推理规则和定量分析的故障诊断技术[J].热能动力工程.2005,20(6)：619-623
[51]刘敏华,萧德云.基于趋势分析和SDG模型的故障诊断[J].控制理论与应用.2006,23(2)：306-310.
[52]Ma Y G, Gao J Q, Ma LY, Yan Q, Tong P. Study on fault diagnosis based on the qualitative /quantitative model of SDG and genetic algorithm[A]. In:Proceedings of the Fifth International Conference on Machine Learning and CyberneticsI, China,2006,2053-2058.
[53]杨帆,萧德云.概率SDG模型及故障分析推理方法[J].控制与决策.2006,21(5)：487-496.
[54]杨帆,萧德云.结构残差在基于SDG故障分离中的应用[J].控制工程.2007,14(3)：320-324.
[55]Ahn S J, Lee C J, Jung Y, Han C, Yong E S, Lee G Fault diagnosis of the multi-stage flash desalination process based on signed digraph and dynamic partial least square[J]. Desalination,2008,228:68-83.
[56]Maurya M R, Rengaswamy R, Venkatasubramanian V. A signed directed graph and qualitative trend analysis-based framework for incipient fault diagnosis [J]. Chem. Eng. Res. Des.2007,85(A10),1407-1422.
[57]宋其江,徐敏强,王日新.模糊概率SDG模型及故障推理方法[J].控制与决策.2009.24(5)：692-696.
[58]Gao D, Zhang B K, Ma X. A signed directed graph and qualitative trend analysis-based method for process monitoring and fault diagnosis [A]. In:Progress in Safety Science and Technology VOL VII, Li S C, Wang Y J, An Y, Sun X Y, Li X,eds., Science Press, China,2008:366-370.
[59]Gao D, Wu C C, Zhang B K, Ma X. Signed directed graph and qualitative trend analysis based fault diagnosis in chemical industry [J]. Chinese Journal of Chemical Engineering. 2010,18:265-276.
[60]Xie G, Wang X, Xie K.SDG-based fault diagnosis and application based on reasoning method of granular computing [A].2010 Chinese Control and Decision Conference[C]. 2010:1718-1722.
[61]Maurya M R, Rengaswamy R, Venkatasubramanian V. A systematic framework for the development and analysis of signed digraphs for chemical processes Ⅰ. Algorithms and analysis. Industrial and Engineering Chemistry Research,2003,42:4789-4810.
[62]Maurya M R, Rengaswamy R., Venkatasubramanian V. A systematic framework for the development and analysis of signed digraphs for chemical processes Ⅱ. Control loops and flowsheet analysis. Industrial and Engineering Chemistry Research,2003,42: 4811-4827.
[63]吴重光,夏涛,张贝克.基于符号定向图(SDG)深层知识模型的定性仿真[J].系统仿真学报.2003,15(10)：1351-1355
[64]李安峰.基于SDG模型的计算机辅助HAZOP分析及应用研究[D].北京：北京化工大学信息科学与技术学院,2006.
[65]Zhang J, Qiu T, Zhao J. Chemical process fault simulation analyses based on an extended SDG [J]. Journal of Tsinghua University.2009,49(9):1561-1564+1568.
[66]纳永良,吴重光,夏迎春,张卫华.化工过程危险剧情分类及SDG定性识别方法[J].化工学报.2009,60(10)：2503-2509.
[67]张贝克,夏涛,吴重光.SDG标准测试图及推理引擎论证[J].系统仿真学报.2003, 15(10)：1368-1373.
[68]张贝克,夏涛,吴重光.集成化SDG建模、推理与信息处理软件平台[J].系统仿真学报.2003,15(10)：12-15.
[69]王杭州,陈丙珍,何小荣,赵劲松,邱彤基于开源组件的SDG推理平台[J].化工学报.2010.61(7)：1829-1836.
[70]吕宁,王雄.基于SDG的加热炉HAZOP与故障诊断[J].系统仿真学报.2006,18(6)：1660-1663
[71]王伟,于达仁,赵辉,胡清华,除氧器故障诊断的含未测节点的符号有向图方法[J].动力工程2007,27(5)：3942
[72]黄卫东,王克昌.基于定性与定量关系的液体火箭发动机故障诊断[J].航空动力学报,1996,11(3)：281-284
[73]黄卫东,王克昌.基于深层知识规则的液体火箭发动机故障诊断[J].宇航学报,1997,18(4)61-65.
[74]刘洪刚,吴建军,陈小前,等.基于SDG的智能故障诊断方法研究[J].系统工程与电子技术,2002,24(1)：103-109.
[75]王文辉,周东华.基于定性与半定性方法的故障检测与诊断技术[J].控制理论与应用,2002,19(5)：653-666.
[76]陈仲生,杨拥民,李聪,尹剑飞.基于振动传递符号有向图的齿轮箱嵌入式传感器优化配置模型与算法[J].航空动力学报.2009.24(10)：2384-2390.
[77]Downs J, Vogel E F.A plant-wide industrial process control problem [J].Computers and Chemical Engineering,1993,17(3):245-255.
[78]Lyman P R, Georgakis C.Plant-wide control of the tennessee eastman problem [J].Comput. Chem. Engng.1995,19:332-331.
[79]Mcavoy, T J, Ye N. Base control for the tennessee eastman problem". Comput. Chem.Engng.1994,18:383-413.
[80]Gao D, Zhang B K, Ma X.Wu C C.Application of signed directed graph based fault diagnosis of atmospheric distillation unit [A]. In:The 2nd International Workshop on Intelligent Systems and Applications[C]. IEEE Computer Society, United States,2010,
[81]Cheung JT, Stephanopoulos G. Representation of process trends-Part Ⅰ. A formal representation framework [J]. Comput.& Chem. Engng.1990,14(4/5):495-510.
[82]Janusz M, Venkatasubramanian V. Automatic generation of qualitative description of process trends for fault detection and diagnosis [J]. Engineering Applications of Artificial Intelligence,1991,4 (5):329-339.
[83]Konstantinov K B, Yoshida T. Real-time qualitative analysis of temporal shapes of (Bio) process variables [J].AIChEJ,1992,38(11):1703-1715.
[84]Whiteley J R, Davis J F. Knowledge-based interpretation of sensor patterns [J]. Comput.& Chem. Engg.1992,16(4):329-346..
[85]Bakshi B R, Stephanopoulos G. Representation of process trends-Ⅲ. Multiscale extraction of trends from process data [J]. Comput.& Chem. Engng.1994,18(4):267-302.
[86]Bakshi B R, Stephanopoulos G. Representation of process trends-Ⅳ. Induction of real-time patterns from operating data for diagnosis and supervisory control [J]. Comput. & Chem. Engng.1994,18(4):303-332.
[87]Rengaswamy, R., Venkatasubramanian, V., A syntactic pattern recognition approach for process monitoring and fault diagnosis [J]. Engineering Applications of Artificial Intelligence,1995,8 (1),35-51.
[88]Rengaswamy R., Hagglund T., Venkatasubramanian V. A qualitative shape analysis formalism for monitoring control loop performance [J]. Engineering Applications of Artificial Intelligence.2001,14(1),23-33.
[89]Oh Y S, Moo K J, Yoon E S, Yonn J H. Fault diagnosis based on weighted symptom tree and pattern matching. Ind. Eng.Chem.Res [J].1997,36:2672-2678.
[90]Haimowitz I J,Le P P, Kohane I S, Clinical monitoring using regression based templates[J]. Arlifical Intelligence in medicine.1995,7:463-496.
[91]Vedam H, Venkatasubramanian V. A wavelet theory-based adaptive trend analysis system for process monitoring and diagnosis [J]. In American Control Conference,1997,309-313.
[92]Vedam H, Venkatasubramanian V. Bhalodia. A B-Spline based method for data compression, process monitoring and diagnosis [J]. Comput.& Chem. Engng., 22:S827-S830,1998.
[93]Vedam H, Venkatasubramanian V.PCA-SDG based process monitoring and fault diagnosis, Control Engineering Practice7 (7),1999,903-917.
[94]Wong J C, McDonald, K A, Palazoglu A. Classification of process trends based on fuzzied symbolic representation and hidden markov models [J]. Journal of process control,1998, 8(5-6):395-408
[95]Wong J C, McDonald, K A, Palazoglu A. Classificaiton of abnormal plant operation using multiple process variable trends [J]. Journal of process control,2001,11(4):409-418
[96]Dash S, Rengaswamy R, Venkatasubramanian V. Fuzzy-logic based trend classification for fault diagnosis of chemical processes [J]. Computers and Chemical Engineering. 2003,27(3),347-362.
[97]Maurya M R, Rengaswamy R, Venkatasubramanian V. Incipient fault diagnosis of Tennessee Eastman flowsheet using signed directed graph and trend analysis [A]. In: Supplementary Proceedings of the 12th European Symposium on Computer Aided Process Engineering (ESCAPE-12)[C]. The Hague, The Netherlands,2002.26-29.
[98]Dash S, Rengaswamy R, Venkatasubramanian V. A novel interval halving algorithm for process trend identification [A]. In 4th IFAC Workshop on On-Line Fault Detection & Supervision in the Chemical Process Industries[C], Korea,2001,155-160.
[99]Dash S. Data-Driven Qualitative and Model-Based Quantitative Approaches to Fault Diagnosis [D]. PhD thesis, Purdue University,2001.
[100]Charbonnier S, Garcia-Beltan C, Cadet C, Gentil S, Trends extraction and analysis for complex system monitoring and decision support [J]. Engineering Applications of Artificial Intelligence,2005,18:21-36.
[101]NOUNOU M N, BASKI B R. On-line Multiscale Filtering of Random and Gross Errors without Process Models [J]. AIChE,1999,45(5):1041-1058.
[102]COHEN A, DAUBECHIES I, VIAL P, Wavelets on the Interval and Fast Wavelet Transforms [J], Appl Comput. Harmonic Analysis,1993,1(1):54-81.
[103]刘志成,陈祥光,李宇峰等.传感器输出时间序列的实时小波滤波方法[J].北京化工大学学报,2007,1(34)：71-75.
[104]SWELDEN W. The lifting scheme:A custom-design construction of biorthogonal wavelets [J]. Appl Comput. Harmonic Analysis,1996,3(2):186-200.
[105]SWELDEN W. The lifting scheme:A construction of second generation wavelets [J]. SIAM J Math Anal,1997,29(2):511-546
[106]SWELDEN W, SCHRODER P. Building your own wavelets at home [EB/OL]. (2000-01-02) [2008-01-10]. http://cm.bell-labs.com/who/wim/papers/athome/athome.pdf
[107]高东,张贝克,吴重光.基于提升格式的过程数据在线去噪方法及其应用[J].计算机应用研究.2008,25(10)：3198-3220.
[108]FERNANDEZ G, PERIASWAMY S. A Software Package for Wavelet Transforms using Lifting.
[109]Wold S, Esbensen K, Geladi P.Principal Component Analysis [J]. Chemometrics and Intelligent Laboratory Systems (S0169-7439),1987,2(1):37.
[110]Kresta J, MacGregor J F, Marlin T E.Multivariate Statistical Monitoring of Process Operating Performance. [J] Canadian Journal of Chemical Engineering(S0008-4034),1991, 69(1):35.
[111]Nomikos P, MacGregor J F. Monitoring batch processes using multiway principal component analysis. AIChE Journal.1994,40(8):1361-1373. [112] Dunia R, Qin S J, Edgar T F, McAvoy T J. Identification of faulty sensors using principal
component analysis[J]. AIChE Journal.1996,42(10):2797-2812.
[2]Venkatasubramanian V, Rengaswamy R, Kavuri S N, Yin K. A review of process fault detection and diagnosis part Ⅱ:qualitative models and search strategies [DB/OL]. Comput. Chem. Eng.,2003,27:313-326.
[3]Venkatasubramanian V, Rengaswamy R, Kavuri S N, Yin K.A review of process fault detection and diagnosis part Ⅲ:process history based methods [DB/OL]. Comput. Chem. Eng.,2003,27:327-346.
[4]Himmelblau D M. Fault detection and diagnosis in chemical and petrochemical processes [M] Amsterdam:Elsevier press,1978.13.
[5]Lapp S A, Powers G J. Computer-aided Synthesis of Fault-trees [J]. IEEE Transactions on Reliability,1977,26(2):2-12.
[6]Iri M, Aoki K, O'shima E, Matsuyama H. An Algorithm for Diagnosis of System Failures in the Chemical Process [J].Computers and Chemical Engineering,1979,3(1-4):489-493.
[7]Umeda T, Kuriyama T. A graphical approach to cause and effect analysis of chemical processing systems [J]. Chemical Engineering Science.1980,35:2379-2388.
[8]Kokawa M, Miyazaki S, Shingai S. Fault location using digraph and inverse direction search with application [J]. Automatica.1983,19(6):729-735
[9]Shiozaki J, Matsuyama H, O'shima E. An improved algorithm for diagnosis of system failure in the chemical process [J]. Comput. Chem. Eng.1985,9(3):285-293
[10]Tsuge Y, Shiozaki J, Matsuyama H, O'shima E. Fault diagnosis algorithms based on signed directed graphs and its modifications [J]. Int. Chem. Engng.1985.
[11]Shiozaki J, Matsuyama H, Tano K, O'shima E. Fault diagnosis of chemical processes by the use of signed, directed graphs. Extension to five-range patterns of abnormality [J]. Int. Chem. Engng.1985,25(4),651-659.
[12]Tsuge Y, Shiozaki J, Matsuyama H, O'shima E, Iguchi Y, Fuchigami M, Matsushita M. Fesibility study of a fault diagnosis system for chemical plants [J]. Int. Chem. Engng. 1985,25(4):660-667.
[13]Kramer M A, Palowitch B L. A rule-based approach to fault diagnosis using the signed directed graph [J]. AIChE J.1987,33(7):1078-607. Shiozaki J, Shibata B, Matsuyama H, O'shima E. Fault diagnosis of chemical processes
[14]utilizing signed directed graphs-improvement by using temporal information. IEEE Trans. Ind. Electr.1989,36(4):469-74.
[15]Oyeleye O O, Kramer M A. Qualitative simulation of chemical process systems: steady-state analysis [J]. AIChEJ.1988,34 (9):1441-1454.
[16]Chang CC, Yu CC. On-line fault diagnosis using the signed directed graph [J]. Ind. Engng. Chem. Res.1990,29(7):1290-1299.
[17]Rostein G E, Lavie R, Lewin D R. Automated synthesis of chemical batch plant procedures-A qualitative process-centered approach for chemical plant operations [A]. In: IFAC Symposium On-Line Fault Detection and Supervision in the Chemical Process Industries[C]. Newark:Delaware,1992,22-24,1992.
[18]Rostein G E, Lavie R, Lewin D R. A qualitative process-oriented approach for chemical plant operation-The generation of feasible operating procedures [J]. Comput. Chem. Eng. 1992,16(Supp1):S22-S28.
[19]Wilcox NA, Himmmelblau H M. The possible cause and effect graphs (PCEG) model for fault diagnosis-Ⅰ. Methodology [J]. Comput. Chem. Eng.1994,18(2):103-116.
[20]Wilcox NA, Himmmelblau H M. The possible cause and effect graphs (PCEG) model for fault diagnosis-Ⅱ.Applications, Comput. Chem. Eng.1994,18(2):117-127.
[21]Han C C, Shih R F, Lee L S. Quantifying signed directed graphs with the fuzzy set for fault diagnosis resolution improvement [J]. Ind. Eng. Chem. Res.1994,1943-1954.
[22]Shih R F, Lee L S. Use of Fuzzy Cause-Effect Digraph for Resolution Fault Diagnosis for Process Plants.1. Fuzzy Cause-Effect Digraph[J]. Ind. Eng. Chem. Res.1995,34(5); 1688-1702.
[23]Shih R F, Lee L S. Use of Fuzzy Cause-Effect Digraph for Resolution Fault Diagnosis for Process Plants.2. Diagnostic Algorithm and Applications [J]. Ind. Eng. Chem. Res.1995, 34(5):1703-1717.
[24]Wang X Z, Yang S A, Veloso E, Lu M L, McGreavy C. Qualitative process modeling-a fuzzy signed directed graph method [J]. Computers and Chemical Engineering.1995, 19:s735-s740.
[25]Wang X Z, Yang S A, Yang S H, Mcgreavy C. The application of fuzzy qualitative in safety and operability assessment of process plants. Computers and Chemical Engineering.1996,671-676.
[26]Tarifa E E, Scenna N J. Fault diagnosis, directed graphs, and fuzzy logic[J]. Computers and Chemical Engineering.1997,21:207-214.
[27]Tarifa E E, Scenna N J. Fault diagnosis for a MSF using a SDG and fuzzy logic[J] Desalination,2003,207-214.
[28]刘敏华,萧德云.基于SDG模型和模糊融合的故障诊断方法[J].控制工程.2006,13(1)：10-14
[29]Vaidhyanathan R, Venkatasubramanian V. Experience with an Expert System for Automated HAZOP Analysis [J]. Computers Chem. Engng.1996,20:1589-1594.
[30]Mylaraswamy D, Venkatasubramanian V. A Hybrid Framework for Large Scale Process Fault Diagnosis [J]. Computers Chem. Engng.1997,21:935-940.
[31]Dash S, Venkatasubramanian V. Challenges in the Industrial Applications of Fault Diagnostic Systems [J]. Computers Chem. Engng.2000,24:785-791.
[32]Venkatasubramanian V, Zhao J, Viswanathan S. Intelligent System for HAZOP Analysis of Complex Process Plants [J]. Computers Chem. Engng.,2000,24:2291-2302.
[33]Vedam H, Venkatasubramanian V, Signed digraph based multiple fault diagnosis [J]. Comput. Chem. Eng.1997,21(6):655-660.
[34]Zhang Z Q,Wu C G,Zhang B K, Xia T,Li A F, SDG multiple fault diagnosis by real-time inverse inference. Reliab. Eng. Syst. Saf.,2005,87:173-189.
[35]Gao D, Zhang B.K., Ma X, Wu C.C.SDG multiple fault diagnosis by fuzzy logic and real-time bidirectional inference [A]. In:2009 international conference on information engineering and computer science[C].2009,118-125.
[36]Chen J, Howell J, A self-validating control system based approach to plant fault detection and diagnosis. Comput. Chem. Eng.2001,25:337-358.
[37]Maurya M R, Rengaswamy R, Venkatasubramanian V. Consistent malfunction diagnosis inside control loops using signed directed graphs [A]. In:European symposium on computer aided process engineering-13:36th uropean symposium of the working party on computer aided process engineering, Turunen, I., ed., Elsevier Science Ltd, Europe,2003, 473-479.
[38]Maurya M R, Rengaswamy R, Venkatasubramanian V. A signed directed graph-based systematic framework for steady-state malfunction diagnosis inside control loops [J]. Chem. Eng. Sci.2006,61:1790-1810.
[39]李安峰,夏涛,张贝克,张钊谦,吴重光.化工过程SDG建模方法[J].系统仿真学报.2003,15(10)：1364-1368.
[40]杨帆,萧德云.控制系统的SDG模型描述及故障传播分析[J].控制与决策.2009：24(7)：1001-1006
[41]Yang F, Shah S, Xiao D Y. SDG model-based analysis of fault propagation in control systems [A]. In:2009 Canadian Conference on Electrical and Computer Engineering[C]. 2009,1152-1157.
[42]卢炳南,张贝克,马昕,许昕,高东.基于SDG模型的控制系统故障诊断方法[J].化工学报.2009,60：2243-2251.
[43]高东,张贝克,马昕,吴重光.基于SDG和定性趋势分析的控制系统故障诊断[J].北京理工大学学报.2010,30(增刊1)：155-160.
[44]Ning N, Zhang J, Gao X Y, Xue J. Formal Verification of SDG via Symbolic Model Checking[A].2009 2nd International Conference on Intelligent Computing Technology and Automation[C].2009,4:p521-524.
[45]Ning N, Zhang J, Gao X Y, Xue J. Formal verification for quality analysis of SDG fault diagnosis model via symbolic model checking[A].2010 International Conference on Measuring Technology and Mechatronics Automation.2010,2:305-308.
[46]黄信林,高建民,高智勇,吕延庆.应用变量因果序分析的符号有向图建模方法[J].计算机应用.2010.44(5)：85-90.
[47]Vedam, H., Venkatasubramanian, V., PCA-SDG based process monitoring and fault diagnosis, Control Eng. Pract.1999,7(7):903-917.
[48]黄道平,龚婷婷,曾辉.基于非线性主元分析和符号有向图的故障诊断方法[J].化工学报.2009.60(12)：3058-3062.
[49]Wang H, Song Z H, Wang H. Statistical process monitoring using improved PCA with optimized sensor locations. Journal of Process Control,2002,12:735-744.
[50]曹文亮,王兵树,马良玉,张冀.基于SDG推理规则和定量分析的故障诊断技术[J].热能动力工程.2005,20(6)：619-623
[51]刘敏华,萧德云.基于趋势分析和SDG模型的故障诊断[J].控制理论与应用.2006,23(2)：306-310.
[52]Ma Y G, Gao J Q, Ma LY, Yan Q, Tong P. Study on fault diagnosis based on the qualitative /quantitative model of SDG and genetic algorithm[A]. In:Proceedings of the Fifth International Conference on Machine Learning and CyberneticsI, China,2006,2053-2058.
[53]杨帆,萧德云.概率SDG模型及故障分析推理方法[J].控制与决策.2006,21(5)：487-496.
[54]杨帆,萧德云.结构残差在基于SDG故障分离中的应用[J].控制工程.2007,14(3)：320-324.
[55]Ahn S J, Lee C J, Jung Y, Han C, Yong E S, Lee G Fault diagnosis of the multi-stage flash desalination process based on signed digraph and dynamic partial least square[J]. Desalination,2008,228:68-83.
[56]Maurya M R, Rengaswamy R, Venkatasubramanian V. A signed directed graph and qualitative trend analysis-based framework for incipient fault diagnosis [J]. Chem. Eng. Res. Des.2007,85(A10),1407-1422.
[57]宋其江,徐敏强,王日新.模糊概率SDG模型及故障推理方法[J].控制与决策.2009.24(5)：692-696.
[58]Gao D, Zhang B K, Ma X. A signed directed graph and qualitative trend analysis-based method for process monitoring and fault diagnosis [A]. In:Progress in Safety Science and Technology VOL VII, Li S C, Wang Y J, An Y, Sun X Y, Li X,eds., Science Press, China,2008:366-370.
[59]Gao D, Wu C C, Zhang B K, Ma X. Signed directed graph and qualitative trend analysis based fault diagnosis in chemical industry [J]. Chinese Journal of Chemical Engineering. 2010,18:265-276.
[60]Xie G, Wang X, Xie K.SDG-based fault diagnosis and application based on reasoning method of granular computing [A].2010 Chinese Control and Decision Conference[C]. 2010:1718-1722.
[61]Maurya M R, Rengaswamy R, Venkatasubramanian V. A systematic framework for the development and analysis of signed digraphs for chemical processes Ⅰ. Algorithms and analysis. Industrial and Engineering Chemistry Research,2003,42:4789-4810.
[62]Maurya M R, Rengaswamy R., Venkatasubramanian V. A systematic framework for the development and analysis of signed digraphs for chemical processes Ⅱ. Control loops and flowsheet analysis. Industrial and Engineering Chemistry Research,2003,42: 4811-4827.
[63]吴重光,夏涛,张贝克.基于符号定向图(SDG)深层知识模型的定性仿真[J].系统仿真学报.2003,15(10)：1351-1355
[64]李安峰.基于SDG模型的计算机辅助HAZOP分析及应用研究[D].北京：北京化工大学信息科学与技术学院,2006.
[65]Zhang J, Qiu T, Zhao J. Chemical process fault simulation analyses based on an extended SDG [J]. Journal of Tsinghua University.2009,49(9):1561-1564+1568.
[66]纳永良,吴重光,夏迎春,张卫华.化工过程危险剧情分类及SDG定性识别方法[J].化工学报.2009,60(10)：2503-2509.
[67]张贝克,夏涛,吴重光.SDG标准测试图及推理引擎论证[J].系统仿真学报.2003, 15(10)：1368-1373.
[68]张贝克,夏涛,吴重光.集成化SDG建模、推理与信息处理软件平台[J].系统仿真学报.2003,15(10)：12-15.
[69]王杭州,陈丙珍,何小荣,赵劲松,邱彤基于开源组件的SDG推理平台[J].化工学报.2010.61(7)：1829-1836.
[70]吕宁,王雄.基于SDG的加热炉HAZOP与故障诊断[J].系统仿真学报.2006,18(6)：1660-1663
[71]王伟,于达仁,赵辉,胡清华,除氧器故障诊断的含未测节点的符号有向图方法[J].动力工程2007,27(5)：3942
[72]黄卫东,王克昌.基于定性与定量关系的液体火箭发动机故障诊断[J].航空动力学报,1996,11(3)：281-284
[73]黄卫东,王克昌.基于深层知识规则的液体火箭发动机故障诊断[J].宇航学报,1997,18(4)61-65.
[74]刘洪刚,吴建军,陈小前,等.基于SDG的智能故障诊断方法研究[J].系统工程与电子技术,2002,24(1)：103-109.
[75]王文辉,周东华.基于定性与半定性方法的故障检测与诊断技术[J].控制理论与应用,2002,19(5)：653-666.
[76]陈仲生,杨拥民,李聪,尹剑飞.基于振动传递符号有向图的齿轮箱嵌入式传感器优化配置模型与算法[J].航空动力学报.2009.24(10)：2384-2390.
[77]Downs J, Vogel E F.A plant-wide industrial process control problem [J].Computers and Chemical Engineering,1993,17(3):245-255.
[78]Lyman P R, Georgakis C.Plant-wide control of the tennessee eastman problem [J].Comput. Chem. Engng.1995,19:332-331.
[79]Mcavoy, T J, Ye N. Base control for the tennessee eastman problem". Comput. Chem.Engng.1994,18:383-413.
[80]Gao D, Zhang B K, Ma X.Wu C C.Application of signed directed graph based fault diagnosis of atmospheric distillation unit [A]. In:The 2nd International Workshop on Intelligent Systems and Applications[C]. IEEE Computer Society, United States,2010,
[81]Cheung JT, Stephanopoulos G. Representation of process trends-Part Ⅰ. A formal representation framework [J]. Comput.& Chem. Engng.1990,14(4/5):495-510.
[82]Janusz M, Venkatasubramanian V. Automatic generation of qualitative description of process trends for fault detection and diagnosis [J]. Engineering Applications of Artificial Intelligence,1991,4 (5):329-339.
[83]Konstantinov K B, Yoshida T. Real-time qualitative analysis of temporal shapes of (Bio) process variables [J].AIChEJ,1992,38(11):1703-1715.
[84]Whiteley J R, Davis J F. Knowledge-based interpretation of sensor patterns [J]. Comput.& Chem. Engg.1992,16(4):329-346..
[85]Bakshi B R, Stephanopoulos G. Representation of process trends-Ⅲ. Multiscale extraction of trends from process data [J]. Comput.& Chem. Engng.1994,18(4):267-302.
[86]Bakshi B R, Stephanopoulos G. Representation of process trends-Ⅳ. Induction of real-time patterns from operating data for diagnosis and supervisory control [J]. Comput. & Chem. Engng.1994,18(4):303-332.
[87]Rengaswamy, R., Venkatasubramanian, V., A syntactic pattern recognition approach for process monitoring and fault diagnosis [J]. Engineering Applications of Artificial Intelligence,1995,8 (1),35-51.
[88]Rengaswamy R., Hagglund T., Venkatasubramanian V. A qualitative shape analysis formalism for monitoring control loop performance [J]. Engineering Applications of Artificial Intelligence.2001,14(1),23-33.
[89]Oh Y S, Moo K J, Yoon E S, Yonn J H. Fault diagnosis based on weighted symptom tree and pattern matching. Ind. Eng.Chem.Res [J].1997,36:2672-2678.
[90]Haimowitz I J,Le P P, Kohane I S, Clinical monitoring using regression based templates[J]. Arlifical Intelligence in medicine.1995,7:463-496.
[91]Vedam H, Venkatasubramanian V. A wavelet theory-based adaptive trend analysis system for process monitoring and diagnosis [J]. In American Control Conference,1997,309-313.
[92]Vedam H, Venkatasubramanian V. Bhalodia. A B-Spline based method for data compression, process monitoring and diagnosis [J]. Comput.& Chem. Engng., 22:S827-S830,1998.
[93]Vedam H, Venkatasubramanian V.PCA-SDG based process monitoring and fault diagnosis, Control Engineering Practice7 (7),1999,903-917.
[94]Wong J C, McDonald, K A, Palazoglu A. Classification of process trends based on fuzzied symbolic representation and hidden markov models [J]. Journal of process control,1998, 8(5-6):395-408
[95]Wong J C, McDonald, K A, Palazoglu A. Classificaiton of abnormal plant operation using multiple process variable trends [J]. Journal of process control,2001,11(4):409-418
[96]Dash S, Rengaswamy R, Venkatasubramanian V. Fuzzy-logic based trend classification for fault diagnosis of chemical processes [J]. Computers and Chemical Engineering. 2003,27(3),347-362.
[97]Maurya M R, Rengaswamy R, Venkatasubramanian V. Incipient fault diagnosis of Tennessee Eastman flowsheet using signed directed graph and trend analysis [A]. In: Supplementary Proceedings of the 12th European Symposium on Computer Aided Process Engineering (ESCAPE-12)[C]. The Hague, The Netherlands,2002.26-29.
[98]Dash S, Rengaswamy R, Venkatasubramanian V. A novel interval halving algorithm for process trend identification [A]. In 4th IFAC Workshop on On-Line Fault Detection & Supervision in the Chemical Process Industries[C], Korea,2001,155-160.
[99]Dash S. Data-Driven Qualitative and Model-Based Quantitative Approaches to Fault Diagnosis [D]. PhD thesis, Purdue University,2001.
[100]Charbonnier S, Garcia-Beltan C, Cadet C, Gentil S, Trends extraction and analysis for complex system monitoring and decision support [J]. Engineering Applications of Artificial Intelligence,2005,18:21-36.
[101]NOUNOU M N, BASKI B R. On-line Multiscale Filtering of Random and Gross Errors without Process Models [J]. AIChE,1999,45(5):1041-1058.
[102]COHEN A, DAUBECHIES I, VIAL P, Wavelets on the Interval and Fast Wavelet Transforms [J], Appl Comput. Harmonic Analysis,1993,1(1):54-81.
[103]刘志成,陈祥光,李宇峰等.传感器输出时间序列的实时小波滤波方法[J].北京化工大学学报,2007,1(34)：71-75.
[104]SWELDEN W. The lifting scheme:A custom-design construction of biorthogonal wavelets [J]. Appl Comput. Harmonic Analysis,1996,3(2):186-200.
[105]SWELDEN W. The lifting scheme:A construction of second generation wavelets [J]. SIAM J Math Anal,1997,29(2):511-546
[106]SWELDEN W, SCHRODER P. Building your own wavelets at home [EB/OL]. (2000-01-02) [2008-01-10]. http://cm.bell-labs.com/who/wim/papers/athome/athome.pdf
[107]高东,张贝克,吴重光.基于提升格式的过程数据在线去噪方法及其应用[J].计算机应用研究.2008,25(10)：3198-3220.
[108]FERNANDEZ G, PERIASWAMY S. A Software Package for Wavelet Transforms using Lifting.
[109]Wold S, Esbensen K, Geladi P.Principal Component Analysis [J]. Chemometrics and Intelligent Laboratory Systems (S0169-7439),1987,2(1):37.
[110]Kresta J, MacGregor J F, Marlin T E.Multivariate Statistical Monitoring of Process Operating Performance. [J] Canadian Journal of Chemical Engineering(S0008-4034),1991, 69(1):35.
[111]Nomikos P, MacGregor J F. Monitoring batch processes using multiway principal component analysis. AIChE Journal.1994,40(8):1361-1373. [112] Dunia R, Qin S J, Edgar T F, McAvoy T J. Identification of faulty sensors using principal
component analysis[J]. AIChE Journal.1996,42(10):2797-2812.