Fault Diagnosis In Chemical Processes Research Articles

A semi-supervised approach to fault diagnosis for chemical processes

A new methodology for improving the performance of fault diagnosis systems (FDS) has been proposed by combining both supervised and unsupervised learning methods. Within this framework, different techniques have been applied, such as Independent Component Analysis (ICA) as feature extraction method, Gaussian Mixture Models (GMM) with Bayesian Information Criterion (BIC) for unsupervised clustering and Support Vector Machines (SVM) for the classification steps. Since supervised learning may fail to fully discriminate some individual faults, the algorithm presented allows the unsupervised grouping of some critical faults (classes) having a diagnosis performance below a threshold defined by the user. Next, an additional classification step provides practical information for decision-making in terms of the quantitative confidence on the occurrence of one fault (or some) among a known reduced subset. The methodology presented was assessed on the Tennessee Eastman Process (TEP) benchmark. The whole set of the TEP faults was considered and an improved diagnosis performance was obtained for all of them, including those faults (3, 9 and 15) whose diagnosis had hardly been addressed previously. These results demonstrate the enhanced capability of this method and the promising potential for the diagnosis of industrial applications.

Improving kernel fisher discriminant analysis for fault diagnosis in chemical process

The sample data in chemical process have strong nonlinearity and involve noise.To solve the problem of condition monitoring for chemical process,an improved KFDA method for fault diagnosis was proposed.It first performed the wavelet transform to remove noise,and the de-noised data were constructed KFDA model.Then a geometry-based feature vector selection(FVS) scheme was adopted to reduce the computational complexity of KFDA.Tennessee Eastman process(TEP) simulations were carried out to show that the given method is effective,and it enhances the accuracy of KFDA for fault diagnosis and reduces memory space and run time.

Sensor Location for Effective Fault Diagnosis in Micro Chemical Processes

It is clear from worldwide research that micro chemical processes (MCPs) offer a unique approach to the spatial and temporal control of chemical reactions. The well-known advantages of MCPs are often counterbalanced by serious faults such as channel blockage and catalyst deterioration. To realize stable long-term operation of MCPs, it is necessary to develop a monitoring system that can detect and diagnose these faults. In this work, a physical model-based process monitoring system for a tubular microreactor is developed. A state space model is derived by using the orthogonal collocation method, and the extended Kalman filter is used as an observer. The optimal sensor locations are determined so that unknown parameters such as catalyst effectiveness can be estimated most accurately. In addition, the validity of the conventional observability measures in solving the sensor location problems of MCPs is assessed.

Systematic Development of Automata Generated Languages for Fault Diagnosis in Continuous Chemical Processes

Abstract Abstract A SDG-based simulation procedure is presented in this study to qualitatively predict all possible effects of one or more fault propagating in a given process system. All possible state evolution behaviors are characterized with an automaton model. By selecting a set of on-line sensors, the corresponding diagnoser can be constructed and the diagnosability of every fault origin can be determined accordingly. Furthermore, it is also possible to construct a formal diagnostic language on the basis of this diagnoser. Every string (word) in the language is then encoded into an IF-THEN rule and, consequently, a comprehensive fuzzy inference system can be synthesized for on-line diagnosis. The feasibility of this approach is demonstrated with a simple example in this paper.

Fault diagnosis in chemical processes with application of hierarchical neural networks

In this paper the chemical process fault diagnosis is considered. It is offered to apply a hierarchical neural network (NN) model built and trained with application of the expert analysis, which results in improvement of NN model architecture and training set selection. At a high level, the network serves for localization of the process faults, and at a low level, a set of networks identifies the causes of these faults. РСА is used for essential dimensionality reduction for the high level network. The decomposition of expert knowledge of the monitoring process determines the number of neurons in the output layer. The training set for that network includes projections of the fuzzy values of diagnostic parameters (the scores) onto the principal component space. These values characterize normal and abnormal states of the process and they are obtained from analysis of the expert information and HAZOP (hazard and operability) analysis of the process. Dimensions of the low level networks are rather low; therefore the scaled process variables can be fed directly into the network. Such an approach reduces the networks retraining time essentially. It also keeps the advantages of expert systems without their explicit introduction in the diagnostic system structure. In particular, if a new situation occurs, the faulty section of the process under control will be defined even in case the network of the low level does not identify this fault. The efficiency of the suggested method is shown on the example of the faults diagnosis of the hydrocarbons pyrolysis process.

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.

역할-거동 모델링에 기반한 화학공정 이상 진단을 위한 이상-인과 그래프 모델의 합성

In this research, the automatic synthesis of knowledge models is proposed. which are the basis of the methods using qualitative models adapted widely in fault diagnosis and hazard evaluation of chemical processes. To provide an easy and fast way to construct accurate causal model of the target process, the Role-Behavior modeling method is developed to represent the knowledge of modularized process units. In this modeling method, Fault-Behavior model and Structure-Role model present the relationship of the internal behaviors and faults in the process units and the relationship between process units respectively. Through the multiple modeling techniques, the knowledge is separated into what is independent of process and dependent on process to provide the extensibility and portability in model building, and possibility in the automatic synthesis. By taking advantage of the Role-Behavior Model, an algorithm is proposed to synthesize the plant-wide causal model, Fault-Causality Graph (FCG) from specific Fault-Behavior models of the each unit process, which are derived from generic Fault-Behavior models and Structure-Role model. To validate the proposed modeling method and algorithm, a system for building FCG model is developed on G2, an expert system development tool. Case study such as CSTR with recycle using the developed system showed that the proposed method and algorithm were remarkably effective in synthesizing the causal knowledge models for diagnosis of chemical processes.

Sensor fault identification based on time-lagged PCA in dynamic processes

Principal component analysis (PCA) is widely employed as a multivariate statistical method for fault detection, isolation and diagnosis in chemical processes. Previously, PCA has been successfully used to identify faulty sensors under normal static operating conditions. In this paper, we extend the reconstruction-based sensor fault isolation method proposed by Dunia et al. to dynamic processes. We develop a new method for identifying and isolating sensor faults in an inherent dynamic system. First, we describe how to reconstruct noisy or faulty measurements in dynamic processes. The reconstructed measurements are obtained by simple iterative optimization based on the correlation structure of the time-lagged data set. Then, based on the sensor validity index (SVI) approach developed by Dunia et al., we propose an SVI for fault isolation in dynamic processes. The proposed method was applied to sensor fault isolation in two strongly dynamic systems: a simulated 4×4 dynamic process and a simulated wastewater treatment process (WWTP). In these experiments, the proposed sensor fault identification method correctly and rapidly identified the faulty sensor; in contrast, the traditional PCA-based sensor fault isolation approach showed unsatisfactory results when applied to the same systems.

Multiple-Fault Diagnosis Based on System Decomposition and Dynamic PLS

This study suggests a hybrid method of signed digraph and partial least squares for the fault diagnosis of chemical processes. Using the local qualitative relationships of each variable in a signed digraph, a process is decomposed into subprocesses to allow for the reliable diagnosis of multiple faults. A partial least-squares model is built for the estimation of each measured variable in each decomposed subprocess. To handle the process dynamics accurately, the input of the partial least-squares model uses both the current values and the past values of the process variables. In each case, the measured and estimated values are compared to diagnose the fault. A case study of a continuously stirred tank reactor illustrates the conclusion that the proposed method greatly improves the accuracy, resolution, and reliability of the diagnosis.

Fault detection and classification in chemical processes based on neural networks with feature extraction

Abstract Feed forward neural networks are investigated here for fault diagnosis in chemical processes, especially batch processes. The use of the neural model prediction error as the residual for fault diagnosis of sensor and component is analyzed. To reduce the training time required for the neural process model, an input feature extraction process for the neural model is implemented. An additional radial basis function neural classifier is developed to isolate faults from the residual generated, and results are presented to demonstrate the satisfactory detection and isolation of faults using this approach.

Fuzzy-logic based trend classification for fault diagnosis of chemical processes

In this paper, fault diagnosis based on patterns exhibited in the sensors measuring the process variables is considered. The temporal patterns that a process event leaves on the measured sensors, called event signatures, can be utilized to infer the state of operation using a pattern-matching approach. However, the qualitative nature of the features leads to imprecise classification boundaries at the trend-identification stage and hence at the trend-matching stage. Moreover, noise and other underlying phenomena may lead to non-reproducibility of the same trends chosen to represent an event. Thus, a crisp inference process might lead to a large knowledge-base of signatures; it could also cause misclassification. To overcome this, a fuzzy-reasoning approach is proposed to ensure robustness to the inherent uncertainty in the identified trends and to provide succinct mapping. A two-staged strategy is employed: (i) identifying the most likely fault candidates based on a similarity measure between the observed trends and the event-signatures in the knowledge-base and, (ii) estimation of the fault magnitude. The fuzzy-knowledge-base consists of a set of physically interpretable if–then rules providing physical insight into the process. The technique provides multivariate inferencing and is transparent. We illustrate the application of the proposed approach in the fault diagnosis of an exothermic reactor case study.

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.

Multi-Agents and Distributed Constraint Reasoning for Fault Diagnosis of Chemical Processes

In this paper, we propose a topology-based, message-passing Diagnostic Agent (DA) architecture. The diagnostic agents in charge of each process unit perform local diagnoses, exchange related information with other diagnostic agents, and cooperatively solve the global diagnostic problem of the whole process plant just like human experts would do. For their better sharing of process knowledge and information, we also suggest a way of remodeling processes taking into account semantic abstracts of process information or data. The benefits of the suggested collaborative problem solving approach are demonstrated by solving the diagnostic problem of a CSTR system with recycle and a first order irreversible reaction.

Cooperative problem solving in diagnostic agents for chemical processes

In this paper we introduce an agent-based framework for the diagnosis of chemical processes, based on spatially distributed diagnosis architecture. Although the suggested multi-agent diagnostic system uses only the information about process topology and control structure, making the most of local information produces global diagnostic solution. A function-behavior model is also suggested to make possible the collaborative problem solving in chemical process fault diagnosis. To demonstrate the benefits of the suggested collaborative problem solving approach, we solve the diagnostic problem of a stirred-tank reactor system with recycle.

Fault diagnosis in chemical processes using Fisher discriminant analysis, discriminant partial least squares, and principal component analysis

Principal component analysis (PCA) is the most commonly used dimensionality reduction technique for detecting and diagnosing faults in chemical processes. Although PCA contains certain optimality properties in terms of fault detection, and has been widely applied for fault diagnosis, it is not best suited for fault diagnosis. Discriminant partial least squares (DPLS) has been shown to improve fault diagnosis for small-scale classification problems as compared with PCA. Fisher's discriminant analysis (FDA) has advantages from a theoretical point of view. In this paper, we develop an information criterion that automatically determines the order of the dimensionality reduction for FDA and DPLS, and show that FDA and DPLS are more proficient than PCA for diagnosing faults, both theoretically and by applying these techniques to simulated data collected from the Tennessee Eastman chemical plant simulator.

SQFDiag: semi-quantitative model-based fault monitoring and diagnosis via episodic fuzzy rules

A method for chemical process fault diagnosis using semi-quantitative model generated behavior envelopes is described. The method generates a sequence of rules for each fault class, with any rule in a sequence valid within the bounds of its time interval. This can be viewed as a qualitative description of the trend of numerical sensor measurements. For each variable in each fault class two sequences of episodic fuzzy rules are automatically generated, one for the lower and one for the upper numerical behavior envelope. The diagnostic system monitors a process via the measured sensors. The measurements are matched against the fuzzy rules for the current time in the rule base. In the case of an overlapping region defined by behavior envelopes, the distance introduced and time based fault belief scaling allows ranking of fault candidates. A novel abnormal situation will not pass the introduced system undetected due to a novel class detection mechanism. In two case studies, the system detected the correct fault even in cases of nearly total overlapped fault regions bounded by behavior envelopes.

Potential applications of artificial neural networks to thermodynamics: vapor–liquid equilibrium predictions

The associative property of artificial neural networks (ANNs) and their inherent ability to “learn” and “recognize” highly non-linear and complex relationships finds them ideally suited to a wide range of applications in chemical engineering. Dynamic Modeling and Control of Chemical Process Systems and Fault Diagnosis are the two significant applications of ANNs that have been explored so far with success. This paper deals with the potential applications of ANNs in thermodynamics — particularly, the prediction/estimation of vapor–liquid equilibrium (VLE) data. The prediction of VLE data by conventional thermodynamic methods is tedious and requires determination of “constants” which is arbitrary in many ways. Also, the use of conventional thermodynamics for predicting VLE data for highly polar substances introduces a large number of inaccuracies. The possibility of applying ANNs for VLE data prediction/estimation has been explored using the back propagation algorithm. The methane–ethane and ammonia–water systems have been studied and the VLE predictions have been found to be accurate to within ±1%. Preliminary results confirm exciting possibilities of ANNs for applications to thermodynamics of mixtures. Advantages and limitations of this application are also discussed. An heuristic approach to reduce the trial and error process for selecting the “optimum” net architecture is discussed.

Semi-Quantitative Model Based Chemical Process Fault Diagnosis via Episodic Fuzzy Rules

A method for chemical process fault diagnosis using numerical behavior envelopes is described in this paper. A sequence of fuzzy rules is generated from numerical behavior envelopes for each fault class where any rule in a sequence is only valid within the bounds of its time interval. For each observed process variable in each fault class two sequences of episodic fuzzy rules, which provIde a parsimonious, qualitative description of the trend of the variable, are automatically generated one for the lower and one for the upper numerical behavior envelope. The observed process measurements are matched against the fuzzy rules for the current time in the rule base. In case of an overlapping region defined by behavior envelopes, the introduced distance and time based fault bellef scahng allows ranking of fault candidates. A novel abnormal situation will not pass the Introduced system undetected due to a novel class detection mechanism. The diagnostic performance of the system is shown in two case studies.

A methodology for fault diagnosis in large chemical processes and an application to a multistage flash desalination process: Part I

Abstract This work presents a new strategy for fault diagnosis in large chemical processes (E.E. Tarifa, Fault diagnosis in complex chemistries plants: plants of large dimensions and batch processes. Ph.D. thesis, Universidad Nacional del Litoral, Santa Fe, 1995). A special decomposition of the plant is made in sectors. Afterwards each sector is studied independently. These steps are carried out in the off-line mode. They produced vital information for the diagnosis system. This system works in the on-line mode and is based on a two-tier strategy. When a fault is produced, the upper level identifies the faulty sector. Then, the lower level carries out an in-depth study that focuses only on the critical sectors to identify the fault. The loss of information produced by the process partition may cause spurious diagnosis. This problem is overcome at the second level using qualitative simulation and fuzzy logic. In the second part of this work, the new methodology is tested to evaluate its performance in practical cases. A multiple stage flash desalination system (MSF) is chosen because it is a complex system, with many recycles and variables to be supervised. The steps for the knowledge base generation and all the blocks included in the diagnosis system are analyzed. Evaluation of the diagnosis performance is carried out using a rigorous dynamic simulator.

A methodology for fault diagnosis in large chemical processes and an application to a multistage flash desalination process: Part II

A methodology for fault diagnosis in large chemical processes and an application to a multistage flash desalination process: Part II