Fuzzy Diagnosis Research Articles

Detection of plugged injectors in a gasoline engine system using a neural fuzzy scheme

An incorrect fuel mixture or the use of inappropriate fuel additives may cause the injectors of a gasoline engine to become restricted, or the needles of the injectors to become stuck. In such an event, the injectors fail to spray normally or may even fail to function at all. Accordingly, this study develops a plugged-injector fault diagnosis system based upon a neural fuzzy scheme. Based upon knowledge of the engine speed, throttle position, injection duration, and vibration frequency, the fuzzy scheme is capable of diagnosing three distinct plugged-injector fault scenarios, namely one permanently plugged injector, two permanently plugged injectors, and one or two temporarily plugged injectors respectively. In addition, a group-injection fault diagnosis system is also developed with the ability to classify further two-plugged-injector fault scenarios as either group-injection faults or ungroup-injection faults. The experimental results confirm the ability of the two systems to diagnose correctly one- and two-plugged-injector faults. Furthermore, it is shown that the neural fuzzy plugged-injector diagnosis scheme provides a more accurate and reliable diagnosis than a polynomial-based approach for the two-plugged-injector fault scenario. Overall, the neural fuzzy schemes proposed in this study provide an efficient and practical means of diagnosing injector faults in gasoline engine systems.

Systematic Enumeration of Fuzzy Diagnosis Rules for Identifying Multiple Faults in Chemical Processes

A signed directed graph (SDG)-based computation procedure is proposed in this paper to predict the effects of one or more fault propagating in a multiloop process system. The conventional version of qualitative simulation techniques1 is modified to identify not only the locations of fault origins but also their magnitude levels. In addition, a computer algorithm is presented to generate the IF−THEN inference rules automatically according to the anticipated fault propagation behaviors. The effectiveness and feasibility of this approach has been tested with three case studies. Two of them are concerned with level control systems and the other an exothermic continuously stirred tank reactor (CSTR) with temperature and level control loops.

Neuro fuzzy schemes for fault detection in power transformer

This paper proposes fuzzy system and neural network approaches to identify the incipient faults in the power transformer using dissolved gas analysis (DGA) method. Using the IEC/IEEE DGA criteria and the gas concentration values as references the fuzzy diagnosis system and neural network are built. The proposed systems are verified using practical data collected from Electricity Board. The fuzzy system is tested with triangular, trapezoidal and Gaussian membership functions and its effectiveness is analyzed through simulation in terms of accuracy in identifying the transformer faults. The proposed Back propagation network is verified to overcome the drawbacks of conventional methods. The proposed schemes are simulated and tested in the software environment. The simulation results are presented.

Fuzzy diagnosis method for control systems with coupled feed forward and feedback loops

By considering the fault propagation behaviors in control systems with coupled feed forward and feedback loops, a fuzzy-logic-based fault diagnosis strategy has been developed in the present work. The proposed methods can be implemented in two stages. In the off-line preparation stage, the root causes of a system hazard are identified by determining the minimal cut sets of the corresponding fault tree. The occurrence order of observable disturbances caused by each fault origin is derived from the system digraph. All possible patterns of the on-line symptoms and their evolution sequences can then be deduced accordingly. These sequences are used as the basis for constructing a two-layer fuzzy inference system. In the next on-line implementation stage, the occurrence indices of the root causes are computed with the IF–THEN rules embedded in the inference engine using the real-time measurement data. Numerical simulation studies have been carried out to demonstrate the feasibility of the proposed approach.

A VIBRATION FAULT DIAGNOSIS SYSTEM OF HGS BASED ON FNN

Based on the characteristics of hydroelectric generating sets (HGS) vibration fault, a vibration fault diagnosis system of HGS is designed by fuzzy neural networks (FNN). At first, aiming at six typical vibration faults, fourteen vibration symptoms are extracted and the fuzzy diagnosis rules are established. Then FNN is used to learn these diagnosis rules and realize fuzzy inference of vibration fault diagnosis. The architecture and learning algorithm of FNN are presented in the paper. The results of simulation show the feasibility and validity of the diagnosis system based on FNN.

Modular expert system for the diagnosis of operating conditions of industrial anaerobic digestion plants

Anaerobic digestion (AD) plants are highly efficient wastewater treatment processes with possible energetic valorisation. Despite these advantages, many industries are still reluctant to use them because of their instability in the face of changes in operating conditions. To the face this drawback and to enhance the industrial use of anaerobic digestion, one solution is to develop and to implement knowledge base (KB) systems that are able to detect and to assess in real-time the quality of operating conditions of the processes. Case-based techniques and heuristic approaches have been already tested and validated on AD processes but two major properties were lacking: modularity of the system (the knowledge base system should be easily tuned on a new process and should still work if one or more sensors are added or removed) and uncertainty management (the assessment of the KB system should remain relevant even in the case of too poor or conflicting information sources). This paper addresses these two points and presents a modular KB system where an uncertain reasoning formalism is used to combine partial and complementary fuzzy diagnosis modules. Demonstration of the interest of the approach is provided from real-life experiments performed on an industrial 2,000 m3 CSTR anaerobic digester.

A framework of fuzzy diagnosis

Fault diagnosis has become an important component in intelligent systems, such as intelligent control systems and intelligent elearning systems. Reiter's diagnosis theory, described by first-order sentences, has been attracting much attention in this field. However, descriptions and observations of most real-world situations are related to fuzziness because of the incompleteness and the uncertainty of knowledge, e.g., the fault diagnosis of student behaviors in the elearning processes. In this paper, an extension of Reiter's consistency-based diagnosis methodology, fuzzy diagnosis, has been proposed, which is able to deal with incomplete or fuzzy knowledge. A number of important properties of the fuzzy diagnoses schemes have also been established. The computing of fuzzy diagnoses is mapped to solving a system of inequalities. Some special cases, abstracted from real-world situations, have been discussed. In particular, the fuzzy diagnosis problem, in which fuzzy observations are represented by clause-style fuzzy theories, has been presented and its solving method has also been given. A student fault diagnostic problem abstracted from a simplified real-world elearning case is described to demonstrate the application of our diagnostic framework.

A fuzzy diagnosis and advice system for optimization of emissions and fuel consumption

In this study, a fuzzy expert system has been developed, which is used for defining possible fuel system faults, ignition system faults, intake valve and exhaust valve faults and refers solution advice for these faults, which uses measurements of CO, HC, CO2, O2 and air ratio (@l). System gives decisions and advice by using rule base, which is prepared theoretic knowledge and experimental results as fuzzy. These decisions and advice are similar to expert views in a very high rate.

A Fuzzy Diagnosis Module for Oil Analysis in Industrial Diesel Engines

This paper presents the basic characteristics of a prototype fuzzy expert system being developed in order to improve the performance of a binary-logic based software on the particular application of oil analysis of Diesel engines (for industrial and transport fleet use). The system allows for reasoning under absent or imprecise measurements, providing with an interval-valued diagnostic of the suspected severity of a particular fault. A set of so-called metarules complements the basic fault dictionary for fine tuning, allowing extra functionality such as linear transformations of membership prior to logic operations, discarding previous conclusions in some circumstances and introducing the possibility of detecting contradiction between different diagnostic alternatives for the same fault.

MULTIMEDIA EXPERT SYSTEM FOR A NUCLEAR POWER PLANT ACCIDENT DIAGNOSIS USING A FUZZY INFERENCE METHOD

The huge and complicated plants such as nuclear power stations are likely to cause the operators to make mistakes due to a variety of inexplicable reasons and symptoms in case of emergency. That's why the prevention system assisting the operators is being developed for. First of all, I suggest an improved fuzzy diagnosis. Secondly, I want to demonstrate that a classification system of nuclear plant's accident investigating the causes of accidents foresees possible problems, and maintains the reliability of the diagnostic reports in spite of improper working in part. In the event of emergency in a nuclear plant, a lot of operational steps enable the operators to find out what caused the problems based on an emergent operating plan. Our system is able to classify their types within twenty to thirty seconds. As so, we expect the system to put down the accidents right after the rapid detection of the damage control-method concerned.

A comparison of two learning mechanisms for the automatic design of fuzzy diagnosis systems for rotating machinery

Abstract In this paper, we approach the problem of automatically designing fuzzy diagnosis rules for rotating machinery, which can give an appropriate evaluation of the vibration data measured in the target machines. In particular, we explain the implementation to this aim and analyze the advantages and drawbacks of two soft computing techniques: knowledge-based networks (KBN) and genetic algorithms (GA). An application of both techniques is evaluated on the same case study, giving special emphasis to their performance in terms of classification success and computation time. A reduced version of this paper first appeared under the title “A comparative assessment on the application of knowledge-based networks and genetic algorithms to the design of fuzzy diagnosis systems for rotating machinery”, published in the book “Soft Computing in Industry—Recent Appliactions” (Springer Engineering).

Evolving neural nets for fault diagnosis of power transformers

This paper proposes evolving neural nets (ENNs) for fault diagnosis of power transformers. Based on the proposed evolutionary algorithm, the ENNs automatically tune the network parameters (connection weights and bias terms) of the neural nets to achieve the best model. The ENNs can identify complicated relationships among dissolved gas contents in transformer oil and corresponding fault types, using the global search capabilities of the evolutionary algorithm and the highly nonlinear mapping nature of the neural nets. The proposed ENNs have been tested on the Taipower Company diagnostic records and compared with the fuzzy diagnosis system, artificial neural networks, and the conventional method. The test results confirm that the proposed ENNs are much more diagnostically accurate and require less learning time than the existing approaches.

A fuzzy diagnosis method in process systems with feedback control loops

By considering the fault propagation behaviors in process systems with control loops, a fuzzy-logic based fault diagnosis strategy has been developed in the present work. The proposed fault diagnosis methods can be implemented in two stages. In the off-line preparation stage, the potential causes of a system hazard are identified by deterrnining the minimal cut sets of a fault tree. The occurrence order of observable fault symptoms is derived frorn the system digraph and then encoded into a set of IF-THEN rules. In the next on-line diagnosis stage, the occurrence indices of the top event and also the fault origins are computed in a fuzzy inference system based on real-time measurement data. Simulation studies have been carried out to demonstrate the feasibility of the proposed approach.

Synthèse de la fonction de classification d'un système de diagnostic industriel

ABSRACT. The aim of this paper is to present a classifier based on a fuzzy inference system. For this classifier, we propose a parameterization method which is not necessarily based on an iterative training. This approach can be seen as a pre-parameterization which allows the determination of the rules base and the parameters of the membership functions. We also present for this classifier an iterative learning algorithm based on a gradient method. An example using the learning basis IRIS, which is a benchmark for classification problems, is presented showing the performances of this classifier. However in many cases the total knowledge necessary to the synthesis of the fuzzy diagnosis system is not, in general, directly available. It must be extracted from an often considerable mass of information. For this reason, a general methodology for the design of a fuzzy diagnosis system is presented and illustrated on a non-linear plant.

Sequential Fuzzy Diagnosis for Plant Machinery

When developing a fuzzy diagnosis system for machinery conditions, the relationship between fault symptoms and fault categories must be defined for fuzzy inference. However, it is not easy to determine the fault symptoms by which all fault categories can be distinguished perfectly and automatically. In order to resolve this problem, we proposed: (1) a new fuzzy diagnosis method called “sequential fuzzy diagnosis”, and (2) an identification method of the membership function of the symptom parameter by possibility theory. The efficiency of the above methods was verified by applying them to the rolling bearing diagnosis system and others. In the system of rolling bearing diagnosis, the symptom parameters are calculated by “goodness of fit” with spectrum analysis. The results of sequential fuzzy diagnosis show the correct conclusions when inputting field data to the system.

Fault identification of power transformers using genetic-based wavelet networks

The paper presents genetic-based wavelet networks (GWNs) for fault identification of power transformers. GWNs are three-layer structures, which contain wavelet, weighting and summing layers. Using a genetic-algorithm (GA) based optimisation process, the GWNs automatically tune the network parameters, translation and dilation in the wavelet nodes and the weighting values in the weighting nodes. The GWNs, with global search abilities of the GA and the multiresolution and localisation natures of the wavelets, can identify the complicated relations of dissolved gas contents in transformer oil to corresponding fault types. The proposed GWNs have been tested on the Taipower Company diagnostic records and compared with the fuzzy diagnosis system, artificial neural networks as well as the conventional method. The experimental results reveal that the GWNs have remarkable diagnostic accuracy and require far less construction time than conventional methods.

Parameterization of a fuzzy classifier for the diagnosis of an industrial process

Abstract The aim of this paper is to present a classifier based on a fuzzy inference system. For this classifier, we propose a parameterization method, which is not necessarily based on an iterative training. This approach can be seen as a pre-parameterization, which allows the determination of the rules base and the parameters of the membership functions. We also present a continuous and derivable version of the previous classifier and suggest an iterative learning algorithm based on a gradient method. An example using the learning basis IRIS, which is a benchmark for classification problems, is presented showing the performances of this classifier. Finally this classifier is applied to the diagnosis of a DC motor showing the utility of this method. However in many cases the total knowledge necessary to the synthesis of the fuzzy diagnosis system (FDS) is not, in general, directly available. It must be extracted from an often-considerable mass of information. For this reason, a general methodology for the design of a FDS is presented and illustrated on a non-linear plant.

A fuzzy diagnosis approach using dynamic fault trees

By incorporating digraph models, fault trees and fuzzy inference mechanisms in a unified framework, a novel approach for fault diagnosis is developed in this work. To relieve the on-line computation load, the fault origins considered in diagnosis are limited to the basic events in the cut sets of a given fault tree. The symptom occurrence order associated with each root cause is derived from system digraph with the qualitative simulation techniques. The implied candidate patterns are enumerated according to two proposed theorems and then encoded in the inference system with IF–THEN rules. The simulation results show that the proposed approach is not only feasible but also capable of identifying the most likely cause(s) of a hazardous event at the earliest possible time.

Evolving wavelet networks for power transformer condition monitoring

This paper proposes a novel model for power transformer condition monitoring using evolving wavelet networks (EWNs). The EWNs are three-layer structures, which contain wavelet, weighting and summing layers. The EWNs automatically adjust the network parameters, translation, and dilation in the wavelet nodes and the weighting values in the weighting nodes, through an evolutionary based optimization process. Global search abilities of the evolutionary algorithm as well as the multiresolution and localization natures of the wavelets enable the EWNs to identify the complicated, numerical-knowledge relations of dissolved gas contents in transformer oil to corresponding fault types. The proposed EWNs have been tested on the Taipower Company diagnostic records and compared with the fuzzy diagnosis system, artificial neural networks as well as the conventional method. The test results reveal that the EWNs possess far superior diagnosis accuracy and require less constructing time than the existing methods.

Abductive network model-based diagnosis system for power transformer incipient fault detection

An abductive network model (ANM)-based diagnosis system for power transformers fault detection is presented that enhances the diagnostic accuracy of the power transformer incipient fault. The ANM formulates the diagnosis problem into a hierarchical architecture with several layers of function nodes of simple low-order polynomials. The ANM links the complicated and numerical knowledge relationships of diverse dissolved gas contents in the transformer oil with their corresponding fault types. The proposed ANM has been tested on the Taipower company diagnostic records and compared with the previous fuzzy diagnosis system, artificial neural networks as well as with the conventional method. The test results confirm that the ANM possesses far superior diagnosis accuracy and requires less effort to develop.