Fault Diagnosis Of Steam Turbine Research Articles

A three-way decision method with probability dominance relation in interval-valued hesitant fuzzy environment for marine steam turbine fault diagnosis

A three-way decision method with probability dominance relation in interval-valued hesitant fuzzy environment for marine steam turbine fault diagnosis

Research on Vibration Fault Diagnosis of Steam Turbine Based on Equipment Tree

As the main major equipment in the power plant, the steam turbine has a complex structure and poor operating environment. Its reliability is very important for the power plant. Intelligent fault diagnosis of steam turbines is an important part of the construction of smart power plants. As a complex system, the operation state of a steam turbine may be affected by a variety of faults. Different faults are interconnected and excited each other, which is often caused by the concurrence of other faults due to the occurrence of one fault. The external phenomenon produced is the result of the comprehensive action of many factors. The intelligent fault diagnosis system of steam turbines is based on traditional parameter monitoring and further analyzes on the basis of monitoring to find out the cause of the fault and gives maintenance suggestions. It includes diagnosing the faults that have occurred to prevent further deterioration and predicting the faults that have not occurred to prevent the occurrence of faults so as to achieve the purpose of fault diagnosis, pre-diagnosis, and intelligent maintenance.

Extreme learning machine – radial basis function (ELM-RBF) networks for diagnosing faults in a steam turbine

ABSTRACT A fast and reliable fault diagnosis system for a steam turbine in thermal power plant is crucial. The system will detect and classify a potential or occurring fault, hence suitable precautions steps will be correctly determined, and unplanned breakdown will be prevented. This study proposes a new application of extreme learning machine-radial basis function networks (ELM-RBF) for steam turbine fault diagnosis system. ELM-RBF recently has been known for its extremely fast computation. The proposed system was tested with real fault historical data from a steam power plant in Jakarta. To evaluate the system performance, a comparison with backpropagation neural networks (BPNN) was conducted. Four scenarios using ELM-RBF and BPNN, with and without ReliefF for feature selection were designed. The results show high accuracy in almost all the scenarios tested. The BPNN shows better accuracy than ELM-RBF, however, ELM-RBF performs considerably faster computation than BPNN without significant decrease in accuracy.

Research on Fault Diagnosis of Steam Turbine Based on Bayesian Network

In the fault diagnosis of steam turbine, multiple faults contain number of uncertainties due to the complexity of fault diagnosis knowledge and the strong correlation and coupling between different faults and massive prior knowledge is needed. In this paper, a fault diagnosis method of steam turbine based on Bayesian network is proposed. Various faults and symptoms are parameterized using Bayesian network nodes. Then rough set theory is used to simplify the complex causal relationship between faults and symptoms, and Noisy-Or model is used to simplify the conditional probability parameters. A diagnostic model of the steam turbine was developed using a simplified Bayesian network. The experiment results are shown to validate the practicality and effectiveness of the proposed designs.

Steam Turbine Performance Evaluation Based on Principal Component Analysis and Information Entropy

Information entropy and fuzzy analytical theory were combined and applied on the state assessment of power plant steam turbine unit. This method can be combined with the measured data of power plant, and made a comprehensive evaluation of the different working conditions. Fuzzy analysis of the original matrix can be a evaluation matrix, and the information entropy was introduced to solve the problem of calculating the weight of multi attribute factor set. Once the attribute weight is determined, the comprehensive evaluation value corresponding to the different working conditions can be defined and calculated. The results obtained by this method were compared with those obtained by the principal component analysis method. And the results obtained by information entropy method were objective and unique. The superiority of the method was verified. Under all conditions, the comprehensive evaluation value can be used as one index of the thermal archives as a benchmark for fault diagnosis, which provided a new idea and evaluation method for steam turbine fault diagnosis, and had a strong basic research and practical application value.

A New Similarity Measure of Picture Fuzzy Sets and Application in the Fault Diagnosis of Steam Turbine

A New Similarity Measure of Picture Fuzzy Sets and Application in the Fault Diagnosis of Steam Turbine

Steam turbine fault diagnosis based on single-valued neutrosophic multigranulation rough sets over two universes

Steam turbine fault diagnosis based on single-valued neutrosophic multigranulation rough sets over two universes

An interval-valued hesitant fuzzy multigranulation rough set over two universes model for steam turbine fault diagnosis

In the field of mechanical engineering, steam turbine fault diagnosis is a difficult task for mechanical engineers who are confronted with challenges in dealing with copious amounts of uncertain information. Different mechanical engineers may have their own opinions about the system fault knowledge base that differs slightly from other mechanical engineers. Thus, to solve the problems presented by uncertain data analysis and group decision-making in steam turbine fault diagnosis, we propose a new rough set model that combines interval-valued hesitant fuzzy sets with multigranulation rough sets over two universes, called an interval-valued hesitant fuzzy multigranulation rough set over two universes. In the multigranulation framework, both basic definitions and some important properties of the proposed model are presented. Then, we develop a general approach to steam turbine fault diagnosis by using the proposed model. Lastly, an illustrative example is provided to verify the established approach and demonstrate its validity and applicability.

Fault diagnoses of steam turbine using the exponential similarity measure of neutrosophic numbers

Since the neutrosophic number consists of its determinate part d and its indeterminate part eI denoted by N = d + eI, it is very suitable for dealing with real problems with indeterminacy. Therefore, this paper proposes the exponential similarity measure of neutrosophic numbers and a fault diagnosis method of steam turbine by using the exponential similarity measure of neutrosophic numbers. By the similarity measure between the fault diagnosis patterns and a testing sample with neutrosophic numbers and its relation indices, we can determine the fault type and indicate fault trends. Then, the vibration fault diagnosis results of steam turbine demonstrate the effectiveness and rationality of the proposed diagnosis method. The proposed diagnosis method not only gives the main fault types of steam turbine but also provides useful information for multi-fault analyses and future fault trends. The developed diagnosis method is effective and reasonable in the fault diagnosis of steam turbine under an indeterminate environment.

Single-valued neutrosophic similarity measures based on cotangent function and their application in the fault diagnosis of steam turbine

Similarity measure is an important tool in pattern recognition and fault diagnosis. This paper proposes two cotangent similarity measures for single-valued neutrosophic sets (SVNSs) based on cotangent function. Then, the weighted cotangent similarity measures are introduced by considering the importance of each element. Moreover, by the comparison between the cotangent similarity measures of SVNSs and existing cosine similarity measure of SVNSs, the developed cotangent similarity measures demonstrate their advantages and rationality and in some cases can overcome some disadvantages of the cosine similarity measure defined in vector space. Finally, the cotangent similarity measures are applied to the fault diagnosis of steam turbine. The proposed fault diagnosis method demonstrates its effectiveness and rationality by the comparative analysis with the cosine similarity measure in the fault diagnosis of steam turbine.

Implementation of VLSI model as a tool in diagnostics of slowly varying process parameters which affect the performance of steam turbine

There is a global challenge in demand and need of electricity. Whenever a serious fault occurs, it affects the productivity of any power plant. So many indicators have been identified in real-time fault diagnosis of steam turbine which is extremely important in a functioning power plant. Detection of fault and early rectification requires a real time intelligent fault diagnostic system. This paper considers seven types of very slowly happening and accumulating physical phenomena which will ultimately lead to deterioration in turbine performance. Based on the acquired domain knowledge, an online intelligent diagnostic analyzer for turbine performance degradation is designed in this paper by using a VLSI based methodology written in Verilog code and simulated using a simulator (Modelsim Altera 6.4a). This system can be easily implemented on to FPGA which enables the identification of the root causes for turbine performance degradation. The simulation results show that the developed real-time fault diagnostic system is accurate, high percentile with less time consuming, cost effective, and easy to apply and user friendly.

Research and Application on Fault Diagnosis for Steam Turbine Using Multi-Parameter Fusion

For the running situation of supercritical and ultra-supercritical steam turbine unit, a fault diagnosis method of steam turbine based on multiple parameters fusion is proposed. The association of the fault mode with the vibration parameters, the thermodynamic parameters and the operational parameters is built, according to fault development mechanism, equipment operation data and professional experience. The overall state evaluation of mechanical equipment is given, the reliability of fault diagnosis is improved, and the need of the steam turbine fault diagnosis is met, by means of comprehensive evaluation of multiple parameters. Example applications verify this method.

Analysis and Application of Three Methods of Fault Diagnosis Problem

The problem of fault diagnosis of steam turbine used three methods of generating units, the results show that not only the method in this paper is multiple fault diagnosis method, and the formula is more simple, more practical application results.

The Research on the Methods of Diagnosing the Steam Turbine Based on the Elman Neural Network

This paper introduces a kind of diagnosis principle and learning algorithm of steam turbine fault diagnosis which based on Elman neural network. Comparing the results of the Elman neural network and the traditional BP neural network diagnosis, the results shows that Elman neural network is an effective way to improve the learning speed , effectively suppress the minimum defects that the traditional neural network easily trapped in, and shorten the autonomous learning time. All these proves that the Elman neural network is an effective way to diagnose the steam turbine.

PNN and GRNN Approach for Fault Diagnosis of Steam Turbine

The artificial neural networks have received wide research efforts in fault diagnostics in recent years. This study proposes two types of feedforward neural networks (PNN and GRNN) for diagnosing the fault of the steam turbine. The eigenvectors of the vibration signals in steam turbine can be extracted by the time-domain analysis after the wavelet packet decomposition and reconstruction. Depending on these eigenvectors, we developed the fault diagnosis program with the PNN and GRNN approach for the steam turbine in Matlab, and diagnosed two common faults of steam turbine (mass unbalance and oil whirl). The diagnostic accuracy is up to 94.44%, and the diagnostic time is short. The results demonstrate that the diagnostic approach is able to identify the common faults of steam turbine quickly and efficiently.

Study on steam turbine fault diagnosis and maintenance service grid system

It is important to ensure the safe operation, quick fault diagnosis, and maintenance of steam turbines. This is a challenging problem since steam turbines tend to be geographically dispersed and it is difficult to offer a timely response to a facility that can be a considerable distance from the maintenance division. The manufacturing grid is resource sharing technology that could provide a solution to this problem. A framework to apply this concept to steam turbine fault diagnosis and maintenance operations is proposed in this paper. In the proposed manufacturing grid the fault type is identified by an artificial neural network algorithm and the maintenance solution is given on the basis case-based reasoning with the framework of rough set theory. A prototype system is developed on the basis of proposed methodologies to demonstrate their feasibility.

Data Mining for Fault Diagnosis and Machine Learning for Rotating Machinery

Data mining is used not only for database analyses, but also for machine learning. The data mining technique described in this paper was used for steam turbine fault diagnostics based on continuous data measurements. The classification rules are based on standardized vibration frequency data for steam turbines and field experts’ analyses of turbine vibration problems. The expert knowledge enables the steam turbine fault diagnosis system to be more powerful and accurate. The system can identify twenty types of standard steam turbine faults. The system was developed using 2000 simulated data sets. The data mining methods were then used to identify 20 explicit rules for the turbine faults. The method was also used with actual power plant data to successfully diagnose real faults. The results indicate that data mining can be effectively applied to diagnosis of rotating machinery by giving useful rules to interpret the data.