Turbine Fault Diagnosis Research Articles

Fault Diagnosis of Horizontal Axis Turbine with Different Twist Angle to Reduce Stress under Failure Thrust Force

Five types of configurations of tidal turbine blade including validation model have been considered with different profile tidal turbine blade with twist angle of 9, 10, 10.5, 11, 11.5 and 12 degrees. An optimized model of tidal turbine blades is developed. The simulation of the optimized model i.e. 12 degree twist angle gives minimum value of stress and deformation at different loads i.e. 441, 271, 272 and 610N which has optimized and converged result compared to respected models of tidal turbine blade, it has also been observed that stress and deformation was reduced at static load of 610N in 12 degree twist angle tidal turbine blade with the Zylon, Kevlar and CFRP material, thus the observed fault is diagnosed in this present research work. The configuration of optimized model gives maximum convergence on all parameters amongst all the configurations used.

Data fusion of wireless sensor network for prognosis and diagnosis of mechanical systems

With the promotion of the latest technologies and the new requirement of humanitarian, the wireless multi-sensor system is applied broadly. This paper studies the data fusion of the industrial wireless sensor networks (IWSNs), in order to acquire more thoughtful data for the prognosis and diagnosis of the monitored device. These authors propose a combination of back propagation neural network (BP NN) and Wavelet Packet algorithm for data fusion. This proposed algorithm is based on each cluster head, which is modelled with a three layers NN. A case study using the ball bearing test data, which is from the Bearing Data Center of the Case Western Reserve University, and to verify the effectiveness of the proposed algorithm. With MATLAB 2016b version, the raw data feature is extracted by the Wavelet Packet and the feature fusion is based on BP NN at sink node. The simulation results show that the proposed algorithm is effective in fault diagnosis of wind turbine.

Research on Multidomain Fault Diagnosis of Large Wind Turbines under Complex Environment

Under the complicated environment of large wind turbines, the vibration signal of a wind turbine has the characteristics of coupling and nonlinearity. The traditional feature extraction method for the signal is hard to accurately extract fault information, and there is a serious problem of information redundancy in fault diagnosis. Therefore, this paper proposed a multidomain feature fault diagnosis method based on complex empirical mode decomposition (CEMD) and random forest theory (RF). Firstly, this paper proposes a novel method of complex empirical mode decomposition by using the correlation information between two-dimensional signals and utilizing the idea of ensemble empirical mode decomposition (EEMD) by adding white noise to suppress the problem mode mixing in empirical mode decomposition (EMD). Secondly, the collected vibration signals are decomposed into IMFs by CEMD. Then, calculate 11 time domain characteristic parameters and 13 frequency domain characteristic parameters of the vibration signal, and calculate the energy and energy entropy of each IMF components. Make all the characteristic parameters as the multidomain feature vectors of wind turbines. Finally, the redundant feature vectors are eliminated by the importance of each feature vector which has been calculated, and the feature vectors selected are input to the random forest classifier to achieve the fault diagnosis of large wind turbines. Simulation and experimental results show that this method can effectively extract the fault feature of the signal and achieve the fault diagnosis of wind turbines, which has a higher accuracy of fault diagnosis than the traditional classification methods.

Implementation of IOT for Real Time Monitoring and Fault Diagnosis of Wind Turbine

Implementation of IOT for Real Time Monitoring and Fault Diagnosis of Wind Turbine

가스터빈 고장 진단을 위한 기계 학습과 유전 알고리즘을 이용한 특징 분석

가스터빈 고장 진단을 위한 기계 학습과 유전 알고리즘을 이용한 특징 분석

Fault Diagnosis of Wind Turbine Based on ELMD and FCM

In view of failure characteristics of wind turbine gear box, this paper put forward a method for fault diagnosis based on the ensemble local means decomposition (ELMD) and fuzzy C-means clustering (FCM) method. By resolving the vibration signal of different fault state of high speed gear box by ELMD, the PF component was obtained with its singular value, which was composed of known sample followed by a test sample as the feature vector. The known sample was clustered by using the FCM clustering, and the test sample was recognized and classified . The experimental results show that the method for fault diagnosis based on ELMD and FCM clustering has good diagnosis results.

3-Dimensional Numerical Simulation of Tesla Disc Turbines for Industrial Dust Blower

Tesla disc turbine has many advantages compared with the traditional blade turbine, but there are few researches on fault diagnosis of Tesla disc turbines for industrial dust blower. In this paper, 3-dimensional model Tesla turbine is established by using CFD software FLUENT to analyze the inner flow field in the given pressure and boundary conditions. The experiments provide a good foundation for the theoretical research and the application of fault diagnosis of the Tesla disc turbines for industrial dust blower.

Fault Diagnosis of Wind Turbine's Converter Based on Memristive Neural Network

In this paper, a memristive neural network was applied to fault diagnosis of wind turbine's converter. A model of memristive neural network was built in order to diagnose and analyze of the failure information by MATLAB Simulink. Experimental results show that the proposed method can achieve better results and has certain significance for the application of memristors widely used in the near future.

Fault Diagnosis of Wind Turbines Based on Improved Neural Network

The gearbox is an important module of wind turbine. In order to diagnosis the fault of wind turbine gearbox, a method based on the improved neural network is proposed. According to the characteristics of the wind turbine gearbox, several vibration sensors are set in the gearbox, so as to acquire the feature vector of gearbox. After training, the improved neural network is verified with some test samples. The result proved that the method is suitable for fault diagnosis in gearbox of wind turbine.. Keywords: wind turbine gearbox, fault diagnosis, particle swam, neural network.

Fault Diagnosis of Wind Turbine Bearings Based on Hilbert Space Feature Entropy

The fault diagnosis of wind turbines is difficult because of the wind speed changing. To solve this problem, a method designated as Hilbert space feature entropy is proposed. The information entropy based on HHT is used to describe the wind turbine bearing vibration signal under different wind speeds. Using this method to analysis the fault of the D70 type wind turbine bearings, which proved that this method can effectively identify the fault of wind turbine bearing under different wind speed . Thus the method can be used as index and basis of the fault diagnosis of wind turbine bearing.

The Research of Data Communication on Wind Power Monitoring and Diagnosis System Based on XML

The wind turbine remote monitoring and fault diagnosis is the key of improving unit efficiency, reducing maintenance costs, and ensuring safe and stable operation of the wind farms. A wide variety of wind farm monitoring systems, non-uniform communication standards, and heterogeneous communication platforms is result in a difficulty of information exchange. In this paper, on the basis of following IEC61400-25 standard, we put forward using XML technology to encapsulate data to avoid the formation of the "information island" in wind farms; By combining with VC++ Socket technology to establish a network communication system, this paper solves the data exchange problem of the wind turbine remote monitoring and fault diagnosis system through achievement of data receiving and dispatching; In the end, we use the waveform curve way to display the XML parsing of data, which is convenient for staff to observe and analyze the data.

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.

Research on Fault Diagnosis Method of Wind Turbine Based on Wavelet Analysis and LS-SVM

Aiming at the fault characteristics of high-speed gearbox fault diagnosis of wind turbine, a fault diagnosis method of combining wavelet analysis with least square-support vector machine (LS-SVM) is proposed. According to the method, the energy of frequency bands generated by wavelet decomposition and reconstruction of the high-speed gearbox's vibration signals in different fault states is normalized as eigenvectors, forming training and testing samples of LS-SVM fault classifier. Train the LS-SVM fault diagnosis model with the training samples and test the accuracy with the testing samples. The result of research shows that the fault diagnosis method based on the wavelet analysis and LS-SVM has good diagnostics effect.

Fault Diagnosis Based on Rough Set and BP Neural Network (RS-BP) for Gas Turbine Engine

This paper presents a new fusion diagnosis based on rough set and BP neural network for the fault diagnosis of gas turbine. The frame is designed to fusion fault diagnosis, which is composed by three parts: the rough set data pre-processor, rough set diagnosis model and BP neural network diagnosis model. Aiming at the difficulty in getting adequate fault samples in fault diagnosis, rough set theory is first used to process the original data, establish the decision table and generate rules, which can eliminate the redundant information and build the rough set diagnosis model. After that, according to the optimal decision attribute pre-treated by rough set, BP neural network is designed for fault diagnosis, which can reduce the scale of neural network, improve the identification rate, and improve the efficiency of the whole fusion diagnosis system. Finally, an example of gas turbine generator sets fuel system is taken as a case study to demonstrate the feasibility and validity of the proposed method in this paper.

Fault Diagnosis of Wind Turbines Based on Noise Detection

Aiming at backward current situation of testing technology and fault diagnosis technology of wind power generation in China, a fault diagnosis method based on based on noise detection is put forward. Studied IEC 61400-11 noise measurement technology standard, this paper elaborates the noise detecting method, analyzes the feasibility and diagnostic steps of fault diagnosis, proposes fault signal extracting method based on wavelet analysis. According to analysis and simulation, it is shown that noise measurement is earlier than vibration detection, and the fault signal can be extracted effectively, so it has important value for engineering application.

Study on Fault Diagnosis of Turbine Using an Improved Cosine Similarity Measure for Vague Sets

Study on Fault Diagnosis of Turbine Using an Improved Cosine Similarity Measure for Vague Sets

Study on Speed Measurement of Steam Turbine Shaft

Speed signal is an important monitoring signal in Steam Turbine Condition Monitoring And Fault Diagnosis(TDM) system. A review on the existing speed measurement methods of rotary machine was proposed to find out the defects of each method. A new approach was introduced to fulfill steam turbine speed accurate measuring. The periods of phase signal pulse generated by the key groove and speed signal pulse generated by the velocimetry gear, were measured respectively by the two independent 16-bit timer/counters, and the "counter overflow" problem was resolved by calling a byte memory unit. According to the record number of the counter, the value of steam turbine speed was calculated accurately. The method of steam turbine speed measurement proposed in this paper can not only simplify the structure of a TDM system, but also reduce its cost.

Identification and Fault Diagnosis of an Industrial Gas Turbine Using State-Space Methods

The objective of this paper is to identify, detect and isolate faults to an industrial gas turbine. The detection scheme is based on the generation of so-called "residuals" that are errors between estimated and measured variables of the process. A State-Space model is used for identification and some observer-based methods are used for residual generation, while for residual evaluation a neural network classifier for MLP is used. The proposed fault detection and isolation tool has been tested on a single-shaft industrial gas turbine simulator.

Fault Diagnosis for Wind Turbines Based on Vibration Signal Analysis

Fault diagnosis is an important technical method to improve the safety index and economic effectiveness of wind turbines, it also provide support to advanced maintenance and design in wind power equipment. In this paper, we have done vibration testing on two wind turbines, one is in normal, the other is with faulty, and then carried on comparative analysis of vibration signal to the experimental data, finally designed a fault diagnosis method for direct-driven wind turbine generators.

A Steam Turbine Fault Diagnostic System Based on the Web and Database Technologies

The steam turbine is the principal mover in the field of electric power generation. It is very important and necessary to monitor and evaluate the running conditions and diagnose the faults of the steam turbine for the safe and normal running of the electric power plant. Fault diagnosis of the steam turbine is a complicated process and requires high level of the expertise. In order to significantly reduce the cost consumed in the fault diagnosis, increase the consistency of diagnosing decision-making, and better utilize the turbine’s management information resource, in this paper, an integrated Web-based expert system of the fault diagnosis for general purpose has been developed for the steam turbine of a power station. Moreover, it can be regarded as an advisory tool to those field engineers having much technical experience and as a training tool to less-experienced personnel who need guidance and advice. This paper describes a research project aiming to develop a web-based intelligent diagnostic system for the steam turbine, and discusses the process of the fault diagnosis and the issues involved in developing the system. The paper also includes several practical issues related to the architectures of the intelligent web-based applications. The system is built on a three-tier architecture, including the following components: knowledge base, inference engine, knowledge administration interface, user interface, knowledge administration, and integrated database. The diagnostic system employs heuristic rules to diagnose the steam turbine faults.