Study on Practical Application of Turboprop Engine Condition Monitoring and Fault Diagnostic System Using Fuzzy-Neuro Algorithms

2012 ◽  
Author(s):  
Changduk Kong ◽  
Semyeong Lim ◽  
Keonwoo Kim
Keyword(s):  
Neural Networks ◽  
Diagnostic System ◽  
Engine Performance ◽  
Performance Model ◽  
Performance Data ◽  
Turboprop Engine ◽  
The Neural Networks ◽  
Fault Diagnostic ◽  
Intelligent Methods ◽  
Learning Data

Recently, the expert engine diagnostic systems using the artificial intelligent methods such as Neural Networks, Fuzzy Logic and Genetic Algorithms have been studied to improve the model based engine diagnostic methods. Among them the Neural Networks is mostly used to engine fault diagnostic system due to its good learning performance, but it has a drawback due to low accuracy and long learning time to build learning data base if only use of the Neural Networks. In addition, it has a very complex structure due to finding effectively faults of single type faults and multiple type faults of gas path components. This work builds inversely a base performance model of a turboprop engine to be used for a high altitude operation UAV using measuring performance data, and proposes a fault diagnostic system using the base performance model and artificial intelligent methods such as Fuzzy and Neural Networks. Each real engine performance model, which is named as the base performance model that can simulate a new engine performance, is inversely made using its performance test data. Therefore the condition monitoring of each engine can be more precisely carried out through comparison with measuring performance data. The proposed diagnostic system identifies firstly the faulted components using Fuzzy Logic, and then quantifies faults of the identified components using Neural Networks leaned by fault learning data base obtained from the developed base performance model. In leaning the measuring performance data of the faulted components, the FFBP(Feed Forward Back Propagation) is used. In order to user’s friendly purpose, the proposed diagnostic program is coded by the GUI type using MATLAB. The proposed program is verified by application of several case studies having the arbitrary implanted engine component faults as well as real engine performance data.

Study on Fault Diagnostics of a Turboprop Engine Using Inverse Performance Model and Artificial Intelligent Methods

2011 ◽  
Author(s):  
Changduk Kong ◽  
Semyeong Lim
Keyword(s):  
Fuzzy Logic ◽  
Diagnostic System ◽  
Engine Performance ◽  
Performance Model ◽  
Performance Parameters ◽  
Artificial Intelligent ◽  
Turboprop Engine ◽  
Base Engine ◽  
Intelligent Methods ◽  
Learning Data

Recently, the health monitoring system of major gas path components of gas turbine uses mostly the model based method like the Gas Path Analysis (GPA). This method is to find quantity changes of component performance characteristic parameters such as isentropic efficiency and mass flow parameter by comparing between measured engine performance parameters such as temperatures, pressures, rotational speeds, fuel consumption, etc. and clean engine performance parameters without any engine faults which are calculated by the base engine performance model. Recently, the expert engine diagnostic systems using the artificial intelligent methods such as Neural Networks (NNs), Fuzzy Logic and Genetic Algorithms (GAs) have been studied to improve the model based method. Among them the NNs are mostly used to the engine fault diagnostic system due to its good learning performance, but it has a drawback due to low accuracy and long learning time to build learning data base if there are large amount of learning data. In addition, it has a very complex structure for finding effectively single type faults or multiple type faults of gas path components. This work builds inversely a base performance model of a turboprop engine to be used for a high altitude operation UAV using measured performance data, and proposes a fault diagnostic system using the base engine performance model and the artificial intelligent methods such as Fuzzy logic and Neural Network. The proposed diagnostic system isolates firstly the faulted components using Fuzzy Logic, then quantifies faults of the identified components using the NN leaned by fault learning data base, which are obtained from the developed base performance model. In leaning the NN, the Feed Forward Back Propagation (FFBP) method is used. Finally, it is verified through several test examples that the component faults implanted arbitrarily in the engine are well isolated and quantified by the proposed diagnostic system.

Artificial Neural Network Based Fault Diagnosis of IC Engines

2012 ◽  
Vol 518 ◽  
pp. 47-56 ◽  
Author(s):  
Jian Chen ◽  
Robert Randall ◽  
Bart Peeters ◽  
Wim Desmet ◽  
Herman Van der Auweraer
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Fault Diagnosis ◽  
Diagnostic System ◽  
The Neural Network ◽  
Detection Stage ◽  
Mechanical Faults ◽  
The Neural Networks ◽  
Ic Engines ◽  
Artificial Neural

Fault diagnosis is important to avoid unforeseen failures of IC engines, but normally requires an expert to interpret analysis results. Artificial Neural Networks are potential tools for the automated fault diagnosis of IC engines, as they can learn the patterns corresponding to various faults. Most engine faults can be classified into two categories: combustion faults and mechanical faults. Misfire is a typical combustion fault; piston slap and big end bearing knock are common mechanical faults. The automated diagnostic system proposed in this paper has three main stages, each stage including three neural networks. The first stage is the fault detection stage, where the neural networks detect whether there are faults in the engine and if so which kind. In the second stage, based on the detection results, the severity of the faults was identified. In the third stage, the neural networks localize which cylinder has a fault. The critical thing for a neural network is its input feature vector, and a previous study had indicated a number of features that should differentiate between the different faults and their location, based on advanced signal processing of the vibration signals measured for different normal and fault conditions. In this study, an advanced feature selection technology was employed to select the significant features as the inputs to networks. The input vectors were separated into two groups, one for training the network, and the other for its validation. Finally it has been demonstrated that the neural network based system can automatically differentiate and diagnose a number of engine faults, including location and severity.

scholarly journals Tax Fraud Detection through Neural Networks: An Application Using a Sample of Personal Income Taxpayers

2019 ◽  
Vol 11 (4) ◽  
pp. 86 ◽  
Author(s):  
César Pérez López ◽  
María Delgado Rodríguez ◽  
Sonia de Lucas Santos
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Income Tax ◽  
Fraud Detection ◽  
Personal Income ◽  
Personal Income Tax ◽  
Tax Returns ◽  
The Neural Networks ◽  
Tax Fraud ◽  
Efficiency Rate

The goal of the present research is to contribute to the detection of tax fraud concerning personal income tax returns (IRPF, in Spanish) filed in Spain, through the use of Machine Learning advanced predictive tools, by applying Multilayer Perceptron neural network (MLP) models. The possibilities springing from these techniques have been applied to a broad range of personal income return data supplied by the Institute of Fiscal Studies (IEF). The use of the neural networks enabled taxpayer segmentation as well as calculation of the probability concerning an individual taxpayer’s propensity to attempt to evade taxes. The results showed that the selected model has an efficiency rate of 84.3%, implying an improvement in relation to other models utilized in tax fraud detection. The proposal can be generalized to quantify an individual’s propensity to commit fraud with regards to other kinds of taxes. These models will support tax offices to help them arrive at the best decisions regarding action plans to combat tax fraud.

Neural networks trained with high-dimensional functions approximation data in high-dimensional space

2021 ◽  
pp. 1-12
Author(s):  
Jian Zheng ◽  
Jianfeng Wang ◽  
Yanping Chen ◽  
Shuping Chen ◽  
Jingjin Chen ◽  
...  
Keyword(s):  
Neural Networks ◽  
Dimensional Space ◽  
Data Distribution ◽  
High Dimensional ◽  
Sufficient Information ◽  
Sufficient Data ◽  
High Dimensional Space ◽  
Positive Effects ◽  
The Neural Networks ◽  
Using Data

Neural networks can approximate data because of owning many compact non-linear layers. In high-dimensional space, due to the curse of dimensionality, data distribution becomes sparse, causing that it is difficulty to provide sufficient information. Hence, the task becomes even harder if neural networks approximate data in high-dimensional space. To address this issue, according to the Lipschitz condition, the two deviations, i.e., the deviation of the neural networks trained using high-dimensional functions, and the deviation of high-dimensional functions approximation data, are derived. This purpose of doing this is to improve the ability of approximation high-dimensional space using neural networks. Experimental results show that the neural networks trained using high-dimensional functions outperforms that of using data in the capability of approximation data in high-dimensional space. We find that the neural networks trained using high-dimensional functions more suitable for high-dimensional space than that of using data, so that there is no need to retain sufficient data for neural networks training. Our findings suggests that in high-dimensional space, by tuning hidden layers of neural networks, this is hard to have substantial positive effects on improving precision of approximation data.

Classification and Recognition of Plant Leaf Based on Neural Networks

2011 ◽  
Vol 464 ◽  
pp. 38-42 ◽  
Author(s):  
Ping Ye ◽  
Gui Rong Weng
Keyword(s):  
Neural Networks ◽  
Fractal Dimension ◽  
Recognition Rate ◽  
Image Binarization ◽  
Characteristic Parameters ◽  
Moment Invariant ◽  
Plant Leaf ◽  
The Neural Networks ◽  
Novel Method ◽  
The Moment

This paper proposed a novel method for leaf classification and recognition. In the method, the moment invariant and fractal dimension were regarded as the characteristic parameters of the plant leaf. In order to extract the representative characteristic parameters, pretreatment of the leaf images, including RGB-gray converting, image binarization and leafstalk removing. The extracted leaf characteristic parameters were further utilized as training sets to train the neural networks. The proposed method was proved effectively to reach a recognition rate about 92% for most of the testing leaf samples

Sign in / Sign up

Export Citation Format

Share Document