• Journal of Information Processing Systems
• /
• v.16 no.4
• /
• pp.870-881
• /
• 2020

Because SCADA monitoring data of wind turbines are large and fast changing, the unbalanced proportion of data in various working conditions makes it difficult to process fault feature data. The existing methods mainly introduce new and non-repeating instances by interpolating adjacent minority samples. In order to overcome the shortcomings of these methods which does not consider boundary conditions in balancing data, an improved over-sampling balancing algorithm SC-SMOTE (safe circle synthetic minority oversampling technology) is proposed to optimize data sets. Then, for the balanced data sets, a fault diagnosis method based on improved k-nearest neighbors (kNN) classification for wind turbine blade icing is adopted. Compared with the SMOTE algorithm, the experimental results show that the method is effective in the diagnosis of fan blade icing fault and improves the accuracy of diagnosis.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.242-252
• /
• 2021

Following the intuition that the local information in time instances is hardly incorporated into the posterior sequence in long short-term memory (LSTM), this paper proposes an attention augmented mechanism for fault diagnosis of the complex chemical process data. Unlike conventional fault diagnosis and classification methods, an attention mechanism layer architecture is introduced to detect and focus on local temporal information. The augmented deep network results preserve each local instance's importance and contribution and allow the interpretable feature representation and classification simultaneously. The comprehensive comparative analyses demonstrate that the developed model has a high-quality fault classification rate of 95.49%, on average. The results are comparable to those obtained using various other techniques for the Tennessee Eastman benchmark process.

• Tunnel and Underground Space
• /
• v.30 no.4
• /
• pp.320-334
• /
• 2020

This study presents an application of hydro-mechanical coupled Particle Flow Code 3D (PFC3D) to simulation of fluid injection induced fault slip experiment conducted in Mont Terri Switzerland as a part of a task in an international research project DECOVALEX-2019. We also aimed as identifying the current limitations of the modelling method and issues for further development. A fluid flow algorithm was developed and implemented in a 3D pore-pipe network model in a 3D bonded particle assembly using PFC3D v5, and was applied to Mont Terri Step 2 minor fault activation experiment. The simulated results showed that the injected fluid migrates through the permeable fault zone and induces fault deformation, demonstrating a full hydro-mechanical coupled behavior. The simulated results were, however, partially matching with the field measurement. The simulated pressure build-up at the monitoring location showed linear and progressive increase, whereas the field measurement showed an abrupt increase associated with the fault slip We conclude that such difference between the modelling and the field test is due to the structure of the fault in the model which was represented as a combination of damage zone and core fractures. The modelled fault is likely larger in size than the real fault in Mont Terri site. Therefore, the modelled fault allows several path ways of fluid flow from the injection location to the pressure monitoring location, leading to smooth pressure build-up at the monitoring location while the injection pressure increases, and an early start of pressure decay even before the injection pressure reaches the maximum. We also conclude that the clay filling in the real fault could have acted as a fluid barrier which may have resulted in formation of fluid over-pressurization locally in the fault. Unlike the pressure result, the simulated fault deformations were matching with the field measurements. A better way of modelling a heterogeneous clay-filled fault structure with a narrow zone should be studied further to improve the applicability of the modelling method to fluid injection induced fault activation.

• Nuclear Engineering and Technology
• /
• v.44 no.4
• /
• pp.421-428
• /
• 2012

Analog instrument and control systems in nuclear power plants have recently been replaced with digital systems for safer and more efficient operation. Digital instrument and control systems have adopted various fault-tolerant techniques that help the system correctly and safely perform the specific required functions regardless of the presence of faults. Each fault-tolerant technique has a different inspection period, from real-time monitoring to monthly testing. The range covered by each faulttolerant technique is also different. The digital instrument and control system, therefore, adopts multiple barriers consisting of various fault-tolerant techniques to increase the total fault detection coverage. Even though these fault-tolerant techniques are adopted to ensure and improve the safety of a system, their effects on the system safety have not yet been properly considered in most probabilistic safety analysis models. Therefore, it is necessary to develop an evaluation method that can describe these features of digital instrument and control systems. Several issues must be considered in the fault coverage estimation of a digital instrument and control system, and two of these are addressed in this work. The first is to quantify the fault coverage of each fault-tolerant technique implemented in the system, and the second is to exclude the duplicated effect of fault-tolerant techniques implemented simultaneously at each level of the system's hierarchy, as a fault occurring in a system might be detected by one or more fault-tolerant techniques. For this work, a fault injection experiment was used to obtain the exact relations between faults and multiple barriers of faulttolerant techniques. This experiment was applied to a bistable processor of a reactor protection system.

• International Journal of Control, Automation, and Systems
• /
• v.5 no.4
• /
• pp.410-418
• /
• 2007

For the purpose of fault detection of the primary control surface, real-time estimation of the longitudinal stability and control derivatives of the DURUMI-II using the flight data is considered in this paper. The DURUM-II, a research UAV developed by KARI, is designed to have split control surfaces for the redundancy and to guarantee safety during the fault mode flight test. For fault mode analysis, the right elevator was deliberately fixed to the specified deflection condition. This study also mentions how to implement the multi-step control input efficiently, and how to switch between the normal mode and the fault mode during the flight test. As a realtime parameter estimation technique, Fourier transform regression method was used and the estimated data was compared with the results of the analytical method and the other available method. The aerodynamic derivatives estimated from the normal mode flight data and the fault mode data are compared and the possibility to detect the elevator fault by monitoring the control derivative estimated in real time by the computer onboard was discussed.

• Nuclear Engineering and Technology
• /
• v.50 no.4
• /
• pp.599-605
• /
• 2018

Fault diagnosis depends critically on the selection of sensors monitoring crucial process variables. Boolean network (BN) is composed of nodes and directed edges, where the node state is quantized to the Boolean values of True or False and is determined by the logical functions of the network parameters and the states of other nodes with edges directed to this node. Since BN can describe the fault propagation in a sensor network, it can be applied to propose sensor selection strategy for fault diagnosis. In this article, a sufficient condition for parameter identifiability of BN is first proposed, based on which the sufficient condition for fault identifiability of a sensor network is given. Then, the fault identifiability condition induces a sensor selection strategy for sensor selection. Finally, the theoretical result is applied to the fault diagnosis-oriented sensor selection for a nuclear heating reactor plant, and both the numerical computation and simulation results verify the feasibility of the newly built BN-based sensor selection strategy.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2012.10a
• /
• pp.388-393
• /
• 2012

Vibration condition monitoring at low rotational speeds is still a challenge. Acoustic emission (AE) is the most used technique when dealing with low speed bearings. At low rotational speeds, the energy induced from surface contact between raceway and rolling elements is very weak and sometimes buried by interference frequencies. This kind of issue is difficult to solve using vibration monitoring. Therefore some researchers utilize artificial damage on inner race or outer race to simplify the case. This paper presents vibration signal analysis of low speed slewing bearings running at a low rotational speed of 15 rpm. The natural damage data from industrial practice is used. The fault frequencies of bearings are difficult to identify using a power spectrum. Therefore the relatively improved method of empirical mode decomposition (EMD), ensemble EMD (EEMD) is employed. The result is can detect the fault frequencies when the FFT fail to do it.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.1
• /
• pp.1-10
• /
• 2018

Wide-area monitoring of tree-related high impedance fault (THIF) efficiently contributes to increase reliability of large-scaled network, since the failure to early location of them may results in critical lines tripping and consequently large blackouts. In the first place, this wide-area monitoring of THIF requires managing the placement of sensors across large power grid network according to THIF detection objective. For this purpose, current paper presents a framework in which sensors are distributed according to a predetermined risk map. The proposed risk map determines the possibility of THIF occurrence on every branch in a power network, based on electrical conductivity of trees and their positions to power lines which extracted from spectral data. The obtained possibility value can be considered as a weight coefficient assigned to each branch in sensor placement problem. The next step after sensors deployment is to on-line monitor based on moving data window. In this on-line process, the received data window is evaluated for obtaining a correlation between low frequency and high frequency components of signal. If obtained correlation follows a specified pattern, received signal is considered as a THIF. Thereafter, if several faulted section candidates are found by deployed sensors, the most likely location is chosen from the list of candidates based on predetermined THIF risk map.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.49 no.9
• /
• pp.512-519
• /
• 2000

A Neural networks has been used for a expert system and fault diagnosis system. It is possible to nonlinear function mapping and parallel processing. Therefore It has been developing for a Diagnosis system of nuclear plower plant. In general Neural Networks is a static mapping but Dynamic Neural Network(DNN) is dynamic mapping.쪼두 a fault occur in system a state of system is changed with transient state. Because of a previous state signal is considered as a information DNN is better suited for diagnosis systems than static neural network. But a DNN has many weights so a real time implementation of diagnosis system is in need of a rapid network architecture. This paper presents a algorithm for RCP monitoring Alarm diagnosis system using Self Dynamic Neural Network(SDNN). SDNN has considerably fewer weights than a general DNN. Since there is no interlink among the hidden layer. The effectiveness of Alarm diagnosis system using the proposed algorithm is demonstrated by applying to RCP monitoring in Nuclear power plant.

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.1
• /
• pp.123-133
• /
• 1998

In this paper, an algorithm of fault detection and diagnosis during operation of induction motors under the condition of various loads and rates is investigated. For this purpose, the spectrum pattern of input currents is used in monitoring the state of induction motors, and by clustering the spectrum pattern of input currents, the newly occurrence of spectrum patterns caused by faults are detected. For the diagnosis of the fault detected, a fuzzy fault tree is designed, and the fuzzy relation equation representing the relation between an induction motor fault and each fault type, is solved. The solution of the fuzzy relation equation shows the possibility of occurence of each fault. The results obtained are summarized as follows : (1) Using clustering algorithm by unsupervised learning, an on-line fault detection method unaffected by the characteristics of loads and rates is implemented, and the degree of dependency for experts during fault detection is reduced. (2) With the fuzzy fault tree, the fault diagnosis process become systematic and expandable to the whole system, and the diagnosis for sub-systems can be made as an object-oriented module.