• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.665-667
• /
• 1999

An adaptive algorithm is presented for diagnosis of actuator faults. The concept of unknown input decoupling is combined with an adaptive observer, leading to an adaptive diagnostic observer, which has the robustness property in the presence of an unmeasurable term such as uncertainties. The observation error equation for the adaptive diagnostic observer does not depend on the effect of uncertainties and used to construct an adaptive diagnostic algorithm that provides the estimates of the gains of actuators, which can be obtained directly via the use of the augmented error technique. The simulation results indicate that the proposed algorithm is more realistic in the sense that better robustness properties can be assured without knowledge about uncertainties and is potentially useful in the development of a fault tolerant control system.

• Proceedings of the KIEE Conference
• /
• 2004.07d
• /
• pp.2182-2184
• /
• 2004

This paper presents a systematic and straightforward fault estimation approach for process fault detection. isolation and accommodation. The approach includes the design of a reduced-order observer and an algebraic-fault estimator. The observer is designed for an unknown input and fault-free system, which is obtained by coordinate transformations of original systems with unknown inputs and faults. The observer information is devoted to- the fault estimation for fault detection and isolation. The fault estimates can be used to form an additional control input to accommodate the fault. The suggested scheme is verified through simulation studies performed on the control of a vertical takeoff and landing (VTOL) aircraft in the vertical plane.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.10
• /
• pp.575-582
• /
• 2003

A new FDOs (fault diagnostic observers) and the residual generation schemes using the FDOs are suggested for the process fault detection and isolation of linear (control) systems. The design method of the FDO is described, first, for the full measurement systems. Then it is extended for the systems with unmeasurable state variables. An unknown input observer is proposed and applied for the extension. The size of the observer bank may be the smallest, specially in full measurement systems, because the order of the proposed FDO is very low. In spite of the simplicity, the scheme provides the same information for the detection and isolation of the anticipated faults as the conventional multiple observer based schemes. The residuals may be structured so that fault isolation can be performed by pre-selected logic. An FDIS using the proposed scheme is constructed for the model of the four-tank system. Simulation results show the practical feasibility of the proposed scheme.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.45 no.2
• /
• pp.175-184
• /
• 1996

In this paper the newly developed discrete-time adaptive sliding mode control method is proposed and applied to the power system stabilization problem. In contrast to the conventional continuous-time sliding mode controller, the proposed method is developed in the discrete-time domain and based on the input/output measurements instead of the continuous-time and the full-states feedback, respectively. Because the proposed control method has the adaptivity property in addition to the natural robustness property of the sliding mode control, it is possible to design the power system stabilizer which can overcome both the minor variations of the parameters of the power system and the diverse operating conditions and faults of the power system. Mathematical proof and the various computer simulations are done to verify the performance and stability of the proposed method.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.969-970
• /
• 2007

In this thesis, an algorithm of fault detection and diagnosis during operation for induction motors under the condition of various loads and rates is investigated. For this purpose, the spectrum pattern of input cutterrents was used to monitor the state of induction motors, and by clustering the spectrum pattern of input currents, the newly occurrence of spectrums pattern caused by faults were detected. For diagnosis of the fault detected, the fuzzy fault tree was designed, and the fuzzy relation equation representing the relation between an induction motor fault and each fault type, was solved. The solution of the fuzzy relation equation shows the possibility of each fault's occurring.

• The KIPS Transactions:PartC
• /
• v.19C no.3
• /
• pp.167-172
• /
• 2012

Mobile phone devices and memory card can be robbed and lost due to the carelessness that might be caused to leak personal information, and also company's confidential information can be disclosed. Therefore, the importance of user authentication to protect personal information is increasing exponentially. However, there are the limitations that criminals could easily obtain and abuse information about individuals, because the input method of personal identification number or the input method of password might not be safe for Shoulder Surfing Attack(SSA). Although various biometric identification methods were suggested to obstruct the SSA, it is the fact that they also have some faults due to the inconvenience to use in mobile environments. In this study, more complemented service for the user authentication was proposed by applying Keystroke method in the mobile environments to make up for the faults of existing biometric identification method. Lastly, the effectiveness and validity of this study were confirmed through experimental evaluations.

• Geophysics and Geophysical Exploration
• /
• v.23 no.3
• /
• pp.149-156
• /
• 2020

The genesis of ore bodies is a very diverse and complex process, and the target depth of mineral exploration increases. These create a need for predictive mineral exploration, which may be facilitated by the advancement of machine learning and geological database. In this study, we confirm that the faults and igneous rocks distributions and magnetic data can be used as input data for potential mapping using deep neural networks. When the input data are constructed with faults, igneous rocks, and magnetic data, we can build a potential mapping model of the metal deposit that has a predictive accuracy greater than 0.9. If detailed geological and geophysical data are obtained, this approach can be applied to the potential mapping on a mine scale. In addition, we confirm that the magnetic data, which provide the distribution of the underground igneous rock, can supplement the limited information from the surface igneous rock distribution. Therefore, rather than simply integrating various data sets, it will be more important to integrate information considering the geological correlation to genesis of minerals.

• Journal of Ocean Engineering and Technology
• /
• v.35 no.4
• /
• pp.287-295
• /
• 2021

This paper describes a recurrent neural network (RNN) for the fault classification of a blade pitch system of a spar-type floating wind turbine. An artificial neural network (ANN) can effectively recognize multiple faults of a system and build a training model with training data for decision-making. The ANN comprises an encoder and a decoder. The encoder uses a gated recurrent unit, which is a recurrent neural network, for dimensionality reduction of the input data. The decoder uses a multilayer perceptron (MLP) for diagnosis decision-making. To create data, we use a wind turbine simulator that enables fully coupled nonlinear time-domain numerical simulations of offshore wind turbines considering six fault types including biases and fixed outputs in pitch sensors and excessive friction, slit lock, incorrect voltage, and short circuits in actuators. The input data are time-series data collected by two sensors and two control inputs under the condition that of one fault of the six types occurs. A gated recurrent unit (GRU) that is one of the RNNs classifies the suggested faults of the blade pitch system. The performance of fault classification based on the gate recurrent unit is evaluated by a test procedure, and the results indicate that the proposed scheme works effectively. The proposed ANN shows a 1.4% improvement in its performance compared to an MLP-based approach.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.11 no.4
• /
• pp.17-22
• /
• 1974

In this paper, the problem of finding tests to detect faults in combinational logic circuits is considered. At first, the method of fault detection in fan-out-free irredundant circuits is derived, and the result is extended to the fan-out redundant circuits. A fan-out circuit is decomposed into a set of fan-out-free subcircuits by cutting the lines at the internal fan-out points, and the minimal detecting test. sets for each subcircuit are found separately. And then, the compatible tests from each test set are combined maximally into composite tests to generate primary input binary vectors. By this procedure. the minimal complete test sets for reconvergent fan-out circuits are easily found and the detectable and undetectable faults are also classified clearly.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.3
• /
• pp.151-157
• /
• 2018

Most previous studies of software fault prediction have focused on supervised learning models for binary classification that determines whether an input module has faults or not. However, binary classification model determines only the presence or absence of faults in the module without considering the complex characteristics of the fault, and supervised model has the limitation that it requires a training data set that most development groups do not have. To solve these two problems, this paper proposes severity-based ternary classification model using unsupervised learning algorithms, and experimental results show that the proposed model has comparable performance to the supervised models.