• Journal of the Korean Society of Propulsion Engineers
• /
• v.10 no.2
• /
• pp.15-22
• /
• 2006

An intelligent performance diagnostic program using the Neural Network was proposed for PW206C turboshaft engine. It was selected as a power plant for the tilt rotor type Smart UAV(Unmanned Aerial Vehicle) which is being developed by KARI (Korea Aerospace Research Institute). For teeming the NN(Neural Network), a BPN(Back Propagation Network) with one hidden, one input and one output layer was used. The input layer has seven neurons: variations of measurement parameters such as SHP, MF, P2, T2, P4, T4 and T5, and the output layer uses 6 neurons: degradation ratios of flow capacities and efficiencies for compressor, compressor turbine and power turbine, respectively, Database for network teaming and test was constructed using a gas turbine performance simulation program. From application of the learned networks to diagnostics of the PW206C turboshaft engine, it was confirmed that the proposed diagnostics algorithm could detect well the single fault types such as compressor fouling and compressor turbine erosion.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.1
• /
• pp.90-96
• /
• 2020

In this era, intelligence is considered a major factor in the defense sector. As a result, securing technology for weapons systems for monitoring and reconnaissance of companies has become inevitable. As a result, UAVs (Unmanned Aerial Vehicles) have been developed and are actively operating around the world if the flight operation of manned aircraft is restricted, such as in environments that are too dangerous, messy or boring for the military to perform directly. The system of unmanned aerial vehicles, which has been researched and developed in Korea, includes Air Vehicle Test Equipment(AVTE). AVTE is equipment that is connected to an UAV to check its status and allows the operator to check its flightability by issuing an operational command to the UAV and verifying that it follows the command values. This study conducts fault finding on the phenomenon where the AVTE has stopped operating due to engine noise during these operations and analyzes the cause in terms of software, hardware and external environment. Present improvement measures according to the cause are analyzed and the results of verifying that the proposed measures can prevent failure are addressed.

• Journal of the Korea Society for Simulation
• /
• v.26 no.3
• /
• pp.35-46
• /
• 2017

Spare engine plays an important role for securing readiness of military strength during unexpected fault occurrences and field/depot planned maintenances. The purpose of this research is to present an approach towards the optimal number of spare engines/modules for diversity of aircraft types. We first reviewed two representative approaches, METRIC and meta model. We then investigated military aircrafts and categorized them into 5 types with regard to the engine type and number of engines/modules per aircraft. Through rigorous investigation of planned/non-planned maintenance of each type, we drew parameters and variables involved. As known, due to the complexity of the problem, it is impossible to develop a simple mathematical model with a closed form solution. Based on the airbase operation and maintenance logic with parameters/variable drawn, we developed a simulation model using ARENA well representing real field exercises. For the optimal solution, we applied OptQuest. It has shown that the program developed generates reliable results through a set of case examples.

• Journal of the Korean Society of Safety
• /
• v.7 no.4
• /
• pp.105-114
• /
• 1992

This paper presents an study on the knowledge based system for diagnosing the fire causes using the Fuzzy Possibility Measure( FPM ) about the electric-fire ignition. The Ignition values needed for causes diagnosis is computed as FPM for electric-fire ignition based on the internal scale technique that assigns numerically the characteristic difference of facts to the-tin-ear scale. For the convinience of inference, ignition sources are classified into seven types : short, ground fault, leakge of electricity, overcurrent, cord junction overheating, bad Insulation and spark. The system for causes diagnosis of electric-fire is composed of Knowledge Acquisition System, Inference Engine and Man-Machine Interface, The diagnosis system is wrritten in an artificial intelligence langusge “PROLOG” which uses depth-first search and backward chaining schemes in reasoning process.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.6
• /
• pp.1065-1070
• /
• 2009

This paper presents the new technique of modeling using Dynamic Link Library(DLL) in ElectroMagnetic Transients Program - Restructured Version(EMTP-RV) in which we have simplified the procedures of OverCurrent Relay(OCR) modeling. The DLL function is designed to allow EMTP-RV users to develop advanced program model modules and interface them directly and intimately with the EMTP-RV engine. The modeled OCR is verified by simulating the various fault cases in the distribution system. Also, the performance for the modeling of OCR using DLL is compared with that of the method using the control components of EMTP-RV and using EMTP/MODELS. The results show the validity of modeled OCR and the effectiveness of the method using DLL function.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.2
• /
• pp.353-360
• /
• 2016

Series hybrid electric vehicles (SHEVs) having multiple power sources such as an engine- generator (EnGen), a battery, and an ultra-capacitor require a power control unit with high power density and reliable control operation. However, manufacturing using separate individual power converters has the disadvantage of low power density and requires a large number of power and signal cable wires. It is also difficult to implement the optimal power distribution and fault management algorithm because of the communication delay between the units. In order to address these concerns, this approach presents a design methodology and a power control algorithm of an integrated power converter for the SHEVs powered by multiple power sources. In this work, the design methodology of the integrated power control unit (IPCU) is firstly elaborately described, and then efficient and reliable power distribution algorithms are proposed. The design works are verified with product-level and vehicle-level performance experiments on a 10-ton SHEV.

• Proceedings of the KIEE Conference
• /
• 2003.11a
• /
• pp.239-241
• /
• 2003

The time domain simulation method of transient stability presents accuracy and reliability, but it demands much computational time. Therefore it is necessary to filter out very stable and very unstable cases from a large set of contingencies. Following a disturbance, the shape and magnitude of representative generator angle which is most increased after fault clearing are the measure of transient stability. This paper propose a method that is not a calculation of the exact CCT of contingency, but a fast assessment of transient stability. Also it can help operators identify transient stability immediately without analyzing the graphical results. The proposed method is applied to the KEPCO system. The PSS/E is used as a time domain simulation engine by IPLAN.

• Proceedings of the KIEE Conference
• /
• 2004.11b
• /
• pp.223-226
• /
• 2004

This paper describers the power demand and the voltage stability in power system. Especially the power demand on summer is more and more increase in korea. According to load quantity is increasing voltage is getting down. And power system becomes unstable. So this paper is prevent voltage down using to ULTC modeling which is a part in a transformer. Therefore our purpose is power system stability increasing as variable state like a load increasing or a fault. Then this paper is using IPLAN and PSS/E as analysis tool. PSS/E is very powerful engine on load flow analysis. And IPLAN is capable of using on variable program compiling with user.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.2
• /
• pp.19-28
• /
• 2019

The purpose of this study is to examine the trends on machine learning and deep learning research in the published journals from the Web of Science Database. To achieve the study purpose, we used the abstracts of 20,664 articles published between 1990 and 2017, which include the word 'machine learning', 'deep learning', and 'artificial neural network' in their titles. Twenty major research topics were identified from topic modeling analysis and they were inclusive of classification accuracy, machine learning, optimization problem, time series model, temperature flow, engine variable, neuron layer, spectrum sample, image feature, strength property, extreme machine learning, control system, energy power, cancer patient, descriptor compound, fault diagnosis, soil map, concentration removal, protein gene, and job problem. The analysis of the time-series linear regression showed that all identified topics in machine learning research were 'hot' ones.

• The Journal of Bigdata
• /
• v.7 no.1
• /
• pp.125-137
• /
• 2022

The transportation industry is one of the important industries due to the geographical requirements surrounded by the sea on three sides of Korea and the problem of resource poverty, which relies on imports for most of its resource consumption. Among them, the proportion of the shipping industry is large enough to account for most of the transportation industry, and maintenance in the shipping industry is also important in improving the operational efficiency and reducing costs of ships. However, currently, inspections are conducted every certain period of time for maintenance of ships, resulting in time and cost, and the cause is not properly identified. Therefore, in this study, the proposed methodology, LSTM-AutoEncoder, is used to detect abnormalities that may cause ship failure by considering the time of actual ship operation data. In addition, clustering is performed through clustering, and the potential causes of ship main engine failure are identified by grouping outlier by factor. This enables faster monitoring of various information on the ship and identifies the degree of abnormality. In addition, the current ship's fault monitoring system will be equipped with a concrete alarm point setting and a fault diagnosis system, and it will be able to help find the maintenance time.