• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.1
• /
• pp.151-160
• /
• 2024

Artificial Neural Networks that enabled Artificial Intelligence are being used in many fields. However, the application to mechanical structures has several problems and research is incomplete. One of the problems is that it is difficult to secure a large amount of data necessary for learning Artificial Neural Networks. In particular, it is important to detect and recognize external forces and forces for safety working and accident prevention of mechanical structures. This study examined the possibility by applying the Current Neural Network of Artificial Neural Networks to detect and recognize the load on the machine. Tens of thousands of data are required for general learning of Recurrent Neural Networks, and to secure large amounts of data, this paper derives load data from ANSYS structural analysis results and applies a stacked auto-encoder technique to secure the amount of data that can be learned. The usefulness of Stacked Auto-Encoder data was examined by comparing Stacked Auto-Encoder data and ANSYS data. In addition, in order to improve the accuracy of detection and recognition of load data with a Recurrent Neural Network, the optimal conditions are proposed by investigating the effects of related functions.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.20 no.10
• /
• pp.669-678
• /
• 2008

When operating a complex facility, Fault Detection and Diagnosis (FDD) system is beneficial in equipment management by providing the operator with tools which can help find out a failure of the system. In this research, FDD algorithm was developed using the general pattern classifier method that can be applied to centrifugal chiller system. The simulation model for a centrifugal chiller system was developed in order to obtain characteristic data of turbo chiller system under normal and faulty operation. We tested FDD algorithm of a centrifugal chiller using data from simulation model at full load performance and 60% part load performance. In this research, we presented fault detection method using a normalized distance. Sensitivity analysis of fault detection was carried out with respect to fault progress. FDD algorithm developed in this study was found to indicate each failure modes accurately.

• Proceedings of the KIEE Conference
• /
• 2007.04b
• /
• pp.107-109
• /
• 2007

From composition transmitter is detached in indicator to individual load direction of 2 channels and adding up display by digital load cell indicator indication method of Bluetooth method is identifying marks.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.117-119
• /
• 2006

In this work, we suggest another method to localize DFT in spatial domain. This enables DFT algorithm to be used for local pattern matching. Once calculated, it costs same load to calculate localized DFT regardless of the size or the position of local region In spatial domain. We applied this method to face detection problem and got the results which prove the utility of our method.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2008.05a
• /
• pp.133-135
• /
• 2008

In a design of ballast for discharge lamp, various kind of protection circuit are essential for safe operation. In this paper, overvoltage and current detection, no-load detection, lamp-fault detection, end of lamp detection for protection are introduced. Individual circuit operation and their function are described with the base that all circuit form is similar with overvoltage protection circuit.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.8
• /
• pp.1515-1522
• /
• 2011

This paper proposes the algorithm for the output AC voltage control of Z-source inverter by the detection of the input DC voltage and Z-network capacitor voltage. The actual modulation index of the proposed method is detected by the capacitor voltage in Z-network and input DC voltage of three-phase Z-source inverter. Control modulation index for the output voltage control is calculated by the detected actual modulation index and reference modulation index. And, calculated control modulation index is applied to the modified space vector modulation (SVM) for control the output voltage of Z-source inverter. To verify the validity of the proposed method, PSIM simulation was achieved and a DSP controlled 1[kW] three-phase Z-source inverter was producted. The simulation and experiment were performed under the condition that the load was changed in case of the constant input DC voltage and the input DC voltage was changed in case of the load was constant. As a result, we could know that the output phase voltage of Z-source inverter followed to the reference voltage 70[VRMS] despite the load or the input DC voltage were suddenly changed.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.8
• /
• pp.1085-1091
• /
• 2014

A model based SOC estimation scheme using parameter identification is described and applied to a Lithium-ion battery module that can be installed in electric vehicles. Simulation studies are performed to verify the effect of sensor faults on the SOC estimation results for terminal voltage sensor and load current sensor. The sensor faults should be detected and isolated as soon as possible because the SOC estimation error due to any sensor fault seriously affects the overall performance of the BMS. A new fault detection and isolation(FDI) scheme by which the fault of terminal voltage sensor and load current sensor can be detected and isolated is proposed to improve the reliability of the BMS. The proposed FDI scheme utilizes the parameter estimation of an input-output model and two fuzzy predictors for residual generation; one for terminal voltage and the other for load current. Recently developed dual polarization(DP) model is taken to develope and evaluate the performance of the proposed FDI scheme. Simulation results show the practical feasibility of the proposed FDI scheme.

• Journal of Communications and Networks
• /
• v.8 no.1
• /
• pp.93-105
• /
• 2006

The domination of the Internet by TCP-based services has spawned many efforts to provide high network utilization with low loss and delay in a simple and scalable manner. Active queue management (AQM) algorithms attempt to achieve these goals by regulating queues at bottleneck links to provide useful feedback to TCP sources. While many AQM algorithms have been proposed, most suffer from instability, require careful configuration of nonintuitive control parameters, or are not practical because of slow response to dynamic traffic changes. In this paper, we propose a new AQM algorithm, hybrid random early detection (HRED), that combines the more effective elements of recent algorithms with a random early detection (RED) core. HRED maps instantaneous queue length to a drop probability, automatically adjusting the slope and intercept of the mapping function to account for changes in traffic load and to keep queue length within the desired operating range. We demonstrate that straightforward selection of HRED parameters results in stable operation under steady load and rapid adaptation to changes in load. Simulation and implementation tests confirm this stability, and indicate that overall performances of HRED are substantially better than those of earlier AQM algorithms. Finally, HRED control parameters provide several intuitive approaches to trading between required memory, queue stability, and response time.

• Journal of Korean Society on Water Environment
• /
• v.32 no.6
• /
• pp.649-669
• /
• 2016

This study explored the analytical conditions for 21 veterinary antibiotics which have been popularly sold in South Korea in 2014 but have not yet been targeted in EPA method 1694. Most of the selected antibiotics were separated by a reverse-phase C18 column with a combination of (buffered) water and organic polar solvent, which was commonly methanol and acetonitrile in the gradient elution mode. Volatile additives such as formic acid, ammonium acetate and ammonium formate were usually added to the mobile phases to minimize asymmetrical and tailing of antibiotics' peaks and to increase their ionization in mass spectrometry. The analytical methods of aminoglycoside antibiotics were distinct from those of the other antibiotics in terms of adoption of ion-pair chromatography (IPC) and hydrophilic interaction liquid chromatography (HILIC) capable of retaining and separating extremely polar compounds due to their hydrophilicity. Trifluoroacetic acid or heptafluorobutyric acid was frequently added to the mobile phase as an ion-pair reagent for the IPC. Tandem mass spectrometry was numerously applied to the detection of antibiotics using positive electrospray ionization (ESI) and the selected reaction monitoring (SRM) mode. All reviewed analytical methods had been/were validated by evaluating recovery, limits of detection and quantification, decision limit or detection capability of the methods.

• Journal of the Korean Society for Railway
• /
• v.11 no.5
• /
• pp.477-481
• /
• 2008

This paper dealt with a detection method of series arc existence which is a symptom of electric fires in low-voltage system. The proposed detection circuit consists of a high-pass filter with a low cut-off frequency of 3kHz to attenuate power frequency voltage by 80 dB and an active band-pass filter with a center frequency of 4kHz to detect only the series arc signals. The performance of the circuit was evaluated in a phase-controlled incandescent lamp as a non-linear load and an inverted-fed induction motor as a high frequency load by using the arc generator specified in UL1699. From the experimental results, it was confirmed that the proposed method solved the detection error, which is being the most problem, by discriminating the series arc signal even in non-linear and high frequency loads.