• Nuclear Engineering and Technology
• /
• v.55 no.2
• /
• pp.506-515
• /
• 2023

This study is to find a method to learn engine sound after the start-up of a diesel generator installed in nuclear power plant with an unsupervised deep learning algorithm (CNN autoencoder) and a new method to predict the failure of a diesel generator using it. In order to learn the sound of a diesel generator with a deep learning algorithm, sound data recorded before and after the start-up of two diesel generators was used. The sound data of 20 min and 2 h were cut into 7 s, and the split sound was converted into a spectrogram image. 1200 and 7200 spectrogram images were created from sound data of 20 min and 2 h, respectively. Using two different deep learning algorithms (CNN autoencoder and binary classification), it was investigated whether the diesel generator post-start sounds were learned as normal. It was possible to accurately determine the post-start sounds as normal and the pre-start sounds as abnormal. It was also confirmed that the deep learning algorithm could detect the virtual abnormal sounds created by mixing the unusual sounds with the post-start sounds. This study showed that the unsupervised anomaly detection algorithm has a good accuracy increased about 3% with comparing to the binary classification algorithm.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2008.04a
• /
• pp.869-873
• /
• 2008

Optimization method for the open loop commutation time intervals in HDD spindle start-up control is presented in this paper. A hard disk drive(HDD) uses a sensorless brushless DC motor(BLDC) for the platter rotation. Because there is no direct sensor for the rotor position, open loop commutations after sensing the rotor position at a standstill using inductive sensing method are performed to speed up the rotor up to a certain speed where the zero crossings of the back electromotive force(EMF) are measurable. Therefore successful open loop commutations are necessary for the stable start-up control of the spindle motors. Random neighborhood search(RNS) algorithm is introduced as a optimization technic in this paper. Rotor speed and its standard deviation are used as a cost function and commutation intervals obtained from the spindle motion equation are used as initial parameter values for the RNS. With the help of the proposed method optimized open loop commutation time intervals for the very low start-up current are acquired and tested. The experimental results shows that the proposed method can decrease the start-up failure rate of a HDD spindle motor.

• Journal of IKEEE
• /
• v.22 no.2
• /
• pp.258-265
• /
• 2018

This paper proposes an algorithm for reducing the starting current when the single-phase induction motor starts and analyzes its operation. Generally, the single-phase induction motors require several starters to generate the starting torque due to their structural characteristics. In this paper, a capacitor-start / capacitor-run method of the single-phase induction motor is basically adopted. This conventional method is efficient and has a large starting torque, but it generates about 5 ~ 6 times of inrush current at startup. As a result, the freezer starting device and peripheral devices are damaged and life time may be reduced. To reduce the inrush current, the current control algorithm based on the virtual dq model is presented to control the starting current. In addition, it validates the proposed algorithm through experiments to smooth transit from start-up operation to the rated operating region.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.35 no.12
• /
• pp.594-602
• /
• 1986

This paper proposes an effective algorithm for short-term generation scheduling for the purpose of economic and secure operation of thermal power systems. Especially, in the procedure of solution by Dynamic Programming, Linear Programming is introduced to promote the possibility of optimal solution and the security of power systems, and evaluation of security function is improved by the application of seven step approximation of normal distribution. Several necessary considerations, that is, time dependent start-up and constant down cost of generating units, demand and spinning reserve constraints, minimum up and sown time constraints, the number of possible start-up of a generating unit in a d and the number of generating units which can be started up at the same time at the same bus, are also incoporated to elevate the usability and flexibility of the algorithm. Finally, the effectiveness of the proposed algorithm has been demonstrated by applying to the 6-gen. 21-bus model power system.

• Journal of Power Electronics
• /
• v.18 no.6
• /
• pp.1720-1728
• /
• 2018

This paper proposes a novel soft starting algorithm by using PWM inverter technique to control an amplitude of the motor starting current at a single-phase induction motor (SPIM). Traditional SPIM starting methods such as a Split-Phase, Capacitor-Start, Permanent-Split Capacitor (PSC), Capacitor-Start Capacitor-Run (CSCR), basically cannot control the magnitude of starting current due to the fixed system structures. Therefore, in this paper, a soft starting algorithm based on a proportional resonant (PR) control with a variable and constant frequency is proposed to reduce the inrush current and starting up time. In addition, a transition algorithm for operation modes is devised to generate a constant voltage and constant frequency (CVCF). The validity and effectiveness of the proposed soft starting method and transition algorithm are verified through experimental results.

• Proceedings of the KIEE Conference
• /
• 2006.07b
• /
• pp.954-955
• /
• 2006

SFC(Static Frequence Converter)system has come to be used as start-up drive system for large synchronous machine in many industry applications. Many papers have been presented the control algorithm for pumped storage power generation using SFC system but they did not included about the detailed start-up algorithm of gas turbine using SFC system. This paper presents the important field weakening control algorithm of a large synchronous machine using SFC system and the results of experiment show that the proposed algorithm is proper and effective about this.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.13 no.6
• /
• pp.411-419
• /
• 2008

SFC(Static Frequence Converter)system has come to be used as start up drive system for large synchronous motor in many industry applications. Many papers have been presented the control algorithm for pumped storage power generation using SFC system but they did not included about start up algorithm of SFC system for gas turbine. This paper presents the field weakening control algorithm for a large synchronous motor using output signal of anti-windup in PI current regulator and the results of experiment show that the proposed algorithm is proper and effective.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.2
• /
• pp.133-142
• /
• 2023

The large process plant is currently implementing predictive maintenance technology to transition from the traditional Time-Based Maintenance (TBM) approach to the Condition-Based Maintenance (CBM) approach in order to improve equipment maintenance and productivity. The traditional techniques for predictive maintenance involved managing upper/lower thresholds (Set-Point) of equipment signals or identifying anomalies through control charts. Recently, with the development of techniques for big analysis, machine learning-based AAKR (Auto-Associative Kernel Regression) and deep learning-based VAE (Variation Auto-Encoder) techniques are being actively applied for predictive maintenance. However, this predictive maintenance techniques is only effective during steady-state operation of plant equipment, and it is difficult to apply them during start-up and shutdown periods when rises or falls. In addition, unlike processes such as nuclear and thermal power plants, which operate for hundreds of days after a single start-up, because the pumped power plant involves repeated start-ups and shutdowns 4-5 times a day, it is needed the prediction and alarm algorithm suitable for its characteristics. In this study, we aim to propose an approach to apply the optimal predictive alarm algorithm that is suitable for the characteristics of Pumped Storage Power Plant(PSPP) facilities to the system by analyzing the predictive maintenance techniques used in existing nuclear and coal power plants.

• Nuclear Engineering and Technology
• /
• v.55 no.6
• /
• pp.2325-2334
• /
• 2023

To study the lubrication performance of tilting-pad thrust bearing (TPTBs) during start-up in nuclear pump, a hydrodynamic lubrication model of TPTBs was established based on the computational fluid dynamics (CFD) method and the fluid-structure interaction (FSI) technique. Further, a mesh motion algorithm for the transient calculation of thrust bearings was developed based on the user defined function (UDF). The result demonstrated that minimum film thickness increases first and then decreases with the rotational speed under start-up condition. The influence of pad tilt on minimum film thickness is greater than that of collar movement at low speed, and the establishment of dynamic pressure mainly depends on pad tilt and minimum film thickness increases. As the increase of rotational speed, the influence of pad tilt was abated, where the influence of the moving of the collar dominated gradually, and minimum film thickness decreases. For TPTBs, the circumferential angle of the pad is always greater than the radial angle. When the rotational speed is constant, the change rate of radial angle is greater than that of circumferential angle with the increase of loading forces. This study can provide reference for improving bearing wear resistance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.8
• /
• pp.2796-2813
• /
• 2014

This paper presents a new algorithm called the adaptive logarithmic increase and adaptive decrease algorithm (A-LIAD), which mainly addresses the Round-Trip Time (RTT) fairness problem in satellite networks with a very high propagation delay as an alternative to the current TCP congestion control algorithm. We defined a new increasing function in the fashion of a logarithm depending on the increasing factor ${\alpha}$, which is different from the other logarithmic increase algorithm adopting a fixed value of ${\alpha}$ = 2 leading to a binary increase. In A-LIAD, the ${\alpha}$ value is derived in the RTT function through the analysis. With the modification of the increasing function applied for the congestion avoidance phase, a hybrid scheme is also presented for the slow start phase. From this hybrid scheme, we can avoid an overshooting problem during a slow start phase even without a SACK option. To verify the feasibility of the algorithm for deployment in a high-speed and long-distance network, several aspects are evaluated through an NS-2 simulation. We performed simulations for intra- and interfairness as well as utilization in different conditions of varying RTT, bandwidth, and PER. From these simulations, we showed that although A-LIAD is not the best in all aspects, it provides a competitive performance in almost all aspects, especially in the start-up and packet loss impact, and thus can be an alternative TCP congestion control algorithm for high BDP networks including a satellite network.