• Nuclear Engineering and Technology
• /
• v.55 no.2
• /
• pp.493-505
• /
• 2023

Comprehensive condition monitoring of large industry systems such as nuclear power plants (NPPs) is essential for safety and maintenance. In this study, we developed novel system-scale diagnostic technology based on deep-learning and IR thermography that can efficiently and cost-effectively classify system conditions using compact Raspberry Pi and IR sensors. This diagnostic technology can identify the presence of an abnormality or accident in whole system, and when an accident occurs, the type of accident and the location of the abnormality can be identified in real-time. For technology development, the experiment for the thermal image measurement and performance validation of major components at each accident condition of NPPs was conducted using a thermal-hydraulic integral effect test facility with compact infrared sensor modules. These thermal images were used for training of deep-learning model, convolutional neural networks (CNN), which is effective for image processing. As a result, a proposed novel diagnostic was developed that can perform diagnosis of components, whole system and accident classification using thermal images. The optimal model was derived based on the modern CNN model and performed prompt and accurate condition monitoring of component and whole system diagnosis, and accident classification. This diagnostic technology is expected to be applied to comprehensive condition monitoring of nuclear power plants for safety.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.3
• /
• pp.242-250
• /
• 2019

In this paper, we propose a method to predict the failure of industrial robot using Seq2Seq (Sequence to Sequence) model, which is a model for transforming time series data among Artificial Neural Network models. The proposed method uses the data of the joint current and angular value, which can be measured by the robot itself, without additional sensor for fault diagnosis. After preprocessing the measured data for the model to learn, the Seq2Seq model was trained to convert the current to angle. Abnormal degree for fault diagnosis uses RMSE (Root Mean Squared Error) during unit time between predicted angle and actual angle. The performance evaluation of the proposed method was performed using the test data measured under different conditions of normal and defective condition of the robot. When the Abnormal degree exceed the threshold, it was classified as a fault, and the accuracy of the fault diagnosis was 96.67% from the experiment. The proposed method has the merit that it can perform fault prediction without additional sensor, and it has been confirmed from the experiment that high diagnostic performance and efficiency are available without requiring deep expert knowledge of the robot.

• Journal of the Korean Society of Safety
• /
• v.15 no.2
• /
• pp.1-7
• /
• 2000

This paper presents the approach involving fault detection and diagnosis of gears using pattern recognition and Wavelet transform. It describes result of the comparison between KDI (Kullback Discrimination Information) with the nearest neighbor classification rule as one of pattern recognition methods and Wavelet transform to know a way to detect and diagnosis of gear damages experimentally. To model the damages 1) Normal (no defect), 2) one tooth is worn out, 3) All teeth faces are worn out 4) One tooth is broken. The vibration sensor was attached on the bearing housing. This produced the total time history data that is 20 pieces of each condition. We chose the standard data and measure distance between standard and tested data. In Wavelet transform analysis method, the time series data of magnitude in specified frequency (rotary and mesh frequency) were earned. As a result, the monitoring system using Wavelet transform method and KDI with nearest neighbor classification rule successfully detected and classified the damages from the experimental data.

• Proceedings of the SAREK Conference
• /
• 2006.06a
• /
• pp.807-813
• /
• 2006

The objective of this study is to develop a rule-based fault detection algorithm and an experimental verification using an artificial air handling unit. To develop an analytical algorithm which precisely detects a tendency of faulty component, energy equations at each control volume of AHU were applied. An experimental verification was conducted on the HVAC simulator. The rule based FDD algorithm isolated a faulted sensor from HVAC components in summer and winter conditions.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.405-410
• /
• 2016

Elevator industry is a field that is mechanical, electrical and electronic technology and constantly requires inspection and maintenance considering various applications and various types. Recently, various elevator control and monitoring technologies with IT are developing for elevators on land. But technologies with IT have been hardly done in marine elevator that is consistently assured safety and reliability of life cycle for its parts in poor environment. In this paper, we implemented embedded main controller, floor controller and car controller that meet the requirements and use NMEA network protocol by analyzing home and abroad integrated elevator operation and management systems. Especially, we secured reliability of maintenance by real-time fault diagnosis and control that was implemented with limit switch, gyro sensor, temperature/humidity/barometric pressure sensor and fire detection sensor thinking over the environmental conditions of terrestrial and marine elevator.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.2
• /
• pp.147-152
• /
• 2016

This paper proposes a new TPC (Transmission Priority Change) algorithm which is used to diagnose failures of a CAN (Controller Area Network) based network system for the oil tank monitoring. The TPC algorithm is aimed to increase the total amount of data transmission and to minimize the latency for an urgent message by changing transmission priority. The urgency of the data transmission has been determined by the conditions of sensors. There are multiple sensors inside of the oil tank, such as temperature, valve, pressure and level sensors. When the sensors operate normally, the sensory data can be collected through the CAN network by the monitoring system. However when there is a dangerous situation or failure situation happened at a sensor, the data need to be handled quickly by the monitoring system, which is implemented by using the TPC algorithm. The effectiveness of the TPC algorithm has been verified by the real experiments. In addition, this paper introduces a method that people can figure out the condition of oil tanks and also can perform the fault diagnosis in real-time by using transmitted packet data. By applying this TPC algorithm to various industries, the convenience and reliability of multiple sensors network system can be improved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.10
• /
• pp.4883-4901
• /
• 2016

Energy efficiency in Wireless Sensor Networks (WSNs) is very appealing research area due to serious constrains on resources like storage, processing, and communication power of the sensor nodes. Due to limited capabilities of sensing nodes, such networks are composed of a large number of nodes. The higher number of nodes increases the overall performance in data collection from environment and transmission of packets among nodes. In such networks the nodes sense data and ultimately forward the information to a Base Station (BS). The main issues in WSNs revolve around energy consumption and delay in relaying of data. A lot of research work has been published in this area of achieving energy efficiency in the network. Various techniques have been proposed to divide such networks; like grid division of network, group based division, clustering, making logical layers of network, variable size clusters or groups and so on. In this paper a new technique of group based WSNs is proposed by using some features from recent published protocols i.e. "Energy-Efficient Multi-level and Distance Aware Clustering (EEMDC)" and "Energy-Efficient Multi-level and Distance Aware Clustering (EEUC)". The proposed work is not only energy-efficient but also minimizes the delay in relaying of data from the sensor nodes to BS. Simulation results show, that it outperforms LEACH protocol by 38%, EEMDC by 10% and EEUC by 13%.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.13 no.6
• /
• pp.430-438
• /
• 2008

Recently, permanent magnet synchronous motor are applied to various applications such as electric vehicle, aerospace, medical service and military applications due to several outstanding characteristics. Because of the importance of high reliable operation in these areas, many research related to the fault detection and diagnosis of inverter system are conducted. In this paper, new simple fault detection method of voltage source inverter for permanent magnet synchronous motor is proposed. The feasibility of the proposed method are improved by simulation and experiment. By the simulation and experiments, rapid detection characteristic of the proposed method has been proved without any additional voltage sensor.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.55-67
• /
• 2022

Sensor data can provide fault diagnosis for equipment. However, the cause analysis for fault results of equipment is not often provided. In this study, we propose an explainable convolutional neural network framework for the sensor-based time series classification model. We used sensor-based time series dataset, acquired from vehicles equipped with sensors, and the Wafer dataset, acquired from manufacturing process. Moreover, we used Cycle Signal dataset, acquired from real world mechanical equipment, and for Data augmentation methods, scaling and jittering were used to train our deep learning models. In addition, our proposed classification models are convolutional neural network based models, FCN, 1D-CNN, and ResNet, to compare evaluations for each model. Our experimental results show that the ResNet provides promising results in the context of time series classification with accuracy and F1 Score reaching 95%, improved by 3% compared to the previous study. Furthermore, we propose XAI methods, Class Activation Map and Layer Visualization, to interpret the experiment result. XAI methods can visualize the time series interval that shows important factors for sensor data classification.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.1 no.2
• /
• pp.49-59
• /
• 1993

A new signal processing technique is applied to four-cylinder spark and compression ignition engines for the diagnosis of power faults inside the cylinders. This technique utilizes two-sided directional power spectra(예S) of complex vibration signals measured from engine blocks as the patterns for engine cylinder power faults. The dPSs feature that they give not only the frequency contents but also the directivity of the engine block motion. For the automatic detection/diagnosis of cylinder power faults, pattern recognition method using multi-layer neural networks is employed. Experimental results show that the sucess rate for diagnosis of cylinder power faults using dPSs is higher than that using the conventional one-sided power spectra. The proposed technique is also tested to check the robustness to the sensor position and the engine rotational speed.