• Journal of the Korean Society of Safety
• /
• v.33 no.2
• /
• pp.21-27
• /
• 2018

The expansion and stable operation of electric power facilities are important factors with development of industrial facilities in modern society. In high-voltage equipment such as GIS, the insulation characteristics may be deterioated by environment-friendly gas adaption and miniaturization. There is also the possibility of accidents due to insulation breakdown due to the deterioration of power facilities. Therefore, it is necessary to extend the diagnosis system to continuously monitor the danger signals of these power equipment and to prevent accidents. Most of the internal defects in the GIS system are conductive particles, floating electrode defects, protrusion defects, and the like. In this case, a partial discharge phenomenon is accompanied. These partial discharge signals occur irregularly and various noise signals are included in the field, so it is difficult to evaluate the reliability in the development of the diagnostic system. In this paper, a study was made on equipment capable of generating a partial discharge simulated signal that can be adjusted in size and frequency to be applied to a diagnostic device by electromagnetic wave detection method. The PD simulated pulse generator consists of a user interface module, a high-voltage charging module, a pulse forming circuit, a voltage sensor and an embedded controller. In order to simulate the partial discharge phenomenon similar to the actual GIS, a discharge cell was designed and fabricated. The application of the prototype pulse generator to the commercialized PD diagnosis module confirmed that it can be used to evaluate the performance of the diagnostic device. It can be used for the development of GIS diagnosis system and performance verification for reliability evaluation.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.10
• /
• pp.445-454
• /
• 2023

Recently, various fault diagnosis studies are being conducted utilizing data from collaborative robots. Existing studies performing fault diagnosis on collaborative robots use static data collected based on the assumed operation of predefined devices. Therefore, the fault diagnosis model has a limitation of increasing dependency on the learned data patterns. Additionally, there is a limitation in that a diagnosis reflecting the characteristics of collaborative robots operating with multiple joints could not be conducted due to experiments using a single motor. This paper proposes an LSTM diagnostic model that can overcome these two limitations. The proposed method selects representative normal patterns using the correlation analysis of vibration and current data in single-axis and multi-axis work environments, and generates residual patterns through differences from the normal representative patterns. An LSTM model that can perform gear wear diagnosis for each axis is created using the generated residual patterns as inputs. This fault diagnosis model can not only reduce the dependence on the model's learning data patterns through representative patterns for each operation, but also diagnose faults occurring during multi-axis operation. Finally, reflecting both internal and external data characteristics, the fault diagnosis performance was improved, showing a high diagnostic performance of 98.57%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.11C
• /
• pp.1044-1051
• /
• 2006

System level diagnosis algorithms use the properties of t-diagnosable system where the maximum number of the faults does not exceed 1. The existing diagnosis algorithms have limit when dealing with large fault sets in large multiprocessor systems. Somani and Peleg proposed t/k-diagnosable system to diagnose more faults than t by allowing upper bounded few number of units to be diagnosed incorrectly. In this paper, we propose adaptive hypercube diagnosis algorithm using t/k-diagnosable system. When the number of faults exceeds t, we allow k faults to be diagnosed incorrectly. Simulation shows that the performance of the proposed algorithm is better than Feng's HADA algorithm. We propose new algorithm to reduce test rounds by analyzing the syndrome of RGC-ring obtained in the first step of HADA/IHADA method. The proposed algorithm also gives similar performance compared to HYP-DIAG algorithm.

• KEPCO Journal on Electric Power and Energy
• /
• v.7 no.2
• /
• pp.323-328
• /
• 2021

Diagnostic models are required. Data augmentation is one of the best ways to improve deep learning performance. Traditional augmentation techniques that modify image brightness or spatial information are difficult to achieve great results. To overcome this, a generative adversarial network (GAN) technology that generates virtual data to increase deep learning performance has emerged. GAN can create realistic-looking fake images by competitive learning two networks, a generator that creates fakes and a discriminator that determines whether images are real or fake made by the generator. GAN is being used in computer vision, IT solutions, and medical imaging fields. It is essential to secure additional learning data to advance deep learning-based fault diagnosis solutions in the power industry where facilities are strictly maintained more than other industries. In this paper, we propose a method for generating power facility images using GAN and a strategy for improving performance when only used a small amount of data. Finally, we analyze the performance of the augmented image to see if it could be utilized for the deep learning-based diagnosis system or not.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.20 no.11
• /
• pp.1009-1017
• /
• 2010

As rotating machines play an important role in industrial applications such as aeronautical, naval and automotive industries, many researchers have developed various condition monitoring system and fault diagnosis system by applying various techniques such as signal processing and pattern recognition. Recently, fault diagnosis systems using artificial neural network have been proposed. For effective fault diagnosis, this paper used MLP(multi-layer perceptron) network which is widely used in pattern classification. Since using obtained signals without preprocessing as inputs of neural network can decrease performance of fault classification, it is very important to extract significant features of captured signals and to apply suitable features into diagnosis system according to the kinds of obtained signals. Therefore, this paper proposes the decision method of the proper feature vectors about each fault signal for neural-network-based fault diagnosis system. We applied LPC coefficients, maximum magnitudes of each spectral section in FFT and RMS(root mean square) and variance of wavelet coefficients as feature vectors and selected appropriate feature vectors as comparing error ratios of fault diagnosis for sound, vibration and current fault signals. From experiment results, LPC coefficients and maximum magnitudes of each spectral section showed 100 % diagnosis ratios for each fault and the method using wavelet coefficients had noise-robust characteristic.

• Journal of Radiation Protection and Research
• /
• v.28 no.4
• /
• pp.263-270
• /
• 2003

Monte Carlo simulation has been peformed to induce optimized parameters of the detector head of gamma camera for the diagnosis of breast cancer and to evaluate it under the diagnosis condition of the breast cancer. For the simulation, we used Tungsten collimator, having a lattice structured array with holes of $3mm{\times}3mm$ and septal thickness of 0.25 mm, which are corresponding to the pixellated photosensor. For driving optimum parameters we used Trade-Offs procedure between the geometric efficiency and the spatial resolution, varying the detector head components. In order to pre-evaluate the performance of the optimized detector head, we assumed diagnosis condition that the breast tumor is located in the middle of phantom with various sizes and its location is 25 mm from the collimator surface, considering background count caused by radiation sources from other organs. It was shown that the performance of the optimized detector head can be degraded according to the breast cancer size and the background count under real diagnosis conditions of breast cancer. Therefore, it is concluded that the spatial resolution, which is used as an indicator to distinguish the various sizes of breast cancer and is dependent on the characteristic of the detector head, appears to be meaningless in early diagnosis of the breast cancer.

• Korean Journal of Radiology
• /
• v.22 no.4
• /
• pp.612-623
• /
• 2021

Objective: To evaluate the diagnostic performance of a deep learning algorithm for the automated detection of developmental dysplasia of the hip (DDH) on anteroposterior (AP) radiographs. Materials and Methods: Of 2601 hip AP radiographs, 5076 cropped unilateral hip joint images were used to construct a dataset that was further divided into training (80%), validation (10%), or test sets (10%). Three radiologists were asked to label the hip images as normal or DDH. To investigate the diagnostic performance of the deep learning algorithm, we calculated the receiver operating characteristics (ROC), precision-recall curve (PRC) plots, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) and compared them with the performance of radiologists with different levels of experience. Results: The area under the ROC plot generated by the deep learning algorithm and radiologists was 0.988 and 0.988-0.919, respectively. The area under the PRC plot generated by the deep learning algorithm and radiologists was 0.973 and 0.618-0.958, respectively. The sensitivity, specificity, PPV, and NPV of the proposed deep learning algorithm were 98.0, 98.1, 84.5, and 99.8%, respectively. There was no significant difference in the diagnosis of DDH by the algorithm and the radiologist with experience in pediatric radiology (p = 0.180). However, the proposed model showed higher sensitivity, specificity, and PPV, compared to the radiologist without experience in pediatric radiology (p < 0.001). Conclusion: The proposed deep learning algorithm provided an accurate diagnosis of DDH on hip radiographs, which was comparable to the diagnosis by an experienced radiologist.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.3
• /
• pp.151-158
• /
• 2024

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2927-2941
• /
• 2022

The primary task of machine fault diagnosis is to judge whether the current state is normal or damaged, so it is a typical binary classification problem with mutual exclusion. Mutually exclusive events and out-of-domain detection have one thing in common: there are two types of data and no intersection. We proposed a fusion model method to improve the accuracy of machine fault diagnosis, which is based on the mutual exclusivity of events and the commonality of out-of-distribution detection, and finally generalized to all binary classification problems. It is reported that the performance of a convolutional neural network (CNN) will decrease as the recognition type increases, so the variational auto-encoder (VAE) is used as the primary model. Two VAE models are used to train the machine's normal and fault sound data. Two reconstruction probabilities will be obtained during the test. The smaller value is transformed into a correction value of another value according to the mutually exclusive characteristics. Finally, the classification result is obtained according to the fusion algorithm. Filtering normal data features from fault data features is proposed, which shields the interference and makes the fault features more prominent. We confirm that good performance improvements have been achieved in the machine fault detection data set, and the results are better than most mainstream models.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2017.05a
• /
• pp.218-223
• /
• 2017

This paper deals with a fault diagnosis algorithm using the Kalman filter for a 75-ton Liquid Propellant Rocket Engine (LPRE). To design the Kalman filter, we linearized a non-linear simulation model of a 75-ton LPRE at an operating point, and checked the performance of the Kalman filter by comparing the measured values with estimated values of the states. Then, we artificially injected a fault of the turbopump efficiency into the simulation to confirm the performance of the fault diagnosis algorithm with the developed Kalman filter by comparing the variation of the residuals of the normal state with that of the fault cases.