• International Journal of Fluid Machinery and Systems
• /
• 제2권1호
• /
• pp.61-71
• /
• 2009

Machine fault diagnostic and prognostic techniques have been the considerable subjects of condition-based maintenance system in the recent time due to the potential advantages that could be gained from reducing downtime, decreasing maintenance costs, and increasing machine availability. For the past few years, research on machine fault diagnosis and prognosis has been developing rapidly. These publications covered in the wide range of statistical approaches to model-based approaches. With the aim of synthesizing and providing the information of these researches for researcher's community, this paper attempts to summarize and classify the recent published techniques in diagnosis and prognosis of rotating machinery. Furthermore, it also discusses the opportunities as well as the challenges for conducting advance research in the field of machine prognosis.

• 대한임베디드공학회논문지
• /
• 제14권6호
• /
• pp.287-294
• /
• 2019

With the automation of production lines in the manufacturing industry, the importance of real-time fault diagnosis of facility is increasing. In this paper, we propose a fault diagnosis algorithm of LM (Linear Motion)-guide based on deep learning using vibration signals. Generally, in order to guarantee the performance of the deep learning, it is necessary to have a sufficient amount of data, but in a manufacturing industry, it is often difficult to obtain enough data due to physical and time constraints. To solve this problem, we propose a convolutional neural networks (CNN) model based on transfer learning. In addition, the spectrogram image is input to the CNN to reflect the frequency characteristic of the vibration signals with time. The performance of fault diagnosis according to various load condition and transfer learning method was compared and evaluated by experiments. The results showed that the proposed algorithm exhibited an excellent performance.

• Journal of Mechanical Science and Technology
• /
• 제19권5호
• /
• pp.1095-1106
• /
• 2005

Recently, the conventional controller of machine-tool has been increasingly replaced by the PC-based open architecture controller, which is independent of the CNC vendor and on which it is possible to implement user-defined application programs. This paper proposes CNC­implemented fault diagnosis and web-based remote services for machine-tool with open architecture CNC. The faults of CNC machine-tool are defined as the operational faults occupied by over $70{\%}$ of all faults. The operational faults are unpredictable as they occur without any warning. Two diagnostic models, the switching function and the step switching function, were proposed in order to diagnose faults efficiently. The faults were automatically diagnosed through the fault diagnosis system using the two diagnostic models. A suitable interface environment between CNC and developed application modules was constructed for the internal function of CNC. In addition, a suitable web environment was constructed for remote services. The web service functions, such as remote monitoring and remote control, were implemented, and their operability was tested through the web. The results obtained through this research could be a model of fault diagnosis and remote servicing for machine-tool with open architecture CNC.

• 마이크로전자및패키징학회지
• /
• 제31권2호
• /
• pp.45-53
• /
• 2024

The maintenance of semiconductor equipment is crucial for the continuous growth of the semiconductor market. System management is imperative given the anticipated increase in the capacity and complexity of industrial equipment. Ensuring optimal operation of manufacturing processes is essential to maintaining a steady supply of numerous parts. Particularly, monitoring the status of substrate transfer robots, which play a central role in these processes, is crucial. Diagnosing failures of their major components is vital for preventive maintenance. Fault diagnosis methods can be broadly categorized into physics-based and data-driven approaches. This study focuses on data-driven fault diagnosis methods due to the limitations of physics-based approaches. We propose a methodology for data acquisition and preprocessing for robot fault diagnosis. Data is gathered from vibration sensors, and the data preprocessing method is applied to the vibration signals. Subsequently, the dataset is trained using Gradient Tree-based XGBoost machine learning classification algorithms. The effectiveness of the proposed model is validated through performance evaluation metrics, including accuracy, F1 score, and confusion matrix. The XGBoost classifiers achieve an accuracy of approximately 92.76% and an equivalent F1 score. ROC curves indicate exceptional performance in class discrimination, with 100% discrimination for the normal class and 98% discrimination for abnormal classes.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.131-134
• /
• 1990

A back-propagation neural network based system for a fault diagnosis of a chemical process is developed. Training data are acquired from FCD(Fault-Consequence Digraph) model. To improve the resolution of a diagnosis, the system is decomposed into 6 subsystems and the training data are composed of 0, 1 and intermediate values. The feasibility of this approach is tested through case studies in a real plant, a naphtha furnace, which has been used to develop a knowledge based expert system, OASYS (Operation Aiding expert SYStem).

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 2001년도 The Seoul International Simulation Conference
• /
• pp.301-305
• /
• 2001

A novel approach based on parameters estimation is presented far fault detection and diagnosis in sensors. Based on known precise parameter of normal working sensors system model is built from real laboratory inputs-outputs data, sequentially residual serial is obtained. Where decision-making rule of detection the fault is given via the use of beys theory, whilst a filter least-square computative algorithm for estimating fault parameters is given. The algorithm is a fast and accurate to calculate value of sensors faults when system model contains noise and sensors outputs contain measured noise. The method can solve both gain type and bias type fault in sensors. Simulated numerical example is included to demonstrate the use of the proposed approaches.

• Journal of Electrical Engineering and Technology
• /
• 제12권2호
• /
• pp.886-889
• /
• 2017

An active Fault Tolerant Model Predictive Control (FTMPC) using Fuzzy scheduler is developed. Fault tolerant Control (FTC) system stages are broadly classified into two namely Fault Detection and Isolation (FDI) and fault accommodation. Basically, the faults are identified by means of state estimation techniques. Then using the decision based approach it is isolated. This is usually performed using soft computing techniques. Fuzzy Decision Making (FDM) system classifies the faults. After identification and classification of the faults, the model is selected by using the information obtained from FDI. Then this model is fed into FTC in the form of MPC scheme by Takagi-Sugeno Fuzzy scheduler. The Fault tolerance is performed by switching the appropriate model for each identified faults. Thus by incorporating the fuzzy scheduled based FTC it becomes more efficient. The system will be thereafter able to detect the faults, isolate it and also able to accommodate the faults in the sensors and actuators of the Continuous Stirred Tank Reactor (CSTR) process while the conventional MPC does not have the ability to perform it.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권4호
• /
• pp.1479-1501
• /
• 2020

Dependable functioning of dynamic networks is essential for delivering ubiquitous services. Faults are the root causes of network outages. The comparison diagnosis model, which automates fault's identification, is one of the leading approaches to attain network dependability. Most of the existing research has focused on stationary networks. Nonetheless, the time-free comparison model imposes no time constraints on the system under considerations, and it suits most of the diagnosis requirements of dynamic networks. This paper presents a novel protocol that diagnoses faulty nodes in diagnosable dynamic networks. The proposed protocol comprises two stages, a testing stage, which uses the time-free comparison model to diagnose faulty neighbour nodes, and a disseminating stage, which leverages a Random Linear Network Coding (RLNC) technique to disseminate the partial view of nodes. We analysed and evaluated the performance of the proposed protocol under various scenarios, considering two metrics: communication overhead and diagnosis time. The simulation results revealed that the proposed protocol diagnoses different types of faults in dynamic networks. Compared with most related protocols, our proposed protocol has very low communication overhead and diagnosis time. These results demonstrated that the proposed protocol is energy-efficient, scalable, and robust.

• Journal of Power Electronics
• /
• 제18권5호
• /
• pp.1608-1617
• /
• 2018

The rapid and correct isolation of faulty submodules (SMs) is of great importance for improving the reliability of modular multilevel converters (MMCs). Therefore, a fast diagnosis method containing fault detection and fault location determination was presented in this paper. An improved incremental predictive model of arm current was proposed to detect failures, and the multi-step prediction method was used to eliminate the negative impact of disturbances. Moreover, a control method was proposed to strengthen the fault characteristics to rapidly locate faulty arms and faulty SMs by detecting the variation rate of the SM capacitor voltage. The proposed method can rapidly and easily locate faulty SMs under different load conditions without the need for additional sensors. The experimental results have validated the effectiveness of the proposed method by using a single-phase MMC with four SMs per arm.

• 대한임베디드공학회논문지
• /
• 제19권3호
• /
• 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.