• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.500-504
• /
• 1995

A neural network based upon the back propagation algorithm was designed and applied to acoustic power spectra of electrohydraulic total artificial hearts in order to diagnose mechanical failure of devices. The trained network distinguished spectra of the mechanically damaged device from those of the undamaged device with overall success rate of 63%. Moreover, the network correctly classified more than 70% of spectra in the frequency bands of 0-100 Hz and 700-950 Hz. Consequently, the neural network analysis was useful for the diagnosis of mechanical failure of a total artificial heart.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.2
• /
• pp.205-210
• /
• 2014

Recently, pattern recognition methods have been widely used by researchers for fault diagnoses of mechanical systems. A pattern recognition method determines the soundness of a mechanical system by detecting variations in the system's vibration characteristics. Hidden Markov models (HMMs) and artificial neural networks (ANNs) have recently been used as pattern recognition methods in various fields. In this study, a HMM-ANN hybrid method for the fault diagnosis of a mechanical system is introduced, and a rotating wind turbine blade with a crack is selected for fault diagnosis. The existence, location, and depth of said crack are identified in this research. For improving the diagnostic accuracy of the method in spite of the presence of noise, a moment with a few specific frequencies is applied to the structure.

• Journal of Drive and Control
• /
• v.9 no.4
• /
• pp.8-13
• /
• 2012

Recently, researches about the eco-friendly vehicles such as hybrid electric vehicle, fuel cell vehicle and electric vehicle have been actively carried out. The regenerative braking system is a key technology to improve the vehicle energy utilization efficiency because it transforms the kinetic energy to the electric energy through the electric motor. This new braking system requires cooperative control between electric controlled brake and regenerative brake. Therefore, it is necessary to establish fault-diagnosis and fail-safe evaluation criteria to secure reliability of the regenerative braking system. In this paper, the failure types and causes in regenerative braking system were analyzed. The transient behavior characteristics were examined based on fault-diagnosis and fail-safe upon failure of regenerative braking system.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.26 no.4
• /
• pp.587-595
• /
• 2002

Recent trend changes a criterion for evaluation of humors that environmental problems are raised as a global issue. Burners with higher thermal efficiency and lower oxygen in the exhaust gas, evaluated better. To comply with environmental regulations, burners must satisfy the NO/sub x/ and CO regulation. Consequently, 'good burner'means one whose thermal efficiency is high under the constraint of NO/sub x/ and CO consistency. To make existing burner satisfy recent criterion, it is highly recommended to develop a feedback control scheme whose output is the consistency of NO/sub x/ and CO. This paper describes the development of a real time flame diagnosis technique that evaluate and diagnose the combustion states, such as consistency of components in exhaust gas, stability of flame in the quantitative sense. In this paper, it was proposed on the flame diagnosis technique of burner using Neuro-Fuzzy algorithm. This study focuses on the relation of the color of the flame and the state of combustion. Neuro-Fuzzy loaming algorithm is used in obtaining the fuzzy membership function and rules. Using the constructed inference algorithm, the amount of NO/sub x/ and CO of the combustion gas was successfully inferred.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.5
• /
• pp.1186-1207
• /
• 2024

Bearings are one of the main components of mechanical equipment and one of the primary components prone to faults. Therefore, conducting fault diagnosis on bearings is a key issue in mechanical equipment research. Belief rule base (BRB) is essentially an expert system that effectively integrates qualitative and quantitative information, demonstrating excellent performance in fault diagnosis. However, class imbalance often occurs in the diagnosis task, which poses challenges to the diagnosis. Models with interpretability can enhance decision-makers' trust in the output results. However, the randomness in the optimization process can undermine interpretability, thereby reducing the level of trustworthiness in the results. Therefore, a hierarchical BRB model based on extreme gradient boosting (XGBoost) feature selection with interpretability (HFS-IBRB) is proposed in this paper. Utilizing a main BRB alongside multiple sub-BRBs allows for the conversion of a multi-classification challenge into several distinct binary classification tasks, thereby leading to enhanced accuracy. By incorporating interpretability constraints into the model, interpretability is effectively ensured. Finally, the case study of the actual dataset of bearing fault diagnosis demonstrates the ability of the HFS-IBRB model to perform accurate and interpretable diagnosis.

• Journal of Mechanical Science and Technology
• /
• v.16 no.12
• /
• pp.1604-1612
• /
• 2002

Rollers in the continuous process systems are ones of key components that determine the quality of web products. The condition of rollers (e.g. eccentricity, runout) should be consistently monitored in order to maintain the process conditions (e.g. tension, edge position) within a required specification. In this paper, a new diagnosis algorithm is suggested to detect the defective rollers based on the frequency analysis of web tension signals. The kernel of this technique is to use the characteristic features (RMS, Peak value, Power spectral density) of tension signals which allow the identification of the faulty rollers and the diagnosis of the degree of fault in the rollers. The characteristic features could be used to train an artificial neural network which could classify roller conditions into three groups (normal, warning, and faulty conditions) The simulation and experimental results showed that the suggested diagnosis algorithm can be successfully used to identify the defective rollers as well as to diagnose the degree of the defect of those rollers.

• Journal of the Korean Society for Precision Engineering
• /
• v.33 no.1
• /
• pp.23-29
• /
• 2016

In this paper, a real-time condition diagnosis system for the lens injection molding process is developed through the use of LabVIEW. The built-in-sensor (BIS) mold, which has pressure and temperature sensors in their cavities, is used to capture real-time signals. The measured pressure and temperature signals are processed to obtain features such as maximum cavity pressure, holding pressure and maximum temperature by the feature extraction algorithm. Using those features, an injection molding condition diagnosis model is established based on a response surface methodology (RSM). In the real-time system using LabVIEW, the front panels of the data loading and setting, feature extraction and condition diagnosis are realized. The developed system is applied in a real industrial site, and a series of injection molding experiments are conducted. Experimental results show that the average real-time condition diagnosis rate is 96%, and applicability and validity of the developed real-time system are verified.

• Journal of Mechanical Science and Technology
• /
• v.20 no.7
• /
• pp.972-980
• /
• 2006

In general, to send out natural gas via a pipeline network across the nation in LNG terminal, high-pressure cryogenic pump supply highly compressed LNG to high-pressure vaporization facilities. The Number of cryogenic pumps determined the send-out amount in LNG receiving terminal. So it is main equipment at LNG production process and should be maintained on best conditions. In this paper, to find out the cause of high vibration at cryogenic pumps-motor system in LNG terminal, vibration spectrum analysis and motor current signature analysis have been performed together. Through the analysis, motor rotor bar problems are estimated by the vibration analysis and confirmed by the current analysis. So, it is demonstrated through the case study in this paper, how performing vibration analysis and current signature analysis together can reliable diagnosis rotor bar problems in pump-motor system.

• Smart Structures and Systems
• /
• v.25 no.4
• /
• pp.459-469
• /
• 2020

The presence of cracks in mechanical components is a very important problem that, if it is not detected on time, can lead to high economic costs and serious personal injuries. This work presents a methodology focused on identifying cracks in unbalanced rotors, which are some of the most frequent mechanical elements in industry. The proposed method is based on Artificial Neural Networks that give a solution to the presented inverse problem. They allow to estimate unknown crack parameters, specifically, the crack depth and the eccentricity angle, depending on the dynamic behavior of the rotor. The necessary data to train the developed Artificial Neural Network have been obtained from the frequency spectrum of the displacements of the well- known cracked Jeffcott rotor model, which takes into account the crack breathing mechanism during a shaft rotation. The proposed method is applicable to any rotating machine and it could contribute to establish adequate maintenance plans.

• Journal of Mechanical Science and Technology
• /
• v.20 no.12
• /
• pp.2079-2086
• /
• 2006

A fundamental study for developing a fault diagnosis system of a pump is performed by using neural network. Acoustic signals were obtained and converted to frequency domain for normal products and artificially deformed products. The neural network model used in this study was 3-layer type composed of input, hidden, and output layer. The normalized amplitudes at the multiples of real driving frequency were chosen as units of input layer. And the codes of pump malfunctions were selected as units of output layer. Various sets of teach signals made from original data by eliminating some random cases were used in the training. The average errors were approximately proportional to the number of untaught data. Neural network trained by acoustic signals can detect malfunction or diagnose fault of a given machine from the results.