• Structural Monitoring and Maintenance
• /
• v.1 no.3
• /
• pp.249-271
• /
• 2014

This paper presents a unique study of Structural Health Monitoring (SHM) for the maintenance decision making about a real life movable bridge. The mechanical components of movable bridges are maintained on a scheduled basis. However, it is desired to have a condition-based maintenance by taking advantage of SHM. The main objective is to track the operation of a gearbox and a rack-pinion/open gear assembly, which are critical parts of bascule type movable bridges. Maintenance needs that may lead to major damage to these components needs to be identified and diagnosed timely since an early detection of faults may help avoid unexpected bridge closures or costly repairs. The fault prediction of the gearbox and rack-pinion/open gear is carried out using two types of Artificial Neural Networks (ANNs): 1) Multi-Layer Perceptron Neural Networks (MLP-NNs) and 2) Fuzzy Neural Networks (FNNs). Monitoring data is collected during regular opening and closing of the bridge as well as during artificially induced reversible damage conditions. Several statistical parameters are extracted from the time-domain vibration signals as characteristic features to be fed to the ANNs for constructing the MLP-NNs and FNNs independently. The required training and testing sets are obtained by processing the acceleration data for both damaged and undamaged condition of the aforementioned mechanical components. The performances of the developed ANNs are first evaluated using unseen test sets. Second, the selected networks are used for long-term condition evaluation of the rack-pinion/open gear of the movable bridge. It is shown that the vibration monitoring data with selected statistical parameters and particular network architectures give successful results to predict the undamaged and damaged condition of the bridge. It is also observed that the MLP-NNs performed better than the FNNs in the presented case. The successful results indicate that ANNs are promising tools for maintenance monitoring of movable bridge components and it is also shown that the ANN results can be employed in simple approach for day-to-day operation and maintenance of movable bridges.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.26 no.6
• /
• pp.447-454
• /
• 2013

A model-based method is proposed to diagnose the gear crack in the gearbox under variable loading condition with the objective to apply it to the wind turbine CMS(Condition Monitoring System). A simple test bed is installed to illustrate the approach, which consists of motors and a pair of spur gears. A crack is imbedded at the tooth root of a gear. Tachometer-based order analysis, being independent on the shaft speed, is employed as a signal processing technique to identify the crack through the impulsive change and the kurtosis. Lumped parameter dynamic model is used to simulate the operation of the test bed. In the model, the parameter related with the crack is inversely estimated by minimizing the difference between the simulated and measured features. In order to illustrate the validation of the method, a simulated signal with a specified parameter is virtually generated from the model, assuming it as the measured signal. Then the parameter is inversely estimated based on the proposed method. The result agrees with the previously specified parameter value, which verifies that the algorithm works successfully. Application to the real crack in the test bed will be addressed in the next study.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.36 no.3
• /
• pp.195-201
• /
• 2016

Eddy current testing (ECT) is commonly applied for the inspection of automated production lines of metallic products, because it has a high inspection speed and a reasonable price. When ECT is applied for the inspection of a metallic object having an uneven target surface, such as the spline gear of a spline shaft, it is difficult to distinguish between the original signal obtained from the sensor and the signal generated by a defect because of the relatively large surface signals having similar frequency distributions. To facilitate the detection of defect signals from the spline gear, implementation of high-order filters is essential, so that the fault signals can be distinguished from the surrounding noise signals, and simultaneously, the pass-band of the filter can be adjusted according to the status of each production line and the object to be inspected. We will examine the infinite impulse filters (IIR filters) available for implementing an advanced filter for ECT, and attempt to detect the flaw signals through optimization of system design parameters for detecting the signals at the system level.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.780-785
• /
• 2012

Wind energy is currently the fastest growing source of renewable energy used for electrical generation around the world. Generally, wind turbine systems are designed to be operated for twenty years long, Therefore, various faults in the wind turbine system inevitably occur during their long term period of operation. Especially, rotor shaft, gear-box and generator are installed inside of nacelle, furthermore, some cooling systems for normal operation of these devices are also required. If these cooing systems have failed in their operation, it is impossible for the entire system to be operated normally. In this work, IR(Infra Red) camera based fault detection system for the preventive detection of various cooling systems faults is proposed. To verify the applicability of the proposed system, physical implementation is embodied and various experiments are carried out.

• Smart Structures and Systems
• /
• v.4 no.4
• /
• pp.429-438
• /
• 2008

The aim of this paper is to define the required measurements and processing tools necessary for developing a maintenance approach applied to rotating machines in the presence of multiple faults. The system responses measured were accelerations and transmission errors. Acceleration measurements provide most of the information on bearing conditions, while transmission error measurements provide pertinent information on gear conditions. The measurements were carried out for several operating conditions (loads and speeds). System responses were processed in several analyzing domains (Time, Spectrum, and Cepstrum domains). The approach developed enables the detection and identification of combined faults and it can be applied to other types of rotating machines once the critical elements and their associated faults have been defined.

• Proceedings of the KSR Conference
• /
• 1999.05a
• /
• pp.143-150
• /
• 1999

The vibration signals of driving parts of electric train are distorted its signal patterns due to the impact components, which occurs when wheel passes rail joints. An elimination method of the impact components is investigated using adaptive signal processing technique in this study. The result shows that adaptive interference canceling method seems to be more effective than line enhancement technique. The application of adaptive interference canceling method to the signal measured at bogie shows that the extractions of the signals of driving parts of traction motor, reduction gear, and axle bearing are successful. Therefore, only the signals of bogie, which is the place to attach an accelerometer easily, is sufficient for the fault diagnosis and the safety evaluation of electric train. Also, adaptive interference canceling method can be applicable to evaluate the performance of vibration isolation between bogie and car body and to investigate the characteristics of indoor sound.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2003.05a
• /
• pp.950-955
• /
• 2003

This paper introduces an enhanced condition monitoring and diagnosis system recently developed for rotating machinery. In the system, the data aquisition/monitoring signal processing, machine condition classifier, case-based reasoning and demonstration modules are effectively integrated with user-friendliness so that machine operators can easily monitor and diagnose the status of rotating machinery in operation. Some of the new features include the directional spectrum, case-based reasoning and neural network techniques. And the demonstrator modules for fault diagnosis of a Bear driving system and for basic understanding of the rotor dynamics are provided to help the potential users better understand the system.

• Journal of Aerospace System Engineering
• /
• v.8 no.4
• /
• pp.7-17
• /
• 2014

Objective of this paper is to introduce a new technology known as prognostics and health management (PHM) which enables a real-time life prediction for safety critical systems under extreme loading conditions. In the PHM, Bayesian framework is employed to account for uncertainties and probabilities arising in the overall process including condition monitoring, fault severity estimation and failure predictions. Three applications - aircraft fuselage crack, gearbox spall and battery capacity degradation are taken to illustrate the approach, in which the life is predicted and validated by end-of-life results. The PHM technology may allow new maintenance strategy that achieves higher degree of safety while reducing the cost in effective manner.

• Proceedings of the KIPE Conference
• /
• 2012.07a
• /
• pp.311-312
• /
• 2012

Blade pitch control system monitors and adjusts angle of the blades and controls rotation speed of blades. This paper shows 2MW pitch system hardware and electric part. Blade pitch system consists of pitch drive, gear box, motor and energy storage. Fieldbus is base on CANopen protocol. Fail-Safe system moves the blades to a safety position in case of any fault condition. The super capacitor energy storage provides emergency back up to the Pitch servo driver during feathering the blades. This paper studied Blade pitch servo driver and a bi-directional DC-DC converter for fail-safe system.

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.885-896
• /
• 2022

Motor failure in manufacturing plays an important role in future A/S and reliability. Motor failure is detected by measuring sound, current, and vibration. For the data used in this paper, the sound of the car's side mirror motor gear box was used. Motor sound consists of three classes. Sound data is input to the network model through a conversion process through MelSpectrogram. In this paper, various methods were applied, such as data augmentation to improve the performance of classifying fault motors and various methods according to class imbalance were applied resampling, reweighting adjustment, change of loss function and representation learning and classification into two stages. In addition, the curriculum learning method and self-space learning method were compared through a total of five network models such as Bidirectional LSTM Attention, Convolutional Recurrent Neural Network, Multi-Head Attention, Bidirectional Temporal Convolution Network, and Convolution Neural Network, and the optimal configuration was found for motor sound classification.