• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.47 no.2
• /
• pp.1-9
• /
• 2024

New motor development requires high-speed load testing using dynamo equipment to calculate the efficiency of the motor. Abnormal noise and vibration may occur in the test equipment rotating at high speed due to misalignment of the connecting shaft or looseness of the fixation, which may lead to safety accidents. In this study, three single-axis vibration sensors for X, Y, and Z axes were attached on the surface of the test motor to measure the vibration value of vibration. Analog data collected from these sensors was used in classification models for anomaly detection. Since the classification accuracy was around only 93%, commonly used hyperparameter optimization techniques such as Grid search, Random search, and Bayesian Optimization were applied to increase accuracy. In addition, Response Surface Method based on Design of Experiment was also used for hyperparameter optimization. However, it was found that there were limits to improving accuracy with these methods. The reason is that the sampling data from an analog signal does not reflect the patterns hidden in the signal. Therefore, in order to find pattern information of the sampling data, we obtained descriptive statistics such as mean, variance, skewness, kurtosis, and percentiles of the analog data, and applied them to the classification models. Classification models using descriptive statistics showed excellent performance improvement. The developed model can be used as a monitoring system that detects abnormal conditions of the motor test.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.25 no.1
• /
• pp.28-34
• /
• 2017

The vehicle stabilizer link is one of the suspension components that reduces the bumping and rolling during vehicle driving. However, this stabilizer link could be a source of the abnormal noises when its free gaps have higher than normal values. Therefore, the current study aims at investigating the quantitative relationships between the abnormal noises and free gaps of the vehicle stabilizer links, as well as the length of time that the vehicle stabilizer links could be used without generating abnormal noises. In this study, the abnormal noises were measured based on the magnitude of the stabilizer link vibration, while the free gaps were quantified through the force-displacement curves of the stabilizer links. Harsh durability tests were also conducted in order to quantify the operating cycles of the stabilizer links before generating the abnormal noises, along with the concomitant measurements of the free gaps. The current results showed that the abnormal noises of the stabilizer links were detected when its free gaps were larger than 0.12 mm. However, the free gaps of the stabilizer links, which are bigger than 0.1 mm, produced the abnormal noises at 1.5 million cycles under harsh durability test conditions. A parametric study in the future that would reflect the different shapes and sizes of the stabilizer links for diverse vehicles could determine more generalized relationships between the abnormal noises and free gaps of the vehicle stabilizer links.

• Journal of the Korean Society for Precision Engineering
• /
• v.30 no.7
• /
• pp.667-672
• /
• 2013

This paper presents the development of a condition monitoring system that monitors the operating conditions of a reduction unit, such as the bearing temperature, gearbox vibration, and gear oil deterioration, and notifies the operator of potential problems or abnormal conditions. A series of field tests on high-speed rail and conventional lines was performed to identify the characteristics of temperature rise and vibration levels on the reduction unit during operation. The monitoring system was designed based on the proper sensor selection, measurement method, and signal analysis to optimize the interface with the operating system of high-speed trains. Application of this monitoring system to high-speed trains will play an important role in their proper maintenance and safe operation.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2008.04a
• /
• pp.876-878
• /
• 2008

The standards of acceptable limit and compensation is one of the most important things in environmental noise and vibration disputes resolution. In this paper, review on the present acceptable limit level and compensation standard in National Environmental Dispute Resolution Commission is introduced. Discordance of standards between in the regulation law and in the dispute resolution commission and it's improvement are discussed. Abnormal reasoning for compensation standards is pointed out from a author's private view.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.18 no.2
• /
• pp.208-214
• /
• 2008

This paper presents a structural modification for the performance improvement of a grain sorting machine. The grain sorting machine is used to sort abnormal grains from normal grains such as rice or wheat. Vibration is one of main causes to deteriorate the sorting performance of the machine. Based on the finite element analysis and the experimental modal testing, the vibration characteristics were investigated for the sorting machine. Furthermore, in order to improve the sorting performance of the machine, the frame, chute and base plate of the sorting machine were modified by using the results of the vibration analysis.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.1
• /
• pp.176-187
• /
• 2015

DC bias will cause abnormal vibration of transformers. Aiming at such a problem, transformer vibration affected by DC bias has been studied combined with transformer core and winding vibration mechanism use multi-physical field simulation software COMSOL in this paper. Furthermore the coupling model of electromagnetic-structural force field has been established, and the variation pattern of inner flux density, distribution of mechanical stress, tension and displacement were analyzed based on the coupling model. Finally, an experiment platform has been built up which was employed to verify the correctness of model.

• Journal of Power System Engineering
• /
• v.9 no.2
• /
• pp.45-49
• /
• 2005

Liquefied natural gas takes up six hundredths of the volume of natural gas, which makes storage and transportation much easier. To send out natural gas via a pipeline network across the nation, high-pressure LNG pumps supply highly compressed LNG to high-pressure vaporization facilities. The Number of high-pressure LNG 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 beat vibration at cryogenic pumps, vibration and motor current signal analysis have been performed. High vibration of cryogenic pumps could be reduced due to the modification of motor rotor.

• Journal of KSNVE
• /
• v.10 no.4
• /
• pp.692-701
• /
• 2000

Escalators are widely used for mass transportation in public places. In recent years, strict requirements on the comfort and reliability for the public transportation have drawn a great attention to vibration in escalators. This paper presents a dynamic model for escalators to be used for the analysis and design of low vibration escalators. The dynamic model is developed so as to reflect the physical observation on peculiar characteristics in escalators such as the difference between up-moving and down-moving, and the abnormal vibration affected by the load applied. For validation of the dynamic model developed, experimental results are compared with numerical results from the model. The numerical study shows that the developed model may be useful for the analysis and design of escalator systems.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2000.06a
• /
• pp.1133-1138
• /
• 2000

This paper describes a signal recognition method for diagnosing the rotating machinery using wavelet-aided Self-Organizing Feature Map(SOFM). The SOFM specialized from neural network is a new and effective algorithm for interpreting large and complex data sets. It converts high-dimensional data items into simple order relationships with low dimension. Additionally the Learning Vector Quantization(LVQ) is used for reducing the error from SOFM. Multi-resolution and wavelet transform are used to extract salient features from the primary vibration signals. Since it decomposes the raw timebase signal into two respective parts in the time space and frequency domain, it does not lose either information unlike Fourier transform. This paper is focused on the development of advanced signal classifier in order to automatize vibration signal pattern recognition. This method is verified by the experiment and several abnormal vibrations such as unbalance and rubbing are classified with high flexibility and reliability by the proposed methods.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2013.10a
• /
• pp.753-756
• /
• 2013

The demand for sailing yacht is increasing in consonance the improvement of people's live. These yachts can be dually propelled by wind and by diesel engine power. A singing (humming, whistling) phenomenon induced on the propeller was discovered on a 55-foot catamaran sailing yacht. As a result, an increase in the structural vibration of the stern tube room and propulsion system with abnormal noise was detected due to this flow. In this study, the cause of the phenomenon is investigated and its possible countermeasures proposed.