• 한국멀티미디어학회논문지
• /
• 제25권11호
• /
• pp.1547-1556
• /
• 2022

As mechanical facilities are interacting with each other, the failure of some equipment can affect the entire system, so it is necessary to quickly detect and diagnose the abnormality of mechanical equipment. This study proposes a deep learning model that can effectively diagnose abnormalities in rotating machinery and equipment. CNN is widely used for feature extraction and LSTMs are known to be effective in learning sequential information. In LSTM, the number of parameters and learning time increase as the length of input data increases. In this study, we propose a method of segmenting an input segment signal into shorter-length sub-segment signals, sequentially inputting them to CNN through a time-distributed method for extracting features, and inputting them into LSTM. A failure diagnosis test was performed using the vibration data collected from the motor for ventilation equipment installed at the urban railway station. The experiment showed an accuracy of 99.784% in fault diagnosis. It shows that the proposed method is effective in the fault diagnosis of rotating machinery and equipment.

• 한국안전학회지
• /
• 제35권3호
• /
• pp.16-23
• /
• 2020

The use of construction machinery has been increasing every year due to the large scale, high-rise and lack of workers in construction work. On the other hand, deaths are on the rise every year due to inadequate risk management for construction machinery work. In addition, the number of deaths caused by the lack of signals or insufficient signals during construction machinery work is increasing rapidly, and it is deemed necessary to analyze the actual conditions and take countermeasures. Therefore this study has developed the Strength Risk Index (SRI) based on the Frequency Risk Index (FRI) and the 5W1H by analyzing in-depth deaths caused by construction machinery over the past five years. The risk index (RI) was assessed using the frequency and strength risk index derived to determine whether it is acceptable (acceptable risk < 0.25 ≦ unacceptable risk) and the risk assessment method for reducing risk was proposed by applying 3E (Engineering, Education, Enforcement) measures for each level of risk for unacceptable risk. It also proposed measures to improve the system, such as requirements for signal numbers, mandatory placement standards, and mandatory installation of side and rear monitoring cameras, as measures for accidents caused by failure to deploy signals or insufficient signals, which account for the highest proportion of deaths among construction machinery operators and workers.

• International Journal of Fluid Machinery and Systems
• /
• 제10권3호
• /
• pp.296-306
• /
• 2017

Hydropower is now changing its role from the energy generator into the most powerful and reliable tool for stabilizing the electrical network, especially under the increase of intermittent power sources like wind-power and solar-power. Although the hydropower plants are the most robust generating facilities, they are not immune from unexpected severe incidents having long downtime, considerable restoration cost and sometimes fatalities. The present paper provides some study results about severe incidents in the conventional hydropower plants, mainly about the flood, fire and electro-mechanical troubles, except for the incidents of civil facilities. It also provides some possible scenarios which may lead some measures how to avoid such incidents. Finally, it provides some comprehensible recommendations to avoid severe incidents based on experiences.

• 대한기계학회논문집A
• /
• 제32권11호
• /
• pp.905-910
• /
• 2008

Vibration analysis is widely used in machinery diagnosis and the wavelet transform has also been implemented in many applications in the condition monitoring of machinery. In contrast to previous applications, this paper examines whether acoustic signal can be used effectively along vibration signal to detect the various local fault, in local fault of gearboxes using the wavelet transform. Moreover, envelop analysis is well known as useful tool for the detection of rolling element bearing fault. In this paper, a acoustic emission (AE) sensor is employed to detect gearbox damage by installing them around bearing housing at driven-end side. Signal processing is conducted by wavelet transform and enveloping to detect her fault all at once gearbox using AE signal.

• International Journal of Fluid Machinery and Systems
• /
• 제3권4호
• /
• pp.301-308
• /
• 2010

Quest for reliability of hydraulic runners is a concern for all mature electricity producers. The fatigue damage caused by dynamics loads is frequently the root cause of runner failure. This paper presents the damage tolerance approach based on fracture mechanics as the method chosen by Alstom and Hydro-Qu$\acute{e}$bec to predict effects of damage on runner lifetime and consequently to be use as a design method. This is sustained by a research on fracture mechanics properties of runner materials and by recommendations on the strategy to define a safety margin for design. The acquired knowledge permits to identify potential improvement of the runner lifetime without significant cost increase, like being more specific on some chemical composition or heat treatment.

• 한국세라믹학회지
• /
• 제40권9호
• /
• pp.832-836
• /
• 2003

Multi-layer ceramic composites were prepared by tape casting followed by hot pressing using silicon nitride layer with silicon nitride whiskers, silicon nitride layer with silicon carbide particles and boron nitride-alumina layer. The whiskers were aligned during the casting. As the whisker content of the silicon nitride layer was increased up to 10 wt％, the flexural strength of the multi-layer composite was increased. However, further increase of the whisker content in the layer resulted in a rapid decrease of the strength of the composite. The results suggest that the strength of multi-layer ceramic composite showing non-catastrophic failure behavior can be significantly improved by incorporating the aligned whiskers in the layers.

• 한국군사과학기술학회지
• /
• 제21권5호
• /
• pp.607-613
• /
• 2018

Hydraulic systems are widely used in the field of defense, construction machinery, agricultural machinery, and general industries, due to various advantages such as quick response speed and precision control. The defense equipments such as light rescue vehicle is operated in very harsh environments, so hydraulic components used in defense equipment are required to have very high reliability. In particular, hydraulic piston pump is very important component in a hydraulic systems, so life prediction of pump is essential. Therefore, in this study, we analyze the potential failure and the main failure mode of the hydraulic piston pump for the light rescue vehicle through the FMEA analysis, and predict the life of the pump by the accelerated life test considering the usage conditions.

• 한국유체기계학회 논문집
• /
• 제19권3호
• /
• pp.53-56
• /
• 2016

In this study, experiments and finite element method analysis were used to determine the autofrettage pressure that is optimal and then maximizes the cycling life of Type3 composite cylinders used in self-contained breathing apparatus. For both approaches, the cylinders were pressurized at 100, 110, ${\ldots}$, 290 % of the test pressure, respectively. The stresses were computed by the FEM analysis; while the strains of cylinders were recorded and the failure modes were monitored during the cycling test. As a result, from the good agreements between the simulations and experiments, it was concluded that at least 70 % of the test pressure should be applied as the autofrettage pressure in order to takes visible effect on the cycling life, and 160 % of the test pressure induces the maximum cycling life and the desired failure mode.

• 한국신뢰성학회지:신뢰성응용연구
• /
• 제11권4호
• /
• pp.331-342
• /
• 2011

The transmission of tracked vehicles performs complex functions as steering, shifting, braking, etc. and the system level life time has been a key influenced by the number of sub-parts like as gear assembly, torque converter, clutches, bearings and so on. In particular, the mechanical type steering system in tracked vehicle has impact shock torques in steering shift and those kind of shock torques can effect on the durability of many sub-parts in power train system. The field failure modes of gear assembly, steering assembly and the bearings of output shaft appear as a very complex phenomenon. In this study, the actual failure, which may occur in field, of the transmission was investigated comprehensively and that the endurance test on the resulting output shaft bearing failure analysis and life assessment was performed. Life time test method used in this study, developed for the purpose of the internal usage, and under these testing techniques the impact of the each bearing damage, which used in tracked vehicle transmission left / right outputs of different structures, was analyzed.

• 한국신뢰성학회지:신뢰성응용연구
• /
• 제11권4호
• /
• pp.343-356
• /
• 2011

This paper proposes an accelerated life evaluation of drive shaft. The life test of drive shaft for independent suspension type AWD vehicle should be performed by use of the least test sample because many number of samples can't be used for the test because of its mass capacity and high price. We calculated the no failure test time by application of no failure test concept, and the already performed test data for drive shaft are applied for some kinds of reliability coefficients which are needed for calculation of life test time. And, for analysis of real driving condition of vehicle, the load spectrum is prepared using the needed road condition and vehicle data. The inverse power model is used for accelerated life test. The equivalent torque of load spectrum is achieved by use of Miner's Rule, and then the final accelerating condition is determined by decision of the accelerated test torque. This paper shows that the accelerated life test results corresponds with the target life and the proposed life test method can be very well applied to no failure life test for mass capacity machinery components.