• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.522-526
• /
• 1994

There are great needs for checking machine operation status precisely in the iron and steel plants. Rotating machines such as pumps, compressors, and motors are the most important objects in the plant maintenance. In this paper back-propagation neural network is utilized in diagnosing rotating machines. Like the finger print or the voice print of human, the abnormal vibrations due to axis misalignment, shaft bending, rotor unbalance, bolt loosening, and faults in gear and bearing have their own spectra. Like the pattern recognition technique, characteristic. feature vectors are obtained from the power spectra of vibration signals. Then we apply the characteristic feature vectors to a back propagation neural net for the weight training and pattern recognition.

• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.7
• /
• pp.591-595
• /
• 2015

The roller rig tester for safety performance evaluation of wheel derailment is a test facility which can give the test load condition to the test wheel, similar to the actual dynamic condition in actual running condition. This study describes the evaluation result on the durability of the resilient wheel equipped with the ring damper and the damping material, and installed in the half part of a full scaled bogie in combination with the primary spring when it rotates under the dynamic condition. The evaluation result on durability of resilient wheel after load test of 2 million cycles shows that the safety of wheel is not affected by the applied load in visual inspection and nondestructive test, however, in the bolt used for fastening the ring damper to the wheel the loosening was found. Accordingly the use of self-locking nut and washer is recommended.

• Proceedings of the KIEE Conference
• /
• 2003.07a
• /
• pp.436-438
• /
• 2003

Wind-induced oscillations are known to cause damage to the conductors and related hardware through fatigue, clashing of the bundled conductors and bolt loosening. Wake-induced oscillations have been known since the advent of bundled conductors, they are caused by aerodynamically unstable forces acting on the leeward conductors in the wake of the windward conductors, They take the form of horizontal galloping, snaking or rolling, in which case all subconductors move together in unison. They can also take the form of the subspan oscillation, which appear as elliptical motions of the subconductors moving out of phase, mainly in the horizontal plane within a subspan. In order to decrease amplitudes of the oscillation, this paper examines the application status of the spacer dampers and suggests proper installation methods.

• Structural Monitoring and Maintenance
• /
• v.5 no.2
• /
• pp.231-242
• /
• 2018

Subway tunnel structure has been rapidly developed in many cities for its strong transport capacity. The model-based damage detection of subway tunnel structure is usually difficult due to the complex modeling of soil-structure interaction, the indetermination of boundary and so on. This paper proposes a new data-based method for the damage detection of subway tunnel structure. The root mean square acceleration and cross correlation function are used to derive a statistical pattern recognition algorithm for damage detection. A damage sensitive feature is proposed based on the root mean square deviations of the cross correlation functions. X-bar control charts are utilized to monitor the variation of the damage sensitive features before and after damage. The proposed algorithm is validated by the experiment of a full-scale two-rings subway tunnel lining, and damages are simulated by loosening the connection bolts of the rings. The results verify that root mean square deviation is sensitive to bolt loosening in the tunnel lining and X-bar control charts are feasible to be used in damage detection. The proposed data-based damage detection method is applicable to the online structural health monitoring system of subway tunnel lining.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.191-200
• /
• 2020

Tracked military vehicles are operated under harsher conditions and climates than ordinary vehicles, and the components require high degrees of reliability and durability. A diesel engine is the main power generator, and when the vehicle breaks down, there is a high possibility of causing a large-scale accident. Therefore, analyzing the cause of engine failure can be important for preventing similar cases that may occur. In this study, we clarified the mechanism of engine failure according to an overhaul test, hardness measurement, and an analysis of the fracture surface. The overhaul test confirmed that a bolt was separated from the connecting rod (number 4). In addition, the hardness measurement results of the connecting rod bolt conformed to the standard, and it was found that the bolt fracture was ductile fracture through an analysis of the fracture surface. Based on the results, it was concluded that damage to a diesel engine of a tracked military vehicle was caused by separating and damage caused by loosening of the connecting rod bolts, resulting in cascading damage. The results of the study could be used as reference examples and could be useful for another study on engine failure analysis.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.8
• /
• pp.965-970
• /
• 2010

Bolts and nuts are widely used to fasten mechanical parts together in machines and structures. The primary role of a nut is to maintain the axial force of a bolt. In this paper, a new type of a lock nut that uses a spring is studied. To have a spring within a nut, a cocking process to narrow the top of the nut is adopted, but cracking occurred in the process. In this study, strain of an initial model is measured using the finite element analysis program, MSC/Marc. The occurrence of the crack was studied by comparing the maximum observed strain of a model with the maximum strain indicated by an accurate stress-strain diagram of 1020 steel. Then, the structure of the lock nut was optimized by response surface analysis to prevent cracking. The prototype of the lock nut was manufactured on the basis of the optimization result, and cracking did not occur.

• Fire Science and Engineering
• /
• v.34 no.3
• /
• pp.67-75
• /
• 2020

In this study, the risk of heat generation due to normal and overload currents that vary with the abnormal loosening angle of wire-connecting bolts were identified. The risks were analyzed based on the thermal characteristics to minimize the carbonization accidents of terminal blocks inside distribution panels typically used in industrial sites. We applied a method for measuring the heating temperature and temperature variations in the terminal blocks in real-time by installing a resistance temperature detector sensor board in the terminal block. The experimental results showed that the terminal block model with a low-rated current exhibited a higher heating temperature, thus, confirming the need to select the terminal block capacity based on load currents. Additionally, the higher the rated current of the terminal block with a high-rated current and the higher the degree of loosening, the faster the carbonization point. Such heating temperature monitoring enabled real-time thermal temperature measurement and a step-by-step risk level setting through thermal analysis. The results of the measurement and analysis of carbonization risks can provide a theoretical basis for further research regarding the risk of fire due to carbonization. Furthermore, the deterioration measurement method using the temperature sensor board developed in this study is widely applicable to prevent fires caused by poor electrical contact as well as risk-level management.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.651-658
• /
• 2021

Because bolts with anti-loosening coatings are used mainly for joining safety-related components in automobiles, accurate automatic screening of these coatings is essential to detect defects efficiently. The performance of the convolutional neural network (CNN) used in a previous study [Identification of bolt coating defects using CNN and Grad-CAM] increased with increasing number of data for the analysis of image patterns and characteristics. On the other hand, obtaining the necessary amount of data for coated bolts is difficult, making training time-consuming. In this paper, resorting to the same VGG16 model as in a previous study, transfer learning was applied to decrease the training time and achieve the same or better accuracy with fewer data. The classifier was trained, considering the number of training data for this study and its similarity with ImageNet data. In conjunction with the fully connected layer, the highest accuracy was achieved (95%). To enhance the performance further, the last convolution layer and the classifier were fine-tuned, which resulted in a 2% increase in accuracy (97%). This shows that the learning time can be reduced by transfer learning and fine-tuning while maintaining a high screening accuracy.

• Structural Monitoring and Maintenance
• /
• v.4 no.3
• /
• pp.237-253
• /
• 2017

Among various structural health monitoring technologies, impedance-based damage detection has been recognized as a promising tool for diagnosing critical members of civil structures. Since the piezoelectric transducers used in the impedance-based technique should be bonded to the surface of the structure using bonding layers (e.g., epoxy layer), it is hard to maintain the as-built condition of the bonding layers and to reconfigure the devices if needed. This study presents an experimental investigation by using magnetically attached PZT-interface for the impedance-based damage detection in bolted girder connections. Firstly, the principle of the impedance-based damage detection via the PZT-interface device is outlined. Secondly, a PZT-interface attachment method in which permanent magnets are used to replace the conventional bonding layers is proposed. Finally, the use of the magnetic attraction for the PZT-interface is experimentally evaluated via detecting the bolt-loosening events in a bolted girder connection. Also, the sensitivity of impedance signatures obtained from the PZT-interface is analyzed with regard to the interface's material.

• Steel and Composite Structures
• /
• v.16 no.6
• /
• pp.703-718
• /
• 2014

The initial clamping forces of high strength bolts subjected to different faying surface conditions drop within 500 hours regardless of loading, any other external force or loosening of the nut. This study develops a mathematical model for relaxation confined to creep on a coated faying surface after initial clamping. The quantitative model for estimating relaxation was derived from a regression analysis for the relation between the creep strain of the coated surface and the elapsed time for 744 hours. This study establishes an expected model for estimating the relaxation of bolted joints with diverse coated surfaces. The candidate bolts are dacro-coated tension control bolts, ASTM A490 bolt, and plain tension control bolts. The test parameters were coating thickness, species of coating. As for 96, 128, 168, and $226{\mu}m$ thick inorganic zinc, when the coating thickness was increased, relaxation after the initial clamping rose to a much higher range from 10% to 18% due to creep of the coating. The amount of relaxation up to 7 days exceeded 85% of the entire relaxation. From this result, the equation for creep strain can be derived from a statistical regression analysis. Based on the acquired creep behavior, it is expected that the clamping force reflecting relaxation after the elapse of constant time can be calculated from the initial clamping force. The manufacturer's recommendation of inorganic zinc on faying surface as $75{\mu}m$, appears to be reasonable.