밸브의 내부 누설 현상은 밸브의 내부 부품의 손상에 의해 발생하며 배관 시스템의 사고와 운전정지를 일으키는 주요 요인이 다. 본 연구는 버터플라이형 밸브의 내부 누설에 따라 배관계에서 발생하는 음향방출 신호를 이용하여 배관 가동 중 실시간 누설 진단의 가능성을 검토하였다. 이를 위해 밸브의 작동 모드별로 측정한 시간영역의 AE 원시신호를 취득하였으며 이로부터 구축한 데이터셋은 데 이터 기반의 인공지능 알고리즘에 적용하여 밸브의 내부 누설 유무를 진단하는 모델을 생성하였다. 누설 유무진단을 분류의 문제로 정의 하여 SVM 기반의 머신러닝과 CNN 기반의 딥러닝 분류 알고리즘을 적용하였다. 데이터의 특징 추출에 기반한 SVM 분류 모델의 경우, 이 진분류 모델에서 구축된 모델에 따라 83~90%의 정확도를 나타냈으며, 다중 클래스인 경우 분류 정확도가 66%로 감소하였다. 반면, CNN 기반의 다중 클래스 분류 모델의 경우 99.85%의 분류 정확도를 얻을 수 있었다. 결론적으로 밸브 내부 누설 진단을 위한 SVM 분류모델은 다중 클래스의 정확도 향상을 위해 적절한 특징 추출이 필요하며, CNN 기반의 분류모델은 프로세서의 성능 저하만 없다면 누설진단과 밸브 개도 분류에 효율적인 접근방법임을 확인하였다.

To estimate weld quality of the resistance spot-welding, the acoustic emission features are investigated from the total acoustic emission signal at the single-spot weld. Typically, the resistance spot welding process consists of several stages: set-down of the electrodes, squeeze, current flow, forging, hold time, and lift-off. Various types of acoustic emission response corresponding to each stage can be separately analyzed by using back-propagation neural network classifier and wavelet transform technique. The presented machine learning results provide a validation for using back-propagation neural network and wavelet transform technique as a valuable insights into the resistance spot-welding process. Especially, a wavelet transform technique is demonstrated and the plots are very powerful in the recognition of the acoustic emission features

In this study, carbon/epoxy composite DCB(double cantilever beam) specimens based on K-means clustering and wavelet transform analyses are presented. For the fracture Mode I, the fiber orientation θ = [0 ]24 and θ = [±45]12 both shown up stable crack growth in DCB testing. For the fiber orientation θ = [0 ]24 , the continuous type AE signal showed at central frequency 130～270kHz, which means that matrix micro cracking was occurred. The Burst type AE signal was occurred at central frequency 200～300kHz due to fiber bridging and fiber breaking. Other burst type AE signals were occurred at central frequency 130～180kHz with very high amplitude due to fiber bridging. For the fiber orientation θ = [±45]12 , the burst type signal showed at central frequency 220～300kHz, which means that fiber breaking was occurred. Mixed type of burst and continuous signals were captured at central frequency 250～480kHz due to fiber friction.

This is a study on the distribution of acoustic emission parameters during a burst test for a type-II CNG vehicle fuel tank. A resonant AE sensor with a central frequency of 150 kHz was attached to the composite materials in the center of the fuel tank. The pressure was increased from 30 to 100% of the expected burst pressure and was maintained for 10 minutes at each level. Damage at 70% of expected burst pressure occurred by various damage mechanisms including fiber breakage and delamination, while that of below 60% only occurred by matrix crack initiation and growth. The count, duration and rise time of the AE signal at 60% of the expected burst pressure are distributed below 500, 5000 μs and 300 μs, respectively. Then, at above 70% they increased with pressure by superimposing of individual AE signal generated at a nearby place. These results confirmed that the analysis of the distribution of AE parameters is an effective tool for estimating damage of a CNG fuel tank.

This study deals with the high frequency induction hardening (HF at 850℃, 120kHz & 50kW condition) SM45C steel. (1) The HF specimen, which was tempered at 150℃, did not show any tempering effect. A brittle fracture occurred at rounded area of the tensile specimen. AE (acoustic emission) amplitude distribution showed between 45dB and 60dB. (2) A slip and fracture occurred at the hole area of the HF specimen which was tempered at 300℃. As they pass the yield point, the AE energy is increased intermittently and AE amplitude distribution exists between 70dB and 85dB. In addition, after imposing the maximum tensile load, AE signals showed high amplitude and energy distribution. The AE amplitude showed between 45dB and 70dB. (3) A brittle fracture occurred at HF specimen which was tempered at 450℃ as if it is torn in the direction of 45° on parallel area over the both sides of the tensile specimen, which lead to several peak appeared in AE energy. It was found that the AE amplitude was relatively low and the AE energy was high.

This study investigated tensile deformation of the stress aging heat-treated SM45C steel which are aging temperature at 250℃ and 300℃; aging time at 1 hour and, 3 hours; applied load at 300N and 400N by using an acoustic emission techniques (AEs). A signal processing technology is applied to evaluate an AE source characterization of different AE measurement systems DiSP & PCI-2. In this study, most suitable aging condition appeared at 250℃, 3 hours and 300N. But in cases of 250℃, 3 hours, 400N and 300℃, 3 hours, 400N conditions, yield load decreased compare to other conditions according to the over-aging phenomena. On the other hand, when arranged via AE amplitude results by K-means clustering pattern recognition of AE raw signals, tendency of signal strength appeared non-heat treatment condition, 'Class 1 < Class 2 < Class 3'; optimal condition, 'Class 3 < Class 2'; over-aging condition, 'Class 3 < Class 2 < Class 1'. This is judged by emitting a lot of AE energy when material causes plastic deformation because ductility increases on factor by over-aging phenomenon.

This study is deal with the high frequency induction hardening (HF at 850℃, 120kHz & 50kW condition) SM45C steel. (1) The HF specimen which was tempered at 150℃, did not appear any tempering effect. A brittle fracture occurred at rounded area of the tensile specimen. AE amplitude distribution showed between 45~60dB. (2) The HF specimen which was tempered at 300℃, slip and fracture occurred at the hole area of the tensile specimen. As it passes the yield point, the AE energy increased intermittently and AE amplitude distribution showed between 70~85dB. In addition, after the maximum tensile load, it showed high amplitude and energy distribution. The AE amplitude showed between 45~70dB. (3) The HF specimen which was tempered at 450℃, a brittle fracture occurred as if it is torn in the direction of 45℃ on parallel area over the both sides of the tensile specimen, which led to several peak to be appeared in AE energy. It was found that the AE amplitude was relatively low and the AE energy was high.

A study of fracture to material is getting interest in nuclear and aerospace industry as a viewpoint of safety. Acoustic emission (AE) is a non-destructive testing and new technology to evaluate safety on structures. In previous research continuously, all tensile tests on the pre-defected coupons were performed using the universal testing machine, which machine crosshead was move at a constant speed of 5mm/min. This study is to evaluate an AE source characterization of SM45C steel by using k-nearest neighbor classifier, k-NNC. For this, we used K-means clustering as an unsupervised learning method for obtained multi -variate AE main data sets, and we applied k-NNC as a supervised learning pattern recognition algorithm for obtained multi-variate AE working data sets. As a result, the criteria of Wilk's λ, D&B(Rij) & Tou are discussed.

The objective of this study is to evaluate the mechanical behaviors and structural integrity of the weldment of high strength steel by using an acoustic emission (AE) techniques. Monotonic simple tension and AE tests were conducted against the 3 kinds of welded specimen. In order to analysis the effectiveness of weldability, joinability and structural integrity, we used K-means clustering method as a unsupervised learning pattern recognition algorithm for obtained multi-variate AE main data sets, such as AE counts, energy, amplitude, hits, risetime, duration, counts to peak and rms signals. Through the experimental results, the effectiveness of the proposed method is discussed.

The objective of this study is to evaluate the mechanical behaviors and structural integrity of the weldment of high strength steel by using an acoustic emission (AE) techniques. Simple tension and AE tests were conducted against the 3 kind of welding test specimens. In order to analysis the effectiveness of weldability, joinability and structural integrity, we used K-means clustering method as a unsupervised learning pattern recognition algorithm for obtained multivariate AE main data sets, such as AE counts, energy, amplitude, hits, risetime, duration, counts to peak and rms signals. Through the experimental results, the effectiveness of the proposed method is discussed.

In this work, the carbon fibers-reinforced carbon matrix composites made with different carbon char yields of phenolic resin matrix have been characterized by mechanical flexural tests for acoustic emission properties. The composites had been fabricated in the form of two-dimensional polyacrylonitrile based carbon fibers during the carbonization process. It was found that the composites made with the carbon char yield-rich of resin matrix result in better mechanical interfacial properties, i.e., the interlaminar shear strength (ILSS) of the composites. The data obtained from the acoustic emission monitored appeared to show that the composites made with carbon char yield-rich were also more ductile. From the acoustic emission results, the primary composite failure was largely depended on the debonding at interfaces between fibers and matrix. The interlaminar shear strengths of the composites were correlated with the acoustic emission results.

bismaleimide취약성을 개선 하기 위하여 toughening agent인 TM120을 첨가하여 carbon/(± 45˚)2s를 제조하고 이들의 파손과 기계적 특성을 인당실험과 음향방출을 통해 자세히 논하였다. 첨가하는 TM120의 비율은 0, 5, 10, 15, 20, 25phr이었고, 1, 4-diazobicyclo-(2, 2, 2)-octane(DABCO) 0.2phr를 경화 촉진제로 사용하였다. 또한, 탄소 섬유는 Toray사의 T300를 사용하였고, 음향방출과 인장실험 결과로 TM120이 적당한 첨가량은 20phr이었으며, TM120은 cabon/(± 45˚)2s의 파손특성과 기계적물성에 많은 영향을 미쳤다.

유리 원형 평판에서 힘의 세기가 1 dyne이고 면에 수직하게 작용하는 Heaviside계단 함수의 시간 의존성을 갖는 점 하중에 의한 진앙점에서 수직 변위를 이론적으로 계산하였다. 연필심 파괴시 방출되는 음향방출신호를 안정화회로가 부착된 Michelson 간섭계로 측정하여, 음향방출 발생원함수를 deconvolution방법을 이용하여 해석하였다. 연필심 파괴시 방출되는 음향방출 발생원을 파 전면에 약 0.7μsec의 지속시간이 갖는 dip부분과 약 0.5μsec인 계단 상승시간과 약 4.5N의 힘의 크기를 갖는 계단함수의 형태였다.

Korea Atomic Energy Research Institute (“KAERI”) has been developing various studies related to the nuclear fuel cycle. Among them, KAERI was focusing on the pyroprocess, which recycles some useful elements white reducing the volume and toxicity of spent nuclear fuel (SNF). Pyroprocess involves the handling of SNF, which cannot be handled directly by the facility worker. Therefore, SNF is handled and processed through remote handling device within a shielded facility such as a hot cell. Nuclear Facilities with such hot cells are called nuclear fuel cycle facilities, and unlike other facilities, heating, ventilating, and air conditioning (HVAC) system are particularly important in nuclear fuel cycle facilities to maintain the atmosphere in the hot cell and remove radioactive materials. In addition, due to the nature of the pyroprocess, which uses molten salt, corrosion is a problem in air atmosphere, so the process can only be carried out in an inert gas atmosphere. KAERI has a nuclear fuel cycle facility called the Irradiation Material Examination Facility (IMEF), and has built and operated the ACPF inside the IMEF, which operates an inert atmosphere hot cell for the demonstration of the pyroprocess. For efficient process development of the pyroprocess, it is necessary to put the developed equipment into the hot cell, which is a radiationcontrolled area, after sufficient verification in a mock-up facility. For this purpose, the ACPF mock-up facility, which simulates the system, space, and remote handling equipment of the ACPF, is operated separately in the general laboratory area. The inert gas conditioning system of the ACPF consists of very complex piping, blowers, and valves, requires special attention to maintenance. In addition, if there is a small leak in the piping within these valves or piping, radioactive materials can be directly exposed to facility workers, so continuous monitoring and maintenance are required to prevent accident. In this study, the applicability of acoustic emission technology and ultrasonic technology for leak detection in the inert gas conditioning system of ACPF mock-up facility was investigated. For this purpose, new bypass pipes and valves were installed in the existing system to simulate the leakage of pipes and valves. Acoustic emission sensors are attached directly to pipes or valves to detect signals, while ultrasonic sensors are installed at a distance to detect signals. The optimal parameters of each technology to effectively suppress background noise were derived and, and the feasibility of identifying normal and abnormal scenarios in the system was analyzed.

The acoustic emission (AE) method as a passive non-destructive monitoring technique is proposed for real-time monitoring of mechanical degradation in underground structures, such as deep geological disposal of high-level nuclear waste (HLW). This study investigates the low-frequency characteristics of AE signals emitted during the fracturing of meter-scale concrete specimens; uniaxial compression tests (UCT) in a lab scale and Goodman jack (GJ) tests in a 1.3 m-long concrete block were conducted while acquiring the AE signals using low-frequency AE sensors. The results indicate a sharp increase in AE energy emission at approximately 60% and 80% of the yield stresses in the UCT and GJ tests, respectively. The collected AE signals were primarily found in two frequency bands: the 4-28 kHz range and the 56-80 kHz range. High-frequency AE signals were captured more as the stress increased in the GJ tests, which was in contrast to the UCT tests. Furthermore, the AE signals obtained from the Goodman jack tests tended to lower RA values than the UCT results. This study presents unique experimental data with low-frequency AE sensors under different loading conditions, which provides insights into field-scale AE monitoring practices.

The underground environment has an advantage to minimize the external influences because it is isolated space with surrounded rock medium. Therefore, underground rock has been used recently as the target for a disposal system of spent fuel with high-level radioactive. The disposal system mainly consists of natural barrier (i.e., surrounded rock medium) and engineered barrier (i.e., concrete lining, plug, backfill, canister, and buffer). In particular, the engineered barrier is important for long-term storage because it has to preferentially block the leakage of radioactive nuclide. Non-destructive technologies (NDT) have been utilized to monitor the state of disposal system for considering the limitation in deep depth conditions such as limited environment for direct damage inspection. Acoustic emission (AE) monitoring technique is an effective method to monitor the damage (crack) magnitude, history (i.e., crack evolution), and location using high-frequency elastic waves. To apply the AE monitoring method in the disposal system, the characteristics of damaged materials should be considered. The concrete lining has multi-failure behavior (i.e., brittle and ductile) resulted from composition as cement and reinforcing steel bar. Therefore, it important to investigate the AE characteristics according to the failure level of reinforced concrete for damage monitoring of the disposal systems. In this study, the four-point bending tests were carried out to measure the AE signals from the cracking of reinforce concrete specimens in laboratory. The test specimens were prepared with different strength. After the experiment, the AE characteristics were analyzed using the AE parameters with loading and failure state in the curve of time-stress. This study will be helpful for damage monitoring using AE technique in the field of high-level radioactive disposal system.