• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.3 no.3
• /
• pp.11-16
• /
• 2004

In this study, the characteristics of signals such as acoustic emission, vibration amplitude and noise level which are derived from the abnormal condition of compressor are investigated. The normal condition, vane stick sound and roller defect condition are chosen to analyze the signal in each cases. From the feature extraction of each signals, the dominant parameters of each signals which can identify the abnormal condition are suggested.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.5
• /
• pp.51-57
• /
• 1995

In this paper, we study a noise-robust feature extraction method of speech signal based on auditory modeling. The auditory model consists of a basilar membrane, a hair cell model and spectrum output stage. Basilar membrane model describes a response characteristic of membrane according to vibration in speech wave, and is represented as a band-pass filter bank. Hair cell model describes a neural transduction according to displacements of the basilar membrane. It responds adaptively to relative values of input and plays an important role for noise-robustness. Spectrum output stage constructs a mean rate spectrum using the average firing rate of each channel. And we extract feature vectors using a mean rate spectrum. Simulation results show that when auditory-based feature extraction is used, the speech recognition performance in noisy environments is improved compared to other feature extraction methods.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2010.10a
• /
• pp.236-241
• /
• 2010

This paper presents a wear diagnosis method for centrifugal impellers by using an accelerometer. The features are calculated from raw and wavelet transformed signals with several statistical methods applied in time or frequency domains. From the effectiveness coefficient test, it is shown that 7th level of wavelet transformed signal is suitable for wear classification problems. A neural network with 5 feature sets is applied to diagnose the wear magnitude of pump impellers. The verification result reveals that high accuracy for the wear diagnosis of impellers can be obtained by using wavelet features transformed from acceleration signals.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.23 no.9
• /
• pp.814-822
• /
• 2013

For the fault diagnosis of a mechanical system, pattern recognition methods have being used frequently in recent research. Hidden Markov model(HMM) and artificial neural network(ANN) are typical examples of pattern recognition methods employed for the fault diagnosis of a mechanical system. In this paper, a hybrid method that combines HMM and ANN for the fault diagnosis of a mechanical system is introduced. A rotating blade which is used for a wind turbine is employed for the fault diagnosis. Using the HMM/ANN hybrid model along with the numerical model of the rotating blade, the location and depth of a crack as well as its presence are identified. Also the effect of signal to noise ratio, crack location and crack size on the success rate of the identification is investigated.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2004.05a
• /
• pp.1047-1051
• /
• 2004

Charge amplifier systems benefit from the very wide dynamic range of PE accelerometers by offering flexibility in adjusting the electrical output characteristics such as sensitivity and range. They are well suited for operation at high temperatures. Modern charge systems feature improved low noise operation, simplified digital controls, and dual mode operation for operation with charge or IEPE voltage mode sensors. high impedance circuitry is not well suited for operation in adverse field or factory environments. The resolution of a PE accelerometer may not be specified or known since noise is a system consideration determined by cable length and amplifier gain. IEPE accelerometrs operate from a constant current power source, provide a high-voltage, low-impedance, fixed mV/g output. They operate through long, ordinary, coaxial cable in adverse environments without degradation of signal quality. They have limited high temperature range. IEPE sensors are simple to operate. Both resolution and operating range are defined specifications. Cost perchannel is lower compared to PE systems since low-noise cable and charge amplifiers are not required.

• International Journal of Aeronautical and Space Sciences
• /
• v.5 no.1
• /
• pp.39-45
• /
• 2004

The vibration characteristics of rotating machinery are directly related withits condition such as rotor types, thereby it should be acquired the information fromthe vibration signal so that operating conditions may be rationally decided.Accordingly, the study is to focus on developing the analysis for identifying theoperational feature of rotor systems. For this purpose the complex frequencyanalysis for identification, which utilizes the directionaI spectrum for effectiveidentification of rotor systems, is introduced. From this proposed method, theanalysis of dynamic model of the rotors is performed including the stabilitybehavior of the general rotor by Ftoquet theory. Through this process theexcitation methodology to identify the types of rotors is investigated and theeffective way to identification is also suggested.

• Smart Structures and Systems
• /
• v.2 no.1
• /
• pp.47-60
• /
• 2006

Bi-spectrum is a tool in the signal processing for identification of non-linear dynamic behvaiour in systems, and well-known for stationary system where components are non-linearly interacting. Breathing of a crack during shaft rotation is also exhibits a non-linear behaviour. The crack is known to generate 2X (twice the machine RPM) and higher harmonics in addition to 1X component in the shaft response during its rotation. Misaligned shaft also shows similar such feature as a crack in a shaft. The bi-spectrum method has now been applied on a small rotating rig to observe its features. The bi-spectrum results are found to be encouraging to distinguish these faults based on few experiments conducted on a small rig. The results are presented here.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.1 no.2
• /
• pp.49-59
• /
• 1993

A new signal processing technique is applied to four-cylinder spark and compression ignition engines for the diagnosis of power faults inside the cylinders. This technique utilizes two-sided directional power spectra(예S) of complex vibration signals measured from engine blocks as the patterns for engine cylinder power faults. The dPSs feature that they give not only the frequency contents but also the directivity of the engine block motion. For the automatic detection/diagnosis of cylinder power faults, pattern recognition method using multi-layer neural networks is employed. Experimental results show that the sucess rate for diagnosis of cylinder power faults using dPSs is higher than that using the conventional one-sided power spectra. The proposed technique is also tested to check the robustness to the sensor position and the engine rotational speed.

• The KSFM Journal of Fluid Machinery
• /
• v.7 no.2 s.23
• /
• pp.41-49
• /
• 2004

Condition monitoring is very important in turbo machinery because single failure could cause critical damages to its plant. So, automatic fault recognition has been one of the main research topics in condition monitoring area. We have used a relatively new fault recognition method, Hidden Markov Model(HMM), for mechanical system. It has been widely used in speech recognition, however, its application to fault recognition of mechanical signal has been very limited despite its good potential. In this paper, discrete HMM(DHMM) was used to recognize the faults of rotor system to study its fault recognition ability. We set up a rotor kit under unbalance and oil whirl conditions and sampled vibration signals of two failure conditions. DHMMS of each failure condition were trained using sampled signals. Next, we changed the setup and the rotating speed of the rotor kit. We sampled vibration signals and each DHMM was applied to these sampled data. It was found that DHMMs trained by data of one rotating speed have shown good fault recognition ability in spite of lack of training data, but DHMMs trained by data of four different rotating speeds have shown better robustness.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2005.05a
• /
• pp.462-467
• /
• 2005

This paper presents virtual machining system in order to realize turning process in virtual space. A reliable virtual turning process simulation was developed based on the surface shaping system which is capable of considering geometric model, thermal error model, and vibration model. Accuracy of surface shape resulting from proposed machining simulator was verified experimentally. This paper also developed the watchdog agent that continuously assessed, diagnosed, and predicted performance of products and machines in machining. The Watchdog agent extracted feature signal using time-frequency analysis among various signals from multi-sensor and evaluated machining condition using performance confidence value.