Search

In the present paper, acoustic emission was studied in honing experiments obtained with different abrasive densities, 15, 30, 45 and 60. In addition, 2D and 3D roughness, material removal rate and tool wear were determined. In order to treat the sound signal emitted during the machining process, two methods of analysis were compared: Fast Fourier Transform (FFT) and Hilbert Huang Transform (HHT). When density 15 is used, the number of cutting grains is insufficient to provide correct cutting, while clogging appears with densities 45 and 60. The results were confirmed by means of treatment of the sound signal. In addition, a new parameter S was defined as the relationship between energy in low and high frequencies contained within the emitted sound. The selected density of 30 corresponds to S values between 0.1 and 1. Correct cutting operations in honing processes are dependent on the density of the abrasive employed. The density value to be used can be selected by means of measurement and analysis of acoustic emissions during the honing operation. Thus, honing processes can be monitored without needing to stop the process. [ABSTRACT FROM AUTHOR]

Faults such as misalignment, rotor cracks and rotor to stator rub can exist collectively in rotor bearing systems. It is an important task for rotor dynamic personnel to monitor and detect faults in rotating machinery. In this paper, the rotor startup vibrations are utilized to solve the fault identification problem using time frequency techniques. Numerical simulations are performed through finite element analysis of the rotor bearing system with individual and collective combinations of faults as mentioned above. Three signal processing tools namely Short Time Fourier Transform (STFT), Continuous Wavelet Transform (CWT) and Hilbert Huang Transform (HHT) are compared to evaluate their detection performance. The effect of addition of Signal to Noise ratio (SNR) on three time frequency techniques is presented. The comparative study is focused towards detecting the least possible level of the fault induced and the computational time consumed. The computation time consumed by HHT is very less when compared to CWT based diagnosis. However, for noisy data CWT is more preferred over HHT. To identify fault characteristics using wavelets a procedure to adjust resolution of the mother wavelet is presented in detail. Experiments are conducted to obtain the run-up data of a rotor bearing setup for diagnosis of shaft misalignment and rotor stator rubbing faults. [ABSTRACT FROM AUTHOR]

• Novel hybrid CNN-MPL model-based bearing faults diagnosis method has high accuracy. • Mixed input processing allows increasing the detection accuracy for bearing faults. • Measured accelerations from the rotating shaft are tightly base for diagnosis. • Angular acceleration of the rotating shaft is highly sensitive to bearing faults. Rolling bearings are one of the most widely used bearings in industrial machines. The technical condition of the rolling bearings has a significant impact on the total condition of rotating machinery. Typically, the rolling bearing condition monitoring is based on signal processing from accelerometers mounted on the machine housing. AI-based signal processing methods allow achieving high results in the diagnosis of rolling bearings. Moreover, hybrid NN-based signal processing methods provide the best diagnostic results. However, the diagnostic value of each signal from the housing-mounted accelerometers is highly depend on the location of the corresponding accelerometer. On the other hand, mounting a sensor on the rotating shaft allows expanding and increasing the signal diagnostic value. This paper proposes a novel hybrid CNN-MLP model-based diagnostic method which combines mixed input to perform rolling bearing diagnostics. The method successfully detects and localizes bearing defects using acceleration data from a wireless acceleration sensor which is mounted on a rotating shaft of the machine. The detection and localization efficiency of the hybrid model with various size datasets (more than 27 k samples and about 1900 samples) for training was estimated. Moreover, the detection and localization efficiency of the trained hybrid model with a dataset of another shaft rotating speed for testing was estimated. The experimental results show that applying the hybrid model allows detecting and localizing the bearing faults with up to 99.6% accuracy. [ABSTRACT FROM AUTHOR]

Abstract: Aiming at more efficient fault diagnosis, this research work presents an integrated anomaly detection approach for seeded bearing faults. Vibration signals from normal bearings and bearings with three different fault locations, as well as different fault sizes and loading conditions are examined. The Empirical Mode Decomposition and the Hilbert Huang transform are employed for the extraction of a compact feature set. Then, a hybrid ensemble detector is trained using data coming only from the normal bearings and it is successfully applied for the detection of any deviation from the normal condition. The results prove the potential use of the proposed scheme as a first stage of an alarm signalling system for the detection of bearing faults irrespective of their loading condition. [Copyright &y& Elsevier]