Search

Traditional bearing sensory diagnostic include touching and hearing rely on personal experience, and for more complex system are unable to meet the needs of equipment fault diagnosis. The research on bearing fault diagnosis is developing significantly. Bearings are used in rotating machinery and most machinery failures are caused by bearing failures. The fault diagnosis of bearings is an important research area. The core of bearing fault diagnosis is the pattern recognition of fault features. The key of pattern recognition is to develop a reasonable classifier. Intelligent pattern recognition has been developed such as principal components, support vector machine, neural network. In this study, a bearing fault diagnosis based on exploring pattern recognition is proposed. The key to pattern recognition is to design a significant classifier. A number of features from bearing vibration of normal and fault bearing are extracted and processed using principal components of correlation matrix. Plot of principal components shows the visualization of normal and fault bearing and the classifier is chosen subjectively. The principal components exploration will be confirmed using least squares support vector machine. The parameter of support vector machine estimated using heuristic optimization particle swarm optimization. The proposed method can be applied in the detection of faults of bearing. [ABSTRACT FROM AUTHOR]

Original data of bogie faults is hardly obtained by a real experimental because a failure bogie system will make the train suffer from serious danger. Therefore a simulation train dynamics often used to simulate a bogie to obtain failure data. A high speed train is a multi body system which includes train body, bogie frameworks and wheels. This paper focused on bearing vibration analysis using data obtained from bearing simulation. A fault simulation platform was adopted as the experimental device. Data collection was conducted to normal state, inner fault, outer fault and rolling fault. Each fault was collected under the rotation of 300 rpm, 10 groups of data were collected of 10 second for.1 second of measurements. It is the objective of bogie fault characterization to develop an accurate diagnosis method. Deep neural network was proposed for fault diagnosis of bogie bearing. Features, time domain and frquency domain, should be extrcted prior to fault diagnosis. Sixteen time and frequency feature domains are used in fault characterization. This paper proposes bearing simulation methodology to explore diagnosis of bearing bogie faults. The simulation is based on mechanical modeling, lifetime of bearing can be determined. Lifetime data with operating conditions are modeled using Weibull regression, and then remaining life of bearing can be predicted. Multivariate analysis is propsed to characterized the bogie bearing faults. Neural networks is proposed to explore the characterization of bogie fault diagnosis and compared to multivariate analysis. [ABSTRACT FROM AUTHOR]

Pronostia FEMTO-ST is an experimental platform enables testing and validating related to bearing prognostic. Pronostia provides vibration acceleration. Bearing is one of the most critical component in rotating machinery, and it's failure may lead to catastrophic accidents. This paper proposes a survival regression to explore the reliability of bearings. The response is the survival time and the predctors are the bearing features extraction. A Cox and Weibull regression are used to evaluate the reliabilty. The training step is used to build a bearing regression model by estimating the regression coefficient. The results show that the proposed method can be used to predict the reability of the bearing. [ABSTRACT FROM AUTHOR]

Bogie bearings performances directly influences the safety of the train. Diagnosis aims to detect the bearing failure, prognosis aims to predict the remaining life of a bearing. This study concerns on bogie bearings prognosis using survival function. Bearing health monitoring providing information of the system state evolved rapidly over the past decade. Root mean square is an efficient indicator of bearing degradation for inspection and maintenance. Numerous degradation models have been developed. However, the failure regression for bearing degradation is not yet well explored. The residual life provides a prediction for future operation has grown as a significant issue for bearing health condition. This article explores the failure regression modeling for bearing degradation. In the industry, bearings operate at different rotation and load conditions. The developed models for bearing residual's life are limited to a single operating condition. Failure regression considers both rotation and load as operating conditions. Root mean square or kurtosis (time domain features) are extracted and used as bearing degradation indicators. Femto technology developed experimental platform that provides time to failure in specific conditions of operating. horizontal and vertical vibrations are measured every 10 s at 25.6 KHz by accelerometers. The time to failure is observed for bearing under three speed and three load conditions. The speed and load are considered as covariates in failure regression. The failure regression yields the bearing reliability, and this conditional reliability is used to calculate the bearing residual life. In the practice, bearing can be operated at different speeds, loads and operating conditions. The effect of internal and external covariates needs to be explored in order to provide better residual life prediction and to optimize to maintenance strategy. Failure regression can be considered as a tool for bearing residual life prediction in presence of internal and external covariates. [ABSTRACT FROM AUTHOR]

Starting from a new condition a bearing will operate at a particular level of performance. The degradation process occurs as its use progress. Degradation can be regarded as two-state processes, the first one is a normal process and the second one is the degradation process. Identifying the initiation point of degradation is an important issue in power generation insurance. Support vector regression is a linear combination of training patterns depends on Lagrange multipliers which act as forces pushing prediction toward target responses. Only nonzero values are significant in forecasting the regression curve. This paper aims to explore the application of support vector regression in identifying the starting point of bearing degradation. One point outside of the action line is considered as the initial point of the degradation. The bearing vibration obtained from FEMTO website consist of training and testing dataset from three condition of bearing experiments. The training dataset is used to estimate the action line, and the testing dataset used to identify the initial point of degradation. [ABSTRACT FROM AUTHOR]

This study aims to investigate the Indonesia business cycle encompassing the determination of smoothing parameter (λ) on Hodrick-Prescott filter. Subsequently, the components of the filter output cycles were analyzed using a spectral method useful to know its characteristics, and Markov switching regime modeling is made to forecast the probability recession and expansion regimes. The data used in the study is real GDP (1983Q1 - 2016Q2). The results of the study are: a) Hodrick-Prescott filter on real GDP of Indonesia to be optimal when the value of the smoothing parameter is 988.474, b) Indonesia business cycle has amplitude varies between ± 0.0071 to ± 0.01024, and the duration is between 4 to 22 quarters, c) the business cycle can be modelled by MSIV-AR (2) but regime periodization is generated this model not perfect exactly with real regime periodzation, and d) Based on the model MSIV-AR (2) obtained long-term probabilities in the expansion regime: 0.4858 and in the recession regime: 0.5142. [ABSTRACT FROM AUTHOR]