A Neuro-Fuzzy Approach to Gear System Monitoring

Detection of machine component failure is very important to be properly applied in a maintenance program in industries. The objective of this research is to detect gear fault using wavelet transforms. The vibration signal is acquired with accelerometer mounted at bearing houses of 2 parallel shafts with 2 spur gears (28 tooth). The gears are rotated at 1200 RPM and the spectrum is displayed. The spectrum cannot indicate gear mesh frequencies (GMF), because they are covered with frequencies such as natural and harmonic frequencies of rotating shaft. This research have developed a method to obtain GMF using wavelet decomposition and cross correlation. The results showed that with FFT applied to cross-correlation of wavelet detil components,, spectrum of visible and distinctable GMF has been obtained. 1. Background Gear units are parts of machines serve to transmit speed and torque between two shafts. The units are used in wind turbine [1], automotive and helicopter engines [2]. During using, the gear defects like wear, broken, cracked usually occure. The damage should be detected in a maintenance program. Gear condition monitoring is therefore required in order to improve safety and reduce operating costs. In this research, a rig consists of 2 shafts with 2 gear is constructed. One gear is normal gear while the other has a partially/full toothcut. Electric motor is used to rotate one shaft to 1200 RPM. Vibration signal is then obtained using accelerometer mounted on the bearing house. The signal processing method uses only FFT has disadvantages, i.e. the frequency associated with fault condition must be known first and if the signal has a low signal to noise ratio or there are many other vibration components then peaks correspond to failure frequency cannot be clearly indicated [3, 4]. This research uses wavelet transformation to indicate GMF features so that gear failure i.e. full / partial toothcut gear can be detected. Wavelet-based signal processing for gear fault detection had been investigated by [4] and [5]. Further studies of wavelet transform applications on vibration signals for gear fault detection have been also performed by [6] and [7] that discuss of wavelet decomposition and feature extraction using PCA.

IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics), 2001

An innovative neuro-fuzzy network appropriate for fault detection and classification in a machinery condition health monitoring environment is proposed. The network, called an incremental learning fuzzy neural (ILFN) network, uses localized neurons to represent the distributions of the input space and is trained using a one-pass, on-line, and incremental learning algorithm that is fast and can operate in real time. The ILFN network employs a hybrid supervised and unsupervised learning scheme to generate its prototypes. The network is a self-organized structure with the ability to adaptively learn new classes of failure modes and update its parameters continuously while monitoring a system. To demonstrate the feasibility and effectiveness of the proposed network, numerical simulations have been performed using some well-known benchmark data sets, such as the Fisher's Iris data and the Deterding vowel data set. Comparison studies with other well-known classifiers were performed and the ILFN network was found competitive with or even superior to many existing classifiers. The ILFN network was applied on the vibration data known as Westland data set collected from a U.S. Navy CH-46E helicopter test stand, in order to assess its efficiency in machinery condition health monitoring. Using a simple fast Fourier transform (FFT) technique for feature extraction, the ILFN network has shown promising results. With various torque levels for training the network, 100% correct classification was achieved for the same torque levels of the test data.

Applied Artificial Intelligence, 2017

A hybrid classifier obtained by hybridizing Support Vector Machines (SVM) and Artificial Neural Network (ANN) classifiers is presented here for diagnosis of gear faults. The distinctive features obtained from vibration signals of a running gearbox, which was operated in normal and fault-induced conditions, were used to feed the SVM-ANN hybrid classifier. Time-domain vibration signals were divided in segments. Features such as peaks in time domain and in spectrum, central moments, and standard deviations were obtained from signal segments. Based on the experimental results, it was shown that SVM-ANN hybrid classifier can successfully identify gear condition and that the hybrid SVM-ANN classifier performs much better than standard versions of ANNs and SVM. The effectiveness of the hybrid classifier under noise was also investigated. It was shown that if vibration signals are preprocessed by Discrete Wavelet Transform (DWT), efficacy of the SVM-ANN hybrid is significantly enhanced.

This paper employs the application of the wavelet transform (WT) to non-stationary gear vibration signals to investigate its sensitivity and limitations in detecting different gear faults. The detection and diagnostic capability of the wavelet analysis is compared to the Fourier-based analysis on the basis of experimental results. The artificially created defects included chipped teeth, and broken teeth as examples of local gear faults. In addition, gear distributed faults are also investigated. The sensitivity to fault severity, and to transducer orientation will be investigated. Adaptive Morlet wavelet filters are developed based upon the kurtosis maximization principle. The parameters in the Morlet wavelet function are optimized to match with the nature of the fault feature to be extracted from the different signals. The experimental results considered in this paper, show that the adaptive WT is very effective in the detection of both local and distributed gear faults. The WT is found to be very sensitive to fault severity. In addition the radial signals show more informative results than the axial signals when using either FFT or WT.

Condition based maintenance (CBM) improves decisionmaking performances for a maintenance program through machinery condition monitoring. Therefore, it is a key step to trace machinery health condition for CBM. In this paper, a novel method is proposed to establish a health evaluation index named automatic evaluation index (AEI) and its corresponding dynamic threshold using Wavelet Packet Transform (WPT) and Hidden Markolv Model (HMM). In this process, WPT is used to decompose signal into detail signals and exhibits prominent gear fault features. In addition, HMM employed here is to recognize two concerned states of gear in the whole life validation, including normal gear state and early gear fault state. It is also important to build a dynamic threshold to differentiate the two states automatically. The proposed dynamic threshold not only renews by itself according to the history values of AEI but also easily and automatically detects occurrence of gear early fault. Finally, a set of whole life time data ending in gear failure is used to verify the proposed method effectively. Further, some related parameters included in this method are discussed and the obtained results show that condition monitoring performance of the proposed method is excellent in detection of gear failure.

iaeme

Monitoring of rotating machines by vibration analysis is a topic that has aroused great interest in the field of research in recent years. Moreover, the vibrations from a machine are very affected by the conditions of its operation (speed, load, etc.). Vibration analysis is especially applicable to the monitoring of enclosed systems, such as gearboxes. A significant challenge remains with the monitoring of gears under fluctuating operating conditions. Gear is one of the most important and frequently encountered components in rotating machinery, whose operation condition directly affects the whole performance of rotating machinery. An unexpected fault of gear may cause huge economic losses, even personal injury. Among the techniques used for this purpose is the signal processing. To diagnose early fault of rotating machinery, feature extraction of vibration signals is a very important and difficult research task on engineering. The signal of rotating machinery is usually non-stationary, non-linear, and with strong noise interference, meantime, the early signal energy is too low to extract fault features in time domain. In this paper, the wavelet packet transform (WPT) is applied to the analysis of vibration signals delivered from a rotating machine to detect early the presence of defects. The mother wavelet used is wavelet of Haar

Measurement, 2019

Gear reducer motors play an important role in industry due to their robustness and simplicity of con struction. However, the appearance of faults in these systems can affect the quality of the product and lead to significant financial losses. Therefore, it is necessary to perform Prognostics and Health Management (PHM) for these systems. This paper aims to develop a practical and effective method allow ing an early fault detection and diagnostic for critical components of the gear reducer, in particular gear and bearing defects. This method is based on a new indicator extracted from electrical signals. It allows characterizing different states of the gear reducer, such as healthy state, bearing faults, gear faults, and combined faults. The diagnostic of these states is done by the Adaptive Neuro Fuzzy Inference System (ANFIS). The efficiency and the robustness of the proposed method are highlighted through numerous experimental tests with different levels of loads and speeds.

Advances in Mechanical Engineering

Nowadays, fault detection, identification, and classification seem to be the most difficult challenge for gear systems. It is a complex procedure because the defects affecting gears have the same frequency signature. Thus, the variation in load and speed of the rotating machine will, inevitably, lead to erroneous detection results. Moreover, it is important to discern the nature of the anomaly because each gear defect has several consequences on the mechanism’s performance. In this article, a new intelligent fault diagnosis approach consisting of Autogram combined with radial basis function neural network is proposed. Autogram is a new sophisticated enhancement of the conventional Kurtogram, while radial basis function is used for classification purposes of the gear state. According to this approach, the data signal is decomposed by maximal overlap discrete wavelet packet transform into frequency bands and central frequencies called nodes. Thereafter, the unbiased autocorrelation of...

A new approach of gear fault diagnosis based on continuous wavelet transform is presented. Continuous wavelet transform can provide a finer scale resolution than orthogonal wavelet transform. It is more suitable for extracting mechanical fault information. In this paper, the concept of time-averaged wavelet spectrum (TAWS) based on Morlet continuous wavelet transform is proposed. Two fault diagnosis methods named spectrum comparison method (SCM) and feature energy method (FEM) based on TAWS are established. The results of the application to gearbox gear fault diagnosis show that TAWS can effectively extract gear fault information. The feature energy of the TAWS features the gear fault advancement very well and is conically proportional to the gear fault advancement.

In gearboxes and in all rotating elements in general, gear damage detection is often very critical and can lead to increased safety in aviation and in industry. Therefore the importance for their regular inspection and/or on-line health monitoring is growing and effective diagnostic techniques and methodologies are the objective of research efforts over the last 30 to 40 years. Gearbox is widely used in all industrial applications and hence there are many analytic techniques, which are used to prevent serious damage in a mechanical system. In general, the mechanical components produce abnormal transient signal when a fault condition occurs. These transient signals can be utilized to identify the fault in various conditions. These fault diagnosis techniques are mainly based on sound emission and vibration signals in time and frequency domains, some more advanced studies are continuous wavelet transform and discrete wavelet transform (DWT) can effectively detect weak impulse signals for fault conditions and hence wavelets can be used for the fault diagnosis of gearbox.