Vibration signature analysis by hybrid multi-layer neuro-fuzzy system (original) (raw)
Related papers
Fault Diagnosis in Rotating Machine Using Full Spectrum of Vibration and Fuzzy Logic
2017
Industries are always looking for more efficient maintenance systems to minimize machine downtime and productivity liabilities. Among several approaches, artificial intelligence techniques have been increasingly applied to machine diagnosis. Current paper forwards the development of a system for the diagnosis of mechanical faults in the rotating structures of machines, based on fuzzy logic, using rules foregrounded on the full spectrum of the machine ́s complex vibration signal. The diagnostic system was developed in Matlab and it was applied to a rotor test rig where different faults were introduced. Results showed that the diagnostic system based on full spectra and fuzzy logic is capable of identifying with precision different types of faults, which have similar half spectrum. The methodology has a great potential to be implemented in predictive maintenance programs in industries and may be expanded to include the identification of other types of faults not covered in the case st...
Identify and classify vibration fault based on artificial intelligence techniques
Journal of theoretical and applied information technology, 2016
Steam turbines (ST) need to be protected from damaging faults in the event it ends up in a danger zone. Some examples of faults include vibration, thrust, and eccentricity. Vibration fault represents one of the challenges to designers, as it could cause massive damages and its fault signal is rather complex. Researches in the field intend to prevent or diagnose vibration faults early in order to reduce the cost of maintenance and improve the reliability of machine production. This work aims to diagnose and classify vibration faults by utilized many schemes of Artificial Intelligence (AI) technique and signal processing, such as Fuzzy logic-Sugeno FIS (FLS), Back Propagation Neural Network (BPNN) hybrid with FL-Sugeno (NFS), and BPNN hybrid with FL-Mamdani FIS (NFM). The signal of the fault and the design of the FL and NN were done using MATLB. The results will be compared based on its ability to feed the output signal to the control system without disturbing system behavior. The res...
Vibration fault detection and classifaction based on the fft and fuzzy logic
ARPN journal of engineering and applied sciences, 2016
Vibration fault exhibit a multifaceted and nonlinear behavior generation in rotated machines, for example in a steam turbine (ST). Vibration fault (VF) is collectedin the form of acceleration, velocity, and displacement via the vibration sensor. This fault damages the turbines if it strays into the danger zone. This paper first models the VF in a time domain to transfer the frequency domain via an FFT technique. The signals were applied to the fuzzy system to be used by the VF for classification via sugeno and mamdani Fuzzy Inference System (FIS) to generate the signal that will reflect the VF in the event it is embedded into the protection system. The Membership Function (MF) sets depends on practical work in a power plant, and the ISO is interested in ST vibration zones. The outcomes of the sugeno fuzzy property is the generation of stable and usable signals that can be used within the protection system, mostly owing to its efficiency in detecting vibrational faults. The results f...
Asia Pacific Journal of Multidisciplinary Research, 2017
Safety, reliability, efficiency and performance of rotating machinery in all industrial applications are the main concerns. Rotating machines are widely used in various industrial applications. Condition monitoring and fault diagnosis of rotating machinery faults are very important and often complex and labor-intensive. Feature extraction techniques play a vital role for a reliable, effective and efficient feature extraction for the diagnosis of rotating machinery. Therefore, developing effective bearing fault diagnostic method using different fault features at different steps becomes more attractive. Bearings are widely used in medical applications, food processing industries, semiconductor industries, paper making industries and aircraft components. This paper review has demonstrated that the latest reviews applied to rotating machinery on the available a variety of vibration feature extraction. Generally literature is classified into two main groups: frequency domain, time frequency analysis. However, fault detection and diagnosis of rotating machine vibration signal processing methods to present their own limitations. In practice, most healthy ingredients faulty vibration signal from background noise and mechanical vibration signals are buried. This paper also reviews that how the advanced signal processing methods, empirical mode decomposition and interference cancellation algorithm has been investigated and developed. The condition for rotating machines based rehabilitation, prevent failures increase the availability and reduce the cost of maintenance is becoming necessary too. Rotating machine fault detection and diagnostics in developing algorithms signal processing based on a key problem is the fault feature extraction or quantification. Currently, vibration signal, fault detection and diagnosis of rotating machinery based techniques most widely used techniques. Furthermore, the researchers are widely interested to make automatic procedures for fault extraction techniques. Such expert systems, neural networks, artificial intelligence and system devices and most powerful methods described above in conjunction with some of the techniques being used fuzzy inference system.
An Expert System for Rotating Machine Fault Detection Using Vibration Signal Analysis
Sensors
Accurate and early detection of machine faults is an important step in the preventive maintenance of industrial enterprises. It is essential to avoid unexpected downtime as well as to ensure the reliability of equipment and safety of humans. In the case of rotating machines, significant information about machine’s health and condition is present in the spectrum of its vibration signal. This work proposes a fault detection system of rotating machines using vibration signal analysis. First, a dataset of 3-dimensional vibration signals is acquired from large induction motors representing healthy and faulty states. The signal conditioning is performed using empirical mode decomposition technique. Next, multi-domain feature extraction is done to obtain various combinations of most discriminant temporal and spectral features from the denoised signals. Finally, the classification step is performed with various kernel settings of multiple classifiers including support vector machines, K-nea...
Vibration based Fault Diagnosis Techniques for Rotating Mechanical Components: Review Paper
IOP Conference Series: Materials Science and Engineering, 2018
A rotating mechanical components in machineries like bearings, gears, pulleys, belt drives etc. are major components in any rotating machinery. The failure of these components leads to downtime of machines and reduction in production. Significant economic losses will be caused due to an unexpected failure of these components. Belt drives are widely employed in various industrial equipment. Finding the early fault symptoms in the belt drive is very important. This can be achieved by various methods. For detecting faults and monitoring the condition of a belt drive, the vibration signal can be used as one of the parameter. Thus, vibration signal can be used as a procedure for predictive maintenance and it is used for machinery maintenance decisions. The changes in vibration signals due to fault can be detected by employing signal processing methods. It can be used to evaluate the health status of the machinery. The nature and severity of the problem can be determined by analysing the vibration signal and hence the failure can be predicted. Signature of the fault in the machine is carried by the vibration signal. It is possible to have early fault detection by analysing these vibration signals. Different signal processing techniques are used for processing these signals. The various techniques used for fault diagnosis based on vibration analysis method are discussed in this paper. The application of the artificial intelligence techniques such as Artificial Neural Network (ANN), fuzzy sets and other emerging technologies are discussed.
Insight - Non-Destructive Testing and Condition Monitoring, 2010
This paper presents an intelligent method for fault diagnosis of the starter motor of an agricultural tractor, based on vibration signals and an Adaptive Neuro-Fuzzy Inference System (ANFIS). The starter motor conditions to be considered were healthy, crack in rotor body, unbalancing in driven shaft and wear in bearing. Thirty-three statistical parameters of vibration signals in the time and frequency domains were selected as a feature source for fault diagnosis. A data mining filtering method was performed in order to extract the superior features among the primary thirtythree features for the classification process and to reduce the dimension of features. In this study, six superior features were fed into an adaptive neuro-fuzzy inference system as input vectors. Performance of the system was validated by applying the testing data set to the trained ANFIS model. According to the result, total classification accuracy was 86.67%. This shows that the system has great potential to serve as an intelligent fault diagnosis system in real applications.
An effective neuro-fuzzy paradigm for machinery condition health monitoring
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.
Fault Classification using Pseudomodal Energies and Neuro-fuzzy modelling
2007
This paper presents a fault classification method which makes use of a Takagi-Sugeno neuro-fuzzy model and Pseudomodal energies calculated from the vibration signals of cylindrical shells. The calculation of Pseudomodal Energies, for the purposes of condition monitoring, has previously been found to be an accurate method of extracting features from vibration signals. This calculation is therefore used to extract features from vibration signals obtained from a diverse population of cylindrical shells. Some of the cylinders in the population have faults in different substructures. The pseudomodal energies calculated from the vibration signals are then used as inputs to a neuro-fuzzy model. A leave-one-out cross-validation process is used to test the performance of the model. It is found that the neuro-fuzzy model is able to classify faults with an accuracy of 91.62%, which is higher than the previously used multilayer perceptron.
Rotating Machine Fault Detection based on Fuzzy Logic and Improved Adaptive Filter
International Journal of Mechanical Engineering and Robotics Research
The rotating machine contains the many rotating parts and one rotating part produces additional noise to the others. As a result, fault signatures of the rotating machine are turned out to be quite weak. This paper proposed an effective method to detect the fault signatures of rotating machines based on improved adaptive filter, fuzzy logic and spectrum analysis. An improved adaptive filter is used to remove the noises from the faulty signal. Since the performance of the adaptive filter depends on the step size, a new technique is proposed to select the step size effectively based on entropy and fuzzy logic. To determine the fault signature of rotating machines of vibration signals effectively, demodulation is often required. Both squared envelope and Hilbert based envelope analysis are performed to identify the fault signature accurately. The effectiveness of the proposed adaptive filter is shown by simulation. Performances of the improved adaptive are also verified by real experimental data. Experimental results show that the proposed method can effectively detect the fault signatures of the rotating machines.