Machine Vibration Data Research Articles

Application of Generative Adversarial Network and Diverse Feature Extraction Methods to Enhance Classification Accuracy of Tool-Wear Status

The means of accurately determining tool-wear status has long been important to manufacturers. Tool-wear status classification enables factories to avoid the unnecessary costs incurred by replacing tools too early and to prevent product damage caused by overly worn tools. While researchers have examined this topic for over a decade, most existing studies have focused on model development but have neglected two fundamental issues in machine learning: data imbalance and feature extraction. In view of this, we propose two improvements: (1) using a generative adversarial network to generate realistic computer numerical control machine vibration data to overcome data imbalance and (2) extracting features in the time domain, the frequency domain, and the time–frequency domain simultaneously for modeling and integrating these in an ensemble model. The experiment results demonstrate how both proposed modifications are reasonable and valid.

Holistic process monitoring with machine learning classification methods using internal machine sensors for semi-automatic drilling

Since one third of rivet holes during aircraft assembly are produced with semi-automatic drilling units, in this work reliable and efficient methods for process state prediction using Machine Learning (ML) classification methods were developed for this application. Process states were holistically varied in the experiments, gathering motor current and machine vibration data. These data were used as input to identify the optimal combination of five data feature preparation and nine ML methods for process state prediction. K-nearest-neighbour, decision tree and artificial neural network models provided reliable predictions of the process states: workpiece material, rotational speed, feed, peck-feed amplitude and lubrication state. Data preprocessing through sequential feature selection and principal components analysis proved to be favourably for these applications. The prediction of the workpiece clamping distance revealed frequent misclassifications and thus, was not reliable.

Enhancement of time-frequency post-processing readability for nonstationary signal analysis of rotating machinery: Principle and validation

Rotating machinery signals are often composed of multiple components and are nonstationary under practical time-varying conditions. In most cases, the constituent frequency components are close to each other on time–frequency plane. As such, better time–frequency readability is necessary to discover the underlying physical nature of such complex nonstationary signals. Nevertheless, conventional time–frequency analysis methods suffer from limited time–frequency resolution and/or cross-term interferences, thus cannot achieve desirable time–frequency readability. In recent decades, some time–frequency post-processing methods (such as time–frequency reassignment, synchrosqueezing transform, multi-tapering, concentration of frequency and time, and higher-order synchrosqueezing transform) have been proposed to improve the time–frequency readability from two aspects: reducing cross-term interferences and enhancing time–frequency energy concentration. However, they still surfer from time-frequency blurs for the signal whose time–frequency ridges are close to each other on time–frequency plane. To address this issue, we propose a framework to improve the post-processing methods. Firstly, the Vold-Kalman filter is employed to extract constituent frequency components, by exploiting its capability to separate mono-components. Then, the time–frequency representation (TFR) of each mono-component is obtained via time–frequency post-processing method separately. Finally, the TFR of raw signal is constructed by superposing the TFR of all mono-components. This framework achieves a TFR of high time–frequency resolution, free from cross-term interferences, and therefore better time–frequency readability. As such, it extends time–frequency post-processing methods to analyze complex nonstationary signals. The proposed framework is illustrated through numerical simulation, and validated using typical rotating machine vibration data (including the experimental signals of a planetary gearbox and an induction motor, ground test data of a civil aircraft engine and in-situ measurement of a hydraulic turbine rotor). The analysis results show the good capability of proposed framework to reveal the frequency contents and their time-varying features of complex nonstationary signals.

Online vibration monitoring system for rotating machinery based on 3-axis MEMS accelerometer

This article discusses the design of a rotating machine vibration monitoring system in real time by utilizing a 3-axis accelerometer MEMS sensor. The system consists of 2 main parts, namely, vibration data acquisition system and data analyse system with the principle of wireless data communication. The results of vibration measurements from each three MEMS accelerometer sensors will be forwarded by the Arduino Nano microcontroller to the data collection device, the Arduino Uno microcontroller. Also, the machine rotating speed data acquired by the TCRT5000 speed sensor will be forwarded by the Arduino Pro Mini microcontroller to the same collection device. Data that has been recorded by the collection device is then transmitted to the computer through wireless communication using the Node-MCU device. The Lab View software is used as a machine vibration data display that has previously been processed by the computer in accordance with parameters desired by the user. Testing stability of data transmission with a certain length of time and communication distance is carried out to ensure the measurement results are in accordance with the real-time vibration conditions. Test results show an average delay time of below 200ms for the farthest distance from the wireless device signal range.

Integrated Fault Detection Framework for Classifying Rotating Machine Faults Using Frequency Domain Data Fusion and Artificial Neural Networks

The availability of complex rotating machines is vital for the prevention of catastrophic failures in a significant number of industrial operations. Reliability engineering theories stipulate that optimising the mean-time-to-repair (MTTR) for failed machines can immensely boost availability. In practice, however, a significant amount of time is taken to accurately detect and classify rotor-related anomalies which often negate the drive to achieve a truly robust maintenance decision-making system. Earlier studies have attempted to address these limitations by classifying the poly coherent composite spectra (pCCS) features generated at different machine speeds using principal components analysis (PCA). As valuable as the observations obtained were, the PCA-based classifications applied are linear which may or may not limit their applicability to some real-life machine vibration data that are often associated with certain degrees of non-linearities due to faults. Additionally, the PCA-based faults classification approach used in earlier studies sometimes lack the capability to self-learn which implies that routine machine health classifications would be done manually. The initial parts of the current paper were presented in the form of a thorough search of the literature related to the general concept of data fusion approaches in condition monitoring (CM) of rotation machines. Based on the potentials of pCCS features, the later parts of the article are concerned with the application of the same features for the exploration of a simplified two-staged artificial neural network (ANN) classification approach that could pave the way for the automatic classification of rotating machines faults. This preliminary examination of the classification accuracies of the networks at both stages of the algorithm offered encouraging results, as well as indicates a promising potential for this enhanced approach during field-based condition monitoring of critical rotating machines.

Comparison of machine learning models based on time domain and frequency domain features for faults diagnosis in rotating machines

The development of technologies for the maintenance industry has taken an important role to meet the demanding challenges. One of the important challenges is to predict the defects, if any, in machines as early as possible to manage the machines downtime. The vibration-based condition monitoring (VCM) is well-known for this purpose but requires the human experience and expertise. The machine learning models using the intelligent systems and pattern recognition seem to be the future avenue for machine fault detection without the human expertise. Several such studies are published in the literature. This paper is also on the machine learning model for the different machine faults classification and detection. Here the time domain and frequency domain features derived from the measured machine vibration data are used separated in the development of the machine learning models using the artificial neutral network method. The effectiveness of both the time and frequency domain features based models are compared when they are applied to an experimental rig. The paper presents the proposed machine learning models and their performance in terms of the observations and results.

A data mining approach for machine fault diagnosis based on associated frequency patterns

Bearings play a crucial role in rotational machines and their failure is one of the foremost causes of breakdowns in rotary machinery. Their functionality is directly relevant to the operational performance, service life and efficiency of these machines. Therefore, bearing fault identification is very significant. The accuracy of fault or anomaly detection by the current techniques is not adequate. We propose a data mining-based framework for fault identification and anomaly detection from machine vibration data. In this framework, to capture the useful knowledge from the vibration data stream (VDS), we first pre-process the data using Fast Fourier Transform (FFT) to extract the frequency signature and then build a compact tree called SAFP-tree (sliding window associated frequency pattern tree), and propose a mining algorithm called SAFP. Our SAFP algorithm can mine associated frequency patterns (i.e., fault frequency signatures) in the current window of VDS and use them to identify faults in the bearing data. Finally, SAFP is further enhanced to SAFP-AD for anomaly detection by determining the normal behavior measure (NBM) from the extracted frequency patterns. The results show that our technique is very efficient in identifying faults and detecting anomalies over VDS and can be used for remote machine health diagnosis.

Bearing condition diagnosis and prognosis using applied nonlinear dynamical analysis of machine vibration signal

In this paper, we introduce a modified form of the correlation integral developed by Grassberger and Procaccia referred to as the partial correlation integral, which can be computed in real time. The partial correlation integral algorithm is then used to analyze machine vibration data obtained throughout a life test of a rolling element bearing. From the experimental results, the dimensional exponent (an approximation of the correlation dimension) as computed from the partial correlation integral algorithm tends to increase as time progresses and the useful remaining life of the bearing is decreasing. The dimensional exponents of a healthy bearing and a bearing close to failure are statistically different. We also propose a computational scheme for bearing condition monitoring (diagnosis and prognosis) using the dimensional exponent integrated with a surrogate data testing technique. As a result, we can characterize the condition of the bearing from the results of the surrogate data test and furthermore, we provide some preliminary evidence that the dimensional exponent can be used to predict the failure of rolling element bearings in rotating machinery from real-time vibration data.

An Amplitude Modulation Detector for Fault Diagnosis in Rolling Element Bearings

The purpose of this research is to identify single-point defects in rolling element bearings. These defects produce characteristic fault frequencies that appear in the machine vibration and tend to modulate the machine's frequencies of mechanical resonance. An amplitude modulation (AM) detector is developed to identify these interactions and detect the bearing fault while it is still in an incipient stage of development (i.e., to detect the instances of AM when the magnitude of the characteristic fault frequency itself is not significant). Use of this detector only requires machine vibration from one sensor and knowledge of the bearing characteristic fault frequencies. Computer simulations as well as machine vibration data from bearings containing outer race faults are used to confirm the proficiency of this proposed technique.

Blind source separation of noisy harmonic signals for rotating machine diagnosis

Blind source separation (BSS) consists of recovering signals from different physical sources from several observed combinations independently of the propagation medium. BSS is also a promising tool for non-destructive machine condition monitoring by vibration analysis, as it is intended to retrieve the signature of a single rotating machine from combinations of several working machines. In this way, BSS can be seen as a pre-processing step that improves the diagnosis. BSS methods generally assume observations that are either noise-free or corrupted with spatially distinct white noises. In the latter case, principal component analysis (PCA) is applied as a first step to filter out the noise and whiten the observations. Obviously, the efficiency of the whole separation procedure depends on the accuracy of the first step (PCA). However, in the real world, signals of rotating machine vibration may be severely corrupted with spatially correlated noises and therefore the signal subspace will not be correctly estimated with PCA. The purpose of this paper is to propose a ‘robust-to-noise’ technique for the separation of rotating machine signals. The sources are assumed here to be periodic and so can be modelled as the sum of sinusoids of harmonic frequencies. A new estimator of the signal subspace and the whitening matrix is introduced which exploits the model of sinusoidal sources and uses spectral matrices of delayed observations to eliminate the influence of the noise. After whitening, the second step of source separation remains unchanged. Finally, performance of the algorithm is investigated with artificial data and experimental rotating machine vibration data.

A fuzzy neural network approach to machine condition monitoring

This paper is focused on the implementation of a predictive neural network for use as an operator's aid in the diagnosis of faults with high prediction accuracy in an automated manufacturing environment. In order to evaluate the performance of the model, the network has been tested using both simulated time series and real time machine vibration data collected in lab experiments.

An ARTMAP neural network‐based machine condition monitoring system

Presents a real‐time neural network‐based condition monitoring system for rotating mechanical equipment. At its core is an ARTMAP neural network, which continually monitors machine vibration data, as it becomes available, in an effort to pinpoint new information about the machine condition. As new faults are encountered, the network weights can be automatically and incrementally adapted to incorporate information necessary to identify the fault in the future. Describes the design, operation, and performance of the diagnostic system. The system was able to identify the presence of fault conditions with 100 percent accuracy on both lab and industrial data after minimal training; the accuracy of the fault classification (when trained to recognize multiple faults) was greater than 90 percent.

Application of wavelet transforms to compression of mechanical vibration data

To detect abnormality of rotating machines in factories and power generating plants, the vibration data of the machines are used as a guide to express abnormal phenomena. In order to improve the diagnostic accuracy of the rotating machine diagnostic system, the storage and analysis of a large amount of vibration data is important. For efficient data storage and transmission, data compression is indispensable. In this paper, with a view to reducing data storage capacity and the transmission capacity in the rotating machine diagnostic system, compression of machine vibration data is attempted. In the proposed compression system, wavelet transforms are used so that the distortion generated in compression and reconstruction have minimal effect on the diagnostics. Considering the mode of system usage, a compression system is proposed that maximizes the compression ratio at allowable distortions. In order to evaluate the overall performance of the proposed compression system, data compression by several orthogonal wavelets composed of Daubechies bases and those generated by DCT (discrete cosine transform) are compared. It is shown that the system using the wavelet with a higher-order tap has the highest compression performance and that the compression factor is about 3 to 8 in the allowable distortion range of 1 to 10%. © 1998 Scripta Technica, Electron Comm Jpn Pt 3, 81(10): 16–25, 1998

Application of wavelet transforms to compression of mechanical vibration data

To detect abnormality of rotating machines in factories and power generating plants, the vibration data of the machines are used as a guide to express abnormal phenomena. In order to improve the diagnostic accuracy of the rotating machine diagnostic system, the storage and analysis of a large amount of vibration data is important. For efficient data storage and transmission, data compression is indispensable. In this paper, with a view to reducing data storage capacity and the transmission capacity in the rotating machine diagnostic system, compression of machine vibration data is attempted. In the proposed compression system, wavelet transforms are used so that the distortion generated in compression and reconstruction have minimal effect on the diagnostics. Considering the mode of system usage, a compression system is proposed that maximizes the compression ratio at allowable distortions. In order to evaluate the overall performance of the proposed compression system, data compression by several orthogonal wavelets composed of Daubechies bases and those generated by DCT (discrete cosine transform) are compared. It is shown that the system using the wavelet with a higher-order tap has the highest compression performance and that the compression factor is about 3 to 8 in the allowable distortion range of 1 to 10%. © 1998 Scripta Technica, Electron Comm Jpn Pt 3, 81(10): 16–25, 1998