Fault Detection of a Spherical Tank Using a Genetic Algorithm-Based Hybrid Feature Pool and k-Nearest Neighbor Algorithm

An improved mathematical model describing acoustic emission (AE) signals generated by different types of partial discharges (PD) that occur in electric power transformer insulation system is presented in the paper. AE signals are analyzed within the AE method as applied for power transformer failure detection due to occurrence of PD. There are several types of basic defects, which are characterized by different types of PD. The mathematical model presented here is crucial for numerical analyses and simulations, where it acts as the function describing the acoustic source in an acoustic model of power transformer insulation system. The regression procedure was performed based on empirical AE signals, registered in a laboratory experiment. The AE signals are described by a mathematical model being a multi-parameter function, which involve both the time domain and the frequency domain. Goodness of the model was evaluated based on analysis of 480 data samples in the time, frequency and time-frequency domains. Also coherence between the registered and modeled signals was calculated. It was stated that the improved model fits very well to the real data, although, due to high level of noise embodied in signals registered in experiments, the coherence values remain low. Moreover, analyses of the estimated data were performed and some example results are presented in this paper. Based on the achieved outcomes a collection of parameter values was prepared for each of the eight considered PD basic types. One can simple use it now in a numerical model for simulation of AE signal source generated by specified type of PD, what corresponds to a particular power transformer insulation system failure. Furthermore, the regression procedure presented in this paper can be easily transferred to any other types of AE sources including processes of compression, tension and cracking.

In order to detect acoustic emission (AE) signals which are transient elastic waves generated by rapid release of strain energy derived from deformation in materials etc., general AE sensors were fabricated by using a piezoelectric film for detection of AE signals. However, these sensors required frequency domain analysis after recording AE signal. Therefore, this research has been developing an AE sensor integrated with cantilever array with different resonant frequencies for detection of AE signals divided into frequency domain by using MEMS techniques. In this paper, a design of cantilever structures was executed. Theoretical analysis and simulation using ANSYS software revealed that a resonant frequency of a cantilever was increased with decrease of its length in the range from 100 k to 1 MHz. Therefore, fabrication and frequency characterization of a cantilever array fabricated in our batch fabrication process were executed.

The goal of this study is to classify Acoustic Emission (AE) signals based on their characteristics into several fracture types. AE method allows us to classify the damage process of CFRP with machine learning. However, unsupervised learning was often applied for classification which required manually matching the resulting clusters to specific damage types. In contrast, supervised learning to AE signals can automatically determine the damage types. A supervised learning technique uses many AE signals corresponding to each damage mode (supervised signals) in advance. In this study, supervised signals for Mode I and Mode II delamination were extracted from AE signals generated during Double Cantilever Beam (DCB) and Short Beam (SB) tests, respectively. While these delamination modes are dominant in each test, AE signals from other damage types, such as matrix cracking and fiber breakage, are also present. To account for this, additional AE data were obtained from tensile and three-point bending tests, where such damage is dominant. Finally, principal component analysis (PCA) was applied to visualize the distribution of AE signals. The results showed that AE signals from DCB and SB formed distinct clusters, while some overlapped with clusters from tensile and three-point bending signals. This suggests that by excluding overlapping clusters, it is possible to extract features that are more specific to Mode I and Mode II delamination.

Acoustic emission signal analysis during chip formation process in high speed machining of 7050-T7451 aluminum alloy and Inconel 718 superalloy

A novel machine learning-based model is introduced in this research paper to forecast tool wear using acoustic emission (AE) signals. Adaptive boosting (AdaBoost) and a sophisticated feature engineering strategy are employed by the model to enhance the precision of its predictions. The proposed model, Machine Learning Tool Wear Prediction (MLTWP), analyzes AE signals generated during machining operations to distinguish between healthy and worn-out tool conditions with remarkable accuracy. The crux of our approach consists of meticulously eliminating and enhancing the temporal and spectral characteristics of the AE signals. We employ the Kolmogorov-Smirnov test to identify the most valuable classification features. We implemented AdaBoost with the objective of progressively enhancing a set of weak classifiers’ ability to identify instances that were incorrectly classified in previous iterations. Utilizing this method increases the model’s sensitivity to minute variations in tool wear conditions and its overall classification precision. The MLTWP model underwent extensive testing on a benchmark data set comprising 25,304 AE signal records from cutting mill tools, using a training tool split of 9,989 worn (positive) and 8,990 benign (negative) instances. The results of our experiments, validated through four-fold cross-validation, indicate that the MLTWP model exhibits superior performance compared to the existing Tool Wear Prediction using Acoustic Emission Signals (TWPAE) model. To provide greater specificity, the MLTWP exhibited the following metrics on average: precision (92.2%), specificity (91.38%), sensitivity (90.42%), accuracy (90.9%), and MCC (81.72%). The fact that these metrics exhibit significant improvement over those of the TWPAE model demonstrates that our method of feature engineering and adaptive boosting is effective at precisely predicting tool wear. This research not only advances the existing understanding of tool wear prediction but also establishes a robust framework for the implementation of machine learning in manufacturing predictive maintenance.

A multisignal nanosecond synchronous acquisition system to measure acoustic emission (AE) and electromagnetic radiation (EMR) generated during the process of loading and failure of coal and rock samples is established. The correlation between the energy of the AE and EMR signals and the loading stress of outburst coal-rock samples was studied, and the characteristics of the AE and EMR signals during the process of loading and fracturing the outburst coal and rock samples were analyzed. The results show that (1) before the failure of the outburst coal and rock samples, the fluctuation of the AE and EMR signals is the largest, with the same rising and falling trend, and the intensity is not strictly positively correlated, with the phenomenon of low EMR when the AE intensity is high; (2) the EMR and AE deviation degree and frequency exhibit a good response to coal and rock fracturing. The correlation between EMR and stress drop is stronger than that of AE, and the AE signal is richer than the EMR signal. The results show that it is feasible to develop combined AE and EMR early warning technology to improve the early forecasting accuracy of coal and gas outbursts.

There is considerable interest in techniques for ensuring the quality of the laser joining process. One approach to quality monitoring is through analysis of acoustic and optical emission signals acquired during welding. Preliminary analyses confirm that these signals fluctuate chaotically, suggesting that there may be benefits to a nonlinear signal processing approach. Lyapunov exponents of cleaned signals were calculated to quantify the nonlinear nature of the process. Inspection of Lyapunov exponents calculated from optical and acoustic emission signals corresponding to a variety of weld penetration conditions revealed that no sharp distinction could be found. The Lyapunov exponents were found to depend strongly on the power and travel speed settings of the process. This variation masked any variations due solely to weld penetration. There was some distinction in Lyapunov exponents noted between non-gap and gap butt joint welds. The Lyapunov exponent for butt welds with significant joint gap was higher than for non-gapped welds. It was concluded that monitoring of weld gap might be possible using the Lyapunov exponent of the optical and/or acoustic signals.There is considerable interest in techniques for ensuring the quality of the laser joining process. One approach to quality monitoring is through analysis of acoustic and optical emission signals acquired during welding. Preliminary analyses confirm that these signals fluctuate chaotically, suggesting that there may be benefits to a nonlinear signal processing approach. Lyapunov exponents of cleaned signals were calculated to quantify the nonlinear nature of the process. Inspection of Lyapunov exponents calculated from optical and acoustic emission signals corresponding to a variety of weld penetration conditions revealed that no sharp distinction could be found. The Lyapunov exponents were found to depend strongly on the power and travel speed settings of the process. This variation masked any variations due solely to weld penetration. There was some distinction in Lyapunov exponents noted between non-gap and gap butt joint welds. The Lyapunov exponent for butt welds with significant joint gap was higher...

A novel method for extracting mutation points of acoustic emission signals based on cosine similarity

This paper is focused on the application of acoustic emission (AE) based monitoring systems to grinding processes. To develop the AE signal model for the process monitoring, a comparison between the AE and power signals is presented. The AE model is developed according to a traditional grinding force model. Based on the developed model, experiment indicates the AE signal is similar to the power of spindle and verifies the proposed AE model can be used to predict the AE root meam square (RMS) signal for monitoring the grinding process.

This paper assessed three signal-processing methods for grinding surface creation monitoring based on acoustic emission (AE) signals in abrasive scratch experiments. The AE signals are analysed in time domain (time direct analysis, TDA), frequency domain (fast Fourier transform, FFT) and in the combined time-frequency domain (singular spectrum analysis, SSA). The result showed that the FFT and SSA signal feature extraction methods gives better indication in correlation to the surface creation with different abrasive geometrical characteristics. For both sapphire and zirconia materials, the FFT method showed the most significative AE features was in the frequency range between 0 and 200 kHz. This work reveals that the AE signals processed with adequate feature extraction method can provide meaningful information for the on-line monitoring of surface creation in grinding processes.

The acoustic emission (AE) signal is weak due to the coupling and intersecting coexistence of other disturbance components in aluminum alloy metal inert-gas welding (MIG) process. It is necessary to analyze and process the AE signal for the accurate identification of the welding state. A time frequency feature extraction method based on synchronous compression wavelet (SST) and principal component analysis (PCA) is proposed in this paper. The SST transform is performed to the collected AE signal of the MIG welding process to obtain the time frequency distribution. The PCA is subsequently performed to the time frequency distribution of the AE signals to determine the principal components. The approximate entropies of the principal components are calculated to quantitatively express the state characteristics of the welding process. The proposed method is applied to the AE signal of the friction, arc shock and the crack in the aluminum alloy MIG welding process. The three kinds AE signals are identified by inputting the calculated approximate entropies into the support vector machine (SVM). The results indicate that the calculated approximate entropies highlight the characteristic ability of the different modal AE signals, which can be used for monitoring the aluminum alloy MIG welding process quantitatively.

Acoustic emission (AE) signals produced by the dynamic friction of a gas face seal are analyzed to uncover their information concerning the status of the seal. Experiments were conducted with a gas face seal test rig. By adjusting different operating parameters, friction occurred in different ways and produced discrepant AE signals. The root-mean-square value of AE signals under different operating conditions has varied fluctuations on a timescale of the rotation period, which distinguishes different dynamic friction patterns and furthermore shows the significant discrepancy of how dynamic friction is affected by different operating parameters. Numerical simulations using a dynamic model for a gas face seal with contact coupled were performed. A combination of the experiments and numerical simulations validates the dynamic friction dependence on waviness, which can be reflected by AE signals. This research demonstrates the approach of revealing the real-time friction status of a seal by analyzing AE signals on a timescale of the rotation period.

An Acoustic Emission (AE) signal processing and analysis system is developed for process and condition monitoring of Dense Medium Cyclones (DMCs), key units in coal preparation plants. This paper describes the use of a combination of statistical signal processing, multivariate statistical analysis and pattern classification methods to formulate robust soft-sensor predictive models for DMC process variables and wear state based on passive contact AE signals. Power spectral density and statistical moment ‘feature’ variables are extracted from AE signals. Principal Component Analysis (PCA) is used to evaluate the sensitivity of the AE ‘features’ to process variables and wear state. Principal Component Regression (PCR) and Partial Least Squares (PLS) are used to quantitatively model process variables. Hierarchical clustering is used to qualitatively model wear state and process variables. The AE hardware, signal processing and soft-sensor modelling system can be used for process and condition monitoring of other mineral processing equipment.

The new method for discrete fractional cosine transform is proposed, and it was introduced in acoustic emission signal enhancement. According to the characteristic of rub-impact acoustic emission (AE) signal from rotating machinery, two constructions are proposed to enhance AE signal, which based on three cycles discrete fractional cosine transform (FDCT3), and modified transform (MFDCT3). The experiment date was rub impact AE signals sampled from rotating test stand, Gaussian white noise and non-stationary noise were added to simulate the real AE signal which polluted seriously by noise. Then, FDCT3 and MFDCT3 were used into de-noising and AE recognition.The result shown that FDCT3 and MFDCT3 are effective at the de-noising, and those performance is better than DCT.

Detection of arc characteristics and weld forming quality of aluminum alloy DP-MIG welding using AE signal through resonance demodulation