Check valve's fault detection with wavelet packet's kernel principal component analysis

Although mud pumps are vital components of a drilling rig, their failures are frequent. The identification of technical condition of these high-pressure piston pumps is difficult. There are no reliable criteria for the assessment of mud pump condition. In this paper, faults of the pump valve module are identified by means of acoustic emission (AE) signals. The characteristics of these signals are extracted by wavelet packet signal processing. This method has been verified by experiments conducted on a NOV (National Oilwell Varco) -made triplex 14-P-220 mud pump (mounted in the drillship). The results show that the wavelet packet signal processing method can effectively extract the frequency band energy eigenvalues of the signals. Besides, some operational problems associated with high pressure piston mud pumps are presented. A non-invasive method for diagnosing the technical condition of such pumps is being developed at the Maritime University of Szczecin.

ANFIS system for prognosis of dynamometer high-speed ball bearing based on frequency domain acoustic emission signals

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.

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.

Strain localization peculiarities and distribution of acoustic emission sources in rock samples tested by uniaxial compression and exposed to electric pulses

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.

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.

Characterization of piezoelectric wafer active sensor for acoustic emission sensing

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

This paper describes the development of a two-dimensional acoustic surface waveguide system to enhance the transmission of Acoustic Emission (AE) signals in high attenuation concrete materials. The design of the surface waveguide system and the AE source location results are described. In this study, steel wires were selected as a waveguide material and were attached on the surface area of reinforced concrete structures. AE sensors were mounted at the end of the waveguides. The waveguides were connected to a concrete slab at joints with small contact areas using epoxy. This minimizes the amount of AE energy that could dissipate back to concrete. Thus, AE signals can be transmitted a longer distance. Experiments using standard pencil-lead breaks were conducted at 49 locations on a surface of a reinforced concrete floor slab to provide artificial AE signals. High transmission efficiencies were experimentally determined for the epoxy joints developed to attach the waveguides on the concrete surface. Results confirm that the use of the two-dimensional surface waveguides can significantly increase the AE monitoring range. A multi-layer Neural Network (NN) system was employed to predict locations of the AE sources. Four data sets of AE parameters and their corresponding 49 source locations in each data set were used to train the NN system. A testing data set was then used to demonstrate the ability of the NN in identifying the locations of the AE sources. Satisfactory prediction results from the NN were obtained.

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.

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.

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

To the instability of acoustic emission (AE) signal of rock fracture, the method about feature extraction and comprehensive recognition of those was came up with combining AE parameters, EMD and BP neural network. Through the acoustic emission experiment of different brittle rock under uniaxial compression, stress-strain curve and AE data were obtained; time-frequency characteristics of AE signal of rock samples were compared. Feature vectors, like AE parameters, and EMD energy entropy, was synthesized to BP neural network to distinguish different AE signal. The results show that evolution characteristic with stress or time of AE parameters of different rock which was under uniaxial compression exist similarities and differences. EMD and Welch spectrum can reflect the difference among spectrum, energy distribution of AE signal of different rock very well. With various characteristics of different rock acoustic emission, the neural network has good recognition effect.