Predicting microseismic,acoustic emission and electromagnetic radiation data using neural networks

Microseism,acoustic emission and electromagnetic radiation(M-A-E)data are usually used for predicting rockburst hazards.However,it is a great challenge to realize the prediction of M-A-E data.In this study,with the aid of a deep learning algorithm,a new method for the prediction of M-A-E data is proposed.In this method,an M-A-E data prediction model is built based on a variety of neural networks after analyzing numerous M-A-E data,and then the M-A-E data can be predicted.The predicted results are highly correlated with the real data collected in the field.Through field verification,the deep learning-based prediction method of M-A-E data provides quantitative prediction data for rockburst monitoring.

Acoustic Emission Recognition Based on a Three-Streams Neural Network with Attention

Acoustic emission(AE)is a nondestructive real-time monitoring technology,which has been proven to be a valid way of monitoring dynamic damage to materials.The classification and recognition methods of the AE signals of the rotor are mostly focused on machine learning.Considering that the huge success of deep learning technologies,where the Recurrent Neural Network(RNN)has been widely applied to sequential classification tasks and Convolutional Neural Network(CNN)has been widely applied to image recognition tasks.A novel three-streams neural network(TSANN)model is proposed in this paper to deal with fault detection tasks.Based on residual connection and attention mechanism,each stream of the model is able to learn the most informative representation from Mel Frequency Cepstrum Coefficient(MFCC),Tempogram,and short-time Fourier transform(STFT)spectral respectively.Experimental results show that,in comparison with traditional classification methods and single-stream CNN networks,TSANN achieves the best overall performance and the classification error rate is reduced by up to 50%,which demonstrates the availability of the model proposed.

Prediction of impedance responses of protonic ceramic cells using artificial neural network tuned with the distribution of relaxation times

A deep-learning-based framework is proposed to predict the impedance response and underlying electrochemical behavior of the reversible protonic ceramic cell(PCC) across a wide variety of different operating conditions.Electrochemical impedance spectra(EIS) of PCCs were first acquired under a variety of opera ting conditions to provide a dataset containing 36 sets of EIS spectra for the model.An artificial neural network(ANN) was then trained to model the relationship between the cell operating condition and EIS response.Finally,ANN model-predicted EIS spectra were analyzed by the distribution of relaxation times(DRT) and compared to DRT spectra obtained from the experimental EIS data,enabling an assessment of the accumulative errors from the predicted EIS data vs the predicted DRT.We show that in certain cases,although the R^(2)of the predicted EIS curve may be> 0.98,the R^(2)of the predicted DRT may be as low as~0.3.This can lead to an inaccurate ANN prediction of the underlying time-resolved electrochemical response,although the apparent accuracy as evaluated from the EIS prediction may seem acceptable.After adjustment of the parameters of the ANN framework,the average R^(2)of the DRTs derived from the predicted EIS can be improved to 0.9667.Thus,we demonstrate that a properly tuned ANN model can be used as an effective tool to predict not only the EIS,but also the DRT of complex electrochemical systems.

Model-constrained and data-driven double-supervision acoustic impedance inversion

Seismic impedance inversion is an important technique for structure identification and reservoir prediction.Model-based and data-driven impedance inversion are the commonly used inversion methods.In practice,the geophysical inversion problem is essentially an ill-posedness problem,which means that there are many solutions corresponding to the same seismic data.Therefore,regularization schemes,which can provide stable and unique inversion results to some extent,have been introduced into the objective function as constrain terms.Among them,given a low-frequency initial impedance model is the most commonly used regularization method,which can provide a smooth and stable solution.However,this model-based inversion method relies heavily on the initial model and the inversion result is band limited to the effective frequency bandwidth of seismic data,which cannot effectively improve the seismic vertical resolution and is difficult to be applied to complex structural regions.Therefore,we propose a data-driven approach for high-resolution impedance inversion based on the bidirectional long short-term memory recurrent neural network,which regards seismic data as time-series rather than image-like patches.Compared with the model-based inversion method,the data-driven approach provides higher resolution inversion results,which demonstrates the effectiveness of the data-driven method for recovering the high-frequency components.However,judging from the inversion results for characterization the spatial distribution of thin-layer sands,the accuracy of high-frequency components is difficult to guarantee.Therefore,we add the model constraint to the objective function to overcome the shortages of relying only on the data-driven schemes.First,constructing the supervisor1 based on the bidirectional long short-term memory recurrent neural network,which provides the predicted impedance with higher resolution.Then,convolution constraint as supervisor2 is introduced into the objective function to guarantee the reliability and accuracy of the inversion results,which makes the synthetic seismic data obtained from the inversion result consistent with the input data.Finally,we test the proposed scheme based on the synthetic and field seismic data.Compared to model-based and purely data-driven impedance inversion methods,the proposed approach provides more accurate and reliable inversion results while with higher vertical resolution and better spatial continuity.The inversion results accurately characterize the spatial distribution relationship of thin sands.The model tests demonstrate that the model-constrained and data-driven impedance inversion scheme can effectively improve the thin-layer structure characterization based on the seismic data.Moreover,tests on the oil field data indicate the practicality and adaptability of the proposed method.

Application of quantum neural networks in localization of acoustic emission

Due to defects of time-difference of arrival localization,which influences by speed differences of various model waveforms and waveform distortion in transmitting process,a neural network technique is introduced to calculate localization of the acoustic emission source.However,in back propagation（BP） neural network,the BP algorithm is a stochastic gradient algorithm virtually,the network may get into local minimum and the result of network training is dissatisfactory.It is a kind of genetic algorithms with the form of quantum chromosomes,the random observation which simulates the quantum collapse can bring diverse individuals,and the evolutionary operators characterized by a quantum mechanism are introduced to speed up convergence and avoid prematurity.Simulation results show that the modeling of neural network based on quantum genetic algorithm has fast convergent and higher localization accuracy,so it has a good application prospect and is worth researching further more.

Acoustic Emission Recognition Based on a Two-Streams Convolutional Neural Network

The Convolutional Neural Network(CNN)is a widely used deep neural network.Compared with the shallow neural network,the CNN network has better performance and faster computing in some image recognition tasks.It can effectively avoid the problem that network training falls into local extremes.At present,CNN has been applied in many different fields,including fault diagnosis,and it has improved the level and efficiency of fault diagnosis.In this paper,a two-streams convolutional neural network(TCNN)model is proposed.Based on the short-time Fourier transform(STFT)spectral and Mel Frequency Cepstrum Coefficient(MFCC)input characteristics of two-streams acoustic emission(AE)signals,an AE signal processing and classification system is constructed and compared with the traditional recognition methods of AE signals and traditional CNN networks.The experimental results illustrate the effectiveness of the proposed model.Compared with single-stream convolutional neural network and a simple Long Short-Term Memory(LSTM)network,the performance of TCNN which combines spatial and temporal features is greatly improved,and the accuracy rate can reach 100%on the current database,which is 12%higher than that of single-stream neural network.

Locating Impedance Change in Electrical Impedance Tomography Based on Multilevel BP Neural Network

Electrical impedance tomography(EIT) is a new computer tomography technology, which reconstructs an impedance (resistivity, conductivity) distribution, or change of impedance, by making voltage and current measurements on the object's periphery. Image reconstruction in EIT is an ill-posed, non-linear inverse problem. A method for finding the place of impedance change in EIT is proposed in this paper, in which a multilevel BP neural network (MBPNN) is used to express the non-linear relation between the impedance change inside the object and the voltage change measured on the surface of the object. Thus, the location of the impedance change can be decided by the measured voltage variation on the surface. The impedance change is then reconstructed using a linear approximate method. MBPNN can decide the impedance change location exactly without long training time. It alleviates some noise effects and can be expanded, ensuring high precision and space resolution of the reconstructed image that are not possible by using the back projection method.

AN INTELLIGENT TOOL CONDITION MONITORING SYSTEM USING FUZZY NEURAL NETWORKS

Reliable on line cutting tool conditioning monitoring is an essential feature of automatic machine tool and flexible manufacturing system (FMS) and computer integrated manufacturing system (CIMS). Recently artificial neural networks (ANNs) are used for this purpose in conjunction with suitable sensory systems. The present work in Norwegian University of Science and Technology (NTNU) uses back propagation neural networks (BP) and fuzzy neural networks (FNN) to process the cutting tool state data measured with force and acoustic emission (AE) sensors, and implements a valuable on line tool condition monitoring system using the ANNs. Different ANN structures are designed and investigated to estimate the tool wear state based on the fusion of acoustic emission and force signals. Finally, four case studies are introduced for the sensing and ANN processing of the tool wear states and the failures of the tool with practical experiment examples. The results indicate that a tool wear identification system can be achieved using the sensors integration with ANNs, and that ANNs provide a very effective method of implementing sensor integration for on line monitoring of tool wear states and abnormalities.

Long Short-Term Memory Recurrent Neural Network-Based Acoustic Model Using Connectionist Temporal Classification on a Large-Scale Training Corpus

A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a forced aligned Hidden Markov Model(HMM) state sequence obtained from the GMM-based acoustic model. Therefore, it requires a long computation time for training both the GMM-based acoustic model and a deep learning-based acoustic model. In order to solve this problem, an acoustic model using CTC algorithm is proposed. CTC algorithm does not require the GMM-based acoustic model because it does not use the forced aligned HMM state sequence. However, previous works on a LSTM RNN-based acoustic model using CTC used a small-scale training corpus. In this paper, the LSTM RNN-based acoustic model using CTC is trained on a large-scale training corpus and its performance is evaluated. The implemented acoustic model has a performance of 6.18% and 15.01% in terms of Word Error Rate(WER) for clean speech and noisy speech, respectively. This is similar to a performance of the acoustic model based on the hybrid method.

Boundary integrated neural networks and code for acoustic radiation and scattering

This paper presents a novel approach called the boundary integrated neural networks(BINNs)for analyzing acoustic radiation and scattering.The method introduces fundamental solutions of the time-harmonic wave equation to encode the boundary integral equations(BIEs)within the neural networks,replacing the conventional use of the governing equation in physics-informed neural networks(PINNs).This approach offers several advantages.First,the input data for the neural networks in the BINNs only require the coordinates of“boundary”collocation points,making it highly suitable for analyzing acoustic fields in unbounded domains.Second,the loss function of the BINNs is not a composite form and has a fast convergence.Third,the BINNs achieve comparable precision to the PINNs using fewer collocation points and hidden layers/neurons.Finally,the semianalytic characteristic of the BIEs contributes to the higher precision of the BINNs.Numerical examples are presented to demonstrate the performance of the proposed method,and a MATLAB code implementation is provided as supplementary material.

Predicting the Reflection Coefficient of a Viscoelastic Coating Containing a Cylindrical Cavity Based on an Artificial Neural Network Model

A cavity viscoelastic structure has a good sound absorption performance and is often used as a reflective baffle or sound absorption cover in underwater acoustic structures.The acoustic performance field has become a key research direction worldwide.Because of the time-consuming shortcomings of the traditional numerical analysis method and the high cost of the experimental method for measuring the reflection coefficient to evaluate the acoustic performance of coatings,this innovative study predicted the reflection coefficient of a viscoelastic coating containing a cylindrical cavity based on an artificial neural network(ANN).First,themapping relationship between the input characteristics and reflection coefficient was analysed.When the elastic modulus and loss factor value were smaller,the characteristics of the reflection coefficient curve were more complicated.These key parameters affected the acoustic performance of the viscoelastic coating.Second,a dataset of the acoustic performance of the viscoelastic coating containing a cylindrical cavity was generated based on the finite elementmethod(FEM),which avoided a large number of repeated experiments.The minmax normalization method was used to preprocess the input characteristics of the viscoelastic coating,and the reflection coefficient was used as the dataset label.The grid search method was used to fine-tune the ANNparameters,and the prediction error was studied based on a 10-fold cross-validation.Finally,the error distributions were analysed.The average root means square error(RMSE)and the mean absolute percentage error(MAPE)predicted by the improved ANN model were 0.298%and 1.711%,respectively,and the Pearson correlation coefficient(PCC)was 0.995,indicating that the improved ANN model accurately predicted the acoustic performance of the viscoelastic coating containing a cylindrical cavity.In practical engineering applications,by expanding the database of the material range,cavity size and backing of the coating,the reflection coefficient of more sound-absorbing layers was evaluated,which is useful for efficiently predicting the acoustic performance of coatings in a specific frequency range and has great application value.

A Rub-Impact Recognition Method Based on Improved Convolutional Neural Network

Based on the theory of modal acoustic emission(AE),when the convolutional neural network(CNN)is used to identify rotor rub-impact faults,the training data has a small sample size,and the AE sound segment belongs to a single channel signal with less pixel-level information and strong local correlation.Due to the convolutional pooling operations of CNN,coarse-grained and edge information are lost,and the top-level information dimension in CNN network is low,which can easily lead to overfitting.To solve the above problems,we first propose the use of sound spectrograms and their differential features to construct multi-channel image input features suitable for CNN and fully exploit the intrinsic characteristics of the sound spectra.Then,the traditional CNN network structure is improved,and the outputs of all convolutional layers are connected as one layer constitutes a fused feature that contains information at each layer,and is input into the network’s fully connected layer for classification and identification.Experiments indicate that the improved CNN recognition algorithm has significantly improved recognition rate compared with CNN and dynamical neural network(DNN)algorithms.

Study of Synthesis Identification in Cutting Process with Fuzzy Neural Network

With the development of industrial production modernization, FMS and CIMS will become more and more popularized. For its control system is increasingly modeled, intellectualized and automatized, in order to raise the reliability and stability in the manufacturing process, the comprehensive monitoring and diagnosis aimed at cutting tool wear and chatter become more and more important and get rapid development. The paper tried to discuss of the intellectual status identification method based on acoustics-vibra characteristics of machining process, and propose that the working conditions may be taken as a core, complex fuzzy inference neural network model based on artificial neural network theory, and by using various kinds of modernized signal processing method to abstract enough characteristics parameters which will reflect overall processing status from machining acoustics-vibra signal as information source, to identify different working condition, and provide guarantee for automation and intelligence in machining process. The complex network is composed of NNw and NNs, Each of them is composed of BP model network, NNw is weight network at rule condition, NNs is decision-making network of each status. Y out is final inference result which is to take subordinate degree as weight from NNw, to weight reflecting result from NNs and obtain status inference of monitoring system. In the process of machining, the acoustics-vibor signal were gotten by the acoustimeter and the acceleration piezoelectricity detector, the date is analysed by the signal processing software in time and frequency domain, then form multi feature parameter vector of criterion pattern samples for the different stage of cutting chatter and acoustics-vibra multi feature parameter vector. The vector can give a accurate and comprehensive description for the cutting process, and have the characteristic which are speediness of time domain and veracity of frequency domain. The research works have been practically applied in identification of tool wear, cutting chatter, experiment results showed that it is practicable to identify the cutting chatter based on fuzzy neural network, and the new method based on fuzzy neural network can be applied to other state identification in machining process.

Estimation of petrophysical parameters using seismic inversion and neural network modeling in Upper Assam basin, India

Estimation of petrophysical parameters is an important issue of any reservoirs. Porosity, volume of shale and water saturation has been evaluated for reservoirs of Upper Assam basin, located in northeastern India from well log and seismic data. Absolute acoustic impedance(AAI) and relative acoustic impedance(RAI) are generated from model based inversion of 2-D post-stack seismic data. The top of geological formation, sand reservoirs, shale layers and discontinuities at faults are detected in RAI section under the study area. Tipam Sandstone(TS) and Barail Arenaceous Sandstone(BAS) are the main reservoirs,delineated from the logs of available wells and RAI section. Porosity section is obtained using porosity wavelet and porosity reflectivity from post-stack seismic data. Two multilayered feed forward neural network(MLFN) models are created with inputs: AAI, porosity, density and shear impedance and outputs: volume of shale and water saturation with single hidden layer. The estimated average porosity in TS and BAS reservoir varies from 30% to 36% and 18% to 30% respectively. The volume of shale and water saturation ranges from 10% to 30% and 20% to 60% in TS reservoir and 28% to 30% and 23% to 55% in BAS reservoir respectively.

Donggan Speech Recognition Based on Convolution Neural Networks

Donggan language, which is a special variant of Mandarin, is used by Donggan people in Central Asia. Donggan language includes Gansu dialect and Shaanxi dialect. This paper proposes a convolutional neural network (CNN) based Donggan language speech recognition method for the Donggan Shaanxi dialect. A text corpus and a pronunciation dictionary were designed for of Donggan Shannxi dialect and the corresponding speech corpus was recorded. Then the acoustic models of Donggan Shaanxi dialect was trained by CNN. Experimental results demonstrate that the recognition rate of proposed CNNbased method achieves lower word error rate than that of the monophonic hidden Markov model (HMM) based method, triphone HMM-based method and DNN- based method.

A zeroing neurodynamics‐based location method for nodes in underwater acoustic sensor network

Zeroing neurodynamics methodology,which dedicates to finding equilibrium points of equations,has been proven to be a powerful tool in the online solving of problems with considerable complexity.In this paper,a method for underwater acoustic sensor network(UASN)localisation is proposed based on zeroing neurodynamics methodology to preferably locate moving underwater nodes.A zeroing neurodynamics model specifically designed for UASN localisation is constructed with rigorous theoretical analyses of its effectiveness.The proposed zeroing neurodynamics model is compatible with some localisation algorithms,which can be utilised to eliminate error in non‐ideal situations,thus further improving its effectiveness.Finally,the effectiveness and compatibility of the proposed zeroing neurodynamics model are substantiated by examples and computer simulations.

The electrical impedance, AC conductivity and dielectric properties of phenol red compound investigated and modeled by an artificial neural network

The impedance spectroscopy,electrical conductivity and electric modulus of bulk phenol red were measured,as a function of both frequency and temperature.Artificial neural networks(ANNs)were used for modeling its electrical properties.The two parts(real and imaginary)of its complex impedance(Z^*)were analyzed and the activation energy related to the electrical relaxation process was evaluated.Nyquist curves were plotted showing semicircles for the different temperatures.The AC electrical conductivity follows a power lawσac(ω)αω^η.The maximum barrier height Bm was derived for specific temperatures.A plausible mechanism for the AC conduction of bulk phenol red was deduced from the temperature reliance of the frequency exponent.The dielectric data was analyzed using electric modulus as a tool.In addition,ANNs were used to model the impedance parts and the total electrical conductivity.Numerous runs were tried,to obtain the best performance.The training and prediction results were compared to the equivalent experimental results,with a good match obtained.An equation describing the experimental results was obtained mathematically,based on the use of ANNs.The outputs demonstrated that ANNs are an admirable tool for modeling experimental results.

Applying acoustic emission and neural network to classify wheat seeds from weed seeds

In the present study,an expert weed seeds recognition system combining acoustic emissions analysis,Multilayer Feedforward Neural Network(MFNN)classifier was developed and tested for classifying wheat seeds.This experiment was performed for classifying two major important wheat varieties from five species of weed seeds.In order to produce sound signals,a 60o inclined glass plate was used.Fast Fourier Transform(FFT),Phase and Power Spectral Density(PSD)of impact signals were calculated.All features of sound signals are computed via a 1024-point FFT.After feature generation,60%of data sets were used for training,20%for validation,and remaining samples were selected for testing.The optimized MFNN model was found to have 500-12-2 and 500-10-2 architectures for“101”and“Shiroodi”wheat varieties,respectively.The selection of the optimal model was based on the evaluation of mean square error(MSE)and correct separation rate(CSR).The CSR percentages for two wheat varieties were 100%.Considering the overall aspects of the results,it can be stated that the developed system was successful enough to correlate the acoustic features with wheat seed type.

Development and Validation of a Deep Learning Predictive Model Combining Clinical and Radiomic Features for Short-Term Postoperative Facial Nerve Function in Acoustic Neuroma Patients

Objective This study aims to construct and validate a predictable deep learning model associated with clinical data and multi-sequence magnetic resonance imaging(MRI)for short-term postoperative facial nerve function in patients with acoustic neuroma.Methods A total of 110 patients with acoustic neuroma who underwent surgery through the retrosigmoid sinus approach were included.Clinical data and raw features from four MRI sequences(T1-weighted,T2-weighted,T1-weighted contrast enhancement,and T2-weighted-Flair images)were analyzed.Spearman correlation analysis along with least absolute shrinkage and selection operator regression were used to screen combined clinical and radiomic features.Nomogram,machine learning,and convolutional neural network(CNN)models were constructed to predict the prognosis of facial nerve function on the seventh day after surgery.Receiver operating characteristic(ROC)curve and decision curve analysis(DCA)were used to evaluate model performance.A total of 1050 radiomic parameters were extracted,from which 13 radiomic and 3 clinical features were selected.Results The CNN model performed best among all prediction models in the test set with an area under the curve(AUC)of 0.89(95%CI,0.84–0.91).Conclusion CNN modeling that combines clinical and multi-sequence MRI radiomic features provides excellent performance for predicting short-term facial nerve function after surgery in patients with acoustic neuroma.As such,CNN modeling may serve as a potential decision-making tool for neurosurgery.