Evaluating the Effects of Size and Precision of Training Data on ANN Training Performance for the Prediction of Chaotic Time Series Patterns

2022 ◽  
pp. 266-282
Author(s):  
Lei Zhang
Keyword(s):  
Time Series ◽  
Open Loop ◽  
Chaotic Time Series ◽  
Training Data ◽  
Acquisition Time ◽  
Lorenz Attractor ◽  
Ann Model ◽  
Training Performance ◽  
Hidden Layer ◽  
Input Delays

In this research, artificial neural networks (ANN) with various architectures are trained to generate the chaotic time series patterns of the Lorenz attractor. The ANN training performance is evaluated based on the size and precision of the training data. The nonlinear Auto-Regressive (NAR) model is trained in open loop mode first. The trained model is then used with closed loop feedback to predict the chaotic time series outputs. The research goal is to use the designed NAR ANN model for the simulation and analysis of Electroencephalogram (EEG) signals in order to study brain activities. A simple ANN topology with a single hidden layer of 3 to 16 neurons and 1 to 4 input delays is used. The training performance is measured by averaged mean square error. It is found that the training performance cannot be improved by solely increasing the training data size. However, the training performance can be improved by increasing the precision of the training data. This provides useful knowledge towards reducing the number of EEG data samples and corresponding acquisition time for prediction.

Evaluating the Effects of Size and Precision of Training Data on ANN Training Performance for the Prediction of Chaotic Time Series Patterns

2019 ◽  
Vol 11 (1) ◽  
pp. 16-30 ◽  
Author(s):  
Lei Zhang
Keyword(s):  
Time Series ◽  
Open Loop ◽  
Chaotic Time Series ◽  
Training Data ◽  
Acquisition Time ◽  
Lorenz Attractor ◽  
Ann Model ◽  
Training Performance ◽  
Loop Feedback ◽  
Hidden Layer

In this research, artificial neural networks (ANN) with various architectures are trained to generate the chaotic time series patterns of the Lorenz attractor. The ANN training performance is evaluated based on the size and precision of the training data. The nonlinear Auto-Regressive (NAR) model is trained in open loop mode first. The trained model is then used with closed loop feedback to predict the chaotic time series outputs. The research goal is to use the designed NAR ANN model for the simulation and analysis of Electroencephalogram (EEG) signals in order to study brain activities. A simple ANN topology with a single hidden layer of 3 to 16 neurons and 1 to 4 input delays is used. The training performance is measured by averaged mean square error. It is found that the training performance cannot be improved by solely increasing the training data size. However, the training performance can be improved by increasing the precision of the training data. This provides useful knowledge towards reducing the number of EEG data samples and corresponding acquisition time for prediction.

Failure pressure prediction of pipeline with single corrosion defect using artificial neural network

2021 ◽  
pp. 166-171
Author(s):  
К. Т. Чин ◽  
Т. Арумугам ◽  
С. Каруппанан ◽  
М. Овинис
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Training Data ◽  
Coefficient Of Determination ◽  
Ann Model ◽  
Failure Pressure ◽  
Corrosion Defect ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Hidden Layer

Описываются разработка и применение искусственной нейронной сети (ИНС) для прогнозирования предельного давления трубопровода с точечным коррозионным дефектом, подверженного воздействию только внутреннего давления. Модель ИНС разработана на основе данных, полученных по результатам множественных полномасштабных испытаний на разрыв труб API 5L (класс от X42 до X100). Качество работы модели ИНС проверено в сравнении с данными для обучения, получен коэффициент детерминации R = 0,99. Модель дополнительно протестирована с учетом данных о предельном давлении корродированных труб API 5L X52 и X80. Установлено, что разработанная модель ИНС позволяет прогнозировать предельное давление с приемлемой погрешностью. С использованием данной модели проведена оценка влияния длины и глубины коррозионных дефектов на предельное давление. Выявлено, что глубина коррозии является более значимым фактором разрушения корродированного трубопровода. This paper describes the development and application of artificial neural network (ANN) to predict the failure pressure of single corrosion affected pipes subjected to internal pressure only. The development of the ANN model is based on the results of sets of full-scale burst test data of pipe grades ranging from API 5L X42 to X100. The ANN model was developed using MATLAB’s Neural Network Toolbox with 1 hidden layer and 30 neurons. Before further deployment, the developed ANN model was compared against the training data and it produced a coefficient of determination ( R ) of 0.99. The developed ANN model was further tested against a set of failure pressure data of API 5L X52 and X80 grade corroded pipes. Results revealed that the developed ANN model is able to predict the failure pressure with good margins of error. Furthermore, the developed ANN model was used to determine the failure trends when corrosion defect length and depth were varied. Results from this failure trend analysis revealed that corrosion defect depth is the most significant parameter when it comes to corroded pipeline failure.

Chaotic System Design Based on Recurrent Artificial Neural Network for the Simulation of EEG Time Series

2019 ◽  
Vol 13 (1) ◽  
pp. 25-35
Author(s):  
Lei Zhang
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Artificial Neural Network ◽  
Chaotic System ◽  
Research Work ◽  
Euler Method ◽  
Open Loop ◽  
Training Data ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Electroencephalogram (EEG) signals captured from brain activities demonstrate chaotic features, and can be simulated by nonlinear dynamic time series outputs of chaotic systems. This article presents the research work of chaotic system generator design based on artificial neural network (ANN), for studying the chaotic features of human brain dynamics. The ANN training performances of Nonlinear Auto-Regressive (NAR) model are evaluated for the generation and prediction of chaotic system time series outputs, based on varying the ANN architecture and the precision of the generated training data. The NAR model is trained in open loop form with 1,000 training samples generated using Lorenz system equations and the forward Euler method. The close loop NAR model is used for the generation and prediction of Lorenz chaotic time series outputs. The training results show that better training performance can be achieved by increasing the number of feedback delays and the number of hidden neurons, at the cost of increasing the computational load.

scholarly journals Generative adversarial network based on chaotic time series

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Makoto Naruse ◽  
Takashi Matsubara ◽  
Nicolas Chauvet ◽  
Kazutaka Kanno ◽  
Tianyu Yang ◽  
...  
Keyword(s):  
Time Series ◽  
Semiconductor Lasers ◽  
Latent Variables ◽  
Chaotic Time Series ◽  
Training Data ◽  
Generative Adversarial Networks ◽  
Data Sets ◽  
Deep Convolutional Neural Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network

Abstract Generative adversarial networks (GANs) are becoming increasingly important in the artificial construction of natural images and related functionalities, wherein two types of networks called generators and discriminators evolve through adversarial mechanisms. Using deep convolutional neural networks and related techniques, high-resolution and highly realistic scenes, human faces, etc. have been generated. GANs generally require large amounts of genuine training data sets, as well as vast amounts of pseudorandom numbers. In this study, we utilized chaotic time series generated experimentally by semiconductor lasers for the latent variables of a GAN, whereby the inherent nature of chaos could be reflected or transformed into the generated output data. We show that the similarity in proximity, which describes the robustness of the generated images with respect to minute changes in the input latent variables, is enhanced, while the versatility overall is not severely degraded. Furthermore, we demonstrate that the surrogate chaos time series eliminates the signature of the generated images that is originally observed corresponding to the negative autocorrelation inherent in the chaos sequence. We also address the effects of utilizing chaotic time series to retrieve images from the trained generator.

An Adaptive Method to Further Improve the Tolerance of an ANN-Based Detection System for Mooring Line Failure

2021 ◽  
Author(s):  
Djoni E. Sidarta ◽  
Nicolas Tcherniguin ◽  
Ho-Joon Lim ◽  
Philippe Bouchard ◽  
Mengchen Kang ◽  
...  
Keyword(s):  
Time Series ◽  
Adaptive Method ◽  
Training Data ◽  
Computational Time ◽  
Mooring Line ◽  
Ann Model ◽  
Hydrodynamic Simulations ◽  
Sensitivity Tests ◽  
Fully Coupled ◽  
And Training

Abstract The use of an Artificial Neural Network (ANN) for detection of mooring line failure has been a growing subject of discussion over the past several years. Sidarta et al. [6, 8, 12] have presented papers on the detection of mooring line failure of a moored vessel by monitoring shifts in the low frequency periods, mean yaw angles as a function of vessel positions, mass and added mass. An ANN model has been trained using MLTSIM hydrodynamic simulations based on information from the early stages of the project. The restoring forces and moments from mooring lines, risers and umbilicals have been solved using catenary equations to significantly reduce the computational time to generate the ANN training data. This paper presents the evaluation of this ANN model using fully coupled OrcaFlex hydrodynamic simulations, based on the latest information of the project. The results of this evaluation demonstrate the tolerance of the trained ANN model as it can properly function when tested using time series of vessel motions from the fully coupled OrcaFlex hydrodynamic simulations. Furthermore, although the ANN model has been trained using simulations with a completely removed line, the trained model can still function when tested with simulations of a line broken at the bottom. These give affirmation that the ANN model can tolerate the differences that exist between the test and training data. Sensitivity of the polyester line stiffness has also been performed using fully coupled OrcaFlex hydrodynamic simulations, and the computed time series of vessel motions have been used to test the ANN model. The ANN model can deal with some level of differences between the sensitivity tests and training data. However, sensitivity tests of the polyester line stiffness to model aging lines has posed a real challenge to the ANN model as its prediction accuracy has decreased significantly. This paper presents an adaptive method that can be implemented such that the ANN model can adapt to relatively new conditions that are quite different from the training data and maintain the accuracy of its prediction. With this approach, an existing ANN model that has been trained under certain assumptions of the system can still function although the behavior of the system has drifted away from those assumptions. This phenomenon may have similarity with a possible reality that measured behavior in the field can be somewhat different from numerical simulations. This adaptive method has a potential for addressing this issue such that a simulation trained ANN model can maintain its expected accuracy although dealing with different conditions from the training data. If successful, this is a good cost saving scenario that an ANN model adapts to some degree to relatively new and different conditions before the differences become too much to handle and the only solution is to retrain the model.

scholarly journals Failure pressure prediction of pipeline with single corrosion defect using artificial neural network

2020 ◽  
Vol 4 (1) ◽  
pp. 10-17 ◽  
Author(s):  
Kiu Toh Chin ◽  
◽  
Thibankumar Arumugam ◽  
Saravanan Karuppanan ◽  
Mark Ovinis ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Training Data ◽  
Coefficient Of Determination ◽  
Ann Model ◽  
Failure Pressure ◽  
Corrosion Defect ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Hidden Layer

This paper describes the development and application of artificial neural network (ANN) to predict the failure pressure of single corrosion affected pipes subjected to internal pressure only. The development of the ANN model is based on the results of 71 sets of full-scale burst test data of pipe grades ranging from API 5L X42 to X100. The ANN model was developed using MATLAB’s Neural Network Toolbox with 1 hidden layer and 30 neurons. Before further deployment, the developed ANN model was compared against the training data and it produced a coefficient of determination of 0.99. The developed ANN model was further tested against a set of failure pressure data of API 5L X52 and X80 grade corroded pipes. Results revealed that the developed ANN model is able to predict the failure pressure with good margins of error (within 15%). Furthermore, the developed ANN model was used to determine the failure trends when corrosion defect length and depth were varied. Results from this failure trend analysis revealed that corrosion defect depth is the most significant parameter when it comes to corroded pipeline failure.

scholarly journals On Practical Aspects of Using RNNs for Fault Detection in Sparsely-labeled Multi-sensor Time Series

2018 ◽  
Vol 10 (1) ◽  
Author(s):  
Narendhar Gugulothu ◽  
Vishnu TV ◽  
Priyanka Gupta ◽  
Pankaj Malhotra ◽  
Lovekesh Vig ◽  
...  
Keyword(s):  
Time Series ◽  
Fault Detection ◽  
Time Series Data ◽  
Unlabeled Data ◽  
Training Data ◽  
Series Data ◽  
Small Subset ◽  
Multiple Sensors ◽  
Unsupervised Approach ◽  
Hidden Layer

In this work, we attempt to address two practical limitations when using Recurrent Neural Networks (RNNs) as classifiers for fault detection using multi-sensor time series data: Firstly, there is a need to understand the classification decisions of RNNs. It is difficult for engineers to diagnose the faults when multiple sensors are being monitored at once. The faults detected by RNNs can be better understood if the sensors carrying the faulty signature are known. To achieve this, we propose a sensor relevance scoring (SRS) approach that scores each sensor based on its contribution to the classification decision by leveraging the hidden layer activations of RNNs. Secondly, lack of labeled training data due to infrequent faults (or otherwise) makes it difficult to train RNNs in a supervised manner. We pre-train an RNN on large unlabeled data via an autoencoder in an unsupervised manner, and then finetune the RNN for the fault detection task using small amount of labeled training data. Through experiments on a public gasoil heating loop dataset and a proprietary pump dataset, we demonstrate the efficacy of the proposed solutions, and show that i) SRS can help point to the sensors relevant for a fault, ii) large unlabeled data can be used to pre-train an RNNbased fault detector in an unsupervised manner in sparselylabeled scenarios, and iii) a purely unsupervised approach for fault detection (e.g. based on RNN-autoencoders) may not suffice when the number of sensors being monitored is large while the signature for fault is present in only a small subset of sensors.

scholarly journals Wavelet-Network based on L1-Norm minimisation for learning chaotic time series

2005 ◽  
Vol 3 (03) ◽  
Author(s):  
V. Alarcon-Aquino ◽  
E. S. Garcia-Treviño ◽  
R. Rosas-Romero ◽  
J. F. Ramirez-Cruz ◽  
L. G. Guerrero-Ojeda ◽  
...  
Keyword(s):  
Time Series ◽  
Back Propagation ◽  
Synthetic Data ◽  
Chaotic Time Series ◽  
Wavelet Network ◽  
L1 Norm ◽  
L2 Norm ◽  
Heavy Tailed ◽  
Hidden Layer ◽  
Propagation Network

This paper presents a wavelet-neural network based on the L1-norm minimisation for learning chaotic time series. The proposed approach, which is based on multi-resolution analysis, uses wavelets as activation functions in the hidden layer of the wavelet-network. We propose using the L1-norm, as opposed to the L2-norm, due to the wellknown fact that the L1-norm is superior to the L2-norm criterion when the signal has heavy tailed distributions or outliers. A comparison of the proposed approach with previous reported schemes using a time series benchmark is presented. Simulation results show that the proposed wavelet network based on the L1-norm performs better than the standard back-propagation network and the wavelet-network based on the traditional L2-norm when applied to synthetic data.

Sign in / Sign up

Export Citation Format

Share Document