scholarly journals Neural Ordinary Differential Equations and Recurrent Neural Networks for Predicting the State of Health of Batteries

2021 ◽  
Author(s):  
Simona Pepe ◽  
Jiapeng Liu ◽  
Emanuele Quattrocchi ◽  
Francesco Ciucci
Keyword(s):  
Neural Networks ◽  
Differential Equations ◽  
Ordinary Differential Equations ◽  
Short Term Memory ◽  
Network Models ◽  
The State ◽  
State Of Health ◽  
Neural Network Models ◽  
Efficient Operation ◽  
Ode Models

<p>Battery management systems require efficient battery prognostics so that failures can be prevented, and efficient operation guaranteed. In this work, we develop new models based on neural networks and ordinary differential equations (ODE) to forecast the state of health (SOH) of batteries and predict their end of life (EOL). Governing differential equations are discovered using measured capacities and voltage curves. In this context, discoveries and predictions made with neural ODEs, augmented neural ODEs, predictor-corrector recurrent ODEs are compared against established recurrent neural network models, including long short-term memory and gated recurrent units. The ODE models show good performance, achieving errors of 1% in SOH and 5% in EOL estimation when predicting 30% of the remaining battery’s cycle life. Variable cycling conditions and a range of prediction horizons are analyzed to evaluate the models’ characteristics. The results obtained are extremely promising for applications in SOH and EOL predictions.</p>

scholarly journals Neural Ordinary Differential Equations and Recurrent Neural Networks for Predicting the State of Health of Batteries

2021 ◽  
Author(s):  
Simona Pepe ◽  
Jiapeng Liu ◽  
Emanuele Quattrocchi ◽  
Francesco Ciucci
Keyword(s):  
Neural Networks ◽  
Differential Equations ◽  
Ordinary Differential Equations ◽  
Short Term Memory ◽  
Network Models ◽  
The State ◽  
State Of Health ◽  
Neural Network Models ◽  
Efficient Operation ◽  
Ode Models

<p>Battery management systems require efficient battery prognostics so that failures can be prevented, and efficient operation guaranteed. In this work, we develop new models based on neural networks and ordinary differential equations (ODE) to forecast the state of health (SOH) of batteries and predict their end of life (EOL). Governing differential equations are discovered using measured capacities and voltage curves. In this context, discoveries and predictions made with neural ODEs, augmented neural ODEs, predictor-corrector recurrent ODEs are compared against established recurrent neural network models, including long short-term memory and gated recurrent units. The ODE models show good performance, achieving errors of 1% in SOH and 5% in EOL estimation when predicting 30% of the remaining battery’s cycle life. Variable cycling conditions and a range of prediction horizons are analyzed to evaluate the models’ characteristics. The results obtained are extremely promising for applications in SOH and EOL predictions.</p>

scholarly journals Lithium Battery SOH Monitoring and an SOC Estimation Algorithm Based on the SOH Result

Energies ◽  
2021 ◽  
Vol 14 (15) ◽  
pp. 4506
Author(s):  
Jong-Hyun Lee ◽  
In-Soo Lee
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Short Term Memory ◽  
Network Models ◽  
Estimation Algorithm ◽  
The State ◽  
State Of Health ◽  
Neural Network Models ◽  
Health Diagnosis

Lithium batteries are the most common energy storage devices in items such as electric vehicles, portable devices, and energy storage systems. However, if lithium batteries are not continuously monitored, their performance could degrade, their lifetime become shortened, or severe damage or explosion could be induced. To prevent such accidents, we propose a lithium battery state of health monitoring method and state of charge estimation algorithm based on the state of health results. The proposed method uses four neural network models. A neural network model was used for the state of health diagnosis using a multilayer neural network model. The other three neural network models were configured as neural network model banks, and the state of charge was estimated using a multilayer neural network or long short-term memory. The three neural network model banks were defined as normal, caution, and fault neural network models. Experimental results showed that the proposed method using the long short-term memory model based on the state of health diagnosis results outperformed the counterpart methods.

scholarly journals Investment portfolio analysis by using neural networks

2019 ◽  
Author(s):  
Nijolė Maknickienė ◽  
Darius Sabaliauskas
Keyword(s):  
Neural Networks ◽  
Short Term Memory ◽  
Network Models ◽  
Memory Cell ◽  
High Tech ◽  
Neural Network Models ◽  
Time Investment ◽  
The Neural Network ◽  
Cell Architecture ◽  
Investment Portfolios

Purpose – the purpose of the article is to compare the formation of portfolios and to make predictions about how it will change. Research methodology – for analysis, optimization and predictions use the neural network models that are created using a neural recurrent long short-term memory cell architecture network and Markowitz’s modern portfolio theory Findings – this article compares the portfolios of IT field with different instruments and level of optimization. Research limitations – the main limit of the article is that only historical data is used. The real-time investment would check the performance of the portfolio creation methodology under uncertain conditions. Practical implications – the results of the article give opportunities for investors and speculators in the finance market by using neural networks for forming investment portfolios, as well as analysing and predicting their changes. Originality/Value – the growing high-tech use in financial markets changes our habits and our understanding of the surrounding world. The financial sphere has also had several changes, and it has undergone major changes that will change the approach to producing financial forecasts and analysis. Including Artificial Intelligence in these processes brings new innovative opportunities.

Recurrent convolutional neural networks for poet identification

2020 ◽  
Author(s):  
Dariush Salami ◽  
Saeedeh Momtazi
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Language Processing ◽  
Short Term Memory ◽  
State Of The Art ◽  
The State ◽  
Support Vector ◽  
Neural Network Models ◽  
Spatial Features ◽  
Input Text

Abstract Deep neural networks have been widely used in various language processing tasks. Recurrent neural networks (RNNs) and convolutional neural networks (CNN) are two common types of neural networks that have a successful history in capturing temporal and spatial features of texts. By using RNN, we can encode input text to a lower space of semantic features while considering the sequential behavior of words. By using CNN, we can transfer the representation of input text to a flat structure to be used for classifying text. In this article, we proposed a novel recurrent CNN model to capture not only the temporal but also the spatial features of the input poem/verse to be used for poet identification. Considering the shortcomings of the normal RNNs, we try both long short-term memory and gated recurrent unit units in the proposed architecture and apply them to the poet identification task. There are a large number of poems in the history of literature whose poets are unknown. Considering the importance of the task in the information processing field, a great variety of methods from traditional learning models, such as support vector machine and logistic regression, to deep neural network models, such as CNN, have been proposed to address this problem. Our experiments show that the proposed model significantly outperforms the state-of-the-art models for poet identification by receiving either a poem or a single verse as input. In comparison to the state-of-the-art CNN model, we achieved 9% and 4% improvements in f-measure for poem- and verse-based tasks, respectively.

scholarly journals Assessment of Water Quality State Dynamics Using Adaptive Filtering Methods and Neural Networks Approaching. Case study - Danube River in Galati area

2019 ◽  
Vol 70 (6) ◽  
pp. 1914-1919 ◽  
Author(s):  
Gabriel Murariu ◽  
Catalina Iticescu ◽  
Adrian Murariu ◽  
Bogdan Rosu ◽  
Dan Munteanu ◽  
...  
Keyword(s):  
Neural Networks ◽  
Carbonic Acid ◽  
Network Models ◽  
Difficult Problem ◽  
The State ◽  
Danube River ◽  
Neural Network Models ◽  
Final State ◽  
Essential Knowledge ◽  
Over Time

The identification of a temporal evolution model for complex systems has, since ancient times, been a subject of great interest. Whether it is mechanical systems for which it was essential knowledge of the final state or electrical systems, the problem of identifying evolution over time has always been extremely interesting. In the case of a complex system such as a river, whose condition is described by a set of physico-chemical parameters, the time description of the evolution of the state becomes a rather difficult problem. In this paper, two ways of identifying and predicting the parameters describing the state of such a system are presented. A LRS type algorithm and a process of approximating evolution over time considering neural networks was used for comparison. Recorded series of pH and carbonic acid values were used as study parameters. The data used covers the period 1990-1998 and consists of measurements of the water samples taken from the Danube River in the area of Galati City. The main result was to obtain a rapid convergence for the adaptive filter used. For comparison, a number of 6 neural network models were built. Finally, findings and discussion of the results are presented.

scholarly journals Opening the black box of neural networks: methods for interpreting neural network models in clinical applications

2018 ◽  
Vol 6 (11) ◽  
pp. 216-216 ◽  
Author(s):  
Zhongheng Zhang ◽  
◽  
Marcus W. Beck ◽  
David A. Winkler ◽  
Bin Huang ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Models ◽  
Black Box ◽  
Clinical Applications ◽  
Neural Network Models

CHAOS AND HYPERCHAOS IN A CLASS OF SIMPLE CELLULAR NEURAL NETWORKS MODELED BY O.D.E.

2006 ◽  
Vol 16 (09) ◽  
pp. 2729-2736 ◽  
Author(s):  
XIAO-SONG YANG ◽  
YAN HUANG
Keyword(s):  
Neural Networks ◽  
Differential Equations ◽  
Ordinary Differential Equations ◽  
Lyapunov Exponents ◽  
Cellular Neural Networks ◽  
New Class ◽  
Connection Matrices ◽  
Low Dimensional

This paper presents a new class of chaotic and hyperchaotic low dimensional cellular neural networks modeled by ordinary differential equations with some simple connection matrices. The chaoticity of these neural networks is indicated by positive Lyapunov exponents calculated by a computer.

A Novel General and Robust Method Based on NAOP for Solving Nonlinear Ordinary Differential Equations and Partial Differential Equations by Cellular Neural Networks

2013 ◽  
Vol 135 (3) ◽  
Author(s):  
Jean Chamberlain Chedjou ◽  
Kyandoghere Kyamakya
Keyword(s):  
Neural Networks ◽  
Partial Differential Equations ◽  
Differential Equations ◽  
Ordinary Differential Equations ◽  
Cellular Neural Networks ◽  
Nonlinear Ordinary Differential Equations ◽  
Van Der Pol ◽  
Partial Differential ◽  
Nonlinear Odes ◽  
First Order

This paper develops and validates through a series of presentable examples, a comprehensive high-precision, and ultrafast computing concept for solving nonlinear ordinary differential equations (ODEs) and partial differential equations (PDEs) with cellular neural networks (CNN). The core of this concept is a straightforward scheme that we call "nonlinear adaptive optimization (NAOP),” which is used for a precise template calculation for solving nonlinear ODEs and PDEs through CNN processors. One of the key contributions of this work is to demonstrate the possibility of transforming different types of nonlinearities displayed by various classical and well-known nonlinear equations (e.g., van der Pol-, Rayleigh-, Duffing-, Rössler-, Lorenz-, and Jerk-equations, just to name a few) unto first-order CNN elementary cells, and thereby enabling the easy derivation of corresponding CNN templates. Furthermore, in the case of PDE solving, the same concept also allows a mapping unto first-order CNN cells while considering one or even more nonlinear terms of the Taylor's series expansion generally used in the transformation of a PDE in a set of coupled nonlinear ODEs. Therefore, the concept of this paper does significantly contribute to the consolidation of CNN as a universal and ultrafast solver of nonlinear ODEs and/or PDEs. This clearly enables a CNN-based, real-time, ultraprecise, and low-cost computational engineering. As proof of concept, two examples of well-known ODEs are considered namely a second-order linear ODE and a second order nonlinear ODE of the van der Pol type. For each of these ODEs, the corresponding precise CNN templates are derived and are used to deduce the expected solutions. An implementation of the concept developed is possible even on embedded digital platforms (e.g., field programmable gate array (FPGA), digital signal processor (DSP), graphics processing unit (GPU), etc.). This opens a broad range of applications. Ongoing works (as outlook) are using NAOP for deriving precise templates for a selected set of practically interesting ODEs and PDEs equation models such as Lorenz-, Rössler-, Navier Stokes-, Schrödinger-, Maxwell-, etc.

Predicting the exchange rate in Sudan using neural networks models during the period (1960 - 2017): التنبؤ بسعر الصرف في السودان باستخدام نماذج الشبكات العصبية خلال الفترة (1960م – 2017م)

2020 ◽  
Vol 4 (14) ◽  
Author(s):  
Fathi Ahmed Ali Adam, Mahmoud Mohamed Abdel Aziz Gamal El-Di
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Exchange Rate ◽  
Network Models ◽  
Neural Network Models ◽  
Classical Models ◽  
Artificial Neural ◽  
The Exchange Rate ◽  
Long Term Forecasting ◽  
Artificial Neural Network Models

The study examined the use of artificial neural network models to predict the exchange rate in Sudan through annual exchange rate data between the US dollar and the Sudanese pound. This study aimed to formulate the models of artificial neural networks in which the exchange rate can be predicted in the coming period. The importance of the study is that it is necessary to use modern models to predict instead of other classical models. The study hypothesized that the models of artificial neural networks have a high ability to predict the exchange rate. Use models of artificial neural networks. The most important results ability of artificial neural networks models to predict the exchange rate accurately, Form MLP (1-1-1) is the best model chosen for that purpose. The study recommended the development of the proposed model for long-term forecasting.

Sign in / Sign up

Export Citation Format

Share Document