scholarly journals Impedance Based Temperature Estimation of Lithium Ion Cells Using Artificial Neural Networks

Batteries ◽  
2021 ◽  
Vol 7 (4) ◽  
pp. 85
Author(s):  
Marco Ströbel ◽  
Julia Pross-Brakhage ◽  
Mike Kopp ◽  
Kai Peter Birke
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Electrochemical Impedance ◽  
Estimation Method ◽  
Lithium Ion ◽  
Computational Effort ◽  
Estimation Accuracy ◽  
Temperature Estimation ◽  
Lithium Ion Cells ◽  
Artificial Neural

Tracking the cell temperature is critical for battery safety and cell durability. It is not feasible to equip every cell with a temperature sensor in large battery systems such as those in electric vehicles. Apart from this, temperature sensors are usually mounted on the cell surface and do not detect the core temperature, which can mean detecting an offset due to the temperature gradient. Many sensorless methods require great computational effort for solving partial differential equations or require error-prone parameterization. This paper presents a sensorless temperature estimation method for lithium ion cells using data from electrochemical impedance spectroscopy in combination with artificial neural networks (ANNs). By training an ANN with data of 28 cells and estimating the cell temperatures of eight more cells of the same cell type, the neural network (a simple feed forward ANN with only one hidden layer) was able to achieve an estimation accuracy of ΔT= 1 K (10 ∘C <T< 60 ∘C) with low computational effort. The temperature estimations were investigated for different cell types at various states of charge (SoCs) with different superimposed direct currents. Our method is easy to use and can be completely automated, since there is no significant offset in monitoring temperature. In addition, the prospect of using the above mentioned approach to estimate additional battery states such as SoC and state of health (SoH) is discussed.

scholarly journals Fast Motion Model of Road Vehicles with Artificial Neural Networks

Electronics ◽  
2021 ◽  
Vol 10 (8) ◽  
pp. 928
Author(s):  
Ferenc Hegedüs ◽  
Péter Gáspár ◽  
Tamás Bécsi
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Dynamic Model ◽  
Piecewise Linear ◽  
Complex Problem ◽  
Computational Effort ◽  
Road Vehicles ◽  
Vehicle Motion ◽  
Artificial Neural ◽  
Original Dynamic

Nonlinear optimization-based motion planning algorithms have been successfully used for dynamically feasible trajectory planning of road vehicles. However, the main drawback of these methods is their significant computational effort and thus high runtime, which makes real-time application a complex problem. Addressing this field, this paper proposes an algorithm for fast simulation of road vehicle motion based on artificial neural networks that can be used in optimization-based trajectory planners. The neural networks are trained with supervised learning techniques to predict the future state of the vehicle based on its current state and driving inputs. Learning data is provided for a wide variety of randomly generated driving scenarios by simulation of a dynamic vehicle model. The realistic random driving maneuvers are created on the basis of piecewise linear travel velocity and road curvature profiles that are used for the planning of public roads. The trained neural networks are then used in a feedback loop with several variables being calculated by additional numerical integration to provide all the outputs of the original dynamic model. The presented model can be capable of short-term vehicle motion simulation with sufficient precision while having a considerably faster runtime than the original dynamic model.

scholarly journals Online Capacity Estimation for Lithium-Ion Batteries Based on Semi-Supervised Convolutional Neural Network

2021 ◽  
Vol 12 (4) ◽  
pp. 256
Author(s):  
Yi Wu ◽  
Wei Li
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Lithium Ion Batteries ◽  
Estimation Method ◽  
Lithium Ion ◽  
Estimation Methods ◽  
Estimation Accuracy ◽  
Capacity Estimation ◽  
Practical Applications

Accurate capacity estimation can ensure the safe and reliable operation of lithium-ion batteries in practical applications. Recently, deep learning-based capacity estimation methods have demonstrated impressive advances. However, such methods suffer from limited labeled data for training, i.e., the capacity ground-truth of lithium-ion batteries. A capacity estimation method is proposed based on a semi-supervised convolutional neural network (SS-CNN). This method can automatically extract features from battery partial-charge information for capacity estimation. Furthermore, a semi-supervised training strategy is developed to take advantage of the extra unlabeled sample, which can improve the generalization of the model and the accuracy of capacity estimation even in the presence of limited labeled data. Compared with artificial neural networks and convolutional neural networks, the proposed method is demonstrated to improve capacity estimation accuracy.

Damaged Cell Location on Lithium-Ion Batteries Using Artificial Neural Networks

2020 ◽  
pp. 477-486
Author(s):  
Mateus Moro Lumertz ◽  
Felipe Gozzi da Cruz ◽  
Rubisson Duarte Lamperti ◽  
Leandro Antonio Pasa ◽  
Diogo Marujo
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Lithium Ion Batteries ◽  
Lithium Ion ◽  
Artificial Neural

scholarly journals The Estimation of Product Standard Time by Artificial Neural Networks in the Molding Industry

2009 ◽  
Vol 2009 ◽  
pp. 1-12 ◽  
Author(s):  
Ergün Eraslan
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Estimation Method ◽  
Time Estimation ◽  
Robust Algorithms ◽  
Standard Time ◽  
Special Measurement ◽  
Artificial Neural ◽  
Product Standard

Determination of exact standard time with direct measurement procedures is particularly difficult in companies which do not have an adequate environment suitable for time measurement studies or which produce goods requiring complex production schedules. For these companies new and special measurement procedures need to be developed. In this study, a new time estimation method based on different robust algorithms of artificial neural networks (ANNs) is developed. For the proposed method, the products that have similar production processes were chosen from among the whole product range within the cleansing department of a molding company. While using ANNs, to train the network, some of the chosen products' standard time that had been previously measured is used to estimate the standard time of the remaining products. The different ANN algorithms are trained and four of them, which are converged the data, are stated and compared in different architectures. In this way, it is concluded that this estimation method could be applied accurately in many similar processes using the relevant algorithms.

scholarly journals Optimizing Predictor Variables in Artificial Neural Networks When Forecasting Raw Material Prices for Energy Production

Energies ◽  
2020 ◽  
Vol 13 (8) ◽  
pp. 2017 ◽  
Author(s):  
Marta Matyjaszek ◽  
Gregorio Fidalgo Valverde ◽  
Alicja Krzemień ◽  
Krzysztof Wodarski ◽  
Pedro Riesgo Fernández
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Energy Production ◽  
Forecast Accuracy ◽  
Raw Material ◽  
Predictor Variables ◽  
Estimation Accuracy ◽  
Optimum Number ◽  
Variable Size ◽  
Artificial Neural

This paper applies a heuristic approach to optimize the predictor variables in artificial neural networks when forecasting raw material prices for energy production (coking coal, natural gas, crude oil and coal) to achieve a better forecast. Two goals are (1) to determine the optimum number of time-delayed terms or past values forming the lagged variables and (2) to improve the forecast accuracy by adding intrinsic signals to the lagged variables. The conclusions clearly are in opposition to the actual scientific literature: when addressing the lagged variable size, the results do not confirm relationships among their size, representativeness and estimation accuracy. It is also possible to verify an important effect of the results on the lagged variable size. Finally, adding the order in the time series of the lagged variables to form the predictor variables improves the forecast accuracy in most cases.

Sign in / Sign up

Export Citation Format

Share Document