State of Charge Estimation using Recurrent Neural Networks with Long Short-Term Memory for Lithium-Ion Batteries

Bockrath, Steffen; Rosskopf, Andreas; Koffel, S.; Waldhör, Stefan; Srivastava, Kashvi; Lorentz, V.R.H.

doi:10.1109/iecon.2019.8926815

Cited by 16 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using LSTMs it was shown, that the ML based simulation approach outperformed classical approaches for SOC-prediction via analytical models, namely an analytical equivalent circuit model combined with an Extended Kalman Filter, with respect to the achieved accuracy. The same statement holds for another investigation regarding the use case of SOC prediction with RNNs (Chemali et al, 2018), but specializing in the use and prediction of measurement data of real driving cycles instead of test bench data under well-defined conditions in laboratory as used in Bockrath et al, 2019. However, in the related work LSTMs were utilized whereas in this contribution gated recurrent units are investigated more closely. Furthermore, the mentioned publications only investigated the ML based simulation approaches for lithium ion batteries models and did not focus on modelling the whole physical effect chains from wheel to battery of hybrid or battery electric vehicles, which is necessary for the optimization and validation of energy management software (see section 4).…”

Section: Related Scientific Workmentioning

confidence: 78%

See 1 more Smart Citation

Machine Learning Based Simulation for Design Space Exploration

2022

View full text Add to dashboard Cite

Design of software in the automotive domain often involves simulation to allow early software parametrization. Modeling complex systems or components impacted by the software in an analytical way can be time-consuming, require domain knowledge and executing the analytical models can result in high computational effort. In specific applications, these challenges can be overcome by applying machine learning based simulation. This contribution presents results of a case study in which powertrain components are modeled data-driven with artificial neural networks to support design space exploration

show abstract

Section: Related Scientific Workmentioning

confidence: 78%

“…Taking the specific use case of this publication, namely the estimation of the state of charge (SOC) of hybrid vehicles and battery electric vehicles (section 4) for virtual validation into account, one of the most relevant related work is focused on the estimation of the SOC with RNNs (Bockrath et al, 2019).…”

Section: Related Scientific Workmentioning

confidence: 99%

Machine Learning Based Simulation for Design Space Exploration

2022

View full text Add to dashboard Cite

show abstract

“…Concurrently, equivalent circuit models (ECM) are often limited due to their poor robustness regarding the highly non-linear dependence of the battery state parameters on the changes of environment and working conditions during a battery's operation. ML and DL approaches like recurrent neural networks, and temporal convolutional neural networks have demonstrated their potential to overcome these problems due to their high adaptability and self-learning ability (Bockrath et al, 2019;AI4DI, 2019). Furthermore, by combining the neural network with a priori knowledge and physical laws, physical guided neural networks can be derived considering physical relationships.…”

Section: Energy Domainmentioning

confidence: 99%

Automotive Intelligence Embedded in Electric Connected Autonomous and Shared Vehicles Technology for Sustainable Green Mobility

Vermesan

John

Pype

et al. 2021

Front. Future Transp.

View full text Add to dashboard Cite

The automotive sector digitalization accelerates the technology convergence of perception, computing processing, connectivity, propulsion, and data fusion for electric connected autonomous and shared (ECAS) vehicles. This brings cutting-edge computing paradigms with embedded cognitive capabilities into vehicle domains and data infrastructure to provide holistic intrinsic and extrinsic intelligence for new mobility applications. Digital technologies are a significant enabler in achieving the sustainability goals of the green transformation of the mobility and transportation sectors. Innovation occurs predominantly in ECAS vehicles’ architecture, operations, intelligent functions, and automotive digital infrastructure. The traditional ownership model is moving toward multimodal and shared mobility services. The ECAS vehicle’s technology allows for the development of virtual automotive functions that run on shared hardware platforms with data unlocking value, and for introducing new, shared computing-based automotive features. Facilitating vehicle automation, vehicle electrification, vehicle-to-everything (V2X) communication is accomplished by the convergence of artificial intelligence (AI), cellular/wireless connectivity, edge computing, the Internet of things (IoT), the Internet of intelligent things (IoIT), digital twins (DTs), virtual/augmented reality (VR/AR) and distributed ledger technologies (DLTs). Vehicles become more intelligent, connected, functioning as edge micro servers on wheels, powered by sensors/actuators, hardware (HW), software (SW) and smart virtual functions that are integrated into the digital infrastructure. Electrification, automation, connectivity, digitalization, decarbonization, decentralization, and standardization are the main drivers that unlock intelligent vehicles' potential for sustainable green mobility applications. ECAS vehicles act as autonomous agents using swarm intelligence to communicate and exchange information, either directly or indirectly, with each other and the infrastructure, accessing independent services such as energy, high-definition maps, routes, infrastructure information, traffic lights, tolls, parking (micropayments), and finding emergent/intelligent solutions. The article gives an overview of the advances in AI technologies and applications to realize intelligent functions and optimize vehicle performance, control, and decision-making for future ECAS vehicles to support the acceleration of deployment in various mobility scenarios. ECAS vehicles, systems, sub-systems, and components are subjected to stringent regulatory frameworks, which set rigorous requirements for autonomous vehicles. An in-depth assessment of existing standards, regulations, and laws, including a thorough gap analysis, is required. Global guidelines must be provided on how to fulfill the requirements. ECAS vehicle technology trustworthiness, including AI-based HW/SW and algorithms, is necessary for developing ECAS systems across the entire automotive ecosystem. The safety and transparency of AI-based technology and the explainability of the purpose, use, benefits, and limitations of AI systems are critical for fulfilling trustworthiness requirements. The article presents ECAS vehicles’ evolution toward domain controller, zonal vehicle, and federated vehicle/edge/cloud-centric based on distributed intelligence in the vehicle and infrastructure level architectures and the role of AI techniques and methods to implement the different autonomous driving and optimization functions for sustainable green mobility.

show abstract

“…36 Other essential techniques based on recurrent neural networks (RNN) are well suited for modeling complex and nonlinear systems due to their characteristic-nonparametric modeling, probabilistic prediction, and relative robustness. 23 The variants of RNN, typically z E-mail: 1935085435@qq.com the long short-term memory (LSTM) 37,38 and the gated recursive units (GRU) 39,40 that address the gradient vanishing phenomenon existing in RNN during traditional backpropagation training, are extensively applied to learn the long-term dependencies among the degraded capacities of LIBs. Currently, other algorithms are integrated with the variants of RNN frequently for jointly estimating SOC to maximally make full use of their benefits.…”

mentioning

confidence: 99%

State of Charge Estimation for Lithium-Ion Batteries Based on TCN-LSTM Neural Networks

Cheng

et al. 2022

J. Electrochem. Soc.

View full text Add to dashboard Cite

Accurately estimating the state of charge (SOC) of lithium-ion batteries is critical for developing more reliable and efficient electric vehicles. However, the commonly used models cannot simultaneously extract effective spatial and temporal features from the original data, leading to an inefficient SOC estimation. This paper proposes a novel neural network method for accurate and robust battery SOC estimation, which incorporates the temporal convolutional network (TCN) and the long short-term memory (LSTM), namely TCN-LSTM model. Specifically, the TCN is employed to extract more advanced spatial features among multivariate variables, and the LSTM captures long-term dependencies from time-series data and maps battery temporal information into current SOC and historical inputs. The proposed model performs well in various estimation conditions. The average value of mean absolute error, root mean square error, and maximum error of SOC estimation achieve 0.48%, 0.60%, and 2.3% at multiple temperature conditions, respectively, and reach 0.70%, 0.81%, and 2.7% for a different battery, respectively. In addition, the proposed method has better accuracy than the LSTM or TCN used independently and the CNN-LSTM network. The computational burden with varying length of input is also investigated. In summary, experiment results show that the proposed method has excellent generalization and robustness.

show abstract

State of Charge Estimation using Recurrent Neural Networks with Long Short-Term Memory for Lithium-Ion Batteries

Cited by 16 publications

References 5 publications

Machine Learning Based Simulation for Design Space Exploration

Machine Learning Based Simulation for Design Space Exploration

Automotive Intelligence Embedded in Electric Connected Autonomous and Shared Vehicles Technology for Sustainable Green Mobility

State of Charge Estimation for Lithium-Ion Batteries Based on TCN-LSTM Neural Networks

Contact Info

Product

Resources

About