An official website of the United States government
The development of lithium-ion battery technology has ensured that battery thermal management systems are an essential component of the battery pack for next-generation energy storage systems. Using dielectric immersion cooling, researchers have demonstrated the ability to attain high heat transfer rates due to the direct contact between cells and the coolant. However, feedback control has not been widely applied to immersion cooling schemes. Furthermore, current research has not considered battery pack plant design when optimizing feedback control. Uncertainties are inherent in the cooling equipment, resulting in temperature and flow rate fluctuations. Hence, it is crucial to systematically consider these uncertainties during cooling system design to improve the performance and reliability of the battery pack. To fill this gap, we established a reliability-based control co-design optimization framework using machine learning for immersion cooled battery packs. We first developed an experimental setup for 21700 battery immersion cooling, and the experiment data were used to build a high-fidelity multiphysics finite element model. The model can precisely represent the electrical and thermal profile of the battery. We then developed surrogate models based on the finite element simulations in order to reduce computational cost. The reliability-based control co-design optimization was employed to find the best plant and control design for the cooling system, in which an outer optimization loop minimized the cooling system cost while an inner loop ensured battery pack reliability. Finally, an optimal cooling system design was obtained and validated, which showed a 90% saving in cooling system energy consumption.
more »
« less
Integration of Hardware and Software for Battery Hardware-In-the-Loop Towards Battery Artificial Intelligence
This paper demonstrates a novel, compact-sized hardware-in-the-loop system, and its verification using machine learning and artificial intelligence features in battery controls. Conventionally, a battery management system involves algorithm development for battery modeling, estimation, and control. These tasks are typically validated by running the battery tester open-loop, i.e., the tester equipment executes the pre-defined experimental protocols line by line. Additional equipment is required to make the testing closed-loop, but the integration is typically not straightforward. To improve flexibility and accessibility for battery management, this work proposes a low-cost highly reliable closed-loop charger and discharger. We first focus on the electronic circuit design for battery testing systems to maximize the applied current accuracy and precision. After functional verification, we further investigate applications for closed-loop battery management systems. In particular, we extend the proposed architecture into the learning-based control design, which is a feedback controller. We utilize reinforcement learning techniques to highlight the benefits of closed-loop controls. As an example, we compare this learning-based control strategy with a conventional battery charging control. The experimental results demonstrate that the proposed experimental design is able to handle the learning-based controller and achieve a more reliable and safer charging protocol driven by artificial intelligence.
more »
« less
- Award ID(s):
- 1847177
- PAR ID:
- 10414957
- Date Published:
- Journal Name:
- IEEE Transactions on Transportation Electrification
- ISSN:
- 2372-2088
- Page Range / eLocation ID:
- 1 to 1
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Real-time (RT) simulation of power and energy conversion systems allows engineers to interface both simulation- and hardware-based controls using controller hardware-in-the-loop (CHiL) simulation of networks of power electronic converters (PECs) in order to de-risk highly developmental systems such as next generation electrified transportation systems and dc microgrids. CHiL exploration and performance verification moves a design from Technology Readiness Level (TRL) 3 to TRL 4 without incurring significant cost investments in developmental hardware platforms, which otherwise discourages such endeavors. A real-time CHiL simulation platform suitable for explorations of protective equipment, protection schemes and networked PEC dc and mixed dc-ac power distribution architectures must be capable of simulating common-mode behavior, various grounding schemes, and fault transients at sufficiently high resolution. This paper demonstrates this capability using a Latency-Based Linear Multistep Compound (LB-LMC) simulation method implemented in a commercially sustainable, adaptable and expandable FPGA-based test and instrumentation platform. The proposed CHiL platform achieves real-time power system simulations, including detailed switching commutations of networked PECs, with 50 ns resolution, and faithfully produces resonant and transient behaviors associated with line-to-ground (LG) and line-to-line (LL) faults and fault recovery in ungrounded PEC-based dc systems. This resolution in RT cannot be achieved with today’s commercial off-the-shelf CHiL platforms. This paper demonstrates the need for high resolution RT simulation of LG and LL faults within dc systems, and demonstrates a CHiL approach that enables dc protection design explorations and protective control hardware testing while taking into account the realistic aspects that affect fault characteristics in PEC-based dc systems, such as cable current rating and length, cable and PEC parasitic LG capacitance and PEC i...more » « less
-
null (Ed.)This paper presents a framework to refine identified artificial neural networks (ANN) based state-space linear parametervarying (LPV-SS) models with closed-loop data using online transfer learning. An LPV-SS model is assumed to be first identified offline using inputs/outputs data and a model predictive controller (MPC) designed based on this model. Using collected closed-loop batch data, the model is further refined using online transfer learning and thus the control performance is improved. Specifically, fine-tuning, a transfer learning technique, is employed to improve the model. Furthermore, the scenario where the offline identified model and the online controlled system are “similar but not identitical” is discussed. The proposed method is verified by testing on an experimentally validated high-fidelity reactivity controlled compression ignition (RCCI) engine model. The verification results show that the new online transfer learning technique combined with an adaptive MPC law improves the engine control performance to track requested engine loads and desired combustion phasing with minimum errors.more » « less
-
Testing and verifying the security of connected and autonomous vehicles (CAVs) under cyber-physical attacks is a critical challenge for ensuring their safety and reliability. Proposed in this article is a novel testing framework based on a model of computation that generates scenarios and attacks in a closed-loop manner, while measuring the safety of the unit under testing (UUT), using a verification vector. The framework was applied for testing the performance of two cooperative adaptive cruise control (CACC) controllers under false data injection (FDI) attacks. Serving as the baseline controller is one of a traditional design, while the proposed controller uses a resilient design that combines a model and learning-based algorithm to detect and mitigate FDI attacks in real-time. The simulation results show that the resilient controller outperforms the traditional controller in terms of maintaining a safe distance, staying below the speed limit, and the accuracy of the FDI estimation.more » « less
-
null (Ed.)Abstract This paper presents a framework to refine identified artificial neural networks (ANN) based state-space linear parameter-varying (LPV-SS) models with closed-loop data using online transfer learning. An LPV-SS model is assumed to be first identified offline using inputs/outputs data and a model predictive controller (MPC) designed based on this model. Using collected closed-loop batch data, the model is further refined using online transfer learning and thus the control performance is improved. Specifically, fine-tuning, a transfer learning technique, is employed to improve the model. Furthermore, the scenario where the offline identified model and the online controlled system are “similar but not identitical” is discussed. The proposed method is verified by testing on an experimentally validated high-fidelity reactivity controlled compression ignition (RCCI) engine model. The verification results show that the new online transfer learning technique combined with an adaptive MPC law improves the engine control performance to track requested engine loads and desired combustion phasing with minimum errors.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1109/TTE.2023.3270870
