skip to main content

Attention:

The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 11:00 PM ET on Friday, July 12 until 2:00 AM ET on Saturday, July 13 due to maintenance. We apologize for the inconvenience.


Title: 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
NSF-PAR ID:
10414957
Author(s) / Creator(s):
; ;
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
  1. 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
  2. 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
  3. 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
  4. Bartocci, Ezio ; Putot, Sylvie (Ed.)
    Switched systems are known to exhibit subtle (in)stability behaviors requiring system designers to carefully analyze the stability of closed-loop systems that arise from their proposed switching control laws. This paper presents a formal approach for verifying switched system stability that blends classical ideas from the controls and verification literature using differential dynamic logic (dL), a logic for deductive verification of hybrid systems. From controls, we use standard stability notions for various classes of switching mechanisms and their corresponding Lyapunov function-based analysis techniques. From verification, we use dL's ability to verify quantified properties of hybrid systems and dL models of switched systems as looping hybrid programs whose stability can be formally specified and proven by finding appropriate loop invariants, i.e., properties that are preserved across each loop iteration. This blend of ideas enables a trustworthy implementation of switched system stability verification in the KeYmaera X prover based on dL. For standard classes of switching mechanisms, the implementation provides fully automated stability proofs, including searching for suitable Lyapunov functions. Moreover, the generality of the deductive approach also enables verification of switching control laws that require non-standard stability arguments through the design of loop invariants that suitably express specific intuitions behind those control laws. This flexibility is demonstrated on three case studies: a model for longitudinal flight control by Branicky, an automatic cruise controller, and Brockett's nonholonomic integrator. 
    more » « less
  5. We present a verification-based learning framework VEL that synthesizes safe programmatic controllers for environments with continuous state and action spaces. The key idea is the integration of program reasoning techniques into controller training loops. VEL performs abstraction-based program verification to reason about a programmatic controller and its environment as a closed-loop system. Based on a novel verification-guided synthesis loop for training, VEL minimizes the amount of safety violation in the proof space of the system, which approximates the worst-case safety loss, using gradient-descent style optimization. Experimental results demonstrate the substantial benefits of leveraging verification feedback for synthesizing provably correct controllers. 
    more » « less