| 1. |
- Zhu, Qingbo, 1992, et al.
(author)
-
Predicting Electric Vehicle Energy Consumption from Field Data Using Machine Learning
- 2024
-
In: IEEE Transactions on Transportation Electrification. - 2332-7782. ; In Press
-
Journal article (peer-reviewed)abstract
- This study addresses the challenge of accurately forecasting the energy consumption of electric vehicles (EVs), which is crucial for reducing range anxiety and advancing strategies for charging and energy optimization. Despite the limitations of current forecasting methods, including empirical, physics-based, and data-driven models, this paper presents a novel machine learning-based prediction framework. It integrates physics-informed features and combines offline global models with vehicle-specific online adaptation to enhance prediction accuracy and assess uncertainties. Our framework is tested extensively on data from a real-world fleet of EVs. While the leading global model, quantile regression neural network (QRNN), demonstrates an average error of 6.30%, the online adaptation further achieves a notable reduction to 5.04%, with both surpassing the performance of existing models significantly. Moreover, for a 95% prediction interval, the online adapted QRNN improves coverage probability to 91.27% and reduces the average width of prediction intervals to 0.51. These results demonstrate the effectiveness and efficiency of utilizing physics-based features and vehicle-based online adaptation for predicting EV energy consumption.
|
|
| 2. |
- Huang, Yicun, 1992, et al.
(author)
-
MINN: Learning the dynamics of differential-algebraic equations and application to battery modeling
- 2023
-
In: IEEE Transactions on Pattern Analysis and Machine Intelligence. - 1939-3539 .- 0162-8828.
-
Journal article (peer-reviewed)abstract
- The concept of integrating physics-based and data-driven approaches has become popular for modeling sustainable energy systems. However, the existing literature mainly focuses on the data-driven surrogates generated to replace physics-based models. These models often trade accuracy for speed but lack the generalisability, adaptability, and interpretability inherent in physics-based models, which are often indispensable in the modeling of real-world dynamic systems for optimization and control purposes. In this work, we propose a novel architecture for generating model-integrated neural networks (MINN) to allow integration on the level of learning physics-based dynamics of the system. The obtained hybrid model solves an unsettled research problem in control-oriented modeling, i.e., how to obtain an optimally simplified model that is physically insightful, numerically accurate, and computationally tractable simultaneously. We apply the proposed neural network architecture to model the electrochemical dynamics of lithium-ion batteries and show that MINN is extremely data-efficient to train while being sufficiently generalizable to previously unseen input data, owing to its underlying physical invariants. The MINN battery model has an accuracy comparable to the first principle-based model in predicting both the system outputs and any locally distributed electrochemical behaviors but achieves two orders of magnitude reduction in the solution time.
|
|
| 3. |
- Huang, Yicun, 1992, et al.
(author)
-
Phase field model of faceted anatase TiO2 dendrites in low pressure chemical vapor deposition
- 2021
-
In: Applied Physics Letters. - : AIP Publishing. - 0003-6951 .- 1077-3118. ; 119:22
-
Journal article (peer-reviewed)abstract
- Anatase TiO2 nanorods with a well-defined ⟨110⟩⟨110⟩ texture have been studied using a model-based characterization technique based on a previous modeling framework. Intricate secondary side facet characteristics of tilt angles of 26.5∘26.5° have been indexed, and a ⟨112⟩⟨112⟩ growth direction of the well-aligned facets is identified. These results have not been accessed experimentally but crucial in understanding the nature of the most abundant facets and their structural properties. We find agreement between our results and indirect experimental measurements. Highly exposed {116} facets are found to be responsible for excellent electrochemical surface properties in nanostructured anatase TiO2 thin films.
|
|
| 4. |
- Li, Yang, 1984, et al.
(author)
-
A PDE Model Simplification Framework for All-Solid-State Batteries
- 2022
-
In: American Control Conference. - 0743-1619. ; 2022-June, s. 1775-1781
-
Conference paper (peer-reviewed)abstract
- All-solid-state batteries (ASSBs) have attracted immense attention due to their superior thermal stability, improved power and energy densities, and prolonged cycle life. Their practical applications require accurate and computationally efficient models for the design and implementation of many onboard management algorithms, so that the safety, health, and cycling performance of ASSBs can be optimized under a wide range of operating conditions. A control-oriented modeling framework is thus established in this work by systematically simplifying a partial differential equation (PDE) based model of the ASSBs developed from underlying electrochemical principles. Compared to the original PDE model, the reduced-order models obtained with the proposed framework demonstrates high fidelity at significantly improved computational efficiency.
|
|
| 5. |
- Li, Yang, 1984, et al.
(author)
-
Control-Oriented Modeling of All-Solid-State Batteries Using Physics-Based Equivalent Circuits
- 2022
-
In: IEEE Transactions on Transportation Electrification. - 2332-7782. ; 8:2, s. 2080-2092
-
Journal article (peer-reviewed)abstract
- Considered as one of the ultimate energy storage technologies for electrified transportation, the emerging all-solid-state batteries (ASSBs) have attracted immense attention due to their superior thermal stability, increased power and energy densities, and prolonged cycle life. To achieve the expected high performance, practical applications of ASSBs require accurate and computationally efficient models for the design and implementation of many onboard management algorithms, so that the ASSB safety, health, and cycling performance can be optimized under a wide range of operating conditions. A control-oriented modeling framework is thus established in this work by systematically simplifying a rigorous partial differential equation (PDE) based model of the ASSBs developed from underlying electrochemical principles. Specifically, partial fraction expansion and moment matching are used to obtain ordinary differential equation based reduced-order models (ROMs). By expressing the models in a canonical circuit form, excellent properties for control design such as structural simplicity and full observability are revealed. Compared to the original PDE model, the developed ROMs have demonstrated high fidelity at significantly improved computational efficiency. Extensive comparisons have also been conducted to verify its superiority to the prevailing models due to the consideration of concentration-dependent diffusion and migration. Such ROMs can thus be used for advanced control design in future intelligent management systems of ASSBs.
|
|
| 6. |
- Li, Yang, 1984, et al.
(author)
-
Nonlinear Model Inversion-Based Output Tracking Control for Battery Fast Charging
- 2024
-
In: IEEE Transactions on Control Systems Technology. - 1063-6536 .- 1558-0865. ; 32:1, s. 225-240
-
Journal article (peer-reviewed)abstract
- We propose a novel nonlinear control approach for fast charging of lithium-ion batteries, where health- and safety-related variables, or their time derivatives, are expressed in an input-polynomial form. By converting a constrained optimal control problem into an output tracking problem with multiple tracking references, the required control input, i.e., the charging current, is obtained by computing a series of candidate currents associated with different tracking references. Consequently, an optimization-free nonlinear model inversion-based control algorithm is derived for charging the batteries. We demonstrate the efficacy of our method using a spatially discretized high-fidelity pseudo-two-dimensional (P2D) model with thermal dynamics. Conventional methods require computationally demanding optimization to solve the corresponding fast charging problem for such a high-order system, leading to practical difficulties in achieving low-cost implementation. Results from comparative studies show that the proposed controller can achieve performance very close to nonlinear and linearized model predictive control but with much lower computational costs and minimal parameter tuning efforts.
|
|
| 7. |
- Li, Yang, 1984, et al.
(author)
-
Optimization-free fast charging for lithium-ion batteries using model inversion techniques
- 2023
-
In: IFAC-PapersOnLine. - 2405-8963. ; 56:2, s. 6636-6641
-
Conference paper (peer-reviewed)abstract
- We propose a novel fast-charging control framework for lithium-ion (Li-ion) batteries that can leverage a class of models including the high-dimensional, electrochemical-thermal pseudo-two-dimensional model. The control objective is to find the highest battery current while fulfilling various operating constraints. Conventionally, computationally demanding optimization is needed to solve such a constrained optimal control problem when an electrochemicalthermal model is used, leading to practical difficulties in achieving low-cost implementation. Instead, this paper provides an optimization-free solution to Li-ion battery fast charging by converting the constrained optimal control problem into an output tracking problem with multiple tracking references. The required control input, i.e., the charging current, is derived by inverting the battery model. As a result, a nonlinear inversion-based control algorithm is obtained for Li-ion battery fast charging. Results from comparative studies show that the proposed controller can achieve performance close to nonlinear model predictive control but at significantly reduced computational costs and parameter tuning efforts.
|
|
| 8. |
- Peprah, Godwin, 1990, et al.
(author)
-
Control-Oriented 2D Thermal Modelling of Cylindrical Battery Cells for Optimal Tab and Surface Cooling
- 2024
-
In: Proceedings of the American Control Conference. - 0743-1619.
-
Conference paper (peer-reviewed)abstract
- Minimising cell thermal gradients and the average temperature rise requires an optimal combination of tab and surface cooling methods to leverage their unique advantages. This work presents a computationally efficient two-dimensional (2D) thermal model for cylindrical lithium-ion battery cells that is developed based on the Chebyshev Spectral-Galerkin method and allows the independent control of tab and surface cooling channels for effective thermal performance optimisa- tion. This obtained model is validated against a high-fidelity finite element model under the worldwide harmonised light vehicle test procedure (WLTP). Results show that the reduced-order model with as few as two states can predict the spatially resolved temperature distribution throughout the cell and that in aggressive cooling scenarios, a model order of nine states can improve accuracy by about 84%. It is also shown that even though cooling all sides of the cylindrical cell achieves the lowest average temperature rise, cooling only the top and bottom sides provides minimum radial thermal gradients.
|
|
| 9. |
- Zhang, Yizhou, 1991, et al.
(author)
-
Early prediction of battery life by learning from both time-series and histogram data
- 2023
-
In: IFAC Proceedings Volumes (IFAC-PapersOnline). - 1474-6670. ; 56:2, s. 3770-3775
-
Conference paper (peer-reviewed)abstract
- Due to dynamic operating conditions, random user behaviors, and cell-to-cell variations, accurately predicting battery life is challenging, especially using information from only a few early cycles. This work proposes a data-driven battery early prediction pipeline using both time-series, measurement-related features, and usage-related histogram features. We first investigate the prediction performance of using these two feature sources individually, then two methods of systematically combining these two feature sources are devised. Additionally, four machine learning algorithms with different characteristics are applied to compare their performances on battery prognostic problems. We show that the prediction accuracy of using these two feature sources individually is comparable. Moreover, a systematic combination of these two features considerably improves the prediction performance in terms of accuracy and robustness, achieving excellent prediction results with a root mean square error of around 150 cycles using only the first 100 cycle’s data. Finally, experimental data of different cell types and cycling conditions are used to verify the developed method’s effectiveness and generality.
|
|
