Next Article in Journal
Influence of Harmonic and DC-Bias Coupling on Transformer Energization Inrush Current in Complex Power Grids
Previous Article in Journal
EnergyPlus EMS Methodology for Dynamic Integration of Earth-to-Air Heat Exchangers in Building Energy Simulation: Implementation, Calibration and Annual Performance Assessment
Previous Article in Special Issue
CFD-Driven Design of an Air-Cooling System for Lithium-Ion Battery Packs in a Formula Student Car
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Energies
Volume 19
Issue 18
10.3390/en19184454
energies-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Prediction-Assisted Control of an Electric-Vehicle CO2 Heat Pump with Secondary Throttling Based on a Bidirectional Feedforward Neural Network

by
Fengxian Wang
1,2,3,
Junjie Wu
2,3,
Ping Zhou
2,
Yuanxing Zhu
2,
Changjiang Li
2,
Haibo Yang
2 and
Jiaheng Chen
1,*
1
School of Mechanical and Power Engineering, Zhengzhou University, Zhengzhou 450001, China
2
Institute of Technology and Innovation, Zhengzhou China Resources Gas Co., Ltd., Zhengzhou 450003, China
3
Zhengzhou Runwu Energy Technology Co., Ltd., Zhengzhou 450003, China
*
Author to whom correspondence should be addressed.
Energies 2026, 19(18), 4454; https://doi.org/10.3390/en19184454 (registering DOI)
Submission received: 30 July 2026 / Revised: 14 September 2026 / Accepted: 16 September 2026 / Published: 20 September 2026
(This article belongs to the Special Issue Advanced Thermal Management in Electric Vehicles)
Browse Figures
Versions Notes

Abstract

To improve the low-temperature heating performance of electric-vehicle CO2 heat pumps, their system configurations and control strategies have become increasingly complex. This has made coordinated regulation among multiple components more difficult and can lead to delayed supply-air temperature response, operating fluctuations, and other problems. Accordingly, this study proposes a shared-parameter bidirectional feedforward neural network (BFNN)-assisted regulation method. The method jointly learns the forward and inverse relationships between controllable components and the prediction variable. The inverse path generates candidate operating parameters, which are verified and corrected by the forward path to improve regulation efficiency. Under a −20 °C cold-start condition, the BFNN-assisted strategy achieved a supply-air temperature stabilization time of 8.2 min, 45.6% and 56.3% shorter than those of unidirectional FNN-assisted control and conventional rule-based feedback control, respectively. Compared with rule-based feedback control, the time-averaged heating COP over the 30 min test increased by 8.9%, while compressor energy consumption decreased by 19.0%. When cabin-side airflow increased from 300 to 550 m3/h, the BFNN-assisted strategy limited the maximum temperature drop to 2.50 °C and the recovery time to 1.67 min. Under the tested conditions, the integrated BFNN-assisted control strategy improved the CO2 heat pump system temperature-response and energy-performance metrics.
Keywords: CO2 heat pump; electric vehicle; bidirectional feedforward neural network; prediction-assisted control; secondary throttling CO2 heat pump; electric vehicle; bidirectional feedforward neural network; prediction-assisted control; secondary throttling

Share and Cite

MDPI and ACS Style

Wang, F.; Wu, J.; Zhou, P.; Zhu, Y.; Li, C.; Yang, H.; Chen, J. Prediction-Assisted Control of an Electric-Vehicle CO2 Heat Pump with Secondary Throttling Based on a Bidirectional Feedforward Neural Network. Energies 2026, 19, 4454. https://doi.org/10.3390/en19184454

AMA Style

Wang F, Wu J, Zhou P, Zhu Y, Li C, Yang H, Chen J. Prediction-Assisted Control of an Electric-Vehicle CO2 Heat Pump with Secondary Throttling Based on a Bidirectional Feedforward Neural Network. Energies. 2026; 19(18):4454. https://doi.org/10.3390/en19184454

Chicago/Turabian Style

Wang, Fengxian, Junjie Wu, Ping Zhou, Yuanxing Zhu, Changjiang Li, Haibo Yang, and Jiaheng Chen. 2026. "Prediction-Assisted Control of an Electric-Vehicle CO2 Heat Pump with Secondary Throttling Based on a Bidirectional Feedforward Neural Network" Energies 19, no. 18: 4454. https://doi.org/10.3390/en19184454

APA Style

Wang, F., Wu, J., Zhou, P., Zhu, Y., Li, C., Yang, H., & Chen, J. (2026). Prediction-Assisted Control of an Electric-Vehicle CO2 Heat Pump with Secondary Throttling Based on a Bidirectional Feedforward Neural Network. Energies, 19(18), 4454. https://doi.org/10.3390/en19184454

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop