Real-Time PMV Thermal Comfort Index Observer Based on Artificial Neural Networks for Infrared Heating Panel Control Rimac Technology

Format:

Book

Conference/Event

Author/Creator:

Cvok, Ivan, author.

Contributor:

Miklauzic, Filip

Yerramilli-Rao, Isha

Conference Name:

WCX SAE World Congress Experience (2025-04-08 : Detroit, Michigan, United States)

Language:

English

Physical Description:

1 online resource cm

Place of Publication:

Warrendale, PA SAE International 2025

Summary:

Improving electric vehicles' range can be achieved by integrating infrared heating panels (IRPs) into the existing Heating Ventilation and Air-Conditioning system to reduce battery energy consumption while maintaining thermal comfort. Localized comfort control enabled by IRPs is facilitated by thermal comfort index feedback to the control strategy, such as the well-known Predicted Mean Vote (PMV). PMV is obtained by solving nonlinear equations iteratively, which is computationally expensive for vehicle control units and may not be feasible for real-time control. This paper presents the design of real-time capable thermal comfort observer based on feedforward artificial neural network (ANN), utilized for estimating the local PMV extended with IRP radiative heating effects. The vehicle under consideration is equipped with 12 heating panels (zones) organized into six controller clusters that rely on the average PMV feedback from its respective zone provided by a dedicated ANN. Each of six ANNs is designed with five inputs and features an input layer, one fully connected layer and output layer to predict the average cluster PMV. Four inputscabin air temperature and relative humidity, cabin inlet air temperature and blower fan flow rateare shared across all ANNs, while the fifth input is specific to each ANN, representing the clusters' IRPs average temperature. The training data for ANNs is generated using an experimentally parametrized high-fidelity cabin model which incorporates 12 local IRP zones and CFD-based air distribution model. Bayesian optimization is employed to optimize the ANN structure and training hyperparameters such as number of neurons and learning rate. Performance of ANN observer integrated within overall control strategy is demonstrated in simulation and benchmarked against ideal PMV feedback. Experimental validation through Hardware-in-the-Loop testing demonstrated that the ANNs require less than 3% of the production VCU's processing power while operating at a 100 Hz sampling rate with low memory footprint

Notes:

Vendor supplied data

Publisher Number:

2025-01-8139

Access Restriction:

Restricted for use by site license