Data-driven prediction of vehicle cabin thermal comfort: using machine learning and high-fidelity simulation results

Warey, Alok; Kaushik, Shubham; Khalighi, Bahram; Cruse, Michael; Venkatesan, Ganesh

doi:10.1016/j.ijheatmasstransfer.2019.119083

Cited by 94 publications

(30 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Increasing passenger comfort in the cabin by maintaining temperature has been discussed extensively, both while the vehicle is running and when the vehicle is from a parking location [2,4,12,13,15]. However, the discussion on the integration of temperaturehumidity-air speed control systems based on effective human comfort is still very limited, except at the simulation stage [16][17][18]. Therefore, this study aims to develop a specific air conditioning control system used in vehicles to adjust temperature-humidity-air speed based on effective human comfort (22 °C; 40% to 60% of relative humidity, RH).…”

Section: Introductionmentioning

confidence: 99%

Vehicle Air Conditioner (Vac) Control System Based on Passenger Comfort: a Proof of Concept

Munahar¹,

Purnomo²,

Izzudin³

et al. 2022

IIUMEJ

View full text Add to dashboard Cite

The air conditioning system (AC) in passenger cars requires precise control to provide a comfortable and healthy driving. In an AC system with limited manual control, the driver has to repeatedly change the setting to improve comfort. This problem may be overcome by implementing an automatic control system to maintain cabin temperature and humidity to meet passenger's thermal comfort. Therefore, this paper presents the development of a laboratory-scale prototype air conditioning control system to regulate temperature, humidity and air circulation in the cabin. The experimental results show that the control system is able to control air temperature in the range of 21 °C to 23 °C and cabin air humidity between 40% to 60% in various simulated environmental conditions which indicate acceptance for comfort and health standards in the vehicle. In conclusion, this method can be applied to older vehicles with reasonable modifications. ABSTRAK: Sistem penyejuk udara (AC) pada kenderaan penumpang memerlukan ketepatan kawalan bagi menyediakan keselesaan dan kesejahteraan pemanduan. Melalui sistem AC dengan kawalan manual terhad, pemandu perlu berulang kali mengubah penyesuaian latar bagi meningkatkan keselesaan. Masalah ini dapat diatasi dengan menerapkan sistem kawalan automatik bagi menjaga suhu dan kelembapan kabin agar memenuhi keselesaan suhu penumpang. Oleh itu, kajian ini merupakan pembangunan prototaip sistem kawalan AC skala laboratari bagi mengawal suhu, kelembapan dan peredaran udara dalam kabin. Hasil eksperimen menunjukkan sistem kawalan ini mampu mengendali suhu udara pada kitaran 21 °C hingga 23 °C dan kelembaban udara kabin antara 40% hingga 60% pada pelbagai keadaan persekitaran simulasi yang menunjukkan penerimaan standard keselesaan dan kesejahteraan kenderaan. Sebagai kesimpulan, cara ini dapat diaplikasi pada kenderaan lama dengan modifikasi bersesuaian.

show abstract

Section: Introductionmentioning

confidence: 99%

Vehicle Air Conditioner (Vac) Control System Based on Passenger Comfort: a Proof of Concept

Munahar¹,

Purnomo²,

Izzudin³

et al. 2022

IIUMEJ

View full text Add to dashboard Cite

show abstract

“…Regarding simulations, Fujita et al [8] established a car cockpit model using CFD, and simulated the internal thermal environment of a car under different air supply conditions by using the standard turbulence model. CFD simulations and machine learning algorithm were combined to predict the thermal comfort of passengers in Ware and Khalighi's paper [9]. Three machine learning algorithms, stochastic gradient descent linear regression, random forest, and artificial neural network, were applied to the simulated data to predict the equivalent uniform temperature for passengers (EHT) and the average air temperature distribution.…”

Section: Introductionmentioning

confidence: 99%

Experimental Study on Manned/Unmanned Thermal Environment in Radar Electronic Shelter Based on Different Air Supply Conditions

Guo

Xue

et al. 2022

Energies

View full text Add to dashboard Cite

Studies on the thermal environment of the electronic radar shelter have been mainly focused on the simulation of the unmanned thermal environment, and there have been few studies on experiments in the thermal environment. Additionally, a comparative study of the experimental results from manned and unmanned shelters has been missing. In this paper, we experimented in thermal environments of manned/unmanned shelter under different air supply conditions. The experiment was divided into cooled, ventilated, and heated trials analyzing three aspects: (1) The average temperature distributions of walls, air inlet points, air outlet points, and surfaces were measured over time under different conditions in an unmanned shelter. The temperature distribution curve was fitted into the function. (2) Based on different working conditions, the temperature distribution experiments were carried out in three different areas for subjects wearing short or long clothing respectively. (3) The wind speed was measured at each measuring point in the air supply pipeline under different working conditions. The wind speed distribution was detected on the setting surfaces. The experimental results show that: (1) The air does not gradually tend to steady state with the time, and under different conditions, the air temperature obviously differs. (2) The clothing selection, air supply conditions, and locations of measuring points have significant influences on human body temperature distribution and left–right difference. (3) The mixing of the thermal plume caused by the vertical temperature difference of the human body and the jet generated by the mechanical air supply will reduce the wind speed of the airflow in the cabin, the adsorption of the jet to the bulkhead, and the stability of the airflow. The experimental data can provide the initial and boundary conditions for the simulation of the shelter. The results can provide a reference for the study of fluid control methods, the setting of thermal boundary conditions, and the simulation of the influence of thermal plumes on the airflow distribution. The experimental study in this paper has filled in the blanks regarding experimental study in electronic radar shelters. It has important research value and practical significance.

show abstract

“…Using ML (machine learning) algorithms, Warey et al [15] predicted and analysed the impact of the AC (air conditioning) system on passenger thermal comfort. Tang et al [16] developed an automated calibration model for the liquid-cooled BTMS to forecast cooling capacity and power utilization using support vector regression (SVR).…”

Section: Introductionmentioning

confidence: 99%

Modelling and Computational Experiment to Obtain Optimized Neural Network for Battery Thermal Management Data

et al. 2021

View full text Add to dashboard Cite

The focus of this work is to computationally obtain an optimized neural network (NN) model to predict battery average Nusselt number (Nuavg) data using four activations functions. The battery Nuavg is highly nonlinear as reported in the literature, which depends mainly on flow velocity, coolant type, heat generation, thermal conductivity, battery length to width ratio, and space between the parallel battery packs. Nuavg is modeled at first using only one hidden layer in the network (NN1). The neurons in NN1 are experimented from 1 to 10 with activation functions: Sigmoidal, Gaussian, Tanh, and Linear functions to get the optimized NN1. Similarly, deep NN (NND) was also analyzed with neurons and activations functions to find an optimized number of hidden layers to predict the Nuavg. RSME (root mean square error) and R-Squared (R2) is accessed to conclude the optimized NN model. From this computational experiment, it is found that NN1 and NND both accurately predict the battery data. Six neurons in the hidden layer for NN1 give the best predictions. Sigmoidal and Gaussian functions have provided the best results for the NN1 model. In NND, the optimized model is obtained at different hidden layers and neurons for each activation function. The Sigmoidal and Gaussian functions outperformed the Tanh and Linear functions in an NN1 model. The linear function, on the other hand, was unable to forecast the battery data adequately. The Gaussian and Linear functions outperformed the other two NN-operated functions in the NND model. Overall, the deep NN (NND) model predicted better than the single-layered NN (NN1) model for each activation function.

show abstract

Data-driven prediction of vehicle cabin thermal comfort: using machine learning and high-fidelity simulation results

Cited by 94 publications

References 13 publications

Vehicle Air Conditioner (Vac) Control System Based on Passenger Comfort: a Proof of Concept

Vehicle Air Conditioner (Vac) Control System Based on Passenger Comfort: a Proof of Concept

Experimental Study on Manned/Unmanned Thermal Environment in Radar Electronic Shelter Based on Different Air Supply Conditions

Modelling and Computational Experiment to Obtain Optimized Neural Network for Battery Thermal Management Data

Contact Info

Product

Resources

About