Performance Optimization of Cold Storage Insulation Materials

Integrating Artificial Intelligence

Dawei Li, Tao Li

, Dong Xiao, Yuchao Jiang and Jinyuan Li

The Second Construction Co., Ltd. of China Construction First Group, 102699, Beijing, China

Keywords. Artificial Intelligence, Cold Storage Insulation Materials, Performance Optimization, Temperature.

Abstract: The optimization of energy efficiency of cold storage has always been a key topic in the field of cold chain

logistics, especially in the context of energy shortage and increasing environmental pressure, improving the

energy efficiency of cold storage and reducing energy consumption is the common goal of most enterprises.

to solve the problems of insufficient performance of insulation materials, unstable temperature control and

high energy consumption in the traditional cold storage design, this paper proposes an artificial intelligence-

based performance optimization model for cold storage insulation materials. The design of this model mainly

includes the optimization of heat conduction performance, heat capacity performance, material thickness,

sealing performance and dynamic optimization, etc., which aims to comprehensively improve the thermal

insulation performance of cold storage and reduce energy consumption. The experimental results show that

the heat loss of the cold storage is reduced by 26.7%, the energy efficiency is increased by 16.7%, and the

internal temperature fluctuation of the cold storage is reduced by 37.8% based on the performance

optimization model of the cold storage integrated with artificial intelligence. In summary, the AI-based

optimization model can effectively improve the energy efficiency of cold storage, reduce its energy

consumption, and improve the temperature control stability of cold storage.

1 INTRODUCTION

Due to the intensification of the global energy crisis

and the increasing severity of greenhouse gas

emissions, the optimization of energy efficiency of

cold storage, as a major energy consumer, has

become a key issue in the field of cold chain logistics

(Eberwein, Hajhariri, et al. 2024). The selection and

configuration of cold storage insulation materials can

directly affect energy efficiency. Traditional cold

storage design often fails to take into account the

interaction and interaction of multiple factors,

resulting in problems such as low energy efficiency

and serious cost increases(Jiang, Zhang, et al. 2024).

Therefore, based on the selection of insulation

materials and the improvement of the rationality of

their configuration, the comprehensive optimization

of heat conduction and temperature control of cold

storage has become a direction of general concern in

the industry. In this regard, some researchers have

proposed solutions to reduce energy consumption by

improving the thermal conductivity of insulation

materials (Li, Yang, et al. 2023). Some researchers

have also used materials with low thermal

conductivity to optimize thermal insulation

performance, in order to reduce the heat exchange

between the inside and outside of the cold store (Liu,

Liu, et al. 2023). Basically, the above methods ignore

the role of the thickness of the insulation material and

the sealing performance of the cold storage, so it can

not achieve a good optimization effect. Some

researchers have also proposed to optimize the heat

capacity performance of cold storage by adjusting the

thickness of the material to reduce temperature

fluctuations and improve energy efficiency (Mahajan,

Emmanuel, et al. 2023). This method fails to adapt to

the thermal insulation needs under dynamic

environmental changes, nor does it effectively

consider the synergies between different modules

(Mahajan, Emmanuel, et al. 2023), to achieve the

goal of high efficiency and energy saving. In this

paper, a performance optimization model of cold

storage insulation materials integrating artificial

intelligence is proposed, which is expected to achieve

a comprehensive optimization of the performance of

cold storage insulation materials, which is conducive

to the application of insulation materials in all walks

of life. This round mainly expounds the various

Li, D., Li, T., Xiao, D., Jiang, Y. and Li, J.

Performance Optimization of Cold Storage Insulation Materials Integrating Artiﬁcial Intelligence.

DOI: 10.5220/0013536300004664

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 3rd International Conference on Futuristic Technology (INCOFT 2025) - Volume 1, pages 109-115

ISBN: 978-989-758-763-4

109

problems that need to be faced in the optimization

process of cold storage insulation materials and

combines the research practice of the academic

community on the optimization of cold storage

insulation materials, and puts forward the research

plan of this paper, so as to better pave the way for

subsequent research.

2 RELATED WORKS

2.1 Prediction and Optimization of

Energy Efficiency of Cold Storage

Based on Artificial Intelligence

The energy efficiency of cold storage is closely

related to the selection and thickness of insulation

materials, but the optimization of energy efficiency of

cold storage also involves the operation efficiency of

the temperature control system in the cold storage,

humidity regulation (Pan, Yuan, et al. 2023), air

circulation, etc. The integration of artificial

intelligence can be based on real-time data

monitoring, using the dynamic changes of the cold

storage operating environment to achieve accurate

prediction of energy efficiency fluctuations, and put

forward accurate energy-saving optimization

suggestions for users. In terms of intelligent sensing

and data collection, based on the deployment of

multiple sensors in the cold storage, including

temperature sensors, humidity sensors, airflow

sensors, etc. (Sartori, Ornaghi, et al. 2023), the real-

time collection of environmental data inside the cold

storage is achieved, and at the same time, it is

uploaded to the artificial intelligence system for

research. The construction of energy efficiency

prediction models is also important. It is mainly based

on historical operating data and environmental

parameters, and uses AI technology to establish an

energy efficiency prediction model. For example, an

AI model can be used to predict the trend of energy

efficiency changes in cold storage in different

environments (Zhou, Zhao, et al. 2024). In addition,

AI models or systems can automatically adjust the

temperature setting and temperature control

parameters in the cold storage based on the energy

efficiency prediction results, and then optimize the

overall energy efficiency of the cold storage to

maximize energy savings.

2.2 AI-Assisted Material Design and

Innovation

The optimization of traditional cold storage insulation

materials is generally affected by the improvement of

existing materials, and the introduction of artificial

intelligence technology (AI) can promote the

innovation of new insulation materials. The AI-

generated model will effectively simulate the process

by which multiple material combinations affect

thermal insulation performance, and then screen for

high-performance materials at the laboratory stage.

Combined with computer-aided technology and

artificial intelligence models (Zotova, Gendelis, et al.

2024), the mechanical properties and thermal

properties of different materials can be effectively

simulated, so as to design various new insulation

materials. Artificial intelligence algorithms can be

used to adjust the composition ratio of composites,

resulting in better thermal conductivity and lower

energy consumption. In addition, AI technology will

help people develop intelligent adaptive materials

that can automatically adjust their thermal

conductivity in response to changes in ambient

temperature and effectively improve the energy

efficiency of cold storage.

3 RESEARCH ON THE MODEL

AND SYSTEM OF COLD

STORAGE INSULATION

MATERIALS INTEGRATING

ARTIFICIAL INTELLIGENCE

3.1 Architecture of Cold Storage

Insulation Material System with

Artificial Intelligence

The cold storage insulation material system designed

in this paper with artificial intelligence mainly

includes data acquisition and monitoring, data

preprocessing and feature engineering, artificial

intelligence optimization model, intelligent decision-

making and control, simulation and verification, self-

learning and adaptation, energy efficiency evaluation

and feedback, etc. The data acquisition and

monitoring module is responsible for obtaining

various parameters inside and outside the cold storage

in real time, including temperature, humidity, airflow,

etc., based on sensors and infrared detectors, so as to

provide powerful data information for the subsequent

decision-making of the system. The data

INCOFT 2025 - International Conference on Futuristic Technology

110

preprocessing module is responsible for completing

the original data cleaning work, combined with

feature extraction, to improve the data quality. The AI

optimization model is used to optimize the

configuration of insulation materials and the energy

efficiency of cold storage. In addition, the intelligent

decision-making module is responsible for adjusting

the operating status of the equipment based on the

optimization results, so as to ensure the stable

operation of the equipment. The simulation module

will use CFD simulation techniques and

thermodynamic principles to verify the effectiveness

of the optimization scheme. The self-learning module

can automatically adjust the optimization strategy to

respond to changes in the environment based on real-

world operational feedback. The energy efficiency

evaluation module is responsible for monitoring the

operation of the cold store and providing energy

efficiency reports. The User Interaction &

Visualization module will provide a simple, easy-to-

understand graphical interface through which data

can be displayed, optimization suggestions,

evaluation results, and remote control and fault

diagnosis will be supported to help managers make

timely decisions.

3.2 Design of Performance

Optimization Model of Cold

Storage Insulation Materials

Integrating Artificial Intelligence

Thermal conductivity optimization is a key design

focus of the performance optimization model of cold

storage insulation materials. Its goal is to reduce the

influence of various factors on its internal

temperature by reducing heat, increasing the speed of

insulation material transfer, and reducing the external

temperature of cold storage, to reduce its energy loss.

The performance optimization model of cold storage

insulation materials integrated with artificial

intelligence will effectively optimize the heat

conductivity performance through a number of

measures, such as selecting low thermal conductivity

materials and adjusting the thickness of insulation

materials. Formula for optimizing thermal

conductivity, as shown in Eq. (1).

()

QEm

abs qd

−

)

In equation (1),

the smaller the value of the heat

transferred per unit of time, the better the insulation

effect of the material, and the higher the energy

efficiency.

Represents the thermal conductivity of

a material, which is mainly used to measure the

ability of a material to conduct heat. A

low value

indicates that heat transfer can be effectively

prevented and the insulation of the cold room can be

improved.

Represents the heat transfer area, which

represents the surface area of the insulation material

in contact with the external environment, and in

general, it is necessary to reduce heat loss by reducing

the contact area and using materials with low thermal

conductivity.

On behalf of the temperature

difference, that is, the temperature difference between

the inside and outside of the cold storage, if the

temperature difference is larger, the faster the heat

transfer, so generally choose materials with better

thermal insulation performance and more optimized

thickness materials to reduce the heat loss caused by

the temperature difference.

Represents the

thickness of the insulation material. The thicker the

material, the greater the resistance of heat based on

the material transfer, which in turn reduces heat loss.

When optimizing the design, AI can automatically

adjust the thickness of the material based on external

temperature differences and insulation needs. This

section will allow one to quantify the heat transfer

process in the cold room and find the important part

of the heat loss. Artificial intelligence can play an

important role in this process to optimize the thermal

conductivity.

The optimization of heat capacity performance is

to reduce temperature fluctuations based on

improving the heat capacity of cold storage insulation

materials,to reduce the operating burden of

refrigeration equipment. By selecting materials with

higher specific heat capacity and reasonably

distributing materials with different heat capacities,

the system can achieve the effect of buffering

temperature changes, as shown in equation (2).

()

ij ij i

df E

ωωαδ

′

)

In equation (2),

′

is the coefficient of heat

change is described, which is used to describe the

amount of heat change inside the cold store. If there

is a change in temperature, then the heat absorbed and

released by the insulation material in the cold storage

can be determined by equation (2).

is The lower

the value, the smaller the temperature fluctuation

inside the cold storage and the higher the energy

efficiency.

Represents the mass of the material, if

the mass of the material is larger, then the material

will have more capacity to store heat, which can

Performance Optimization of Cold Storage Insulation Materials Integrating Artiﬁcial Intelligence

111

better mitigate temperature fluctuations. High-quality

materials can absorb more heat during the

temperature change process and avoid problems such

as excessive fluctuations in the temperature of the

cold storage.

is the specific heat capacity of the

material. The specific heat capacity represents the

unit mass of the material, the heat absorbed and

released when the temperature changes, the

higher

the material, the more heat can be absorbed, and then

the impact of temperature changes inside and outside

the cold storage on the temperature control system

can be slowed down, and at the same time, the number

of starts of the refrigeration equipment and the energy

consumption are reduced. This step clarifies how cold

storage insulation can affect fluctuations in internal

temperatures. In the process of practical application,

the AI model can adjust the selection of materials

based on real-time temperature data to maintain a

stable temperature environment in the cold storage.

The thickness of the insulation material directly

affects the heat conduction efficiency and overall

energy efficiency of the cold storage. In order to

ensure the insulation effect and reduce excessive

material waste, the thickness optimization method

can select the optimal thickness based on the

relationship between the optimized material thickness

and heat transfer. As shown in Equation (3)

()

max min

max

wwt

−

=−

)

In Eq. (3),

is the

maximum permissible heat

transfer, which is the maximum heat loss value that

can be accepted by the cold storage system.

is This

allows the system to better determine the optimal

material thickness and keep the heat transfer rate

within a safe and economical range. This step helps

managers to maximize the use of insulation materials

on the basis of ensuring the temperature control effect

of cold storage. By constantly adjusting the thickness

of the material, the heat loss can be kept within a

reasonable range, thereby reducing the waste and

energy loss of the material, and can help people find

the most economical thickness configuration by

combining the cost and efficiency of the material.

Tightness is one of the important factors in the

insulation effect of cold storage, especially at the

doors, windows and joints of cold storage. Based on

the optimization of the sealing material and heat

transfer coefficient, the external heat intrusion of the

cold storage can be reduced, and the overall thermal

insulation performance of the cold storage can be

improved, so the optimization of the sealing

performance is extremely important, see Equation (4)

for this step.

kkk

)

In equation (4),

represents the heat loss of the

sealing part, which is used to describe the heat loss

caused by the heat transfer of the sealing part, the

greater the heat loss, the worse the insulation effect of

the cold storage, and the lower the energy efficiency.

Represents the heat transfer coefficient of the

sealed part. Based on the selection of sealing

materials with low thermal conductivity, heat loss

will be effectively reduced. Equation (4) shows that

under the premise of ensuring the rationality of the

design of the sealing part, the artificial intelligence

system can operate automatically and effectively, and

reduce the heat loss of the cold storage. The artificial

intelligence system can automatically monitor the

sealing performance, and continuously adjust its

optimization strategy based on the monitored

situation, and then improve the insulation effect of the

sealing part, so that the overall performance of the

cold storage can be improved.

The artificial intelligence dynamic optimization

module is the focus of the design of the cold storage

insulation material performance optimization system,

which uses deep learning algorithms, based on real-

time monitoring and analysis of multi-directional

data, will automatically adjust the configuration of

thermal insulation materials in the cold storage, and

then improve the energy-saving effect. Artificial

intelligence dynamic optimization, see Eq. (5).

ii i



)

In equation (5),

f represents the energy

consumption of cold storage, which contains various

energy needs such as refrigeration and lighting,

ventilation, etc. Based on real-time data and

intelligent algorithms, the AI system will adjust the

temperature and sensor parameters in the cold storage

to maximize the energy efficiency of the cold storage

and effectively reduce energy consumption. In this

way, the performance optimization system of cold

storage insulation materials applied by artificial

intelligence technology will adjust the insulation

level of materials, sealing strategies, and the

operation mode of temperature control equipment

based on the temperature data in the cold storage, so

INCOFT 2025 - International Conference on Futuristic Technology

112

as to achieve the goal of maximizing energy saving

and emission reduction.

4 RESULTS AND DISCUSSION

4.1 Background of the Application

Case of the Performance

Optimization System of Cold

Storage Insulation Materials

Integrating Artificial Intelligence

Enterprise H is a high-quality enterprise specializing

in cold chain logistics and cold storage facility

construction, which mainly provides practical

temperature control solutions for food and medical

industries. From 2019 to 2024, the impact of global

climate change will increase the number of problems

such as energy consumption and energy prices.

Enterprises in all walks of life have now realized the

importance and urgency of the energy efficiency

problem of cold storage, and at the same time,

affected, enterprise H is also facing many problems,

especially the insufficient performance of insulation

materials and excessive energy consumption, which

seriously affects the effect of temperature control

services for users and threatens the future

development of enterprises. Based on this, the

company decided to introduce this set of artificial

intelligence cold storage insulation material

performance optimization system to achieve a high

level of performance optimization of insulation

materials, and reduce heat loss, energy waste, high

cost, poor effect and other problems. Enterprise H

hopes that the introduction of the optimization system

can provide high-quality solutions for the

comprehensive improvement of the thermal

insulation effect of cold storage by integrating heat

conduction performance and heat capacity

performance, material thickness, sealing

performance, dynamic optimization, etc. Enterprise H

has 30 different sets of cold storage insulation

equipment, serving more than 20 countries, more than

100 high-quality enterprises, at present, enterprise H

uses this set of cold storage insulation material

performance optimization system to carry out cold

storage temperature control work. Specifically, the

thermal conductivity of the original insulation

material of the cold storage is 0.033 W/m·K, the heat

loss is 1500W, and the material thickness is 0.15,

which seriously affects the quality of the cold storage.

The distribution of cold storage insulation equipment

of enterprise H is shown in Figure 1.

Figure 1: Distribution of cold storage insulation equipment

of enterprise H

4.2 Comparative Analysis of Data Such

as Heat Conduction Performance

Before and After Optimization

After adopting the artificial intelligence cold storage

insulation material performance optimization system

designed this time, based on the selection of thermal

insulation materials with relatively low thermal

conductivity and adjusting the thickness of the

materials, the heat loss of the cold storage has been

reduced, the heat loss of the cold storage before

optimization is 1500W, and the heat loss of the cold

storage after optimization is 1100W, and the

improvement range reaches 26.7, as shown in Table

Table 1: Comparison of before and after optimization of

thermal conductivity performance

Parameter medianM(P25，P75)

Kruskal

-Wallis

test

statistic

H value

Thermal

conductivity

（W/m·K）

(

n=1

)

Thickness of

the material

（m）(n=1)

Heat loss (W) (n=1).

0.033(0.0,0.0

)

0.150(0.1,0.1

)

1500.000(1500.0,1500.

2.000

0.022(0.0,0.0

)

0.120(0.1,0.1

)

1100.000(1100.0,1100.

2.000

0.333(0.3,0.3

)

-0.200(-0.2,-

0.2)

0.267(0.3,0.3) 2.000

According to Table 1, the artificial intelligence

cold storage insulation material performance

optimization system designed this time can adjust the

selection and thickness of materials, and improve the

thermal conductivity of materials and reduce the

impact of external heat on the internal temperature of

cold storage. The overall architecture of the artificial

intelligence cold storage insulation material

performance optimization system designed this time

is shown in Figure 2.

Performance Optimization of Cold Storage Insulation Materials Integrating Artiﬁcial Intelligence

113

Figure 2: The overall architecture of the performance

optimization system for artificial intelligence cold storage

insulation materials

Through the performance optimization of

artificial intelligence cold storage insulation

materials, the specific heat capacity of cold storage

materials has increased from 1300 J/kg· K increased

to 1700 J/kg· K, an improvement of 30.8%.

Moreover, the temperature fluctuation is significantly

reduced, from 4.5 K to 2.8 K, an improvement of

37.8%. In terms of energy consumption, the

optimization has been reduced from 1200 kWh to

1000 kWh, with an energy saving of 16.7%, as shown

in Table 2.

Table 2: Comparison before and after heat capacity

performance optimization

Parameters (Median)

Optimize

the

revious

value

Optimize

value

Extent of

improvemen

Specific heat capacity（

J/kg· K）(n=1)

1300.000 1700.000 0.308

Temperature fluctuation

(

)

(

n=1

)

4.500 2.800 0.378

energy

consum

tion

(

kWh

)(

n=1

)

1200.000 1000.000 0.167

Kruskal-Wallis test

statistic H value

2.000 2.000 2.000

p 0.368 0.368 0.368

* p<0.05 ** p<0.01

According to Table 2, it can be seen that through

the application of the performance optimization

system of cold storage insulation materials

integrating artificial intelligence studied in this paper,

the thermal performance of cold storage materials of

enterprise H has been improved, its energy

consumption has been reduced, and the optimization

effect is remarkable. The design focus of this set of

artificial intelligence cold storage insulation material

performance optimization system is shown in Figure

Figure. 3: Design focus of the performance optimization

system for artificial intelligence cold storage insulation

materials

4.3 Analysis of the Optimization

Results of Sealing Performance

The optimization of sealing performance is one of

the key points of the application of the performance

optimization system of this set of cold storage

insulation materials, and the sealing performance of

the cold storage materials has been significantly

optimized after the application of this optimization

system by enterprise H. Among them, the sealing heat

loss is reduced from 500W to 350W, a reduction of

30%. The sealing area has been reduced from 12 m²

to 10 m², a reduction of 16.7%, and the sealing

performance has been greatly improved. In terms of

heat transfer coefficient, the coefficient of heat

transfer increased from 0.035 W/m²· K to 0.025

W/m²· K, an increase of 28.6%, as shown in Table 3.

Table 3: Comparison of before and after sealing

performance optimization

Parameter median M(P25，P75)

Krusk

al-

Walli

’s test

statist

ic H

value

Seal heat loss

(W) (n=1).

Sealing area

(m²) (n=1).

Heat

transfer

coefficien

t (W/m²·

K) (n=1)

Optimize

the

revious

value

500.000(500.0,

500.0)

12.000(12.0,

12.0)

0.035(0.0,

0.0)

2.000

0.3

Optimize

d value

350.000(350.0,

350.0

)

10.000(10.0,

10.0

)

0.025(0.0,

0.0

)

2.000

0.3

Extent o

improve

ment

0.300(0.3,0.3)

-0.167(-0.2,-

0.2)

0.286(0.3,

0.3)

2.000

0.3

INCOFT 2025 - International Conference on Futuristic Technology

114

According to Table 3, based on the improvement

of the sealing of the doors and windows of the cold

storage and the joints, the overall thermal insulation

effect of the cold storage has been significantly

improved, and the heat loss has been effectively

controlled. Through the analysis of Table I, Table II

and Table III, after the introduction of artificial

intelligence optimization system, the company's cold

storage has achieved many performance

improvements. Based on the optimization of the

insulation material, the thermal conductivity of the

cold storage is increased by 33.3%, and because the

thermal conductivity of the insulation material is

improved, the intrusion of external heat can be

avoided, and the energy loss can be reduced. At the

same time, the optimization of the specific heat

capacity and sealing performance of the material also

increases the specific heat capacity of the cold storage

by 30.8%, and greatly improves the sealing

performance of the cold storage. In this way, the

overall thermal insulation effect of the cold storage

has been significantly improved, and the heat loss has

been effectively controlled. It can be proved that after

using the performance optimization system of cold

storage insulation materials integrating artificial

intelligence, the temperature control effect of

enterprise H has been greatly improved, and it can

provide effective temperature control solutions for

many enterprise customers.

5 CONCLUSIONS

In this paper, an artificial intelligence-based

performance optimization model and integrated

system of cold storage insulation materials are

designed to achieve a comprehensive optimization of

the performance of cold storage insulation materials,

and based on this, the temperature control effect of

cold storage is improved. It has been proved that

artificial intelligence can be fully utilized in the

performance optimization of cold storage insulation

materials, reduce the energy consumption of cold

storage, improve its energy utilization efficiency, and

improve the stability of cold storage temperature

control. the application of artificial intelligence

technology can also help enterprises greatly save

material costs and enhance the reliability of cold

storage operation. In the future, people can apply the

cold storage temperature control technology fused by

artificial intelligence to more fields, so as to provide

green and efficient cold chain temperature control

solutions for more enterprises. Although the research

in this paper is as comprehensive as possible, there

are still many shortcomings, which need to be further

discovered and improved in the future.

REFERENCES

Eberwein, R., Hajhariri, A., Camplese, D., Scarponi, G. E.,

Cozzani, V., & Otremba, F. (2024). Experimental

Investigation On The Behavior Of Thermal Super

Insulation Materials For Cryogenic Storage Tanks In

Fire Incidents. Process Safety And Environmental

Protection, 187, 240-248.

Jiang, X. X., Zhang, L., Wang, K., Zhang, B., Wu, T., Ren,

Z. M., Et Al. (2024). Super Lightweight, Scalable,

High-Strength, Thermal Insulating Molded Corrugated

Wood Boards For Cold Chain Transport Construction.

Acs Applied Engineering Materials, 2(6), 1687-1697.

Li, H. P., Yang, S. Y., Zha, Z. Q., Fei, B. H., & Wang, X.

H. (2023). Hygrothermal Properties Analysis Of

Bamboo Building Envelope With Different Insulation

Systems In Five Climate Zones. Buildings, 13(5).

Liu, J. Y., Liu, J. X., Shi, F., Wan, J. X., Ma, C. C., Sun, H.

J., Et Al. (2023). Transparent And Bendable Silica

Aerogels Integrated With Cs X

Wo3 Films For Photothermal

Temperature Self-Regulating Systems. Acs Applied

Nano Materials, 6(24), 22968-22978.

Mahajan, U. R., Emmanuel, I., Rao, A. S., & Mhaske, S. T.

(2023). Development Of Rigid Polyurethane Foam

Incorporating Phase Change Material For A Low-

Temperature Thermal Energy Storage Application.

Polymer International, 72(5), 490-499.

Mahajan, U. R., Emmanuel, I., Sreenivasarao, A., &

Mhaske, S. T. (2023). Development Of Smart

Polyurethane Foam With Combined Capabilities Of

Thermal Insulation And Thermal Energy Storage By

Integrating Microencapsulated Phase Change Material.

Polymer Bulletin, 80(12), 13099-13115.

Pan, X. Y., Yuan, M. D., Xu, G. Z., Hu, X., Liao, Z. R., &

Xu, C. (2023). Structure And Operation Optimization

Of A Form-Stable Carbonate/Ceramic-Based Electric

Thermal Storage Device For Space Heating. Energies,

16(11).

Sartori, A. P., Ornaghi, H. L., Guerra, N. B., Wander, P. R.,

Giovanela, M., Nunes, R. C. R., Et Al. (2023).

Development And Characterization Of Sandwich

Panels For Thermal Insulation In A Cold Storage

Chamber. Journal Of Cellular Plastics, 59(3), 215-230.

Zhou, B. T., Zhao, J., Li, Y. C., Gao, J. M., Huang, B. J.,

Wu, R. T., Et Al. (2024). Optimization Strategies Of

The Envelope Insulation For A Detached House Based

On Load Sensitivity And Thermal Storage

Performance. Journal Of Building Physics, 47(5), 496-

525.

Zotova, I., Gendelis, S., Kirilovs, E., Stefanec, D.,

Mongibello, L., & Morciano, M. (2024). Thermal

Performance Of Lignocellulose's By-Product

Wallboards With Bio-Based Microencapsulated Phase

Change Materials. Energies, 17(1).

Performance Optimization of Cold Storage Insulation Materials Integrating Artiﬁcial Intelligence

115