Performance Of Air Conditioner Research Articles

Assessment of using different ozone-friendly R22 alternative refrigerants in residential air conditioners in a high-ambient temperature country

The performance of a vapor compression refrigeration system (VCRS)-based residential air conditioner operating in a high-ambient temperature (HAT) country was investigated using six zero-ODP (ozone depletion potential) refrigerants as replacements to R22. The non-flammable alternative refrigerants considered in the present research were R134a, R404A, R407C, R410A, R448A, and R507A. Using the basic conservation laws, the VCRS was modeled during steady-state operation and solved using engineering equation solver (EES) software. Coefficient of performance (COP), pressures and temperatures at compressor suction and discharge, Global Warming Potential (GWP), critical pressure and temperature, compressor pressure ratio, volumetric cooling capacity (VCC) specific cooling capacity (SCC), and refrigeration effect were utilized as assessment criteria for the alternative refrigerants considered. From these refrigerants, the highest values of suction pressure, discharge temperature, and condenser pressure were attained by R410A. In addition, the discharge temperatures for all refrigerants, except R134a, were all higher than their corresponding critical values, causing a quicker drop in the VCRS’s performance. As an alternative refrigerant, R407C showed the highest SCC of 141.0 kJ/kg followed directly by 139.2 and 138.0 kJ/kg for R410A and R448A, respectively. A reverse trend was found for VCC with respective values of 4722 and 3775 kJ/m3 for R410A and R448A. Lower volume flow rates and smaller-sized compressors are expected for higher VCC refrigerants. The same trend was found for the compressor’s specific work input and condenser’s specific heat transfer with values of (51.14, 46.82, and 45.38 kJ/kg) and (190.3, 187.8, and 183.4 kJ/kg) for R410A, R407C, and R448A, respectively. For applications in HAT countries, larger condenser’s specific heat transfer makes the refrigerant more applicable. Conversely, with respect to COP, refrigerant R134a with a value of 3.075 was the superior alternative followed by R448A and R407C with respective COPs of 3.042 and 3.011. Based on the overall assessment in terms of environmental obligation, COP, compressor input power, refrigerant flow rate required, and all the evaluations made in this research, refrigerant R448A was recommended as the most appropriate substitute to R22 which can effectively be used in residential air conditioners in a HAT country.

Condensation Heat Transfer of Zeotropic Refrigerant Mixtures R407C and R448A in a Horizontal Smooth Tube

Zeotropic refrigerant blends have attracted wide interest due to their promises to reduce global warming potential as well as their potential ability to improve the performance of heat pumps and air conditioners. The complex phenomenon of non-isothermal phase change complicates condensation of zeotropic mixture refrigerants and merits extensive investigation to better understand their performance profiles. The present work experimentally studied condensation heat transfer of R407C and R448A – two R134a-based zeotropic refrigerant mixtures – in a horizontal smooth tube, condensed by counter-current water cooling. Measurements for mass flux were in the range of 120 to 320 kg m−2 s−1 and saturation temperature in the range of 42 to 64 °C. Variation in refrigerant temperature and composition shift during condensation were quantitatively presented. The experimental data showed the effects of mass flux and saturation temperature on the heat transfer coefficients of R407C and R448A in different vapor quality regions. The analysis of heat and mass transfer resistances related to the flow regimes and refrigerant thermophysical properties provides a deep understanding of the condensation heat transfer of zeotropic refrigerant mixtures. The experimental data presented in this work are of value for the design of condensers.

A novel rule mining method for knowledge discovery of relationships among indoor air quality, HVAC operation and occupants’ activities

This paper presents a novel data mining method to discover the occurrence time, co-occurrence and sequential association rules among indoor air quality (IAQ), Heating, Ventilation and Air Conditioning (HVAC) operations and occupants’ activities. The novelty of this work includes a peak detection method to discover the pollutants' peaks and a rule mining method with extended rule selection criteria that considers both the time lags between events and relationships among multiple events. The peak detection method aimed to use moving windows and criteria to find the candidate peaks and the non-maximum suppression to filter the overlapped candidate peaks. The proposed rule mining method is based on the Apriori and Apriori-All with the rule selection criteria extended by labeling the occurrence time to events to find the rules among various occurrence times and multiple events and by limiting the time lags among the occurrences of the events to discover the sequential rules. Two datasets, one from 70 houses and one from a single commercial building, were used to evaluate the performance of this proposed data-driven method. The results showed that 93.19% of the peak detection results matched the peaks detected from the data records. The CO2 peaked frequently at 12:00, 17:00 and from 19:00 to 24:00. The occurrence of occupants’ activities could lead to pollutants’ concentrations and pollutants peaks within 2 hours in the residential buildings. The occurrence of a high Wifi connection number was frequently followed by a CO2 peak within 2 hours in the commercial building. These findings can support the development of control strategies for building HVAC systems to achieve better indoor air quality control.

Real-time thermodynamic monitoring of split inverter ACs: amicrocontroller-driven investigation of performance

Recent technological advancements, particularly in air conditioning cooling systems, have led to rapid developments such as inverter technology. Inverter technology provides various advantages including energy savings compared to non-inverter air conditioners. Globally, the inverter modulates the compressor to continue operation despite reaching the set temperature. This study aimed to monitor the performance of split inverter air conditioners utilizing microcontroller technology. The microcontroller model employed was the ATmega2560, capable of logging each test parameter and displaying in real-time. Additionally, the ATmega2560 integrated sensors including the DS18B20 temperature sensor and PZEM 004-T multifunction electrical sensor. Monitoring occurred over one hour of operation on a 8525 Btu/h capacity split inverter AC. Experimental monitoring results showed the lowest Tsupply at T1 compared to other temperatures, reaching 8°C. At Treturn, both T1 and T2 exhibited identical decreasing trends to 25.5°C around 3000 s. The minimum power variation occurred at P5 relative to other variations. The average power consumption of the split inverter AC was approximately 750 W. The minimum energy consumption observed was at E5 during the study, while the maximum was at E1 with peak energy consumption of 0.96 kWh. Microcontroller-based experimental monitoring can provide real-time results and shows promise for monitoring split inverter AC performance.

Machine Learning-Based Simulation of the Air Conditioner Operating Time in Concrete Structures with Bayesian Thresholding.

Efficient energy use is crucial for achieving carbon neutrality and reduction. As part of these efforts, research is being carried out to apply a phase change material (PCM) to a concrete structure together with an aggregate. In this study, an energy consumption simulation was performed using data from concrete mock-up structures. To perform the simulation, the threshold investigation was performed through the Bayesian approach. Furthermore, the spiking part of the spiking neural network was modularized and integrated into a recurrent neural network (RNN) to find accurate energy consumption. From the training-test results of the trained neural network, it was possible to predict data with an R2 value of 0.95 or higher through data prediction with high accuracy for the RNN. In addition, the spiked parts were obtained; it was found that PCM-containing concrete could consume 32% less energy than normal concrete. This result suggests that the use of PCM can be a key to reducing the energy consumption of concrete structures. Furthermore, the approach of this study is considered to be easily applicable in energy-related institutions and the like for predicting energy consumption during the summer.

Influence of air-conditioning intermittent operation on the cooling load from opaque envelopes in residences

Air-conditioning (AC) intermittent operation is extensively employed owing to occupancy regulations and residents' habits. This conditioning operation type significantly affects the indoor air temperature as a result of the on-off cycles of AC, leading to potential high temperature differences between adjacent rooms due to varying operation rules. Based on this, numerical simulations were done to deal with the overall thermal behavior of typical bedrooms under intermittent operation, and the individual contributions from different envelope components were discussed considering four models of AC operation in adjacent rooms. The results demonstrate that optimizing these four envelope components can lower average transient heat flows by 16.6 %–65.03 % with the consideration of the operation model. Among these components, the ceiling exhibited the highest energy efficiency potential with a reduction ratio of up to 42.8 %. Furthermore, the AC operation model in adjacent rooms had a significant impact on cooling load, and optimizing these four envelope components greatly reduced thermal disturbances from neighboring rooms. The fluctuation percentage of daily heat transfer capacities decreased from 33.89%-37.16 % to 20.64%–23.76 %. Specifically, optimizing opaque envelopes resulted in reductions in heat transfer capacities by 32.06 % and 30.48 % respectively, with ceilings contributing most significantly at 15.1 % and 14.2 %.

Coconut shell-derived activated carbon-enhanced water phase change material for cold thermal energy storage.

In building cooling, the demand for cooling surges during specific times, stressing air-conditioner operation, and additional cooling is often wasted during low-demand periods. Water-phase change material (W-PCM)-based thermal energy storage (TES) allows for load shifting and effective management of peak demand by storing cooling energy when the demand is low. This stored energy can be deployed during peak hours, decreasing energy usage and associated CO2 emissions. However, the use of W-PCMs was hindered by phase separation, slow energy transfer, and high supercooling degree (SCD). We synthesized coconut shell (CNS)-produced activated carbon (ACC) to use as a thermal enhancer in W-PCMs for the first time. First, ACC was synthesized from CNS via steam activation. Then, transmission electron microscopy was used to confirm the pore morphology of the CNS-ACC.The synthesis of the W-PCM with various weight percentages (0.1, 0.6, and 1.2) of CNS-ACC was accomplished in two steps. Zeta potential distribution analysis revealed that the W-PCM with CNS-ACC exhibited colloidal stability. Thermal conductivity (TC) and thermogram analyses revealed that a dose of 1.2 wt% CNS-ACC enhanced liquid and solid TC by 9% and 22%, respectively, despite a 6% and 8% decrease in specific heat and latent heat. More specifically, solidification assessment in a spherical enclosure revealed 100% suppression of SCD with 1.2 wt% CNS-ACC. As a result of this and the enhanced TC, the overall solidification process was accelerated, reducing the overall duration by 18.5%. Thus, the combination of CNS-derived ACC and W-PCM for TES in building cooling could reduce energy consumption and associated CO2 emissions.

Simulation Study on Performance of Solar-Powered Desiccant Wheel and Ground Source Heat Pump Air Conditioning in Qingdao

In China, a large amount of the total energy consumption is made up of building energy, particularly in humid regions. The conventional vapor compression refrigeration systems cannot effectively control the indoor humid and thermal environment. Therefore, this article proposes a solar-powered desiccant wheel and ground-source heat pump (SDW-GSHP) air conditioning system. The energy consumption of the system is mainly from sustainable sources of solar and geothermal energy, showcasing excellent energy efficiency and environmental friendliness. The desiccant wheel (DW) processes latent heat loads, and the GSHP processes the sensible heat load. The regeneration air of the DW is heated by a solar collector. The operational performance of the system was simulated by using TRNSYS during the typical summer week (15 July to 22 July) in Qingdao. The simulation results indicated that indoor temperature was maintained within 25.8–26.2 °C and the relative humidity was maintained in the range of 57–61%. The COP of the SDW-GSHP air conditioning system was 42.1% higher than that of the DW air conditioning system with electric heating regeneration, and electricity saved 43.7%.

Information entropy analysis of the relation between climate and thermal adaptation: A case study in hot summer and cold winter region of China

The shift of paradigm from reductionist to holism in the field of thermal adaptation promoted a boom in thermal adaptation theory and provided a systemic perspective on this issue. The thermal adaptation theory confronts twin difficulties of scale and complexity. The complexity and entropy of occupants' thermal adaptation emerging. This paper aims to investigate the information entropy exchange in the coupled climate-building-occupants system. First, we justified that the building-occupants system is an open system and exchanges energy, matter, and entropy with its surrounding climate system. Then, correlation analysis results suggested that climate entropy could influence thermal adaptation entropy. Thermal adaptation entropy fluctuated with climate entropy and the difference varied between −0.5 and 0.5 below 31 °C. A generalized entropy balance model was proposed for quantifying the entropy exchange among coupled climate-building-occupants systems for both free-running and air-conditioning buildings. The quantitative relation between the entropy of thermal adaptation and H_DTR reveals the dynamic occupant's thermal adaptation under the process of entropy exchange with the climate system. The H_DTR and entropy relation models provide a new perspective on thermal adaptation coupled with climate beyond outdoor daily mean temperatures. Control strategies that integrate the dynamic characteristics of DTR can bring more economical, energy-efficient and comfortable effects to the operation of air conditioning or heating systems. Our findings shed some light on the dynamical and complex thermal adaptation. In further studies, more results and methods from meteorological research could be used for thermal adaptation research and interdisciplinary theories could be adopted to help us better understand occupants' thermal adaptation.

Diagnostic Insights for Optimal Avanza/Xenia AC Performance

This study investigates the AC system of Avanza/Xenia vehicles through diagnostic procedures aimed at identifying potential issues and ensuring adherence to maintenance standards. The air conditioning (AC) system in vehicles plays a pivotal role in ensuring driver and passenger comfort, necessitating regular monitoring and maintenance. Utilizing measuring tools such as compressors and multimeters, the main components including the magnetic clutch and evaporator were assessed. Results indicate that measured values, including magnetic clutch coil resistance (3.9 ohms), magnetic clutch gap (0.5 mm), and blower system resistance (ranging from 0 to 2.6 ohms), fall within acceptable service limits outlined in the Avanza/Xenia manual. Consequently, no repair procedures were deemed necessary, affirming the normal condition and suitability for use of the AC system. This research fills a knowledge gap by providing a systematic diagnostic approach for evaluating vehicle AC systems, offering implications for maintenance practices in ensuring optimal performance and longevity. Highlights: Routine maintenance prolongs AC system lifespan. Accurate diagnosis prevents potential issues. Component inspection ensures system health. Keywords: PMCB, Vehicle Air Conditioning System, Maintenance, Repair, Troubleshooting

Investigation of smart thermostat fault detection and diagnosis potential for air-conditioning systems using a Modelica/EnergyPlus co-simulation approach

Smart thermostats offer low-cost alternative for fault detection and diagnosis (FDD) in residential air-conditioning (AC) systems. However, smart thermostats do not directly measure AC performance, but measures indoor air conditions which reflect the indoor air responses to both AC operations and other factors like weather and building gains. Estimating uncontrollable building gain disturbances is essential to differentiate them from AC impacts. Since the uncontrollable disturbances are difficult to monitor using smart thermostat data, there is need to investigate the actual capability of smart thermostats for FDD. In this study, an integrated building and Vapor Compression cycle-based AC model was developed and simulated using EnergyPlus/Spawn and Dymola. The simulation was performed under ten scenarios covering relevant gains, low charge, and low indoor airflow faults. The sensitivity of the time-to-cool feature under these scenarios was studied. The results show about 10% time-to-cool increase from varied internal gains and infiltration. Meanwhile, low charge at 10%, 20% and 30% severity increased time-to-cool by about 3%, 6%, and 20%, respectively, suggesting that if these gains are neglected in an FDD method, it might not be possible to detect low charge below 30% using smart thermostat data since even without a fault, the combined impact of those gains already exceeded that for 20% low charge. For low indoor airflow at 10%, 20% and 30% severity, the increase in time-to-cool was about 3%, 9% and 12%, meaning that only low indoor airflow fault above 30% can be confidently detected if those gains are not captured. Thus, this study demonstrates the need to consider some of these gains in developing smart thermostat based FDD algorithms.

Revealing and optimizing the design of cover installation for outdoor units of air conditioners through CFD simulations and thermodynamic modeling

When renewing building facades in most Chinese cities, covers are often designed and installed to conceal the outdoor units of residential split air conditioners for congruousness of building facades. However, how those covers impact airflow and energy efficiency should be thoroughly examined. This study investigates two popular designs of cover (louver and circular-hole) and selects Nanjing, renowned for its hot summers, as the case city. This study employs Computational Fluid Dynamics models to simulate airflow obstruction caused by the covers surrounding the outdoor units. Grey Model, trained from the CFD results, quantifies interactions between design of cover and inlet air temperature. Additionally, a thermodynamic model assesses the covers' impact on the coefficient of performance of air conditioners. The findings reveal that the primary cause of outdoor unit overheating is warm air backflow from the outlet to the inlet. A mere 1 °C increase in inlet air temperature can reduce COP by 4.1%–8.7%. The maximum temperature differences caused by different designs of cover are 4.5 °C for the louver type and 4.4 °C for the circular-hole type. To mitigate these negative impacts, optimal design recommendations are provided: a minimum distance between the cover and outdoor unit of 0.29 m for louver type and 0.1 m for circular-hole type, both feasible in most installations. These findings can help designers, manufacturers, installers and policymakers, to facilitate the design and installation of optimal covers for outdoor air-conditioning units, thus minimizing energy efficiency losses.

THE IMPACT OF INTERGENERATIONAL PARENTING ON AC COOLING DEMAND: EVIDENCE FROM SOUTHERN CHINA

Given ever-increasing temperatures, household air conditioner (AC) usage is increasing rapidly, posing significant sustainability challenges. Identifying the drivers of residential demand is critical, especially in developing countries such as China. In contrast to assumptions made by the existing literature, intergenerational parenting and multigenerational households are widespread in China. To address this oversight, this study is the first to use data from an appliance-level, 15-min AC operation database from southern China to quantify the impact of intergenerational parenting families on cooling-related electricity consumption and examine its mechanisms. First, intergenerational parenting significantly positively impacts such consumption. Compared to working-age households, Intergenerational households consume 49% more electricity for cooling, and families with children consume 28% more. In contrast, families with older adults but no children use 6% less electricity for cooling than working-age families. Second, intergenerational families use the AC for 0.5 additional hours per day, set the temperature 0.9°C lower, and keep the AC idle longer than working-age households. Third, intergenerational parenting’s impact shows an M-shaped pattern throughout the day (peaking at 9:00 and 17:00). Fourth, working-age adults significantly moderate the impact of intergenerational parenting on electricity demand.

Data-driven approach enabling post-operation evaluation of air conditioning performance regarding thermal conditions attained indoors

Data-driven approaches become more and more attractive in building performance analysis including performance assessment of heat, ventilation, and air conditioning (HVAC) systems. Their popularity is associated with the increasing availability of large amounts of high-quality building-related measurement data. The study is focused on a data-driven approach that enables post-operation evaluation of AC performance based on indoor air monitoring. It allows for the identification of the classifying solution which recognizes the monitoring data that is representative of thermal conditions during AC operation. The major novelty consists in proposing the classification performance criterion, which is F1w-Score (the weighted F1-Score), and the procedure of weights selection. The procedure utilizes Hellinger distance (H). It is applied to measure the similarity between the binary empirical probability distribution of T and RH (EPDtr), associated with AC operation, and the prediction of this distribution (EPDes), made by the classifier. The approach was tested on three years of data from continuous indoor air monitoring in the IT engineers' room equipped with an AC unit. The best weights of F1w-Score were wPPV = 0.85 and wTPR = 0.15. The best classifying solution was identified using F1w-Score. It involved: Logistic Regression as the classifier and feature vector being Fourier spectrum of 16 min long fragments of RH and T time series. The performance of the best classifying solution was high as indicated by F1w-Score = 0.89 ± 0.05. The corresponding H(EPDtr, EPDes) = 0.17 ± 0.04 pointed at the capability to identify the measurement data that characterizes indoor conditions during AC operation well. This work contributes to the development of data-driven approaches serving diagnostics of HVAC systems. It draws attention to the problem of defining the classification performance criterion which takes into account the ultimate, domain-specific use of the classification results.

Hot, cold, or just right? An infrared biometric sensor to improve occupant comfort and reduce overcooling in buildings via closed-loop control

To improve occupant comfort and save energy in buildings, we have developed a closed-loop air conditioning (AC) sensor-controller that predicts occupant thermal sensation from the thermographic measurement of skin temperature distribution, then uses this information to reduce overcooling (cooling-energy overuse that discomforts occupants) by regulating AC output. Taking measures to protect privacy, it combines thermal-infrared (TIR) and color (visible spectrum) cameras with machine vision to measure the skin-surface temperature profile. Since the human thermoregulation system uses skin blood flow to maintain thermoneutrality, the distribution of skin temperature can be used to predict warm, neutral, and cool thermal states. We conducted a series of human-subject thermal-sensation trials in cold-to-hot environments, measuring skin temperatures and recording thermal sensation votes. We then trained random-forest classification machine-learning models (classifiers) to estimate thermal sensation from skin temperatures or skin-temperature differences. The estimated thermal sensation was input to a proportional integral (PI) control algorithm for the AC, targeting a sensation level between neutral and warm. Our sensor-controller includes a sensor assembly, server software, and client software. The server software orients the cameras and transmits images to the client software, which in turn assesses occupant skin temperature distribution, estimates occupant thermal sensation, and controls AC operation. A demonstration conducted in a conference room in an office building near Houston, TX showed that our system reduced overcooling, decreasing AC load by 42% when the room was occupied while improving occupant comfort (fraction of “comfortable” votes) by 15 percentage points.

Load Forecasting and Operation Optimization of Ice-Storage Air Conditioners Based on Improved Deep-Belief Network

The prediction of cold load in ice-storage air conditioning systems plays a pivotal role in optimizing air conditioning operations, significantly contributing to the equilibrium of regional electricity supply and demand, mitigating power grid stress, and curtailing energy consumption in power grids. Addressing the issues of minimal correlation between input and output data and the suboptimal prediction accuracy inherent in traditional deep-belief neural-network models, this study introduces an enhanced deep-belief neural-network combination prediction model. This model is refined through an advanced genetic algorithm in conjunction with the “Statistical Products and Services Solution” version 25.0 software, aiming to augment the precision of ice-storage air conditioning load predictions. Initially, the input data undergo processing via the “Statistical Products and Services Solution” software, which facilitates the exclusion of samples exhibiting low coupling. Subsequently, the improved genetic algorithm implements adaptive adjustments to surmount the challenge of random weight parameter initialization prevalent in traditional deep-belief networks. Consequently, an optimized deep-belief neural-network load prediction model, predicated on the enhanced genetic algorithm, is established and subjected to training. Ultimately, the model undergoes simulation validation across three critical dimensions: operational performance, prediction evaluation indices, and operating costs of ice-storage air conditioners. The results indicate that, compared to existing methods for predicting the cooling load of ice-storage air conditioning, the proposed model achieves a prediction accuracy of 96.52%. It also shows an average improvement of 14.12% in computational performance and a 14.32% reduction in model energy consumption. The prediction outcomes align with the actual cooling-load variation patterns. Furthermore, the daily operational cost of ice-storage air conditioning, derived from the predicted cooling-load data, has an error margin of only 2.36%. This contributes to the optimization of ice-storage air conditioning operations.

Investigation Of Automotive Air Conditioning Using Eco-Friendly R600a As An Alternative Refrigerant To R134a

One of the main reasons for replacing R134a with R600a is the impact of global warming. In this study, a numerical approach was applied to investigate changes in automotive air conditioning (AAC) performance due to the replacement of R134a with R600a. A thermodynamic evaluation was carried out with evaporating and condensing temperatures of 5oC and 45oC, respectively. The study simulates AAC performance at five engine rotation speeds: 1000, 2000, 3000, 4000 and 5000 rpms. The results show that replacing R134a with R600a reduces the cooling capacity and input power by 45.42% and 47.02%, respectively. However, due to the dominant decrease in input power as compared to the decrease in cooling capacity, the COP of AAC increases by 2.93%. Although the increment in COP is relatively small, this replacement greatly contributes to the reduction of greenhouse gas emissions that causes the problem of global warming due to the lower GWP of R600a as compared to R134a.

Performance Air conditioner on retrofitted refrigerant hydrocarbon

Synthetic refrigerants used in air conditioner (AC) are very important in depleting the ozone layer and prohibiting global warming. This has led to the application of R32 and Musicool 22 (MC22) as a substitute for R22 because refrigerant is considered more environmentally friendly. Therefore, this research aimed to compare the performance of applying both R32 and MC22 refrigerants in 1 PK split AC using the coefficient of performance (COP) as the indicator for AC performance and compressor power consumption. MC22 filling mass was varied at 90% (202.14 grams), 100% (224.6 grams), and 110% (247.6 grams) of R32 mass, and condenser inlet temperatures at 28°C, 30°C, 32°C, and 34°C. The results showed that MC22 could be used as a viable alternative to R32 due to the higher refrigeration effect value of 332.36 kJ/kg recorded for refrigerant

Spatial distribution and transient responses of the thermal environment in an office space equipped with a standing-type air conditioner

Air conditioner (AC) systems are important for maintaining indoor thermal comfort, but discrepancies can exist between setpoints and the actual room temperature. In the present study conducted in a typical Korean office during summer, we identified differences of up to 2.77 °C between the AC setpoint and the average room temperature. This variation may have originated from the oscillatory cooling pattern, leading to moments of discomfort even though the overall thermal balance was maintained. While consistent initial cooling rates were observed for various setpoints, oscillations at 20 °C lowered the efficiency of the AC system. A bi-exponential model applied to the cooling pattern confirmed a two-phase cooling process. Interestingly, the coefficient of performance was highest at the lowest temperature setpoint, even though this led to greater energy consumption and possible overcooling. The weather strongly affected AC performance, with rainy conditions requiring less power than sunny conditions at the same setpoint. Furthermore, our experiment comparing the predicted mean vote (PMV) with actual human comfort revealed that the PMV often recommends a cooler ambient temperature than what occupants actually prefer.

Development of Virtual Sensor Based on LSTM-Autoencoder to Detect Faults in Supply Chilled Water Temperature Sensor

Supply chilled water temperature (SCWT) is an important variable for the efficient and stable operation of heating, ventilation, and air conditioning (HVAC) systems. A precisely measured value ensured by the continuous reliability of the temperature sensor is essential for optimal control of an HVAC system because temperature sensor faults can affect the chiller operation and waste energy. Therefore, temperature sensor fault-detection strategies are imperative for maintaining a comfortable indoor thermal environment and ensuring the efficient and stable operation of HVAC systems. This study proposes a fault-detection method for an SCWT sensor using a virtual sensor based on a long short-term memory-autoencoder. The fault-detection performance is evaluated considering a case study under various sensor fault scenarios to evaluate changes in indoor thermal comfort and energy consumption after correcting sensor faults detected by the virtual sensor. The results verify excellent fault-detection performance in various fault scenarios (F-1 scores ranging from 0.9350 to 1.000). After correcting the SCWT fault, indoor thermal comfort is steadily maintained without additional energy consumption (indoor set-point temperature unmet hour reduced by a maximum of 105.7 hours, and energy consumption decreased by up to 1.8%).