Heating, Ventilation And Air Conditioning System Research Articles

HVAC System Management with a Low-Cost Solution

Abstract The paper presents a low-cost solution for managing HVAC (Heating, Ventilation, and Air Conditioning) systems using an ESP32 microcontroller as the primary control unit. The proposed system integrates multiple DHT temperature sensors and actuators, such as relays, to regulate heating, cooling, and ventilation within a residential environment. The ESP32 hosts a web-based application that enables users to monitor and control the HVAC system in real-time, offering an intuitive interface accessible via any device connected to the home network. By automating the HVAC operations based on real-time data, this solution not only provides convenience but also enhances energy efficiency by optimizing temperature control and reducing unnecessary power consumption. This affordable and user-friendly system demonstrates the potential of IoT technology in creating efficient and accessible home automation systems, making it an attractive option for homeowners aiming to reduce costs and improve climate control within their living spaces.

Impacts of HVAC cleaning on energy consumption and supply airflow: A multi-climate evaluation

Energy-efficiency interventions are crucial for sustainable building operations to accommodate emerging indoor air quality (IAQ) criteria into their engineering life cycles. While several studies have addressed building energy consumption and IAQ considerations separately, few provide integrated analysis of these aspects in response to building hygiene practices. In response, this study evaluates the effectiveness of routine heating, ventilation, and air conditioning (HVAC) cleaning on energy consumption and supply airflow patterns in non-residential public buildings. This study juxtaposes HVAC energy consumption and ventilation performance before, during and after routine HVAC cleaning, across buildings situated in four different climate zones, while operating in cooling mode. Each site had nearly identical HVAC systems serving similar architectural features and occupational loads; these were segregated into an intervention (cleaned HVAC system) that could be compared to an otherwise identically operating HVAC (control system), which was not cleaned. Following prescriptive cleaning, HVAC systems exhibited significant energy consumption reductions and delivered higher airflows compared to their uncleaned counterparts. On average, intervention systems saved between 41 % and 60 % on conveyance (fan/blower) energy, with one exception, and supplied 10 % and 46 % more airflow compared to their uncleaned counterparts. This research demonstrates how a new generation of low-cost HVAC system monitors can compile Internet of Things (IoT) archives to show immediate energy consumption benefits associated with cleaning HVAC components and their associated ductwork serving relatively high occupancy commercial and educational spaces.

Optimizing energy efficiency, thermal comfort, and indoor air quality in HVAC systems using a robust DRL algorithm

This study presents a novel deep reinforcement learning (DRL) framework designed to optimize energy efficiency, thermal comfort, and indoor air quality, particularly focusing on CO2 levels, in Heating, Ventilation, and Air Conditioning (HVAC) systems. Existing DRL methods often face challenges in maintaining control effectiveness under environmental disturbances, leading to higher energy consumption and reduced system performance. To address these limitations, we propose the Decoupled Adversarial Long Short-Term Memory and Proximal Policy Optimization (DAL-PPO) algorithm, which integrates a Decoupled Adversarial Strategy (DAP) with Long Short-Term Memory networks (LSTM) to better handle temporal dynamics and disturbances. Using the EnergyPlus simulation tool and PyTorch, DAL-PPO was evaluated in a disturbed experimental setting, achieving a 15 % reduction in PMV and CO2 levels and an 8 % decrease in energy consumption compared to traditional reinforcement learning algorithms. These results highlight DAL-PPO's ability to maintain system stability and efficiency even under dynamic disturbances, offering a significant improvement in HVAC system control and contributing to the development of more energy-efficient and resilient buildings.

How far back shall we peer? Optimal air handling unit control leveraging extensive past observations

Heating, Ventilation, and Air Conditioning (HVAC) systems play a critical role in ensuring occupant comfort in buildings. Traditional Rule-Based Feedback Control (RBFC) systems, while widely deployed for their simplicity, suffer from low adaptability. Recent improvements, such as Model Predictive Control (MPC) methods demand complex mathematical modeling and substantial expert knowledge, creating a high barrier for system design and optimization. Reinforcement Learning (RL) emerges as a promising solution with its adaptability and model-free nature, albeit challenged by sample inefficiency and suboptimal convergence. Given the intrinsic delayed effects from previous actions and prolonged thermal inertia in the HVAC systems, this study introduces an innovative deep RL framework that can leverage historical observations to refine RL agent performance. By incorporating a state-of-the-art (SOTA) Transformer model, we capture the temporal patterns in HVAC data and build a more precise RL training environment. Implemented on high-resolution, real-world HVAC datasets, our framework showed superior performance in both HVAC system modeling and RL control performance. Specifically, compared to the two baseline models—Bidirectional Long Short-Term Memory (Bi-LSTM) and vanilla Transformer, our proposed RL environment model achieved an average of 30.5% and 35.8% prediction accuracy improvement, respectively. Moreover, our optimal past observable RL agent swiftly delivers 35.3% of electricity saving and 54.4% of thermal comfort improvement over traditional RBFC. These results show the effectiveness of the pioneering integration of extensive historical observations for HVAC operation optimization.

Optimizing ventilation systems considering operational and embodied emissions with life cycle based method

Efforts to enhance the energy efficiency of Heating, Ventilation, and Air Conditioning (HVAC) systems have been bolstered by technical advancements and stringent regulations. However, HVAC systems not only emit during operation due to energy consumption but also have significant embodied emissions, which recent studies show can exceed those of the operational phase. This study introduces an optimization framework aimed at minimizing lifetime emissions—both operational and embodied—for ventilation systems, an area previously underexplored. The optimization framework incorporates detailed calculations of pressure drop, fan power and newly developed life cycle ventilation inventory data with a life cycle assessment perspectiveA case study of ventilation ductwork in a “BREEAM Excellent” certified energy-efficient building in Norway applies this optimization framework. Findings indicate that for this case, optimizing ductwork dimensions can reduce lifetime emissions of the ventilation system by 15 %, compared to the existing designs with an emission intensity of 0.3 kg CO2/kWh. Further, the study examines how the emission intensity of electricity generation and service lifetime influence total emissions, highlighting the growing importance of embodied emissions as electricity generation becomes cleaner. This underscores the necessity of considering both operational and embodied emissions in design decisions. This study presents an optimization tool for low-emissions ventilation design, capable of processing diverse layouts and aiding in decarbonizing ventilation systems towards achieving zero-emission buildings. Future integration with building information modeling (BIM) and artificial intelligence (AI) could further enhance autonomous low-carbon design and decision-making.

High-resolution simulations of gas-liquid Couette-type sealing gap flows

Abstract The two-phase flow in sealing gaps of twin-screw compressors is investigated using highly resolved coupled multiphase simulations. Oil-injected rotary-type positive displacement compressors (RPDC) such as twin-screw machines are used for the compression of refrigerants in HVAC (Heating, Ventilation, and Air Conditioning) systems. The efficiency of such machines is largely determined by the inevitable two-phase surge and gap flows. The simulation of flows in such compressors is still a challenge due to the complexity of the two-phase flow in the narrow gaps (<0.3mm) with organic working fluids and moving boundaries. Due to the rotation of the screws relative to the housing, gaps are present between the rotors and the end plates of the housing and between the tips of the rotors and the cylindrical housing walls. Oil injection can increase the efficiency of screw compressors or expanders by more than 10%, since oil enhances the sealing of the gaps where leakage occurs. On the other hand, additional momentum losses are caused by the two-phase gap flows. The oil injection, however, increases the hydraulic losses which depend on the geometry of the gap, the liquid, and the kinematics of the established multiphase flow in the gap. In this work, a highly efficient, high-resolution numerical method is used for the simulation of the gas-liquid multiphase flow in the screw compressor gap between the rotor tip and the stationary housing. The Lattice-Boltzmann method (LBM) defines the basis of the method used in this work, forming an in-house developed framework in which each fluid phase is solved by a separate solution algorithm. To capture the motion of the liquid-gas phase boundary, a level-set method is used. In the present work, a generic gap flow is considered. A Couette-type flow configuration, where the sealant flow in the gap is driven by the moving inner wall, is investigated. The Reynolds number based on the height of the channel is Re = 20000. Finally, we discuss the impact of bubble-laden sealing gaps on the momentum losses of the system.

Accelerating chiller sequencing using dynamic programming

Effective management of heating, ventilation, and air conditioning (HVAC) systems is crucial for enhancing building energy efficiency. Chillers, a significant component of HVAC systems, are responsible for more than 50 % of energy usage of the whole cooling plant, underscoring the importance of optimizing chiller sequencing. Although Model Predictive Control (MPC) has demonstrated efficacy in enhancing chiller performance, its widespread adoption is hindered by its high computational complexity. This study introduces a dynamic programming approach coupled with a 2-step optimization method to expedite chiller sequencing optimization while upholding MPC’s real-time control capabilities. The MPC method implemented in this study integrates a load forecasting model with an artificial neural network (ANN) based chiller model. Through simulation tests utilizing historical HVAC operational data from a commercial building located in Shanghai, the proposed chiller sequencing strategy achieves a 9.73 % decrease in energy consumption. Moreover, the dynamic programming approach, especially in conjunction with the 2-step optimization process, significantly reduces the MPC solution time at each control step from 165 min to 3.61 s, making it a viable solution for real-time MPC deployment. Additionally, the research delves into the influence of the chiller model’s complexity, the optimization strategy, and control horizon on computational efficiency. This research provides a feasible solution to implement chiller sequencing in real buildings to pick up the low-hanging fruits in an effective way.

Efficient multi-agent reinforcement learning HVAC power consumption optimization

This work proposed a novel reinforcement learning (RL) approach deep deterministic policy gradient with multi-stabilization network (MADDPG-MSN). It enhanced the sample efficiency of RL in heating, ventilation, and air conditioning (HVAC) power consumption optimization. Employing the multi-stabilization network trick, MADDPG-MSN efficiently learned to balance temperature control and power consumption with a limited number of interactions, expanding the potential of RL in the power consumption optimization of real-world HVAC systems. Evaluated by the simulated data center scenario, it reduced 28% power usage without compromising temperature control capability compared with the traditional model-predictive controller. In the real-world air conditioner testing, it demonstrated a similar control performance of indoor temperature to the built-in controller while consuming 32% less power.

A novel high-dimensional sensor calibration framework integrating thermodynamic laws in complex HVAC systems

Accurate calibration of sensors is critical for ensuring energy efficient operation of Heating, Ventilation, and Air Conditioning (HVAC) systems in buildings. Due to the high dimensionality of sensor data and the complexity of multiple-fault scenarios, calibrating sensors in large and complex HVAC systems presents significant challenges. To address this issue, this study introduces a novel sensor calibration framework that integrates thermodynamic laws for high-dimensional sensor calibration in complex HVAC systems. The traditional calibration method heavily relies on accurate data, making it difficult to apply in practical engineering projects. The innovative aspect of our method lies in its integration of thermodynamic laws, such as mass balance and energy conservation, with sensor calibration framework. This approach enables the framework to handle high-dimensional sensor measurements effectively without any training data. We compared five optimization algorithms and applied them to a central cooling system in Hong Kong. The results demonstrated that the simulated annealing (SA) is the most robust for solving the calibration problem, even in scenarios with up to 21 faulty sensors, with the calibrated sensor accuracy meeting the standards for conventional chiller plant operations. This novel framework provides a robust and reliable solution for high-dimensional sensor calibration in large and complex HVAC systems, addressing the growing need for precise sensor calibration as the number of installed sensors increases.

A dynamic maintenance planning methodology for HVAC systems based on Fuzzy-TOPSIS and failure mode and Effect Analysis

Maintenance is critical to the efficiency of Heating, Ventilation, and Air Conditioning (HVAC) systems in buildings. The conventional maintenance methods are planned for ideal situations and cannot easily be adapted to prevailing management/operational conditions, resulting in increased use of resources and energy. This study developed a dynamic maintenance planning framework for HVAC systems employing Fuzzy-TOPSIS and FMEA and aimed at reducing and stabilising maintenance costs while enhancing system reliability. Fuzzy-TOPSIS technique was used to establish maintenance priorities based on a carefully identified set of criteria, including the risk priority number (RPN), which is adaptable to changing conditions and ensures continuous monitoring. This is a novel application to HVAC systems. A real-world implementation in an HVAC company involving data collection, fuzzification of expert evaluations, priority ranking of components, and development of maintenance ranking validated the framework's efficiency. The running conditions of the HVAC system under the new approach, expressed by the air quality and air leakages (by extension energy saving), showed a significant improvement at the various test points in the 600-h running. The results demonstrated significant cost savings, enhanced system reliability, improved energy efficiency, and better indoor air quality. This dynamic maintenance planning framework offers a concise and adaptable solution for optimising HVAC maintenance operations.

Investigating the Reliability of Heating, Ventilation, and Air Conditioning Systems Utilized in Passenger Vehicles

A Heating, Ventilation, and Air Conditioning (HVAC) system is often utilized in passenger vehicles to enhance the comfort of both the driver and the passengers. The reliability of an HVAC system refers to the probability that a component within the system will fulfil its intended function during a specified timeframe while operating according to the predefined operational and environmental conditions. Conducting a reliability analysis for the HVAC system of a passenger vehicle is crucial to ensure safety, comfort, cost-effectiveness, and a positive standing. A methodology for analyzing the reliability analysis of a HVAC system using field failure data were developed to identify the critical failure modes, components, and subsystems. A detailed Pareto analysis was applied at subsystem and failure mode levels in order to prioritize them accordingly to their failure frequency. The analysis showed that the A/C evaporator and blower front sides were observed to be the most critical subsystems, contributing to approximately 50% of all failures. Furthermore, the leakages at the joints and vibrations are the primary failure modes of the HVAC system. The Weibull++ software package (version 2021) was used to estimate the best-fit probability distributions for each subsystem and system reliability modelling using a Reliability Block Diagram. The results show that the exponential distribution fits well for several subsystem’s Time-To-Failure (TTF) data and show that the failures were random and due to external reasons.

Fault detection research on novel transfer learning-based method for cross-condition, cross-system and cross-operation in public building HVAC sensors

Transfer learning (TL) has the inspiring potential for artificial intelligence in heating, ventilation and air conditioning (HVAC) system with insufficient data labels. However, traditional TL-based methods are limited when applied across different conditions, systems, and operations.Unfortunately, public building HVAC systems encounter challenges related to data acquisition and richness, making it difficult to obtain data from similar HVAC systems conditions, scenarios and operations. It proposes a novel TL-based method that combines energy and mass balance constraint equation (EBCe) to diagnose the sensor faults in HVAC systems across different systems, conditions and operations.Firstly, it utilizes laboratory data as the source domain data and constructes EBCe based on the common physical laws of HVAC system to reduce the data differences between laboratory and public buildings. Then, an laplacian kernel domain-adaptive neural network (LkDaNN) is proposed to generalize more efficiently feature differences between the source domain data and target domain data. Finally, experiment analyzes the non-fault and four control-sensors fault under both cross-operation and non-cross operation conditions. The experimental results demonstrate that the EBCe-LkDaNN method achieves satisfactory fault detection and diagnosis (FDD) performance.The overall FDD accuracy of porposed method can reach 90.72 % and 88.64 % under different cross-operation, respectively. Practical application of the EBCe-LkDaNN strategy for HVAC sensor FDD are discussed at last.

Cross-condition fault diagnosis of chillers based on an ensemble approach with adaptive weight allocation

The Heating, Ventilation and Air Conditioning (HVAC) systems are complex and prone to failures during operation, often leading to significant energy waste. Timely and accurate Fault Detection and Diagnosis (FDD) can enhance energy efficiency. The HVAC system operates under diverse conditions, data-driven models trained under existing conditions may experience performance degradation when faced with new conditions. Transfer learning offers an effective solution to this issue. This study proposes a novel transfer learning ensemble model based on adaptive weights, leveraging different transfer learning strategies to improve diagnosis performance under new conditions. Multiple cross-condition transfer learning tasks were implemented to test the proposed method, and its effectiveness was validated through multiple experiments to minimize the impact of randomness. Results showed that, compared to fine-tuning (FT), domain-adversarial neural network (DANN), and baseline models, the proposed method outperforms the other models. The average accuracy of multiple experiments improved by 0.21 % to 2.34 % compared to FT. Additionally, modifying DANN to utilize a small amount of labeled information from the target domain has led to greater overlap between the feature distributions of the source and target domains, resulting in improved performance that is close to that of FT. Finally, we analyzed the impact of target domain data volume on the performance of the four methods. The performance of the baseline model improved significantly with the increase in data volume, while the other models showed less improvement. Meanwhile, the diagnostic results of the baseline model were significantly influenced by experimental randomness when there is less training data, whereas the FT diagnostic results were relatively more stable.

Fuzzy logic-supported building design for low-energy consumption in urban environments

Climate, building materials, occupancy patterns, and HVAC (heating, ventilation, and air conditioning) systems all interact in complex ways, making it difficult to design low-energy buildings. Thus, innovative architectural and engineering design strategies are required to meet the worldwide need to decrease building energy usage. To improve the calculation of energy consumption of buildings, this work introduces the FCR-BCS (fuzzy clustering rule-based building control systems), which integrates fuzzy logic concepts into computational simulations. FCR-BCS can contemplate real-world uncertainties and fluctuations using linguistic factors and approximate reasoning for more precise and trustworthy results in energy-efficient building design. This method's significance rests in its potential to significantly reduce energy use, advance sustainability, and improve urban residents' quality of life; architects and engineers can thus employ FCR-BCS to enhance the efficiency of HVAC systems and insulation. The outcomes of FCR-BCS simulation assessments show that it is capable of making buildings more energy efficient. The experimental outcomes demonstrate that the suggested model increases the sensitivity analysis by 99.4 %, energy efficiency analysis by 99.8 %, occupancy patterns analysis by 97.5 %, temperature profile analysis by 98.8 %, and energy consumption analysis by 99.6 % compared to other existing models.

Experimental evaluations of Berkeley thermal sensation and comfort models in electric vehicle cabin under cold outdoor conditions

As the automobile industry is transitioning toward electric vehicles, manufacturers have started implementing local warmers alongside cabin heating, ventilation, and air conditioning (HVAC) systems for effective thermal comfort management. However, optimal operating strategies need to be developed for integrating local warmers with HVAC systems. Although the Berkeley models comprising local/overall thermal sensation and comfort models offer insights in this regard, they lack follow-up assessments for occupants transitioning from very cold states. In this study, Berkeley models were evaluated using two sets of experimental data collected in a transient vehicle cabin under cold outdoor conditions: test (A) with cabin HVAC alone and test (B) with both HVAC and local warmers. The findings confirm the satisfactory performances of the Berkeley models for predicting overall sensation and comfort, with a maximum root mean-squared error (RMSE) of 0.15. The local comfort model performed poorly with the original coefficients across both datasets (maximum RMSE of 1.96). Therefore, the model coefficients were regressed for the dataset from test A and validated against the dataset from test B to achieve a maximum RMSE of 0.49. With these regressed coefficients, it was observed that moving toward a neutral whole-body state diminished the potential to maximize local comfort. Conversely, the local sensation model showed poor agreement (maximum RMSE of 1.9); we confirmed that accurate adaptive setpoint temperatures are a prerequisite for ensuring good predictions from the model. These findings are expected to contribute toward future efforts in using Berkeley models to formulate effective local warmer–HVAC operational strategies in electric vehicles.

Generation Method for HVAC Systems Design Schemes in Office Buildings Based on Deep Graph Generative Models

The design process of heating, ventilation, and air conditioning (HVAC) systems is complex and time consuming due to the need to follow design codes. Since the design standards are not fixed, the final outcome often depends on the designer’s experience. The development of building information modeling (BIM) technology has made information throughout the building lifecycle more integrated. BIM-based forward design is now widely used, providing a data foundation for combining HVAC system design with machine learning. This paper proposes an unsupervised learning method based on deep graph generative models to uncover hidden design patterns and optimization strategies from the design results. We trained and validated four deep graph generative models—GAE, GNF, GAN, and diffusion—using HVAC system terminal pipeline layout data. Accuracy and precision metrics were used to compare the generated designs with automated forward design solutions, assessing the models’ ability to capture both local variations and broader changes in design logic. A graph-neural-network-based evaluation method was employed to measure the models’ capacity to detect changes. The results indicate that all four models achieved prediction accuracies exceeding 90% and precision rates above 75%. The models effectively captured both local modifications made by designers and global design changes, showing greater sensitivity to global layout adjustments than to local updates. When comparing the results generated by deep graph generative models and the actual design, it is obvious that the accuracy of the predictions varies significantly due to the complexity of the test buildings.

Recent Advances in Desiccant Materials for Energy‐Efficient and Sustainable Heat Transfer Systems

The expanding prevalence of heating, ventilation, and air conditioning (HVAC) systems, currently reliant on fossil fuel‐derived energy, necessitates energy‐saving measures to address climate change concerns. Implementing desiccants with high water vapor affinity reduces latent heat input, impacting the heat exchanger's functionality based on system and desiccant characteristics. This review analyzes the materials in solid desiccants, binders, and substrates, emphasizing advancements for enhanced heat transfer efficiency. Some notable materials explored include metal–organic frameworks, activated carbon, silica gel, polymers, and zeolite. In system level, the article discusses about the dual‐channel heat exchanger which emerges as a solution to drawbacks in existing dehumidification systems, offering higher performance and lower latent heat load in modern solid desiccant‐coated heat exchangers. Despite the environmental impact of material usage, future research should focus on sustainable materials, such as those derived from biomass or recycled sources, to maintain efficiency while minimizing waste in HVAC systems.

Electric Vehicle Thermal System Concept Development for Multiple Variants Using Digital Prototype and AI

The automotive industry is experiencing a surge in system complexity driven by the ever-growing number of interacting components, subsystems, and control systems. This complexity is further amplified by the expanding range of component options available to original equipment manufacturers (OEMs). OEMs work in parallel on more than one vehicle model, with multiple vehicle variants for each vehicle model. With the increasing number of vehicle variants needed to cater to diverse regional needs, development complexity escalates. To address this challenge, modern techniques like Model-Based Systems Engineering (MBSE), digitalization, and Artificial Intelligence (AI) are becoming essential tools. These advancements can streamline concept development, optimize thermal and HVAC system design across variants, and accelerate the time-to-market for next-generation EVs. The development of battery electric vehicles (BEVs) needs a strong focus on thermal management systems (TMSs) and heating, ventilation, and air conditioning (HVAC) systems. These systems play a critical role in maintaining optimal battery temperature, maximizing range and efficiency, and ensuring passenger comfort. This article proposes a digital prototype (DP) and AI-based methodology to specify BEV thermal system and HVAC system components in the concept phase. This methodology uses system and variant thinking in combination with digital prototype (DP) and AI to verify BEV thermal system architecture component specifications for future variants without extensive simulation. A BEV cabin cooling requirement of 22 °C to be achieved within 1800s at a high ambient temperature (45 °C) is required, and its verification is used to prove this methodology.

Barriers to implement energy efficiency strategies to heating, ventilation, air conditioning of airside system in commercial buildings in Sri Lanka

At present, debates on climate change, fossil fuel depletion, and energy saving highlight the need for a sustainable built environment to reduce energy consumption and emission trends. The Heating, Ventilation, and Air Conditioning (HVAC) system is a priority due to its significant share of a building’s electricity consumption. While energy efficiency strategies for central air conditioning systems focus on both waterside and airside components, implementing airside efficiency strategies is notably lacking in Sri Lanka. This is a concern because airside inefficiencies lead to excessive energy use, higher operational costs, and compromised indoor air quality. Thus, the study aims to address this gap by identifying the barriers to implementing energy efficiency strategies for HVAC airside systems in Sri Lankan commercial buildings. To explore these barriers, a qualitative research approach was employed, involving interviews with 17 industry experts. The study identified 27 barriers, with key barriers being a lack of technical expertise, rapid technological advancements, misalignment with organisational objectives, limited financial resources, inadequate training and technical knowledge, and insufficient regulatory support. The insights gained from this study can assist industry professionals in enhancing HVAC energy performance and encourage further academic research on this sub-branch of HVAC systems in the Sri Lankan context.

Adaptive fusion graph convolutional network based interpretable fault diagnosis method for HVAC systems enhanced by unlabeled data

Fault diagnosis is critical in maintaining the operational stability and reliability of Heating, Ventilation, and Air Conditioning (HVAC) systems, which are crucial for ensuring indoor environmental quality and energy efficiency in buildings. However, traditional fault diagnosis methodologies face substantial challenges in accurately capturing the dynamic interactions within these systems and effectively utilizing unlabeled data. To overcome these limitations, an innovative fault diagnosis approach utilizing the Adaptive Fusion Graph Convolution Network (AFGCN) is proposed in this paper. This method significantly enhances the model's learning and inference abilities, particularly in scenarios with limited labeled data, by adaptively integrating the associative graph features of both unlabeled and labeled data. Furthermore, to augment the transparency and trustworthiness of the diagnostic outcomes, this paper introduces an interpretability analysis module. This module is designed to quantify the contribution of each sensor node in the fault diagnosis process. Experimental evaluations using the ASHRAE RP-1043, actual building operating chillers datasets, and LBNL FDD Data Sets_SDAHU indicate that this method offers substantial performance improvements in diagnosing faults in HVAC systems.