Support vector machine based fault detection and diagnosis for HVAC systems

The malfunctioning of the heating, ventilating, and air conditioning (HVAC) system is considered to be one of the main challenges in modern buildings. Due to the complexity of the building management system (BMS) with operational data input from a large number of sensors used in HVAC system, the faults can be very difficult to detect in the early stage. While numerous fault detection and diagnosis (FDD) methods with the use of statistical modeling and machine learning have revealed prominent results in recent years, early detection remains a challenging task since many current approaches are unfeasible for diagnosing some HVAC faults and have accuracy performance issues. In view of this, this study presents a novel hybrid FDD approach by combining random forest (RF) and support vector machine (SVM) classifiers for the application of FDD for the HVAC system. Experimental results demonstrate that our proposed hybrid random forest–support vector machine (HRF–SVM) outperforms other methods with higher prediction accuracy (98%), despite that the fault symptoms were insignificant. Furthermore, the proposed framework can reduce the significant number of sensors required and work well with the small number of faulty training data samples available in real-world applications.

In this work, HVAC (Heating, Ventilation and Air Conditioning) systems applied in university buildings with control based on PMV (Predicted Mean Vote) and aPMV (adaptive Predicted Mean Vote) indexes are discussed. The building’s thermal behavior with complex topology, in transient thermal conditions, for summer and winter conditions is simulated by software. The university building is divided into 124 spaces, on two levels with an area of 5931 m2, and is composed of 201 transparent surfaces and 1740 opaque surfaces. There are 86 compartments equipped with HVAC systems. The simulation considers the actual occupation and ventilation cycles, the external environmental variables, the internal HVAC system and the occupants’ and building’s characteristics. In this work, a new HVAC control system, designed to simultaneously obtain better occupants’ thermal comfort levels according to category C of ISO 7730 with less energy consumption, is presented. This new HVAC system with aPMV index control is numerically implemented, and its performance is compared with the performance of the same HVAC system with the usual PMV index control. Both HVAC control systems turn on only when the PMV index or the aPMV index reaches values below −0.7, in winter conditions, and when the PMV index or the aPMV index reaches values above +0.7, in summer conditions. In accordance with the results obtained, the HVAC system guarantees negative PMV and aPMV indexes in winter conditions and positive PMV and aPMV indexes in summer conditions. The energy consumption level is higher in winter conditions than in summer conditions for compartments with shading, and it is lower in winter conditions than in summer conditions for compartments exposed to direct solar radiation. The consumption level is higher using the PMV control than with the aPMV control. Air temperature, in accordance with Portuguese standards, is higher than 20 °C in winter conditions and lower than 27 °C in summer conditions. In Mediterranean climates, the HVAC systems with aPMV control provide better occupants’ thermal comfort levels and less energy consumption than the HVAC system with PMV control.

A data-driven fault detection and diagnosis scheme for air handling units in building HVAC systems considering undefined states

A strategy of fault detection and diagnosis (FDD) for HVAC sub-systems at the system level is presented in this paper. In the strategy, performance indices (PIs) are proposed to indicate the health condition of different sub-systems including cooling tower system, chiller system, secondary pump systems before heat exchangers, heat exchanger system and secondary pump system after heat exchangers. The regression models are used to estimate the PIs as benchmarks for comparison with monitored PIs. The online adaptive threshold determined by training data and monitored data is used to determine whether the PI residuals between the estimation and calculation or monitoring are in the normal working range. A dynamic simulation platform is used to simulate the faults of different sub-systems and generate data for training and validation. The proposed FDD strategy is validated using the simulation data and proven to be effective in the FDD of heating, ventilating and air-conditioning (HVAC) sub-systems. Copyright © 2009 John Wiley & Sons, Ltd.

Due to the growing demand on high efficient heat ventilation and air conditioning (HVAC) systems, how to improve the efficiency of HVAC system regarding reduces energy consumption of system has become one of the critical issues. Reports indicate that efficiency and availability are heavily dependent upon high reliability and maintainability. Recently, the concept of e-maintenance has been introduced to reduce the cost of maintenance. In e-maintenance systems, the fault detection and isolation (FDI) system plays a crucial role for identifying failures. Finding healthy HVAC source as the reference for health monitoring is the main aim in this area. To dispel this concern a comprehensive transient model of heat ventilation and air conditioning (HVAC) systems is developed in this study. The transient model equations can be solved efficiently using MATLAB coding and simulation technique. Our proposed model is validated against real HVAC system regarding different parts of HVAC. The developed model in this study can be used for a pre tuning of control system and put to good use for fault detection and isolation in order to accomplish high-quality health monitoring and result in energy saving. Fan supply consider as faulty device of HVAC system with six fault type. A sensitivity analysis based on evaluated model shows us three features are sensitive to all faults type and three auxiliary features are sensitive to some faults. The magnitude and trait of features are a good potential for automatic fault tolerant system based on machine learning systems

Fault Detection and Diagnosis (FDD) in complex industrial systems requires methods that can handle uncertain operating conditions, soft thresholds, evolving sensor behavior, and increasing volumes of heterogeneous data. Traditional model-based or rule-driven approaches offer interpretability but lack adaptability, while purely data-driven and Large Language Model (LLM)-based methods often struggle with consistency, traceability, and causal grounding. Dynamic Master Logic (DML) provides a causal and temporal reasoning structure with fuzzy rules that capture gradual drift, soft limits, and asynchronous sensor signals while preserving traceability and deterministic evidence propagation. Building on this foundation, this paper presents a DML-LLM hybrid architecture that integrates targeted LLM inference to interpret unstructured information such as logs, notes, or retrieved documents under controlled prompts that maintain domain constraints. The combined system integrates Bayesian updating, deterministic routing, and semantic interpretation into a unified FDD pipeline. In a semiconductor manufacturing case study, the proposed framework reduced time to detection (TTD) from 7.4 h to 1.2 h and improved the F1 score from 0.59 to 0.83 when compared with conventional Statistical Process Control (SPC) and Fault Detection and Classification (FDC) workflows. Provenance completeness increased from 18% to 96%, while engineer triage time was reduced from 72 min to 18 min per event. These results demonstrate that the hybrid framework provides a scalable and explainable approach to anomaly detection and fault diagnosis in sensor-rich industrial environments.

Fault detection and diagnosis (FDD) is of utmost importance in ensuring the safety and reliability of electric vehicles (EVs). The EV’s power train and energy storage, namely the electric motor drive and battery system, are critical components that are susceptible to different types of faults. Failure to detect and address these faults in a timely manner can lead to EV malfunctions and potentially catastrophic accidents. In the realm of EV applications, Permanent Magnet Synchronous Motors (PMSMs) and lithium-ion battery packs have garnered significant attention. Consequently, fault detection methods for PMSMs and their drives, as well as for lithium-ion battery packs, have become a prominent area of research. An effective FDD approach must possess qualities such as accuracy, speed, sensitivity, and cost-effectiveness. Traditional FDD techniques include model-based and signal-based methods. However, data-driven approaches, including machine learning-based methods, have recently gained traction due to their promising capabilities in fault detection. This paper aims to provide a comprehensive overview of potential faults in EV motor drives and battery systems, while also reviewing the latest state-of-the-art research in EV fault detection. The information presented herein can serve as a valuable reference for future endeavors in this field.

Building performance can degrade precipitously after commissioning without adequate maintenance. HVAC system malfunctions can result in excessive energy consumption, associated CO2 emissions, and poor indoor environmental quality, and productivity loss. Fault Detection and Diagnosis (FDD) algorithms using sensor networks and IoT devices are a topic of significant research. This paper presents a comprehensive literature review of HVAC FDD applications using machine learning methods, including supervised classification, unsupervised learning, regression, statistics-based, and hybrid approaches. Each is discussed with respect to their state of development, relative advantages and limitations.

A LTHOUGH the past three decades have witnessed several important developments in attitude stabilization control [1,2], there still remain certain open problems that are of great theoretical and practical interests, such as actuator constraint. Because of physical limitations, typical control actuators (e.g., reaction wheels and thrusters) for attitude control have an upper bound on the torque they can generate. If this issue is not solved during attitude maneuvering, then the attitude system will continue issuing its commands that may no longer be achievable by the satellite, and the required control will quickly saturate actuators. This will subsequently destabilize and even lead to loss of control of the satellite. Therefore, actuator constraint is one key issue that needs to be addressed. At present, a great deal of attention has been focused on the stability analysis and the attitude control design with saturated actuators [3–6]. Another problem that needs to be addressed is fault tolerant control for the attitude system. Any component or system fault can potentially cause a host of economic and safety problems. As a result, online and real-time fault tolerant control (FTC) design for satellites has received considerable attention [7]. Generally speaking, FTC can be classified into two types: passive and active [8]. The passive FTC is designed to be robust to a class of possible faults. It does not require fault detection and diagnosis (FDD) schemes. In an attempt to develop attitude controllers that can accommodate faults, extensive studies on the passive FTC control system for satellites have been performed [9–11]. The active FTC can react to fault events by using a reconfigurationmechanism. The active FTC relies on the availability of an FDD mechanism that gives, in real time, information about the nature and the intensity of the fault. The design of active FTC, especially the fault detection and diagnosis scheme for satellite attitude, has attracted considerable interest [12–14]. Although the methodologies including FDD and control law reconfiguration for the control-type faults of satellite attitude system have been studied extensively (as seen in the preceding references), the problem that is not solved yet is the effective and practical strategies for handling severe failure cases combining with actuators constraint. Lack of such effective FTC strategies may lead to substantial performance deterioration and even the loss of a satellite. The clear knowledge of the link between control reconfiguration and the actuator input constraint is still lacking. Because the control reconfiguration at different time instants with different types of faults has greatly different effects on control actuators saturation, there is no explicit and simple relationship between them, which makes this problem even more difficult. This leads to an important practical problem: how tomake use of the control reconfiguration on available control redundancy. Motivated by this problem, a novel attitude control approach is presented in this paper; an observer-based FDD scheme combining a sliding mode controller by using the estimated information is designed in a framework of active FTC system. The main contribution of this study, relative to otherworks, is that actuator faults, actuator constraints, and external disturbances are simultaneously addressed in an attitude FTC system design.

Fault Detection and Diagnosis for Nonlinear Systems: A Support Vector Machine Approach

Feasibility and improvement of fault detection and diagnosis based on factory-installed sensors for chillers

This study presents a comprehensive methodology for developing a Fault Detection and Diagnosis (FDD) system for an industrial distillation column using advanced machine learning algorithms. Steady state and dynamic simulations in Aspen Plus® generate extensive datasets under normal and faulty conditions. Feature engineering, using the Minimum Redundancy Maximum Relevance (MRMR) algorithm, selects the most relevant features for fault detection. Various machine learning models, including Decision Trees, Support Vector Machines, k-nearest Neighbours, and Neural Networks, were trained and evaluated based on performance metrics such as accuracy, recall, precision, and F1 score. The top models were integrated into a stacked classifier system with a voting mechanism to enhance fault detection reliability. Explainable Artificial Intelligence (XAI) techniques, such as Local Interpretable Model-agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP), were incorporated to improve model interpretability, allowing engineers to understand and validate the FDD system's decision-making process. Simulation results confirm that the proposed methodology accurately identifies and classifies faults. By integrating dynamic simulations, advanced machine learning, and XAI techniques, a robust and scalable solution is achieved for fault detection in distillation columns, improving operational reliability, safety, and reducing downtime. Future work could extend this approach to other industrial processes and explore additional machine learning algorithms to further enhance performance.

The problem of fault detection and diagnosis (FDD) in dynamic systems has received considerable attention in last decades due to the growing complexity of modern engineering systems and ever increasing demand for fault tolerance, cost efficiency, and reliability (Willsky, 1976; Basseville, 1988). Existing FDD approaches can be roughly divided into two major categories including model-based and knowledge-based approaches (Venkatasubramanian et al., 2003a; Venkatasubramanian et al., 2003b). Model-based approaches make use of the quantitative analytical model of a physical system. Knowledgebased approaches do not need full analytical modeling and allow one to use qualitative models based on the available information and knowledge of a physical system. Whenever the mathematical models describing the system are available, analytical model-based methods are preferred because they are more amenable to performance analysis. Generally, there are two steps in the procedure of model-based FDD. First, on the basis of the available observations and a mathematical model of the system, the state variable x and test statistics are required to be obtained. Then, based on the generated test statistics, it is required to decide on the potential occurrence of a fault. For linear and Gaussian systems, the Kalman filter (KF) is known to be optimal and employed for state estimation. The innovations from the KF are used as the test statistics, based on which hypothesis tests can be carried out for fault detection (Belcastro & Weinstein, 2002). In reality, however, the models representing the evolution of the system and the noise in observations typically exhibit complex nonlinearity and non-Gaussian distributions, thus precluding analytical solution. One popular strategy for estimating the state of such a system as a set of observations becomes available online is to use sequential Monte-Carlo (SMC) methods, also known as particle filters (PFs) (Doucet et al., 2001). These methods allow for a complete representation of the posterior probability distribution function (PDF) of the states by particles (Guo & Wang, 2004; Li & Kadirkamanathan, 2001). The aforementioned FDD strategies are single-model-based. However, a single-model-based FDD approach is not adequate to handle complex failure scenarios. One way to treat this

Heat, ventilation, and air conditioning (HVAC) systems are some of the most energy-intensive equipment in buildings and their faulty or inefficient operation can significantly increase energy waste. Non-Intrusive Load Monitoring (NILM), which is a software-based tool, has been a popular research area over the last few decades. NILM can play an important role in providing future energy efficiency feedback and developing fault detection and diagnosis (FDD) tools in smart buildings. Therefore, the review of NILM-based methods for FDD and the energy efficiency (EE) assessment of HVACs can be beneficial for users as well as buildings and facilities operators. To the best of the authors’ knowledge, this paper is the first review paper on the application of NILM techniques in these areas and highlights their effectiveness and limitations. This review shows that even though NILM could be successfully implemented for FDD and the EE evaluation of HVACs, and enhance the performance of these techniques, there are many research opportunities to improve or develop NILM-based FDD methods to deal with real-world challenges. These challenges and future research works are also discussed in-depth.

This paper investigates the problem of fault detection and diagnosis (FDD) problem for non-gausian singulat stochastic distribution control (SDC) systems via the output probability density functions(PDFs). The PDFs can be approximated by using square-root B-spline expansion,via this expansions to represent the dynamics weighting systems between the system input and the weights related to the output PDFs. In this works ,an optimal fault detection and diagnosis algorith is present by introducing the parameter-updating .when the fault occurs, an adaptive network parameter-updating law is designed to approximated the fault. Finally, the simulation result are given to show that the approach can detect faults and estimate the size of fault.