A deep neural network based fault diagnosis method for centrifugal chillers

With industrial production processes becoming more and more sophisticated, traditional fault diagnosis systems may not achieve reliable diagnosis performance. In order to improve fault diagnosis performance, this paper proposes an enhanced fault diagnosis system by integrating neural networks with Andrews plot. On-line measurements are first processed by Andrews plot and then fed to a neural network for fault classification. Application to a simulated CSTR process indicates that the proposed method can give more reliable and earlier diagnosis than the traditional neural network based fault diagnosis method combined with principal component analysis.

The battery system, as the core energy storage device of new energy vehicles, faces increasing safety issues and threats. An accurate and robust fault diagnosis technique is crucial to guarantee the safe, reliable, and robust operation of lithium-ion batteries. However, in battery systems, various faults are difficult to diagnose and isolate due to their similar features and internal coupling relationships. In this paper, the current research of advanced battery system fault diagnosis technology is reviewed. Firstly, the existing types of battery faults are introduced in detail, where cell faults include progressive and sudden faults, and system faults include a sensor, management system, and connection component faults. Then, the fault mechanisms are described, including overcharge, overdischarge, overheat, overcool, large rate charge and discharge, and inconsistency. The existing fault diagnosis methods are divided into four main types. The current research and development of model-based, data-driven, knowledge-based, and statistical analysis-based methods for fault diagnosis are summarized. Finally, the future development trend of battery fault diagnosis technology is prospected. This paper provides a comprehensive insight into the fault and defect diagnosis of lithium-ion batteries for electric vehicles, aiming to promote the further development of new energy vehicles.

Comparative study on deep transfer learning strategies for cross-system and cross-operation-condition building energy systems fault diagnosis

Deep neural network approach for fault detection and diagnosis during startup transient of liquid-propellant rocket engine

Large non-residential buildings can contain complex and often inefficient water distribution systems. As requirements for water increase due to water scarcity and industrialization, it has become increasingly important to effectively detect and diagnose faults in water distribution systems in large buildings. In many cases, if water supply is not impacted, faults in water distribution systems can go unnoticed. This can lead to unnecessary increases in water usage and associated energy due to pumping, treating, and heating water. The majority of fault detection and diagnosis studies in the water sector are limited to municipal water supply and leakage detection. The application of detection and diagnosis for faults in building water networks remains largely unexplored and the ability to identify and distinguish between routine and non-routine water usage at this scale remains a challenge. This study using case-study data, presents the application of principal component analysis and a multi-class support vector machine to detect and classify faults for non-residential building water networks. In the absence of a process model (which is typical for such water distribution systems), principal component analysis is proposed as a data-driven fault detection technique for building water distribution systems for the first time herein. Hotelling T2-statistics and Q-statistics were employed to detect abnormality within incoming data, and a multi-class support vector machine was trained for fault classification. Despite the relatively limited training data available from the case-study (which would reflect the situation in many buildings), meaningful faults were detected, and the technique proved successful in discriminating between various types of faults in the water distribution system. The effectiveness of the proposed approach is compared to a univariate threshold technique by comparison of their respective performance in the detection of faults that occurred in the case-study site. The results demonstrate the promising capabilities of the proposed fault detection and diagnosis approach. Such a strategy could provide a robust methodology that can be applied to buildings to reduce inefficient water use, reducing their life-cycle carbon footprint.

During the past few years, adaptation to renewable energy and utilizing solar power have attracted an exponentially increasing interest in interdisciplinary research domains as well as large-scale economies. However and due to many environmental factors, providing a reliable and fault tolerant control solution that can accomplish the main objectives of the power generation, even in the presence of faults, is an inevitable requirement. The main objective of this paper is to review the challenges of fault diagnosis of solar power systems and to present a hybrid and cloud-enabled architecture for a health monitoring system for photovoltaic (PV) farms, where both model-based and data-driven methods are utilized in a unified framework. The main focus of our proposed architecture is to explain the main components of a practical solution such that it can be easily integrated into currently available cloud technologies. This solution can significantly improve reliability of the new generations of power supply networks. The key enabler of our proposed solution is its modular structure; particularly, it can be augmented with any available or future control systems such as automated PV cleaning systems in order to provide a fully autonomous fault tolerant control solution that can (i) detect, (ii) localize, and (iii) rectify various types of faults in PV systems (such as shade faults). Furthermore, we discuss data privacy concerns and how our architecture addresses this issue.

Buildings are subject to faults in their heating, ventilation and air-conditioning (HVAC) systems that can lead to excessive energy wastage, poor indoor climate, equipment failures and high maintenance costs. Field studies have shown that employing fault detection, diagnosis and prognosis (FDDP) tools followed up with equipment services and corrections can help achieve up to 40% of energy savings within the HVAC system and improve indoor climate, increase equipment lifecycle and reduce maintenance costs. The increasing adoption of building automation systems (BAS), Internet of Things (IoT) and other smart technologies in recent years have allowed large amounts of data to be continuously collected from building systems. This data-rich environment, along with the surge in data analytics and machine learning tools, has made cost-effective data-driven FDDP strategies possible. Compared to purely physics-based methods, data-driven methods require less explicit knowledge of the underlying physical system, thus are often easier to develop, and can learn certain intricate relationships that exist among data. Within the reported data-driven FDDP methods, there exists a few research gaps: 1) data imputation methods that leverage mutual information from correlated measurements to defy poor data quality from BAS have not been utilized efficiently; 2) there lacks a systematic and scalable fault diagnosis framework that incorporates probabilistic temporal relationships to track fault evolution; 3) existing fault diagnosis strategies typically focus on traditional rule-based control strategies and their scalability for advanced control strategies such as Guideline 36 have not been explored yet; 4) active threats information such as cyber-attacks, are typically not incorporated in an FDDP framework; 5) fault prognosis strategies to preemptively identify gradual faults for predictive maintenance have rarely been studied. This research attempts to address the above-mentioned research gaps through the following: Data Imputation: reported data imputation methods that are suitable for handling and repairing multi-source BAS data are evaluated. Data collected from a medium-sized, mixed-use institution building situated in Stockholm, Sweden and a small commercial building simulated in a laboratory setup is used to evaluate five different data imputation methods. Results demonstrate that incorporating time-lagged cross-correlations within the k-Nearest Neighbor (kNN) method helps to significantly improve the imputation accuracy and minimize the impact of repaired data on data-driven algorithms. Dynamic Bayesian Network (DBN)-based Framework for Cyber-Physical Fault Diagnosis: a DBN framework with discretized conditional probabilities parameters to represent the temporal relationships among building measurements is developed. Both domain knowledge and machine learning methods are used to develop the DBN structure and parameter model. The developed framework is evaluated for both traditional rule-based and Guideline 36 controls using datasets from a real building, a laboratory building, and a virtual testbed. Results show that the developed DBN framework is effective in diagnosing and isolating faults in systems even with different control strategies. The framework also successfully distinguishes whether system abnormalities originate from cyber-attacks or naturally occurring physical faults. Potential future direction to improve fault isolation using modified DBN topological structure is also reported in this study. DBN-based Framework for Fault Prognosis: an extension of the DBN framework in conjunction with Robust Multivariate Temporal (RMT) variate selection is proposed for fault prognosis. The RMT variate selection is used to extract localized temporal features from high dimensional datasets to determine the best inputs for training forecasting models. The expected fault-free behavior of multiple target variates, selected using domain knowledge, is forecasted using incoming data. The prediction errors generated from the forecasting phase are used as evidences in the DBN inference to estimate future fault probabilities. Gradual faults simulated in the virtual testbed are used to evaluate the prognosis framework. Results show that the developed framework is effective in prognosing gradual faults by leveraging the trending growth on the prediction errors. The research presented in this thesis contributes to the overall objective of developing a robust and cost-effective DBN-based framework for fault diagnosis and prognosis of building HVAC systems. Potential solutions to other existing challenges of implementing data-driven FDDP strategies, such as obtaining high-quality datasets, handling and repairing missing data, establishing a baseline model for detecting abnormalities despite other disturbances such as weather and internal conditions changes, and extracting temporal features from timeseries data are also examined.

Ensemble learning with member optimization for fault diagnosis of a building energy system

With growing realization of the benefits brought by fault detection and diagnosis(FDD), a large body of research pertinent to FDD methods for centrifugal chillers has been conducted during the past two decades. However, at the present time, relatively few FDD methods can handle multiple simultaneous faults on centrifugal chillers. This article describes the development of some decoupling features, which are the basis of a decoupling-based FDD methodology that can handle multiple simultaneous faults on centrifugal chillers. The performance of the decoupling features were validated and evaluated by the laboratory data from a 90-ton centrifugal chiller tested in a laboratory environment.

Improved on-line process fault diagnosis through information fusion in multiple neural networks

A new adaptive PCA based thresholding scheme for fault detection in complex systems

This study presents a fault diagnosis system for vehicle heating, ventilation and air conditioning (HVAC) acoustic signal with various feature extractions in deep learning neural network. Traditionally, sound used for fault diagnosis or signal classification is observed the difference of energy in time or frequency domains. Unfortunately, the frequency smearing effect often arises in some critical conditions. In the present study, discrete wavelet transform (DWT) and wavelet packet transform (WPT) are proposed in fault diagnosis. Meanwhile, when using mechanical learning methods, the data are relatively large, in order to reduce the amount of data, DWT and WPT low-frequency decomposition could be used to improve the performance. Furthermore, the signal characteristics more comprehensive, this study attempts to use the feature extraction method of wavelet packet conversion to improve the signal characteristics. In the experiment process, the operation state of the blade blower in the vehicle air conditioner, four different faults were designed, test database was established through sound to classify, and identify the data using deep neural networks to achieve the purpose of blower fault diagnosis. In data analysis, the original signal is presented through wavelet packet decomposition and discrete packet conversion technology, compared with traditional time and frequency domain signals to explore the identification rate, identification speed and related issues. Experimental results show that using WPT combined with deep neural networks have good fault diagnosis and discrimination capabilities, training, and identification time is shorter than time-frequency domain signals.

This paper presents a neural network based fault diagnosis approach for analog circuits, taking the tolerances of circuit elements into account. Specifically, a normalization rule of input information, a pseudo-fault domain border (PFDB) pattern selection method and a new output error function are proposed for training the backpropagation (BP) network to be a fault diagnoser. Experimental results demonstrate that the diagnoser performs as well as or better than any classical approaches in terms of accuracy, and provides at least an order-of-magnitude improvement in post-fault diagnostic speed.

The importance of symbolic analysis in the neural network approach to analog circuit fault diagnosis is discussed in this paper. Theoretical explanations and two explicative examples are presented, by taking into account the k-fault hypothesis.

With the development of big data, artificial intelligence and other technologies, data-driven aviation equipment fault diagnosis and prediction technology has gradually become a research hotspot in the aviation field. Many typical intelligent algorithm models have been applied to this field. However, limited by the airborne embedded computing environment, there are still some problems in the deployment of intelligent prediction models represented by deep neural networks on aircraft. This paper summarizes and analyzes the research and application of typical deep neural networks such as convolutional neural networks in the field of aircraft fault diagnosis and prediction. Facing the airborne embedded environment, the current difficulties in deploying the deep neural network algorithm model in the airborne environment are analyzed. The development direction of the application of fault prediction and diagnosis algorithms represented by neural networks in the future is discussed.