Automatic Fault Diagnosis Research Articles

An automatic and efficient fault diagnosis strategy for air conditioning units by combining attention mechanisms

The air conditioning system is a very important energy-consuming device in the field of construction. Timely troubleshooting of air conditioning chillers is an important aspect of reducing building energy consumption. Aiming at the problems of many model parameters, large amount of calculation and strong dependence of diagnostic performance on input features in data-driven diagnostic methods, this paper proposes an efficient fault diagnosis strategy combining RepVGG network and SENet attention mechanism. The multi-parameter feature signal is converted into a two-dimensional matrix to obtain multiple feature images. Based on the SENet attention mechanism, the multi-channel weights of the images are extracted, and the weighted feature image is input into the RepVGG network for feature depth mining and classification. Therefore, the method proposed in this paper greatly reduces the calculation amount of parameters, improves the representativeness of signal features to faults and the efficiency of model training. The effectiveness of the method is validated using the ASHRAE RP-1043 chiller unit dataset. The results show that the accuracy of this method reaches 96.55%, which is significantly better than the comparison methods PSO-ELM(96.4%), DT(95.1%), RepVGG(91.6%), ELM(87.6%) and BP(80.8%).

An entropy-based causality framework for cross-level faults diagnosis and isolation in building HVAC systems

Faults, such as malfunctioning sensors, equipment, and control systems, significantly affect a building’s performance. Automatic fault detection and diagnosis (AFDD) tools have shown great potential in improving building performances, including both energy efficiency and indoor environment quality. Since modern buildings have integrated systems where multiple subsystems and equipment are coupled, many faults in a building are cross-level faults, i.e., faults occurring in one component that trigger operational abnormalities in other subsystems. Compared with non-cross-level faults, it is more challenging to isolate the root cause of a cross-level faults due to the system coupling effects. Bayesian networks (BNs) have been studied for the root cause isolation for building faults. While promising, existing BN-based diagnosis methods highly rely on expert domain knowledge, which is time-consuming and labor expensive, especially for cross-level faults. To address this challenge, we propose an entropy-based causality learning framework, termed Eigen-Entropy Causal Learning (EECL), to learn BN structures. The proposed method is data-driven without the use of expert domain knowledge; it utilizes causal inference to determine the causal mechanisms between faults status and symptoms to construct the BN model. To demonstrate the effectiveness of the proposed framework, three fault test cases are used for evaluation in this study. Experimental results show that the BN constructed by the proposed framework is able to conduct building cross-level faults diagnosis with a comparable isolation accuracy to those by domain knowledge while maintaining less complexed BN structure.

Fault detection and diagnosis in light commercial buildings’ HVAC systems: A comprehensive framework, application, and performance evaluation

The data-driven approach currently dominates the field of Automatic Fault Detection and Diagnosis (AFDD) in HVAC systems. However, a significant concern lies in the prevalent use of labeled experimental and simulation data, which often does not represent real-world operational conditions. This study unveils a comprehensive framework for AFDD in light commercial buildings, effectively leveraging unlabeled raw data extracted directly from their Building BAS. Its main goal is to provide a versatile methodology tailored for real-world applicability. Buildings classified as “light commercial” typically have less than 2,500 square meters of floor area and no more than six stories, such as small offices, medical facilities, banks, small manufacturing facilities, etc. A common feature of these buildings is the fact that the HVAC systems tend to be relatively simple and have similar configurations, thus making it easy to develop scalable and reproducible fault detection methods. This paper focuses on a practical case study in a light commercial building HVAC system situated in Montreal, Canada, encompassing a single Air Handling Unit (AHU) and four Variable Air Volume (VAV) reheating boxes to evaluate the framework. This comprehensive framework encompasses a sequence of sub-objectives: creating a sizable, synchronized raw dataset from diverse BAS sensor tags, comprehensive data cleansing to address inconsistencies, developing an anomaly detection method, investigating these anomalies to extract underlying rules, and finally, dataset labeling. An AFDD classification model is then applied to evaluate its ability to distinguish normal from faulty conditions across various fault types. The study highlights the potential of dimensional reduction techniques and unsupervised clustering for effective anomaly detection in light commercial buildings, as well as the power of the Decision Tree classifier for uncovering hidden patterns, especially in anomaly conditions. It also highlights the significance of addressing imbalanced datasets in AFDD and the complexities of detecting sizing-related faults. Despite these challenges, the framework exhibits robust performance in detecting and diagnosing a range of HVAC faults. It offers a systematic and adaptable approach for handling real-world operational data in light commercial building HVAC systems, extendible to other building types, bridging the gap between data-driven methods and practical applications.

A Deep Learning-Based Fault Diagnosis Approach for Power System Equipment via Infrared Image Sensing

Automatic fault diagnosis for power system equipment has always been an essential concern in this industry. Conventionally, such works are conducted by manual patrol inspection, which consumes much human labor and expert knowledge. Fortunately, infrared images can present diagnosis areas inside the equipment via the thermal sensing function. In such context, this work utilizes deep neural network to construct a specific infrared image processing framework that can realize automatic fault diagnosis. Thus in this paper, a deep learning-based fault diagnosis approach for power system equipment via infrared image sensing is proposed. First, a pulse-coupled neural network structure is employed to enhance feature representation for infrared images of the equipment. Next, a fuzzy [Formula: see text]-means (FCM)-based segmentation method is developed to filter diagnosis areas from the infrared images. Finally, a convolution operation-based fault diagnosis operator is adopted to identify the diagnosis types. After that, some simulation experiments are conducted on real-world infrared images on the power system equipment, in order to make the performance evaluation of the proposed approach. The proposal realizes the end-to-end process of feature extraction and fault detection and identification, and avoids the problems of single feature. It is due to manual extraction of fault features, and the inability to detect and identify faults effectively in specific situations and scenarios.

Chiller fault diagnosis based on improved variational autoencoder and co-training framework: A case study of insufficient samples

Implementing efficient automatic fault diagnosis is critical for saving energy and minimizing financial losses in the heating ventilation air-conditioning (HVAC) systems of commercial buildings. However, the limited quantity and weak features of fault samples acquired during HVAC operations hinder the effectiveness of conventional machine learning-based fault diagnosis methodologies. This paper proposes a method based on an improved conditional variational autoencoder (MCVAE) and co-training (CT) ideology to address the issue of insufficient training samples. Initially, we employ MCVAE to synthesize an extensive dataset of chiller fault samples from the original training dataset. Subsequently, the beneficial samples for training our fault diagnostic classifier, namely high-quality samples, are selected from the generated dataset using the CT-based framework. Finally, the selected high-quality samples are merged into the original training dataset to train the ultimate fault classifiers. Experimental results demonstrate that our proposed method outperforms in effectiveness and efficiency compared to recently published methods. For instance, in the case of fault level 1 compared to the suboptimal model, our approach exhibits improvements of 2.41% when each type has 5 fault samples.

Comprehensive fault diagnosis in UAV-assisted sensor networks: A three-phase automated approach

Ensuring operational safety in an automated working environment is a crucial requirement. In this article, we propose a technique for automated fault diagnosis in unmanned aerial vehicle-based sensor networks (UAV-sensor networks) aimed explicitly at the composite nature of different faults. Our technique consists of 3-stages: (1) UAVs collecting data from sensors and running a modified Z-score statistics to diagnose faulty readings; (2) the UAV cluster head running a multivariate analysis of variance (MANOVA) to identify data faults in cluster members; and (3) utilizing a probabilistic neural network with correlation centroids at the ground control station for further diagnosis of collected UAV data. This approach is intended for progressive improvement in fault diagnosis at different stages of data collection in a UAV-sensor network for critical applications. We conduct an extensive evaluation of our 3-stage approach on the data collected in real-time from the sensors in a physically created UAV-sensor network. The performance of the proposed modified Z-score test improves fault detection accuracy of ∼20.8%, false alarm rate of ∼54.3%, and false positive rate of ∼67.2% with the traditional and existing sensor fault detection approach. The performance of MANOVA to identify the permanent UAV data fault shows fault detection accuracy of ∼10.9%, false alarm rate of ∼44.3%, and false positive rate of ∼48.7% superior to the intermittent and transient faults. Our preliminary results suggest that the proposed approach can handle multiple composite faults and outperforms existing research results.

Automatic Fault Detection Method of Rotating Machinery Bearing Based on Complexity Analysis

In order to improve the working condition stability of rotating machinery bearings, an automatic fault detection method of rotating machinery bearings based on complexity analysis is proposed. The parameters of rotating machinery bearings are detected by using discrete sensor detection method, and the fault characteristics of rotating machinery bearings are extracted by fault type parameter extraction method. The complexity of rotating machinery bearings is detected by wavelet transform and fuzzy logic analysis. Considering the load mutation, noise disturbance, control strategy and other factors of rotating machinery bearings, the fault diagnosis and feature analysis model of rotating machinery bearings is established. The clustering and feature detection of rotating machinery bearings’ fault types are realized by the method of discrete complexity fusion clustering. Based on adaptive feedback compensation and parameter estimation, the output diagnostic error is taken as the fault detection index parameter, and the feature estimation in normal state and fault state is realized by harmonic level detection, so as to realize automatic fault detection of rotating machinery bearings. The simulation results show that this method has high accuracy and small deviation in fault detection of rotating machinery bearings, which improves the ability of automatic fault diagnosis.

Precision Leak Detection in Supermarket Refrigeration Systems Integrating Categorical Gradient Boosting with Advanced Thresholding

Supermarket refrigeration systems are integral to food security and the global economy. Their massive scale, characterized by numerous evaporators, remote condensers, miles of intricate piping, and high working pressure, frequently leads to problematic leaks. Such leaks can have severe consequences, impacting not only the profits of the supermarkets, but also the environment. With the advent of Industry 4.0 and machine learning techniques, data-driven automatic fault detection and diagnosis methods are becoming increasingly popular in managing supermarket refrigeration systems. This paper presents a novel leak-detection framework, explicitly designed for supermarket refrigeration systems. This framework is capable of identifying both slow and catastrophic leaks, each exhibiting unique behaviours. A noteworthy feature of the proposed solution is its independence from the refrigerant level in the receiver, which is a common dependency in many existing solutions for leak detection. Instead, it focuses on parameters that are universally present in supermarket refrigeration systems. The approach utilizes the categorical gradient boosting regression model and a thresholding algorithm, focusing on features that are sensitive to leaks as target features. These include the coefficient of performance, subcooling temperature, superheat temperature, mass flow rate, compression ratio, and energy consumption. In the case of slow leaks, only the coefficient of performance shows a response. However, for catastrophic leaks, all parameters except energy consumption demonstrate responses. This method detects slow leaks with an average F1 score of 0.92 within five days of occurrence. The catastrophic leak detection yields F1 scores of 0.7200 for the coefficient of performance, 1.0000 for the subcooling temperature, 0.4118 for the superheat temperature, 0.6957 for the mass flow rate, and 0.8824 for the compression ratio, respectively.

Automatic fault diagnosis of rolling bearings under multiple working conditions based on unsupervised stack denoising autoencoder

In practical engineering, data often lack labels, resulting in difficulty in fault diagnosis. Because stack-denoising autoencoders possess robust feature extraction capabilities and resistance to interference, an automatic and unsupervised bearing fault diagnosis method based on the stack-denoising autoencoder without an output layer was proposed in this study. As the stacked denoising autoencoder is an unsupervised algorithm, this approach can reduce reliance on manually labeled data labels. Therefore, this study proposed a new method for automatic fault diagnosis. First, the bearing fault features of the rolling bearing were extracted using the stack denoising autoencoder without an output layer. Meanwhile, the dimensions of the features were directly reduced to two or three dimensions by several hidden layers, thereby reducing manual experience. Second, the labels extracted from the clustering model were selected as inputs for different classifier models to automatically identify different types of faults. Two open-source rolling bearing datasets under various conditions were used to validate the classification performance of the proposed method. Finally, its effectiveness was verified using the experimental results. Various indicators were used to evaluate the performance of the proposed method, and the results showed an automatic bearing fault diagnosis accuracy of up to 90% when using different models and working conditions. Among the two datasets, the classification model achieved the highest accuracies of 0.99667 and 0.97143 and the lowest accuracies of 0.98000 and 0.90476, respectively.

Integrated building fault detection and diagnosis using data modeling and Bayesian networks

Heating, ventilation, and air-conditioning (HVAC) equipment faults and operational errors result in comfort issues and waste of energy in buildings. An Automatic Fault Detection and Diagnosis (AFDD) tool could help facility managers fix comfort and energy issues more efficiently, by identifying the most probable root causes. Existing AFDD methods mostly focus on equipment-level fault detection and diagnostics; almost no attention is given to building level fault diagnosis, considering inter-dependency between equipment through the energy distribution chain. In this work we propose a methodology to automatically derive a Bayesian network from HVAC system topology description such as Haystack. This Bayesian network models and estimates the state of all elements in the system, helping users to identify the most probable root fault. As it is able to ingest evidence from any source (field data, operators, or other models) and is capable of updating its estimates when new evidence is delivered, such a tool could have a great potential to be used interactively on the field. We applied the proposed methodology on simulated and real-world buildings and present in this paper one specific case.

Intelligent Processing of Power Operation Data Based on Improved Apriori Algorithm

This paper addresses several problems in the power system. Key challenges include low-power information integration, inappropriate system data management, inaccurate system data updating, and inefficient fault diagnosis. We focus on analyzing and diagnosing transmission line faults using the operation data of the power system. The study incorporates the quantitative identification of statements. This is done using the Apriori big data analysis and calculation method. Additionally, we utilize big data analysis and vast power operation data. We aim to achieve automatic analysis and pinpoint the causes of transmission line faults. Furthermore, we seek to optimize the traditional Apriori calculation method. This optimization results in a reduction of about 52% in the candidate item set calculation. The optimized M-Apriori calculation method can analyze the correlation between event index data and faults in real time, and realize automatic diagnosis and analysis of faults through operation data.

A Novel Electric Motor Fault Diagnosis by Using a Convolutional Neural Network, Normalized Thermal Images and Few-Shot Learning

Motors constitute one critical part of industrial production and everyday life. The effective, timely and convenient diagnosis of motor faults is constantly required to ensure continuous and reliable operations. Infrared imaging technology, a non-invasive industrial fault diagnosis method, is usually applied to detect the equipment status in extreme environments. However, conventional Infrared thermal images inevitably show a large amount of noise interference, which affects the analysis results. In addition, each motor may only possess a small amount of fault data in practice, as collecting an infinite amount of motor data to train the diagnostic system is impossible. To overcome these problems, a novel automatic fault diagnosis system is proposed in this study. Data features are enhanced by a normalization module based on color bars first, as the same color in various infrared thermal images represent different temperatures. Then, the few-shot learning method is used to diagnose the faults of unseen electric motors. In the few-shot learning method, the minimum dataset size required to expand system universality is fifteen pieces, effectively solving the universality problem of artificial-to-natural data migration. The method saves a large amount of training data resources and the experimental training data collection. The accuracy of the fault diagnosis system achieved 98.9% on similar motor datasets and 91.8% on the dataset of motors that varied a lot from the training motor, which proves the high reliability and universality of the system.

A Model for Prediction of Outer Race Defects of Rolling Contact Bearing based on Vibration Data Using Machine Learning Algorithms

The detection of bearing defects while the machinery is in use is essential for predicting the incipient failure and thereby providing an opportunity to take remedial measures for preventing the costly downtime and ensuring the safe and efficient operation of rotating machinery. With the increasing availability of vibration sensor data and the development of machine learning techniques, the ML methods have become a popular approach for automated fault diagnosis in bearings. In this paper, an attempt has been made to detect the faults in the outer race of bearing using different ML algorithms. An experimental setup has been designed and fabricated to conduct experiments on healthy and faulty bearings and the vibration signals were captured. The captured vibration signals were directly employed as images for training the ML algorithms without the need for conducting the spectral analysis. Six machine learning algorithms, namely, Linear Regression (LR), Decision Tree (DTR), KNN Regression (KNNR), Random Forest Regression (RFR), Convolution Neural Network (CNN), Naive Bayes (NB) were separately applied to classify the location of defects within the outer race of the ball bearing. The accuracy table are used to find the best suitable algorithm for the predictions. The methodology includes data preprocessing techniques, network architectures, training strategies, and evaluation metrics. It has been established that the use of ML technique is very effective in detecting the bearing defects and CNN is able to achieve 100% accuracy.

Barriers and drivers for implementation of automatic fault detection and diagnosis in buildings and HVAC systems: An outlook from industry experts

This study aimed to assess the current status of Fault Detection and Diagnosis (FDD) implementation in building and Heating, Ventilation and Air Conditioning (HVAC) systems in the building industry. Semi-structured qualitative interviews were conducted with 29 experts from different HVAC company types in the building industry. In addition, a literature review was performed to investigate academic research on FDD implementation. The study identified barriers and drivers to implementing FDD systems, these included; technological and technical, economic and business, users, social and societal, and regulatory. An Automatic Fault Detection and Diagnosis (AFDD) implementation matrix was developed to evaluate FDD implementation in building systems, and all interviewed companies were classified based on their FDD knowledge, services, and type. Results show that expert-rule systems are still prevalent in the industry. The literature review revealed a scarcity of FDD implementation studies in academic research due to challenges in testing and validating results in actual building operation conditions. Lastly, this study discusses the key findings: 1) FDD does not sell, 2) Lack of actively engaging and promoting FDD services, 3) FDD seems to be an academic definition, 4) The bottlenecks: The fault handling process and user’s mindset towards FDD, and 5) Governmental regulations and legislatives drive the implementation focus.

Blockchain-based trusted accountability in the maintenance of medical imaging equipment

Preventative maintenance is imperative for ensuring the longevity and reliability of diagnostic medical imaging equipment. However, conventional maintenance systems face challenges related to centralization, fragmented information, and ineffective tracking mechanisms. In response to these challenges, this research presents a blockchain-based solution that introduces a robust framework for managing preventative maintenance tasks. The proposed solution leverages blockchain technology, smart contracts, IPFS, and timer oracles to promote transparency, accountability, and traceability in maintenance operations. To ensure the integrity and availability of maintenance data while preserving the confidentiality of sensitive information, a detailed system architecture is outlined. Sequence diagrams and algorithms are developed to define the flow and logic of the solution, focusing on automatic fault detection and diagnosis. The smart contracts, which are made publicly available on GitHub, were rigorously tested to guarantee their intended functionality, thus addressing software reliability concerns. Additionally, the solution includes a maintenance incentive mechanism, actively motivating stakeholders to engage in preventative maintenance activities, and establishing accountability. Security testing confirms the absence of vulnerabilities in smart contracts, aligning with the scope of automatic fault detection and diagnosis. Furthermore, potential generalizations of the solution are discussed, and future directions emphasize the importance of continuous improvement and innovation in maintenance practices.

Contrastive learning and dynamics embedding neural network for label-free interpretable machine fault diagnosis

Industrial machinery often produces vibration signals that can serve as indicators of underlying faults. However, these signals often need to be labeled, presenting a challenge for accurate and interpretable fault diagnosis. While supervised learning methods, such as deep neural networks, have been applied for fault diagnosis, they need help in effectively distinguishing between different vibration-related faults. In response to this issue, our study introduces an innovative approach for automatic fault diagnosis through the application of the Bootstrap Your Own Latent and Dynamical Systems Model Discovery algorithm (BYOLDIS). This method not only addresses the challenge of unlabelled signals but also provides readily interpretable results. The proposed methodology consists of three fundamental steps. First, we derive a matrix of differential equations to capture the dynamic behavior of faulty bearings. Second, we employ a contrastive learning network alongside a time-delay embedding matrix to reconstruct the coordinates of the fault-dynamical system. Lastly, we construct a library of fault machine dynamic polynomial equations, incorporating prior constraints based on physical models. To assess the effectiveness and robustness of our proposed method, we conducted both simulations and experiments. The results of these case studies affirm that BYOLDIS can accurately diagnose bearing faults and offer dynamic explanations for the diagnostic outcomes. This suggests that BYOLDIS holds substantial promise as a diagnostic tool for processing unlabelled vibrational data.

Intelligent fault diagnosis for air handing units based on improved generative adversarial network and deep reinforcement learning

Data-driven Automatic fault detection and diagnosis (AFDD) for air handling units (AHUs) is crucial for ensuring the stable operation and energy consumption of the heating ventilation air-conditioning (HVAC) system. However, traditional machine learning methods often underperform when confronted with insufficient training sample data, especially when lacking samples from the fault types. Based on the issues of insufficient samples from the fault types and imbalanced training dataset, this study proposes a novel AFDD approach using transformer integrated conditional Wasserstein generative adversarial network and deep reinforcement learning (TCWGAN-DRL) to synthesize the fault data and select high quality synthetic data samples. Firstly, we utilize the proposed TransCWGAN to synthesize fault samples. Then, reinforcement learning is utilized to select high quality synthetic samples. Finally, the filtered samples and the real fault samples are merged to form the training dataset for conventional supervised learning classifiers. Experimental results demonstrate that the enriched training dataset can effectively improve the AFDD results and outperforms recently published existing methods, for instance, compared to the suboptimal model, our method exhibits an increase in fault recognition accuracy of 4.9%, 3.66%, and 4.02% when the number of real fault samples is 15, 20, and 30, respectively.

Set-based fault diagnosis for uncertain nonlinear systems

Automated fault diagnosis algorithms aim to identify the root cause of a fault after it is detected, which is crucial for determining a safe and effective response. Set-based methods are attractive for this task due to their unique ability to provide formal guarantees that the observed data is inconsistent with candidate fault models. However, such diagnosis methods have scarcely been applied to nonlinear systems because nonlinearity often makes the required inconsistency tests either very conservative or very computationally demanding using existing techniques. This paper proposes a new set-based fault diagnosis algorithm for nonlinear systems and demonstrates improved diagnosis speed and accuracy compared to existing set-based methods. The method tests for inconsistency using a new set-based observer enabled by recent advances in discrete-time reachability analysis.

Differentiable sampling based efficient architecture search for automatic fault diagnosis

Intelligent diagnosis on rotating machinery has developed rapidly, but different methods have fluctuating performance and fussy design, causing poor effect in practical applications. Thus, it would be great to automatically generate the optimal method for given diagnosis tasks, as differentiable neural architecture search (DNAS) does. However, three challenges severely restrict DNAS methods in industrial scenarios: 1) vibration signals are multi-scale and non-stationary; 2) huge memory cost by supernet-based search is unsuitable to practical diagnosis; 3) manual architecture derivation causes performance collapse between architecture search and practical diagnosis. Thus, we propose Differentiable Sampling based Efficient Architecture Search (DS-EAS), which generates architecture by differentiable sampling. First, the operator involution is introduced to adaptively extract critical features from noisy signals. Second, Gumbel Max-Softmax is adopted to forward sample and backward propagate the gradient on single sub-architecture at one iteration, alleviating huge memory cost. Third, progressively pruning is proposed to eliminate manual discretization error, leading to the final architecture with zero operators. Based on the searched architecture, a deeper one is built to test its real performance. Traction motor experiment is performed to discuss the performance of DS-EAS on three different sample cases. Compared with other state-of-the-art methods, outperformance of DS-EAS is successfully verified.

Multispectral Balanced Automatic Fault Diagnosis for Rolling Bearings under Variable Speed Conditions

As a key component of machine, most rolling bearings operate under variable speed conditions. Therefore, it is critical to complete automatic fault diagnosis for rolling bearings under variable speed conditions. Although there have been many research studies on fault diagnosis in recent years, the following two problems still exist in fault diagnosis of variable speed bearing: (1) due to the large range of energy distribution for signals under variable speed conditions, the existed signal processing methods lead to the loss of fault information; (2) when directional filtering is carried out according to four different types of faults, the difference in amplitudes of the obtained spectrums is large. This means that the filtering result with the maximum amplitude will be determined as the fault type by mistake. In order to integrate the information scattered across different frequency spectrums and use reasonable filtering to complete automatic diagnosis, Multispectral Balanced Automatic Fault Diagnosis is proposed for rolling bearings under variable speed conditions. On the one hand, signals are preprocessed by the Multispectral Lossless Preprocessing Module, which can eliminate the influence of variable rotating speeds and avoid the loss of fault information. On the other hand, the Balanced Envelope Demodulation Module is designed to realize automatic fault diagnosis by Protrugram and Balancing Envelope Spectrum. The effectiveness of the proposed method is verified by simulated signals and experimental data. Results indicate that the method can complete automatic fault diagnosis of rolling bearings under variable speed conditions with an accuracy of 76%, which outperforms state-of-the-art methods.