Support Vector Data Description Research Articles

Research on online anomaly detection methods for bearing degradation

In industrial applications, rolling bearings operate under conditions of high precision and high speed, and their physical and mechanical characteristics change with the increase in operating time. Traditional diagnostic methods struggle to adapt well to the changing characteristics of bearings for online anomaly detection. Therefore, this research proposes an online anomaly detection method for rolling bearings based on time-density-weighted incremental support vector data description (TISVDD). A classification strategy is proposed to prevent samples misclassification in the updating process. The Detection Boundary is established based on SVDD decision boundary to enhance the recognition of abnormal samples in the process of model updating. A dual-screening mechanism update strategy for support vectors is proposed. It involves establishing a preliminary screening mechanism based on the Elimination Boundary. On this basis, an in-depth screening mechanism based on time density weight is introduced by considering spatiotemporal characteristics of samples, enhancing the real-time performance of online anomaly detection for bearings. Building upon the fused dual-boundary SVDD, a TISVDD framework for online anomaly detection is proposed, enabling the detection model to dynamically update in response to data changes over time. To validate the effectiveness of the proposed method, experiments were conducted using the XJTU-SY bearing dataset and real-time datasets collected on an online hardware platform. The results demonstrate the effectiveness and superiority of the method in practical applications.

Performance degradation assessment of rolling bearings based on the comprehensive characteristic index and improved SVDD

Abstract Rolling bearing is one of the most critical parts of mechanical equipment, so the performance degradation assessment of rolling bearing is vital to ensure the normal operation of the whole mechanical equipment. Aiming at the problems that a single degradation characteristic can only contain limited performance degradation information of rolling bearings, a large number of redundant characteristics exist in the high-dimension characteristic set resulting in the inability to effectively mine the characteristic information of rolling bearings, and that traditional degradation assessment models are not suitable for the shortage of fault data during the actual operation of rolling bearings, a performance degradation assessment method of rolling bearings based on the comprehensive characteristic index and improved support vector data description (SVDD) is proposed in this paper. Firstly, to solve the parameter selection problem of variational mode decomposition (VMD), a parameter-adaptive VMD method based on salp swarm algorithm based on mixed strategy (MSSSA) is proposed. Secondly, to extract the performance degradation information of rolling bearings more comprehensively and fully, the comprehensive characteristic index is proposed. Then, a kernel locality preserving projection orthogonal kernel principal component analysis (KLPPOKPCA) method is proposed to reduce the dimensionality of the extracted multi-domain characteristic set of the rolling bearing. Finally, a support vector data description with negative samples (NSSVDD) is proposed and optimized by MSSSA to solve the problem that traditional degradation assessment models are not suitable for the shortage of fault data during the actual operation of rolling bearings and improve the detection performance of abnormal data. The experimental results show that the proposed method can accurately divide the performance degradation process of the rolling bearing. Moreover, the comparison with other methods further highlights the superiority of the proposed method in determining the point in time of early fault of the rolling bearing. 

Novel Transfer Learning Based on Support Vector Data Description for Aeroengine Fault Detection

Novel Transfer Learning Based on Support Vector Data Description for Aeroengine Fault Detection

A self-supervised leak detection method for natural gas gathering pipelines considering unlabeled multi-class non-leak data

Detecting leaks in natural gas gathering pipelines is paramount for the safe and reliable operation of the gas and oil industry. Due to the lack of leak data and the changes in leak features, semi-supervised leak detection methods that use normal data for health model learning have attracted much attention. However, these approaches usually consider one-class normal samples as health data, which may fail to fit the reality of unlabeled multi-class non-leak data under variable operating conditions. In addition, existing semi-supervised methods often suffer from insufficient representation learning as they employ step-by-step training or rely on the low-level reconstruction of autoencoders. To address the above two key challenges, this paper proposes a novel end-to-end self-supervised leak detection method, self-supervised multi-sphere support vector data description. Specifically, it utilizes the presented multi-sphere support vector data description to model unlabeled multi-class non-leak data and the introduced self-supervised learning strategy to boost the representation learning of the end-to-end semi-supervised model. Moreover, the categories of unlabeled multi-class non-leak data are learned in an unsupervised way through alternating feature clustering and pseudo-label-based classification. A robust leak score calculation method is also designed to improve the performance of the proposed method. Finally, the experimental results on the field data collected from pipelines demonstrate the effectiveness of the proposed method.

Deep Multiscale Soft-Threshold Support Vector Data Description for Enhanced Heavy-Duty Gas Turbine Generator Sets’ Anomaly Detection

This paper introduces an innovative approach, Deep Multiscale Soft-Threshold Support Vector Data Description (DMS-SVDD), designed for the detection of anomalies and prediction of faults in heavy-duty gas turbine generator sets (GENSETs). The model combines a support vector data description (SVDD) with a deep autoencoder backbone network framework, integrating a multiscale convolutional neural network (M) and soft-threshold activation network (S) into the Deep-SVDD framework. In comparison with conventional methods, such as One-Class Support Vector Machine (OCSVM) and autoencoder (AE), DMS-SVDD demonstrates improvements in accuracy (by 22.94%), recall (by 32%), F1 score (by 12.02%), and smoothness (by 39.15%). The model excels particularly in feature extraction, denoising, and early fault detection, offering a proactive strategy for maintenance. Furthermore, the DMS-SVDD demonstrated enhanced training efficiency with a reduction in the convergence rounds by 66% and overall training times by 34.13%. The study concludes that DMS-SVDD presents a robust and efficient solution for gas turbine anomaly detection, with practical advantages for decision support in turbine maintenance. Future research could explore additional refinements and applications of the DMS-SVDD model across diverse industrial contexts.

TTSAD: TCN-Transformer-SVDD Model for Anomaly Detection in air traffic ADS-B data

ADS-B (Automatic Dependent Surveillance-Broadcast) is a key technology in the new generation air traffic surveillance system. However, it is vulnerable to various cyber attacks because it broadcasts data in plaintext format and lacks authentication mechanism. Previous research has rarely considered the application scenarios of ATM (Air Traffic Management) in commercial air transport, and there are the problems of low anomaly detection rate and the non-lightweight model. This paper focuses on ADS-B anomaly detection under the background of ATM. We propose the TTSAD (TCN-Transformer-SVDD Model for Anomaly Detection) model, which aims to address the problems of existing ADS-B anomaly detection methods including inadequate considerations of long-term dependencies and distribution characteristic, the non-lightweight model and the poor adaptive threshold. First, ADS-B time series is input into TCN (Temporal Convolutional Network) prediction module which predicts data in an accurate and quick way using causal convolution and dilated convolution. Then, the predicted ADS-B time series is input into Transformer reconstruction module which reconstructs data accurately and quickly based on Self-Attention and Multi-Head Attention mechanism. Finally, the difference values between the reconstructed values and the real values are input into SVDD (Support Vector Data Description) threshold determination module for an optimal threshold. Experimental results show that the TTSAD model can detect ADS-B anomaly data generated from attacks such as altitude slow offset and DOS (Denial of Service). The TTSAD model is superior to other machine learning methods in terms of recall rate, detection rate, accuracy rate, missing detection rate and false alarm rate. Furthermore, compared with other deep learning methods including LSTM, GRU and LSTM-AE, the TTSAD model has a shorter training time and a lightweight characteristic. This approach guarantees the information security of ADS-B, thereby improving the operational security of ATM.

Credit risk prediction based on an interpretable three-way decision method: Evidence from Chinese SMEs

Credit risk prediction can provide essential tools for use in commercial banking credit and credit-related decision-making. This paper proposes a three-way decision method based on prospect theory and evidence theory for predicting credit risk. The first problem in this study is determining the optimal classification boundary, and the second is effectively predicting the sample default status within an uncertain boundary. To address the limitation of the SVDD model, which is that it does not consider the aggregation degree, a new sample-weighted support vector data description (SW-SVDD) model is constructed by ranking samples according to their relative membership degree. The classification boundaries of the default and nondefault samples are determined according to the maximum prediction accuracy of the SW-SVDD model. The samples are divided into definite boundary nondefault, definite boundary default, and uncertain boundary samples. The default status of samples falling into definite boundaries is predicted by the SW-SVDD model. The three-way decision method combining prospect theory and evidence theory predicts the default status of samples falling into uncertain boundaries. This paper also proposes a new interpretability method based on the default probability, nondefault probability, and optimal threshold point obtained by the three-way decision model. The empirical results show that the proposed three-way decision method is a model that balances accuracy and interpretability. It has a higher classification performance than traditional models and can reveal the key features that lead to each customer's default. The proposed three-way decision method can enhance the accuracy and reliability of risk assessments, enabling financial institutions to make more informed lending decisions and more effectively manage credit portfolios.

Vibration anomaly detection of wind turbine based on temporal convolutional network and support vector data description

Due to the complex working conditions and harsh environment, wind turbines often encounter abnormalities, resulting in great operation and maintenance difficulties. As nacelle vibration signals reveal the structure's dynamic characteristics and the interaction between components, vibration anomaly detection has a strong potential. However, vibration anomaly detection is challenging due to the complex characteristics and non-stationarity of high dynamic nacelle vibration signals. To solve this problem, this paper proposed a semi-supervised vibration anomaly detection approach for wind turbines, combining deep learning and one-class classification. Firstly, a healthy behavior model (HBM) for predicting wind turbine nacelle vibration based on the temporal convolutional network (TCN) is developed. To use all available information, a Hilbert spectrum fusion technology (HSFT) was proposed to enhance model performance. Then, based on the support vector data description (SVDD) algorithm, we established a one-class classifier of vibration prediction residual and realized the vibration anomaly detection. The proposed approach can be trained on the healthy dataset to provide accurate detection of different abnormal types. The effectiveness of the proposed anomaly detection approach was verified on simulated and actual monitoring datasets.

The study of hydraulic machinery condition monitoring based on anomaly detection and fault diagnosis

The existing intelligent monitoring methods are hard to apply directly to hydraulic machinery due to fault data collection difficulties and the uncertainty of fault occurrence. To monitor the hydraulic machinery effectively, we design a novel feature extraction method called TFF_VMD and propose a comprehensive framework based on support vector data description (SVDD) and support vector machine (SVM), dividing the monitoring task into anomaly detection and fault identification. A pump test bench is built for data collection and method validation. Meanwhile, one online bearing dataset is used to pre-train SVM. The proposed method achieves satisfying results on three datasets, getting the accuracy of anomaly detection at 0.891, 0.999, and 0.995, respectively, getting mean and standard deviation of fault diagnosis accuracy at 0.954 ± 0.05, 0.96 ± 0.04, and 0.98 ± 0.03. Results show that TFF_VMD is valuable for SVDD and SVM, and the proposed framework can preliminarily achieve early warning and diagnosis of mechanical and hydraulic faults.

The fuzzy support vector data description based on tightness for noisy label detection

AbstractMachine learning (ML) is an approach driven by data, and as research in machine learning progresses, the issue of noisy labels has garnered widespread attention. Noisy labels can significantly reduce the accuracy of supervised classification models, making it important to address this problem. Therefore, it is a very meaningful task to detect as many noisy labels as possible from the big data. In this study, a new method is proposed for detecting noisy labels in datasets. This method leverages a deep pre-trained network to extract a feature set from the image data first which can extract more accurate data features. Then, a membership degree based on tightness into the support vector data description (SVDD) model named TF-SVDD is introduced to detect noisy data in the dataset. In order to simulate different types of label noise more accurately, we first assumed that the labels of the datasets used were all correct, and in addition constructed the noise set using two method: the density peak noise set and the random noise set. Experimental results demonstrate that the TF-SVDD can effectively detect noisy label data, surpassing traditional support vector data description algorithms and other methods in terms of outlier detection accuracy, with the average accuracy mostly exceeding 50$$\%$$ % , and even reaching 80$$\%$$ % . Furthermore, one novel measure called ‘confidence’ is employed to rectify noisy labels in the data. Following the correction of noisy labels, the accuracy of image classification experiences a significant improvement, with the average promotion ratio mostly exceeding 10$$\%$$ % , and reaching 30$$\%$$ % .

Unsupervised deep learning approach for structural anomaly detection using probabilistic features

Civil structures may deteriorate during their service life due to degradation or damage imposed by natural hazards such as earthquakes, wind, and impact. Structural performance anomaly detection is essential to provide an early warning of structural degradation limit states in order to prevent potential catastrophic failure. Data-driven machine learning approaches have been widely used for this, due to their capability in capturing features sensitive to damage-induced anomalies from structural health monitoring (SHM) data, assuming that such data are available. Although machine learning models have been used, many are challenged by the vast operational and environmental variability that can corrupt SHM data and by (typically) strongly correlated information from different sensors in the SHM data. This paper proposes an unsupervised deep learning approach for the detection of structural anomaly based on a deep convolutional variational autoencoder (DCVAE) for feature extraction coupled with support vector data description (SVDD) for anomaly detection. The proposed DCVAE-SVDD method has several appealing strengths. First, the variational latent encoding is used to capture the features of monitoring data through a probability distribution. The integration of the Kullback–Leibler divergence in the loss function provides accurate estimation of the probability distributions. Second, the DCVAE designed with convolutional and deconvolutional operations utilizes the correlation among multisensor data to avoid loss of correlation features and achieve better performance in feature extraction. Third, the SVDD is utilized to create a minimum-volume hypersphere that contains the anomaly-sensitive statistical features of the state. The hypersphere accurately separates anomaly-sensitive statistical features of reference states of structure from the anomalous ones. A computational frame model and a laboratory grandstand model are used to evaluate the performance of the proposed method for detecting structural anomaly. The results demonstrate the superiority of the proposed DCVAE-SVDD in detection accuracy over the other commonly used structural anomaly detection methods (deep autoencoder combined with SVDD autoregressive model with one-class support vector machine, and principal component analysis).

A novel framework based on two-stage multi-view feature optimization and improved support vector data description for aeroengine bearing early fault detection

Early fault detection is crucial to avoid catastrophic flight accidents caused by unplanned downtime of equipment. Aimed at the shortcomings of feature selection and early fault detection, this paper proposes a method combining two-stage multi-view feature optimization and improved support vector data description for aeroengine bearing early fault detection. First, a comprehensive evaluation index is constructed via combining monotonicity, correlation, robustness index and entropy weight method to be used for initial screening sensitive degradation features from multi-view candidate degradation feature. After that, the hierarchical clustering algorithm and local preserving projection algorithm is introduced to realize sensitive degradation features clustering and dimensionality reduction. On this basis, the Euclidean distance sample reduction and the sparrow search algorithm is utilized to complete the training sample selection and model parameter optimization of different clusters and further use the verification samples to filter the optimal features and model. Finally, based on the optimal degradation features and models, a fusion performance degradation index is built to achieve intelligent detection of early fault. Comparisons with some existing fault detection methods, the proposed method improves degradation trend sensibility and demonstrates potential of good early fault detection engineering applications.

Fault detection in the marine engine using a support vector data description method

Fast detection and correct diagnosis of any engine condition changes are essential elements of safety and environmental protection. Many diagnostic algorithms significantly improve the detection of malfunctions. Studies on diagnostic methods are rarely reported and even less implemented in the marine engine industry. To fill this gap, this paper presents the Support Vector Data Description (SVDD) method as applied to the fault detection of the fuel delivery system of a two-stroke marine engine. The selected diagnostic data is the exhaust gas composition, with four components considered: oxygen, carbon oxide, nitric oxide, and carbon dioxide. With these diagnostics, the method distinguishes eight different engine faults from the efficient state. The manuscript presents in detail the methodology for applying the SVDD method in a marine engine. The method of obtaining diagnostic data and its scaling is described. The method of training and validating the algorithm is also presented, along with ready-made algorithms for use. The 100% accuracy of the proposed fault detection method. Based on the obtained results, the proposed fault detection method is promising for a simple application. Moreover, generalised algorithms that may be adapted to different technical solutions are also presented. Highlights SVDD was used for marine engine fault detection from exhaust gas composition Laboratory measurements were carried out on the two-stroke diesel engine The proposed algorithm detected the considered faults with 100% accuracy A generalised algorithm for adapting other complex technical objects was proposed

Radar High-Resolution Range Profile Rejection Based on Deep Multi-Modal Support Vector Data Description

Radar Automatic Target Recognition (RATR) based on high-resolution range profile (HRRP) has received intensive attention in recent years. In practice, RATR usually needs not only to recognize in-library samples but also to reject out-of-library samples. However, most rejection methods lack a specific and accurate description of the underlying distribution of HRRP, which limits the effectiveness of the rejection task. Therefore, this paper proposes a novel rejection method for HRRP, named Deep Multi-modal Support Vector Data Description (DMMSVDD). On the one hand, it forms a more compact rejection boundary with the Gaussian mixture model in consideration of the high-dimensional and multi-modal structure of HRRP. On the other hand, it captures the global temporal information and channel-dependent information with a dual attention module to gain more discriminative structured features, which are optimized jointly with the rejection boundary. In addition, a semi-supervised extension is proposed to refine the boundary with available out-of-library samples. Experimental results based on measured data show that the proposed methods demonstrate significant improvement in the HRRP rejection performance.

Open‐set recognition of LPI radar signals based on a slightly convolutional neural network and support vector data description

AbstractLPI radar signal recognition based on convolutional neural networks usually assumes that the signal to be recognized belongs to a closed set of known signal classes. In an open electromagnetic signal environment, this type of closed‐set recognition method will experience a drastic drop in performance due to the encounter with unknown types of signals. We propose an SCNN‐SVDD model based on a combination of a lightweight convolutional neural network and a support vector data description algorithm to achieve open‐set recognition of LPI radar signals under unknown signal conditions. In this approach, Choi‐William's time‐frequency distribution is used to obtain two‐dimensional time‐frequency images of the signal to be identified, and convolutional neural networks are used to achieve high‐precision classification of known signals and extract the corresponding feature vectors. Then, the feature vectors are used as input to the SVDD algorithm and a hypersphere is constructed to detect whether the signal to be identified belongs to a known class. Experimental results show that the proposed method can detect unknown signals while maintaining high recognition accuracy for known signals.

Selecting Indispensable Edge Patterns With Adaptive Sampling and Double Local Analysis for Data Description

Support vector data description (SVDD) inspires us in data analysis, adversarial training, and machine unlearning. However, collecting support vectors requires pricey computation, while the alternative boundary selection with O(N2) is still a challenge. The authors propose an indispensable edge pattern selection method (IEPS) for data description with direct SVDD model building. IEPS suggests a double local analysis to select the global edge patterns. Edge patterns belong to a subset of the target problem of SVDD and its variants, and neighbor analysis becomes pivotal. While an excessive number of participating data result in redundant computations, an insufficient number may impede data separability or compromise the model's quality. Consequently, a data-adaptive sampling strategy has been devised to ascertain an optimal ratio of retained data for edge pattern selection. Extensive experiments indicate that IEPS keeps indispensable edge patterns for data description while reducing the interference in the norm vector generation to guarantee the effectiveness for clustering analysis.

Adaptive Graph-Based Support Vector Data Description for Weakly-Supervised Anomaly Detection

Adaptive Graph-Based Support Vector Data Description for Weakly-Supervised Anomaly Detection

Machinery Fault Signal Detection with Deep One-Class Classification

Fault detection of machinery systems is a fundamental prerequisite to implementing condition-based maintenance, which is the most eminent manufacturing equipment system management strategy. To build the fault detection model, one-class classification algorithms have been used, which construct the decision boundary only using normal class. For more accurate one-class classification, signal data have been used recently because the signal data directly reflect the condition of the machinery system. To analyze the machinery condition effectively with the signal data, features of signals should be extracted, and then, the one-class classifier is constructed with the features. However, features separately extracted from one-class classification might not be optimized for the fault detection tasks, and thus, it leads to unsatisfactory performance. To address this problem, deep one-class classification methods can be used because the neural network structures can generate the features specialized to fault detection tasks through the end-to-end learning manner. In this study, we conducted a comprehensive experimental study with various fault signal datasets. The experimental results demonstrated that the deep support vector data description model, which is one of the most prominent deep one-class classification methods, outperforms its competitors and traditional methods.

Non-contact sensing for anomaly detection in wind turbine blades: A focus-SVDD with complex-valued auto-encoder approach

The occurrence of manufacturing defects in wind turbine blade (WTB) production can result in significant increases in operation and maintenance costs of WTBs, reduce capacity factors of wind farms, and occasionally lead to severe and disastrous consequences. Therefore, inspection during the manufacturing process is crucial to ensure consistent fabrication of composite materials. Non-contact sensing techniques, such as Frequency Modulated Continuous Wave (FMCW) radar, are becoming increasingly popular as they offer a full view – cross sectional analysis – of these complex structures during assembly and curing. In this paper, we enhance the quality assurance of WTB manufacturing utilising FMCW radar as a non-destructive sensing modality. Additionally, a novel anomaly detection pipeline is developed that offers the following advantages: (1) We use the analytic representation of the Intermediate Frequency signal of the FMCW radar as a feature to disentangle material-specific and round-trip delay information from the received wave. (2) We propose a novel anomaly detection methodology called focus Support Vector Data Description (focus-SVDD). This methodology involves defining the limit boundaries of the dataset after removing healthy data features, thereby focusing on the attributes of anomalies. (3) The proposed method employs a complex-valued autoencoder to remove healthy features and we introduces a new activation function called Exponential Amplitude Decay (EAD). EAD takes advantage of the Rayleigh distribution, which characterises an instantaneous amplitude signal. The effectiveness of the proposed method is demonstrated through its application to collected data, where it shows superior performance compared to other state-of-the-art unsupervised anomaly detection methods. This method is expected to make a significant contribution not only to structural health monitoring but also to the field of deep complex-valued data processing and SVDD application. The code and dataset will be made publicly available. The code and dataset are available here 11https://github.com/FrusqueGaetan/Focus_SVDD_EAD.

Large-margin multiple kernel [formula omitted]-SVDD using Frank–Wolfe algorithm for novelty detection

Using a variable ℓp≥1-norm penalty on the slacks, the recently introduced ℓp-norm Support Vector Data Description (ℓp-SVDD) method has improved the performance in novelty detection over the baseline approach, sometimes remarkably. This work extends this modelling formalism in multiple aspects. First, a large-margin extension of the ℓp-SVDD method is formulated to enhance generalisation capability by maximising the margin between the positive and negative samples. Second, based on the Frank–Wolfe algorithm, an efficient yet effective method with predictable accuracy is presented to optimise the convex objective function in the proposed method. Finally, it is illustrated that the proposed approach can effectively benefit from a multiple kernel learning scheme to achieve state-of-the-art performance.The proposed method is theoretically analysed using Rademacher complexities to link its classification error probability to the margin and experimentally evaluated on several datasets to demonstrate its merits against existing methods.