检索结果-内蒙古大学图书馆

Detecting structural anomalies of quadcopter UAVs based on lstm autoencoder

PERVASIVE AND MOBILE COMPUTING 2023年 88卷

作者： Jeon, Seunghyeok Kang, Jaeyun Kim, Jiwon Cha, Hojung Yonsei Univ Dept Comp Sci Seoul South Korea

Detecting a structural anomaly, such as a damaged propeller or motor, is crucial for mission-critical operation of unmanned aerial vehicles (UAVs). The existing solutions often fail to detect structural anomalies because the pre-defined parameters required for the solution are limited in reflecting the flight pattern or the external environment, such as wind conditions. In this paper, we propose a method for detecting structural anomalies in quadcopter UAVs, using only regular data and specifically considering flight patterns and runtime flight conditions. To this end, we employ a long shortterm memory (lstm) autoencoder model to learn complex features of regular flight data. While flying the UAV, the trained model estimates the degree of outlierness of the incoming data and assesses abnormal behavior of UAV by adaptively considering its movement. This way, the proposed method accurately detects structural anomalies in UAVs regardless of the runtime environment or flight mission. Our experiment results with an off-the-shelf UAV show that the proposed approach detects diverse structural anomalies by an average of 98.6% specificity and 90.3% sensitivity. (c) 2022 Elsevier B.V. All rights reserved.

关键词： lstm autoencoder Structural anomaly detection UAV

来源：评论

学校读者我要写书评

暂无评论

lstm-autoencoder Based Anomaly Detection Using Vibration Data of Wind Turbines

引用

SENSORS 2024年第9期24卷 2833页

作者： Lee, Younjeong Park, Chanho Kim, Namji Ahn, Jisu Jeong, Jongpil Sungkyunkwan Univ Dept Smart Factory Convergence 2066 Seobu ro Suwon 16419 South Korea Gfyhealth AI Res Ctr 20 Pangyo Ro Seongnam Si 13488 South Korea

The problem of energy depletion has brought wind energy under consideration to replace oil- or chemical-based energy. However, the breakdown of wind turbines is a major concern. Accordingly, unsupervised learning was performed using the vibration signal of a wind power generator to achieve an outlier detection performance of 97%. We analyzed the vibration data through wavelet packet conversion and identified a specific frequency band that showed a large difference between the normal and abnormal data. To emphasize these specific frequency bands, high-pass filters were applied to maximize the difference. Subsequently, the dimensions of the data were reduced through principal component analysis, giving unique characteristics to the data preprocessing process. Normal data collected from a wind farm located in northern Sweden was first preprocessed and trained using a long short-term memory (lstm) autoencoder to perform outlier detection. The lstm autoencoder is a model specialized for time-series data that learns the patterns of normal data and detects other data as outliers. Therefore, we propose a method for outlier detection through data preprocessing and unsupervised learning, utilizing the vibration signals from wind generators. This will facilitate the quick and accurate detection of wind power generator failures and provide alternatives to the problem of energy depletion.

关键词： wavelet packet transform high pass filter principal component analysis lstm autoencoder unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

A deep lstm autoencoder-based framework for predictive maintenance of a proton radiotherapy delivery system

引用

ARTIFICIAL INTELLIGENCE IN MEDICINE 2022年第0期132卷 102387-102387页

作者： Dou, Tai Clasie, Benjamin Depauw, Nicolas Shen, Tim Brett, Robert Lu, Hsiao-Ming Flanz, Jacob B. Jee, Kyung-Wook Harvard Med Sch Massachusetts Gen Hosp Dept Radiat Oncol Boston MA 02115 USA Texas Ctr Proton Therapy Irving TX USA Hefei Ion Med Ctr Hefei Peoples R China

Introduction: Unscheduled machine downtime can cause treatment interruptions and adversely impact patient treatment outcomes. Conventional Quality Assurance (QA) programs of a proton Pencil Beam Scanning (PBS) system ensure its operational performance by keeping the beam parameters within clinical tolerances but often do not reveal the underlying issues of the device prior to a machine malfunction event. In this study, we propose a Predictive Maintenance (PdM) approach that leverages an advanced analytical tool built on a deep neural network to detect treatment delivery machine issues ***: Beam delivery log file data from daily QA performed at the Burr Proton Center of Massachusetts General Hospital were collected. A novel PdM framework consisting of long short-term memory-based autoencoder (lstm-AE) modeling of the proton PBS delivery system and a Mahalanobis distance-based error metric evalu-ation was constructed to detect rare anomalous machine events. These included QA beam pauses, clinical operational issues, and treatment interruptions. The model was trained in an unsupervised fashion on the QA data of normal sessions so that the model learned characteristics of normal machine operation. The anomaly is quantified as the multivariate deviation between the model predicted data and the measured data of the day using Mahalanobis distance (M-Score). Two-layer and three-layer Long short-term memory-based stacked autoencoder (lstm-SAE) models were optimized for exploring model performance improvement. Model vali-dation was performed with two clinical datasets and was analyzed using the area under the precision-recall curve (AUPRC) and the area under the receiver operating characteristic (AUROC).Results: lstm-SAE models showed strong performance in predicting QA beam pauses for both clinical validation datasets. Despite severe skew in the dataset, the model achieved AUPRC of 0.60 and 0.82 and AUROC of 0.75 and 0.92 in the respective 2018 and 2020 datasets. M

关键词： Deep neural network lstm autoencoder Predictive maintenance Anomaly detection Class imbalance Proton radiotherapy

来源：评论

学校读者我要写书评

暂无评论

Air Pressure System Failures Detection Using lstm-autoencoder 4

Air Pressure System Failures Detection Using LSTM-Autoencode...

引用

4th IEEE International Workshop on Metrology for Automotive (MetroAutomotive)

作者： Mumcuoglu, Mehmet Emin Farea, Shawqi Mohammed Unel, Mustafa Mise, Serdar Unsal, Simge Cevik, Enes Yilmaz, Metin Koprubasi, Kerem Sabanci Univ Fac Engn & Nat Sci Istanbul Turkiye Ford OTOSAN Prod Dev Istanbul Turkiye

ISBN: (纸本)9798350384994;9798350384987

The reliability of Heavy-Duty Vehicles (HDVs) is critical for continuous operations in sectors like transportation and logistics. However, the complexity of these vehicles' subsystems, including the Air Pressure System (APS), poses significant challenges where failures lead to costly downtimes and safety risks. This paper introduces a novel semi-supervised anomaly detection approach based on a Long Short-Term Memory autoencoder (lstm-AE) model to identify APS failures in HDVs. Leveraging 30 days of operational time-series data from 140 vehicles, of which 30 experienced APS failures, our study presents a semi-supervised formulation of the problem bypassing the limitations of supervised classification and addressing the scarcity of labeled data in the real-world scenarios. After applying several essential preprocessing steps, the proposed model was rigorously trained and validated to ensure robustness. It achieved an F1 score of 0.75 with a corresponding accuracy of 91.4%. The proposed framework in this research promotes enhanced vehicle uptime and improved safety standards, providing practical implications for both HDV manufacturers and operators.

关键词： Air pressure system failure detection heavy-duty vehicles lstm autoencoder predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Estimation of Frequency-Dependent Impedances in Power Grids by Deep lstm autoencoder and Random Forest

引用

ENERGIES 2021年第13期14卷 3829页

作者： Bagheri, Azam Bongiorno, Massimo Gu, Irene Y. H. Svensson, Jan R. Chalmers Univ Technol Dept Elect Engn S-41296 Gothenburg Sweden Hitachi ABB Power Grids Power Grids Res S-72178 Vasteras Sweden

This paper proposes a deep-learning-based method for frequency-dependent grid impedance estimation. Through measurement of voltages and currents at a specific system bus, the estimate of the grid impedance was obtained by first extracting the sequences of the time-dependent features for the measured data using a long short-term memory autoencoder (lstm-AE) followed by a random forest (RF) regression method to find the nonlinear map function between extracted features and the corresponding grid impedance for a wide range of frequencies. The method was trained via simulation by using time-series measurements (i.e., voltage and current) for different system parameters and verified through several case studies. The obtained results show that: (1) extracting the time-dependent features of the voltage/current data improves the performance of the RF regression method;(2) the RF regression method is robust and allows grid impedance estimation within 1.5 grid cycles;(3) the proposed method can effectively estimate the grid impedance both in steady state and in case of large transients like electrical faults.

关键词： frequency-dependent grid impedance lstm autoencoder PRBS random forest regression time-series analysis unsupervised deep learning

来源：评论

学校读者我要写书评

暂无评论

Sensor and Component Fault Detection and Diagnosis for Hydraulic Machinery Integrating lstm autoencoder Detector and Diagnostic Classifiers

引用

SENSORS 2021年第2期21卷 433-433页

作者： Mallak, Ahlam Fathi, Madjid Univ Siegen Dept Elect Engn & Comp Sci Knowledge Based Syst & Knowledge Management D-57076 Siegen Germany

Anomaly occurrences in hydraulic machinery might lead to massive system shut down, jeopardizing the safety of the machinery and its surrounding human operator(s) and environment, and the severe economic implications following the faults and their associated damage. Hydraulics are mostly placed in ruthless environments, where they are consistently vulnerable to many faults. Hence, not only are the machines and their components prone to anomalies, but also the sensors attached to them, which monitor and report their health and behavioral changes. In this work, a comprehensive applicational analysis of anomalies in hydraulic systems extracted from a hydraulic test rig was thoroughly achieved. First, we provided a combination of a new architecture of lstm autoencoders and supervised machine and deep learning methodologies, to perform two separate stages of fault detection and diagnosis. The two phases were condensed by-the detection phase using the lstm autoencoder. Followed by the fault diagnosis phase represented by the classification schema. The previously mentioned framework was applied to both component and sensor faults in hydraulic systems, deployed in the form of two in-depth applicational experiments. Moreover, a thorough literature review of related work from the past decade, for autoencoders related fault detection and diagnosis in hydraulic systems, was successfully conducted in this study.

关键词： deep learning lstm autoencoder supervised learning hydraulic test rig sensor faults component faults

来源：评论

学校读者我要写书评

暂无评论

Sensor Fault Detection and Classification Using Multi-Step-Ahead Prediction with an Long Short-Term Memoery (lstm) autoencoder

引用

APPLIED SCIENCES-BASEL 2024年第17期14卷 7717页

作者： Hasan, Md. Nazmul Jan, Sana Ullah Koo, Insoo Univ Ulsan Dept Elect Elect & Comp Engn 93 Daehak Ro Ulsan 44610 South Korea Edinburgh Napier Univ Sch Comp Engn & Built Environm Edinburgh EH10 5DT Scotland

The Internet of Things (IoT) is witnessing a surge in sensor-equipped devices. The data generated by these IoT devices serve as a critical foundation for informed decision-making, real-time insights, and innovative solutions across various applications in everyday life. However, data reliability is often compromised due to the vulnerability of sensors to faults arising from harsh operational conditions that can adversely affect the subsequent operations that depend on the collected data. Hence, the identification of anomalies within sensor-derived data holds significant importance in the IoT context. This article proposes a sensor fault detection method using a Long Short-Term Memory autoencoder (lstm-AE). The AE, trained on normal sensor data, predicts a 20-step window, generating three statistical features via SHapley Additive exPlanations from the estimated steps. These features aid in determining potential faults in the predicted steps using a machine learning classifier. A secondary classifier identifies the type of fault in the sensor signal. Experimentation on two sensor datasets showcases the method's functionality, achieving fault detection accuracies of approximately 93% and 97%. It is possible to attain a perfect fault classification performance by slightly modifying the feature calculation approach. In a univariate prediction scenario, our proposed approach demonstrates good fault detection and classification performance.

关键词： sensor faults lstm autoencoder SHAP multi-step prediction

来源：评论

学校读者我要写书评

暂无评论

VidAnomaly: lstm-autoencoder-based Adversarial Learning for One-class Video Classification with Multiple Dynamic Images

VidAnomaly: LSTM-autoencoder-based Adversarial Learning for ...

引用

IEEE International Conference on Big Data (Big Data)

作者： Li, Shusheng He, Wenho McMaster Univ Dept Comp & Software Hamilton ON Canada

ISBN: (纸本)9781728108582

One-class video classification (anomalous video detection) serves an important role when abnormal videos are absent during training, poorly sampled or not well defined. However, one-class video classification is challenging. Due to the unavailability of abnormal samples, it is a cumbersome task to train an end-to-end deep supervised learning model. Meanwhile, video data representation is challenging because of the unstructured scheme of video contents. To represent video data with temporal and spatial information, we propose multiple dynamic images in our task because dynamic image encodes the temporal evolution of video frames and represents video contents at the level of the image pixels. Multiple dynamic images are viewed as the input sequence with temporal and spatial information and achieve dimension reduction of original video data. In this paper, we propose a lstm-autoencoder-based adversarial learning model for one-class video classification ("VidAnomaly") without abnormal samples in the training stage. Our architecture is composed of three sub-networks. lstm-autoencoder network (R) learns the temporal dependence of the input sequence and reconstructs the input sequence for the discriminator network (D) to achieve adversarial learning. The novelty of the proposed model is that we add an additional lstm-encoder network (A) to obtain the latent representation of the reconstructed sequence. Minimizing the distance between the two latent representations from R and A benefits the model to further capture the training data distribution because it forces the lstm-autoencoder network to yield an essential representation of training samples in latent space. In the inference stage, for a given abnormal sample as the input, the model poorly reconstructs the input abnormal sample and the reconstruction error would be high because the proposed model is trained merely on normal samples and its parameters are only suitable for reconstructing normal samples. Based on this,

关键词： Anomalous video detection lstm autoencoder Adversarial learning Dynamic image

来源：评论

学校读者我要写书评

暂无评论

Detecting Intra Ventricular Haemorrhage in Preterm Neonates Using lstm autoencoders 10th

Detecting Intra Ventricular Haemorrhage in Preterm Neonates ...

引用

10th International Work-Conference on Bioinformatics and Biomedical Engineering (IWBBIO)

作者： Muniru, Idris Oladele Grobler, Jacomine Van Wyk, Lizelle Stellenbosch Univ Stellenbosch South Africa

ISBN: (纸本)9783031349522;9783031349539

The neonatal period is a critical stage where physiological adaptations for extra-uterine life occur, and newborns are vulnerable to various diseases and disorders. Among these conditions, preterm neonates (PN) born before 37 weeks' gestation are at higher risk of developing intraventricular hemorrhage (IVH), a common complication that can result in severe neurological complications such as cerebral palsy, developmental delays, and cognitive impairments. Early detection and intervention are essential to prevent long-term consequences. Non-invasive cardiac output monitors (NICOM) have been widely accepted in the neonatal intensive care unit (NICU) for monitoring hemodynamic parameters and have provided vast amounts of data. However, further research is required to explore their predictive tendencies in relation to IVH. The present study aimed to evaluate the potential of deep learning models to enhance early detection and prevention of IVH in preterm neonates using NICOM parameters. From this study, it was shown that by the lstm autoencoders are able to predict IVH with moderate precision and accuracy but poor specificity. Nonetheless, this study represents a significant step towards developing a non-invasive, accurate, and timely method for monitoring and preventing IVH in preterm neonates, especially in low-resource settings.

关键词： lstm autoencoder Non-invasive cardiac output monitor Medical anomaly detection

来源：评论

学校读者我要写书评

暂无评论

lstm autoencoders Applied to Semi-Supervised Crop Classification 29

LSTM AutoEncoders Applied to Semi-Supervised Crop Classifica...

引用

29th IEEE Conference on Signal Processing and Communications Applications (SIU)

作者： Teloglu, Hatice Kubra Aptoula, Erchan Gebze Tekn Univ Bilgisayar Muhendisligi Kocaeli Turkey Gebze Tekn Univ Bilisim Teknolojileri Enstitusu Kocaeli Turkey

ISBN: (纸本)9781665436496

Since creating labelled data in the field of remote sensing requires time and manpower, it has become important to use unlabelled data. In this paper we study a semi supervised long short term memory autocoder approach for crop classification with multi-temporal remote sensing data. In this study, a long short-term memory autoencoder network was trained with unlabelled data and the learned weights were used for the initialization of a model trained for classification with labelled data. The challenging Breizhcrops time series dataset, and multitemporal images of the Sakarya region were used for validation. It has been observed that the network trained with unlabelled data outperformed the network trained with only labelled data. The results shed light on the potential for unlabelled data use in the crop classification field.

关键词： Remote sensing crop classification multispectral time series sentinel-2 lstm autoencoder

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：