Anomalies Classification in Fan Systems Using Dual-Branch Neural Networks with Continuous Wavelet Transform Layers: An Experimental Study DOI Creative Commons

Cezary Pałczyński,

Paweł Olejnik

Information, Год журнала: 2025, Номер 16(2), С. 71 - 71

Опубликована: Янв. 21, 2025

In this study, anomalies in a fan system were classified using real measurement setup to simulate mechanical such as blade detachment or debris accumulation. Data collected under normal operating conditions and with an added unbalancing mass. Additionally, sensor introduced by manipulating accelerometer readings examining three types: spike, stuck, dropout. To classify the anomalies, four neural network models—variations Long Short-Term Memory (LSTM) Convolutional Neural Network (CNN) tested. These models incorporated Continuous Wavelet Transform (CWT) layer. A novel approach for implementing CWT layer both LSTM CNN architectures was proposed, along dual-branch input structure featuring two layers different mother wavelets. The configuration wavelets yielded better accuracy simpler network. Accuracy comparisons conducted 10 best-performing based on validation set predictions, revealing improved classification performance. study concluded summary of prediction test sets data, calculation average accuracy, demonstrating effectiveness proposed classifying systems.

Язык: Английский

A Literature Review on Security in the Internet of Things: Identifying and Analysing Critical Categories DOI Creative Commons

Hannelore Sebestyen,

Daniela Elena Popescu, Doina Zmaranda

и другие.

Computers, Год журнала: 2025, Номер 14(2), С. 61 - 61

Опубликована: Фев. 11, 2025

With the proliferation of IoT-based applications, security requirements are becoming increasingly stringent. Given diversity such systems, selecting most appropriate solutions and technologies to address challenges is a complex activity. This paper provides an exhaustive evaluation existing related IoT domain, analysing studies published between 2021 2025. review explores evolving landscape security, identifying key focus areas, challenges, proposed as presented in recent research. Through this analysis, categorizes efforts into six main areas: emerging (35.2% studies), securing identity management (19.3%), attack detection (17.9%), data protection (8.3%), communication networking (13.8%), risk (5.5%). These percentages highlight research community’s indicate areas requiring further investigation. From leveraging machine learning blockchain for anomaly real-time threat response optimising lightweight algorithms resource-limited devices, researchers propose innovative adaptive threats. The underscores integration advanced enhance system while also highlighting ongoing challenges. concludes with synthesis threats each identified category, along their solutions, aiming support decision-making during design approach applications guide future toward comprehensive efficient frameworks.

Язык: Английский

Процитировано

1
Anomalies Classification in Fan Systems Using Dual-Branch Neural Networks with Continuous Wavelet Transform Layers: An Experimental Study DOI Creative Commons

Cezary Pałczyński,

Paweł Olejnik

Information, Год журнала: 2025, Номер 16(2), С. 71 - 71

Опубликована: Янв. 21, 2025

In this study, anomalies in a fan system were classified using real measurement setup to simulate mechanical such as blade detachment or debris accumulation. Data collected under normal operating conditions and with an added unbalancing mass. Additionally, sensor introduced by manipulating accelerometer readings examining three types: spike, stuck, dropout. To classify the anomalies, four neural network models—variations Long Short-Term Memory (LSTM) Convolutional Neural Network (CNN) tested. These models incorporated Continuous Wavelet Transform (CWT) layer. A novel approach for implementing CWT layer both LSTM CNN architectures was proposed, along dual-branch input structure featuring two layers different mother wavelets. The configuration wavelets yielded better accuracy simpler network. Accuracy comparisons conducted 10 best-performing based on validation set predictions, revealing improved classification performance. study concluded summary of prediction test sets data, calculation average accuracy, demonstrating effectiveness proposed classifying systems.

Язык: Английский

Процитировано

0