NIGWO-iCaps NN: A Method for the Fault Diagnosis of Fiber Optic Gyroscopes Based on Capsule Neural Networks

Micromachines, Год журнала: 2025, Номер 16(1), С. 73 - 73

Опубликована: Янв. 10, 2025

When using a fiber optic gyroscope as the core measurement element in an inertial navigation system, its work stability and reliability directly affect accuracy of system. The modeling fault diagnosis is great significance ensuring high long endurance Traditional diagnostic models often encounter challenges terms accuracy, for example, difficulties feature extraction, computational cost, training time. To address these challenges, this paper proposes new model that performs gyroscopes enhanced capsule neural network (iCaps NN) optimized by improved gray wolf algorithm (NIGWO). wavelet packet transform (WPT) used to construct two-dimensional vector matrix, deep extraction module (DFE) added extract deep-level information maximize features. Then, combined with adaptive (Adam) proposed determine optimal values parameters, which improves optimization performance. dynamic routing mechanism utilized greatly reduce In paper, effectiveness experiments were carried out on simulation dataset real dataset, respectively; method reached 99.41% dataset; loss value converged 0.005 increase number iterations; average 95.42%. results show NIGWO-iCaps NN 13.51% compared traditional methods. It effectively confirms capable efficient accurate FOG has strong generalization ability.

Язык: Английский

Improved Black-Winged Kite Algorithm with Multi-Strategy Optimization for Identifying Dendrobium huoshanense

Biomimetics, Год журнала: 2025, Номер 10(4), С. 226 - 226

Опубликована: Апрель 4, 2025

An improved black-winged kite algorithm with multiple strategies (BKAIM) is proposed in this paper to address two critical limitations the original optimization (BKA): restricted search capability caused by low-quality initial population and reduced diversity resulting from blind following behavior during migration phase. Our enhancement implements three strategic modifications across different stages. During initialization, an opposition-based learning strategy was incorporated generate a higher-quality population. For phase, differential mutation integrated facilitate information exchange among members, mitigate tendency of leader-following behavior, enhance convergence precision, achieve optimal balance between exploration exploitation capabilities. Regarding boundary handling, conventional absorption method replaced random approach increase subsequently improve algorithm’s Comprehensive testing conducted on four benchmark function sets (CEC2017, CEC2019, CEC2021, CEC2022) validate effectiveness algorithm. Detailed analysis Wilcoxon rank-sum test comparisons other algorithms demonstrated BKAIM’s superior performance robustness. Furthermore, support vector machine (SVM) model optimized BKAIM for grade identification Dendrobium huoshanense based near-infrared spectral data, thereby confirming its practical applications.

Язык: Английский

RBFNN-PSO Intelligent Synchronisation Method for Sprott B Chaotic Systems with External Noise and Its Application in an Image Encryption System

Entropy, Год журнала: 2024, Номер 26(10), С. 855 - 855

Опубликована: Окт. 10, 2024

In the past two decades, research in field of chaotic synchronization has attracted extensive attention from scholars, and at same time, more methods, such as master-slave synchronization, projection sliding film fractional-order so on, have been proposed applied to secure communication. this paper, based on radial basis function neural network theory particle swarm optimisation algorithm, RBFNN-PSO synchronisation method is for Sprott B system with external noise. The RBFNN controller constructed, its parameters are used parameters, optimal values obtained by PSO training method, which overcomes influence noise achieves system. Then, it shown numerical simulation analysis that scheme a good performance against Because multiple attractors richer dynamics, chaos image encryption particular, Zigzag disambiguation top corner rotation RGB channel selection proposed, sequences diffused disambiguated data streams, respectively. Therefore, decryption transmission implemented results given, random distribution characteristics encrypted images analysed using histogram Shannon entropy final achieve expected results.

Язык: Английский