An environment information-driven online Bi-level path planning algorithm for underwater search and rescue AUV

Ocean Engineering, Год журнала: 2024, Номер 296, С. 116949 - 116949

Опубликована: Фев. 7, 2024

Язык: Английский

---

Deep Learning Network Based on Improved Sparrow Search Algorithm Optimization for Rolling Bearing Fault Diagnosis

Mathematics, Год журнала: 2023, Номер 11(22), С. 4634 - 4634

Опубликована: Ноя. 13, 2023

In recent years, deep learning has been increasingly used in fault diagnosis of rotating machinery. However, the actual acquisition rolling bearing signals often contains ambient noise, making it difficult to determine optimal values parameters. this paper, a sparrow search algorithm (LSSA) based on backward lens imaging and Gaussian Cauchy variation is proposed. The reverse strategy enhances traversal capability allows for better balance exploration development. Then, performance proposed LSSA was tested benchmark function. Finally, find modal component K penalty factor α VMD-GRU, which turn realizes bearings. experimental results show that model can achieve 96.61% accuracy diagnosis, proves effectiveness method.

Язык: Английский

---

A multi-mechanism balanced advanced learning sparrow search algorithm for UAV path planning

Cluster Computing, Год журнала: 2024, Номер 27(5), С. 6623 - 6666

Опубликована: Март 5, 2024

Язык: Английский

---

An enhanced sparrow search swarm optimizer via multi-strategies for high-dimensional optimization problems

Swarm and Evolutionary Computation, Год журнала: 2024, Номер 88, С. 101603 - 101603

Опубликована: Май 18, 2024

Язык: Английский

---

Mining soil heavy metal inversion based on Levy Flight Cauchy Gaussian perturbation sparrow search algorithm support vector regression (LSSA-SVR)

Ecotoxicology and Environmental Safety, Год журнала: 2024, Номер 287, С. 117295 - 117295

Опубликована: Ноя. 1, 2024

Soil heavy metal pollution in mining areas poses severe challenges to the ecological environment. In recent years, machine learning has been widely used inversion by hyperspectral data. However, deterministic algorithms and probabilistic may confront local optimal solutions practical applications. The solution is not value obtained within entire defined interval, as a result will affect reliability of these approaches. This paper proposes Levy Flight Cauchy Gaussian perturbation Sparrow Search algorithm Support Vector Regression (LSSA-SVR) soil content prediction model. It introduces (LF) measurement based on search algorithm. LSSA-SVR model was shown increase breadth searched, avoiding problem. When applied experiments, we found that gave good fit for elements Cu, Zn, As, Pb. correlation coefficients between predicted results actual four were all above 0.94. have small error margin both overall distribution individual differences. study provides an efficient accurate monitoring method inversion. also strong support environmental management remediation.

Язык: Английский

---

Optical fiber sensor used for measuring the rotation angle of the disconnecting switch

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 14, 2025

In order to solve the problem that traditional electronic angle sensor cannot be directly installed on high voltage isolation switch for Angle measurement, a system isolating le measurement is proposed. The rotation converted straight line and of calculated by photoelectric conversion technology. light source fluctuation laser receiver causes nonlinear output result receiver, which compensates intensity received in both hardware software respectively. aspect, two-optical path receiving compensation method proposed compensation. terms software, sparrow search algorithm (SSA) (SSA-BP) improve detection accuracy. experimental results show average absolute error decreased 0.18 0.3 after dual-path SSA-BP

Язык: Английский

---

Data-driven hydraulic pressure prediction for typical excavators using a new deep learning SCSSA-LSTM method

Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 127078 - 127078

Опубликована: Фев. 1, 2025

Язык: Английский

---

An improved guide weight method for multi-constraints structural optimization design

Structures, Год журнала: 2025, Номер 77, С. 109058 - 109058

Опубликована: Май 5, 2025

Язык: Английский

---

Improved Sparrow Search Algorithm Based on Multistrategy Collaborative Optimization Performance and Path Planning Applications

Processes, Год журнала: 2024, Номер 12(12), С. 2775 - 2775

Опубликована: Дек. 5, 2024

To address the problems of limited population diversity and a tendency to converge prematurely local optima in original sparrow search algorithm (SSA), an improved (ISSA) based on multi-strategy collaborative optimization is proposed. ISSA employs three strategies enhance performance: introducing one-dimensional composite chaotic mapping SPM generate initial population, thus enriching diversity; dung beetle dancing behavior strategy strengthen algorithm’s ability jump out optima; integrating adaptive t-variation improvement balance global exploration exploitation capabilities. Through experiments with 23 benchmark test functions comparison algorithms such as PSO, GWO, WOA, SSA, advantages convergence speed accuracy are verified. In application robot path planning, compared exhibits shorter lengths, fewer turnings, higher planning efficiency both single-target point multi-target planning. Especially obstacle rate increases, can more effectively find shortest path. Its traversal order different from that making planned smoother intersections. The results show has significant superiority performance applications.

Язык: Английский

---

A 3D Coverage Method Involving Dynamic Underwater Wireless Sensor Networks for Marine Ranching Monitoring

Electronics, Год журнала: 2024, Номер 13(22), С. 4536 - 4536

Опубликована: Ноя. 19, 2024

In view of the poor adaptability and uneven coverage static underwater wireless sensor networks (UWSNs) to environmental changes need for dynamic monitoring, a three-dimensional method involving UWSNs marine ranching, based on an improved sparrow search algorithm (ISSA), is proposed. Firstly, reverse learning strategy was introduced generate individuals fuse with initial population, individual sparrows high fitness were selected improve range. Secondly, Levy flight optimize location update producer, which effectively expanded local capability algorithm. Finally, Cauchy mutation perturbation mechanism into scrounger optimal solution, enhanced ability obtain global solution. When deploying nodes, autonomous vehicle (AUV) used as mobile node assist deployment. case obstacles, hole in covered by AUV at specific times. The experimental results show that compared other algorithms, ISSA has shorter path achieves higher rate, lower energy consumption.

Язык: Английский

---