Heuristic Optimization Algorithm of Black-Winged Kite Fused with Osprey and Its Engineering Application

Biomimetics, Journal Year: 2024, Volume and Issue: 9(10), P. 595 - 595

Published: Oct. 1, 2024

Swarm intelligence optimization methods have steadily gained popularity as a solution to multi-objective issues in recent years. Their study has garnered lot of attention since problems hard high-dimensional goal space. The black-winged kite algorithm still suffers from the imbalance between global search and local development capabilities, it is prone even though combines Cauchy mutation enhance algorithm's ability. heuristic fused with osprey (OCBKA), which initializes population by logistic chaotic mapping fuses improve performance algorithm, proposed means enhancing ability (BKA). By using numerical comparisons CEC2005 CEC2021 benchmark functions, along other swarm solutions three engineering problems, upgraded strategy's efficacy confirmed. Based on experiment findings, revised OCBKA very competitive because can handle complicated high convergence accuracy quick time when compared comparable algorithms.

Language: Английский

---

A Review of Machine Learning-Based Thermal Error Modeling Methods for CNC Machine Tools

Machines, Journal Year: 2025, Volume and Issue: 13(2), P. 153 - 153

Published: Feb. 17, 2025

Heat source-induced thermal error is a primary element influencing the precision of CNC machine tools. A practical and economical approach to mitigating errors through compensation. To provide comprehensive understanding modeling its advancements, this paper systematically reviews learning-based methods for Thermal most critical step in compensation, as it directly influences effectiveness compensation due accuracy robustness. With rapid development big data artificial intelligence, learning has emerged powerful tool modeling, leading significant research progress recent years. In paper, an overview based on deep that have been researched applied years presented. Specifically, two reducing errors, namely, suppression are introduced analyzed. Second, categorized into traditional learning-driven approaches. The application these reviewed summarized detail. By synthesizing studies, identifies key challenges trends modeling. Finally, discussed summarized, future directions proposed further enhance

Language: Английский

---

A novel hybrid Bayesian-optimized CNN–SVM deep learning model for real-time surface roughness classification and prediction based on in-process machined surface image analysis

International Journal on Interactive Design and Manufacturing (IJIDeM), Journal Year: 2025, Volume and Issue: unknown

Published: March 1, 2025

Language: Английский

---

Multi-strategy dung beetle optimizer for global optimization and feature selection

International Journal of Machine Learning and Cybernetics, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 26, 2024

Language: Английский

---

Hybrid Multi-Objective Chameleon Optimization Algorithm Based on Multi-Strategy Fusion and Its Applications

Biomimetics, Journal Year: 2024, Volume and Issue: 9(10), P. 583 - 583

Published: Sept. 25, 2024

Aiming at the problems of chameleon swarm algorithm (CSA), such as slow convergence speed, poor robustness, and ease falling into local optimum, a multi-strategy improved optimization (ICSA) is herein proposed. Firstly, logistic mapping was introduced to initialize population improve diversity initial population. Secondly, in prey-search stage, sub-population spiral search strategy global ability accuracy algorithm. Then, considering blindness chameleon's eye turning find prey, Lévy flight with cosine adaptive weight combined greed enhance guidance random exploration eyes' rotation stage. Finally, nonlinear varying update position prey-capture refraction reverse-learning used activity later stage so jump out optimum. Eighteen functions CEC2005 benchmark test set were selected an experimental set, performance ICSA tested compared five other intelligent algorithms. The analysis results 30 independent runs showed that has stronger ability. applied UAV path-planning problem. simulation algorithms, paths generated by different terrain scenarios are shorter more stable.

Language: Английский

---

SABO-ILSTSVR: a genomic prediction method based on improved least squares twin support vector regression

Frontiers in Genetics, Journal Year: 2024, Volume and Issue: 15

Published: June 14, 2024

In modern breeding practices, genomic prediction (GP) uses high-density single nucleotide polymorphisms (SNPs) markers to predict estimated values (GEBVs) for crucial phenotypes, thereby speeding up selection process and shortening generation intervals. However, due the characteristic of genotype data typically having far fewer sample numbers than SNPs markers, overfitting commonly arise during model training. To address this, present study builds upon Least Squares Twin Support Vector Regression (LSTSVR) by incorporating a Lasso regularization term named ILSTSVR. Because complexity parameter tuning different datasets, subtraction average based optimizer (SABO) is further introduced optimize ILSTSVR, then obtain GP SABO-ILSTSVR. Experiments conducted on four crop datasets demonstrate that SABO-ILSTSVR outperforms or equivalent in efficiency widely-used methods. Source codes are available at: https://github.com/MLBreeding/SABO-ILSTSVR .

Language: Английский

---

3-axis computer numerical control machine positioning error dataset for thermal error compensation

Data in Brief, Journal Year: 2024, Volume and Issue: 57, P. 110942 - 110942

Published: Sept. 14, 2024

Language: Английский

---

In-depth research on fault diagnosis of turbine rotor utilizing NGSABO-Optimized VMD and CNN-BiLSTM

Engineering Research Express, Journal Year: 2024, Volume and Issue: 6(4), P. 045205 - 045205

Published: Sept. 24, 2024

Abstract To solve the problem of difficulty in extracting and identifying fault types during turbine rotor operation, a diagnosis method based on improved subtraction mean optimizer (NGSABO) algorithm to optimize variational mode decomposition (VMD) CNN-BiLSTM neural network is proposed. Firstly, three improvements are made average algorithm. Secondly, optimal VMD parameter combination NGSABO adaptive selection number K penalty factor α used decompose signal, minimum sample entropy as fitness function for feature extraction. Combining convolutional bidirectional long short-term memory identify classify features. Compared with other methods, this has outstanding performance single coupled faults. The accuracy reaches 98.5714%, which good practical application value.

Language: Английский

---

Research on Prediction Model of Gas Concentration in Power Transformer Oil

Published: Sept. 20, 2024

Language: Английский

---

Thermal error prediction model for long-term operating of machine tool using transfer learning techniques

The International Journal of Advanced Manufacturing Technology, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 23, 2024

Language: Английский

---