Simulating and predicting soil water dynamics using three models for the Taihu Lake region of China DOI Creative Commons
Can Chen, Qing Lv, Qian Tang

и другие.

Water Science & Technology Water Supply, Год журнала: 2022, Номер 22(4), С. 4030 - 4042

Опубликована: Янв. 29, 2022

Abstract Drought stress under a changing climate can significantly affect agricultural production. Simulation of soil water dynamics in field conditions becomes necessary to understand changes develop irrigation guidelines. In this study, three models including Auto-Regressive Integrated Moving Average (ARIMA), Back-Propagation Artificial Neural Network (BP-ANN), and Least Squares Support Vector Machine (LS-SVM) were used simulate the content 0–14 cm 14–33 layers across Taihu Lake region China. Rainfall, evaporation, temperature, humidity wind speed that considered BP-ANN LS-SVM, but not ARIMA. The results showed variability layer was greater than cm. Correlation coefficients (r) between simulations observations highest (0.9827) using LS-SVM layer, while they lowest (0.7019) ARIMA layer; no significant difference r values observed two with model. Compared other models, model seems be more accurate for forecasting moisture. suggested agro-climatic data predict severity drought provide guidance increase crop production

Язык: Английский

Bearing fault diagnosis using transfer learning and optimized deep belief network DOI
Huimin Zhao, Xiaoxu Yang,

Baojie Chen

и другие.

Measurement Science and Technology, Год журнала: 2022, Номер 33(6), С. 065009 - 065009

Опубликована: Фев. 11, 2022

Abstract Bearing is an important component in mechanical equipment. Its main function to support the rotating body and reduce friction coefficient axial load. In actual operating environment, bearings are affected by complex working conditions other factors. Therefore, it very difficult effectively obtain data that meets of independent identical distribution training test data, which result unsatisfactory fault diagnosis results. As a transfer learning method, joint adaptive (JDA) can solve problem inconsistent data. this paper, new bearing method based on JDA deep belief network (DBN) with improved sparrow search algorithm (CWTSSA), namely JACADN proposed. JACADN, employed carry out feature between source domain samples target samples, is, mapped into same space kernel function. Then maximum mean difference used as metric two domains. Aiming at parameter selection DBN, (CWTSSA) global optimization ability optimize parameters DBN order construct optimized model. The obtained divided set set, input model for improving accuracy. effectiveness proposed verified vibration QPZZ-II machinery. experimental results show improve accuracy rolling under variable conditions.

Язык: Английский

Процитировано

104
Feature Extraction Using Parameterized Multisynchrosqueezing Transform DOI
Xinyan Li, Huimin Zhao, Ling Yu

и другие.

IEEE Sensors Journal, Год журнала: 2022, Номер 22(14), С. 14263 - 14272

Опубликована: Июнь 7, 2022

Parametrized time-frequency analysis (PTFA) can effectively improve energy aggregation of non-stationary signal and immunity cross term interference, but it exists the diffusion near real instantaneous frequency. The improved multi-synchrosqueezing transform (IMSST) aggregation, still has defects in processing strong FM AM signals under noise interference. Therefore, order to make use their advantages overcome disadvantages, a novel parametrized method based on weighted least square, IMSST PTFA, namely PMSST is proposed this paper. In PMSST, designed obtain representation with high aggregation. Then ridge extraction algorithm employed extract frequency ridges each mono-component signal. square used estimate parameters parameterized kernel. Finally, spectrum superimposed enhanced experiment results show that process varying by simulated actual fault signals.

Язык: Английский

Процитировано

96
MOTEO: a novel multi-objective thermal exchange optimization algorithm for engineering problems DOI
Nima Khodadadi, Siamak Talatahari, Armin Dadras Eslamlou

и другие.

Soft Computing, Год журнала: 2022, Номер 26(14), С. 6659 - 6684

Опубликована: Апрель 15, 2022

Язык: Английский

Процитировано

40
A Novel Adaptive Sparrow Search Algorithm Based on Chaotic Mapping and T-Distribution Mutation DOI Creative Commons
Xiaoxu Yang, Jie Liu, Yi Liu

и другие.

Applied Sciences, Год журнала: 2021, Номер 11(23), С. 11192 - 11192

Опубликована: Ноя. 25, 2021

Aiming at the problems of basic sparrow search algorithm (SSA) in terms slow convergence speed and ease falling into local optimum, chaotic mapping strategy, adaptive weighting strategy t-distribution mutation are introduced to develop a novel algorithm, namely CWTSSA this paper. In proposed CWTSSA, is employed initialize population order enhance diversity. The applied balance capabilities mining global exploration, improve speed. An operator designed, which uses iteration number t as degree freedom parameter characteristic exploration abilities, so avoid optimum. prove effectiveness 15 standard test functions other improved SSAs, differential evolution (DE), particle swarm optimization (PSO), gray wolf (GWO) selected here. compared experiment results indicate that can obtain higher accuracy, faster speed, better diversity abilities. It provides new for solving complex problems.

Язык: Английский

Процитировано

40
Intelligent Optimization Algorithm‐Based Path Planning for a Mobile Robot DOI Creative Commons
Qisong Song, Shaobo Li, Jing Yang

и другие.

Computational Intelligence and Neuroscience, Год журнала: 2021, Номер 2021(1)

Опубликована: Янв. 1, 2021

The purpose of mobile robot path planning is to produce the optimal safe path. However, robots have poor real‐time obstacle avoidance in local and longer paths global planning. In order improve accuracy prediction planning, shorten length reduce time, then obtain a better path, we propose decision model based on machine learning (ML) algorithms, an improved smooth rapidly exploring random tree (S‐RRT) algorithm, hybrid genetic algorithm‐ant colony optimization (HGA‐ACO). Firstly, algorithms are used train datasets, established, cross validation performed. Secondly, greedy algorithm idea B‐spline curve introduced into RRT redundant nodes removed, reverse iteration performed generate Then, fitness function operation method optimized, pheromone update strategy deadlock elimination ant genetic‐ant fusion fuse two algorithms. Finally, optimized for simulation experiment. Comparative experiments show that forest has highest S‐RRT can effectively total generated by HGA‐ACO number reasonably, search time effectively, solution

Язык: Английский

Процитировано

38
An adaptive dynamic programming-based algorithm for infinite-horizon linear quadratic stochastic optimal control problems DOI
Heng Zhang

Journal of Applied Mathematics and Computing, Год журнала: 2023, Номер 69(3), С. 2741 - 2760

Опубликована: Апрель 5, 2023

Язык: Английский

Процитировано

12
Optimizing fault diagnosis for electric vehicle battery systems: Improved Giza pyramids construction and advanced gradient boosting decision trees DOI

R. Subramaniyan

Journal of Energy Storage, Год журнала: 2024, Номер 81, С. 110319 - 110319

Опубликована: Янв. 16, 2024

Язык: Английский

Процитировано

5
Analysis of hybrid fractional differential equations with nonlocal boundary conditions and linear perturbations DOI Creative Commons
Khaled Aldwoah, Amjad Ali,

Bakri Adam Ibrahim Younis

и другие.

Boundary Value Problems, Год журнала: 2025, Номер 2025(1)

Опубликована: Март 28, 2025

This research focuses on the study of hybrid fractional differential equations with linear perturbation second type. The primary objective this work is to establish existence solutions for proposed equations. To achieve desired results, we apply tools Banach contraction and Krasnoselskii's fixed point theorem respectively derive conditions considered problem. Moreover, developed stability analysis our In addition, fundamental types inequalities are used necessary minimal maximal underlying equation. Finally, present illustrative examples demonstrate key findings study.

Язык: Английский

Процитировано

0
Finite-Time Adaptive NN Backstepping Dynamic Surface Control for Input-Delay Fractional-Order Nonlinear Systems DOI Creative Commons
Yifei Xing, Yantao Wang

IEEE Access, Год журнала: 2023, Номер 11, С. 5206 - 5214

Опубликована: Янв. 1, 2023

This article focuses on a finite-time adaptive dynamic surface control (DSC) approach for kind of nonstrict fractional-order nonlinear systems (FONSs) with input delay. An auxiliary compensation function is presented by using the integral signal to handle delay problem. To overcome problem inherent computational complexity, filter applied virtual controller and its derivative in each step backstepping procedure. By technology neural network (NN), DSC developed, stability criteria based Lyapunov method are introduced prove convergence tracking error into small region around origin. The effectiveness scheme demonstrated two examples.

Язык: Английский

Процитировано

8
Study on Aerodynamic Drag Reduction at Tail of 400 km/h EMU with Air Suction-Blowing Combination DOI Creative Commons

Hongjiang Cui,

Guanxin Chen,

Ying Guan

и другие.

Machines, Год журнала: 2023, Номер 11(2), С. 222 - 222

Опубликована: Фев. 3, 2023

In order to further reduce the aerodynamic drag of High-speed Electric Multiple Units (EMU), an active flow control reduction method combining air suction and blowing is proposed at rear EMU train. A numerical calculation based on realizable k-ε used investigate characteristics a three-car with speed 400 km/h. The influence different suction-blowing mass rates, position number ports surface pressure tail are analyzed. results demonstrate that EMU. And growth rate, rate car gradually increases, but increment decreases. Under same blowing, closer upper lower edges windscreen, is. At flux more ports, better effect car. This study provides reference for next generation great significance breaking through limitations traditional reduction.

Язык: Английский

Процитировано

8