Chaos-based support vector regression for load power forecasting of excavators

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 246, P. 123169 - 123169

Published: Jan. 9, 2024

Language: Английский

---

Adaptive neural observer-based output feedback anti-actuator fault control of a nonlinear electro-hydraulic system with full state constraints

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 24, 2025

Language: Английский

---

Reinforcement learning‐based trajectory planning for continuous digging of excavator working devices in trenching tasks

Computer-Aided Civil and Infrastructure Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 27, 2025

Abstract This paper addresses the challenge of real‐time, continuous trajectory planning for autonomous excavation. A hybrid method combining particle swarm optimization (PSO) and reinforcement learning (RL) is proposed. First, three types excavation trajectories are defined different geometric shapes digging area. Then, an based on PSO algorithm established, resulting in optimal trajectories, sensitive parameters, corresponding variation ranges. Second, RL model built, results obtained offline used as training samples. The RL‐based can be applied tasks, which beneficial improving overall efficiency operation excavator. Finally, simulation experiments were conducted four distinct conditions. demonstrate that proposed effectively accomplishes with generation completed within 0.5 s. Comprehensive performance metrics remained below 0.14, rate exceeded 92%, surpassing or matching optimization‐based PINN‐based method. Moreover, produced consistently balanced across all sub‐tasks. These underline method's effectiveness achieving multi‐objective, excavators.

Language: Английский

---

Application of physics-informed machine learning for excavator working resistance modeling

Mechanical Systems and Signal Processing, Journal Year: 2024, Volume and Issue: 209, P. 111117 - 111117

Published: Jan. 12, 2024

Language: Английский

---

A Comparative Analysis of Machine Learning Algorithms in Predicting the Performance of a Combined Radiant Floor and Fan Coil Cooling System

Buildings, Journal Year: 2024, Volume and Issue: 14(6), P. 1659 - 1659

Published: June 4, 2024

Machine learning algorithms have proven to be practical in a wide range of applications. Many studies been conducted on the operational energy consumption and thermal comfort radiant floor systems. This paper conducts case study self-designed experimental setup that combines fan coil cooling (RFCFC) develops data monitoring system as source historical data. Seven machine (extreme (ELM), convolutional neural network (CNN), genetic algorithm-back propagation (GA-BP), radial basis function (RBF), random forest (RF), support vector (SVM), long short-term memory (LSTM)) were employed predict behavior RFCFC system. Corresponding prediction models then developed evaluate operative temperature (Top) (Eh). The performance model was evaluated using five error metrics. obtained results showed RF had very high predicting Top Eh, with correlation coefficients (>0.9915) low Compared other models, it also demonstrated accuracy Eh prediction, yielding maximum reductions 68.1, 82.4, 43.2% mean absolute percentage (MAPE), squared (MSE), (MAE), respectively. A sensitivity ranking algorithm analysis conducted. importance adjusting parameters, such supply water temperature, enhance indoor comfort. provides novel effective method for evaluating efficiency It insights optimizing systems, lays theoretical foundation future integrating this field.

Language: Английский

---

Prediction of the Unconfined Compressive Strength of Salinized Frozen Soil Based on Machine Learning

Buildings, Journal Year: 2024, Volume and Issue: 14(3), P. 641 - 641

Published: Feb. 29, 2024

Unconfined compressive strength (UCS) is an important parameter of rock and soil mechanical behavior in foundation engineering design construction. In this study, salinized frozen selected as the research object, GDS tests, ultrasonic scanning electron microscopy (SEM) tests are conducted. Based on classification method model parameters, 2 macroscopic 38 mesoscopic 19 microscopic parameters selected. A machine learning used to predict considering three-level characteristic parameters. Four accuracy evaluation indicators evaluate six models. The results show that radial basis function (RBF) has best UCS predictive performance for both training testing stages. terms acceptable stability loss, through analysis gray correlation rough set total amount proportion optimized so there 2, 16, 16 macro, meso, micro a sequence, respectively. simulation aforementioned models with RBF still performs optimally. addition, after optimization, sensitivity third-level more reasonable. proved be effective predicting UCS. This study improves prediction ability by classifying optimizing provides useful reference future salty seasonally regions.

Language: Английский

---

Battery state of health prediction based on voltage intervals, BP neural network and genetic algorithm

International Journal of Green Energy, Journal Year: 2023, Volume and Issue: 21(8), P. 1743 - 1756

Published: Oct. 4, 2023

ABSTRACTAccurate prediction of lithium ion (li-ion) battery capacity is great significance to health status management. In this paper, the different discharge time corresponding equal voltage interval taken as factor. Three highly correlated factors are extracted from curve, and Back Propagation neural network (BPNN) optimized by a genetic algorithm (GA) used estimate accurately quickly. Firstly, related cycle life test extracted, selected analyzed using Spearman correlation coefficient Pearson coefficient. Secondly, paper analyzes effect combinations BPNN algorithm. Then, verify superiority proposed optimization algorithm, algorithms adjust optimize parameters automatically, experimental data for comparative analysis. Finally, GA-BP compared with other common methods. The results show that model can effectively predict li-ion when factors.KEYWORDS: Lithium batterybattery managementdischarge curvegenetic algorithmback propagation Disclosure statementNo potential conflict interest was reported author(s).Data availability statementThe available author on reasonable request.Additional informationFundingThis work supported National Natural Science Foundation China (NSFC, U1966602, 52377161, 52007158), Excellent Young Scientists Fund (51922090), Southwest Jiaotong University new interdisciplinary cultivation project (YH1500112432273 YH15001124322105), Fundamental Research Funds Central Universities (A0920502052301-170).

Language: Английский

---

Video surveillance-based multi-task learning with swin transformer for earthwork activity classification

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 131, P. 107814 - 107814

Published: Dec. 31, 2023

Language: Английский

---

Real-time prediction of port water levels based on EMD-PSO-RBFNN

Frontiers in Marine Science, Journal Year: 2025, Volume and Issue: 12

Published: Jan. 23, 2025

Addressing the spatial variability, temporal dynamics, and non-linearity characteristics of port water levels, a hybrid prediction scheme was proposed, which integrates empirical mode decomposition (EMD) with radial basis function neural network (RBFNN), optimized using particle swarm optimization (PSO) algorithm. First, through application EMD, level time series decomposed into sub-series characterized by lower non-linearity. Subsequently, PSO applied to fine-tune center spread parameters RBFNN, thereby enhancing model’s predictive performance. The PSO-RBFNN model employed make predictions on sub-series. Finally, reconstruction predicted yielded final predictions. feasibility effectiveness proposed were validated measured data. Results from simulations highlighted ability deliver accurate across various lead times. Furthermore, comparative analysis revealed that outperforms alternative methods in prediction. Therefore, serves as reliable, efficient, real-time tool, providing robust support for operational safety.

Language: Английский

---

Power generation efficiency and resources saving of the hydropower industry using the extended data based convolutional neural network

Renewable Energy, Journal Year: 2025, Volume and Issue: unknown, P. 122541 - 122541

Published: Jan. 1, 2025

Language: Английский

---