A NEW INTELLIGENT METHOD BASED ON COGNITIVE ARTIFICIAL INTELLIGENCE FOR PREDICTING TRANSFORMER REMAINING USEFUL LIFE

MethodsX, Год журнала: 2025, Номер 14, С. 103330 - 103330

Опубликована: Апрель 29, 2025

Язык: Английский

---

Metaheuristic algorithms applied in ANN salinity modelling

Results in Engineering, Год журнала: 2024, Номер 23, С. 102541 - 102541

Опубликована: Июль 11, 2024

Salinity is a classic problem in planning the quality of freshwater resources management. Recent studies related to hybrid machine learning models have shown it's capability simulate salinity dynamics. However, previous metaheuristic algorithms not dealt with comparing single- and hybrid-based much detail. The present study aimed develop univariate by applying an artificial neural network model (ANN) integrated (hybrid-based) coefficient-based particle swarm optimisation chaotic gravitational search algorithm (CPSOCGSA). methodology was developed tested using electrical conductivity (EC) total dissolved solids (TDS) data collected from Euphrates River Babylon Province, Iraq, 2010 2019. CPSOCGSA performance evaluated various single-based ones, including multi-verse optimiser (MVO), marine predator's (MPA), (PSO), slim mould (SMA). principal finding here confirms that outperformed four based on different criteria. outcomes for TDS were 0.004, 0.0248, 0.98 CPSOCGSA-ANN technique concern scatter index (SI), root-mean-squared error (RMSE), correlation coefficient (R2), respectively. For EC, results 0.96 R2, 0.0386 RMSE, 0.006 SI. Due its predictive accuracy, proposed approach suggested as potential strategy predicting monthly data. Considering agriculture's vital role Province's economy, this may help inform future management decisions.

Язык: Английский

---

Modeling Nitrogen behavior in Tigris River Using System Dynamics Approach

Results in Engineering, Год журнала: 2024, Номер unknown, С. 102880 - 102880

Опубликована: Сен. 1, 2024

Язык: Английский

---

Artificial Neural Network-driven Optimization of Fe3O4 Nanoparticles/PVDF Macrospheres in Fenton-like System for Methylene Blue Degradation

Journal of Advanced Research in Micro and Nano Engieering, Год журнала: 2024, Номер 22(1), С. 68 - 84

Опубликована: Авг. 27, 2024

Efficient degradation of industrial dyes remains a critical challenge in environmental engineering. This study introduces novel Fe3O4 nanoparticles/PVDF macrospheres Fenton-like system, optimized using an Artificial Neural Network (ANN) for the Methylene Blue (MB). A feedforward backpropagation neural network model to optimize and predict performance this advanced oxidation process under various operational conditions. The was trained, validated, tested with robust datasets, demonstrating high predictive accuracy generalization capability. Mean Square Error (MSE) Root (RMSE) during testing were 0.0200 0.1414, respectively, indicating precise predictions. coefficient determination (R²) correlation (R) exceptionally at 0.9744 0.9871, affirming model's ability capture underlying dynamics effectively. ANN-driven approach not only enhanced efficiency MB but also provided significant insights into scalability applicability Fe3O4/PVDF system practical water treatment solutions. underscores potential integrating machine learning techniques chemical engineering processes achieve sustainable efficient management solutions, particularly recalcitrant wastewater contaminants.

Язык: Английский

---

A Smart, Multi-configuration, and Low-cost System for Water Turbidity Monitoring

Results in Engineering, Год журнала: 2024, Номер unknown, С. 103116 - 103116

Опубликована: Окт. 1, 2024

Язык: Английский

---

Innovative Methods Predicting the Remaining Useful Life of Transformer Using Limited Data

Опубликована: Янв. 1, 2024

Язык: Английский

---