.png){kind=icon}
.png){kind=icon}
Return
Optimization of Process Parameters for electrodeposited Watts Nickel Coating Using a Genetic Algorithm Approach
.png){kind=icon}
OA
AI
DOI：10.33961/jecst.2025.00164.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We utilized a Back Propagation (BP) neural network combined with a Genetic Algorithm (GA) to optimize the parameters of the Watts nickel plating pro-cess, aiming to enhance the coating hardness. The BP neural network model used current density, pH value, boric acid concentration, and bath tempera-ture as input parameters, while coating hardness was the output. The intro-duction of quadratic polynomial features allowed the model to achieve a coefficient of determination (R-2) of 0.973. After GA optimization, the optimal parameter combination was identified as: current density of 1.3 A dm(-2), pH value of 3.6, boric acid concentration of 20.5 g.L-1, and plating bath tem-perature of 42.3 degrees C. The results reveal that orientation and grain size signifi-cantly affect the microhardness of nickel coatings. Specifically, the specialIntscript crystal plane most strongly influences hardness, followed by the specialIntscript crystal plane, while the specialIntscript crystal plane has the least effect. By optimizing the electroplating process parameters, it is possible to control the crystal orien-tation of the coating, thereby affecting the hardness of the coatings. There is a negative correlation between grain size and the hardness. Additionally, In Watts nickel plating, the current density, pH value, boric acid concentration, and bath temperature jointly affect the mechanical properties of the coat-ings, their synergistic action determines the coating quality. We demonstrate that combining GA with neural networks is an effective method for optimiz-ing the deposition parameters and solution chemistry of Watts nickel plating and improving the quality of the coatings.
Keywords:
Genetic
Algorithms
Watts nickel plating
Microhardness
Neural networks
Journal
J
IF:
3
Papers:
182
Citations:
1.1K