PlumX Metrics
Embed PlumX Metrics

Artificial Neural Networks Approach for Hardness Prediction of Copper Cold Spray Laser Heat Treated Coatings

Journal of Thermal Spray Technology, ISSN: 1544-1016, Vol: 31, Issue: 3, Page: 525-544
2022
  • 9
    Citations
  • 0
    Usage
  • 16
    Captures
  • 0
    Mentions
  • 0
    Social Media
Metric Options:   Counts1 Year3 Year

Metrics Details

  • Citations
    9
    • Citation Indexes
      9
  • Captures
    16

Review Description

Laser heat treatment offers localized heating zone, high processing speed, and feasibility to treat complex large parts, making it a technology of choice to tailor the hardness and fatigue properties of parts. Determining laser heat treatment process parameters is important to achieve the sought material performance; however, the technique’s high speed makes it difficult to record the thermal history of the part via standard measurement techniques. Furthermore conducting experiments to explore the effect of process parameters is costly. This work aimed at designing a laser heat treatment to be applied to as-deposited copper cold spray coating to meet a 30% through-thickness hardness reduction. An artificial neural network model was developed and used to find laser heat treatment conditions allowing meeting the sought hardness reduction. The thermal histories were obtained through thermal modeling of the laser heating process and the resulting hardness reductions obtained experimentally. This allowed the neural network to correlate the local hardness reduction (model output) to local thermal history (model input). The model was capable of predicting the local hardness reduction of the part according to the local thermal history resulting from various laser heat treatment conditions and thus, may eventually be used to assist in process parameters selection and optimization. Graphical Abstract: Demonstrating ANN model input and output and the methods they were collected 140 × 101mm (600 × 600 DPI) [Figure not available: see fulltext.].

Bibliographic Details

Maryam Razavipour; Bertrand Jodoin; Jean Gabriel Legoux; Dominique Poirier; Bruno Guerreiro; Jason D. Giallonardo

Springer Science and Business Media LLC

Physics and Astronomy; Materials Science

Provide Feedback

Have ideas for a new metric? Would you like to see something else here?Let us know