• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Thermal Spray Conference >Artificial Intelligent Aided Analysis and Prediction of High Velocity Oxy Fuel (HVOF) Sprayed Cr3C2-25NiCr Coatings
【24h】

Artificial Intelligent Aided Analysis and Prediction of High Velocity Oxy Fuel (HVOF) Sprayed Cr3C2-25NiCr Coatings

机译：高速氧气燃料（HVOF）喷涂CR3C2-25NICR涂层的人工智能辅助分析及预测

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In the high velocity oxygen fuel (HVOF) technology, the coating properties are sensitive to the behaviors of in-flight particles that are mainly influenced by the operating parameters of the HVOF process. Due to the complex chemical and thermodynamic reactions, obtaining a comprehensive multi-physical modeling or analytical analysis of the full HVOF spray process is too difficult to be practical. A precise prediction of the coating properties is still a challenging issue. This study focused on analyzing and predicting the HVOF sprayed Cr3C2-25NiCr coatings by applying an artificial neural network (ANN) model to optimize the operating parameters. The feedstock powders were deposited onto the stainless steel substrates via a HVOF spray system, in which the process parameters (served as inputs for the ANN model) were automatically recorded during the spray process. Corresponding tests were carried out to assess the coatings properties (served as targets for the ANN model). The ANN model was built in MATLAB software and trained with experimental data and corresponding coating properties to investigate the relationship between the operating parameters and the mechanical/wear performance of the coatings. The reliability and accuracy of the trained ANN model were verified by the test set of the ANN model.
机译：在高速氧气燃料（HVOF）技术中，涂层性能对飞行中颗粒的行为敏感，主要受HVOF工艺的操作参数的影响。由于复杂的化学和热力学反应，获得全综合HVOF喷涂过程的综合多物理建模或分析分析太难实用。精确预测涂层性质仍然是一个具有挑战性的问题。该研究专注于通过应用人工神经网络（ANN）模型来优化操作参数来分析和预测HVOF喷涂的CR3C2-25NICR涂层。通过HVOF喷雾系统将原料粉末沉积在不锈钢基材上，其中在喷涂过程中自动记录工艺参数（作为ANN模型的输入）。进行相应的测试以评估涂层特性（作为ANN模型的靶标）。 ANN模型内置于MATLAB软件中，采用实验数据和相应的涂层性能培训，以研究操作参数与涂层的机械/磨损性能之间的关系。 ANN模型的测试集验证了培训的ANN模型的可靠性和准确性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号