Scholarlink

<p>A coupled two-body mass Lagrangian is used to model a magnetic rail nScrypt printer extruder with a sensor attached to the side for signal reconstruction and digital twinning. The equations of motion (EQM) derived from the Lagrangian are then used to improve the accelerometer signal by incorporating them as activation functions in the layers of the neural network, then using the damping constant and frequency matrix as learnable parameters. This is compared to a modular neural network that uses the EQM as the loss residuals for backward propagation and the physical constants as neural nets, both methods were found to give a root-mean square error (RMSE) of ~ 14&#xa0;mm to 0.75&#xa0;mm from the original position signal respectively. The physics informed neural network (PINN) activation layer produced a better detailed fit, while the PINN loss function produced a better average line and standard deviation. The two methods are then combined to achieve a final result with an RMSE of 0.96&#xa0;mm to 16.7&#xa0;mm, and a standard deviation that drops significantly during training to ~ 1.6&#xa0;mm, but comparable to the PINN activation of 44–827&#xa0;mm for test samples.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Physics informed activation functions and loss functions for signal reconstruction and digital twinning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月23日

查看全文
  • Brent Cook,
  • Adryel Gainza,
  • Bryan Portocarrero,
  • Mubarak Mujawar,
  • Vivek Kamat,
  • Dan Ewing,
  • Himanshu Upadhyay,
  • Shekhar Bhansali

摘要

A coupled two-body mass Lagrangian is used to model a magnetic rail nScrypt printer extruder with a sensor attached to the side for signal reconstruction and digital twinning. The equations of motion (EQM) derived from the Lagrangian are then used to improve the accelerometer signal by incorporating them as activation functions in the layers of the neural network, then using the damping constant and frequency matrix as learnable parameters. This is compared to a modular neural network that uses the EQM as the loss residuals for backward propagation and the physical constants as neural nets, both methods were found to give a root-mean square error (RMSE) of ~ 14 mm to 0.75 mm from the original position signal respectively. The physics informed neural network (PINN) activation layer produced a better detailed fit, while the PINN loss function produced a better average line and standard deviation. The two methods are then combined to achieve a final result with an RMSE of 0.96 mm to 16.7 mm, and a standard deviation that drops significantly during training to ~ 1.6 mm, but comparable to the PINN activation of 44–827 mm for test samples.