A multi-jet electrospinning direct writing deep learning control system and control method
A deep learning and control system technology, which is applied in the fields of comprehensive factory control, textile and paper making, filament/thread forming, etc., can solve problems such as complex process and lack of suitable control strategy, so as to improve uniformity and achieve long-term stable injection , to overcome the effects of uncertainty and nonlinearity
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0067] In step (7), use the built-up deep learning model to carry out electrospinning direct writing system parameter identification. in each pick
[0070]
[0071] represents the activation of hidden neuron j when the input data is x. In order to make the average activation
[0072] The loss function expression without sparse constraints is:
[0073]
[0074] After adding the sparse constraint to the hidden layer, the loss function is:
[0075]
[0077] After obtaining high-level features from the stacked sparse denoising autoencoder network, support vector regression by estimating the model
[0078] The SVR nonlinear regression function is expressed as:
[0085] Although the above embodiments have been described, those skilled in the art will recognize the basic
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


