Electric actuator fault diagnosis test method based on extended convolution confrontation auto-encoder
A test method and fault diagnosis technology, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as difficulty in obtaining training data, insufficient data conditions, and difficulty in reproducing faults.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0031] Before explaining one or more embodiments of the present disclosure in detail, it should be understood that the embodiments are not limited to construction details in their specific applications, steps or methods set forth in the following description or drawings.
[0032] Among basic deep learning algorithms, convolutional neural network (CNN) is one of the most dominant recognition models, especially when the data conditions are poor. Adversarial autoencoder (AAE) is a general method that can convert autoencoders into generative models. It combines the semi-supervised learning ability of autoencoder (AE) and the generation ability of GAN, which is better than traditional Generative Adversarial Networks (GANs) are easier to train and better capture the data manifold. Therefore, combining the feature extraction capability of CNN with the semi-supervised learning and data generation capabilities of AAE is a feasible way to achieve robust fault diagnosis testing of EMA un...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More