Introduction
AIFS/PQA is a quality prediction application in the derivative series of the AIFS platform Perform multiple AI model operation management to simplify the operation and maintenance and update process AIFS/PQA: Quality Prediction of High-Permeability Film Application Case PQA AI model and AIFS system help the customer collect and analyze the Roll-to-Roll program parameters of the film making machine, as well as establish a Predictive Quality Analytics (PQA) model and a quality predictive warning system, which immediately adjust the relevant parameters when there are warnings to improve film rolls’ quality.
Features
- 01
Workspace
Online Code IDE: By using the Jupyter Notebook, you can quickly develop many kinds of analytic models based on Python 3. The Jupyter Notebook supports machine learning and deep learning frameworks, such as Scikit-Learn, Pytorch, Keras and TensorFlow.
Upload Code: If you want to program offline, you can upload your code package and docker image during runtime.
- 02
Task Management
Training Tasks: Allows you to easily create a schedule for running training tasks automatically.
Model Deployment Tasks: Allows you to easily create model deployment schedules and define deployment rules such as the best model and model performance.
Hyperparameter Tuning: Allows you to find optimal hyperparameters for learning algorithms and for optimizing target variables.
- 03
Catalog
Provides many pre-build analytic modules for you to subscribe to and start training tasks.
- 04
Model Board
Visualizes each models’ learning outcomes, helping you assess them.
- 05
Inference Engine
Edge Inference: Allows you to quickly deploy models to edge devices without having to conduct on-site installation.
Cloud Inference: Allows to you push the inference engine app via RestfulAPIs to your WISE-PaaS/EnSaaS cluster, workspace, or namespace.
- 06
AIFS SDK
Model SDK: Allows you to easily upload your training models to the AIFS model repository.
Data Source SDK: Allows you to easily input, query, and update training data in the WISE-PaaS platform.
Additional Information
- Published by
- Advantech
- Copyright
- Advantech