Main Functionalities
- Possibility to stop and cancel a learning or prediction process in A-Eye App
- A-Eye Help document and A-Eye Examples documents have been updated.
Known Bug
- Kriging interpolation (direct or with POD, FFT, Clustering) with cubic basis function is returning the error
“LU decomposition failed. at “
A-Eye App
This version includes the following:
- The Sent to database button in the Learning tab and the Prediction The Prediction tab can now be used to stop the Learning and Prediction process when these are running. In such case, the buttons are labelled Cancel.
- A scroll bar in ODYSSEE Launcher
- When a PDF prediction report is created, it is automatically opened.
- In the Launcher, the type of input and output are displayed below the name of the customization.
- The number of characters for the title of project is limited to 40 characters.
- The number of characters for the title of descriptive variables and results is limited to 30 characters.
- The coordinates in the curve displayer are highlighted to see them correctly.
- When the user clicks on top-right red cross to close A-Eye App, a Cancel button (that has been added to the message box) appears.
- Bug Fixes
- The long customization titles were cut in the launcher page. Now the title is displayed on 2 lines.
- In the CNC Quote customization, the change of the values of the physical parameters was giving unexpected resulting machining times. This is fixed by updating the Y matrix with more coherent results and by switching from Inverse Distance to RBF prediction method.
A-Eye Manager
- When creating or modifying a customization in A-Eye Manager, the names of Descriptive Variables and Results must now contain at least one letter.
- Bug Fix
- When a CSV type is selected in the Manager, no script is associated.
ODYSSEE Quasar – Solver
- Learning speed for Neural Networks (MINN and MLP) has been improved.
- New function read_OUTPUT() added in the <Useful_Functions.qsr> allowing to display in the command prompt the content of the OUTPUT file generated from external function execution.
- The error message of MLP function that appears when normalization is not possible has been updated.
- Bug Fix
- With the MLP solver, if the data contained columns full of zeros, the normalization was not possible, which blocked interpolation. This is fixed, if there are columns full of zeros, these are skipped, and normalization is not applied.