Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

- JMP User Community
- :
- Discussions
- :
- Predictive of the batch failure

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

Highlighted
##

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Predictive of the batch failure

May 5, 2020 12:46 AM
(436 views)

Hello to every one.

I would have a suggestions for the following problem:

I have two different process (A and B) to compare and I would understand the probability to get batch failure by using A or B process.

I compare the batch properties with two parameters (c and d).

Then, I want to have "c" parameter greater than equal to 1000 and the batch failure is get if "d" is lower than 70.

Do you have suggestions?

2 REPLIES 2

Highlighted
##

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Re: Predictive of the batch failure

I'm not quite sure of the details of what you want, but 'step one' is to get your data in shape for whatever will come next.

So, how much data do you actually have? Does it look anything like the data here? Cut and copy the JSL below, do 'File > New > New Script', paste in the code, then do 'Edit > Run Script'.

```
NamesDefaultToHere(1);
// Make some dummy data
dt =
New Table( "Test Data",
Add Rows( 0 ),
New Column( "Process",
Numeric,
"Nominal",
Format( "Best", 12 ),
Formula( Random Integer( 0, 1 ) ),
Value Labels( {0 = "A", 1 = "B"} ),
Use Value Labels( 1 )
),
New Column( "Response c",
Numeric,
"Continuous",
Format( "Fixed Dec", 12, 1 ),
Formula(If( :Process == 1, Random Normal( 1100, 50 ), Random Normal( 1050, 100 ))),
Set Property(
"Response Limits",
{Goal( Maximize ), Importance( 1 ), Show Limits( 0 )}
),
Set Property( "Spec Limits", {LSL( 1000 ), Show Limits( 0 )} )
),
New Column( "Response d",
Numeric,
"Continuous",
Format( "Fixed Dec", 12, 1 ),
Formula(If( :Process == 1, Random Normal( 90, 20 ),Random Normal( 95, 25 ))),
Set Property(
"Response Limits",
{Goal( Maximize ), Importance( 1 ), Show Limits( 0 )}
),
Set Property( "Spec Limits", {LSL( 70 ), Show Limits( 0 )} )
)
);
dt << addRows(100);
// Make a graph
gb = dt <<
Graph Builder(
Size( 534, 448 ),
Show Control Panel( 0 ),
Show Legend( 0 ),
Variables( X( :Process ), Y( :Response c ), Y( :Response d ) ),
Elements( Position( 1, 1 ), Points( X, Y, Legend( 9 ) ) ),
Elements( Position( 1, 2 ), Points( X, Y, Legend( 10 ) ) ),
SendToReport(
Dispatch(
{},
"Response c",
ScaleBox,
{Add Ref Line( 1000, "Dashed", "Medium Dark Green", "", 1 )}
),
Dispatch(
{},
"Response d",
ScaleBox,
{Add Ref Line( 70, "Dashed", "Medium Dark Green", "", 1 )}
)
)
);
```

Highlighted
##

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Re: Predictive of the batch failure

Yes data are in that way.

Article Labels

There are no labels assigned to this post.