Hi Jon, 

Here's some documentation about BayesDistribution: 
http://openturns.github.io/user_manual/_generated/openturns.BayesDistribution.html
 

Julien 

----- Mail original -----

> De: "Jon Gould" <[email protected]>
> À: "regis lebrun" <[email protected]>, [email protected]
> Envoyé: Dimanche 13 Mars 2016 00:43:27
> Objet: Re: [ot-users] Help for a new user.

> Regis

> Thank you so much for your help. I would have been happy with you just
> pointing me to the relevant section in the reference manual, but by writing
> guide the code for me you helped me to understand what was going on very
> quickly.

> OpenTURNS is a very interesting tool and I look forward to learning more
> about it.

> Kind Regards

> Jon Gould

> -------- Original message --------
> From: regis lebrun <[email protected]>
> Date: 10/03/2016 6:28 pm (GMT+08:00)
> To: Jon Gould <[email protected]>, [email protected]
> Subject: Re: [ot-users] Help for a new user.

> Hi Jon,

> Many thanks for using OpenTURNS. It is fairly easy to build what you need
> with OpenTURNS using the BayesDistribution object. I join a script that do
> the work.

> Best regards,

> Régis

> >________________________________
> > De : Jon Gould <[email protected]>
> >À : "[email protected]" <[email protected]>
> >Envoyé le : Jeudi 10 mars 2016 1h58
> >Objet : Re: [ot-users] Help for a new user.
> >
> >
> >
> >
> >Hi,
> >
> >I’m resending this as I realized that I hadn’t signed up to the mail list
> >and might not get a reply.
> >I’m signed up now.
> >
> >Jon
> >
> >From:Jon Gould
> >Sent: Wednesday, 9 March 2016 5:11 PM
> >To: '[email protected]' <[email protected]>
> >Subject: Help for a new user.
> >
> >
> >Hi,
> >
> >This is my first time with OpenTURNS.
> >
> >I have been looking at using OpenTURNS software from a structural
> >reliability the point of view.
> >
> >In my case the vector the random variable vector(X) has two elements
> >representing wave height(h) and wave period(t).
> >
> >I have built myself a simple two variable response function that calculates
> >a critical response of a floating structure.
> >I have built two simple distributions WEIBULL and LogNormal to represent the
> >wave height and wave period and if the variable are uncorrelated I can use
> >the FORM example to calculate the Design Point of the system.
> >
> >Now I’d like to make it more complicated. I’d like to include the
> >correlation between h and t. The relationship is defined in terms of a
> >conditional relationship ie P(Tz | Hs) = F(t, h) I have a function for
> >that.
> >
> >
> >Mu and sigma are functions of h.
> >
> >
> >
> >My problem is that I don’t understand how to implement that in OpenTURNs.
> >I’m kind of expecting to use a Rosenblatt transform somewhere.
> >
> >Any advice will be gratefully received.
> >
> >Kind Regards,
> >
> >Jon Gould
> >Senior Technical Consultant – Floating Systems
> >Asia Pacific - Perth
> >Peritus International
> >
> >T +61 8 9324 7933
> >F +61 8 9324 7997
> >M +61 416 044 972
> >E [email protected]
> > www.peritusint.com
> >This email and any files transmitted with it are confidential and intended
> >solely for the use of the individual or entity to whom it is addressed. If
> >you have received this email in error please notify the sender and delete
> >the email. Any material that may constitute legal advice or opinion is
> >solely for the reliance and use of Peritus International and its related
> >bodies corporate. You should only read, disclose, re-transmit, copy,
> >distribute, act in reliance on or commercialise the information if you are
> >authorised to do so.
> >
> >_______________________________________________
> >OpenTURNS users mailing list
> >[email protected]
> > http://openturns.org/mailman/listinfo/users
> >
> >
> >

> _______________________________________________
> OpenTURNS users mailing list
> [email protected]
> http://openturns.org/mailman/listinfo/users

-- 
Julien Schueller 
Phimeca Engineering 
www.phimeca.com 
_______________________________________________
OpenTURNS users mailing list
[email protected]
http://openturns.org/mailman/listinfo/users

Reply via email to