# Updating a variable every time step using NeuralPDE.jl and Physics-Informed NN

**URL:** <https://discourse.julialang.org/t/updating-a-variable-every-time-step-using-neuralpde-jl-and-physics-informed-nn/49621>\
**Category:** General Usage\
**Tags:** diffeq\
**Created:** [November 5, 2020, 9:49am UTC](https://discourse.julialang.org/t/updating-a-variable-every-time-step-using-neuralpde-jl-and-physics-informed-nn/49621 "2020-11-05T09:49:53Z")\
**Posts on this page:** 1\
**Showing post:** 6

<div class="post-metadata">

**Author:** ![Fathya.Salih](https://avatars.discourse-cdn.com/v4/letter/f/47e85d/32.png) [@Fathya.Salih](https://discourse.julialang.org/u/Fathya.Salih)\
**Post date:** [November 5, 2020, 3:26pm UTC](https://discourse.julialang.org/t/updating-a-variable-every-time-step-using-neuralpde-jl-and-physics-informed-nn/49621/6 "2020-11-05T15:26:39Z")

</div>

Thank you!  
Using `u(something)` worked.

```julia
function foo(u)
    a = u(t,x,θ)^2
    return a
end

# Initial and boundary conditions
X = collect(range(-1, 1, step=0.1))
bcs = Vector{ModelingToolkit.Equation}(undef, length(U)+2)
for i in eachindex(X)
    a = foo(u)
    bcs[i] = u(0,X[i],θ) ~ -a*sin(X[i]*pi)
end

```

---

_[View the full topic](https://discourse.julialang.org/t/updating-a-variable-every-time-step-using-neuralpde-jl-and-physics-informed-nn/49621)._