Implicif differential equation and zero

Click For Summary

Homework Help Overview

The discussion revolves around an implicit differential equation given by \((x^2+y^2)^2=x^2-y^2\). Participants are exploring how to find points where the derivative \(y'\) equals zero, derived from the implicit equation.

Discussion Character

  • Exploratory, Mathematical reasoning, Problem interpretation

Approaches and Questions Raised

  • Participants discuss various methods to find the points where \(y' = 0\), including graphing, substituting values, and parametrization. There are attempts to derive solutions through differentiation and substitution into the original equation.

Discussion Status

Multiple approaches are being explored, with some participants suggesting specific values and others questioning the validity of their methods. There is a mix of proposed solutions and expressions of confusion regarding the intersection of the derived equations.

Contextual Notes

Some participants express uncertainty about the implications of their findings and the correctness of their logic, indicating a need for further clarification on the relationships between the equations involved.

Yann
Messages
48
Reaction score
0
I have an implicit differential equation;

[tex]\left(x^2+y^2\right)^2=x^2-y^2[/tex]

With a little work;

[tex]y' = -\frac{x\left(2x^2+2y^2-1\right)}{y\left(2y^2+2x^2+1\right)}[/tex]

Now I have to find the 4 points where y' = 0, how can I do that ?
 
Physics news on Phys.org
you can graph it or you can sub x = y = 0 for two of the roots and then use the quadratic for the other two factors
 
Let's look at your original function:
(x^2 + y^2)^2 = x^2 - y^2
Let's parametrize, x = cos t, y = sin t, now:
(cos^2 t + sin^2 t)^2 = cos^2 t - sin^2 t
cos^2 blabla + sin^2 blabla = 1, right? So...
1 = cos^2 t - sin^2 t
cos^2 t - sin^2 t - 1 = 0
Differentiating...
-2sin t cos t - 2 sin t cos t = 0
-2 sin t cos t = 2 sin t cos t
- sin t cos t = sin t cos t
Looking at it, you can tell t = 0 is a solution to this equation, and so is t = pi/2...
Let's look a bit further... t = pi is a solution too, isn't it? Also, t = 2pi...
Looking closer, t = 2pi - pi/2 = 3pi/2 would also yield the same answer, wouldn't it?
And let's think again... if t were negative, it would also yield the same answers, thus we also have t = -pi/2, t = -2pi, t = -3pi/2
There, we've got 8 solutions now to this parametrized equation..
Let's go back to your original equation now...
x = cos t
y = sin t
Let's look at our values of t... 0, pi/2, pi and 2pi... let's plug them in..
x(0) = 1
y(0) = 0
(1,0), let's just keep this in mind for now, shall we?
x(pi/2) = 0
y(pi/2) = 1
(0,1)
x(pi) = -1
y(pi) = 0
(-1, 0)
x(2pi) = 1
y(2pi) = 0
(1,0)
x(-2pi) = 1
y(-2pi) = 0
(1,0)
x(-3pi/2) = 0
y = 1
(0,1)
x(-pi) = -1
y(-pi) = 0
(-1, 0)
x(-pi/2) = 0
y(-pi/2) = -1
(0, -1)
OK, let's look at the solution sets we have here, (-1,0), (0,1), (1,0), (0, -1)
From your implicitly differentiated formula, let's plug one of them in, the first one..
As you can see, it yields a 0 in the denominator, we'll rule it out..
Let's look at (0,1)...
It gives you 0 in the numerator... and in the denominator is leaves you with 3... nice... we want this.
Write (0,1) down...
(1,0) would yield a 0 in the denominator as well... oh...
(0, -1) works great too... doesn't leave us with a nasty 0 in the denominator!
OK, so far we have (0,-1) and (0,1) working... that leaves us to find two more solutions...
Let's look at the quadratic...
2x^2 + 2y^2 - 1 = 0
Hmm, looks familiar; a circle, isn't it? (re-arranging...)
x^2 + y^2 = 0.5
Hmm.. interesting... we can now find out when this will equal 0; let's set x = 0..
y^2 = 0.5
y = + or - 1/root 2
Hmm... interesting... let's plug this into the equation... it gives us 0!
OK, we found our four points:
(0, 1)
(0, -1)
(0, 1/root2)
(0, -1/root2)

I think those are the answers anyway..
Oh well, atleast I tried...

disregard me, my logic is very wrong :P
 
Last edited:
Why not try the obvious: set y' equal to 0 and solve!

[tex]y' = -\frac{x\left(2x^2+2y^2-1\right)}{y\left(2y^2+2x^2+1\right)}= 0[/tex]
Immediately multiply both sides by that denominator to get:
[tex]x\left(2x^2+2y^2-1\right)= 0[/tex]
x= 0 is an obvious solution, but gives complex y. If x is not 0, then we have
[tex]x^2+ y^2= \frac{1}{2}[/tex].
Any point on that circle makes y'= 0.

Putting that back into the original equation,
[tex]x^2- y^2= \frac{1}{2}[/tex]
That's a hyperbola that intersects the circle above when (add the two equations) 2x2= 1 or
[tex]x= \pm\frac{\sqrt{2}}{2}[/tex]
Of course
[tex]y= \pm\frac{\sqrt{2}}{2}[/tex]
also and those give the four points.
 
Last edited by a moderator:
Sorry, but i don't understand the "Putting that back into the original equation". Y' = 0 when the circle and the basic equation intersect;

[tex](x^2+y^2)^2 - x^2+y^2 = 2x^2+2y^2-1[/tex]

How can you solve that ?
 
Yann said:
Sorry, but i don't understand the "Putting that back into the original equation". Y' = 0 when the circle and the basic equation intersect;
[tex](x^2+y^2)^2 - x^2+y^2 = 2x^2+2y^2-1[/tex]
How can you solve that ?
HallsofIvy just showed you. Expand what you have posted there, and simplify! :smile: You'll see that some terms cancel out.
 
How ? I understand the idea, but I cannot solve it. There's two unkown. By expanding I have;

[tex]x^4+2x^2y^2+y^4-3x^2-y^2 +1 = 0[/tex]

It's not better.

HallsofIvy said that I can get x^2-y^2 = 1/2 but I can only see;

[tex]\left(\frac{1}{2}\right)^2 = x^2-y^2 \to x^2-y^2 = \frac{1}{4}[/tex]

Which make no sense !
 
Last edited:

Similar threads

Replies
5
Views
3K
  • · Replies 6 ·
Replies
6
Views
2K
  • · Replies 18 ·
Replies
18
Views
4K
  • · Replies 2 ·
Replies
2
Views
2K
  • · Replies 3 ·
Replies
3
Views
2K
  • · Replies 2 ·
Replies
2
Views
2K
Replies
1
Views
2K
  • · Replies 24 ·
Replies
24
Views
4K
  • · Replies 1 ·
Replies
1
Views
2K
  • · Replies 15 ·
Replies
15
Views
2K