8
Stack Exchange
votes

Contribution in action from collisions for a gas?

Posted on 1/7/2022
UQ ID:402
Science
Matter Modeling
Original

So if I write the action for a gas:

where is the kinetic energy and is potential energy.

I suspect there is a constant term (which does not affect the equations of motion) for the gas (in classical mechanics). I was hoping to verify my ~~paper's idea ~~ (There is now an updated version see here) up to equation .The summary of ideas section wise are as follows:

We consider an arbitrary potential which everywhere until both the gas molecules collide.

Assuming a non-ideal collision (finite collision time) I get a non-zero action

We use Newton's second law to find the finite collision time and the average force is considered as pressure.

The deformed face of the molecule has an area which is also considered.

Since we are considering spheres colliding which is a function of their relative velocity we can find the average momentum change assuming the collision is not a special event.

The collision per unit 4-volume is mentioned as derived by Einstein.

Combining all the above subsections we derive a constant action term:

where is the number of particles, is the radius of the particle, is the spatial derivative potential and are constants.

Is this expression correct?

Keywords & Tags
molecular-dynamics
thermodynamics
Model Answers (9)
Submitted answers from various AI models
Unsolved
No reviews yet

K2-Think

Pending UQ Validation
Needs Human Verification
MBZUAI-IFM
Qwen2.5-32B
Sep 18, 2025, 01:50 PM

The expression for the constant action term ( S_c ) provided is not correct, primarily due to dimensional inconsistencies and issues with how collision contributions to the action are modeled. Here's a breakdown:

1. Dimensional Analysis

The action ( S ) has units of energy × time (J·s). Let’s analyze the units of ( S_c ):

  • ( N ): Dimensionless (count of particles).
  • ( R ): Length...
0 model reviews
0 human reviews
No reviews yet

GPT-5

UQ Validated
Needs Human Verification
OpenAI
Sep 2, 2025, 06:56 AM

Short answer: No. There is no universal, state‑independent “constant collision term” that should be added to the action of a classical gas. Collisions are already fully accounted for by the interparticle potential in the standard Lagrangian L = T − U, and any additive constant to L has no physical effect on the dynamics or thermodynamics.

Why a constant “collision action” does not arise

  • Proper...
0 model reviews
0 human reviews
No reviews yet

Claude 3.7 Sonnet

Failed UQ Validation
Needs Human Verification
Anthropic
Aug 1, 2025, 12:00 AM

Evaluating the Constant Action Term for Gas Collisions

The question asks about the validity of a derived constant action term for a gas system that accounts for molecular collisions. Let me analyze this carefully.

Analysis of the Approach

The approach you've taken is interesting - attempting to derive a contribution to the action from finite-time collisions between gas molecules. Let me ex...

0 model reviews
0 human reviews
No reviews yet

o3 Pro

UQ Validated
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

Short answer
No. In classical mechanics there is no extra “collision-term’’ that must be added to the action of a gas.
If the molecules interact through a pair potential

  V(r) = 0   for r > 2R
  V(r) = ∞  for r ≤ 2R (hard spheres)

then along every admissible trajectory one always has r>2R, so V≡0 and the action of N particles is simpl...

0 model reviews
0 human reviews
No reviews yet

DeepSeek R1

UQ Validated
Needs Human Verification
DeepSeek
deepseek-ai/DeepSeek-R1
Aug 1, 2025, 12:00 AM
<think> We are given a question about the contribution to the action from collisions in a gas. The user has derived an expression for the collision action term and wants to know if it is correct.

The action for a system is defined as: [ S = \int (T - U) dt ] where ( T ) is the total kinetic energy and ( U ) is the total potential energy.

The user's derived expression for the collision act...

0 model reviews
0 human reviews
No reviews yet

Gemini 2.5 Pro

Failed UQ Validation
Needs Human Verification
Google
Aug 1, 2025, 12:00 AM

This is a very interesting and thought-provoking question. It delves into the fundamental connection between microscopic dynamics (described by the action) and macroscopic thermodynamics.

Let's break down your idea and analyze the expression for .

The short answer is: **No, the expression for as a contribution to the classical action is not correct in the standard fo...

0 model reviews
0 human reviews
No reviews yet

Claude Opus 4

UQ Validated
Needs Human Verification
Anthropic
Aug 1, 2025, 12:00 AM

Looking at your derivation, I can see several issues with the proposed constant action term from collisions:

Conceptual Issues

  1. Action principles don't include collisions directly: In classical mechanics, the action integral is defined for smooth trajectories. Collisions represent discontinuities where the standard variational principle breaks down. The action formulation assumes differ...
0 model reviews
0 human reviews
No reviews yet

o4 mini

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

A few remarks up front:

  1. In classical mechanics any constant piece in the Lagrangian L→L+C
    does not change the equations of motion (it just adds an overall C · t to S, which drops out of δS=0). So whatever constant you pull out of the collision‐term will have no effect on the trajectories of your gas molecules.

  2. If you do go ahead and compute
    S_c ≡ ∑₍collis...

0 model reviews
0 human reviews
No reviews yet

o3

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

In classical mechanics the dynamical information of a gas that is made up of (N) point particles of masses (m_i) is contained in the Lagrangian

[ L({\mathbf r_i,\dot{\mathbf r}i});=;T-U ;=;\sum{i=1}^{N}\frac{m_i}{2}\dot{\mathbf r}i^{2} ;-;\sum{i<j}V(r_{ij}), \qquad r_{ij}=|\mathbf r_i-\mathbf r_j|. ]

The action is the time–integral of the Lagrangia...

0 model reviews
0 human reviews
Submit Your Model's Answer
Your submission will be validated by our LLM validator and then by human experts

You need to be logged in to submit an answer