[Stoves] What do the AIs ChatGPT3.5 and Perplexity know about the upward and downward flow of air?

Wed Feb 28 12:08:32 CST 2024

Thanks for this Julien

It is clear in both cases that the AI's think the flow is unbounded. Within a stove there are several pretty severe constraints which give different results.

When a down-drafting heat exchanger is observed, there is a tendency for hot air to rise even if the flow is generally downward.  The issue of importance is whether the flow is strong enough to overcome the buoyancy of the hot molecules.

Using the example of 200 mm / sec horizontally the buoyancy is about 30 times the force of the tendency to create turbulence and keep the hot molecules away from the upper surface.  That is why there is no need to put a baffle under a pot to "stir the air".

When descending in the stove you drew the other day the hottest molecules rise top the top of the enclosed space and the cooler ones head down.  The relevant question is if the hot gases are drawn downward with more force than the tendency to rise due to buoyancy.   The answer is in the speed v.s. temperature.  Unfortunately it is not a simple calculation, taking about a page of handwritten notes.  But you can measure the gas temperature and see if it remains hottest at the top v.s. somewhere along the path.

The AIs have missed this entirely because they only know about unbounded gas flow.
It is all good clean fun

Regards
Crispin

From: Stoves <stoves-bounces at lists.bioenergylists.org> On Behalf Of Julien Winter
Sent: Wednesday, February 28, 2024 9:51 AM
To: Discussion of biomass cooking stoves <stoves at lists.bioenergylists.org>
Subject: [Stoves] What do the AIs ChatGPT3.5 and Perplexity know about the upward and downward flow of air?

Hi folks;

Just for sport, I thought I would ask ChatGPD 3.5 and Perplexity a question about air flow:

QUESTION: "How do the turbulent vs. laminar characteristics differ between downward flowing and upward flowing air?"

Both AIs didn't give a good answer on the first try and required a follow-up clarification. Perplexity though I was asking for definitions of turbulent and laminar flow, and ChatGPT thought that downward-flowing air would bump into more obstacles.

So, having sorted them out, this is what they said.

ChatGPT ========================

Certainly! When comparing the turbulent and laminar characteristics of downward flowing and upward flowing air without any obstacles obstructing the flow, the differences lie primarily in the effects of buoyancy and stability. Here's a revised comparison:

Downward Flowing Air:

  *   Turbulence: Even without obstacles, downward flowing air can still exhibit turbulence, especially if it encounters changes in temperature, pressure, or wind shear. As the air descends, it may encounter different atmospheric layers with varying properties, leading to turbulence.
  *   Laminar Flow: In ideal conditions with minimal atmospheric disturbances, downward flowing air can exhibit more laminar flow compared to upward flowing air. However, the presence of any instabilities or variations in the atmospheric properties can disrupt laminar flow.

Upward Flowing Air:

  *   Turbulence: Upward flowing air tends to be less turbulent compared to downward flowing air, especially in the absence of obstacles. The buoyancy force driving the air upward can result in a smoother, more coherent flow pattern. However, localized turbulence can still develop due to convective processes or changes in atmospheric conditions.
  *   Laminar Flow: Upward flowing air has a greater tendency to maintain laminar flow in the absence of obstacles and under stable atmospheric conditions. Buoyancy-driven flow, such as in thermals or updrafts, can promote more organized, laminar flow patterns.

In summary, in the absence of obstacles, downward flowing air can still exhibit turbulence due to the potential for encountering atmospheric disturbances, while upward flowing air tends to be smoother and more conducive to laminar flow, driven by buoyancy effects. However, both directions of flow can experience variations depending on the stability and properties of the surrounding atmosphere.

Perplexity =====================================

When comparing upward and downward flows of air in terms of turbulent and laminar characteristics, the differences lie in the behavior of the airflow:

Upward Flow:

  *   Turbulent Characteristics: Upward turbulent airflow involves irregular and chaotic movement with unpredictable fluctuations, mixing of fluid particles, swirling vortices, rapid changes in velocity, and pressure fluctuations.
  *   Application: Commonly observed in scenarios like smoke coming out of exhaust pipes or turbulence in aircraft, upward turbulent flow is influenced by irregularities or obstructions in the airflow path.

Downward Flow:

  *   Laminar Characteristics: Downward laminar airflow is characterized by smooth and streamlined movement where fluid layers move parallel to each other without mixing or disruption.
  *   Observation: In downward laminar flow, the fluid flows in a straight line with low flow rate and constant properties like velocity and pressure.

In essence, upward flowing air tends to exhibit turbulent characteristics with chaotic movement and mixing of particles, while downward flowing air typically displays laminar behavior with smooth and orderly movement of fluid layers. These distinctions are crucial for various applications where understanding airflow dynamics is essential for system design and efficiency.

==================================

With some iterative, leading or loaded questions, it might be possible to push the AIs into the answer you want.  But that is a human training the AI, not the AI training the human.

Niether AI seems to have read the book Norbert suggested: Groume-Grjikailo in his 1923 book "The Flow of Gases in Furnaces"  on pages 88 - 91. https://archive.org/details/TheFlowOfGasesInFurnaces/page/n107/mode/2up?view=theater

It is also interesting to see how it is good to use several AIs, because they give different answers.

Have a whack at it and see what you get.

Cheers,
Julien.

--
Julien Winter
Cobourg, ON, CANADA
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.bioenergylists.org/pipermail/stoves_lists.bioenergylists.org/attachments/20240228/26d3b6b5/attachment.html>