You are not logged in.
The sprint from 4 to 4.25 seconds just finished after 14 hours...
Courant Number mean: 0.008756053 max: 0.7000001
deltaT = 6.317508e-07
Time = 4.2500002sdiagonal: Solving for rho, Initial residual = 0, Final residual = 0, No Iterations 0
smoothSolver: Solving for Ux, Initial residual = 8.808286e-07, Final residual = 7.10012e-10, No Iterations 1
smoothSolver: Solving for Uy, Initial residual = 1.375834e-05, Final residual = 2.93126e-11, No Iterations 2
smoothSolver: Solving for e, Initial residual = 9.916011e-10, Final residual = 9.916011e-10, No Iterations 0
DILUPBiCGStab: Solving for p, Initial residual = 2.718559e-08, Final residual = 2.17732e-12, No Iterations 1
diagonal: Solving for rho, Initial residual = 0, Final residual = 0, No Iterations 0
time step continuity errors : sum local = 1.603446e-12, global = 1.407235e-13, cumulative = -5.695204e-05
DILUPBiCGStab: Solving for p, Initial residual = 5.209757e-09, Final residual = 5.209757e-09, No Iterations 0
diagonal: Solving for rho, Initial residual = 0, Final residual = 0, No Iterations 0
time step continuity errors : sum local = 2.041394e-09, global = 4.116878e-10, cumulative = -5.695163e-05
ExecutionTime = 51686.46 s ClockTime = 51694 sEnd
I'll work on images to show how things look ... The ** main ** question I have is whether the "new normal" thrust held steady.
***
I've been thinking about the heating mechanism for the physical system. By accident, OpenFOAM may have provided a hint for a solution. The nature of an OpenFOAM model is that it uses a slice of the 3D structure to work with. The slice in the case of the OpenFOAM extendedMerlin mesh is only a couple of centimeters thick. The exact dimensions are published earlier in this topic. ChatGPT5 and I have been 'thinking' about how to apply heat across the entire 40 centimeter width of the heat pipe, and ChatGPT5 tells me doing this is NOT prohibited. The Z surface is not ** normally ** used for anything, but our need to improve the heating simulation leads us to the idea of applying heat to all 52 faces in a segment of the intake, instead of just the current 2. We can see the deficiency caused by the current practice, since only hydrogen near the hot plates is heated, while the cold hydrogen fed into the intake travels all 240 meters down the heat pipe without receiving any heating at all.
However! This quirk of the OpenFOAM environment ** may ** show the way forward for the physical manifestation of the Optical Plane hydrogen engine. We've been imagining a large pipe, but the thin flat model leads us toward a matrix of small diameter quartz pipes with a black surface in 1/2 of the interior. We could feed our 2 kg/s of hydrogen into a lot of pipes and feed photons through the quartz wall to impinge upon the black interior surface. All that gas would then exit into a funnel that would deliver to the intake, which will be reduced dramatically in diameter, per GW Johnson's advice, supported by research kbd512 has done.
kbd512 found examples of satellite maneuvering engines that look close to what is needed for our application.
If all goes well, we will be discussing the latest run and plans for next steps at the Google Meeting tomorrow.
(th)
Offline
Like button can go here
This post contains links to images from the most recent sprint to 4.25 seconds.
The links point to files saved on the Azure test site. They are visible to members who sent IP address information to newmarsmember at gmail.com
kbd512 is working on a permanent solution. In the mean time, if you would like to see the images, please send your IP address. (speedtest.net)
Plot showing steady thrust just above 1 ton-force:
http://40.75.112.55/phpBB3/download/file.php?id=88
EnginePressure:
http://40.75.112.55/phpBB3/download/file.php?id=89
Engine temperature:
http://40.75.112.55/phpBB3/download/file.php?id=90
Engine Velocity:
http://40.75.112.55/phpBB3/download/file.php?id=91
Intake Pressure:
http://40.75.112.55/phpBB3/download/file.php?id=92
Intake Temperature:
http://40.75.112.55/phpBB3/download/file.php?id=93
Intake Velocity:
http://40.75.112.55/phpBB3/download/file.php?id=94
(th)
Offline
Like button can go here
This post is about planning for conversion of the heating system for the extendedMerlin OpenFOAM mesh to a system that applies heat at every one of each of the 52 faces of the intake segments.
Thank you for this comprehensive conceptual overview and detailed work plan. I'd like to share this with our (small) international audience. Our venue is an older forum which uses BBCode but which cannot support LaTex. Please format your plan in BBCode, and please be sure to show the mathematical relationships in text form.
CFD Heating Upgrade Plan (BBCode edition)
Context & Baseline
[]Stable Merlin-derived CFD case with asymmetric heating (hot Y faces only).
[]Inputs: mass flow m_dot = 2 kg/s (H2), thermal power Q_total = 40 MW.
[]Measured thrust ≈ 1 metric ton-force ≈ 9.81 kN.
[]Effective exhaust velocity ve ≈ 9,810 N / 2 kg/s ≈ 4,905 m/s → Isp ≈ 500 s.Jet kinetic power P_kin ≈ 0.5 * m_dot * ve^2 ≈ 24 MW (remainder = thermal/viscous/mixing losses).
Goal for this phase
[]Reduce thermal stratification and lift mass-averaged stagnation temperature at the throat by extending heating from the Y-plates to the full circumference (all 52 plate positions), while keeping total heat input fixed at Q_total = 40 MW.
[]Explore a “plethora of small tubes” (tube-bundle) heating concept that matches the thin-wide intake geometry without exploding mesh size.Step 1 — Full-Circumference Wall Heating (no geometry change)
Idea: Apply the same wall-heat boundary condition to all plate families, hold total power constant.
[]Power bookkeeping: set new wall heat flux as
q_pp_new = Q_total / A_heated_total,
where A_heated_total = sum of areas of all newly heated wall patches.
[]Use a short heat ramp (e.g., 5–10 flow-through times) to avoid harsh transients.What to watch: higher thrust plateau, better exit-plane uniformity, and energy balance still near 40 MW.
Step 2 — Tube-Bundle “Proxy” (homogenized model, no tiny tubes in the mesh)
Goal: Mimic many small heated tubes using distributed sources/sinks instead of explicit micro-geometry.
2a) Distributed energy addition
[]Create thin “slab” regions (cellZones) hugging each plate set, with thickness delta roughly comparable to the intended tube depth or hydraulic diameter.
[]Add a volumetric heating source with rate qdot_V (W/m^3) in those slabs such that
sum_over_slabs( qdot_V * V_slab ) = Q_total,
if this is the only heating.If you keep some wall heat too, enforce:
sum(Q_walls) + sum(qdot_V * V_slab) = 40 MW.2b) Momentum penalty (pressure-drop proxy)
[]Apply a Darcy–Forchheimer sink in the same slabs to represent tube-bundle drag.
[]Start light: target an added total pressure drop across the heated region of ~1% to 3% so the baseline m_dot ≈ 2 kg/s is preserved.Tune coefficients later from unit-cell results (see Step 3).
2c) Why this helps now
[]You capture the two dominant effects of a micro-tube array—distributed heat addition and mild added drag—without a massive cell count increase.
[]Spreading 40 MW over more surface area lowers wall temperatures and flattens gas-phase T, improving nozzle feeding and thrust.Step 3 — Unit-Cell Micro-Channel (optional calibration)
Purpose: Calibrate the homogenized model with a periodic “one-tube” study.
[]Run a periodic micro-channel at the intake Reynolds number.
[]Extract Nusselt number Nu = f(Re,Pr) → effective heat-transfer coefficient:
h = (Nu * k_fluid) / D_h.
[]Extract friction factor f(Re) to set pressure-loss:
deltaP_per_length = 4 * f * (rho * U^2) / (2 * D_h).
[]Use h to shape qdot_V distribution (streamwise bias if needed), and use f to set Darcy/Forchheimer coefficients so the slab imposes the right added drag.Step 4 — Conjugate Heat Transfer (when ready)
Upgrade path: Replace volumetric sources with actual solid regions (fins/tubes) and run a multi-region CHT case.
[]Deposit power on the solid side (or impose wall heat flux), keeping the same global total:
sum(Q_solid_side) ≈ 40 MW.
[]This captures fin conduction and peak metal temperature, informing materials and thermal limits.Do this after Steps 1–2 show clear performance upside.
Power & Stability Guards
[]Energy balance check: verify
sum(Q_walls) + sum(qdot_V * V_slab) ≈ 40 MW (within ~1–2%).
[]Ramps: apply time ramps to heat additions and porous sinks to keep the solver stable.Solver health: maintain CFL and monitor residuals; avoid sudden stiffness changes.
Diagnostics to Track
[]Thrust vs. time: higher steady plateau with similar steadiness.
[]Stagnation temperature at throat (T0): T0 = T * (1 + ((gamma-1)/2) * M^2) for ideal gas; seek higher mass-averaged T0.
[]Exit-plane fields: Mach, T, and rho uniformity; cleaner shock structure.
[]Total pressure loss across intake: confirm porous drag remains small (target +1% to +3%).Heat accounting: confirm total power remains ~40 MW.
Expected Outcomes
[]More uniform pre-nozzle temperature → higher effective exhaust velocity ve at the same m_dot and Q_total.
[]Reduced mixing losses and smoother symmetry → higher thrust than the current ~9.81 kN baseline.Lower wall peak temperatures when heat is spread over more area (tube-bundle concept), improving thermal margins.
Symbol Key (text form)
[]m_dot = mass flow rate (kg/s)
[]Q_total = total thermal power input (W)
[]q_pp = wall heat flux (W/m^2)
[]qdot_V = volumetric heat source (W/m^3)
[]A_heated_total = total area of all heated walls (m^2)
[]V_slab = volume of a heated slab region (m^3)
[]ve = effective exhaust velocity (m/s)
[]Isp = specific impulse (s)
[]T0 = stagnation (total) temperature (K)
[]M = Mach number (-)
[]gamma = ratio of specific heats (-)
[]h = heat-transfer coefficient (W/m^2-K)
[]k_fluid = fluid thermal conductivity (W/m-K)
[]D_h = hydraulic diameter (m)f = friction factor (-), U = mean velocity (m/s), rho = density (kg/m^3)
Notes: Keep Q_total fixed during comparisons to isolate the benefit of geometry/heating distribution. Begin with equal heat per area; only introduce biases (e.g., streamwise or circumferential) after you’ve measured gains from uniform heating.
(th)
Offline
Like button can go here
Here is a bonus from ChatGPT5:
Materials & Tube-Bundle Feedback (Quick Prompt)
Goal: spread Q_total = 40 MW across all 52 plate positions using many small tubes (thin-wide intake geometry).
Operating context: m_dot = 2 kg/s (H2). Target gas temperature rise deltaT ≈ 1000 to 1400 K (text form). Keep metal temperatures within material limits.What we’d love from the group
[]Materials short-list: C/C, SiC or SiSiC, Inconel family, TZM, W-based coatings—pros/cons (max temp, thermal conductivity k, emissivity, H2 compatibility).
[]Tube geometry: suggested inner diameter, wall thickness, and pitch; triangular vs. square packing; target open-area fraction.
[]Surface & coatings: options to reduce hydrogen embrittlement/erosion; emissivity targets for radiative balance.
[]Manufacturing: joining/brazing schemes, modular cartridges, replaceable liners.Sensing & test: thermocouples vs. optical pyrometry vs. thin-film RTDs; pressure taps for deltaP; safe lab instrumentation.
Table-top prototype idea
[]Closed loop at ~1 bar with heated carrier gas (start with N2/Ar; progress to H2 with safety controls).
[]Measure: (1) gas T-rise across bundle, (2) pressure drop, (3) wall temperature map.Success criteria: even outlet temperature field; modest added deltaP; stable materials/coatings after thermal cycling.
Notes
[]Power bookkeeping: sum(Q_walls) + sum(qdot_V * V_slab) ≈ 40 MW (text form).
[]Keep total power fixed while changing geometry to isolate the effect of distribution.
(th)
Offline
Like button can go here
This post contains a suggestion for how a NewMars member (or a non-member reader) might build a table top test apparatus to learn about the effectiveness of the heating method are are considering for the Optical Plane vessel:
Table-Top Heating Demo: from Heat Lamp to Tube-Bundle Proxy
A small, safe bench setup can teach us a lot before we touch complex hardware. Below is a compact plan you can run in a garage or makerspace, starting with a heat-lamp and a carbon (graphite) pipe, then stepping up to flowing gas and tube-bundle surrogates.
1) Objectives
[]Observe how wall heating raises gas temperature and how the effect scales with flow.
[]Measure basic pressure drop through simple “bundle-like” inserts.Generate numbers we can map back into the CFD (effective heat transfer and porous drag).
2) Minimal Setup: Heat Lamp + Carbon Pipe (no flow first, then add flow)
Materials (easy mode)
[]1× infrared heat lamp (e.g., 250 W) with ceramic socket and a simple reflector/hood.
[]1× graphite or carbon pipe (OD ~20–40 mm; length 200–600 mm). Matte black surfaces help absorb IR.K-type thermocouples (2–4) or a handheld IR thermometer (for surfaces; beware emissivity).
* Watt-meter to read lamp power; foil/board to shield surroundings.Build
[]Place the pipe on non-flammable supports. Aim the lamp 10–20 cm away.
[]Instrument: one thermocouple on the outer wall (mid-length), one near an end; add one inside the bore if you can.Warm up in still air: record surface temperatures vs. time for several lamp-to-pipe distances.
What you learn here
[]Radiative coupling and steady wall temperature with essentially zero convective sink.
[]Quick check that your sensors and logging work.3) Add Flowing Gas Through the Pipe (start with N2 or air)
Extra materials
[]Small blower (for air) or a nitrogen cylinder with regulator and a simple rotameter/needle valve.
[]Soft tubing/adapters to couple to the pipe ends; a crude plenum box is fine.U-tube manometer (clear hose + water) or a 0–20 mbar differential gauge to measure pressure drop.
Procedure
[]Run several steady flow points. For each point, log: inlet gas temperature, outlet gas temperature, wall temperature, and pressure drop across the pipe.
[]If you lack a flow meter, use the “bag method”: inflate a known volume (trash bag or balloon), time it, and compute volumetric flow; convert to mass flow using density at room conditions.Back-of-envelope physics (text form)
[]Energy balance: P_absorbed ≈ m_dot * cp * deltaT, so deltaT ≈ P_absorbed / (m_dot * cp).
[]Example with nitrogen: m_dot = 0.0005 kg/s, cp ≈ 1000 J/kg-K, lamp 250 W → deltaT ≈ 250 / (0.00051000) ≈ 500 K (real deltaT will be lower due to losses and partial absorption).
[]Overall heat transfer (one-pass pipe): Q ≈ U * A * deltaT_lm, where deltaT_lm is the log-mean temperature difference between wall and gas along the pipe; solve U ≈ Q / (A * deltaT_lm).
[]Pressure drop: deltaP ≈ K * (rho * U_mean^2 / 2) for a fitting, or for a straight duct use Darcy–Weisbach: deltaP/L ≈ 4f*(rhoU_mean^2)/(2D_h).4) Tube-Bundle Surrogates You Can Build Cheaply
Goal: emulate the “plethora of small tubes” to see how distributed passages affect heating and pressure drop—without high temperatures (initially).
Options
[]Ceramic honeycomb (catalytic-converter blank or kiln honeycomb): known cell density, good temperature capability, straight channels → perfect for deltaP vs. flow mapping.
[]Stainless capillary bundle: zip-tie small tubes into a bundle; insert in a short duct; test at modest temperatures.Graphite fins + spacers: stack thin graphite sheets with uniform spacers to create many narrow passages (thin-wide geometry similar to your intake).
Measurements
[]Mount the surrogate between two short ducts; measure inlet/outlet temperature and deltaP for a range of flows (start with air or N2).
[]Fit a simple model: deltaP/L ≈ (mu/alpha)U_mean + (1/2)rhoC_fU_mean^2.Mapping note: From measured deltaP vs. U_mean, fit alpha (Darcy term) and C_f (Forchheimer term) to drive CFD porous coefficients later.
5) How These Numbers Feed the CFD
[]Effective heating: From Q = m_dot * cp * deltaT and wall–gas temperature data, compute U (overall HTC). Use U to shape a distributed volumetric heat source (qdot_V) so that sum(qdot_V * V_slab) ≈ target power (e.g., 40 MW at scale).
[]Porous drag: From deltaP/L fit, extract alpha and C_f for the Darcy–Forchheimer sink used in the cell-zone slabs. Text form: deltaP/L = (mu/alpha)U + (1/2)rhoC_fU^2.Power bookkeeping: keep total power constant during comparisons: sum(Q_walls) + sum(qdot_V * V_slab) = Q_total.
6) Practical Tips
[]Use matte/black surfaces facing the lamp; shiny metals reflect IR and reduce absorption.
[]Collimate or hood the lamp to avoid heating the room. A cardboard frame lined with foil (inside) works; keep clearance to prevent scorching.
[]Thermocouples: secure with high-temp tape or tiny hose clamps; add a bead just entering the outlet flow to get a reliable gas temperature.
[]Log data every 1–2 seconds; allow each point to reach steady readings before recording.7) Safety (read first, run slow)
[]Start with air or nitrogen. Only consider hydrogen after you’ve proven the rig and procedures.
[]Hydrogen-specific: run outdoors or in a well-ventilated space; hydrogen detector present; no open flames/sparks; use rated regulators, check valves, and a flash arrestor; purge with N2 before and after; leak-check with soap solution; keep cylinders upright and secured.
[]IR lamp: hot surfaces; keep combustible materials away; add a wire guard.
[]Electrical: use grounded outlets; keep wiring away from hot zones; GFCI if available.PPE: safety glasses, heat-resistant gloves, cotton clothing.
8) A Tiny Data Sheet You Can Paste in Replies
[]Lamp power (W): ____; distance (cm): ____; hood/reflector: Y/N
[]Pipe type & size: ____; length (mm): ____
[]Gas: ____; m_dot (kg/s): ____; Tin (°C): ____; Tout (°C): ____ → deltaT (K): ____
[]Wall mid-length (°C): ____
[]Pressure drop (Pa): ____; test article length (m): ____ → deltaP/L (Pa/m): ____
[]Estimated Q = m_dot * cp * deltaT (W): ____
[]Estimated U from Q = U * A * deltaT_lm (W/m^2-K): ____
[]Fitted porous terms (if bundle): alpha (m^2): ____ ; C_f (-): ____Why this matters: spreading the same input power over many passages lowers wall peak temperatures, flattens the gas temperature field, and reduces mixing losses before the throat. Even a humble lamp+pipe test will show the trend: as you distribute heat and tune flow passages, deltaT per watt improves up to a point, while added pressure drop stays modest.
If you want, I can also post a one-page BBCode “lab card” (printable) with wiring, sensor placement sketches (ASCII), and the calculation steps (P = m_dot * cp * deltaT; U = Q/(A*deltaT_lm); deltaP/L model) so others can replicate exactly.
(th)
Offline
Like button can go here