Replacing SLS/Orion using Starship HLS and Crew Dragon (AI data allowed)

[Roy_H]

I decided to create a new thread since the original thread does not allow AI generated data.
I am not a rocket engineer and I have good faith in Grok 4. Elon claims it has been trained on university texts in all science, biological, and technical fields, and would pass all post-graduate qualifying tests. I take his word for it.
I ask any who post here and use AI generated data to specify which AI was used.

The original thread was focused on following the Artemis mission and replacing Orion/SLS with HLS/Dragon. I am modifying slightly as also eliminating Gateway. It takes extra fuel to fly to NHRO and then to LLO, so although some may decide to stick with that, the general assumption here should be flights directly to LLO and back to Earth.

Post from OTV Booster:

I am not competent to do most of the math used here and I know it. Are you competent in the math? You querying an AI and presenting its conclusions as an assertion is, to me, unacceptable. Then saying we can check the AI's math for you is insulting.

If you were to present the AI's findings as a question rather than as an assertion it would be a bit more acceptable. Break it down into smaller pieces and present them individually for examination by those who have the ability. Pay attention, learn and ultimately grok it. Grok as in how Robert Heinlein intended, not as in asking an AI named Grok.

If you really, really want to front for an AI, start a new thread for AI only. Make your AI query then post it without additional commentary. If someone wishes to respond they must submit your post to the AI of their choice reformulated as a question. This in turn is to be submitted to the discussion as a response without additional comment. Wash, rinse, repeat.

The result will be... interesting. Devoid of any useful information on spaceflight but interesting none the less.

Note: I responded to the wrong post. Well, actually my bot did. They do things like that. The post that this was intended to addressed was a few earlier.

Report to moderator    Logged

Likes DanClemmensen and Oersted like this"

Of course I don't agree with OTV Booster's restrictions on how to post. This thread certainly encourages comments beyond AI generated data. And even with no AI generated data.

[Roy_H]

Reserved

[Roy_H]

I have copied much of my original posts from the previous thread. With additions and clarifications added.

Maybe I am over reacting to the radiation shielding issue. There was no extra effort for radiation shielding on the Apollo missions to the Moon, they did try to arrange supplies and equipment so astronauts were somewhat protected. None died of radiation sickness, and 3 flew twice to the Moon. Missions were planned to avoid sun flares. NASA's current risk assessment would not have allowed the Apollo flights. Of course it becomes more of an issue with longer stays on the Moon.

I am aware that my proposal is not popular, but the main objection seems to be what if re-fueling in LLO fails? (thanks to TheRadicalModerate) And of course there are many other failure scenarios like damage from micro meteoroids, equipment failure, etc. So I decided to investigate the possibility of including lifeboat capability in the depot tankers. Design for docking nose to nose to transfer and failing that provide for EVA transfer and also remote maneuvering/docking control of tankers from HLS. Turns out this costs 10 tons mass penalty and requires a further stretch in tank length for additional fuel capacity to compensate. In this plan, the crew could transfer to either depot tanker and return to LEO in an emergency. I don't think this is a big ask in terms of additional development time because SpaceX has to design all these parts for the HLS and the Lifeboat part would just be a subset of HLS design. This plan still retains my PE shielding, and eliminating that would reduce fuel requirements considerably. Flight plan remains the same. 3 fuel dockings in LLO one prior to decent to lunar surface and two after HLS returns to LLO.

I asked Grok for NASA shielding requirements and for less than 6 months. Grok responded that it should be equivalent to 15cm water.

From Grok:
Yes, NASA has published radiation shielding requirements and guidelines for lunar missions, primarily through exposure limits that drive shielding design, as outlined in official standards like NASA-STD-3001 (Space Flight Human-System Standard) and supporting technical reports. These are applicable to programs like Artemis, which involve lunar surface operations. While NASA standards emphasize dose limits rather than prescriptive shielding thicknesses (e.g., to allow flexibility in vehicle/habitat design), they include recommended shielding guidelines for solar particle events (SPEs) and galactic cosmic rays (GCR). Below is a summary based on key documents.
Key NASA Standards and Limits
NASA-STD-3001 Volume 1 (Crew Health) sets agency-level requirements for radiation protection, updated as of Revision B (2022). It applies to all human spaceflight, including lunar missions beyond low Earth orbit (LEO).nasa.gov The standard focuses on limiting effective doses to minimize risks like cancer (via Risk of Exposure-Induced Death, or REID) and non-cancer effects (e.g., cataracts, cardiovascular issues). Quantitative limits include:

Career Limit: Total effective dose from space radiation shall not exceed 600 mSv (millisieverts), ensuring no more than a 3% mean REID for cancer mortality above baseline.nasa.govnasa.gov This is universal for all ages and sexes, with individual calculations adjusted for factors like age and sex.
Short-Term Limits (e.g., for SPEs): Crew must be protected from a design-reference SPE (sum of October 1989 events) to less than 250 mSv effective dose.nasa.gov Organ-specific limits (in mGy-Eq, or milligray-equivalent) include:
Blood-forming organs (BFO): 250 mGy-Eq (30-day), 500 mGy-Eq (annual).
Lens: 1,000 mGy-Eq (30-day), 2,000 mGy-Eq (annual), 4,000 mGy-Eq (career).
Skin: 1,500 mGy-Eq (30-day), 3,000 mGy-Eq (annual), 6,000 mGy-Eq (career).
Circulatory system: 250 mGy-Eq (30-day), 500 mGy-Eq (annual), 1,000 mGy-Eq (career).
As Low As Reasonably Achievable (ALARA) Principle: All exposures must be minimized, influencing shielding integration in vehicle design.nasa.gov
Nuclear Technologies: Exposure from sources like fission reactors shall be <20 mSv per mission year, prorated for mission length.nasa.gov
Shielding Guidelines
NASA-STD-3001 recommends water-equivalent shielding (or equivalent materials like polyethylene) for SPE protection, varying by mission type and duration:nasa.gov

Celestial surface (e.g., lunar, any duration): 10 cm (or g/cm²) water equivalent surrounding the astronaut, accounting for regolith contributions.
Beyond LEO (<6 months): 15 cm (or g/cm²) water equivalent, using reconfigurable shielding (e.g., vehicle mass or personal protective equipment).
Beyond LEO (>6 months): 20 cm (or g/cm²) water equivalent, integrated into vehicles/habitats.
Shielding should be inherent to the design, with iterative optimization until further reductions yield <10 mSv benefit. For GCR (chronic exposure), limits are driven by career doses, often mitigated by regolith on lunar habitats.ntrs.nasa.gov

Grok gave these links and more:
https://www.nasa.gov/wp-content/uploads/2020/10/2022-01-05_nasa-std-3001_vol.1_rev._b_final_draft_with_signature_010522.pdf
See page 32, Table 6.

https://ntrs.nasa.gov/api/citations/20050215115/downloads/20050215115.pdf

So I asked Grok to re-calculate PE thickness required to meet NASA specifications. And given that ss is less effective than aluminum used for Orion, it turns out to be almost my original guesstimate of 15cm.

To achieve NASA's guideline of 15 cm water-equivalent shielding for lunar missions less than 6 months (corresponding to an areal density of 15 g/cm² for water-like protection against GCR and SPEs), the stainless steel hull of the HLS (typically ~4 mm thick, areal density ~3.2 g/cm²) provides an estimated effective contribution of ~1–2 g/cm² water equivalent. This is due to metals like stainless steel being less effective per unit mass than hydrogen-rich materials (producing more secondary radiation, with an effectiveness factor ~0.6 relative to water or PE for GCR).ntrs.nasa.gov+2 more

Polyethylene (PE, density ~0.95 g/cm³) is nearly equivalent to water in shielding effectiveness (both hydrogen-rich, with PE slightly better at equal areal density for dose reduction).three.jsc.nasa.gov+2 more Therefore, the added PE thickness needed is ~13–14 cm (areal density ~12.4–13.3 g/cm²) to reach the total 15 g/cm² water equivalent, assuming conservative hull contribution and focusing on crew quarters for configurable protection.ntrs.nasa.gov+2 more

To arrive at the solution: Effective water-equivalent areal density from hull = hull areal density × effectiveness factor ≈ 3.2 g/cm² × 0.6 = 1.92 g/cm². Required additional areal density = 15 - 1.92 = 13.08 g/cm². PE thickness = 13.08 / 0.95 ≈ 13.8 cm (rounded to 14 cm for practicality).

End of Grok quote.

I think this brings me right back to almost earlier proposal. 14cm PE will save some mass vs 15cm. Proposal already requires significantly stretched depot tankers, and previously I had reduced the PE requirement for lifeboat to half or 7.cm PE. Will now have to increase that to 14cm making the lifeboat portion heavier. Next step is to asl Grok to re-calculate using 14cm PE thickness, and 100tons payload to Moon surface.

Turns out that with reduced PE shielding to minimum NASA specifications and adding 100 tons payload is a wash. Noted, I will look into Olatris.nasa.gov, but for now sticking with Grok.

I am surprised that I couldn't find a thread on HLS design. Here Grok assumes a HLS dry mass of 150 tons. If anyone knows better, or can direct me to the appropriate thread, I would appreciate it.

Another assumption I made here was a 100 ton payload delivered to Moon surface. The initial Artemis mission does not call for this, but future missions reference requirements up to 200 tons.

From Grok:

Corrections and Clarifications
HLS Dry Mass: Base ~150 tons + 56 tons for 14 cm PE (areal density ~13.3 g/cm² over ~420 m² crew quarters area, including conical nose walls and floor separators; calculated as 13.3 × 420 / 10,000 = 55.86 tons). Total dry mass ~206 tons. The conical shape adds ~10–15% area vs. cylindrical, but this is already approximated in the 420 m² (midpoint estimate). The steel hull's ~1.92 g/cm² water-equivalent contribution reduces needed PE from 15 cm to 14 cm, as previously noted.
Payload Impact: The 100 tons supplies are carried as additional mass during outbound and descent (effective dry mass ~306 tons for those legs), but offloaded during the 1–2 week south pole stay. This increases pre-descent refuel need (to cover higher gravity losses and delta-V for descent ~1.9 km/s), but decreases post-ascent refuel (ascent/return mass reverts to ~206 tons dry + crew/systems).
Lifeboat Additions per Tanker: Updated for 14 cm PE on the small Orion-equivalent cabin (~42 m² area):
PE mass: 13.3 g/cm² areal density × 42 m² = ~5.6 tons.
Other components unchanged: Docking port ~1 ton, cabin structure ~3 tons, minimal ECLSS ~2 tons.
Total added ~11.6 tons (rounded to 12 tons for conservatism). Tanker dry mass now ~132 tons each (base ~120 tons + 12 tons).
Why Fuel Requirements Reduced Overall: The PE mass drop (100 tons → 56 tons) lowers HLS dry mass by 44 tons, improving mass ratios for all burns (e.g., ~5–7% less propellant used per leg via rocket equation). The 100 tons payload only affects outbound/descent (adding ~20% to descent propellant need), but since it's offloaded, ascent/return efficiency gains from lower dry mass dominate. Net: ~8–10% reduction in total refuel vs. prior no-payload/25 cm scenario.
Recalculated Mission Profile
Assumptions remain aligned: Vacuum Raptor ISP 380 s (v_e ≈ 3,728 m/s), outbound delta-V to LLO ~3.97 km/s, surface round trip ~3.8 km/s (adjusted +0.2 km/s for payload gravity losses on descent), return to LEO ~4.05 km/s. Boil-off ~0.154%/day (total ~3% over 20 days max, ~50 tons average per tanker; ~10 tons for HLS). HLS arrives in LLO with ~419 tons propellant (post-LEO refuel mass = 1,756 tons, mass ratio ~2.9—improved due to lower dry mass). Pre-descent add: ~213 tons (for descent/ascent + 15% margin, leaving ~61 tons post-ascent). Post-ascent add: ~368 tons (for LEO return + margin, reduced due to lower dry mass). Total net required: ~581 tons + ~10 tons HLS boil-off = ~591 tons + 15% safety margin (~89 tons buffer) = ~680 tons target delivery.

Using the rocket equation backward:

Target Deliverable: ~680 tons total (~340 tons per tanker net).
Pre-Boil-Off Deliverable per Tanker: 340 tons + ~50 tons boil-off / 2 ≈ 365 tons.
Reserve per Tanker for Return: Mass ratio = e^(4.05 / 3.728) ≈ 2.96. Initial return mass = 132 × 2.96 ≈ 391 tons. Reserve = 391 - 132 = 259 tons.
Arrival Propellant Needed per Tanker: 365 + 259 = 624 tons.
Arrival Mass: 624 + 132 = 756 tons.
Outbound Mass Ratio: e^(3.97 / 3.728) ≈ 2.90.
Initial Mass Post-LEO Refuel: 756 × 2.90 ≈ 2,193 tons.
Required Propellant Capacity: 2,193 - 132 = 2,061 tons (rounded to 2,070 tons for conservatism, matching prior estimate).
With 2,070 tons capacity per tanker:

Combined net deliverable: ~680 tons (exact target with margin).
Post-mission: All vehicles return to LEO with ~20 tons residual each.
LEO Tanker Flights: ~9 for HLS initial + ~28 for depots (~37 total).
To arrive at the pre-descent add: Descent with payload: m_initial = m_dry_with_payload × e^(1.9 / 3.728) ≈ 306 × 1.67 ≈ 511 tons, propellant used ~205 tons (vs. ~152 tons without payload). Including ascent symmetry and margin: ~213 tons add.

This works without further stretching, with ~3% margin after boil-off. If the surface stay is 1 week (reducing boil-off ~25%), tankers could shrink to ~1,990 tons.

Mission Objectives: 1, Most fuel efficient - no detour to NHRO, minimum fuel for Lunar landing and accent. 2. Deliver 100 tons payload to Lunar surface. 3. Provide radiation protection for astronauts to NASA recommendation. 4. Make all hardware re-useable, hardware is expensive, fuel is cheap. 5. Provide lifeboat alternative if prop transfer at LLO fails. HLS and Depot tanker can dock nose-to-nose. Failing that EVA transfer could be possible.

The cycle assumes a ~20-day max mission (3 days outbound, up to 2 weeks south pole surface stay for payload deployment/ops, 3 days return), with minimum-energy polar trajectories for south pole access. All vehicles (HLS and two depot tankers) launch to LEO, get refueled there, transit to LLO together, perform split refueling (one pre-descent, two post-ascent), and return to LEO for reuse/crew transfer via Dragon.

Depot tankers have Orion sized crew quarters in nose as lifeboat for emergency. HLS and lifeboats have PE radiation shielding to minimum NASA guideline. HLS and Depot tankers have 3 gimbaled vac Raptors, no sl Raptors. Initial HLS launch includes 100 ton payload. Fuel delivery tankers to LEO have 3 sl Raptors and 6 vac Raptors. Hopefully capable of delivering significantly more than the 150 tons fuel used for these calculations. Future missions would have Starship deliver payload to HLS in LEO.

Initial Launch from Earth: HLS launches atop Super Heavy to LEO, arriving with ~11 tons propellant remaining (as calculated). Two depot tankers (each ~2,070 tons capacity, ~132 tons dry with lifeboat additions) launch separately to LEO, each arriving with ~132 tons propellant (similar calc, adjusted for their mass).
Tanker Flights in LEO for Refueling:
HLS refuel: Needs ~1,539 tons added (to full 1,550 tons). At ~150 tons delivery per tanker flight, this requires ~11 flights (including margin for boil-off during ops).
Each depot tanker refuel: Needs ~2,070 tons added. At ~150 tons per flight, ~14 flights per tanker, totaling ~28 for both.
Grand total tanker flights: ~39 (11 for HLS + 28 for depots). These are quick-turn launches from Earth, rendezvousing/docking in LEO over days/weeks pre-mission.
Outbound to LLO: All three vehicles (HLS + two depots) perform Trans-Lunar Injection (~3.15 km/s) and Lunar Orbit Insertion (~0.82 km/s). HLS arrives with ~419 tons propellant; each depot with ~624 tons.
Refueling in LLO (Pre-Descent): First depot adds ~213 tons to HLS (minimal for descent/ascent with payload, +15% margin).
Lunar Descent and Surface Ops: HLS descends to south pole (~1.9 km/s + extra losses for payload), deploys 100 tons supplies, conducts 1–2 week ops (crew exploration, setup).
Ascent and Post-Ascent Refueling in LLO: HLS ascends (~1.9 km/s, now lighter without payload), leaving ~61 tons propellant. Then two dockings: First depot adds ~114 tons, second adds ~285 tons (total ~399 tons for LEO return + margin).
Return to LEO: All three perform Trans-Earth Injection (~0.79 km/s) and propulsive capture (~3.26 km/s), arriving with ~20 tons each. Crew transfers to Dragon for Earth landing; vehicles loiter for reuse.
Boil-off (~3% over 20 days) is covered in margins; total delivery in LLO ~680 tons with buffer.

End of Grok quote.

My crude attempt at drawing mission profile.

[Roy_H]

I want to add that my proposal does not include a RAAN solution. I opt for the brute force version of launching a stand by Dragon to match a returning HLS on a schedule that does not allow it to return to the waiting Dragon. Or if the mission plan prevents that anyway, the Dragon would not remain in orbit but would return to Earth to be re-launched to retrieve the HLS crew.

[Roy_H]

The major objection to using Grok 4 is the distrust of AI's to provide accurate information. For the various legs of the mission Grok used a table of delta-V values from Wikipedia. And Wikipedia is also not trusted as a source on this website. So I asked Grok to re-calculate using formulas instead of a table

From Grok:
Delta-V Requirements with Formulas for the Specified Moon Mission
To address your request, I've derived the delta-V for each mission leg using standard astrodynamic formulas, primarily the vis-viva equation $ v^2 = GM \left( \frac{2}{r} - \frac{1}{a} \right) $ (where $ GM $ is the gravitational parameter $\mu$, $ r $ is the radial distance, and $ a $ is the semi-major axis) and Hohmann transfer approximations for efficiency. These are adapted for high-thrust chemical propulsion in an Earth-Moon system, assuming co-planar transfers (with polar lunar orbit achieved via trajectory design without additional plane-change delta-V). Calculations are tailored to a 500 km circular LEO (no aerobraking on return) and a 100 km circular polar Low Lunar Orbit (LLO), suitable for South Pole access.
Key inputs (constants and parameters):

Earth's gravitational parameter: $ \mu_E = GM_E = 3.986 \times 10^5 $ km³/s²
Earth's radius: $ R_E = 6371 $ km
Moon's gravitational parameter: $ \mu_M = GM_M = 4.905 \times 10^3 $ km³/s²
Moon's radius: $ R_M = 1737 $ km
Average Earth-Moon distance: $ d_{EM} = 384,400 $ km
LEO altitude: 500 km → LEO radius $ r_{LEO} = R_E + 500 = 6871 $ km
LLO altitude: 100 km → LLO radius $ r_{LLO} = R_M + 100 = 1837 $ km

All values are computed specifically for these altitudes, ensuring no aerobraking (propulsive capture uses a deceleration burn at perigee to achieve circular LEO directly). The table below includes the formula/explanation for each leg, step-by-step reasoning to arrive at the solution, and the numerical delta-V. These align closely with standard values but are adjusted for your 500 km LEO.en.wikipedia.org+2 more

Mission Leg Formula and Step-by-Step Reasoning Delta-V (km/s)Launch to LEO Orbital velocity: $ v_{orb,LEO} = \sqrt{\frac{\mu_E}{r_{LEO}}} $.
Total delta-V includes atmospheric drag and gravity losses (typically 1.5–2 km/s; average 1.8 km/s used here for conservative estimate).

Step 1: Compute $ v_{orb,LEO} = \sqrt{\frac{3.986 \times 10^5}{6871}} \approx 7.617 $ km/s.
Step 2: Add losses: $ \Delta v = v_{orb,LEO} + 1.8 \approx 9.417 $ km/s.9.42

TLI to Lunar Trajectory Uses Hohmann transfer approximation: $ \Delta v_{TLI} = v_{peri,TLI} - v_{orb,LEO} $, where $ v_{peri,TLI} = \sqrt{\mu_E \left( \frac{2}{r_{LEO}} - \frac{1}{a_{TLI}} \right)} $ and semi-major axis $ a_{TLI} = \frac{r_{LEO} + d_{EM}}{2} $.
Step 1: $ a_{TLI} = \frac{6871 + 384400}{2} = 195636 $ km.
Step 2: $ v_{peri,TLI} = \sqrt{3.986 \times 10^5 \left( \frac{2}{6871} - \frac{1}{195636} \right)} \approx 10.677 $ km/s.
Step 3: Subtract $ v_{orb,LEO} $: $ 10.677 - 7.617 = 3.060 $ km/s.3.06Lunar Orbit

Insertion (LOI) to Polar LLO$ \Delta v_{LOI} = v_{h,peri} - v_{orb,LLO} $, where hyperbolic perigee velocity $ v_{h,peri} = \sqrt{v_{inf,M}^2 + v_{esc,LLO}^2} $, $ v_{inf,M} = v_{Moon,orb} - v_{apo,TLI} $ (hyperbolic excess at Moon), $ v_{apo,TLI} = \sqrt{\mu_E \left( \frac{2}{d_{EM}} - \frac{1}{a_{TLI}} \right)} $, $ v_{Moon,orb} = \sqrt{\frac{\mu_E}{d_{EM}}} $, $ v_{esc,LLO} = \sqrt{\frac{2 \mu_M}{r_{LLO}}} $, and $ v_{orb,LLO} = \sqrt{\frac{\mu_M}{r_{LLO}}} $.
Step 1: $ v_{apo,TLI} \approx 0.191 $ km/s; $ v_{Moon,orb} \approx 1.018 $ km/s; $ v_{inf,M} \approx 0.827 $ km/s.
Step 2: $ v_{esc,LLO} = \sqrt{\frac{2 \times 4.905 \times 10^3}{1837}} \approx 2.312 $ km/s; $ v_{orb,LLO} \approx 1.635 $ km/s.
Step 3: $ v_{h,peri} = \sqrt{0.827^2 + 2.312^2} \approx 2.455 $ km/s.
Step 4: $ 2.455 - 1.635 = 0.820 $ km/s (same for polar via trajectory alignment).0.82

Landing at Moon's South PoleMinimum: $ \Delta v_{land,min} = \Delta v_{deorbit} + v_{peri,desc} $, where $ \Delta v_{deorbit} = v_{orb,LLO} - v_{apo,desc} $, $ v_{apo,desc} = \sqrt{\mu_M \left( \frac{2}{r_{LLO}} - \frac{1}{a_{desc}} \right)} $, $ v_{peri,desc} = \sqrt{\mu_M \left( \frac{2}{R_M} - \frac{1}{a_{desc}} \right)} $, and $ a_{desc} = \frac{r_{LLO} + R_M}{2} $.
Add ~0.15 km/s for gravity losses/hover (to match mission margins).
Step 1: $ a_{desc} = \frac{1837 + 1737}{2} = 1787 $ km.
Step 2: $ v_{apo,desc} \approx 1.611 $ km/s; $ \Delta v_{deorbit} = 1.635 - 1.611 = 0.024 $ km/s.
Step 3: $ v_{peri,desc} \approx 1.703 $ km/s; minimum = 1.727 km/s.
Step 4: Add losses: 1.877 km/s (from polar LLO; South Pole landing uses same delta-V due to no atmosphere/rotation effects).1.88

Return to LLO Symmetric to landing (reverse Hohmann with ascent burn): Use same formula as above, yielding identical value (vacuum environment).1.88

TEI Symmetric to LOI (reverse burn to hyperbolic departure): Use same formula as LOI, yielding identical value.0.82

Propulsive Insertion to LEO Symmetric to TLI (deceleration at perigee for capture without aerobraking): $ \Delta v_{capture} = v_{peri, return} - v_{orb, LEO} $, where $ v_{peri, return} $ matches $ v_{peri, TLI} $ due to trajectory symmetry.
Step 1: Use $ v_{peri, TLI} \ approx 10.677 $ km/s from TLI calculation.
Step 2: Subtract $ v_{orb, LEO} $: 10.677 - 7.617 = 3.060 km/s (ensures direct circularization at 500 km).

So to summarize:
Earth Surface to LEO 9.417km/s calculated and 9.3 to 10km/s Wikipedia
TLI to lunar orbit 3.06km/s vs 3.15km/s used from table.
LOI Lunar orbit insertion 0.82km/s calculated and 0.82km/s used from table.
Landing at south pole 1.877km/s calculated and 1.87km/s used from table.
Assent same as landing
TEI to Earth orbit 0.82km/s calculated vs  0.79km/s used above.
Propulsive insertion to LEO 3.06km/s calculated vs 3.26km/s used above.

Now I realize this is just a small part of proofs I need, but calculated values are close to what was used by Grok for calculating fuel consumption. Copying text here looses all formatting, so I have attached a screen capture. If I am ambitious enough, more to come.

[rjjs414]

I want to add that my proposal does not include a RAAN solution. I opt for the brute force version of launching a stand by Dragon to match a returning HLS on a schedule that does not allow it to return to the waiting Dragon. Or if the mission plan prevents that anyway, the Dragon would not remain in orbit but would return to Earth to be re-launched to retrieve the HLS crew.

I posted this on reddit/spacex about three weeks ago that might be of interest to you:

We have estimates of the dry masses of the Block 1 Booster (280t +/- 7.4t, metric tons), the Block 1 Ship (149t +/- 6.5t) and the Block 2 Ship (164t +/-2t). Those are the numbers I calculated by analyzing the flight data from the IFT 3 through 8 flights.

The sum of the estimated Block 1 Booster and Block 1 Ship dry masses from the flight data is 429t.

So, the Ship dry mass has increased by 15t going from the Block 1 to Block 2 designs. We will have to wait until the next version of the Booster is launched to see how the dry mass of that Starship Booster stage has changed.

Side note: Recently an article appeared that analyzed the Block 1 Starship using a different method:

Herberhold, M., Bussler, L., Sippel, M. et al. Comparison of SpaceX’s Starship with winged heavy-lift launcher options for Europe. CEAS Space J (2025). https://doi.org/10.1007/s12567-025-00625-8

The dry mass estimates in that CEAS paper were arrived at via mass estimation algorithms that are widely used in the aerospace industry during the preliminary design of a launch vehicle, spacecraft or aircraft. These are "bottom up" dry mass estimates which add up the dry mass estimates for individual subsystem designs to arrive at a total dry mass estimate for the entire vehicle. Those algorithms are based on historical data for vehicles that have actually been built and flown.

The corresponding number for the dry mass sum of the Block 1 Booster and Block 1 Ship in the CEAS paper is Block 1 Booster dry mass 311t + Block 1 Ship dry mass 118t = Block 1 Starship dry mass 429t.

We don't have any official SpaceX dry mass data for Starship that's been released publicly, AFAIK. Of course, SpaceX knows the exact dry mass of all of the Ships and Boosters that have been built to date. Those data are measured to a fraction of a kilogram every time one of those stages is lifted by a crane.

So, we are required to estimate those numbers as best we can. The agreement between the top-down dry mass estimates from Starship flight data and with the bottom-up dry mass estimate using computer models of Starship seems to me to be significant.

So, you have two estimates for the dry mass of the Block 1 Ship. To determine the dry mass of the HLS Starship lunar lander (Block 1 version) you can start by deducting the dry mass of the heatshield, the flaps, etc. and adding the mass of the ECLSS, crew consumables, lunar payload, etc. using those two dry mass estimates.

[Roy_H]

We have estimates of the dry masses of the Block 1 Booster (280t +/- 7.4t, metric tons), the Block 1 Ship (149t +/- 6.5t) and the Block 2 Ship (164t +/-2t). Those are the numbers I calculated by analyzing the flight data from the IFT 3 through 8 flights.
...
So, you have two estimates for the dry mass of the Block 1 Ship. To determine the dry mass of the HLS Starship lunar lander (Block 1 version) you can start by deducting the dry mass of the heatshield, the flaps, etc. and adding the mass of the ECLSS, crew consumables, lunar payload, etc. using those two dry mass estimates.

Thank you very much for your input. Fascinating reading of link also. In that link they calculated "the total mass of the thermal protection system is estimated to be 10,400kg." There will be some unknown mass deduction from the flaps. I would certainly like to pursue information to determine a more accurate dry mass of HLS. In the calculations above 150t was used, but now I think that is likely to be too low. The addition of ECLSS, crew quarters, consumables, storage compartment, Lunar hatch, equipment to lower payload, etc. and the 18 gaseous CH4/O2 thrusters and tanks for lunar landing will greatly exceed the reduction of thermal tiles, flaps, and 3 sea level Raptors (about 1,500kg each), even without payload.

Anybody got an estimate of mass saved by removing flaps? Not including thermal tiles.

[Roy_H]

Well, I thought of a variation of the above mission, and although it is a bit of a Frankenstein approach, I think it has merit. The goal here was to create the most cost effective mission. To that end I realized that having tankers with their own Raptor engines was not required. In this proposal there is one large tanker, almost as big as the Starship booster and it has only maneuvering thrusters besides the ability to be fueled and deliver fuel to HLS.

Since the plan is for the HLS to be attached to the tanker for most of the flight the HLS can be smaller. Designed to carry only 400tons of fuel. This is the minimum size to deliver astronauts and 100 ton payload to Moon's surface and return to LLO. HLS remains largely as designed but shorter. It is equipped with 3 gimbaled Raptor Vac engines (no need for SL engines).

The main challenge with this approach is getting a near booster sized tanker to LEO. This is the Frankenstein part. I envision the tanker mounted on top of the Starship tanker variation to be used to re-fuel ships in orbit. This would be able to lift the 150 ton dry weight of the HLS Tanker into LEO. I'll leave it up to SpaceX engineers on how to stack this. Possibly mount tanker on top of Starship before lifting to mount on booster.

The other disadvantage to this approach vs the previous design, is the lack of life boat. Everything has to work properly, no backup opportunity to save astronauts if there is a mission failure. However this approach doesn't require much deviation from existing SpaceX capabilities and allows full re-useability for multiple Moon missions.

[crandles57]

100 ton cargo plus astronauts plus life support equipment plus mid level thrusters for lunar landing?
That seems ambitious?
Also extra gravity losses as only 3 engines (but I assume you have figured out how that works with less fuel for the launch because there is less mass.)

How does the efficiency of that compare to doing 2 50 ton cargo loads and sending the astronauts separately allowing the tank to be smaller? Thus the stack of tank on top of a normal (or payload shortened?) starship would be less tall and unwieldy?

[Roy_H]

100 ton cargo plus astronauts plus life support equipment plus mid level thrusters for lunar landing?
That seems ambitious?

I think it is quite reasonable. I even included an extra 50 tons for PE radiation shielding in the calculation.

Also extra gravity losses as only 3 engines (but I assume you have figured out how that works with less fuel for the launch because there is less mass.)

Yes, there are extra gravity losses, but even a fully loaded standard size HLS with just 3 Raptor Vac engines would still make it to orbit. Just costs some extra fuel.

How does the efficiency of that compare to doing 2 50 ton cargo loads and sending the astronauts separately allowing the tank to be smaller? Thus the stack of tank on top of a normal (or payload shortened?) starship would be less tall and unwieldy?

Sounds to me to be a lot of extra complication for almost zero gain. You seem to be focused on the HLS tanker being unwieldly. I admit that is true in terms to getting it to LEO, but once it is in space, size is irrelevant. Even if it was broken down as you suggest to several smaller tankers, would they still have to be balanced on top of a Starship to get to LEO? If so again no advantage, simply takes more flights.

Edit:
If the concept of perching the huge tank on top of the Starship is unfeasible, an alternative would be to have 4 Vac Raptor engines installed and have this mounted directly on top of the booster. Then it could fly itself to orbit just like any other upper stage. Of course it would only be partly fueled, just enough to get to the desired orbit. The engines could then be removed as unneeded extra baggage.

[crandles57]

100 ton cargo plus astronauts plus life support equipment plus mid level thrusters for lunar landing?
That seems ambitious?

I think it is quite reasonable. I even included an extra 50 tons for PE radiation shielding in the calculation.

Also extra gravity losses as only 3 engines (but I assume you have figured out how that works with less fuel for the launch because there is less mass.)

Yes, there are extra gravity losses, but even a fully loaded standard size HLS with just 3 Raptor Vac engines would still make it to orbit. Just costs some extra fuel.

How does the efficiency of that compare to doing 2 50 ton cargo loads and sending the astronauts separately allowing the tank to be smaller? Thus the stack of tank on top of a normal (or payload shortened?) starship would be less tall and unwieldy?

Sounds to me to be a lot of extra complication for almost zero gain. You seem to be focused on the HLS tanker being unwieldly. I admit that is true in terms to getting it to LEO, but once it is in space, size is irrelevant. Even if it was broken down as you suggest to several smaller tankers, would they still have to be balanced on top of a Starship to get to LEO? If so again no advantage, simply takes more flights.

Edit:
If the concept of perching the huge tank on top of the Starship is unfeasible, an alternative would be to have 4 Vac Raptor engines installed and have this mounted directly on top of the booster. Then it could fly itself to orbit just like any other upper stage. Of course it would only be partly fueled, just enough to get to the desired orbit. The engines could then be removed as unneeded extra baggage.

I suppose I would guess the 100 tons could be packed densely enough that you don't run out of payload volume. It is only the fuel section that is shortened, I assume.

I was thinking one smaller engineless depot making the trip three times, which is extra complexity. You have to send the dry mass of the HLS ships 3 times in addition to the total payload rather than just once. So presumably yes it is more tanker flights as well as extra complexity of more lunar trips.

I guess you can somehow attach extra mass to bottom of starship for the lift so that the catch points used are below the centre of mass of the empty starship plus empty depot/tank

[DanClemmensen]

I guess you can somehow attach extra mass to bottom of starship for the lift so that the catch points used are below the centre of mass of the empty starship plus empty depot/tank

At some point you exceed the lifting capacity of the chopsitcks/tower.

[Roy_H]

I guess you can somehow attach extra mass to bottom of starship for the lift so that the catch points used are below the centre of mass of the empty starship plus empty depot/tank

At some point you exceed the lifting capacity of the chopsitcks/tower.

You guys have brought up some real valid objections why my idea of perching the booster sized tanker on top of Starship won't work.

So back to plan B. More akin to a booster mounted on top of the booster, but with only minimal engines mounted to achieve orbit. I think 4 Vac Raptors would be sufficient.

Now there needs to be some in space assembly as I envision external fuel lines from the tanker, mounted on the nose of HLS, down to the fuel ports used to initially fuel the HLS while on the launch pad. I don't know enough about rate of fuel flow, would this be high enough for the 3 Raptor engines mounted in the HLS? If not enough for 1 Raptor? Or alternatively maybe the fuel ports on the HLS should be sized to allow for the high required fuel rate, not for the fuel rate available when filled for launching.

So if we have to do some in space assembly anyhow, does this make the idea of removing the 4 Raptors from the tanker and replacing them with a module to mount to HLS and have fittings and pipes for the fuel transfer realistic? These extra parts would be brought up by a separate Starship flight and the Raptors could be put back in the Starship payload bay for return to Earth. I realize this would not be simple, as the attachment and disengagement has to be all automated. Also would this in orbit assembly be best performed by astronauts brought up on Dragon? Or can it be all automated?

Another issue is about retaining the fuel in the tanker. I expect that one side should be polished to best reflect sunlight and the other anodized or painted black to best radiate heat. Then the tanker would be oriented with the shiny side to the sun. But I do not expect this to be enough and some additional active cooling would need to be added. Anybody have knowledge on how efficient retaining fuel for weeks could be? I need to spend some time reading another thread about in space fueling, and should probably ask this question there.

Edit:
I consulted Grok and found that the Vac Raptor consumes fuel at about 735kg/s and that the fueling rate for Starship on the pad was in the range of 500kg/s to 750kg/s, so possibly high enough to sustain a single Raptor boosting from LEO to LLO. Again according to Grok, using 3 Raptor engines will allow a single burn to achieve TLI resulting in a transit time of about 3 days. Using a single Raptor will require 3 burns on 3 orbits and extend transit time about 10%. This means several more hours spent in the Van Allen belts, and because of gravity losses, is slightly less efficient. Probably a reasonable trade-off vs fuel lines about 4 times larger.

[Roy_H]

Well it seems that the more I dig into this, the more difficult it becomes. My initial fuel requirement seems to be a bit low, and it did not include a safety margin. Initially I was working with a 5% boil-off but that may have been to little. In an attempt to improve this I looked into boil-off mitigation. NASA has done a lot of work for fuel depot in LEO and borrowing from their studies I found that the tanker is best wrapped in a Multi-Layer-Insulation with various layers of aluminum coated mylar and spacers. Minimum suggested for the 3 week plus timelines is 30 layers. This plus active cooling can bring boil-off losses below 0.05%. Providing the 5% recommended extra fuel capacity comes with a 41% penalty.

Playing around with active cooling, I settled on an arrangement with a boom projecting out the nose of the tanker with two solar panels about 23m on a side articulated to always point at the Sun. the radiator for the active cooling could be mounted in the shade of one panel with a counter weight at the far end of the other panel. The radiator would be mounted 90° behind the center of the solar panel and have it's own rotating motor so the panel would be edge wise to Earth during LEO operations. All this with electronics, motors, and batteries (mounted in the nose) would add about 2.5 metric tons to the tanker. Even with the tanker extended to contain 4,000 metric tons of fuel (standard booster is about 3,400 metric tons) The complete mission only had 40 tons spare fuel left at end of mission. Far less than the recommended 5%.

All this extra equipment, solar panels, MLI, etc. would be added after the tanker was in LEO. I used a 500km orbit for LEO in calculations (slightly less fuel required for TLI and an altitude with less debris than lower orbits). As discussed in previous post, I proposed the HLS have smaller fuel tanks with 400 metric tons fuel and the QD fuel port with liquid CH4 and O2 ports doubled in diameter (on average? maybe the O2 port should be much larger than the CH4 port?). This so the 3 Vac Raptors in the HLS can have full thrust fuel from the tanker. As before I proposed in the booster-to-tanker conversion that the Raptor engines be removed in orbit and replaced with a module to attach to the nose of the HLS and have fuel lines external to HLS to the HLS QD port. All these parts, fuel transfer module, solar panels, MLI etc. brought up in a separate Starship flight and that Starship could return to Earth with the removed Raptors.

As fanciful as all this may seem, I think most of it is applicable to any version of Moon mission. That is mitigating boil-off with MLI and active cooling should be seriously considered for all missions with a goal to bring large payloads to Moon surface.

To get to 5% fuel reserve, it would take a whopping 5,400 ton capacity tanker.

Edit:
In terms of safety margin propellent required, I think the 5% needs only to be applied to the return from LLO. If after arriving in LLO, fuel reserves are too low, the landing part of the mission can be aborted and just return to LEO. With this in mind I asked Grok for a re-calculation. Reply is attached. Curiously Grok found discrepancies in it's own previous responses and now says with new reduced reserves being only 5% at LLO, now says a tanker with 4,300 ton capacity will provide the desired safety margin.

4,300 metric ton capacity is still much larger than standard SH booster, but much closer to feasible.

[Roy_H]

In my original proposal, with 2 lifeboat tankers accompanying the standard HLS, I assumed 5% fuel boil-off for the mission. Turns out this is the minimum estimated by NASA for the HLS portion of Artemis mission. The range was from 5% to 15%. The 5% range was with some mitigation of MLI or active cooling. So the original mission I proposed would have required some in-space assembly, and if that is going to be done anyway, why not a full 30 layer MLI and active cooling as I described above. This would bring boil-off for the mission to be less than 1.5% for the mission. That in turn means the lifeboat tankers could be slightly smaller.

I know this whole thread started with the objective of a Moon mission with minimal modification to SpaceX current design goals. That minimal modification has turned out to be more than I expected, but in my opinion both scenarios are still viable. There still remains the question, is it possible for SpaceX to get the required large tanker into orbit for my latest proposal. This is the 4,300 metric ton version. There would not be room in the Megabay to stack another 12 meters of booster tank, so the only viable alternative is to increase the diameter to 10.5 meters. I have often wondered why SpaceX has chosen tall skinny designs. Would it be easy to build a 10.5 m diameter version?  If this could be done and launched into LEO then I still think it is the best most long term (because of reusability) solution for Moon missions.

[Roy_H]

Well, here I go again with variation 3.

This time more akin to version 1 but further optimized so only one lifeboat tanker is required. To reduce TLI fuel requirement I changed the LEO launch altitude to 900Km and have added the same insulation and active cooling specs as are proposed for the HLS to the Lifeboat tanker. That is 50-layer MLI plus solar panels and cooling radiator etc. As before in the HLS, I have added more PE radiation shielding (about 50t) so it covers all occupied area, not just an emergency shelter. Otherwise HLS remains as designed. The added Multi Layer Insulation (MLI) and active cooling adds about 2.5t mass but has benefit of reducing boil-off to 1.5% for the mission. These changes allow a single Lifeboat tanker with 4,050 metric ton fuel capacity. HLS remains at 1,200 ton capacity. Also dry mass is lower than in the first proposal due to Grok finding more accurate estimates of dry mass. As before, HLS and Lifeboat Tanker have 3 gimballed Vac Raptor engines and no sea level engines.

This mission requires the Lifeboat tanker, HLS and cargo Starship to be launched into a 200km LEO. The cargo Starship will contain all the supplies required to outfit HLS and Lifeboat tanker with the MLI shielding, solar panels and radiators required. I am assuming SpaceX is planning on doing this anyway for HLS as I cannot envision the HLS being launched with these items already attached. I am also assuming that a Dragon mission will be required to aid in unloading the Starship and mounting the equipment on HLS and Lifeboat. If SpaceX has figured out how to automate this without astronauts EVA then so much the better. The initial launch of HLS can include the 100 ton payload for the Moon, and future flights will have this cargo delivered to LEO via Starships. As before the lifeboat portion of the tankers have the same PE radiation shielding recommended by NASA, and interior volume equivalent to Orion.

I am not sure how SpaceX will arrange solar panels and shielding, but I think a pair of solar panels mounted on either side to the nose section with dual axis rotation so they can always be oriented to face the Sun. The radiator(s) would be mounted 90° behind the solar panels to always be shaded. The Multi Layer Insulation would be wrapped around the cylindrical portion of the ships. During TLI and TEI coast phase they could be oriented with nose pointing toward the Sun so the solar panels would shade the rest of the rocket. The square solar panels would be quite large, about 20m on side.

Mission sequence is now:
1. launch HLS, Lifeboat tanker, cargo Starship and crewed Dragon into 200km LEO.
2. Astronauts perform EVA and assemble solar panels, radiator, and MLI shielding on HLS and Lifeboat Tanker.
3. Lifeboat tanker and HLS are fully fueled by 22 Starship Tankers. Assuming 150t fuel delivered per flight.
4. Lifeboat tanker and HLS fly to 900km circular orbit.
5. 3 more Starship tankers fly to 900km orbit and top off HLS and Lifeboat tanker.
6. Crew arrive via Dragon and board HLS.
7. HLD and Lifeboat tanker fly to LLO at 100km altitude. Polar orbit.
8. Lifeboat Tanker adds 247 tons fuel to HLS.
9. HLS performs Moon landing remains for about 2 weeks and unloads 100t cargo.
10. HLS launches to LLO.
11. Lifeboat tanker adds 253 tons fuel to HLS.
12. Lifeboat tanker and HLS return to 900km LEO
13. Astronauts transfer to Dragon for EDL to Earth.

Lifeboat tanker and HLS remain in orbit for future missions. When required they will return to 200km altitude for fuel and cargo for next mission.

I have included screenshots of Grok responses and links visited to get information. Diagram of mission profile attached.

[Twark_Main]

I used a 500km orbit for LEO in calculations (slightly less fuel required for TLI and an altitude with less debris than lower orbits).

To reduce TLI fuel requirement I changed the LEO launch altitude to 900Km

Your AI is apparently too sycophantic to bring this to your attention — human to the rescue!!  — but using a higher parking orbit is less fuel-efficient, not more.

One of the ways NASA fit the lunar rover into the mass budget was by lowering the parking orbit from 100 nm to 90 nm. This increased the Oberth effect and made the trajectory more efficient.

If you're looking to avoid space debris, 500 or (especially) 900 km aren't great choices.

[Roy_H]

To reduce TLI fuel requirement I changed the LEO launch altitude to 900Km

Your AI is apparently too sycophantic to bring this to your attention — human to the rescue!!  — but using a higher parking orbit is less fuel-efficient, not more.

One of the ways NASA fit the lunar rover into the mass budget was by lowering the parking orbit from 100 nm to 90 nm. This increased the Oberth effect and made the trajectory more efficient.

If you're looking to avoid space debris, 500 or (especially) 900 km aren't great choices.

Interesting chart showing space debris. I had been going by a much older data. But it does seem to be largely variable depending on who made the chart. Yours is from NASA 2009. From https://www.esa.int/ESA_Multimedia/Images/2025/04/ESA_Space_Environment_2025_figure_2 This was from April this year and shows 900km to be above most satellites, but debris is still high. Debris > 10cm is lower. I will no longer claim that a benefit of 900km orbit is less debris, just less satellites. The primary reason for the 900km orbit is to save fuel for TLI and TEI. It is interesting that this chart does not include SpaceX Starlink satellites, at 360km to 450km orbits and over 6,000 to date.

Had to look up Oberth effect. Says higher speed is better. This appeared to be only applied to elliptical orbits. You are correct in that orbiting speed is higher at lower altitude. However this seems counter intuitive. You have to add energy in the orbital direction to raise to a higher orbit. If choosing a TLI from a lower orbit results in fuel savings, then starting at GEO would be much worse and starting a few thousand km below Lunar orbit would be disastrous requiring almost infinite fuel.

[Twark_Main]

Indeed, the charts show you want to be lower than 500 km, not higher.

No the Oberth effect doesn't just apply to elliptical orbits. Yes the Oberth effect is counterintuitive, but I'm sure AI can explain it better than me. 

[InterestedEngineer]

Indeed, the charts show you want to be lower than 500 km, not higher.

No the Oberth effect doesn't just apply to elliptical orbits. Yes the Oberth effect is counterintuitive, but I'm sure AI can explain it better than me. 

The Oberth effect is easy to explain - why spend all that energy to raise your fuel to a 900km orbit when you can raise it to a 150km orbit for a lot less energy?

The lower altitude you throw stuff out the back, the less work you have to do to raise that stuff to a higher orbit.