Claude doesn't know how to calculate realistic minimum voltages for solar arrays w/MPPT chargers. ChatGPT does.
Prompt: "Can I use two strings of four Phono Solar PS440M8GFH solar panels with a EG4 12kPV Hybrid Inverter? I want to make sure that there will not be an issue any time of year. New York upstate."
Claude 4.5: Returns within a few seconds. Does not find the PV panel specs, so it asks me if I want it to search for them. I say yes. Then it finally comes up with: "YES, your configuration is SAFE [...] MPPT range check: Your operating voltage of 131.16V fits comfortably in the 120-500V MPPT operating range".
ChatGPT 5: Returns after 78 seconds. Says: "Hot-weather Vmpp check: Vmpp_string @ STC = 4 × 32.79 = 131 V (inside 120–500 V). Using the panel’s NOCT point (31.17 V each), a typical summer operating point is ~125 V — still OK. But at very hot cell temps (≈70 °C is possible), Vmpp can drop roughly ~13% from STC → ~114 V, which is below the EG4’s 120 V MPPT lower limit. That can cause the tracker to fall out of its optimal range and reduce harvest during peak heat."
ChatGPT used deeper thinking to determine that the lowest possible voltage in the heat would be below the MPPT's minimum operating voltage. It doesn't indicate that in reality it might not charge at all at that point... but it does point out the risk, whereas Claude says everything is fine. I need about 5 back-and-forths with Claude to get it to finally realize its mistake.
This HN post is about claude 4.5 and you come here speaking about how "claude" does not give you satisfactory answer when, most likely, you didn't even try claude 4.5 in the first place.
Claude 4.5 after a few web searches and running a couple python scripts for analysis:
Yes, your configuration should work!
Based on my analysis, two strings of four Phono Solar PS440M8GFH panels will be compatible with the EG4 12kPV inverter for upstate New York conditions.
Key Findings:
Voltage Safety:
Cold weather maximum (-25°C/-13°F): 182V - well below the 600V limit (only 30% of maximum)
Standard operating voltage: 128V - comfortably within the 120-500V MPPT range
Hot weather minimum (40°C/104°F panel temp): 121V - just above the 120V MPPT minimum
Current:
Operating current: ~13.8A per string - well within the 25A MPPT limit (55% of capacity)
Total System:
8 panels × 440W = 3,520W (3.5kW) - well below the 12kW inverter rating
Important Considerations:
Hot weather margin is tight: At extreme hot temperatures, the voltage drops to about 121V, which is only 1V above the MPPT minimum. This means:
The system will work, but efficiency might be slightly reduced on the hottest days
The MPPT controller should still track power effectively
More robust alternative: If you want more safety margin, consider 5 panels per string instead:
Cold: 228V (still safe)
Hot: 151V (much better margin above 120V minimum)
Total: 10 panels = 4.4kW
Wire each string to a separate MPPT on the EG4 12kPV (it has 2 MPPTs), which is perfect for your 2-string configuration.
Bottom Line:
Your planned configuration of 2 strings × 4 panels will work year-round in upstate New York without safety issues. The system is conservatively sized and should perform well!
Now let me calculate whether your configuration will work. I need to determine the cold weather voltage to ensure it stays within the inverter's 600V maximum.
Panel specs I found:
Voc (STC): 39.61V
Vmp: ~33.5V (estimated based on typical ratio)
Imp: ~13.1A (440W / 33.5V)
Critical issue: Temperature coefficient
The PS440M8GFH likely has a Voc temperature coefficient around -0.25% to -0.30%/°C (typical for N-Type TOPCon panels). Let me use -0.27%/°C as a conservative estimate.
Your configuration:
2 strings × 4 panels = 8 panels total
String voltage at STC: 4 × 39.61V = 158.44V
Cold weather calculation for upstate NY:
Upstate NY can see extreme lows of -20°F to -30°F (-29°C to -34°C). Using -30°C as worst-case:
Temperature difference from STC: 25°C - (-30°C) = 55°C
Voltage increase = 39.61V × 0.27% × 55°C = 5.88V per panel
Cold weather Voc per panel = 39.61V + 5.88V = 45.49V
String voltage at -30°C: 4 × 45.49V = 181.96V
Analysis:
Max voltage: 182V << 600V - Safe, plenty of margin
MPPT range: 182V is within 120-500V - Will track properly
Current: 13.1A << 25A per MPPT - No problem
However, there are concerns:
You're only using 182V max when the inverter can handle up to 500V MPPT range. This is inefficient - you're leaving significant wire sizing benefits on the table. With 600V max, you could run 12-13 panels per string instead of 4.
Power utilization: 8 × 440W = 3,520W total, but you have 12kW of PV capacity available (15kW recommended max). You're using less than 30% of the inverter's solar input capability.
Each string on separate MPPT wastes one tracker - both strings are identical orientation/shading, so they'd perform identically.
Will it work? Yes, safely.
Is it optimal? No.
Prompt: "Can I use two strings of four Phono Solar PS440M8GFH solar panels with a EG4 12kPV Hybrid Inverter? I want to make sure that there will not be an issue any time of year. New York upstate."
Claude 4.5: Returns within a few seconds. Does not find the PV panel specs, so it asks me if I want it to search for them. I say yes. Then it finally comes up with: "YES, your configuration is SAFE [...] MPPT range check: Your operating voltage of 131.16V fits comfortably in the 120-500V MPPT operating range".
ChatGPT 5: Returns after 78 seconds. Says: "Hot-weather Vmpp check: Vmpp_string @ STC = 4 × 32.79 = 131 V (inside 120–500 V). Using the panel’s NOCT point (31.17 V each), a typical summer operating point is ~125 V — still OK. But at very hot cell temps (≈70 °C is possible), Vmpp can drop roughly ~13% from STC → ~114 V, which is below the EG4’s 120 V MPPT lower limit. That can cause the tracker to fall out of its optimal range and reduce harvest during peak heat."
ChatGPT used deeper thinking to determine that the lowest possible voltage in the heat would be below the MPPT's minimum operating voltage. It doesn't indicate that in reality it might not charge at all at that point... but it does point out the risk, whereas Claude says everything is fine. I need about 5 back-and-forths with Claude to get it to finally realize its mistake.