Sure thing, let's dig into the mystery. That hum probably means some stray energy is still trapped in the circuit—think inductive kickback, a magnetised inductor, or even a capacitive bleed from a forgotten component. First thing: isolate the circuit, use a good ground reference, and put an oscilloscope on the output to see if it’s a pure DC ripple or a real oscillation. If the hum persists after you’ve grounded everything and unplugged it, check for any magnetised components or long leads that might be acting like a little coil. Also, keep an eye on temperature; a hot component can generate a subtle thermal current that sounds like humming. Once you’ve got the waveform, we can decide if it’s a harmless residual or something that needs a proper bleed resistor or shield. What does the board look like? Any obvious inductors or long wires?

I don’t have the exact PCB layout, but here’s the typical lineup for a “dead” board that still makes noise: 1. Power supply rail – usually a 5 V or 12 V regulator that still sits on the board. 2. Large bulk capacitor near the rail – often a 100 µF electrolytic that can act like a tiny inductive source if it’s partially damaged. 3. Several surface‑mount inductors or ferrite beads that are meant to snub high‑frequency spikes – these can trap magnetic flux and slowly release it as a hum. 4. A few small resistors and maybe a tiny MOSFET that’s been left in a floating state. 5. Any copper pours that cross the power rail can act as inadvertent loops, picking up or radiating stray fields. If you can pull that copper patch off or isolate it with a thin dielectric, the humming should drop. Also, put a small ferrite bead around the power input and a bulk capacitor on the other side of the regulator; that usually cuts the ghost hum. Let me know what you see on the board and I can walk you through pinpointing the loop.

Yeah, that copper patch is the prime suspect. Measure its impedance at 50 Hz or whatever frequency the hum sounds like—if it’s in the hundreds of ohms, that’s the loop’s resonance. Use a LCR meter or a multimeter in AC mode; keep the probe close to the patch to avoid picking up stray capacitance from the rest of the board. If the impedance drops sharply around a few kilohms, that confirms it’s a resonant loop. Then just add a small piece of insulation or a ferrite sleeve around it, and you’ll silence the ghost. Let me know the numbers and we can tweak the damping.

Sounds good, just keep the probe in the air over that copper patch, no touching the surrounding area. Record the impedance curve—look for a clear dip. If it’s at 50 Hz, 60 Hz, or 400 Hz, that’s your target. Then add the ferrite bead or a 10 nF ceramic across the patch and retest. If the dip moves or the value climbs, you’re over‑damping; if it disappears, the loop’s gone. Keep a simple log of the numbers—impedance versus frequency, with and without the add‑on—and we’ll pin it down.