Battery-less Audio Node Design
Worked for 8 mins 57 sec
I renamed the project and captured the concept in Project Specification. I also completed a datasheet-grounded feasibility check in Feasibility and Power Analysis.
Conclusion: the exact 2 mm cube off-the-shelf design should not proceed to schematic as stated—the microphone and EFR32-class SoC packages alone exceed the volume, and the 01005 buffer capacitor is orders of magnitude too small for RF/audio burst energy. Recommended next step is to choose a revised target: larger proof-of-concept PCB, true custom bare-die/SiP research package, or reduced-function NFC-style node.
Design a larger proof-of-concept PCB around these components.
Thought for 11 sec
I’ll design a practical proof-of-concept schematic around the same RF SoC, PDM mic, Schottky rectifier, and GRM02 buffer concept. I’ll size the power path first, add the components and support circuitry, wire the schematic, then run review and document the firmware/power notes.
Worked for 8 mins 44 sec
Designed the larger proof-of-concept schematic around the EFR32MG22, SPK0641HT4H-1 mic, SMS7621 rectifier bridge, GRM02 benchmark capacitor, larger reservoir cap, AP2112K 3.3 V rail, SMA RF test port, coil input, SWD header, reset, decoupling, and RF match.
I documented the implementation in Proof-of-Concept Design Notes and added firmware bring-up guidance in Firmware Starter. Schematic connectivity is complete; remaining review issues are expected layout airwires and generic-part MPNs to resolve before fabrication. Next step is PCB layout setup and placement—ready when you want me to proceed.
Set board stackup
Auto-place components
Run ERC/DRC
Resolve BOM MPNs
Add test points
Refine this doc
Ask about this doc
RF-Harvested Audio Node — Project Specification
User Concept
Battery-less microsystem intended to fit inside a 2 mm x 2 mm x 2 mm volume. It is powered by inductive coupling or ambient RF harvesting, buffers harvested energy in miniature ceramic capacitors, records audio with a MEMS microphone, and transmits short data bursts using an active RF SoC.
Target Envelope
- Maximum external envelope: 2 mm x 2 mm x 2 mm, total volume 8 mm^3.
- User text also mentioned $2 mm^3$; this conflicts with the 2 mm cube envelope. Current working assumption: 2 mm cube / 8 mm^3.
- Proposed mechanical concept: shell-and-core assembly with a 44 AWG wire coil around a 1.8 mm mandrel, electronics inserted inside the coil, and acoustic port left unblocked.
Functional Blocks
- RF/inductive energy pickup: micro-coil or antenna.
- Rectification and power conditioning: Schottky diode rectifier or energy-harvesting power management.
- Energy storage: miniature MLCC buffer capacitor bank.
- Processor/RF: ultra-low-power wireless MCU/SoC.
- Acoustic capture: MEMS microphone.
- Nonvolatile storage: internal flash if available, otherwise external die-level memory.
- Encapsulation: acoustic-compatible environmental coating such as Parylene-C with acoustic port protection.
Candidate Parts from User
Table
| Function | User Candidate | Notes to Verify |
|---|---|---|
| Acoustic sensor | Knowles SPK0641HT4H | Verify interface, supply current, package, acoustic port, and availability. |
| SoC / RF IC | Silicon Labs EFR32MG WLCSP | Verify exact MPN/package; EFR32MG family parts are usually far larger than 1.6 mm x 1.6 mm unless bare die/custom packaging is available. |
| Rectifier diode | Skyworks SMS7621-060 | Verify package availability, forward drop at harvested current, reverse leakage, RF frequency suitability. |
| Storage capacitor | Murata GRM02 01005 metric | Verify available capacitance at working voltage after DC-bias derating. |
| Antenna/coil | 44 AWG bonded copper wire | Verify achievable inductance, Q, series resistance, tuning capacitance, coupling distance, and manufacturing repeatability. |
Initial Engineering Concerns
- The selected SoC and MEMS microphone may not physically fit together inside a true 2 mm cube once interconnect, coil wall thickness, storage capacitance, rectifier, and encapsulation are included.
- RF burst current of approximately 5 mA to 10 mA requires substantial stored energy; a single 01005 capacitor likely cannot support useful radio TX plus microphone/MCU operation.
- Audio capture is data-heavy. Internal MCU flash endurance may not tolerate continuous writes every few milliseconds unless write buffering, wear leveling, or FRAM/MRAM is used.
- A passive diode bridge wastes harvested voltage; for low RF/inductive input levels, an integrated energy-harvesting PMIC or synchronous rectifier is usually required.
- 2.4 GHz ambient RF harvesting at this size is likely impractical for active audio capture unless the transmitter is very close and intentionally powering the device.
- Standard PCB layout is likely not enough; this is closer to chip-scale assembly / bare-die / wire-bond / custom package design.
Immediate Validation Tasks
- Verify the exact purchasable part variants and dimensions.
- Pull datasheet values for supply voltage, current, interface, external passives, and package for each active/RF part.
- Build a burst energy budget: E = 0.5C(V_hi^2 - V_lo^2), compare against MCU + mic + RF TX energy per burst.
- Decide whether the schematic should target a proof-of-concept dev-scale board first, or an ultra-miniature conceptual chip-scale assembly.
Current Status
Project renamed and requirements captured. Datasheet/library search and feasibility analysis pending before schematic capture.
Welcome 👋
Flux helps you build PCBs faster with an AI teammate!
Create your account to collaborate, stay updated, fork your own version, and get instant answers from our AI agent.