Devlog 2 - Smart Bin

ml pipeline

• 6 modules, tensorflow only, three dependencies. cut it from 629 lines to 308, and the old one trained in pytorch then converted to tflite for the pi, so it needed both frameworks
• the split is by session, not by frame. frames from one session are near-duplicates, so a random split puts near-copies of your training data in the test set and the accuracy number means nothing
• evaluate.py prints both numbers and the gap. the frame-split one is there as the number not to believe

firmware

• 11 files. trigger, weigh, light, capture, classify, decide, tilt, log, serve
• the safety rule is enforced twice: a confidence gate at runtime, and a config check that refuses to start if the rules file would ever send an unidentified item to recycling
• weight adjusts the result too. paper over 40 g is probably wet, so it goes to trash

bom

priced everything out, then checked the parts against my own schematic. found five problems:

• the mcp3208 had nothing to measure. its only connected input is the battery divider, and there’s no 12 V source in the build, so i dropped it
• the load cell “kit” ships an hx711 module. my hat already has an hx711 on it, and those modules run at 5 V where mine is deliberately at 3.3 V. bought the bare IC instead
• camera module 3 at $36 to module 2 at $9.49. autofocus is pointless when the camera and the pan never move relative to each other

before: $283.52
now: $195.19

Devlog 1 - Smart Bin

why: recycling bins get contaminated easily, and one bad load can get the whole bin rejected and landfilled. every recycling project i’ve seen is an app telling you which bin to use. i wanted the bin to just do it.

schematic

• 34 components, 26 nets: pi header, load cell (hx711), battery sense (mcp3208), servo rail, led driver, break-beam
• hx711 runs at 3.3 v so both signals are pi-safe, which deletes 4 level-shifting parts
• servo has its own ground meeting pi ground at one 0r link. a shared return browns out the pi and corrupts the sd card
• caught a real bug: led on gpio18 and servo on gpio12 are both pwm0

board

• 65 × 45 mm, 2 layers, pi zero hat footprint. fully routed, ground plane poured. gerbers exported.

cad

• 7 parts on a base plate: pan, hub, idler, servo mount, bearing block, pi mount, plate.

• it couldn’t move. pivot sat 16 mm above the plate, but the pan is 180 mm wide, so at 45° the edges swing 65 mm down and cut through it. raised the pivot to 70 mm

• also measured my actual mg996r instead of trusting the spec (it was actually 39.9 not 40.7 mm, shaft 10.95 off centre not 10.35)

FYI i accidently cadded on fusion and forgot to lapse (there goes like 4 hours of my life) and i imported to onshape so u can see it