[HN Gopher] Show HN: A trainable, modular electronic nose for in...
___________________________________________________________________
Show HN: A trainable, modular electronic nose for industrial use
Hi HN, I'm part of the team building Sniphi. Sniphi is a modular
digital nose that uses gas sensors and machine-learning models to
convert volatile organic compound (VOC) data into a machine-
readable signal that can be integrated into existing QA,
monitoring, or automation systems. The system is currently in an
R&D phase, but already exists as working hardware and software and
is being tested in real environments. The project grew out of
earlier collaborations with university researchers on gas sensors
and odor classification. What we kept running into was a gap
between promising lab results and systems that could actually be
deployed, integrated, and maintained in real production
environments. One of our core goals was to avoid building a
single-purpose device. The same hardware and software stack can be
trained for different use cases by changing the training data and
models, rather than the physical setup. In that sense, we think of
it as a "universal" electronic nose: one platform, multiple smell-
based tasks. Some design principles we optimized for: -
Composable architecture: sensor ingestion, ML inference, and
analytics are decoupled and exposed via APIs/events - Deployment-
first thinking: designed for rollout in factories and warehouses,
not just controlled lab setups - Cloud-backed operations: model
management, monitoring, updates run on Azure, which makes it easier
to integrate with existing industrial IT setups - Trainable across
use cases: the same platform can be retrained for different
classification or monitoring tasks without redesigning the hardware
One public demo we show is classifying different coffee aromas, but
that's just a convenient example. In practice, we're exploring use
cases such as: - Quality control and process monitoring - Early
detection of contamination or spoilage - Continuous monitoring in
large storage environments (e.g. detecting parasite-related grain
contamination in warehouses) Because this is a hardware system,
there's no simple way to try it over the internet. To make it
concrete, we've shared: - A short end-to-end demo video showing
the system in action (YouTube) - A technical overview of the
architecture and deployment model: https://sniphi.com/ At this
stage, we're especially interested in feedback and conversations
with people who: - Have deployed physical sensors at scale - Have
run into problems that smell data _might_ help with - Are curious
about piloting or testing something like this in practice We're
not fundraising here. We're mainly trying to learn where this kind
of sensing is genuinely useful and where it isn't. Happy to answer
technical questions.
Author : kwitczak
Score : 26 points
Date : 2026-03-03 16:34 UTC (3 days ago)
(HTM) web link (sniphi.com)
(TXT) w3m dump (sniphi.com)
| limel wrote:
| The problem is not whether we can digitize the sense of smell,
| but that no industrial process currently relies on it by default.
| The real challenge is identifying the first scalable use case
| that proves measurable business value (sniphi team member here).
| gh5000 wrote:
| There are a few industries that use odorants/aromas.
|
| What is the limit of detection on the sensors? Can they
| reliably pick up compounds in the parts per billion range?
| Parts per trillion?
| murdockq wrote:
| The nearest current use of detection of particles in the air
| that I can think of is smoke and carbon-monoxide detectors for
| safety. Could adoption on these smart versions like Nest or
| Ring by adding your sniphi detector provide other types of
| early warning systems for safety, air quality or sensing?
|
| Some thoughts are musty odors from mold/mildew, rotten egg
| smells indicating gas leaks, and fishy/burning plastic odors
| from electrical issues.
| chabes wrote:
| I built a prototype "digital nose" almost a decade ago, inspired
| by this blog post
| https://web.archive.org/web/20180513090020/http://www.maskau...
|
| I have a friend with Chrons, IBS, and a handful of other gut
| issues. He wants me to build something like this to help self-
| diagnose acute issues as they arise. Yes, a fart classifier.
|
| I want to use a smell classifier to identify ripeness levels in
| agriculture.
|
| I haven't tested to see if this is even feasible, but I'd like to
| also use a tool like this for pest scouting in agriculture. If
| the sensors are sensitive enough to detect small amounts of
| fungi, arthropod activity, or hormonal shifts, this could be
| useful for early detection in integrated pest management systems.
| limel wrote:
| We conducted research with local universities, and the digital
| nose was able to detect the presence of pests in oat flakes and
| beans (two different species).
|
| When we published the white paper ( https://sniphi.com/wp-
| content/uploads/2025/10/Sniphi_digital... ), we expected a
| queue of agricultural companies interested in the technology.
| However, pests apparently aren't "sexy" enough to capture
| attention.
|
| We observed the same reaction with bananas -- fresh vs.
| overripe, like in the video. Technically interesting, but no
| one saw clear business potential.
|
| So now we are looking for use cases that are more obvious and
| compelling from a business perspective. Any ideas?
| MyHonestOpinon wrote:
| Are not there medical applications ? Like the lady that can
| detect parkinson's by the smell.
| https://www.scientificamerican.com/article/a-supersmeller-
| ca...
|
| How good are digital smellers compared with super human
| smellers?
| thebuilderjr wrote:
| Interesting direction. My guess is the first strong wedge is
| narrow pass/fail decisions where people already use smell
| informally and misses are expensive: fermentation batches,
| packaging seal leaks, or early spoilage or mold detection in
| storage. If you can show earlier-than-human detection plus low
| recalibration burden across facilities and seasons, the ROI story
| becomes much easier to sell than a broad platform story. How
| close are you on handling humidity and temperature variation plus
| sensor drift without site-specific retraining?
| embeddding wrote:
| From the pictures, it looks like it's using sensirion VOC sensor.
| There are plenty of "experimental" VOC detectors in the market,
| including BME688/690 with their AI SDK, so far I haven't seen a
| single reliable industry-grade application, only demos that work
| sterile conditions and fail in the harsh real-world conditions.
| gavmor wrote:
| Can't wait to run smell-to-image GGUF models from HF.
| m0llusk wrote:
| Strictly speaking not directly related, but this kind of thing
| always reminds me of the classic Gogol story:
| https://www.libraryofshortstories.com/storiespdf/the-nose.pd...
| sovietswag wrote:
| Part of my training for doing "engine room checks" on a boat
| involved checking for any unusual smells, e.g. fuel leak, burning
| oil (from generator/engine), burning coolant (from
| generator/engine), or burning rubber (from sea chest raw water
| impeller). All of the components in there are equipped with
| sensors[1] that measure levels, temperature, etc. Perhaps there
| is room for a new olfactory sensor there? Aside from avoiding
| catostrophic issues like fire and engine or generator failure,
| it's also important to not pump out[2] any water from the
| compartment into the ocean if it's contaminated with oil, fuel,
| or coolant (the laws about this are super strict).
|
| [1] There are digital sensors that are readable directly from the
| pilothouse by the captain which are rigged to automated alarms,
| as well as manual sensors (e.g. a pressure dial) that are
| readable from the engine room itself, for redundancy. So I don't
| think an olfactory sensor would replace the unusual smell check,
| but it could maybe augment it.
|
| [2] The "bilge pump" is used to pump out water from the bilge
| (bottom floor cavity of engine room). To be honest on my vessel
| the policy is to never turn on the bilge pumps in the engine room
| at all because the risk of dumping contaminants is too high. But
| I still thought to mention this just in case there's an idea
| there.
___________________________________________________________________
(page generated 2026-03-06 23:01 UTC)