Sensor Anomaly Detector

Flags sensor windows far from normal operation.

Industry	Level	Difficulty	Recommended mode
Manufacturing & IoT	3 of 5	Advanced	sq8

Coming soon

A complete, runnable Sensor Anomaly Detector reference implementation is in progress. The architecture and core code below already work with SrvDB 0.3.

The problem

• Thresholds miss subtle patterns.
• Failures are expensive.
• Edge devices are small.

How SrvDB powers Sensor Anomaly Detector

1. Normal sensor windows are stored as feature vectors with sq8.
2. New windows are compared; a large distance is an anomaly.
3. Runs on ARM edge devices.
4. Crash-safe through power cuts.

What changes

Today	With Sensor Anomaly Detector on SrvDB
Static thresholds	Learned normal behaviour
Late failure detection	Early deviations
Cloud dependence	On the device

How it works

1. Collect normal windows.
2. Store in SrvDB (sq8).
3. Score live windows.
4. Alert operators.
5. Refresh baseline.

SrvDB features it uses

• SQ8 compression (sq8): stores each value in one byte, 4× smaller than full precision.
• True cosine scores: scores in [-1, 1] mean the same in every mode, so thresholds are stable.
• Crash-safe persist(): after it returns, data survives a crash or power loss and reopens exactly as committed.
• Rust API: embed SrvDB directly in Rust services and devices.

Use cases

• Vibration anomalies
• Temperature drift
• Pressure patterns
• Motor current signatures
• Energy anomalies
• Process deviations

Core code

embed() is your embedding model (for example sentence-transformers, or a function that turns your records into feature vectors).

import json
import srvdb

db = srvdb.Database("./sensor-anomaly-detector-db", dimension=128, mode="sq8")

def ingest(items):
    """items: list of (id, text, metadata dict)"""
    db.upsert(
        ids=[i for i, _, _ in items],
        embeddings=[embed(t) for _, t, _ in items],
        metadatas=[json.dumps(m) for _, _, m in items],
    )
    db.persist()                      # crash-safe checkpoint

def deviation(window, k=5):
    hits = db.search(embed(window), k)
    return [(json.loads(db.get(i)), round(score, 3)) for i, score in hits]

Limits and honest notes

• Requires a representative baseline and tuning.

Build roadmap

1. Prototype: load a sample of real data with flat mode and check that searches return what an expert expects.
2. Measure: if you move to an approximate mode, compare its results with flat on the same queries (recall).
3. Pipeline: add continuous upsert and decide when to call persist().
4. Harden: test restarts and crashes, add logging, review every output path with domain experts.
5. Deploy: ship the database directory with the application or service.

All Manufacturing & IoT projects

Level	Project	What it does
1 · Beginner	Maintenance Assistant	Technicians describe a symptom and get the right manual section and past fixes.
2 · Intermediate	Defect Matcher	Matches new defects to past ones, from text and images.
3 · Advanced	Sensor Anomaly Detector (this page)	Flags sensor windows far from normal operation.
4 · Expert	Plant Knowledge Agent	An agent with shift memory across lines, manuals and quality records.
5 · Frontier	Predictive Maintenance at the Edge	Finds machines whose behaviour resembles past pre-failure signatures.

See also: Use cases · Live examples (coming soon)