Testing & Validation

Rigorous verification across every system layer — authentication, real-time data, ML detection, and alert accuracy

Login & Session Management

The application opens on a secure login screen. Credentials are validated against a hashed JSON credential store. Failed attempts are rejected cleanly with no crash or information leak. Three distinct roles unlock different pages and capabilities.

Verified

  • Successful login for all three roles (Administrator, Operator, Analyst)
  • Incorrect credentials rejected — no crash, no stack trace exposed
  • Session token issued on login, cleared on logout
  • Credential store uses hashed values — no plaintext passwords at rest
  • Role-based page visibility enforced after login
A.U.R.A.Secure Login
A.U.R.A.
AUTONOMOUS UTILITY & RESPONSE AGENT
USERNAME
operator_01
PASSWORD
••••••••••
ROLE
Operator
LOGIN
✓ Session authenticated · token issued
AURA
Digital Twin Dashboard Sensor Detail Trends Alerts 1
⚠ FAULT
Module Status
US Lab
Node 1
Node 2
Columbus
Cupola
Airlock
JLP&JPM

ISS Schematic & Live Overlays

The Digital Twin page renders an SVG ISS diagram with color-coded health indicators at all 7 module locations. Testing confirmed all indicators update in real time as fault states are injected and cleared via the data generator.

Verified

  • All 7 module indicators render at correct pixel positions on the SVG
  • Color transitions: green → red on fault injection, back on clearance
  • Clicking a module navigates to Sensor Detail for that location
  • SVG schematic scales correctly across all tested window sizes
  • WebSocket updates received and rendered within 1 second of server tick

Sensor Trend Graphs

Historical sensor data is plotted as interactive Chart.js line charts. Each parameter shows its nominal range as a reference, and anomaly-flagged readings are visually distinguished from nominal data. Testing confirmed data integrity across full historical queues.

Verified

  • Charts render correctly for all 20 sensor parameters
  • Nominal range reference accurate per parameter
  • Historical queue loads 10,000+ rows without performance degradation
  • Anomaly-flagged points visually distinct from nominal readings
  • Charts update live as new WebSocket data arrives each second
  • Export to CSV produces valid, complete files
📈 Sensor TrendsUS Lab · CO₂ Partial Pressure
■ Nominal ■ Anomaly Range band
0.0 0.4 0.8 1.2 -120s -60s now
Current: 1.31 mmHg Nominal: 0.30–0.70
CSV ↓
AURA
Digital Twin Dashboard Sensor Detail Trends
⚠ FAULT
ECLSS System Overview Refresh
US LAB NOMINAL
O2 PP
20.87
CO2 PP
0.38
Temp
21.5°C
DQN: No Action Needed (96%) LSTM: NOMINAL
COLUMBUS FAULT
⚠ Detected: CO₂ Scrubber Failure
CO2 PP
1.31
Temp
24.8°C
DQN: Replace CO₂ Filter (89%) LSTM: CRITICAL

Quick Look — All Sensors

The Quick Look view surfaces all 20 sensor readings across all 7 modules simultaneously. Operators can scan the entire system state at a glance without navigating between locations. Parameter status indicators update in sync with the 1-second WebSocket tick.

Verified

  • All 20 parameters displayed with current value and engineering unit
  • Status indicators (nominal / warning / critical) accurate for all parameter ranges
  • No stale data — all cells update on each WebSocket tick
  • Layout remains stable across browser window sizes

Critical Alert Detection

When the Isolation Forest + Random Forest pipeline classifies incoming sensor data as an active fault, the system fires a critical alert. Testing validated all 8 fault types trigger correctly with zero false positives during nominal operation.

All 8 Fault Types Verified

  • Cabin Leak — pressure drop cascade across N₂, O₂, CO₂ channels
  • O₂ Generator Failure — output rate and purity collapse
  • O₂ Leak — O₂ partial pressure drop without generator fault pattern
  • CO₂ Scrubber Failure — CO₂ partial pressure rise above limit
  • CHX Failure — temperature and humidity excursions
  • Water Processor Failure — TOC and production rate degradation
  • Trace Contaminant Filter Saturation — NH₃, H₂, CO elevation
  • NH₃ Coolant Leak — NH₃ spike with pressure and temperature effects

Zero false alerts raised during 1,000 consecutive nominal samples.

⚠ CRITICAL ALERT ACTIVE FAULT
CO₂ SCRUBBER FAILURE
CO₂ Partial Pressure critical exceedance detected in US Lab
CO₂ PP
1.31 mmHg
LIMIT
0.70 mmHg
RF CONFIDENCE
97.2%
TICKS ACTIVE
8 / 5 gate
ACKNOWLEDGE
VIEW DETAIL
0 false positives · 1,000 nominal samples tested
AURA
Trends Alerts 2 AI Analyst Maintenance
⚠ FAULT
Alert History Refresh Ack All
CRITICAL
CO₂ Scrubber Failure (97.2%) — Columbus
2025-01-01 04:12:38
Ack
CRITICAL
NH₃ Coolant Leak (91.5%) — Node 2
2025-01-01 03:58:11
Ack
WARNING
Humidity Drift — Columbus
2025-01-01 04:09:04
Ack
WARNING
NH₃ Concentration Drift — Node 2
2025-01-01 04:02:17
Ack

Two-Tier Notification System

A.U.R.A. distinguishes Critical alerts (active fault confirmed by ML pipeline) from Warning alerts (parameter drifting toward out-of-range). Both tiers were validated independently for threshold accuracy and display correctness.

⬤ Critical

Active fault. RF confidence above gate. Fires after N consecutive anomalous ticks.

⬤ Warning

Parameter approaching limit. Pre-fault indicator. Fires before Critical triggers.

Verified

  • Critical and Warning tiers fire at correct, distinct thresholds
  • No overlap — fault clears warning and elevates to critical correctly
  • Cooldown timer prevents duplicate alerts within configured window
  • Fault latch clears only after sustained nominal readings resume
  • Alert badge count on nav tab stays accurate throughout test runs

Settings & Runtime Config

Alert thresholds, cooldown windows, and ML gate values are configurable at runtime. Changes persist to disk and take effect on the next server tick without restart.

Verified

  • All configurable parameters render correctly with current values
  • Changes saved to config file and confirmed present on re-read
  • Threshold changes take effect within one server tick (1 second)
  • Invalid values rejected with a clear validation message
  • Default values restore correctly via the reset function
AURA
AI Analyst Maintenance ⚙ Settings
● NOMINAL
Data Alerts Generation Faults ML Security
alert_min_consecutive10
130
alert_cooldown_seconds600
01800
alert_critical_rf_gate0.85
0.51.0
latch_threshold0.95
0.51.0
SAVE
RESTORE DEFAULTS

Validation at a Glance

8 Fault Types Verified
0 False Positives (1,000 samples)
7 ISS Modules Confirmed
1s Max Update Latency