ρ-MATRIQS™ | Stochastic Mass-Balance Control for Secondary Metal Processing | TejTatv AI

Physics-Led · Multi-Sensor · Bayesian Inference · Industrial Grade

Closing the
Yield Gap in
Mixed Scrap Streams

15,000 data points/sec · <20ms end-to-end inference · per-particle economic classification

Stochastic mass-balance control for secondary metal processing. Every particle on your conveyor belt classified by composition, density, and economic value — without stopping the line.

94%
Sort Accuracy
±2%, material-dependent
<20ms
End-to-End Latency
sensor → actuator
7
Sensor Modalities
fused in parallel
72hr
Install
no shutdown
📡 7 Sensor Modalities ⚡ <20ms End-to-End 🏭 Industrial IP69K 🧠 Bayesian Inference Engine 🔌 Plug-in to Existing DCS 🛡 Edge-First, Air-Gapped Capable
The Problem

Yield Loss Is Happening on Every Shift

The loss is not visible — it leaves as undervalued mixed fraction. ρ-MATRIQS™ converts invisible loss into a traceable, recoverable number.

⚠ Typical 100 TPD Shredder — Without Classification
3–5%Recoverable metal exits as mixed low-grade fraction
₹3–5 CrUnrealised value per month at current LME prices
ZeroVisibility on where the loss occurs or which fraction
ManualAudit prep — 2–4 weeks per year, error-prone
✓ Same 100 TPD — With ρ-MATRIQS™
+3–5%Recovery gain — validated across two pilot sites
TraceableLoss map per shift — fraction, grade, particle count
ControlledOutput grades — Cu, Cu-Zn, Cu-Sn classified separately
AutoCPCB + EPR compliance data — no manual entry
Capability

Multi-Sensor Fusion vs Single-Signal Classification

Single sensors produce unacceptable error rates on real industrial scrap. Error rate is bounded within ±2% only when all seven signals are fused and cross-validated.

❌ Single-Sensor Systems

  • Surface oxidation causes misclassification — sub-surface composition unknown
  • Binary output only — pass or reject, no alloy-grade resolution
  • No confidence scoring — classification errors undetected until audit
  • Manual recalibration required between material changes

✓ ρ-MATRIQS™ 7-Signal Fusion

  • 7 signals cross-validate — errors self-cancel. Error rate bounded within ±2%
  • Alloy-grade resolution: Cu, Cu-Zn, Cu-Sn classified as separate fractions
  • Confidence score on every decision — uncertainty always explicit and logged
  • Self-calibrating — adapts to feed composition changes within 24h cycle

Not a sorter — a post-separation value recovery layer. Installs downstream of your existing ECS and magnet, on the belt you already have.

Check My Fit →
Sensor Technology

Seven Ways to Read a Single Particle

Each sensor reads a different physical property. Alone, each can be defeated by surface state, particle geometry, or contamination. Combined, their cross-validated output produces a classification whose error rate is bounded within ±2% under mixed-material real-world conditions.

XRT
X-Ray Transmission
Density via bulk mass

X-ray penetration up to 120mm particle depth. Denser materials attenuate more flux. Identifies true internal composition — unaffected by surface oxidation, paint, or coating.

Penetration: up to 120mm · Cycle: 2–4ms
LIBS
Laser Spark Chemistry
Elemental composition

1–2ms pulse cycle. Micro-plasma flash reveals elemental spectrum. Resolves Cu from Cu-Zn from Cu-Sn — grade-level, not class-level. No surface prep required.

Pulse cycle: 1–2ms · Elements: Cu, Al, Zn, Pb, Fe, Li
VIS/NIR
Near-Infrared + Visual
Mineral / surface type

Spectral range 400–2500nm. NIR fingerprints mineral types; VIS captures shape, colour, and surface texture at 4MP @ 120fps. Dual-mode cross-check eliminates single-band ambiguity.

Range: 400–2500nm · Frame: 4MP @ 120fps
EM
Electromagnetic
Conductivity grade

Multi-frequency induction field separates Al from Cu, brass from zinc — by conductivity signature at each frequency. Resolves alloys that look identical to NIR.

Multi-frequency · Resolves: Al / Cu / Brass / Zn
MAG
Magnetic Detection
Ferrous / non-ferrous

First-pass ferrous gate. Instant identification of iron content — removes Fe contamination from the classification pipeline before non-ferrous stages run.

Response: <1ms · Fe removal: first-pass gate
3D TOF
Time-of-Flight Volume
True particle volume

±1.5mm volumetric accuracy. Measures exact particle volume in milliseconds. Combined with XRT mass, yields true bulk density — not estimable from surface geometry alone.

Accuracy: ±1.5mm · Output: 3D point cloud
BULK ρ
Density Modelling
Physics-corrected ρ

Corrects all density readings for moisture content, temperature drift (±0.3°C resolution), vibration, and void space. Outputs real composition signal — not environmental noise.

Temp resolution: ±0.3°C · Moisture-corrected
Why not just use one? On clean, single-material lab samples, a single sensor is sufficient. On real industrial scrap — oxidised, contaminated, variable particle size, mixed alloys — single sensors produce unacceptable error rates. Fusion is not optional at industrial scale.
Sensor Fusion

One Installed System. One Certain Answer.

Each sensor's reading is weighted by its reliability for that material type. The Bayesian engine cross-checks, resolves conflicts, and produces a single classification with an explicit confidence score. Low-confidence particles pass through — they are never silently contaminated into a high-value fraction.

Step 1
Raw Sensor Data
7 parallel streams
Step 2
Noise Filtering
Env. correction
Step 3
Spatial Alignment
Particle tracking
Step 4
AI Fusion Engine
Weighted merge
Step 5
Material ID + Confidence
Score: 0–100%
Output
Sort Action → Higher Value
+ Compliance log
Three-Stage Decision Pipeline

Measure → Decide → Recover

Each stage is physics-led, hardware-synchronised, and logged. Uncertainty is always explicit — never silently discarded.

01

Measure — 7 Signals, Simultaneously

Density, elemental composition, shape, conductivity, magnetic response — all read in under 20ms per particle. Belt encoder position-syncs every signal. No sequential sampling — all modalities fire in parallel.

02

Decide — Bayesian Inference Engine

Each signal is weighted by material-type reliability. Posterior probability P(material|signal) computed for all candidate classes. Mass-balance constraint applied per shift. Confidence score output on every decision.

03

Recover — Route + Record

Air jet fires at belt-encoder-tracked position. Grade certificate issued. CPCB/EPR compliance record created. All three outputs — physical sort, certificate, log — generated in the same decision cycle.

FUSION DECISION LOG — LIVE STREAM
Every decision logged · Compliance record auto-created · Edge compute only
System Performance

Measured on Deployed Installations

94%
Sort Accuracy Sustained
±2%, material-dep.
<20ms
End-to-End Latency
sensor → actuator
+3–5%
Recovery Gain per Tonne
pilot validated
100%
Decisions Logged
per-particle, auto
How We Measured This Pilot data from deployed installations — not lab benchmarks
94% Sort Accuracy

Measured over 3-month HMS scrap pilot · 2,40,000+ decisions logged · XRF blind-verified sample set of 500 particles · ±2% material-dependent variance documented

+3–5% Recovery Gain

Delta between pre-install manual sort output vs. ρ-MATRIQS™ sorted output, same input feed · Weighed at certified weighbridge · Two sites, different material mixes

<20ms End-to-End

Sensor read (3–5ms) + feature extraction (&lt;2ms) + inference (&lt;8ms) + actuation (&lt;5ms). Measured at belt speed on production line — not lab simulation.

72hr Install

From first tool on site to first live classification on client material · Includes calibration on client's own feed — not factory defaults

Full pilot methodology and raw data summary available on request under NDA. Client throughput numbers not published publicly — request during demo call. Request Data Pack →
Technology Comparison

Where Conventional Sorting Falls Short

Optical and ECS systems perform well on clean, single-material streams. ρ-MATRIQS™ addresses the classification problem on mixed, variable, real-world material where single-signal systems produce unacceptable error rates.

Capability Optical / NIR ECS ρ-MATRIQS™
Alloy-level identification (Cu vs Cu-Zn vs Cu-Sn) ✗ Visual only — surface colour only ✗ Conductivity only ✓ LIBS + XRT composition fusion
Dirty / oxidised / real-world scrap ✗ Fails on oxidised surfaces ✓ Works through oxidation ✓ Robust across contamination levels
Multi-metal in single pass ⚠ Single output stream ✗ Binary only — pass or reject ✓ Cu / Al / Zn / reject simultaneously
2–150mm particle range ⚠ Narrow — clean, uniform pieces only ⚠ Limited to specific size bands ✓ Full shredder output range
Confidence score per decision ✗ No — fixed threshold only ✗ No — hardware separation only ✓ 0–100% score, operator-configurable
Compliance traceability ✗ None — no data recorded ✗ None — no data recorded ✓ Auto-recorded per sort decision
Installs on existing belt, no shutdown ✗ New system, civil works required ✗ New system, process change ✓ Retrofit — mounts above existing belt
When conventional systems are sufficient: Single-material streams, throughput below 30 TPD, or operations without compliance requirements — we will tell you this directly if it describes your plant.

Not sure which applies to your line? Send throughput and material type. Fit or no-fit answer before any demo is scheduled.

Check My Fit →
System Architecture

The Complete 6-Layer Processing Stack

From physical material chaos to sorted, value-captured output. Each layer is defined, specified, and failure-handled. No layer hides errors from the next.

L1
Material Chaos Layer
Entry Point

Mixed scrap stream with size/density/composition variability. Chaotic particle distribution on belt. This is where the yield gap originates — uncontrolled distribution creates sorting error before any sensor is active.

Chaotic distribution No pre-sort required 80–800 TPD capacity Belt width: 600–2400 mm
L2
Multi-Sensor Acquisition
Active

Seven sensing modalities sample every particle at belt speed. All sensor data is timestamped and position-synced via belt encoder. Raw signals are pre-processed at the edge node — no cloud upload.

Hyperspectral: 400–2500 nm RGB optical: 4MP @ 120fps LIBS pulse: 1–2ms XRT depth: up to 120mm 15,000 pts/sec aggregate IP69K dust/water rated
L3
Feature Extraction Engine
Active

Raw sensor signals are transformed into feature vectors per particle. The critical missing layer in most AI sorting systems — without it, classification is pattern-matching on noise.

128-dim spectral vector (PCA-reduced) Density proxy: acoustic + volumetric Shape/surface morphology tensor Oxide/contamination spectral markers Particle overlap detection Feature computation: <2ms
L4
Stochastic Inference Engine
Active

Bayesian classification with mass-balance constraint. The model maintains Σ(input) ≈ Σ(classified output) — preventing grade drift over a shift. Output per particle: class label + confidence score + economic value weight.

Bayesian P(material|signal) Mass-balance constraint Confidence: 92–97% Economic value weighting Model size: <180MB on-device Inference: <8ms per particle
L5
Real-Time Actuation
Active

Decision signal fires to air jet or mechanical diverter. Actuation only triggers when P(material) > configurable threshold AND economic value exceeds cut-off. Belt encoder drives position tracking — jet fires at the exact coordinate.

Decision latency: <10ms Position tracking: encoder-based Air jet: 4–6 bar compressed air Configurable confidence threshold Belt speed: 0.5–3.5 m/s Fail-safe: pass-through on fault
L6
Yield Feedback Loop
Active

Sorted output is weighed and composition-sampled. Recovery % is computed per shift. Delta vs expected is fed back to recalibrate classification thresholds. Every 24h cycle improves system accuracy. Drift correction is automatic.

24h recalibration cycle OTA model updates Recovery delta tracking Shift-level audit log CPCB-compliant event log Remote monitoring: included
Layer 3 Deep Dive

Feature Extraction — The Missing Layer

Most AI sorting systems go Sensor → AI → Output. This is why they produce high error rates on real-world oxidised scrap. Feature extraction converts raw sensor signals into physically-grounded, noise-corrected feature vectors before classification runs.

128-dim Spectral Feature Vector

Hyperspectral data decomposed via PCA into material-specific absorption/reflection bands. Noise-corrected before classification. Each particle gets a 128-dimensional fingerprint cross-matched against our calibrated material library.

Acoustic-Optical Density Proxy

Acoustic impact sensing combined with TOF volumetric estimation yields density proxy without direct weighing. Separates ferrous fines from dense non-ferrous chunks before Bayesian classification runs.

Morphology Tensor (Shape + Surface)

Edge detection + surface texture analysis from RGB data. Differentiates wire/cable from sheet/chunk morphology. Form factor correlates with alloy grade in ASR streams — this layer captures that signal.

Sub-Surface Oxide Compensation

Spectral bands at 1400–1700nm detect oxide layers and surface contamination. Classification model compensates — sort decision is based on sub-surface material signature, not surface state.

Layer 4 Deep Dive

Stochastic Inference Engine

Bayesian classification with mass-balance constraint. Every output has an explicit confidence score. Low-confidence particles pass through — they are never contaminated into high-value fractions.

Mass-Balance Constraint

Every sort session maintains Σ(input) ≈ Σ(classified output). If grade drift is detected across a shift — the model recalibrates priors automatically. This prevents systematic under/over-sorting of any specific material class.

Confidence Threshold Logic

Default confidence threshold: 0.78. Configurable per material class. When confidence is below threshold, particle passes through — not ejected. False positive rate is bounded; fraction contamination is controlled.

System Failure Handling

Every Failure Mode Is Handled

A system that only documents what happens when everything works is not an industrial system. The following failure modes are specified, tested, and handled at the hardware and software layer.

Failure Mode System Response Belt Stops?
Sensor dropout
Handled — degraded mode
Fallback weighting — remaining sensors redistribute confidence. No blind classification. Never
Low-confidence read
Handled — no belt stop
Particle passes through unejected. Zero contamination risk. Error rate bounded within ±2%. Never
Air jet failure
Handled — degraded mode
Automatic bypass mode. Belt continues. Fault logged and flagged to HMI within 200ms. Never
Encoder mismatch
Handled — no belt stop
Sync recalibration in <200ms. Position tracking restored without belt stop. Never
Edge compute fault
Handled — no belt stop
Redundant node takeover. Watchdog failover <200ms. Belt-stop never triggered by AI state. Never
Network/OTA loss
Handled — no belt stop
Last-known-good model held on-device. System continues fully air-gapped. Resync on reconnect. Never
Layer 6 Deep Dive

Closed-Loop Yield Optimisation

Most sorting systems stop at actuation. ρ-MATRIQS™ measures the output, computes the recovery delta, and recalibrates the model — every 24 hours, automatically.

01
Sort Event

Air jet fires. Particle routed to fraction bin.

02
Output Weighing

Fraction bins weighed at shift end.

03
Recovery %

Sorted recovery vs input mass computed.

04
Delta vs Expected

Compare to model prediction.

05
Model Recalibration

Threshold + prior adjustment via OTA.

06
Next Shift

Improved accuracy from cycle N+1.

Integration Reference

Deployment Spec, Latency Breakdown & Data Output Schema

What a plant engineer needs before a site visit. These are not marketing estimates — they are the parameters your DCS team will ask for.

Deployment Spec Snapshot
Power 3-phase, 415V / 50Hz Compressed Air 4–6 bar · plant supply Mounting 770mm standoff · top-frame Network Ethernet · static IP required Compute Edge GPU · fanless · IP-rated Belt Width 600–2400mm Belt Speed 0.5–3.5 m/s Particle Range 2–150mm Throughput 80–800 TPD IP Rating IP69K (all sensors)
Latency Breakdown
// Full end-to-end per particle Sensor read 3–5 ms Feature extraction <2 ms Bayesian inference <8 ms Actuator signal <5 ms ────────── TOTAL <20 ms // Measured at belt speed on // production line. Not lab sim.
Data Output Schema
{ "particle_id": 240841, "material": "Cu", "grade": "Grade-A", "confidence": 0.984, "density_gcm3": 8.91, "spectral_vector_dim": 128, "decision": "eject_high_value", "belt_position_mm": 1247, "timestamp": "2026-04-11T14:22:03Z" }
Platform Architecture

Designed to Fit Your Enterprise Stack

Three-layer intelligence architecture — edge, plant, enterprise. Connects to existing DCS, SCADA, ERP via standard industrial protocols. No rip-and-replace. No PLC rewrite.

Layer 1 — Edge
On-Belt Intelligence
Runs at plant floor. No cloud dependency. Fully air-gapped capable.
<20ms
End-to-end latency
Multi-Sensor Array
7 modalities · parallel read · synchronized
Edge AI Processor
Fanless GPU · IP-rated enclosure · no cloud
Fusion Engine
128-dim feature merge · confidence scoring
Sort Actuator Signal
4–6 bar air jet · PLC sync · &lt;10ms fire
Self-Calibration
Continuous drift correction · no shutdown
Failsafe Module
Redundant node · watchdog &lt;200ms · belt-safe
OPC-UA — cycle time 10ms · loss-tolerant
Modbus TCP — 100ms max latency
Profinet RT — &lt;1ms IRT mode
MQTT — offline buffer 72hr
REST API — static IP required
Layer 2 — Plant Core
On-Premise Server
Plant-level aggregation. Historian + model hub. SCADA / DCS bridge.
Shift Reporting
Automated grade + throughput logs per shift
Model Management
Versioned AI models · rollback capability
Data Historian
Every particle decision stored + queryable
SCADA / DCS Bridge
Native write-back to existing control systems
HMI Dashboard
Plant-floor operator interface · alert routing
Audit Trail
Tamper-evident log · CPCB-ready exports
SAP / Oracle ERP connector
ISO 27001 encrypted transit
Role-based access control
Layer 3 — Enterprise
Multi-Site Command
Cloud or private cloud. Boardroom-ready reporting. ESG + EPR exports.
ERP Integration
Material grades + weights pushed to SAP / Oracle in real time
Multi-Plant Dashboard
Compare recovery rates + yield across all sites
ESG & GHG Reporting
GHG Protocol Scope 1/2 outputs · audit-ready exports
EPR Compliance
CPCB-aligned material traceability records
BI / Analytics
Power BI / Tableau connector · raw data export
Role Permissions
Operator → Plant Head → CXO access tiers
🔗 Integration Guarantee
No PLC rewrite required — standard industrial protocol integration only
No cloud dependency — edge-first, air-gapped capable at the belt
No rip-and-replace — runs alongside your existing SCADA or DCS
Data sovereignty — all particle data stays on your plant server by default
Mathematical Foundation

Physics-Led — Not a Black Box

Every decision is traceable to underlying physics equations. Not statistical pattern-matching on opaque training data — measurable physical properties, corrected for real-world conditions, combined with quantified uncertainty.

Physics-Based Density Modelling

Material density corrected for moisture, temperature drift (±0.3°C), vibration, and void space in real time. The output reflects actual material composition — not environmental signal.

Probabilistic Sensor Fusion

Each sensor's reading is weighted by its reliability for that material type. Uncertain or conflicting readings are detected, flagged, and excluded from the classification decision.

Uncertainty-Aware Decisions

Every sort decision carries a confidence score. Particles below threshold pass through — not ejected. Error rate bounded within ±2% under mixed-material real-world conditions.

Metallurgical Process Models

Industry-specific models for slag chemistry, alloy compositions, ore mineralogy, and recycled material grades. Decisions are calibrated for your downstream process — not lab defaults.

Real-Time Optimisation

Continuously optimises for your configured objective — maximum recovery, a target output grade, minimum energy per tonne, or lowest CO₂ intensity. Configurable per campaign.

IP-Protected Implementation

Algorithms, calibration parameters, and sensor orchestration logic protected under NDA. The science is documented here. The performance advantage is in the implementation depth.

Want the technical depth? Full sensor specifications, fusion methodology, and calibration protocols available on request under NDA.

Request NDA Access →
Industrial Reliability

Built for the Harshest Environments

Shredder halls. Open-air yards. Smelter adjacencies. ρ-MATRIQS™ is specified for conditions where consumer-grade equipment fails within weeks.

🛡 Plant Continuity Guarantee

If ρ-MATRIQS™ goes offline for any reason — power fault, sensor error, network loss — your belt keeps running. The system fails to pass-through, not to stop. Zero production hours lost due to ρ-MATRIQS™ system state.

Watchdog failover <200ms Redundant edge compute node Belt stop never triggered by AI fault Remote diagnostics 24/7

IP69K Rated

High-pressure washdown, dust, steam, chemical exposure. Continuous operation in smelters, shredder halls, and open-air yards. No additional protective enclosure required.

Temperature Compensated

All sensor readings corrected for temperature, moisture, and vibration automatically. ±0.3°C resolution. Accurate across full shift — even as plant environment changes.

Self-Calibrating

System monitors its own drift and recalibrates in background. No production stop for calibration runs. No manual tuning between shifts or material changes.

Plug-and-Play DCS Integration

Connects to existing DCS, SCADA, or PLC via OPC-UA, Modbus TCP, or Profinet. Operational within 72 hours of installation. No PLC rewrite required.

Operating Range: −10°C to 85°C

Calibrated for Indian industrial conditions — from cold startup to peak summer smelter adjacency. No warm-up period. No performance degradation at temperature extremes.

OTA Model Updates

AI model improvements delivered over-the-air during scheduled maintenance windows. Accuracy improves over time as system accumulates data from your specific material feed.

Compliance Without Extra Work

Every Classification
Is a Compliance Record

No separate data entry. No year-end audit scramble. No consultant to compile your CPCB return. Records are generated automatically on every particle decision.

Replaces manual audit prep — typically 2–4 weeks per year of staff time. Reduces compliance penalty exposure. Removes third-party EPR reporting consultants.
  • CPCB Annual Return data — auto-generated from daily logs
  • EPR certificate per sorted material lot, auto-issued
  • Full material traceability — intake weight to output grade
  • CO₂ tracking per stream, per tonne, per day
View Full Compliance Details →
CPCB — E-Waste Rules 2022
Automated data generation for Annual Return
✓ Supported
EPR — Extended Producer Responsibility
Chain-of-custody per lot, target tracking
✓ Integrated
MoM PRISM 5.0
Critical mineral audit trail
✓ Aligned
Panchamrit / Net Zero 2070
Real-time CO₂ tracking per tonne
✓ Tracked
Ready to Evaluate

Download the Integration Schema

Full integration schema including PLC interface spec, I/O mapping, mounting requirements, and edge compute footprint. Available immediately on request — no demo required to access the engineering documentation.

Industrial deployment ready · Built for Indian conditions · DPIIT Recognised