← Platform Overview

AI & Analytics

Anomaly detection that connects alerts to action

Multi-algorithm anomaly detection for industrial assets, process equipment, and utility systems. TwinEdge connects abnormal signals to asset context, governed recommendations, work orders, field evidence, and replayable audit trails.

SENSOR WAVEFORMVIB_X [mm/s]+3σ-3σTHRESHOLD: 4.5 mm/sCURRENT: 2.7 mm/sISOLATION FOREST??AN?NNANOMALY SCORE1.00.50.0THRESH0.15NORMALConfidence35%CROSS-SENSOR CORRELATIONVIBVIBTEMPTEMPFLOWFLOWPRESPRES1.000.650.140.490.731.000.270.440.480.071.000.020.030.330.251.00ALGORITHM CONSENSUSIsolation Forest0.12Autoencoder0.18SPC / CUSUM0.08One-Class SVM0.22Spectral Res.0.10CONSENSUS: NORMAL OPERATIONALERT TIMELINELAST 24 HOURS00:0002:0004:0006:0008:0010:0012:0014:0016:0018:0020:0022:0024:00WARNCRITWARNCRITWARNanomaly-engine@twinedge:~$ watch --sensors=4 --interval=1sVIB_X2.1 mm/sTEMP67.0 °CFLOW42.0 L/sPRES3.2 bar[00:00:00]ALL CLEAR -- 0/5 algorithms flaggedlatency: 22ms

Downtime reduction proof

Anomalies matter when they turn into the right operational response.

TwinEdge connects anomaly detection to DataOps context, digital twin state, governed agents, AssetOps EAM, Field execution, API/MCP products, and audit evidence so teams do not stop at another alarm.

5

Detection methods

Statistical, ML, spectral, sequence, and correlation patterns.

Context

Before alert

Signals are interpreted with asset, process, history, and rule context.

Work

After insight

Recommendations can flow into EAM, Field, reports, and APIs.

Anomaly response boardTwinEdge connects anomaly detection to DataOps context, digital twin state, governed agents, AssetOps EAM, Field execution, API/MCP products, and audit evidence so teams do not stop at another alarm.Anomaly response boardEvidence attachedINPUTSVibrationSpectral and trendTemperatureDrift and limitsPressureEnvelope changeFlowProcess impactHistoryWork and eventsTelemetry, baselines, asset state, work history, operating limits, and field contextPRODUCT LAYERSignalsDetectBaselinesCompareAgentsExplainAssetOpsWorkFieldVerifyReportsReplayOne signal, full contextOUTCOME DASHBOARDResponse readinessConfirmed anomalies become recommendations, work drafts, field tasks, and evidenceEvery flagged anomaly carries its physics evidence into recommendations, work, and replay — not just another red light.

Detection Algorithms

Five algorithms running in parallel, each with different strengths.

AlgorithmTypeStrengthLatency
Isolation ForestUnsupervisedCatches multi-dimensional outliers across correlated sensor groups<50ms
AutoencoderDeep LearningLearns complex normal operating patterns; detects subtle deviations<80ms
Statistical Process ControlStatisticalCUSUM and EWMA charts for gradual drift detection over time<5ms
One-Class SVMSemi-SupervisedEffective with limited training data; good for rare equipment types<30ms
Spectral ResidualFrequency DomainDetects periodic anomalies and unexpected frequency components<20ms

Detection Timeline

0hNormalAll sensors within baseline. Models continuously updating normal operating profile.
-6hEarly WarningAutoencoder reconstruction error rises 2.3 sigma. Cross-sensor correlation shifts detected.
-2hAnomaly ConfirmedIsolation Forest and SPC both flag. Multi-algorithm consensus triggers formal anomaly alert.
-1hAlert DispatchedAlert routed to operations team with root cause hypothesis, affected sensors, and recommended action.
0hThreshold AlarmTraditional alarm fires. But your team already diagnosed the issue 6 hours earlier.

Core Capabilities

Earlier Warning Window

Detect changes before fixed threshold alarms where signal quality, history, and deployment conditions support early detection.

Cross-Sensor Correlation

Analyze relationships between vibration, temperature, pressure, and flow simultaneously. Catch issues no single sensor reveals.

Adaptive Baselines

Models retrain continuously on recent data. Seasonal changes, load variations, and process shifts are learned automatically.

Consensus Scoring

Multiple algorithms and operating context can be used before an anomaly becomes a recommendation, work draft, or alert.

Turn abnormal behavior into a response your team can trust.

Hours of early warning instead of seconds. Multi-algorithm consensus instead of single-threshold guessing.