Drop gauge locations from a CSV, the bridge mesh, and the live telemetry feed on one canvas, calibrate raw microstrain to stress, and set per-member thresholds. You get a color-mapped stress twin that repaints as trucks cross and an alert log you can export the moment a gauge exceeds its limit.
A structural-health rig on a bridge produces exactly one thing operators can't use directly: a firehose of microstrain numbers from a few dozen gauges, streaming over REST. Somewhere there's a CSV of where each gauge is bonded and a glTF mesh of the structure from the design model, but the numbers and the geometry never meet. When a gauge spikes, the on-call engineer is reading a row in a table, not looking at the girder.
LSD binds the three sources — gauge map, mesh, and live feed — into one canvas so the stress lives on the structure instead of in a spreadsheet. The mesh isn't a separate CAD viewer; the gauges are entities placed on the structure, and every reading flows to the member it's bonded to. Calibration and thresholding are live nodes, so the limits you set are things you watch take effect, not constants buried in a script. Cached intermediates mean a fresh telemetry batch repaints the twin and re-scans for exceedances without touching the calibration upstream.
Two things come off the same canvas: a color-mapped 3D twin that repaints as load crosses the span, and an alert log — one CSV row per exceedance window with gauge, timestamp, peak stress, and duration — ready to hand to the maintenance team. Point it at the next bridge by swapping the gauge CSV and the mesh.
Drag the gauge-location CSV onto the canvas and a @load node lists all 48 gauges — ID, position along the deck, and mounting face. LSD plots them as points in the 3D viewer straight away. Each gauge is now an entity waiting for its mesh and its signal.
Drop the bridge's glTF export next to it and the structure renders around the floating gauge points. Line the two up and the gauges settle onto the girders and deck where they are actually bonded. Now every reading has a place to land on the geometry.
Point a @load node at the telemetry REST endpoint and set it to poll every few seconds. Raw microstrain per gauge streams in as live entities, and the node preview ticks as traffic crosses the span. That stream is the twin's heartbeat.
Chain a @shape calibration node and apply each gauge's gauge-factor and zero offset from the CSV. Raw counts become engineering stress in MPa, and the preview replots the corrected values live. Nudge a zero offset and the whole channel re-baselines instantly.
Add a @shape threshold node and drag the caution and alarm limits per member. LSD flags every window where a gauge crosses its limit and lists start, peak, and duration. Because the node is live, tightening a limit re-scans the whole history in place.
Wire the calibrated stress into a @deliver node that colors the mesh green-to-red by live load — the bridge repaints as each axle rolls across. Set an alert-log delivery that writes every exceedance window to CSV with gauge, time, and peak. Drop a new telemetry batch and both rebuild from cached intermediates.
Place 48 gauges from CSV, load the bridge mesh, and stream live strain telemetry onto one canvas.
Convert raw microstrain to engineering stress and flag every window where a gauge crosses its limit.
Color the bridge by live stress and export an alert log of every exceedance.
Join a live meter feed to 85 campus building meshes, aggregate it hourly, and paint a 3D heat-map that repaints as energy use shifts, plus a weekly report.
Model post-closure pit-lake rebound in LSD — krige borehole heads against a NetCDF recharge grid and deliver a live 3D drawdown model plus report.
Validate 63 LAS drillhole logs against collar surveys, krige a lithology block model, and export one glTF the whole team can open.
Build churn features from Postgres events and Parquet snapshots, catch a leaky window visually, and score the holdout with ONNX — on one canvas.
Score a million-row Parquet batch with an ONNX model — training-identical normalization, live previews, scored Parquet and metrics out.
Turn raw LAS/LAZ sweeps from a mobile robot into a nav-ready occupancy grid and 3D map — registration to export with zero scripts.
Sync CSV sensor logs with live REST telemetry, flag outliers and dropouts, and score every robot pass/fail before the field trial.
Turn folders of line-scan images and a label CSV into an ONNX defect-segmentation pipeline with overlay QA and a per-coil defect report.
Turn GeoTIFF orthomosaics into a stitched land-cover raster with per-class area stats, using tiled ONNX segmentation you can preview at every step.
Align CMM measurement points to a nominal CAD mesh, compute point-to-surface deviation, and export a color-mapped glTF model with a pass/fail report.
Resample a week of machine sensor logs, baseline each tag, and flag drift and step changes on a live dashboard with a ranked maintenance shortlist.
Turn a CT DICOM series into an ONNX organ segmentation you QA in 3D, then export an annotated volume and a per-organ volumetrics report.
Drop the bridge's glTF export next to it and the structure renders around the floating gauge points. Line the two up and the gauges settle onto the girders and deck where they are actually bonded. Now every reading has a place to land on the geometry.
Chain a @shape calibration node and apply each gauge's gauge-factor and zero offset from the CSV. Raw counts become engineering stress in MPa, and the preview replots the corrected values live. Nudge a zero offset and the whole channel re-baselines instantly.
Wire the calibrated stress into a @deliver node that colors the mesh green-to-red by live load — the bridge repaints as each axle rolls across. Set an alert-log delivery that writes every exceedance window to CSV with gauge, time, and peak. Drop a new telemetry batch and both rebuild from cached intermediates.