Read cofounder Muhammad Umar's memo, Compression and Reinflation
CodeNinja AtomsUnited StatesSaudi ArabiaPakistan

Sector · Heavy industry and construction

Physical AI for heavy industry and construction

Mills, factories and building sites produce counts, alarms and progress data in many systems, and each one sees only part of the operation. These are the questions engineers ask first, answered from 5 published CodeNinja Atoms reference architectures.

  1. What does a physical AI system for heavy industry and construction look like?
  2. Which AI models can a heavy industry and construction operator run on its own hardware?
  3. How much compute and hardware does AI in heavy industry and construction need?
  4. Is it cheaper to own AI hardware or rent cloud GPUs in heavy industry and construction?
  5. What ontology or object model does a heavy industry and construction AI system need?
  6. Who approves the decisions an AI system makes in heavy industry and construction?

What does a physical AI system for heavy industry and construction look like?

A complete physical AI design for heavy industry and construction names what to sense, which existing systems to join, the object model that joins them, the models and hardware, the three-year cost and the person who approves every action. CodeNinja Atoms has published 5 such reference architectures for heavy industry and construction, each free to reuse under CC BY 4.0.

DesignCountryWhat it does
Structure Phase WatchSaudi Arabiaone live model of a construction site's structure phase that forecasts schedule slips three days out and shows safety breaches as they happen, on the contractor's own hardware inside the Kingdom.
Steel Count LedgerPakistancameras and a GPU industrial PC at every casting strand and cooling bed count billets, ingots, rebars and girders as they are made, publish the counts through a one-way link into one record the authority owns, and let revenue officers reconcile counted against declared production.
Factory Fire WatchSaudi Arabialive, read-only visibility of fire alarm panels, fire pumps, fire water tanks and energy meters across an operator's highest-risk factories, read through contacts, PLC inputs and LoRaWAN into an IoT platform hosted in Saudi Arabia, with never a write path into certified life-safety equipment.
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaSaudi ArabiaAn open reference architecture for system design in physical AI, built for a cement company in Saudi Arabia that runs several integrated plants, each with a preheater and precalciner kiln line of several thousand tonnes of clinker a day, where owning the inference node that runs it costs about 570,000 US dollars over three years. When a new alternative fuel lot drifts the burning zone over a shift, the design joins the streaming tags, the fuel lot, the raw meal, the laboratory results, the shell scan and the shift log into one argument, so the control room operator sees the likely cause, the recovery moves that worked in matching past upsets and the setpoint adjustments with their expected effect on thermal energy per tonne, and every confirmed outcome is kept as the memory the next shift reads. The models run entirely on the company's own hardware in the country under the national energy efficiency program's reporting, the environmental permit's emission limits, the national operational technology cybersecurity controls and the company's own management of change procedure.
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanPakistanAn open industrial AI reference architecture for system design in physical AI, built for a fertilizer manufacturer in Pakistan whose ammonia and urea complex, designed to run steadily between annual turnarounds, has been stopped and restarted repeatedly in 2026 by gas supply suspensions, where owning the inference node that runs it costs about 572,000 US dollars over three years. When the gas comes back after a two week suspension, the design joins the historian, the work orders, the inspection and corrosion records, the vibration readings and the shift log into one story per piece of equipment, so the restart agent drafts the plan from the last three restarts, the synthesis compressor's seal is flagged for inspection before the start, and the shift superintendent confirms every step. The models run entirely on the operator's own hardware inside the country, behind a hardware data diode that makes the read of the control system physically one way.

Which AI models can a heavy industry and construction operator run on its own hardware?

Each published heavy industry and construction design names its models and why, and every model is open-weight or no model is used at all, so the operator can run it on hardware it owns.

DesignModels
Structure Phase Watch5 self-hosted open models: GLM 5.3 (reasoning), Chronos-2 (forecasting), BGE-M3 (multilingual retrieval), RF-DETR (vision), Roboflow trackers
Steel Count Ledger3 self-hosted open models: RF-DETR (detection, fine-tuned per product type and mill), Roboflow trackers (identity across camera fields), GLM 5.3 (compliance work surface)
Factory Fire WatchOne: IBM Granite Tiny Time Mixers (TTM-R2), about 0.85 million parameters, Apache-2.0, on CPU inside the platform; threshold evaluation on the safety path is rule logic
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaGLM 5.3 (GLM-5.3 bespoke licence, 753B at FP8) for cause drafting, handover drafting, ontology maintenance and the command centre's cited answers; Chronos-2 (Apache-2.0) forecasting the stable band on the streaming tags to raise the drift trigger; BGE-M3 (MIT) embedding past upsets, shift logs and maintenance history in Arabic and English; no third party model service, nothing trained into weights
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanGLM 5.3 (GLM-5.3 bespoke licence, 753B at FP8) for the restart, cycle damage and turnaround drafting agents and the cited conversational interface; Chronos-2 (Apache-2.0) forecasting historian tags and thermal cycle stress residuals on the site server; BGE-M3 (MIT) embedding work orders, findings, readings and shift log entries for cited retrieval; vision models on Frigate NVR and ONNX Runtime for steam plume, flange leak, operator, scaffold and fire or smoke; no third party model service, nothing trained into weights
DesignChoiceWhat was pickedWhy
Structure Phase WatchDetection andRF-DETR fine tuned on site footageApache-2.0 from package to checkpoints;
Structure Phase Watchsegmentationthe JV owns and hardens weights apackaged safety product would rent
Structure Phase WatchTrackingRoboflow trackers, ByteTrack classApache-2.0 motion only identity without the AGPL exposure of the BoxMOT collection
Structure Phase WatchForecastingChronos-2 universal forecastingApache-2.0 with no field of use restriction; weights may be held, fine tuned and redistributed on site
Structure Phase WatchEmbeddingBGE-M3 hybrid multilingual embedderMIT with no field of use restriction; multilingual retrieval across a workforce tagged by language
Structure Phase WatchFrontierOne node of eight 141 GB HBM GPUs (H2001,128 GB holds the 904 GB of FP8 weights,
Structure Phase Watchhardwareclass)KV cache and activations with headroom for sessions
Structure Phase WatchEdge compute powered enclosuresJetson Orin industrial edge class in solar coverage at gates and laydown areasDetection survives patchy private LTE
Structure Phase WatchSite inferenceEight L40S class PCIe GPUs, 48 GB classForecasting, embedding and breach
Structure Phase Watchserveraggregation on JV hardware in the site dataroom
Structure Phase WatchCamera class Profile S/T; thermal at 9 Hz or lessFixed visible cameras, Frigate ready ONVIF a reuse survey holds; the 9 Hz ceiling keepsThe existing 38 fixed cameras serve where US origin thermal units outside the 6A003.b.4.b export license to Saudi Arabia
Structure Phase WatchSizing rules gain, with a cleaning interval as a design parameterEnclosure thermal budget including solar accuracy problems unless the thermal budget is engineered firstDust, glare and 50 C summer ambient fail as
Structure Phase WatchSensing haulage GPS for 40 tracked trucks plus proposed trackers for 20 mixers, weather station, biometric turnstiles, batch plant SCADACrane anti-collision logs, crawler telematics, crews actually did, joined through the adaptersGround truth of what cranes, trucks and
Structure Phase WatchPattern recommendation with a named approver PA R T I I I · C H A P T E R 9 Shadow Mode Comes Before Any Flag Is Trusted Three phases with counted items and hard gates prove the slip forecast and the breach detection against the record before anyone acts on a flag. Chapter 8 fixed the models, their licenses and the hardware classes they run on. This chapter sets out how the design earns the right to be trusted: three phases with counted items, workstreams and hard exit gates, so the slip forecast and the breach detection are proven against the record before anyone acts on a flag, and the work can be stopped cheaply if a gate does not hold.Adapter tier, one object model, never directly, and every re-sequencingEvery source enters through an adapter, output stays a recommendation a person approves
Steel Count LedgerDetection modelRF-DETR, Nano to Large checkpoints, fine-tuned per product type and per millApache-2.0 from package to checkpoints; the operator owns and hardens the weights that count its product
Steel Count LedgerTrackingRoboflow trackers, OC-SORT and ByteTrack classApache-2.0; holds identity across frames so one billet crossing two camera fields counts once
Steel Count LedgerWork surface modelGLM 5.3, 753B parameter mixture of experts, FP8Frontier open weights for the operator's compliance agents; 904 GB against one node of 1,128 GB; bespoke license allows commercial use, fine-tuning and redistribution
Steel Count LedgerEdge computeGPU-accelerated industrial PC class, sealed, wide temperature, cooled enclosureSized from stream decode plus inference with headroom, hardened for mill heat, dust and electromagnetic interference
Steel Count LedgerFrontier nodeOne node of eight 141 GB HBM GPUs, H200 class, in a dedicated data centerThe class is export controlled for Pakistan, so the node runs where an export license naming the end user holds, checked at the phase one licensing checkpoint
Steel Count LedgerCamerasIP66/67 HDR industrial camera class, chosen from the pixel-density table per installation point; thermal, ECCN 6A003, only where hot billets blind visible camerasSurvives the mill environment while meeting country legality per model
Steel Count LedgerEnclosures and powerClosed-loop cooled enclosures, vibration-damping mounts, surge protection, UPS with clean shutdown under NUT monitoringA failing cooler is caught before the industrial PC cooks
Steel Count LedgerSite networkingHardened PoE industrial switches, VPN tunnel, IEC 62443 zoningThe camera zone stays segmented from mill control
Steel Count LedgerTime synchronizationPTP grandmaster with GNSS and OCXOCount events reconcile across systems only when every clock agrees
Factory Fire WatchModelIBM Granite Tiny Time Mixers TTM-R2, about 0.85M parameters, FP32, about 0.003 GBCPU-only forecaster inside the operator's platform hosted in Saudi Arabia; Apache-2.0 with no field of use restriction leaves the artifact owned outright
Factory Fire WatchHardware classRugged enclosure, mounting, power and UPS with NUT-class clean shutdown; IP ratings per IEC 60529; NEMA enclosure types; SABER conformityOutdoor exposure to dust, direct sun and hose washing, with certification lead time built into the bill of materials
Factory Fire WatchHardware classFanless hardened industrial switches; copper-versus-fibre run selectionFibre between buildings and near the high-current systems being metered; copper for short powered drops
Factory Fire WatchSensingFACP general alarm status contacts; fire pump controller PLC IOs and relaysRead-only interface into certified life-safety equipment, never a write path
Factory Fire WatchSensingSubmersible tank level transmitters; CT energy meters; LoRaWAN field sensors with store-and-forward gatewaysThe four monitored point families: panel status, pump status, water level and energy
Factory Fire WatchComputeNone purchased; CPU inside the operator's existing IoT platform; field gateways carry no model runtimeThe requirement asks for no server or GPU, and compute that is not needed at the extremity is not deployed there
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaReasoning modelGLM 5.3, 753 billion parameters filed, FP8 (753 GB of weights), GLM-5.3 bespoke licence, served on vLLM on one node in the company's own data centre in Saudi ArabiaNamed in the requirement; the licence allows commercial use, fine tuning and redistribution, and its model as a service trigger stays inapplicable to internal advisory use, so the company holds the weights; carries cause drafting, shift handover drafting, ontology maintenance and the command centre's cited answers
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaForecast modelChronos-2, about 0.24 GB at 16 bit (0.48 GB at 32 bit), Apache-2.0, on the plant GPU serverZero shot multivariate forecasting with covariates on the streaming tags; forecasts the stable band and its residuals are thresholded to raise the drift trigger; Apache-2.0 imposes nothing beyond attribution and no fine tuning is planned
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaEmbedding modelBGE-M3, about 1.1 GB at FP16 (2.27 GB at float32, 0.6 GB at 8 bit), MIT, on the plant GPU serverOne pass retrieves dense, sparse and multi vector across Arabic and English shift logs and maintenance part numbers; embeds past upsets, shift logs and maintenance history for the reasoning tier; MIT licence held outright
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaFrontier hardware141 GB HBM GPU class, eight accelerators per node, one node (1,128 GB)Holds GLM 5.3's 753 GB of FP8 weights plus the 1.2 planning factor (904 GB) on one node with 375 GB beside the weights for KV cache and activations; held at one node, with two nodes of the 80 GB class as the fallback shape if the export licence position changes it
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaSizing ruleGLM 5.3 node count by GPU classSizes the frontier node from the filed parameter count before any hardware order
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaPlant GPU server classPlant GPU server, one or two PCIe cards, no high bandwidth memory nodeChronos-2 and BGE-M3 fit on a single card with room to spare, so no further frontier hardware is bought for them; the paper does not size this server
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaEdge compute classIndustrial octa core SoC edge unit, 6 TOPS NPU, sealed fanless enclosure, served by ONNX RuntimeHolds roughly 33 C of margin at the 52 C record ambient before solar gain; restarts and resynchronises against the plant time source after a power loss
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaBoundary equipmentLidi with Eurydice one-way transfer stack (data diode class)Reads leave the control zone for analysis and no return path exists to block; fails closed: the adapters buffer and the agents pause while the kiln's control path is untouched
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaServing runtimevLLM for GLM 5.3 and ONNX Runtime at the edgeServes the FP8 weights within the KV cache ceiling the sizing reserves; the edge unit serves its models under ONNX Runtime
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaRegistryHarbor, air gapped offline artifact and model registryContainers and models are staged
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaSensingStreaming DCS tag stream of hundreds of variables, clinker quality data, fuel and alternative fuel feed records, the shell scan profile, shift log and production figuresExisting instrumentation only, read as it exists; no new field devices and no camera system
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaPattern: memoryMemory loops over confirmed outcomes, nothing trained into weightsThe requirement forbids training on the fly; every confirmed cause, accepted recovery and shift outcome is kept and read before the next draft, and a moving model would invalidate the frozen baseline
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaPattern: proofControlled on and off comparison of thermal energy per tonne of clinker on the same lineThe sector precedent read 4.1 percent in a continuous month and 2.2 percent under a controlled comparison, so the phase one gate reads the comparison only, never the headline month
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaPattern: approvalsShadow mode before any draft is approved, the advisory layer treated as a process change under the plant's own hazard study methodsDrafts run first in shadow, every draft names its cause and expected effect, and the operator's confirmation or rejection is the recorded outcome the memory compounds on
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaPattern: boundaryThe company's own hardware in its own plant and data centre in Saudi Arabia; one way inbound, read only, no write path into the control systemThe national operational technology cybersecurity controls by facility criticality level and the company's own rule that nothing about the plants leaves the country
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanReasoning modelGLM 5.3, filed at 753 billion parameters, FP8 (753 GB of weights; about 756 GB as published), GLM-5.3 bespoke licence, served on vLLM on one node of eight 141 GB class GPUs on the operator's own dedicated in country hardware in PakistanThe model the operator's own requirement names; frontier class at or above the 300 billion threshold; carries the restart, cycle damage and turnaround drafting agents and the cited conversational interface; the licence allows commercial use, fine tuning and redistribution and its managed access trigger does not bind internal use
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanForecast modelChronos-2, Apache-2.0, FP32, about 0.48 GB at 32 bit as published and about 0.24 GB at 16 bit, served by ONNX Runtime on the site serverZero shot multivariate forecasting with covariates over the historian tag mirror; thresholded residuals give the cycle damage agent its cycling stress signal with no fine tuning
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanEmbedding modelBGE-M3, MIT, run at FP16 (about 1.1 GB; about 2.27 GB at float32 and about 0.6 GB at 8 bit), served by ONNX Runtime on the site serverDense, sparse and multi vector retrieval in one pass keeps tag numbers and error codes findable across work orders, inspection findings, corrosion readings and shift log entries, so every answer cites its record
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanVision detector modelsUnnamed in the register: detection models for steam plume, flange leak, operator, maintenance scaffold and fire or smoke, on Frigate NVR and ONNX Runtime on the site server in phase oneFixed cameras at the reformer top deck, the synthesis compressor train and the bagging plant lane watch fixed process equipment, so no tracking or trajectory duty exists and no camera group edge unit is needed in phase one
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanFrontier hardware141 GB HBM GPU class, eight GPUs per node, one node (1,128 GB), new dedicated in country hardware the operator ownsHolds GLM 5.3's 753 GB of FP8 weights on one node; an ECCN 3A090 and 4A090 licence determination precedes any card being quoted, run as a phase one checkpoint, with an approved in country data centre held as the fallback placement
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanFrontier footprint sizing ruleGLM 5.3 node count by GPU class, with the 1.2 planning factor753 GB of weights times 1.2 is 904 GB against the node's 1,128 GB, leaving 375 GB beside the weights of which about 151 GB is reserved for KV cache and activations; at BF16 the weights would be roughly 1.5 TB and would not fit
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanSite inference serverAn air cooled server inside the plant boundary holding Chronos-2, BGE-M3 and the vision models, class named and not sized in the paperForecasting belongs beside the historian it reads continuously, retrieval beside the records it embeds, and vision on the site server rather than camera group edge units in phase one
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanOne way crossingA hardware data diode carrying the lidi one way file service, with store and forward on the OT sideThe requirement never writes to the control system; a diode is physically one way where a firewalled read only connection is only policy one way, and any change to the boundary passes management of change with the control engineer's signature
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanServing runtimesvLLM for GLM 5.3 on the frontier node; ONNX Runtime for the site modelsServes the FP8 weights within the KV cache ceiling the sizing reserves; one runtime for every small model on the site server
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanEvent backboneApache Kafka 4.3.x with KRaft, replicated in country on the operator's own hardwareOrdering per partition key (tag id, work order number, restart identifier); delivery at least once with idempotent writes keyed by source timestamp and identifier; buffering on the OT side of the diode
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanTime synchronisationOCP Time Card grandmaster under linuxptp with a chrony NTP fallbackHistorian, vibration and shift log records join on a common clock
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanPlatform servicesK3s for container orchestration, Harbor as the air gapped artifact and model registry, Keycloak for identity on site, Prometheus, Grafana and Loki for observabilityArtifacts arrive through the controlled import path and the registry's versions are the rollback; identity is held inside the boundary; delivery lag is watched so a stalled feed is seen before the next shift's refresh
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanOntology and graph storeHyper Ontology v0.9 (Semantics plus Kinetics), fourteen objects refreshed shift by shiftThe one place the plant's story is joined, anchored on the equipment master
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanTime series storeClass only: the InfluxDB 3 Core, TimescaleDB and QuestDB family, product confirmed at designThe pick turns on the historian's volume and the operator's estate
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanSensingFixed cameras at the reformer top deck, the synthesis compressor train and the bagging plant lane; historian tag mirror, compressor vibration, route based corrosion readings, laboratory feed, gas restoration notices, digitised shift log; a citation check on conversational answersTwelve sources once sensing is counted: eight systems of record named by the operator plus the camera lanes and the citation check; condition collection is route based, with continuous sensing on the critical tier held open
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanPattern: memoryMemory loops over confirmed restart causes and accepted inspections, nothing trained into weightsThe requirement asks that the next restart plan improve without training a model on the fly, and the weights the operator holds stay the ones it can account for
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanPattern: shadow modeRestart drafts run beside the standing written procedure until measured agreementThe superintendent confirms every step before any draft is trusted; a procedure nobody reads is no protection at all
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanPattern: groundNew dedicated in country hardware in Pakistan, open weight licences, no third party model service; report packs for the insurer's engineer leave only through a controlled export path after a disclosure reviewNothing about the plant leaves the country; the operator owns the object model, the weights, the decision record and the boundary
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanPattern: export licence gateThe ECCN 3A090 and 4A090 licence determination as a phase one checkpoint before any card is quotedExport controls turn on total processing performance rather than memory; if the determination blocks the class, the fallback in country route is already held and the rest of the design is unchanged

How much compute and hardware does AI in heavy industry and construction need?

The compute follows from the models: the published heavy industry and construction designs size it as follows, from no new hardware to a full GPU node.

DesignPartThe design
Structure Phase WatchFrontier computeOne node of eight 141 GB HBM-class GPUs holds GLM 5.3 at FP8 (753 GB of weights, 904 GB with headroom)
Structure Phase WatchEdgeFive Jetson Orin class nodes in solar powered enclosures at the gate, laydown, crane slew zone, batch plant and haul road
Steel Count LedgerFrontier computeOne node of eight 141 GB HBM-class GPUs holds GLM 5.3 at FP8 (753 GB of weights, 904 GB with headroom), in a dedicated data center behind an export licence checkpoint
Steel Count LedgerEdgeOne sealed GPU industrial PC and IP66 HDR cameras per installation point; counting survives a slow wide-area link
Steel Count LedgerThe hard dependency141 GB-class accelerators need a US export licence for Pakistan (Country Group D:4); the node is ordered only once a licence naming the end user holds
Factory Fire WatchComputeNone bought: the requirement asks for no server or GPU, and the field gateways carry no model runtime
Factory Fire WatchEquipment, per factoryAbout 2,600 to 3,200 US dollars in list prices: a LoRaWAN gateway, two tank transmitters, two CT meters, four contact nodes, a switch, an enclosure and a UPS
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaComputeOne node of eight 141 GB HBM accelerators (1,128 GB) in the company's own data centre in Saudi Arabia, holding 753 GB of FP8 weights with a 1.2 planning factor, 904 GB; a plant GPU server of one or two PCIe cards for the forecast and embedding models; a sealed fanless industrial edge unit at the plant. The node is a 4A090 class item for a D:3 and D:4 destination, so an export licence determination comes before the order, with two 80 GB class nodes as the fallback shape
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanComputeOne node of eight 141 GB HBM cards (1,128 GB) on new dedicated in country hardware the operator owns, holding 753 GB of FP8 weights with a 1.2 planning factor, 904 GB; an air cooled site server inside the plant for Chronos-2, BGE-M3 and vision; a hardware data diode on the OT boundary and an OCP Time Card grandmaster for time. The node is a 4A090 class item for a destination in Country Groups D:2, D:3 and D:4, so an ECCN 3A090 and 4A090 licence determination is a phase one checkpoint before any card is quoted, with an approved in country data centre held as the fallback

Is it cheaper to own AI hardware or rent cloud GPUs in heavy industry and construction?

Each heavy industry and construction design prices three years of ownership in its Appendix A, with every price cited, against renting the same capacity from a cloud region at its deepest three-year commitment where hardware is bought.

DesignLineThree years
Structure Phase WatchThree-year cost, ownedAbout 642,000 US dollars with support and power at the Saudi industrial tariff
Structure Phase WatchThree-year cost, rented1.41 million to 2.81 million US dollars for the same GPUs around the clock; ownership is about one half the cheapest three-year commitment
Structure Phase WatchClosed model break-evenThe cheapest closed model matches the owned stack at about 31 users; above that, ownership is cheaper and the gap grows with every user
Steel Count LedgerThree-year cost, ownedAbout 4,445,000 US dollars for 300 installation points, of which the counting kits are 2,832,000 and cannot be rented; owning the frontier node costs about 686,000 against 751,000 on AWS's deepest three-year plan
Steel Count LedgerClosed model break-evenThe cheapest closed model matches the owned node at about 33 users; above that, ownership is cheaper
Factory Fire WatchThree-year cost, 100 factoriesAbout 328,000 to 439,000 US dollars with support and power; the eight-factory pilot is about 21,000 to 26,000 of equipment
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaThree-year costAbout 570,000 US dollars to own the frontier node for three years (a range of 542,000 to 594,000: server, support and power at the national commercial electricity tariff), against about 751,000 to rent the same eight cards on the deepest three year commitment in AWS Middle East (UAE), so ownership costs about three quarters of it, and about 2.00 million on demand, against which ownership costs a little over a quarter. Renting is a price reference only, because AWS lists no Saudi region on the day read and every rented option would carry plant data across the border (Appendix A)
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanThree-year costAbout 572,000 US dollars to own the node for three years (a range of 542,000 to 610,000: server, support and power at the national industrial tariff), against about 751,000 to rent the same eight cards on the deepest three year commitment in AWS Asia Pacific (Mumbai), so ownership costs about three quarters of it, and about 2.00 million on demand, against which ownership costs a little over a quarter. Renting is a price reference only, because AWS lists no region in Pakistan and every rented option would carry plant data across the border (Appendix A)

What ontology or object model does a heavy industry and construction AI system need?

The object model is the part that makes the system an ontology rather than a pipeline: typed objects for the things in the heavy industry and construction operation, with properties, status values and typed links. Every published design ships its object model as hyper-ontology/1 JSON that loads into Hyper Ontology.

DesignSizeObjectsDownload
Structure Phase Watch15 objects, 12 linksTower crane (TC-01 to TC-14), Crawler crane (6 units), Casting bed, Precast unit, Flatbed or mixer truck, Batch ticket, P6 activity (owner baseline or fragnet), Permit to work, Incident or observation form, Gate movement, Delivery window, Lift schedule entry, Pour, Worker, Work zone (Zone A to D)objects.json
Steel Count Ledger14 objects, 12 linksSteel melting and re-rolling unit, Installation point, Industrial PC, Production count event, Product type (Billets, Ingots, Rebars, Girders), Declared production, Discrepancy case, Revenue field officer, Audit team, Steel mill staff, Tamper or offline alert, Daily uptime record, Product calibration record, Weighbridge recordobjects.json
Factory Fire Watch14 objects, 12 linksHigh-risk factory, Fire alarm control panel, Fire pump, Fire water tank, Tank level transmitter, Energy meter (CT set), LoRaWAN gateway, Monitored point, Safety-critical alert, Audit log record, Periodic monitoring round, Preventive maintenance visit, Technical personnel, Monitoring officerobjects.json
A Self-Improving AI System for Cement Kiln Control in Saudi Arabia16 objects, 10 linksKiln line, Equipment, Tag, Setpoint, Recipe, Raw meal lot, Fuel lot, Clinker sample and quality result, Upset, Operator action, Shell scan, Work order, Shift, Control room operator, Shift supervisor, Production managerobjects.json
Industrial AI Reference Architecture for Fertilizer Plant Reliability in Pakistan14 objects, 10 linksProcess unit, Equipment, Historian tag, Trip, Restart, Thermal cycle, Work order, Inspection finding, Corrosion reading, Vibration reading, Lab result, Shift log entry, Turnaround task, Restart planobjects.json

Who approves the decisions an AI system makes in heavy industry and construction?

In every published heavy industry and construction design a named person makes the decision that changes the physical world; the system prepares it.

DesignHuman control
Structure Phase WatchEvery re-sequencing is a recommendation a named planner approves; every breach alert is confirmed, dismissed or escalated by the HSE officer
Steel Count LedgerEvery discrepancy case is judged by a named revenue field officer; the system counts and reconciles, it never assesses, and the mill never edits a count
Factory Fire WatchA monitoring officer acknowledges or escalates every safety-critical alert; the design monitors and never controls a panel, pump or valve
A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaAgents draft and people decide, by name: the control room operator confirms the upset agent's cause and recovery draft, the shift supervisor approves the setpoint agent's draft, and the production manager confirms the shift agent's handover and its energy and quality comparison; drafts run in shadow before anyone approves them, and every confirmation or rejection is kept as the memory the next shift reads
Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanAgents draft and people decide, by name: the shift superintendent confirms every step of the restart plan, the reliability engineer approves the cycle damage draft and the inspections it brings forward, the turnaround manager approves the scope additions, and report packs for the insurer's engineer leave only through a controlled export path after a disclosure review; every status change carries a named person and a timestamp, and every confirmation is kept as memory the next restart reads, never as a weight update

Every answer on this page is drawn from the papers linked in it: each paper's At a glance table, model register and cost appendix. Full text for agents: llms-full.txt. Designed on Praxis; object models load into Hyper Ontology.

Want one of these designs for your own operation? Talk to us.