Mate in the Loopby Kenny Jung
KOEN

AI / MLMaritime & ports

HD Hyundai Heavy Industries has built AI CIP (AI Coating InsPector), a vision-AI and deep-learning system that finds and analyses coating defects on ships, and on October 29 signed an MOU in Ulsan with four classification societies — LR, ABS, DNV and KR — joined by HD Korea Shipbuilding & Offshore Engineering and HD Hyundai Samho.

AI-drafted · reviewed by KennyCodex check · partly supported3 min read

Source [1] en.sedaily.com · 29 Oct 2026 · “HD Hyundai Heavy Develops AI Ship Coating Inspection System” ↗
Adoption stage: Pilot — A named organisation is trialling it on real data, bounded scope or time.

Summary

HD Hyundai Heavy Industries has built AI CIP (AI Coating InsPector), a vision-AI and deep-learning system that finds and analyses coating defects on ships, and on October 29 signed an MOU in Ulsan with four classification societies — LR, ABS, DNV and KR — joined by HD Korea Shipbuilding & Offshore Engineering and HD Hyundai Samho. The system has been developed with HD KSOE's AX Center since 2024 on coating quality data from the yards, replacing inspections that depended on workers' eyes and experience and varied with inspector skill. Under the MOU the two yards expand its use and the four class societies work on technical reviews and standard inspection procedures.

Basis: the source [1], facts F1–F6

Kenny's take

Coating inspection has run on the inspector's eye and experience, and the same defect could be judged differently by different people. HD Hyundai Heavy is moving that judgement to deep-learning vision and has pulled LR, ABS, DNV and KR into writing standard procedures for it. The stage is pilot: use is being expanded and the class procedures do not yet exist. It becomes production when the class societies publish procedures accepting AI inspection results and shipowners take delivery on them. If accuracy or detection-rate figures never appear, this signal weakens.

AI draft · approved by Kenny

Analysis

Stage: pilot. The system is in use at the yards (the official says introducing it "has secured consistency in inspections"), but the agreement is to "expand use of the system at their yards", and the class societies are still to establish standard inspection procedures, so this is bounded use that is being widened rather than a settled day-to-day process.

For the pattern ai-visual-quality-inspection, this is the maritime (shipbuilding) instance on the same day that a manufacturing instance reports production results (see signals/2026/10/30/engineering-com-2026-10-29-siemens-pg-ai-visual-inspection-expansion.md): there the system runs at line speed across P&G sites with scrap reductions quoted; here the source gives no accuracy, throughput or defect-rate figures, only the consistency claim.

For q-standards-speed, the notable part is that four classification societies are signed up to write standard inspection procedures for AI results, and the company says its aim is a quality framework that lets shipowners "objectively verify inspection results". Whether those procedures arrive, and when, is not dated in the source.

Facts from the source

  1. F1HD Hyundai Heavy Industries has developed "AI CIP, or AI Coating InsPector", an AI-based inspection system for ship coating quality that "combines vision AI and deep learning to automatically identify and analyze coating defects on ships", which it calls "a first for South Korea's shipbuilding industry". [1]
  2. F2On the 29th (October 29, 2026) it signed a memorandum of understanding on advancing AI technology with four classification societies — Lloyd's Register, the American Bureau of Shipping, DNV and the Korean Register — at its human resources development center in Ulsan's Dong District; HD Korea Shipbuilding & Offshore Engineering and HD Hyundai Samho also joined. [1]
  3. F3The system was developed jointly with the AX Center of HD Korea Shipbuilding & Offshore Engineering since 2024, "training the AI on coating quality data gathered from shipyards". [1]
  4. F4Coating inspections on newly built ships "have relied on workers' eyes and experience, meaning results varied with the inspector's level of skill"; the company says it "recently completed technical reviews with major classification societies". [1]
  5. F5Under the agreement, HD Hyundai Heavy Industries and HD Hyundai Samho "will expand use of the system at their yards", HD KSOE will improve performance and verify compatibility with different coatings, and the four class societies "will cooperate on technical reviews and on establishing standard inspection procedures". [1]
  6. F6An HD Hyundai Heavy Industries official: "Introducing the AI coating inspection system has secured consistency in inspections and made quantitative quality analysis possible through accumulated data." [1]

Organisations: HD Hyundai Heavy Industries, HD Korea Shipbuilding & Offshore Engineering, HD Hyundai Samho, Lloyd's Register, American Bureau of Shipping, DNV, Korean Register

Counterpoint — verification notes

Codex checked each sentence against the source and searched for counter-evidence. Verdict: Codex check · partly supported.

  • Other sideThe live article’s photo caption dates the MOU September 29, conflicting with its body’s October 29 account. Other October 29 reporting corroborates the body date.
5 sentence-level checks
  • summary_enpartly-supported: The system is replacing inspections that depended on workers’ eyes and experience. — The article describes groundwork to shift inspections, not a completed replacement. The Korean summary correctly presents that shift as a goal.
  • analysispartly-supported: The company says its aim is a framework that lets shipowners “objectively verify inspection results”. — That quoted wording is absent from the cached article. It discusses an objective, data-based framework and building trust with shipowners, but does not say shipowners will verify results.
  • analysispartly-supported: Four classification societies are signed up to write standard inspection procedures. — The article says they will cooperate on establishing procedures; it does not assign them sole responsibility for writing them.
  • takepartly-supported: 선급 표준 절차는 만들어지지 않았다. — Future cooperation on establishing procedures is reported, but the article does not establish that no relevant procedures currently exist.
  • takepartly-supported: The class procedures do not yet exist. — Future cooperation on establishing procedures is reported, but the article does not establish that no relevant procedures currently exist.

Sources

  1. [1] en.sedaily.com — “HD Hyundai Heavy Develops AI Ship Coating Inspection System” original

Keep reading

Same industry

The Maritime Executive

Cisco and PSA Singapore will build a proof of concept of an AI-powered observability and incident management platform at Tuas Port, which the release calls the world's largest fully automated container terminal.

The platform pulls real-time performance data from PSA's applications, infrastructure and network into one view and uses AI to map service interactions so that, during an incident, technical teams can see which services are affected, diagnose the root cause and get resolution recommendations. It is meant to reduce and eventually pre-empt outages such as Terminal Operating System (TOS) failures, starts at the Tuas Port Phase 2 Living Lab, and is justified with Cisco research putting average annual downtime cost per organisation at US$300 million.

Maritime & portsAI / MLStage · Pilot
Codex check · partly supportedRead the take
쉬핑뉴스넷

HD Hyundai and Anduril ran a 3.5-hour autonomous-operations demo on a converted 368-ton US Navy test vessel off Long Beach, with the Navy, Coast Guard and ABS watching.

Beyond navigation and formation sailing, it showed an engine-failure emergency response driven by an engine-autonomy layer that monitors machinery and reacts on its own. It is a bounded demonstration on a defence platform, not commercial service.

Maritime & portsAI / MLAI agentStage · Pilot
Codex check · partly supportedRead the take
dredgewire.com

Fincantieri is putting nearly €100 million of its Industrial Plan into robotics, Physical AI and automation under BOOST² – The Shipyard of the Future, a three-year-old programme spanning 13 shipyards in Italy, Romania and the United States and more than 450 employees.

The toolkit covers collaborative robots, digital twin, smart supply chain systems and additive manufacturing. Solutions already in operation and under validation were demonstrated as the programme moves "from innovation to industrial deployment", but the article gives no timelines or productivity figures.

Maritime & portsManufacturingAI / MLStage · Pilot
Codex check · partly supportedRead the take

Same AI technology

전기신문

At the Korean Society for Railway autumn conference on October 29, Lee Dong-seop of Daeati presented the AI train-conflict prediction and resolution system planned for the Second Railway Traffic Control Center (about KRW 250 billion, completion targeted for 2028).

It couples physics-based micro-simulation (gradient, curves, track length, vehicle specs) with AI trained on actual operating records and track occupancy, aiming to predict about 2 hours ahead and compute conflicts and resolution options in about 3 seconds; resolution runs reinforcement learning first, which handles about 995 of 1,000 cases, with a CP-SAT solver for the rest. The system presents conflict types and options and the dispatcher makes the final choice on punctuality, cost and energy; the Guro control center is to be upgraded to the same system for redundancy.

Other industriesAI / MLData science & classical MLStage · Research
Codex check · partly supportedRead the take
engineering.com

Siemens and P&G are rolling their jointly developed Visual Inspection Cockpit (VIC) out across P&G's manufacturing operations worldwide.

It inspects products in real time at full line speed; depending on the product, scrap rates are down 10 to 20 percent, and new deployments commission five to ten times faster than traditional custom vision systems. P&G's deep-learning models run near the equipment on Siemens Industrial Edge with Nvidia-GPU industrial PCs, and the system can automatically trigger alerts or removal of defective products from the line.

ManufacturingAI / MLStage · Production
Codex check · partly supportedRead the take
pv magazine

Gritt Robotics retrofits off-the-shelf construction machinery with AI control and has put it to work on utility-scale solar sites run by EPC Burns & McDonnell.

The company says it is working with three top-10 solar EPCs to install six million panels — about 2.8 GW — over the next two years. The article ties this to a cited shortfall of 53,000 workers on ongoing projects and an estimate that 41% of construction workers will retire by 2031.

Energy & utilitiesAI / MLStage · Pilot
Codex check · supportedRead the take

Same stage, another industry — the pattern elsewhere