Skip to content
realvirtual.io realvirtual WEB

AI Diagnosis

AI Diagnosis helps an operator investigate an alarm using the documentation delivered for that machine. The workflow retrieves relevant passages from manuals and service knowledge before an answer is written, so the result can present a likely cause, a remedy and links to the supporting PDF pages.

The diagnosis can include project context such as the fault code, current machine context and shared operator comments. It is an advisory aid: verify the cited source and follow the machine’s approved safety and service procedures before taking action.

How the diagnosis is grounded

Section titled “How the diagnosis is grounded”
  • Machine documents provide the searchable manuals, datasheets and service information.
  • Fault context identifies the active error or PLC signal associated with the request.
  • Retrieved passages ground the answer in relevant source text instead of relying on a general response.
  • Source links open the supporting document at the cited page when that reference is available.
  • Operator comments can preserve useful service experience across later diagnoses when shared notes are configured.

In a CONNECT-based deployment, the documents, search index and embeddings stay on the CONNECT backend. Only the required text excerpts are sent to the configured language model, and the model provider can be an EU-hosted service or a fully local OpenAI-compatible endpoint. The language-model API key does not need to reach the browser.

Asking about the part in front of you

Section titled “Asking about the part in front of you”

Select a part before you ask, and the question stops being generic. The request then carries what the twin knows about that part:

  • Its documents. The manuals linked to the part and its parents are searched with priority, so the answer comes from the right chapter of the right document rather than from whichever manual happened to match the words.
  • Its current state. The component type, the values of its signals and its active alarms travel with the question, so the answer can address the machine as it is right now.
  • What was worked out earlier. If a note was left on that part, it is included as well.

The dialog shows a context chip naming the part that was included, and an expandable line showing exactly what was sent. Removing the chip re-runs the question without it — useful when the part turns out not to be the one at fault.

Each answer also lists affected parts: the parts of the model whose documentation matches the cited sources. Clicking one selects and focuses it in 3D, so a cited paragraph leads you to the hardware.

Your installation may have live machine state switched off for privacy. The documentation search then works exactly as described; only the current-state part of the question is left out, and the context line shows that.

Quick Start

Section titled “Quick Start”
  1. Open an alarm or diagnostic entry that offers Ask AI.
  2. Start the diagnosis and wait for the document search and response to complete.
  3. Read the proposed cause and remedy together with the current fault context.
  4. Open the listed source and verify the cited PDF page before following a recommendation.
  5. Add an operator comment when the deployment provides shared history and the note will help future service work.

See also

Section titled “See also”