AI Error Diagnosis

When a machine reports an error, the answer is usually somewhere in the manual. With AI diagnosis, the viewer sends the error to CONNECT, which searches the manual. CONNECT returns a probable cause, a remedy and its sources, including the location within each document.

The knowledge base is your own PDF documentation. Operators can attach comments per error, so the second person to hit the same alarm finds what the first one did.

This feature is off by default and has to be enabled deliberately.

What it needs


Documents	PDF manuals in the gateway’s documentation folder. Subfolders act as categories
An LLM key	For the language model that phrases the answer
Nothing in the browser	The browser never holds the key, the index or the document text

Setting it up

Put the machine PDFs into the documentation folder of the gateway data directory. Use subfolders to separate, for example, mechanical from electrical documentation.
Enable the feature and enter the model key in the configuration.
Open the tray menu and choose Index Documentation now, or ask the first question. Indexing runs on the first request.
Verify with Test AI Query… in the tray menu.

Indexing is incremental: unchanged PDFs are never processed twice, and adding one document does not re-process the rest.

Asking

In the viewer, an error signal offers the diagnosis. The answer cites its sources by document and page so you can check it.

Answers are limited to a few requests per minute per gateway, so a flapping error signal cannot trigger a request storm.

What the twin adds to the question

When you select a part, the viewer includes information about it from the digital twin in the request:

What travels	What the gateway does with it
Document hints: the PDFs linked to that part and its parents	Gives those documents a small ranking bonus in the search without filtering out other documents. A passage from another document still wins if it provides a better answer
Machine context: the part’s component type, its relevant configured values, the current values of its signals and its active alarms	Adds a clearly marked data block to the prompt. The answer can then address the machine’s current state rather than just the manual’s general description
Node notes: what an assistant previously worked out about that part	Appends notes after the alarm lines. Each line is marked as author-written text to distinguish it from a live alarm

Even without a selection, the documents of the parts that match the typed question are added as hints, so a question that names a part still gets a part-specific answer.

The context block is size-capped, and the viewer shows the person asking exactly what travelled with their question.

Keeping live machine state off the language model

The documentation search runs on the gateway; phrasing the answer does not. If live signal values must not reach the configured language model, switch the machine-context block off:

Diagnosis:MachineContext=false

With it off, document hints and the documentation search work unchanged. Only the live state block is suppressed. It is on by default because the current machine state improves diagnosis. Operators should turn it off where the model provider is outside their control.

A second, broader block that would carry general machine status beyond the selected part is off by default (Diagnosis:GlobalContext=true enables it). An existing installation therefore never starts transmitting more than it did before, and selected-part context stays available either way.

Comments

Operators can attach comments to an error id and read what others wrote. Comments are stored in a file next to the gateway configuration or in InfluxDB when the historian is in use. In InfluxDB, they sit alongside the signal history recorded at the same moment.

What leaves the machine

Step	Where it runs
Reading and splitting PDFs	On the gateway
Embedding (turning text into vectors)	Through the configured cloud gateway. Document text is sent for this step
Searching	On the gateway
Re-ranking (optional)	On the gateway, with a local model. No text leaves the machine
Phrasing the answer	Through the configured language model, with the retrieved passages

If your documentation is confidential, decide whether it can be sent to the configured cloud gateway. The pipeline is prepared for a local embedding model, and re-ranking already runs locally.

Embedding sends document text and the query text. The language model receives the question, retrieved passages and, unless you set Diagnosis:MachineContext=false, the selected part’s machine context (type, values, signals, alarms and node notes); re-ranking is optional (default: none), and local uses an ONNX model on the gateway.

The index and local models are stored in a private folder that the gateway never serves over HTTP. The index contains the full extracted document text.

Local re-ranking

With re-ranking enabled, the gateway retrieves a broad set of passages and ranks them locally with a cross-encoder model. It sends only the best passages to the language model. This improves answers for large documentation sets, and the ranking step uses no network connection.

If the model file is missing, the pipeline runs without re-ranking and reports the missing model without failing the request.

Prepared documentation

A gateway can be delivered with the documentation and its index already built in. The customer then gets working diagnosis on the first start, with no indexing wait and no re-processing. Documents added or edited on site survive later updates.