Zum Inhalt springen

Focus: local AI and Pseudomizer. Together. More

Industry partners wanted. Become a partner

EIGENKERNLocal AI
AI-generated

Concern 5 · heat

Where does the heat go?

The heat network at a glance: sites, meters, flow and return, output, flow rate and storage. One click on a card opens the chart.

Sound familiar?

Three questions about the heat network.

AI-generated

How much heat do I deliver where?

Several heat meters deliver series, but no overall picture.

AI-generated

Does the network run in the right range?

Flow and return temperature show whether the network works cleanly.

AI-generated

Is the storage filled correctly?

The fill level decides how flexibly the engine can run.

How the learning system answers

From the diagram to the chart in one click.

The cards in the network diagram show the current state. A click opens flow, return, output and flow rate over 24 hours, 7 or 30 days.

How was the heat delivery at the sites last week?

Site 1 was above site 2 for most of the week. At the weekend output dropped at both. The series are linked.

Source: heat meters, plant raw values, updated continuously

Example with invented data

Questions you can ask

  • How high was the return temperature yesterday?
  • How much heat did site 2 take?
  • How full is the storage?
  • When was the output last above the normal range?

Every number comes from a fixed calculation, not from the language model. Every answer names its source.

AI-generated

Where the heat flows

Several sites, several meters, one picture.

What it looks like

Flow, return and output.

The two temperatures on top, the output below. One shared zoom applies to both.

Where does the heat go?00:00
HEAT NETWORK · OUTPUT, 24 H0 kW407010000:0006:0012:0018:0024:00HEATING PLANTBHKWSTORAGE0 %FLOWRETURN0 °C0 °CSITE 10 kWSITE 20 kWFlow, warmReturn, colderStorage: charges at night, discharges in the eveningExample: two sites, looked at separately.
Output–
Flow–
Storage–

Example with invented values

AI-generated

The storage at a glance

The fill level decides how flexibly the engine can run.

How it works

From the meters to the chart.

01

Fetch raw values

The raw values of the meters are fetched at short intervals.

02

Look at sites separately

Every site has its own meters and storage. They are not mixed.

03

Click and check

A click on a card opens the chart for the chosen period.

Learning system and Pseudomizer

Two building blocks, one goal: answers without handing out originals.

AI-generatedLearning system

The learning system (RAG)

A system of your own with its own storage. It reads your documents and measurement data, answers in plain sentences and names the source. At night it asks itself new questions and reports gaps.

More on the local AI
Pseudomizer

The Pseudomizer

If you also want to use a large cloud AI, the Pseudomizer creates a shadow copy and checks it with subject-specific check chains. The original stays with you. Leak rate at the exit: 0.00 %. Guards detect, the judge stage blocks when in doubt, healing cleans up.

To the Pseudomizer

More concerns

What operators also want to know.

AI-generated

Who uses how much electricity?

The plant's own consumption split across consumers, even when not everything is measured.

To the page
AI-generated

What to feed, and when?

Feeding recommendation next to the electricity prices: substrates, amounts and times.

To the page
AI-generated

When should the CHP run?

Electricity price outlook as a heat map, to plan operation against the price.

To the page
AI-generated

May this go to the cloud?

Original versus mirror: use cloud AI without originals leaving the house.

To the page

Bring us your biggest annoyance.

One conversation, one real task from your daily work. We use it to show what AI and automation can do for you.