Process control · since 1991

Your plant already told you. It is in the data.

Three tools that read a plant's own historian export and say what changed, when, and which of it is worth acting on — with the evidence printed beside every conclusion, including what it could not settle.

See the products Read a worked example

What we build

Three questions, three tools

Each answers one question. None of them assumes a model of how your plant should behave: normal is learned from your plant's own history.

Continuous process

IPA — Industrial Plant Assessment

Is the data good enough to trust, when did the plant leave normal operation, and which of those departures are worth acting on?

How it works →

Batch process

BPA — Batch Process Assessment

Which batches did not run like a good one, where in the batch did they diverge, and which tag took them there?

How it works →

Control loops

CLA — Control Loop Analysis

This loop is cycling — is the cause inside it, or is it only passing on someone else's problem?

How it works →

How we work

A conclusion you can check

An assessment is only useful if someone can disagree with it. Every report here is built so that they can.

See for yourself. The worked examples run all three tools on public and anonymised data, including benchmarks where the faults are known in advance, so every claim on this site can be checked against a result.

Standards

Procedure automation, written out in full

Assessment tells you what is wrong. Procedure automation is a large part of what you do about it — and ISA-106 is the standard that says how.

Summary edition

Procedure Automation for Continuous Process Operations

A fifteen-chapter summary edition covering the three models, automation styles, the lifecycle management strategy, and the procedure automation lifecycle from specification through to retirement.

Read the summary edition →

The full edition is in process to be published. Ask for a draft.

Why it is here

  • It is the vocabulary a plant already uses, so a deliverable written in it needs no translation.
  • It connects the assessment to the work: a finding about a loop or a unit becomes a procedure.
  • Our work is aligned with it — the structure and terminology are followed. That is not a certification, and we do not claim one.

Want to know what your data says?

Send a few days of historian export and a tag list. The first conversation is about whether the data can answer your question at all.

Start a conversation See a worked example