Industry solution
Reliability and compliance across the fleet.
Aging assets, distributed operations, and heavy regulatory scrutiny. Tokoaido reads asset condition live over OPC UA and MQTT Sparkplug B, watches it, and turns it into governed, auditable action. SCADA and historian connectors are built for your stack in a pilot.
How Tokoaido helps
What changes.
Watch rotating and thermal assets, and surface degradation before it becomes an outage.
Every recommended intervention is risk-tiered, approved by a person when it matters, and written to the audit log with who decided and why.
Your SCADA and historians remain the system of record. The platform keeps a working copy of the signals a use case needs.
Platform controls are mapped to the EU AI Act, NIST AI RMF and SOC 2 criteria, with figures drawn from the platform itself. This is a self-assessment, not a certification.
Sound familiar?
The work nobody signed up for.
If you have said one of these this month, the rest of this page is for you.
We have three hundred substations and four people who can read a condition report properly.
After an event the regulator asks what happened. I spend a week rebuilding the timeline from SCADA logs and email.
Half our condition data sits in a historian only one engineer knows how to query.
We hit the peak on one hot afternoon and pay for it the whole month.
A crew drove two hours to a pump station and found nothing wrong. That happens every week.
Nobody is letting software near the protection settings, and they are right not to.
Use cases
What you would use it for, first.
Each one starts from a problem you can name, and ends with something a person can see has changed. Live means it runs in the product today; pilot means we build it with you.
- 01
Condition watch on rotating assets
Live todayTodayPumps, fans and compressors are checked on a calendar route, so a failing one is found by the route or by the outage, whichever comes first.
With the platformThe platform reads condition signals over OPC UA or MQTT Sparkplug B, flags degradation against ISO 20816-3 zones, and proposes an inspection with the trend and the evidence attached.
What changesCrews go to the asset that is drifting, not to the next stop on the route.
- 02
Peak demand, managed with a signature
Live todayTodayA load decision made at 2pm sets the demand charge for the whole month, and nobody sees the cost until the invoice.
With the platformThe energy agent models output against energy cost, demand charge included, and proposes a setpoint that a person approves before it goes through SCADA.
What changesPeaks are shaved where output allows, and each change has a reason and a named approver.
- 03
A decision record for every intervention
Live todayTodayAfter an event, the sequence of who saw what and who decided what is spread across logs, tickets and inboxes.
With the platformEvery finding, approval and action is written to one audit log as it happens, with the actor, the target, the risk and the reason. Regulatory report formats such as SAIDI and SAIFI are built with you in a pilot.
What changesThe decision history exists before anyone asks for it.
- 04
Historian and SCADA in one model
Built in a pilotTodayCondition history lives in the historian, the work in another system, and the two are joined in a spreadsheet.
With the platformIn a pilot we connect your historian and SCADA through the edge or the REST/OAuth connector, read-only first, without moving the system of record.
What changesAsset condition and work history sit side by side for the whole team.
Business value
Where the return comes from.
The levers, and the range other organizations have published for each. Ranges are typical of the category, not a promise and not our customers' results.
Energy saved by managing it systematically
~11% on averageA case-study average for organizations that manage energy as a system. Typical of the category, not a product result.
International Energy Agency, Industrial facilities could save billions by implementing energy management (2025)Sites exposed to steep demand charges
over 1 in 4 at ≥$15/kWAbout five million US commercial customers face demand charges of $15/kW or more, so a shaved peak is real money.
NREL & Clean Energy Group, Identifying Potential Markets for Behind-the-Meter Battery Energy Storage: A Survey of U.S. Demand Charges (press release) (2017)Maintenance cost on monitored assets
−5–10%The typical published range for predictive maintenance. Your asset mix decides where you land.
Deloitte Insights, Predictive maintenance and the smart factory (2017)Truck rolls that find nothing
Inspections go where condition data says they are needed, so fewer crews drive out to healthy equipment. Measure it on your own dispatch records.
Run your numbers
Demand charges you could shave.
Every input is yours to change, and the arithmetic is shown in full. Nothing is hidden in a multiplier.
€2,000,000 × 30% × 8% = €48,000
An estimate on the numbers above, not a measurement and not a customer result. In an Operations X-Ray we replace the assumptions with figures measured on your own systems.
Before and after
The same week, run differently.
Crews follow a fixed inspection route.
Crews go first to the assets whose condition is drifting.
The demand peak is discovered on the invoice.
The peak is weighed before the setpoint changes, and someone signs for it.
After an event, the timeline is rebuilt from logs and email.
The decision record was written as it happened.
Condition data waits for the one engineer who can query the historian.
Condition signals land in one model the whole team can read.
In practice · Example scenario
Asset degradation → governed maintenance
A transformer's condition signals drift out of band. The platform correlates across the graph, proposes an inspection, routes it for approval, and records who approved it and why.
Other industries
Operations X-Ray
Start with one site and one peak.
We read one site's condition and energy data and show where the drifting assets and the avoidable peak are.