Industry solution
Governed operations for the modern plant.
Unplanned downtime, tribal knowledge, and a widening gap between the plant floor and the back office. Tokoaido spans both, discovering the as-run process from real telemetry and turning conditions into governed action.
How Tokoaido helps
What changes.
Rising vibration crosses an ISO 20816-3 alarm zone, the failure is localized on the asset graph, and a governed maintenance work order is raised and verified.
Ingest over OPC UA / MQTT Sparkplug, rediscover the as-run process, and see conformance, bottlenecks and rework, no data hand-labeled.
Find the energy vs. throughput optimum under demand charges, and route the change through SCADA with human approval.
A hard boundary keeps agents off the PLC and the Safety Instrumented System, always.
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 find out a bearing was going when it seizes on the night shift, and the line sits until the fitter gets in.
The vibration alarm went off three times last month. Nobody raised a work order, because nobody owned the alarm.
The recipe says 180 degrees. The oven log says it has run at 172 for six weeks, and nobody knows why.
Every Monday I rebuild the downtime report by hand from the MES, the CMMS and a spreadsheet the shift leads keep.
IT will not go near the PLCs, and the controls team does not trust anything that writes to them.
When our senior fitter retires, half of what we know about Line 2 leaves with him.
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
From a vibration trend to a signed-off work order
Live todayTodayA coolant pump drifts into ISO 20816-3 zone C over a weekend. The alarm lands in a historian nobody is watching, and the bearing fails on Tuesday's first shift.
With the platformThe platform reads the pump over OPC UA or MQTT Sparkplug B, sees the trend cross into zone C, traces the cause on the asset graph and puts a work order with the evidence in front of the reliability lead. Once approved it is raised, and the vibration is measured again after the repair.
What changesThe bearing is changed in Saturday's window instead of failing on a running shift, and the record shows who approved it and whether the repair worked.
- 02
Recipe drift caught at the step that causes it
Live todayTodayThe master recipe says one thing and the line does another. The gap only shows up as rework at final inspection, three steps downstream.
With the platformTelemetry from the line is mined into the as-run process and compared with the master recipe step by step, naming the bottleneck and the parameter that drifts.
What changesProcess engineers get the real operating norms back, and the fix lands where the drift starts instead of at QA.
- 03
Output weighed against the demand charge
Live todayTodayRunning the curing oven flat out looks productive until the peak-demand charge arrives on next month's bill.
With the platformThe energy agent models output against energy cost, demand charge included, and proposes a setpoint. The change goes through SCADA as a high-risk action that a person approves, and the energy setpoint decision carries hash-chained lineage from data to action.
What changesSetpoints change with a cost case and a signature, not by feel on the night shift.
- 04
Your CMMS and MES in the same loop
Built in a pilotTodayWork orders live in the CMMS, production orders in the MES, and the two never meet until the planning meeting.
With the platformIn a pilot we connect your CMMS and MES through the REST/OAuth connector or the edge, read-only first, so work orders are raised where your planners already work.
What changesMaintenance and production plan from one picture of the asset.
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.
Uptime on monitored assets
+10–20%Catching degradation early turns breakdowns into planned stops. This is Deloitte's typical range for predictive maintenance, not a guarantee.
Deloitte Insights, Predictive maintenance and the smart factory (2017)Maintenance planning time
−20–50%Work orders arrive with the asset identified and the evidence attached, so planners stop chasing the story behind each alarm.
Deloitte Insights, Predictive maintenance and the smart factory (2017)Capacity lost to weak maintenance
5–20%The share of productive capacity a poor maintenance strategy can cost a plant. Some of it comes back when stops are planned.
Deloitte Insights, Predictive maintenance and the smart factory (2017)The peak on the energy bill
30–70% of the billDemand charges can be this large a share of a commercial bill, which is why a setpoint that respects the peak is worth a signature.
NREL & Clean Energy Group, Identifying Potential Markets for Behind-the-Meter Battery Energy Storage: A Survey of U.S. Demand Charges (press release) (2017)Run your numbers
Unplanned downtime you could avoid.
Every input is yours to change, and the arithmetic is shown in full. Nothing is hidden in a multiplier.
324 × €25,000 × 25% = €2,025,000
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.
A bearing fails mid-shift and the line waits for a fitter.
The bearing is replaced in a planned window, with the work order approved days earlier.
Vibration alarms sit in the historian until someone happens to look.
A rising trend becomes a work order proposal with the evidence attached.
The downtime report is rebuilt by hand every Monday.
Every stop, finding and decision is already in one record.
Setpoints change on the night shift with no reason written down.
A setpoint change carries its cost case and the name of the person who approved it.
Rework shows up at inspection, three steps after the cause.
The drifting parameter is named at the step where it starts.
In practice · Example scenario
From a vibration signature to a work order
A coolant pump trends into ISO 20816-3 zone C. The platform localizes the root cause on the twin graph, proposes a bearing-service work order, waits for approval, files it in your work-order system, and verifies the outcome, end to end.
Other industries
Operations X-Ray
Run this on one line of yours.
Pick a line you know well. In a week the X-Ray shows its as-run process, its machine health, and what to automate first.