📍 6 Raffles Quay, #14-06, Singapore 048580 ✉ enquiries@twotwotech.ai ☎ +65 6717 0088
CASE STUDYManufacturing

Predictive maintenance cuts unplanned downtime 41% for a precision-engineering exporter

Vision-AI inspection station + vibration-based spindle anomaly detection + Yonyou NC Cloud work-order integration recovered ~3 days of production per month across two pilot lines. Nine months from kickoff to steady-state.

Client: Precision-engineering exporter (NDA · SG HQ · CN production) Period: FY2025 · 2 pilot lines · 9 months Services: AI Data Platforms, Enterprise IT Integration
-41%
Unplanned downtime
9 mo
Kickoff → steady state
<2s
Defect detection at 60 units/min
0
Costly returns from false-rejects (6mo)

Context

A Singapore-headquartered precision-engineering exporter ran two production lines (CNC + post-process inspection) producing high-mix, low-volume parts for the medical-device and aerospace supply chain. Roughly 18% of planned production hours were lost to unplanned downtime — split between bearing failures on the spindle heads and cosmetic-defect false-rejects from the human inspection station.

The cost: ~3 days of production lost per month per line, plus inventory carrying cost on customer reservations they couldn’t ship on time. They’d evaluated three “predictive maintenance” SaaS products. None of them tied into their Yonyou NC Cloud ERP, none adapted to the specific failure modes their spindles exhibited, and none could close the work-order loop without a human re-keying the alert into their existing maintenance system.

What we did

Spindle vibration monitoring

Instrumented the spindle-head bearings with three-axis accelerometers, streaming via OPC UA → MQTT into Azure IoT Hub. Trained a per-asset anomaly model that tied vibration signatures to specific failure modes (not generic “outlier” scoring) — bearing wear vs. lubrication loss vs. misalignment each surfaces a distinct frequency-domain fingerprint, and the maintenance team’s response is different for each.

Vision-AI inspection station

Deployed a Vision-AI inspection rig next to the line — small convolutional model running on an edge box, fail-safe to manual inspection if confidence dropped below threshold. 60 units/minute throughput, sub-2-second decision. The team kept the human inspector station running in parallel for the first 8 weeks; we measured agreement rate, tuned, then transitioned the human to exception review only.

Yonyou NC Cloud work-order integration

Alerts flowed into the existing Yonyou maintenance work-order module — pre-filled with asset ID, failure-mode prediction, recommended parts, and a suggested 48-hour scheduling window that minimized production impact. The maintenance team confirmed and dispatched from the same screen they’d been using for years.

Results

What we learned

The biggest unlock wasn’t the model — it was getting maintenance to trust the alerts enough to schedule the work. We spent more time on the human-process change than on the ML itself: every false-positive investigation reviewed publicly, every saved bearing failure celebrated, the model’s confidence threshold tuned with the maintenance lead in the room.

The Yonyou integration mattered more than we expected. The previous SaaS tools had failed at adoption because alerts arrived as email — which got filtered, ignored, and eventually distrusted. Arriving as a pre-filled work order in the system the team already used closed the loop in days, not months.

“The model wasn't the hard part. Getting maintenance to trust the alert enough to schedule the work — that was the unlock.”

— Operations Director (named NDA), Precision-engineering exporter

More case studies

Dive Deeper

Talk to us

Start with the problem. The solution comes after.

A 30-minute call with a solution architect. No spec needed — just tell us where the business is stuck. Systems that don't talk. Data that won't behave. An overseas office with no one running IT. A DR plan on paper that no one has tested. A first AI use case you want to try for real. If we fit, we'll show you the next step. If not, we'll tell you straight.