Case Study — Nexora

Manufacturing Operations Hub

Connecting 12 Production Lines Under a Single Real-Time Operations Platform

Unified production visibility eliminating paper-based shift management

Industry

Discrete Manufacturing

Timeline

20 weeks

Team

7 engineers

Tech

OPC-UA + TimescaleDB + React

The Challenge

A discrete manufacturer running 12 production lines across 2 facilities had no unified view of throughput, quality, or utilization. Line managers operated with paper-based shift logs, verbal handoffs, and end-of-day Excel reports. Leadership was making production scheduling decisions on yesterday's data — decisions that were wrong 30% of the time.

Our Approach

How We Solved It

01

OPC-UA Machine Connectivity

Connected 180 machines across 12 production lines via OPC-UA protocol, establishing a real-time data stream of machine state, cycle counts, and quality signals without requiring PLC replacement.

02

Digital Shift Log & Handoff

Replaced paper shift logs with a tablet-based digital system that captures production events, quality holds, and maintenance requests in structured form — feeding directly into the operations dashboard.

03

Real-Time OEE Calculation

Built a streaming OEE (Overall Equipment Effectiveness) engine that calculates Availability, Performance, and Quality in real time for each machine, line, and facility, updated every 60 seconds.

04

Production Scheduling Intelligence

Integrated real-time OEE and downtime data with the ERP demand plan to generate scheduling recommendations that optimize throughput against actual machine availability rather than theoretical capacity.

Engineering Process

How We Built It

Edge Computing for Data Collection

Deployed edge computing nodes at each line to aggregate machine data before sending to the cloud — reducing WAN bandwidth by 80% and enabling local dashboard functionality during connectivity outages.

Time-Series Architecture

TimescaleDB's hypertable partitioning handles 2M+ data points per day with automatic retention policies, compressing data older than 30 days by 92% while retaining full query capability.

Shift-Based Data Contextualization

Machine data is automatically tagged with shift, operator, product, and work order context, enabling root cause analysis by crew, product family, and production run — not just by machine.

Architecture Decisions

Key Technical Choices

OPC-UA Over Custom Protocols

Standardizing on OPC-UA rather than machine-specific protocols meant one integration framework across 14 different machine manufacturers — the connectors are reusable across future plant expansions.

Edge-Cloud Hybrid

Edge nodes provide local resilience (dashboards keep running during internet outages) while the cloud layer provides historical analytics, cross-facility comparison, and ML training data.

Event-Driven OEE vs Batch Calculation

Real-time event-driven OEE calculation rather than hourly batch jobs meant line supervisors could see OEE degradation within minutes of a problem, not after the shift ended.

Results

What We Delivered

12
Production Lines Connected
28%
OEE Improvement
65%
Reduction in Unplanned Downtime
99.2%
Machine Data Capture Rate

Solution Blueprint

How It All Fits Together

Machine Connectivity Layer
  • OPC-UA adapters (180 machines)
  • Edge computing nodes
  • Real-time event stream
Analytics Layer
  • Streaming OEE engine
  • TimescaleDB time-series
  • Quality defect detection
Operations Layer
  • React operations dashboard
  • Digital shift handoff
  • ERP scheduling integration

Lessons Learned

What We Improved

01

OEE Visibility Alone Changes Behavior

Simply showing real-time OEE on screens at each line changed operator behavior before we deployed any alerting or automation. Visibility is an intervention.

02

Supervisor Buy-In Before Line Operator Buy-In

Line supervisors needed to understand the system before operators would adopt the digital shift logs. Skipping the supervisor layer caused two weeks of passive resistance.

03

Paper Doesn't Disappear Immediately

Operators ran parallel paper and digital logs for 3 weeks. We planned for it and used the parallel period to validate data quality rather than forcing immediate transition.

Related Research

Research Reports for This Industry

Enterprise AI24 min

Enterprise AI Adoption Trends 2026

Enterprise AI has crossed the operational threshold. Seventy-two percent of Fortune 500 organizations now run at least one AI system in production — and the average enterprise manages 3.4 concurrent AI initiatives. This report maps the state of enterprise AI across healthcare, manufacturing, financial services, retail, and beyond.

Read report
Manufacturing & Industry 4.020 min

Manufacturing AI Adoption Report 2026

Manufacturing is at an inflection point in its relationship with artificial intelligence. The period of exploratory pilots and executive enthusiasm without operational grounding is giving way to a more sober, implementation-focused phase. Organizations that invested early in shop floor connectivity, data infrastructure, and cross-functional AI governance are beginning to realize measurable operati...

Read report
Manufacturing & Industry 4.020 min

Industry 4.0 Outlook 2026

Industry 4.0 has moved decisively past the hype cycle into a phase of disciplined, enterprise-scale execution — and the gap between leaders and laggards is widening. Organizations that committed early to foundational investments in industrial IoT infrastructure, edge computing architecture, and OT/IT data integration are now compounding those returns through AI-driven quality, predictive operation...

Read report
Manufacturing & Industry 4.018 min

Predictive Maintenance Trends 2026

Predictive maintenance has moved from a niche capability explored by early adopters to a core operational priority across asset-intensive industries. The confluence of lower-cost industrial sensors, accessible edge computing platforms, and mature machine learning toolchains has made it technically feasible for organizations that previously lacked the budget or infrastructure to pursue condition-ba...

Read report

Work With Halkwinds

Build Something Exceptional

Partner with the team that built Nexora.

View Platform