The plant's managers see every production line live and act on a machine fault before it stops output.
The manufacturer wanted its plant in India to produce to plan, with machine problems caught early instead of disrupting the schedule.
What stood in the way.
Equipment tracking, production planning and inventory at the plant were managed by hand, and each production line kept its own data.
Machine downtime was dealt with after it happened, so schedules were often disrupted and inventory levels were inconsistent.
What we built.
- IoT sensors on equipment reporting temperature, vibration and alarms, feeding a live dashboard of line status, machine health and inventory.
- Daily, weekly and monthly production reports showing planned, target and actual output per line.
- An equipment failure table with time, machine, alarm code and description, plus scatterplots and Pareto charts to find the causes of failures.
- Line status over time with halt reasons logged by operators, safety incident records, and admin masters for lines, plants, defect codes and loss reasons.
- A .NET Core backend, an AngularJS front end that works on desktops and phones, and a migration from Oracle to PostgreSQL.
- .NET Core
- AngularJS
- PostgreSQL
- IoT sensors
What this work shows about us.
Plan against actual, line halts with reasons, defect codes and failure alarms are the facts a production manager works from every shift.
Machine data becomes a table and a chart a manager can act on, on a phone as well as a desktop.
Want to build a similar IoT production management platform? Tell us what you want to change. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with the right team.
Start your plan ↗If we built it today, with AI.
This work came before today's AI. If the Japanese multinational in air conditioning, refrigeration and chemicals asked us now, this is what we would add, step by step.
An agent would read the sensor trends, warn maintenance about a machine likely to fail and propose a slot for the repair that least affects the plan. Maintenance still decides when to stop a line.
An agent would compare actual output with the plan each shift and tell the planner which orders are at risk and why, from the halt and defect records. Planners still reset the schedule.
Where this work fits.
- Manufacturers & distributorsYour company is meant to get dealers the right stock, on time, without making them chase it.
- Supply chain & assets (inventory, assets, procurement)The right stock in the right place on time, and everyone knows what has been ordered without chasing.
- DENSODENSO's service dealers are audited by video call or self-audit, without waiting for an auditor to travel.
Facts and figures from the project records; nothing added.
Want this for your business?
Tell us what you run or what you're building. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with a senior AI engineer.
Send us a note instead
An AI agent. This prototype uses prepared answers and sends nothing.
We use essential cookies to run this site. With your consent we also use analytics cookies to see which pages help. Privacy policy