Case studies
Real-time Failure Detection Case Study in a Multimillion-Dollar Saving Plan
Who
Our client, one of the leading automotive manufacturers in the world, working to implement real-time failure detection using a flexible Process Failure Sheet (PFS) system also referred to as roaming PFS to detect and address defects in real time during the production process.
Why
Traditionally, car manufacturers relied on stationary PFS systems with a limited number of checkpoints along the assembly line. This approach, while functional, had its limitations. Technicians stationed at these checkpoints had to manually monitor and detect defects, often leading to inefficiencies, human errors and extremely high costs.
To address these challenges, our client turned to a roaming PFS system.
As a matter of fact, a roaming PFS system moves along and can cover the entire assembly line, allowing for improved detection of production anomalies, more effective resource allocation, and faster response times to address defects.
Using a roaming PFS system in car manufacturing can lead to significant improvements in operational efficiency, overall product quality and cost management.
How
To implement the roaming PFS system, our client used Digazu to integrate, process, and analyse real-time data from various sources.
In a few hours, Digazu ingested around 200 million records, applied data transformations and quality controls, and pushed results to a live reporting tool, facilitating anomaly detection in the assembly line. From there on, Digazu has been ingesting over 2 million records per day in real-time.
The project was purely no-code, meaning there was no need for a data engineer even though it addressed all the essential governance requirements such as data lineage, retention and standardisation.
What
Previously, the defect reporting process was inefficient, time-consuming, and error-prone.
Yet, the new system led to significant improvements:
Operational Efficiency: Thanks to real-time failure detection, anomalies were caught instantly, enabling immediate corrective actions, hence optimising operations and production processes.
Enhanced Product Quality: Immediate anomaly detection led to better product quality, as defects were addressed at the earliest stages of production.
Cost Savings: The reduction in checking time meant fewer technicians were required per shift. This translated to an impressive cost saving of £1.75 per vehicle, accumulating to over £400,000 per year. This specific use case was part of a multimillion dollar saving plan driven by a newly established data program. It is important to note that this use case was put into production in just two-weeks. This laid the foundation for many other data projects to follow.