_Lesson Learned Explained: Improving KPIs in the FMCG Industry through automation and data analysis on semi-automated production lines

Introduction

In the highly competitive food and beverage industry, achieving optimal Key Performance Indicators (KPIs) such as availability, performance, and quality is essential for maximizing operational efficiency and profitability. A client operating semi-automated production lines was experiencing persistent underperformance in these KPIs. To address this issue, the company required a robust and precise data-driven approach to monitor production processes and identify the root causes behind its declining KPI performance.

Challenge

Despite deploying a system that leveraged real-time data acquisition from machine controllers (PLCs) to calculate KPIs, the client continued to face significant inefficiencies, particularly in machine availability and overall performance. Preliminary data analysis showed that the downtime monitoring system failed to capture the full scope of the operational issues.

Upon closer examination, it was discovered that downtime events were disproportionately high during night shifts. This led to the hypothesis that procedural or operational inefficiencies specific to night shift management could be contributing to the overall KPI shortfall.

Solution

To address the client’s KPI challenges, a multi-faceted, technically advanced solution was implemented. The approach involved integrating real-time data from production machines and contextualizing it with shift information to provide actionable insights. Key components of the solution included:

• Contextualized Data Correlation: Downtime data was augmented with contextual information, particularly shift scheduling and operator data. This allowed for a granular analysis of downtime causes correlated with the specific shifts responsible, providing a clear indication of shift-specific performance bottlenecks.
• Machine and System Integration: The existing PLC architecture was enhanced with seamless integration into the corporate Manufacturing Execution Systems (MES) and Enterprise Resource Planning (ERP) systems. This allowed for real-time synchronization of machine states, enabling accurate data collection for KPI calculation without manual intervention.
• Advanced Data Visualization: A sophisticated dashboard system was introduced, allowing operations personnel to visualize live KPI data such as machine uptime, throughput, and quality metrics. The user-friendly interface facilitated the immediate detection of deviations, enabling quicker response to production issues.
• Signal and Event History: Comprehensive historical logging was deployed, archiving detailed machine signals, downtime events, and system outputs over time. This provided long-term visibility into performance trends and helped in identifying recurring issues linked to specific production conditions.

Result

Once the data collection infrastructure and advanced KPI analysis tools were in place, a clear pattern emerged: a significant percentage of unreported downtimes occurred during night shifts, which had not been flagged in the original manual reporting system.

Through the detailed correlation of downtime events with shift schedules, it was determined that these downtimes were frequently caused by non-compliance with standard operational procedures. Further analysis suggested that these events were largely “unintentional,” indicating a need for stricter oversight and adherence to established workflows during night operations.

Correction

Following the identification of the root cause, the following corrective measures were implemented:

• Enforcement of Accountability: One supervisor from the night shift was held accountable for repeated procedural violations. Disciplinary action was taken, reinforcing the importance of following operational guidelines and ensuring that such issues would not recur.
• Targeted Staff Retraining: Night shift personnel were provided with extensive retraining focused on operational standards, system utilization, and adherence to machine maintenance protocols. Training emphasized the importance of real-time reporting and proactive machine monitoring.

Conclusion

While the client initially sought a solution for automated KPI calculation based on machine data, the introduction of advanced downtime monitoring and data contextualization proved essential for identifying deeper operational inefficiencies. The key insight was gained through correlating downtime events with shift performance, which revealed a management issue during night shifts.

As a result of the corrective actions, the company observed a marked improvement in operational performance. Machine availability increased, downtime incidents were significantly reduced, and overall KPI targets for performance and quality were met, leading to enhanced production efficiency and throughput.

Lesson Learned Explained: how proper data collection and storage proved crucial in predictive maintenance