Skip to content Skip to footer

Case Study: Transforming Automobile Manufacturing With Real-Time Monitoring And Predictive Maintenance

1. BACKGROUND & PROBLEM STATEMENT:

A global automobile manufacturing leader faces challenges in their production processes, notably unplanned and extended downtime due to issues with real-time monitoring and maintenance. The absence of effective solutions led to disruptions in operations, managing KPIs, hindering productivity and competitiveness in the dynamic automotive industry landscape. In collaboration with Ranial Systems, the objective is to implement the CognitIoT™ platform to achieve seamless connectivity and proactive issue detection. The integration would also capture the process parameters used by the automated assembly line workstations. This partnership anticipates a reduction in downtime, infuse a automated quality control, enhancement of operational efficiency, and maximization of asset lifetime value by leveraging Cognitive edge computing and real-time decision intelligence at the point of action.

2. APPROACH:

To address the manufacturing challenges encountered by the global automobile manufacturing company, an approach involving the development of autonomous control and engineering assembly lines was undertaken. This innovative system facilitated real-time tracking, monitoring, and anomaly detection of both equipment health conditions and prefeed process parameters, allowing for proactive notification of potential issues, anomalies to the supervisors and engineers. By promptly identifying issues, the system enabled recalibration of equipment, thereby mitigating product defects and enhancing quality control.

The condition-based monitoring has introduced real-time predictive maintenance insights to address the equipment health concerns much ahead of time, minimizing downtime significantly. Furthermore, the real-time data provided insights for logistics planning and improved Overall Equipment Effectiveness (OEE). Additionally, the system was designed to assess the overall efficiency of the assembly line, empowering the production team to optimize manufacturing processes and plan for increased productivity.

 

3. SOLUTION:

In response to the challenges encountered by the global automobile manufacturing company, Ranial Systems devised a comprehensive solution by leveraging its Cognitive IoT platform. The process commenced with the collection of data from manufacturing assets. This data served as the foundation for training machine learning models and incremental learning at the edge, empowering the system to discern patterns and forecast potential failures. Following stringent testing to ensure model precision and efficacy, the AI-powered models were seamlessly deployed onto the edge device, enabling real-time analysis and decision-making at the data’s source. The cloud-based monitoring has facilitated efficient data processing and immediate response to emerging issues, broadcasting predictive and prescriptive insights through SMS/ email, notifications effectively minimizing downtime and optimizing maintenance schedules.

Ranial Systems’ patented platform, CognitIoT™, enables seamless scalability of the solution for the automobile manufacturing company. Providing a centralized management platform, it streamlines bootstrapping, data consolidation, dashboard creation, and visualization of all aggregated data in one convenient location. Additionally, the platform efficiently oversees license and firmware updates, facilitates application deployment, and ensures optimal data storage, thereby maximizing return on investment.

The implementation of Ranial Systems’ solution significantly bolstered the automobile manufacturing company’s capabilities in responsive condition monitoring and machine optimization. Through the cloud application, stakeholders on the shop floor gain access to real-time and historical trends, enabling informed decision-making. Moreover, the system proactively sends real-time notifications via email and SMS upon detecting potential risks of catastrophic events. The implementation prioritizes intelligent monitoring, tailored to enhance machine health, reduce scrap, and augment utilization rates through AI application services.

 

4. RESULT:

The implementation of a cognitive IoT platform in the manufacturing process with the client has yielded significant results. By developing autonomous control and engineering assembly lines, real-time tracking capabilities have been enhanced, allowing for the immediate detection of anomalies and lowered unplanned downtime by 78%. The platform enables prompt notification of supervisors and engineers when issues arise, facilitating timely recalibration of equipment and avoidance of product defects. Leveraging real-time data, logistics planning has been streamlined, leading to improvements in overall equipment efficiency (OEE). Moreover, the cloud platform provides comprehensive insights into the assembly line’s efficiency, empowering production teams to optimize manufacturing processes effectively. Through the cognitive IoT platform, the client has achieved enhanced operational efficiency by 2.x, reduced downtime, and improved product quality, thereby reinforcing its competitive edge in the automotive industry.

Leave a comment