BACKGROUND & PROBLEM STATEMENT:
In heavy industrial engineering, a leading engine company faces challenges with down time and prolonged onsite maintenance and repair of its diverse automotive and construction equipment. Lengthy inspection and repair cycles lead to extended downtime during unplanned shutdowns, compounded by the inaccessible data within their machinery. Partnering with Ranial Systems, they aim to implement the CognitIoT™ platform for seamless connectivity and proactive issue detection. Through this collaboration, they anticipate reducing downtime, improving operational efficiency, and maximizing asset lifetime value and maintenance lifecycle.
APPROACH:
To address the challenges encountered by the global engine
manufacturing company, an approach involving the implementation of a Cognitive IoT edge controller was proposed. This solution enables seamless integration of automotive and construction equipment with over 30 sensors via connected OBD sensors using a CAN-based communication protocol. Real-time condition-based monitoring, predictive and prescriptive insights, along with remote automated detection capabilities, would be provided.
The aim was to preemptively identify potential failures, autonomic shutdown to prevent catastrophic breakdowns, and minimize downtime, ultimately optimizing machine performance and improving energy efficiency. The cloud platform was designed to perform 24X 7 monitoring of the assets, aggregate and broadcast the intuitive alerts and notifications and perform remote command and control functions.
SOLUTION:
In response to the challenges faced by the global engine manufacturing company, Ranial Systems implemented a comprehensive solution leveraging its Cognitive IoT platform. The process began with the edge device collecting data from OBD sensors installed on the automotive and construction equipment. This data was then utilized to train machine learning models, enabling the system to analyze patterns and predict potential failures/ fault conditions at the point of action. After rigorous testing to ensure model accuracy and performance, the AI-powered mod
els were deployed directly onto the edge device, enabling incremental learning of the model over time to improve the accuracy of real-time analysis and decision-intelligence at the source of data generation. This approach allowed for efficient event processing and immediate response to emerging issues, minimizing downtime and optimizing maintenance schedules.
The patented platform, CognitIoT™, facilitates seamless scalability of the solution for the engine manufacturing company. It provides a centralized management platform for streamlined bootstrapping, data consolidation, dashboard creation, and visualization of all aggregated data in one location. Additionally, the platform efficiently manages license and firmware updates, facilitates application deployment, and ensures optimal data storage, ultimately maximizing return on investment.
The implementation of Ranial Systems’ solution has significantly enhanced the client’s capabilities in responsive condition monitoring and machine optimization. Through the cloud application, real-time and historical trends are displayed to share operating status with stakeholders on the shop floor. Furthermore, the system sends real-time notifications via email and SMS upon detecting potential risks of catastrophic events. In its early phase, the implementation prioritizes intelligent monitoring and is tailored to improve machine health, reduce scrap, and enhance utilization rates through AI application services.
RESULT
The implementation of Ranial Systems’ Cognitive IoT solution has yielded remarkable results for the global engine manufacturing company. By mounting automotive and construction equipment with Cognitive IoT edge controllers and integrating over 30+ sensors, the company achieved real-time condition-based monitoring to perform remote troubleshoots addressing 60% of the maintenance tickets within 24 hours. With a previous cycle time of two weeks for inspection and repair during unplanned shutdowns, the system introduced remote automated detection capabilities, enabling the detection of potential failures ahead of time to prevent catastrophic breakdowns and minimize downtime. As a result, the company maintained an impressive 90% uptime by preemptively detecting potential failures. Moreover, the Cognitive IoT implementation significantly reduced repair timelines by 43% through early indication diagnosis of potential problems. Leveraging a cloud-based system with a single pane of glass interface, the company received real-time notifications and alarms upon detecting anomalies, further enhancing operational efficiency and minimizing risks. Overall, the effectiveness of the Cognitive IoT solution has revolutionized the company’s maintenance practices, optimizing asset performance, and ensuring continuous productivity.