With the newest release of Syncron Uptime, Ashok Leyland is set to leverage advanced industrial predictive maintenance capabilities for increased product reliability and decreased downtime. 

Syncron, a privately-owned intelligent SaaS solutions company, dedicated to Service Lifecycle Management (SLM), announced its partnership with Ashok Leyland. As the second largest manufacturer of commercial vehicles in India and the fourth largest manufacturer of buses in the world, Ashok Leyland’s fully integrated manufacturing footprint extends across 50 countries and is fueled by a constant drive for efficiency, cost control, quality, reliability, and innovation – the same attributes that Syncron’s solutions address.

Alignment between Syncron’s extensive experience in the automotive, service, and parts industries and Ashok Leyland’s advanced machine learning models and sensor data led the companies to work on developing an industrial IoT-enabled predictive maintenance solution for the manufacturer’s extensive fleet of vehicles. As a part of the partnership, Syncron is integrating an anomaly detection model into Ashok Leyland Condition Monitoring Systems (CMS) for a highly effective, completely connected vehicle solution that will potentially fuse predictive analytics with more accurate and relevant prediction processing to improve product reliability.

In support of the partnership, Syncron has released new capabilities for Syncron Uptime that further enable manufacturers to leverage a proactive “react before failure” approach by predicting and resolving issues before downtime occurs. Additionally, Syncron Uptime now goes beyond aggregating and analyzing data to offer a personalized recommendation for issue resolution by domain experts.

“In a highly competitive market where vehicle uptime and total cost of ownership are critical to both sales and customer trust, our priority is to develop innovative ways to improve the customer experience through digital transformation that includes early resolution of potential failures,” says Dr. N Saravanan, Chief Technology Officer, Ashok Leyland. “We look forward to our partnership with Syncron further enabling our reliability engineers to identify failure and degradation problems earlier, maximize uptime, and deliver the exceptional products and service our customers expect.”

New functionality:

  • Virtual Sensor Framework: To capture a complete picture of equipment performance, new formula-based Virtual Sensors with advanced machine learning (ML) Model predictions and anomaly alerts have been added.
  • Data Validation: Increasing the accuracy of ML predictions, Syncron Uptime now includes a data validation framework through which data scientists can accept or reject values
  • Aggregation Algorithm: Applying the right aggregation strategies is significant to enabling efficient anomaly and failure prediction analysis. Uptime now picks the most critical data for in an aggregated view for anomaly analysis.
  • Rule-Based Data Filter: Data scientists can use rule-based filtering to control the noise from non-operational equipment and enable more accurate, relevant prediction processing.
  • Prediction Window: Users can now visualize the major contributors to high anomaly scores in sensor readings and automatically perform root cause analysis to gain meaningful insights from prediction windows.

“As manufacturers shift from a reactive break-fix model towards a predictive and proactive one, they look to leverage data from connected products and gain actionable insights using advanced AI/ML technology,” says Ashok Kartham, Chief Product Officer (CPO), Syncron. “Through this partnership with Ashok Leyland, we hope to equip their customers with Syncron Uptime’s powerful failure detection technology in order to get ahead of the equipment failure, thus improving product uptime and customer service satisfaction.”

Over the next three years, Syncron and Ashok Leyland aim to scale the number of vehicles equipped with Uptime and to use advanced machine learning and artificial intelligence tools for prognostic recommendations and allow service and parts functions to leverage data for proactive maintenance.