Using AI and Machine Learning for Improved Fleet Performance

January 29, 2019 Sriranjani Ramakrishnan

 

Introduction 

Artificial Intelligence (AI) and Machine Learning (ML) have reached a pivotal point for their impact on businesses, consumers and society. AI serves as both a catalyst and an outcome of increasing consumer expectations for more personalized, pervasive and intelligent experiences in every area of our lives. 

No industry remains untouched by the real-world applications of AI — intelligent solutions that can sense, learn and interpret human behavior and complex situations. AI is augmenting the human experience by assisting, making, or even acting on critical decisions — transforming intelligence, perception and decision capabilities across every area of our lives. 

ML-based approaches can automate analytical model building using data analysis and enable software applications to become more accurate in forecasting outcomes without being specially programmed.  AI using ML is like having a team of automated eyes and ears with analytical and predictive abilities. Whether monitoring data coming from a fleet of vehicles, manufacturing equipment, medical devices or health monitoring devices, AI/ML can provide feedback on any modification. For this discussion, we’ll focus on the monitoring of public transportation fleets. 

 

Predictive Solutions 

Unforeseen incidents occurring to public transit fleet vehicles can cause inconvenience to commuters as well as financial loss to the operating agency. These incidents also create traffic congestion and reduce roadway capacity. Each minute of freeway lane blockage leads to four to five minutes of traffic delay until it is cleared. Moreover, longer incident duration often leads to secondary incidents.  Hence, it is crucial for transit agencies to have efficient insight and maintenance management strategies. These strategies help them proactively reduce the number of unexpected incidents, and avoid financial loss, customer dissatisfaction and possible life-threatening situations.  

Conduent has developed a ML automation model that uses data obtained from sensors installed on vehicles and maintenance data to predict the occurrence of equipment breakdowns or component failures before they happen. Predictive solutions enable agencies to have better and more complete maintenance schedules for their vehicle fleet as well as better planning for contingency vehicles in case of unavoidable breakdowns. 

These AI insights are unique in their ability to include operational attributes such as the load of the vehicle, number of trips and number of repairs of the vehicle for modeling. A predictive automation model proactively manages maintenance, improving operational costs for transit agencies and reducing breakdown delays and traffic congestion.  

 

Conclusion   

As the digital future of equipment-based industries unfolds, there’s one thing we can count on: data will continue to provide insights for proactive action resulting in increased efficiency. From IoT-based vehicle maintenance to ML models and omnichannel customer experience, companies will continue to rely on vast amounts of data to make the decisions that matter to them. 

The Conduent Analytics Platform brings together the core capabilities of today’s most powerful AI technologies, enabling smart solutions across our offerings to augment and enhance human work.  

We’re helping our clients across many different industries manage transactions and interactions with their customers to optimize outcomes by leveraging these and other publicly available data assets. We collect, manage and use big data assets every day, to help clients quickly and easily derive insights and take action by applying highly sophisticated data processing, modeling and analytics capabilities.  
 
Conduent can also help your company leverage AI in your business, to achieve your business goals — for your employees, customers and other stakeholders, and to create a roadmap for the future. To learn more, visit our innovation page.  

 

About the Author

Sriranjani Ramakrishnan - Scientist, Computer Science Engineering

More Content by Sriranjani Ramakrishnan

No Previous Articles

Next Article
Solving the Mystery of Parking with Big Data
Solving the Mystery of Parking with Big Data