ST. LOUIS, MO – Metro St. Louis is partnering with Accenture to develop a pioneering system the two companies claim could "shape the future of fleet vehicle maintenance."
The system, known as Predictive Monitoring, uses sensors and statistical analysis in a pilot project aimed at forecasting bus equipment failures before they occur. It marks the first such project in the public transit industry.
“This represents a significant leap forward in the field of business insight,” said Bob Suh, Accenture’s chief technology strategist. “Today most businesses and organizations rely on older data. Predictive monitoring shifts the orientation by capturing data in real time, and using the information to preview the future.”
For instance, bus fleet operators such as Metro St. Louis, which owns and operates the city’s public transportation system, could cut costs and improve system-wide performance by reducing vehicle failures and enhancing maintenance schedules.
Under the pilot project launched in February, 20 Metro buses have been equipped with sensors that monitor engine and transmission information. The information is stored electronically in data collection boxes installed on the buses. The data are downloaded and sent electronically to computers at Accenture’s research and development facility, Accenture Technology Labs, in Chicago for analysis.
Once at the Labs, the data are evaluated by an analytic engine – software that compares a snapshot of the buses’ operational data with an analytic model that reflects ‘normal’ operating behavior. When the software identifies potential issues, it automatically notifies Metro St. Louis maintenance personnel via e-mails, pages or website alerts. Metro can then determine how to react, performing maintenance at an appropriate time to minimize service disruption and costs. The system is more accurate and sensitive than other approaches, identifying deviations and operating anomalies in the engines and transmissions before costly problems occur.
The pilot project has already yielded results that underscore the system’s potential. For example, it provided advanced warning that one bus had an overheating hydraulic retarder, part of the transmission system. While the problem was not severe or dangerous, the early detection could prevent a minor problem from growing into a costly repair.
“We’re a progressive transit organization committed to enhancing passenger convenience,” said Dianne Williams, Director of Communications for Metro St. Louis. “While our maintenance facilities are recognized to be among the best in the country, there’s always room for improvement. We are enthusiastic about the pilot project’s early results.”
In addition to reducing vehicle failures and maintenance expenses, predictive monitoring can also extend vehicle life by customizing, for each vehicle, the intervals between scheduled maintenance and overhauls. “By performing maintenance on each bus when needed, the life of the bus and parts can be extended, which decreases the overall cost of ownership,” said Baiju Shah, who directs Accenture Technology Lab’s Predictive Insight practice.
When the pilot is completed later this spring, Metro St. Louis will determine if it plans to go forward with the fleet-wide rollout. Accenture plans to package and sell the system to other transit organizations.
“The technology has shown exceptional results in other industries, including power generation, aviation, and chemicals,” said Shah. Added Tom Dutton, Director of IT Operations Systems of Metro St. Louis: “We hope to enjoy similar results. We’re very excited about the long-term benefits we could realize with predictive monitoring.”
Accenture partially funded the pilot in order to prove the technology concept. For its part, Metro St. Louis contributed time and service credits from a previous project with Accenture.
Supporting Metro St. Louis and Accenture on the project are technology partners SmartSignal Corporation for data analytics, Orbcomm for satellite service and Quake Global for sensor translation.
Have your say
We won't publish or share your data