IoT and AI boost Volvo Trucks vehicle connectivity

The vehicles manufactured by Volvo Trucks keep getting smarter.

More than 350,000 Volvo rigs crossing North American highways each day are outfitted with IoT sensors that monitor conditions and send data for troubleshooting and analysis. Embedded telematics allow for over-the-air updates to engine software. The on-board technology, combined with a back-end analytics platform, enables Volvo Trucks to process millions of data records instantaneously. Using IoT and artificial intelligence, Volvo Trucks has been able to reduce diagnostic time by 70% and truck repair time by 25%. 

For fleet managers, the biggest benefit is improved uptime. “With more effective and proactive maintenance, Volvo Trucks can help customers maximize vehicles’ time on the road and minimize the costs of service disruptions,” says Conal Deedy, director of customer productivity solutions at Volvo Trucks North America, which is part of Swedish multinational manufacturing company Volvo Group.

Volvo Trucks’ vehicle connectivity capabilities are eight years in the making. Its initial foray into connected trucks began in 2012, when it developed a remote diagnostics service that allows customers to transmit information to and from their trucks and monitor mechanical fault codes in real-time. Shortly after launching its diagnostics service, Volvo Trucks unveiled a remote programming service that allows for over-the-air software and parameter updates via cellular service.

Fault codes are triggered when something goes wrong with one of a vehicle’s major systems, such as the engine or transmission. Sensors on each truck collect streaming IoT data in real time to provide context. This data includes where a mechanical event happened and what conditions were present during the fault, such as altitude, ambient air temperature, RPM level, and torque load. The goal is to provide faster, more comprehensive diagnostics and repairs than traditional “set-mileage scheduled” service appointments, while at the same time giving fleet operators information about driving habits, fuel consumption, truck performance, and other factors.

Over the last few years, Volvo Trucks has focused on improving and expanding its analytics capabilities. It partnered with analytics vendor SAS to deploy a more advanced platform that leverages event stream processing and AI. “The SAS analytics platform gives Volvo Trucks a way to define complex rules to improve how its remote diagnostics cases are created and acted upon,” Deedy says.

Where the data goes

Each Volvo truck in North America that’s equipped with remote diagnostics has hundreds of sensors, about 75 of which are monitored closely because the analytics have determined that those sensors provide useful information on critical failures. The trucks send the data to a telematics communication gateway, using an over-the-air cellular network.

The proprietary gateway “is designed to access the core data networks within the trucks in order to reliably collect and store data without interfering with truck operations,” Deedy says. Key data is transmitted directly to Volvo Trucks’ dedicated servers, which translate the information for further processing.

Any data that indicates a mechanical fault is sent in near real time to an inbound message queue, where it is picked up and processed by the SAS Event Stream Processing engine over a 10Gb network.

The SAS system applies analytical-based rules and can trigger the creation of support cases via an outbound message queue. Volvo Trucks’ ASIST system, a Web-based service management platform, picks up messages from the outbound message queue to process customer notifications.

“The rules engine analyzes and applies complex business rules to streaming fault data in motion,” Deedy says. Customers are then notified of faults by a Volvo Trucks Uptime Center employee via email, text, or phone. “All of the data capture and processing are done within Volvo Trucks’ firewalls to ensure data security.”

The system processes 1.5 million fault alerts per day, with each alert containing 30 to hundreds of data items such as powertrain sensor readings. The event stream processing by SAS triggers some 4,000 rules each day, including about 3,000 updated cases and 1,000 new cases.

Another component of the system, SAS Asset Performance Analytics, is an analytics engine Volvo Trucks uses to examine historical fault data. Managers can use the analysis capabilities to refine parameters in the rules engine, perform data selections, and report on historical fault data.

The analytics engine stores 8 terabytes of data and holds historical fault data from 2015 through the present. These faults, now totaling about 1 billion, have been generated from a growing fleet of connected trucks—currently 350,000—over that time period. One and a half million faults are added to the analytics engine each day.

The SAS platform, which took about 11 months to deploy because of the complexity of the operation, is built on a cluster of high-performance servers that use in-memory technologies and low-latency/high-throughput solid-state drives.

The AI capabilities have enabled Volvo Trucks to uncover hidden insights in the collected data and merge it with the truck knowledge of its engineering group. That puts the company in a much better position to understand exactly what the data is saying and integrate it into the remote diagnostics service. The SAS analytics deployment has cut down significantly on false positives and improved Volvo Trucks’ diagnostic accuracy.

Challenges/benefits of vehicle connectivity

Volvo Trucks had to overcome some challenges to execute its connectivity strategy. One hurdle was ensuring seamless collaboration among multiple parties, including Volvo Trucks; HCL Technologies, an IT services provider that acquired Volvo’s external IT business in 2016; SAS; and HPE, whose hardware is used to run the SAS software. Volvo Trucks took a “one team” approach and identified key resources from each party to work together on major developments.

One of the biggest technical issues was integrating SAS rules-processing technologies into existing Volvo Trucks’ processes and systems. The telematics infrastructure and ASIST system were already built and proven entities at Volvo Trucks. Modification of these systems required that the SAS technology plug in seamlessly with these systems. To make it happen, Volvo Trucks created detailed requirements for gathering data and relied on the flexibility of SAS event stream processing to integrate with its internal systems. It worked closely with SAS professional services and R&D teams to handle implementation of the complex rules.

For reliability, Volvo Trucks opted to use the failover capabilities of the SAS analytics engine and integrate it with Apache Kafka, an open-source stream-processing software platform. A standby server will process data if the primary event stream processing server goes offline. Data is saved in Apache Kafka for a defined retention period, so that if both servers go offline, the servers can reprocess time-based rules and catch up upon restart.

Advancing the strategy

Volvo Trucks continues to push forward on its connectivity strategy. The company recently unveiled its Dynamic Maintenance service, created with IoT vendor partner Noregon. The service uses existing connected technologies and data analytics, combined with Noregon’s platform, to provide customized service plans down to the individual vehicle level to improve fleet operations efficiency.

Another new service is Geotab Drive for Volvo Trucks, an electronic logging device (ELD) developed with telematics and IoT company Geotab that provides customers with a tool to monitor and record driving logs, such as vehicle inspection reports. The key benefit is the ability to deliver accurate logs in compliance with the ELD mandate of Federal Motor Carrier Safety Administration (FMCSA) regulations.

Volvo’s factory-fit telematics device works in combination with Geotab’s ELD cloud-based application to provide data capture and delivery. Fleet managers can access ELD data through a MyGeotab portal, so they can keep track of fleet compliance with real-time data, with the ability to view detailed reports on driver logs, violation alerts, and running reports on the status of a fleet.

Most ELDs deliver data through Wi-Fi or Bluetooth-based systems, Volvo Trucks says, but Geotab Drive operates over a cloud-based system that it says provides customers with more reliable ELD data-capture capabilities.

Volvo Trucks also introduced the Parameter Plus subscription package, a supplement to its remote programming service. The package leverages the company’s embedded telematics and allows fleet managers to do more over-the-air updates to engine parameters and software via cellular networks, which cuts down on interruptions to driving schedules. The package was designed based on feedback from customers. Previously, parameter and software updates could require two or more days of downtime along with added work and costs. With the new service, powertrain software updates can be completed in less than 20 minutes.

“All of these efforts are designed to make the company a leader in commercial vehicle connectivity,” Deedy says.