A single bus journey pollutes 82% less than the same journey by car.
For this reason, a small decision like taking public transport instead of driving is a big step towards lowering emissions. If we then consider the significant reduction in greenhouse gas emissions that transport operators can achieve by implementing eco-driving solutions or by transitioning to electric vehicles, choosing the bus over personal vehicles becomes an even more sustainable choice. Transport operators are already moving in the right direction in terms of minimising the environmental impact of their services, and they’re doing so by leveraging vehicle data.
The bus is essentially a black box, where vehicle technical data is locked and remains largely inaccessible to transport operators. However, by automating the collection and analysis of this data, fleet managers can rely on artificial intelligence (AI) and machine learning (ML) algorithms to implement a predictive maintenance approach. This means that vehicle sensor data can be turned into actionable insights to help reduce the carbon footprint of internal combustion engine (ICE) buses, hasten the transition to zero-emission transport, and minimise breakdowns and downtime, resulting in a more reliable public transport service.
Car vs Bus
With cars representing 72% of EU road transport emissions, it’s key to make public transport the preferred form of travel. However, in order to create a push towards shared mobility and leverage the environmental benefits of public transport, operators and public transport agencies need to ensure it can live up to the promise of reliability, getting passengers where they need to be, when they need to be there. To guarantee reliability, it is necessary to turn our attention back to the most crucial component of public transport: the vehicle.
AI predictive maintenance is like a digital stethoscope for buses, enabling operators to tune in to the state of health of their vehicles’ critical systems and components. By collecting the data from built-in vehicle sensors and analysing the patterns that indicate the condition of components, maintenance managers can leverage real-time, actionable insights to inform their decisions. AI can identify tricky faults that humans could overlook – tracing leaks in the compressed air system or the wear and tear of brake pads, for example.
With such a system in place, bus operators can depend on real-time monitoring to assess whether their vehicles’ brake pads need to be replaced, meaning that parts can be ordered in bulk and that maintenance can be scheduled during off-peak periods to avoid service disruptions. Maintenance and repairs can be scheduled automatically and more accurately, contributing to better fleet utilisation and cost savings. More importantly, by preventing equipment failure, vehicle breakdowns can be pre-empted to reduce downtime and protect both revenue and customer experience.
Reduced resource consumption & enhanced asset lifecycle management
The data on equipment behaviour, failure modes, and degradation patterns can also inform asset management strategies, including engineering decisions related to repair, replacement, or refurbishment of components and systems. By extending the useful life of assets and maximising their performance, operators can minimise waste generation, reduce the need for new equipment production, and lower the environmental impact associated with resource extraction, manufacturing, and disposal.
Moreover, early identification of sub-optimal operating conditions enables engineers to fine-tune equipment settings, adjust operational parameters or identify faulty components, reducing energy consumption and resource waste. By optimising resource utilisation, operators can function at higher energy efficiency, reduce carbon emissions, and enhance the overall sustainability of their operations.
Curbing ICE emissions
Predictive maintenance solutions can also be used to inform eco-driving strategies to further reduce the carbon footprint of ICE bus road usage. By analysing driver patterns, optimal RPM and idling time, operators can implement strategies to lower fuel consumption and put in place a range of continuous improvement processes. Arriva Czech Republic has recorded a saving of 942 litres of diesel per vehicle per year using this approach. This equates to 2.6 tons of carbon dioxide emissions avoided per vehicle, per year.
Speeding the transition to EVs
For transport operators, new EV technology poses challenges as well as opportunities. It comes with new breakdown patterns and failure modes and requires a new knowledge-set to minimise life cycle costs and optimise battery maintenance and route management. Additionally, the greater up front, maintenance and infrastructure costs of the transition mean that operators must have a detailed strategy in place to minimise the impact of the shift on their bottom line.
Just as with their ICE counterparts, by combining the granular collection of vehicle data and large-scale data processing with autonomous AI systems, public transport operators can gain valuable insights from the new EV data they have access to, creating a continuous feedback loop that constantly increases the ways in which data can be leveraged. The performance, faults, and range of EVs can be analysed and used to inform the planning of smooth, efficient, and profitable operations.
Predictive battery analytics for example can provide an accurate, comprehensive view of the battery health evolution of an EV bus, allowing for effective route planning and charging requirements, as well as usage optimisation metrics to extend the lifespan of the vehicles. This is crucial given the high proportion of the overall cost of an electric bus that the battery represents. By leveraging State of Charge (SoC) and Depth of Discharge (DoD) data, fleet managers can understand if the operation profile can be changed to maximise battery life, reducing the total cost of ownership of electric buses. This type of analysis is fundamental for an operationally successful and profitable EV fleet deployment.
The future of AI and ML for public transport
By onboarding next-gen AI and ML predictive maintenance technology, the future of sustainable, affordable, and highly efficient public transport is promising. The actionable insights on potential component failures, fuel consumption and operational efficiency offer full control over the health of both ICE and electric buses. This can be harnessed to enhance reliability, encourage passengers to move away from private car usage, curb emissions and wastage through inefficient driving and maintenance strategies, and pave the way for a smoother and faster transition to EV usage.
AI is constantly learning, picking up data about different categories of vehicle and enabling fine tuning for improved operations. It is a system that will keep on growing with huge benefits and impact, contributing to the goals of sustainable and reliable public transport. With some operators already implementing predictive maintenance, the approach will become more ubiquitous in 2023 and beyond, representing the new frontier when it comes to smoother, more efficient and environmentally friendly operations.
