Fleet Digitalization by Applying Data Analytics

Our client, a leading company in the machinery rental sector with a fleet of more than 800 machines, Data Analytics, Fleet Digitalizationdecided to embark on a FleetDigitalization process with B’Smart applying BIG DATA in collaboration with B’Smart. Prior to the implementation, the company faced constant challenges, with high levels of breakdowns, lack of visibility into machine performance, and reactive maintenance management significantly impacting productivity.

Results obtained through Fleet Digitalization applying BIG DATA

  1. 30% reduction in breakdowns: With the implementation of B’Smart’s fleet digitalization solution, our customer has experienced a 30% decrease in machine breakdowns. The ability to monitor the status of each machine in real-time has made it possible to proactively identify and address issues before they become major failures.


  1. 30% Productivity Increase: The company has managed to increase its productivity by 30% thanks to the detailed information provided by B’Smart. Tasks have been automated and digitized, such as capturing the fuel level of the machines at the departure and arrival of the delegations, and added as a field in the rental contract, being updated automatically. It is also possible, for example, knowing how many hours each machine works per month, and if they work more than 160 hours, (maintenance costs increase if machine working time increases), the time each machine spends in the workshop and how long it is rented, being able for example to prioritize the repair of the machines that produce the most value. This information has made it possible to optimize maintenance scheduling and improve operational efficiency.


  1. Return on Investment per Machine: B’Smart has provided its customer with the ability to calculate the return on investment for each machine. This includes detailed data on usage, maintenance costs, and profitability, allowing informed decisions to be made about refurbishing, repairing, or retiring specific machines.


  1. Segmentation of Utilization by Type of Machine: The company can now analyze what time of year machines are used the most, allowing them to segment utilization by machine type. This strategic information has facilitated seasonal planning and efficient fleet management.


  1. Deep Problem Analysis: B’Smart’s system not only presents data, but performs a comprehensive analysis of the entire fleet that reveals hidden problems. For example, the company can identify recurrence and the specific nature of problems, such as:


Diesel Machinery

    • Cost reduction by avoiding clogging of the particulate filter in diesel machinery.
    • Detection of temperature excesses, or with any other KPI outside the acceptable parameters for the proper operation of the machines.
    • Detection and disabling of the machine to avoid breakdowns due to lack of diesel.
    • Immediate detection of alternator failure



    • Detection of unbalanced loads
    • Overload and underload detection.

Electrical Machinery

    • Detection of lack of water in the electrolyte of traction batteries.
    • Monitoring of charge and discharge cycles in traction batteries (a lead-acid battery has a maximum of 1500 charges, therefore, there is an extra cost if it is charged more than once a day).
    • Inclinometer and overweight detection (lifting platforms)

Common to all machines: Geolocation via GPS, LBS, AGPS and WIFI, and solution with and without CAN BUS, and with specific solution for theft.

analítica de datos

Business intelligence through data analytics

    • Prediction of hours that a machine will work in the coming weeks or months and prediction of hours that a machine will break down and spend in the workshop, which will allow better resource planning.
    • Predictive maintenance: Prediction of when a machine is going to break down, automatically creating alarms based on certain KPIs and therefore allowing you to anticipate the breakdown and avoid unnecessary machine stoppages.
    • Which machines work the most in a certain period of time, and, therefore, what is the repair priority.
    • About machines of a certain type, which is the machine that has worked the most, and the one that has worked the least?
    • Which are the machines that work more than 160 hours/month and, consequently, require more maintenance with the increase in costs that this entails.
    • Which are the machines that break down the most, what type of breakdown they suffer, and with what recurrence.
    • Of the entire fleet, what are the brands and models that break down the most? And the ones that break down the least?
    • What are the most common causes of breakdowns?
    • What is the failure rate based on the working hours of a given machine or group?
    • Which machines have the highest performance at the business level?
    • Find out what your business’s Co2 footprint is and broken down by machine.
    • Automatic detection of anomalies in machines.

Increased productivity through the automation and digitalization of processes associated with the fleet

    • Automated fleet stock control between delegations.
    • Capture of the diesel level and other important parameters of the machine at the exit and entry of the machine into the delegation.
    • Automated generation and sending of invoices for machines working on weekends.
    • Control of revisions, including what has been done in them, and what materials have been used.
    • Inclusion of manuals and other technical information at the click of a button on the same platform.
    • Any other manual and repetitive process can be automated and digitized.

It is important to note that all this data is obtained automatically directly from the machine and is available on our platform at the level of a click.

Comments from the Management Team on Fleet Digitalization applying Business Intelligence through data analytics:

Workshop Leader: “Prior to working with B’Smart, we were dealing with a high level of stress due to constant breakdowns. The lack of visibility kept us in reactive mode. Now, with B’Smart Fleet Digitalization, I can proactively manage maintenance, significantly reducing disruptions and improving workshop efficiency. I would also highlight that we have all the information, including real-time data analytics on the same platform, and without having to carry out any calculations, which facilitates and accelerates decision-making.”

CEO: “The implementation of B’Smart’s Fleet Digitalization service has been a key strategic decision for the business. By adopting this solution, we have not only achieved complete monitoring of our machines, but we have also moved towards a smarter business model. The choice of B’Smart as a strategic partner is based on the confidence that it is a technologically advanced and innovative company, positioning it as a leader in digitalization within its sector. This pioneering approach will undoubtedly boost the company’s operational efficiency and competitiveness in an increasingly digital business environment.”

Predictive Maintenance: B’Smart’s system not only provides historical data, but also uses BIG DATA and Machine Learning techniques to perform predictive maintenance of the machines. It automatically projects the necessary maintenance based on the accumulated data, giving us a vision of the future that allows us to address potential problems before they affect the operability of the machines.

In short, the collaboration with B’Smart has transformed the management of our fleet and associated processes, delivering operational efficiency, cost reduction and a clear view of the profitability of each machine. This case study highlights how Fleet Digitalization with B’Smart can make a difference in the long-term competitiveness and sustainability of companies.