Peer review: Bhoopathi Rapolu
Head of Analytics EMEA, Cyient
This article went into a lot of detail about data collection and topics such as innovation, accountability, ownership and future trends. However, I would like to touch on a couple of points that I feel could have been explored in further detail.
Firstly, while the coverage of data sources was very detailed, all of the examples used referred to the consumer side of the industry. I would like to have seen more consideration being given to how data is being used in the operational side of the railway.
Operations and Maintenance (O&M) in the rail industry has undergone revolutionary changes in the past few years, in terms of data collection and application of that data for Condition Based Monitoring (CBM) and Predictive Maintenance (PM). CBM is a strategy that assesses the condition of each component to decipher what maintenance needs to be done and when best to carry it out. PM takes this one step further, by identifying looming faults and forecasting the optimal time for maintenance, enabling action to be taken before a fault occurs.
Recently, there has been a significant increase in data collection from signalling systems, network and wayside assets. Huge advancements in sensors and communication technologies have been made in the past few years that have led to continuous data collection from various systems and subsystems in trains. These enable mechanical and electrical conditions, operational efficiency and multiple other performance indicators to be monitored 24/7, allowing maintenance activities to be planned with the maximum interval between repairs, while minimising the number and cost of unscheduled outages created by system failures.
Secondly, the section on data source classification could have been a little clearer. Of course, there are different ways to classify different types of data in the rail industry, but a dataset is either quantitative or qualitative. Anthony refers to passenger ticketing data as a third distinctive group, whereas it should really be taken as quantitative data. Yes, there is a significant amount of passenger data to be considered, but when you compare this with the sheer volume of machine data being generated from trains in real-time, the size is irrelevant - it should all still be classified as quantitative.
Finally, while the various methods of data collection were covered in depth, it would have been beneficial to hear a greater analysis focused on the application of this data and the resulting benefits to both the industry and passengers.
There could have been more discussion around how that data was being used and what benefits had been realised so far. The benefits of using data in PM are significant, as it can help increase the availability and reliability of train services and reduce maintenance costs. This is especially important at a time when there is such a spotlight on network operators to improve the quality of service for passengers. PM enhances the overall effectiveness of transportation systems, ultimately leading to improved safety and higher customer satisfaction.
Overall, the piece was very informative and engaging, but could have built further on aspects such as how machine and sensor data is being collected and used in the operational side of the industry for CBM and PM, and some of the benefits of this - both to the rail industry as a whole and to passengers on the trains.
