How Swiss Federal Railway Is Improving Passenger Safety With The Power Of Deep Learning

SBB’s traditional data processing approach was conducted in real-time on the diagnosis train, which produces an excessive rate of false positives and negatives — to the extent that railway experts still need to go onto the track to physically inspect anomalies. This requires a lot of human labor, with people operating in dangerous environments that are sometimes impractical to access.

SBB partnered with CSEM (Swiss research and development center) to address this challenge by initiating the “Railcheck” project, which aims to use deep learning technologies to:

The first and very important step is to have the right data, which serves as the “new source code” for deep learning problems. CSEM went through the following process to make sure their data pipeline would enable a successful deployment:

1) Data Gathering. SBB is planning to inspect 3,800 km of track per month by the year 2020. Images capture different weather conditions (rain, snow, ice) and artifacts (leaves, dirt, etc.).

2) Preprocessing. A model is trained to detect regions of interest (for example, railway beams, clamps) in the images.

3) Anomaly Detection. CSEM used generative adversarial networks (GANs) — which consist of deep neural net architectures composed of two networks, pitting one against the other — to define clusters within datasets. These clusters were then used to identify anomalies in railway components.

4) Fault Detection/Classification. Classification requires supervised learning. There are, in principle, about 20 different fault categories, but SBB decided to simplify it to five categories (that is, welding, joint, surface defect, squat, wheel slip) since determining the appropriate fault category is not always trivial.

5) Data Labeling. As is common with many businesses starting with deep learning, very little labeled data was available when the project started. Additionally, certain fault categories require the judgment of well-trained railway experts who may not always agree. As a solution, CSEM decided to apply a crowd-sourced approach to decision-making:

By doing the above steps iteratively, the model accuracy improves over time, in what is known as lifelong machine learning.

NVIDIA DGX Station, the purpose-built AI workstation, has played a significant role behind the scenes, helping accelerate deep learning training and improving detection accuracy.

“DGX Station just works! It was up and ready within a few hours,” says Nathalie Rauschmayr, a machine learning engineer at CSEM. “The best part about the DGX Station is it’s a complete system with the latest and most optimized deep learning frameworks. Instead of worrying about how to configure many low-level components on the system, I can focus on gathering the right data, training the AI workloads, and working with experts to identify faults accurately.”

To learn more about Swiss Federal Railway’s deep learning journey, join us in this upcoming webinar for more detailed insights.

On a daily basis, Swiss Federal Railway (SBB) manages 15,000 trains, serving 1.2 million riders on 4,000 miles of track.