Robotic Railway Multi-Sensing and Profiling Unit Based on Artificial Intelligence and Data Fusion

Abstract

This article presents the research and results of field tests and simulations regarding an autonomous/robotic railway vehicle, designed to collect multiple information on safety and functional parameters of a surface railway and/or subway section, based on data fusion and machine learning. The maintenance of complex railways, or subway networks with long operating times is a difficult process and intensive resources consuming. The proposed solution delivers human operators in the fault management service and operations from the time-consuming task of railway inspection and measurements, by integrating several sensors and collecting most relevant information on railway, associated automation equipment and infrastructure on a single intelligent platform. The robotic cart integrates autonomy, remote sensing, artificial intelligence, and ability to detect even infrastructural anomalies. Moreover, via a future process of complex statistical filtering of data, it is foreseen that the solution might be configured to offer second-order information about infrastructure changes, such as land sliding, water flooding, or similar modifications. Results of simulations and field tests show the ability of the platform to integrate several fault management operations in a single process, useful in increasing railway capacity and resilience.

Keywords: data fusion; infrastructure failure detection; machine learning; multisensory platform; railway automation; statistical data filtering.

Figure 1

General functional blocks diagram of the autonomous cart.

Figure 2

Sensitivity over distance for the obstacle detection sensor (reference target: white paper).

Figure 3

Shape and main dimensions for the Bucharest Underground Gauge (transversal section, a typical section of a tunnel, semi-rectangular section. There are also ovoidal and circular sections).

Figure 4

Frontal view of the equipment.

Figure 5

Detail with lateral view: web camera above, obstacle and fire/smoke detection modules.

Figure 6

Detail for gauge assessment module with LIDAR scanner and obstacle detection module (ultrasonic).

Figure 7

Test bed setup, placement of sensors and elements measured.

Figure 8

Direct data sampling from XL Maxsonar EX sensor measurements.

Figure 9

Gauge measurement with LIDAR, (a) tunnel gauge profiling, (b) third rail (used in subway for power supplying), (c) lineside box equipment (LDE) gauge measurement (LDE is mounted on the tunnel wall, round-shaped subway tunnel profile between stations).

Figure 10

Diagram showing the variation of distance measurements between three sensors.

Figure 11

Implementation of the KPCA algorithm for feature manipulation.

Figure 12

The results obtained for reducing the database size using the KPCA algorithm.

Figure 13

Software implementation of the PCA T²Q training algorithm.

Figure 14

Results of the training templates using PCA T²Q.

Figure 15

The software architecture for the detection of defects and anomalies.

Figure 16

Ultrasonic sensors for detection of small obstacles. Reflection received from targets larger than the wavelength (a), and error of detection for smaller objects than the wavelength (b).

Figure 17

Variations of the relative error for obstacles of different sizes. Error of detection for objects 60 mm wide (a), 40mm wide (b) and 20 mm (c). Error increases inversely with the object width.

Figure 18

Obstacles of various forms.

Figure 19

Measuring the distance to obstacles of different shapes. (a): variation error for rectangular objects, (b): variation error for triangular prism, (c): variation error for cylindrical object.

Figure 20

Relative error variation for different materials.

Figure 21

The difference between the real shapes (right) and those determined by the radar (left).

Figure 22

Pre-processing steps of the acquires ultrasound signals.

Figure 23

Determining the mechanical deformations of rails based on ultrasonic sensors.

Figure 24

Ultrasonic measurement technique (a); data acquisition amplitude modulated scan; (b) ultrasonic imaging for the analysis of rail fracturing inside the subway line.

Figure 24

Ultrasonic measurement technique (a); data acquisition amplitude modulated scan; (b) ultrasonic imaging for the analysis of rail fracturing inside the subway line.

Figure 25

The flow chart of the proposed algorithm.

Figure 26

Feature manipulation reducing the database size using the KPCA algorithm.

Figure 27

Estimation of rails anomaly detection and predicted result—machine learning modeling using PCA with T²Q and ultrasonic sensors.