Automatic Rail Vehicle Inspection & Anomaly detection using Machine Learning
to
Collaborative R&D
Routine train inspection and maintenance is a continuous activity ensuring equipment is maintained to an acceptable safety standard. Preventing failure of expensive major components (engines, gearboxes, wheel sets, axle bearings) and safely maximising their service life is key to an efficient railway. Continuous automatic inspection based on multi-spectral imaging and computer vision algorithms using specialist cameras, lights and software can be used to detect faults and anomalies before components overheat causing irrevisble damage. Gobotix Vehicle Underframe Examination System - VUES, will uses an array of multi-spectral cameras to detect and report changes and anomalies in the physical state of the underside of a railway vehicle as it passes over the system. Each vehicle is identified by reading its RFID tag and its history recalled. Then, machine learning techniques are applied on the data to detect anomalies and use trending to highlight components which are nearing the end of their service life. VUES holds statistics and can identify trends and has knowledge of standard and safe operating ranges of components. VUES will enable an engineer to access this information through a web application or GUI and take action before a problem becomes serious. VUES removes the need for manual routine maintenance inspection and allows inspection to be automated and thus carried out much more frequently.
RAS for train fluid servicing
0
2017-12-01 to 2019-02-28
Collaborative R&D
This project will carry out proof-of-concept tasks necessary for the development of a robotic autonomous system (RAS) for fluid servicing of passenger trains. It will be designed by a collaborative team from TBG Solutions and Brunel University London with support from Chiltern Railways. The need for such a system is demanded by the expected 100% growth in rail passenger traffic over the next 30 years and consequent massive increase in train servicing demand. We will apply robust engineering design research to map out the RAS performance over the range of train port locations and representative environmental conditions. We will design a RAS interface that has greater throughput and zero spillage and cross-contamination of ports. Safety will be an important design aspect to provide for the optimum robot-human co-working environment. While the rail industry has not yet followed industries such as automotive in exploiting RAS developments, it can be an innovative solution to the increasing refuelling requirements of expanding train fleets.The application of RAS technology in this area will have a role to play in improving the service provided for the consumer. The project will serve to contribute to greater acceptance of RAS in the working environment with consequent economic and job quality benefits.
Get notified when we’re launching.
Want fast, powerful sales prospecting for UK companies? Signup below to find out when we're live.