Asia Mobiliti demonstrates predictive analytics features for advanced railway track condition monitoring with KTMB

  • Live testbed first-of-its kind in Malaysia with solution developed in-house
  • Digital twin of tracks allows rail operators to adopt predictive maintenance

Asia Mobiliti engineers in front of a KTMB rolling stock.

Asia Mobility Technologies Sdn Bhd, a leading mobility-as-a-service and Internet of Things (IoT) solutions provider, has successfully completed a live testbed programme for railway condition monitoring with Malaysia’s largest railway operator, KTM Bhd (KTMB).

Known as IOrail, the system involves the use of drive-by sensing technologies with custom- designed IoT devices installed onboard trains. The data collected by these devices is fed into Asia Mobiliti’s cloud platform that is powered by machine learning algorithms, which processes vibration signals and performs defect prediction in real-time.

This allows railway operators to monitor physical railway tracks via a virtual model and provide real-time condition parameters and defect detection capabilities to uncover faults and address them before actual accidents occur. The live testbed is the first-of-its- kind in Malaysia and the complete solution was developed in-house by Asia Mobiliti.

Asia Mobiliti demonstrates predictive analytics features for advanced railway track condition monitoring with KTMB“We are excited to have developed a system on our IoT and machine learning platform that digitizes railway track monitoring and predicts defects in real-time,” said Ramachandran Muniandy (pic), Asia Mobiliti CEO and co-founder. “Having proven its capability for Malaysia's largest railway company, we now look towards a full deployment and expansion into other markets in the region.”

Stressing the value of IOrail, which enables the creation of a digital twin of railway tracks, thus enabling rail operators to move away from preventive and towards predictive maintenance, Ramachandran adds, “Such solutions are typically associated with large and costly systems from multinational vendors that run into million of ringgit, but we have shown that Asia Mobiliti have the expertise and capabilities to do so in a cost-effective manner with 70% cost savings.”

According to an industry survey conducted by Asia Mobiliti and ASAP Mobility, a Malaysian based system engineering and consultancy firm, half of railway operators in Asia are without conditioning monitoring systems and of those that do, 54% carry out monitoring using manual inspection methods. Furthermore, four in five operators indicated a willingness to upgrade to better digital systems while almost two-thirds want higher detection accuracy and faster reporting turnaround times.

The survey respondents comprised railway operators and rail asset owners in Hong Kong, Malaysia, Indonesia, India, Philippines and Saudi Arabia.

Asia Mobiliti claims IOrail’s proactive monitoring capability to be a boon for railway operators as current railway condition monitoring systems require infrastructure to be installed along the railway tracks or wayside.

With IOrail’s deployment only requiring installation on rolling stocks and using open 4G connectivity, operators are relieved of heavy capital expenditure. This makes it far more cost effective and scalable for railway operators across the developing world, where railway networks are critical for movement of passengers and goods.

The testbed programme saw IOrail deployed on KTMB trains traversing the Skypark Link and selected Komuter routes. More than 400GB of data was collected, spanning more than 135,000km of track distance travelled over an eleven-month period. This yielded a 100% detection rate of manually observed defects with two times the number of anomalies detected compared to manual inspections.

IOrail is available immediately for suitable commercial partners to bring to market across Southeast Asia.


Related Stories :

Keyword(s) :
Author Name :
Download Digerati50 2020-2021 PDF

Digerati50 2020-2021

Get and download a digital copy of Digerati50 2020-2021