Registration And Breakfast Networking Hosted By

Conference Chair’s Welcome & Opening Remarks

Optimising Infrastructure Maintenance From Utilising Predictive Maintenance And Implementing innovative New Technologies

• Comparing user experiences from infrastructure operators with utilising predictive maintenance and big data to run more trains on the network safely

• What kind of data is being used to identify possible infrastructure failures?

• Which data represents the highest quality or highest value for predictive models?

• In which categories can you predict failures and defects? (e.g. switch failures, train induction, rail body)

• Changes in work processes and how to work co-operatively with contractors

• Decision making processes for predictive maintenance strategies

Practical Implementation Of The Latest Innovations In Trackside Monitoring Technologies To Improve Cost, Safety And Availability Of Infrastructure Assets

• How to inspect and accurately measure crossings and turnouts

• Ensuring the safety of the switches/points

• How to inspect crossings and turnouts reducing track possession, with no transportation and with an accurate measurement?

• Using video inspection & machine-learning techniques for the identification of potential defects of switches: Do we use another technology or better using both technologies combined?

• How to maintain the environments of your SNC’s in the best way? How to measure them?

• New approaches on maintenance strategies of SNC’s to optimise safety factor – Maintenance Performance Indicator (MPI) & research projects

• Track geometry and switch geometry digital measuring

• What types of sensors you get most reliable on this data for these different switches and systems

Using Measurement Data For Quality Tamping

• Utilization of tamping and how to better align material tamping

• Using liability switching crossings

• How are railways maintaining the environments of their switching and crossings?

Morning Break & Networking

Network Break Sponsorship/Host

Vehicle Monitoring The Track – Development Of The Track Condition Monitoring System From In Service Vehicles

• Vehicles Monitoring the Track

• Detection of Track Faults from In-vehicle Data

• Detection Algorithm Development

• Trials on Infrastructure

• Track Quality Assessment from In-service Vehicles

Optimising Infrastructure Maintenance & The Current Market State

• Identifying the current challenges: Reduce cost – whilst increasing capacity and safety

• Identifying the areas and opportunities for financial gain

• Understanding the real opportunities and challenges: Reliability, Cost, Efficiency and Standards

• Asking the right questions is the first route to go entering the world of BIG DATA – translating Big Data into financial gains

• Advances in Predictive Maintenance

• What are the major challenges when driving down cost? Capacity, Downtime, scheduling?

• What information is required to benefit your business?

Signalling Systems Digitaliazation: Towards A New Generation Of O&M Solutions

Nadia Mazzino, Vice President – Control Center Integration and Advanced Services, Hitachi Rail STS (tbc)

• STS signaling products evolution in the digital revolution

• STS Intelligent Asset Management System (IAMS): Description of the STS platform and its capabilities leveraging on signaling systems digitalization to drive O&M capabilities

• IAMS application over the world on different STS systems: Metro and Railway (passenger and freight) applications

• Final results & O&M benefits

Reducing Maintenance Cost And Failures With Successful Predictive Maintenance

Bruno GAJAN, HealthHub Tenders & Infra Project Manager, Alstom Group (tbc)

• Opportunities for predictive maintenance: Using geo-data for Track maintenance

• What Data? Finding data that you didn’t know existed and strategic Data Utilisation

• Diagnosing track defects: Diagnostic data to monitor track conditions

• Leverage asset management to maximise maintenance delivery & reliability of assets

• Reduce number of failures and unplanned maintenance

Smart System Engineering For High Speed Trains Maintenance

José Antonio Marcos Alberca Carriazo, Head manager of Smart maintenance Engineering, TALGO (tbc)

• Nowadays High-speed train maintenance is very complex and high tech, and the challenges to achieve as reliability availability are very high. In order to reach these challenges, Talgo has developed new maintenance technologies basedon the latest technology and innovation to perform condition-based maintenance (CBM) to predict the failures and increase train availability and reliability.

• To apply condition-based maintenance techniques, Talgo has developed algorithms capable to predict the failures, using machine learning technology to do it.

• Machine learning, need a lot of data to model the algorithms, therefore Talgo have developed a real-time monitoring system using Google Cloud architecture.

• The health status is assessed by machine learning algorithms, capable of detecting anomalous behaviour. In addition to this approach of Artificial Intelligence, in the health of the component other relevant factors in the maintenance play an important role, such as the information of the component maintenance operations performed or the events and alarms that the component has generated.

• Through this technology the Talgo Maintenance team is able to anticipate the failure of the component, which makes it possible to achieve train reliabilities around 100%. In addition, with this possibility of prediction, it is possible to perform a more effective maintenance of the components, taking advantage of a longer life of them. On the other hand, this anticipated vision allows maintenance operations to be programmed more efficiently, reducing their time and cost of execution

Networking Luncheon

Buffet Style

Sponsorship Opportunity

Industrial Internet Of Things (IIOT) Technologies Into Rail And Transport Of Environments Offers The Benefits Of Connected Operations While Providing Unmatched Security

James Birdsall, Project Manager, Asset Management Practice Leader, PARSONS Corporation (tbc)

• System wide infrastructure digitization efforts to support formation of BIM, asset inventory, and condition assessment data sets

• Asset performance modeling and automated deficiency management

• Use of improved technology capabilities including native mobile applications, 3D cameras, and drones to semi- to fully-automate infrastructure digitization efforts

• Real-time video capture and analysis capabilities to provide real-time system support

• Comprehensive cybersecurity capabilities to address vulnerabilities within Railway Systems and Infrastructure,

• Improved access control and drone identification and suppression capabilities

• Edge computing on connected devices to optimize data processing and response times,

• Last mile and broader network interconnectivity to optimize bulk good, freight, and ridership usage

Luncheon Networking Exhibition Area

Network Break Sponsorship/Host

Separating Meaningful Data From The Mass Of Data Collected By Sensors

Mehmet Ali Dagil, Chief Engineer, Istanbul Metro (tbc)

• Mass of Data Challenge

• Mining for the Valuable Data

• Finding the Right Miner

• Importance of Analysis Methods

• Cost of Separation, Finding in the Right Way

Achieving Optimum Asset Reliability And Minimise Maintenance Costs

Martin Vallance, Head of Digital Asset Management and Operations MEA, Atkins (tbc)

Shifting from traditional maintenance to a predictive model: Diagnostic inspections vs visual inspections

• Methods and process for implementing track predicative maintenance

• The future of technology applications for maintenance and data utilisation

• Algorithms and image processing technologies

• Real-time information: Separating meaningful data from the enormous amount that has been collected

Diagnostic And Maintenance Machines

Adrian Sutton, Managing Director at Vortex IoT (tbc)

• Automatic inspection: Vision systems technology

• Automatic patrolling and periodical inspection

• Track Geometry

• At which speeds are you able to recognise defects

• Continuous monitoring with unmanned systems

• Machine learning

Automatic Inspection: Vision System Technology