How Digital Twins Can Transform Track Maintenance

Written by Bentley Systems
image description

Explore how digital twins support Big Data decisions to transform rail track maintenance and deliver safe, reliable, and resilient service. Learn how Bentley’s AssetWise application helps advance transportation organizations by going digital.

Advancing technology provides rail owners and operators the opportunity to improve rail network asset performance through increasing volumes of data. However, effectively consuming, managing, and analyzing that data can be challenging. Organizations are now putting their trust in digital twins to gain improved information visibility and better understand the past, present, and future conditions of linear rail assets. With linear analytics powered by a digital twin, owners can make big data decisions to improve track maintenance strategies and asset performance.

The Performance Digital Twin in Rail and Transit

Technological advancements and the Internet of Things (IoT) have had a significant impact on the way rail and transit organizations handle day-to-day track maintenance. Today, railways rely on autonomous inspection vehicles to provide near real-time monitoring of track conditions. This advancement ensures the safety and reliability of their linear network and the assets along the right-of-way. Digital twins can leverage continuous survey data to analyze asset performance. The “digital DNA”  utilizing digital twins provides the ability to understand an asset’s condition and change over time based on the physical assets in the field.

Here are six common track maintenance challenges and how digital twins can overcome them:

Derailment: Should track assets deteriorate to the point they are no longer fit for purpose, they can cause a catastrophic derailment. Today, rail and transit organizations operate safely by following federal regulations. However, with available technology, organizations can improve on an already great benchmark. The maintenance team can get an accurate representation of when and where a potential failure might occur by using linear analytics in the digital twin for condition monitoring. Additionally, lifecycle management with a geo-referenced digital twin can add value by visualizing linear analytical conditions on a map, with added context in appropriate formats for decision-makers.

Linear Network Management

Rail breaks: Physical rail breaks can be detected with track code, but this notification only happens when an asset has completely failed. Additionally, track code runs the risk of generating too many false positives. Instead, ultrasonic scanning can analyze assets in near real-time, and trouble spots can be located quickly to ensure the appropriate maintenance is applied in the correct location, minimizing rail breaks across the network. Additionally, rail defects detected with ultrasonic equipment can be shown within the digital twin, providing immersive visualization and analytics in an interactive 3D environment for decision support.

AssetWise Digital Twin Services

Tie (sleeper) breaks:  Allowing ties to break or degrade into poor quality is a reactive maintenance procedure, but could become more proactive with the right technology. Image scanning results can be integrated into a linear analytics system, with a cluster analysis then performed to find areas of the greatest concern. Image condition analysis within a digital twin is also an excellent opportunity for rail and transit agencies to apply artificial intelligence and machine learning to plan and optimize maintenance across the network.

Fastener failures: Rail fastening systems typically break at the clips used to attach the rails to the railroad ties. Often clips are replaced after breaking, and if it becomes a continuous problem, larger clips are used to handle more significant loads. This quick fix is reactive and only addresses the symptom of a bigger problem, not the root cause. A digital twin empowers track and maintenance engineers to drill into the data, be proactive, and perform cluster analyses to find the locations of greatest concern, including the root cause of the problem. This type of approach and analysis ensures the safety and reliability of rail networks.

Excessive rail wear: Linear analysis in a digital twin provides an understanding of where the rail assets are degrading faster than average. By aligning other data sets to find the root cause of the problem, owners/operators can extend the life of its rail assets. With dynamic segmentation, linear analysis can determine the condition based on straights, transitions, and curves as one way to view the track condition over time. This is a common tactic for rail wear analysis. 

AssetWise Linear Analytics

Poor ride quality and vibration:  Consistent poor ride quality results in negative customer satisfaction. Ridership falls when customers are not happy, and when ridership is down, the organization’s business objectives cannot be achieved. Not only can track vibration loosen connected equipment, vibration damage to assets across a network also generates noise, creating negative sentiment within the surrounding community. Generating Track Quality Indexes (TQI) with near real-time geometry data that can be gathered by a digital twin is an effective tactic for early detection and proactive corrective action.

AssetWise Linear Analytics

The Need for Linear Analytics in Rail and Transit Asset Management

An asset management system isn’t a single solution. Rail and transit requirements for linear assets are a great example as to why different tools are needed for different groups, individuals, and tasks performed within an organization. When looking at linear network assets, such as a long continuous track or a roadway, the relationships between each are based on a linear referencing system.  Terms like ‘near to’ or ‘overlapping’ are often used to indicate proximity, but the lack of specificity in this approach can mean the difference between catching or missing a potential failure.

Organizations do not maintain an entire network all at once. Maintenance typically occurs on parts of a network, which means that over time, it becomes more difficult to understand how various assets or segments arrived at their current condition. The challenge is understanding how linear assets are used, deteriorate, and are maintained over time. Linear analytics can help rail organizations overcome that challenge.

Click on the illustration to see a video.

Interoperability with the Big Data Challenge

Rail and transit operators are leveraging big data to more accurately pinpoint network asset degradation, though the huge volumes of data must be analyzed to gain actionable insights. The big data challenge can be solved with open technologies like AssetWise Linear Analytics. Technology suppliers need to work together for the benefit of owners/operators in the rail and transit industry.  AssetWise is a hardware-neutral solution and accepts condition data from any third-party hardware supplier. The condition data is transmitted to the asset management system for near real-time analysis, ensuring the safety and reliability of the linear network. Condition monitoring and thresholding within the linear analysis provides advanced alerts, ensuring safety by creating faster speed restriction orders or line shutdown alerts when the asset has deteriorated to the point that it is no longer fit for purpose. 

To perform an appropriate analysis for proactive track maintenance, AssetWise Linear Analytics relies on IoT data from operational systems and historical data stored in computerized maintenance management systems (CMMS), along with GIS data, attribution, and network asset definitions. Interoperability with CMMS is required to ensure work requests can be triggered on time based on the analysis performed by AssetWise.

AssetWise Enterprise Interoperability

The Importance of Data Quality and Predictive Maintenance

By working proactively and acting on the real-world condition of an asset rather than performing actions based only on time or the age of an asset, track maintenance engineers can overcome challenges faced every day as a result of siloed data. Timely access to relevant data facilitates more informed decisions, but the criticality of data quality in predictive maintenance should not be underestimated.

Here are five factors to consider when determining data quality:

  1. Accuracy: How accurate is the data when maintenance or repair issues are flagged?
  2. Reproducibility: Can you report an issue in the same location using different equipment?
  3. Currency: Is the data is up-to-date and valid?
  4. Completeness: Is the data set complete? Does it cover all the related assets?
  5. Relevance: How relevant is the data, and does it bring value to the operation when making informed decisions?
AssetWise Linear Analytics

Realizing the Potential of the Digital Twin for Rail and Transit

Today rail and transit agencies have started to embrace new technologies in linear analytics, including artificial intelligence, machine learning, and the Internet of Things. Railroads have increased the safety and reliability of their linear networks and their associated assets with condition monitoring and advanced analytics solutions like AssetWise. However, digital twins are an important part of the solution for continuously surveying assets, visualizing the network, and analyzing data in near real-time. With the ability to see conditions changing over time, rail and transit agencies can add a crucial fourth dimension to their asset management systems.

Digital twins have created a monumental technological opportunity in the rail and transit industry because of their ability to leverage innovation to improve operations by increasing asset reliability and performance. With the backdrop of owner/operators working within tighter budgets, shorter deadlines, and increased legislation, change can be extremely challenging.  Yet the benefits of digital twins can be transformational and directly impact the business outcomes of an organization.

The highly complex nature of rail networks and their related systems generates the opportunity to innovate and leverage technology to change for the better the way rail and transit operators operate. Leading owner/operators around the world have recognized the potential for digital twins and begun to explore ways in which the application of big data analytics, artificial intelligence, and machine learning can positively effect performance across the entire asset lifecycle – from planning and conceptual design through construction and the operation and maintenance of rail and transit networks.

Start Going Digital

With digital technology changing the rail industry, your organization is likely to be going digital already, but if you are struggling to embrace change or realize the full potential of your digital data, Bentley can help.

To assess what stage your organization has reached, we have developed a digital maturity assessment. Covering your current business practices and use of digital context, components, and workflows to help benchmark your organization’s existing digital practices, it identifies areas of opportunity and highlights where the greatest value might be gained.

The digital assessment covers five levels of advancement – aware, engaging, connecting, automating, and optimizing. It is often the case that organizations find variation within the different disciplines, teams, or phases of the lifecycle in which they work, so Bentley encourages you to use the assessment across key areas of your business and in collaboration with different team members.

Join our virtual events today

Download this e-book to see how you can advance your asset performance to deliver safe, reliable, compliant, and cost-effective service.

Watch the on-demand webinar to learn how digital twins support big data-driven decisions to transform track maintenance.

For more information on how you can improve rail and transit asset performance visit this page.

Tags: ,