TeleMARS was engaged with Sequana on an asset lifecycle modelling initiative for a major Australian rural water supplier.
Asset management is a complex business function comprising many variables specific to each project. The objectives, asset characteristics, geographic distributions, operational frameworks, environmental and system contexts vary across business environments.
Despite many asset management and analytics software products being available on the market, asset-intensive industries still struggle with gaining trustworthy insights that effectively support decision-making.
Sequana designed an asset lifecycle modelling method to validate market solutions and guide asset planners and decision makers. The method helps achieve the optimal balance between risk and investment over the short, medium, and long term (1 to 30 years).
The lifecycle modelling considers the asset conditions, operational parameters and objectives, as well as operational and capital costs incurred as assets age and degrade over time.
It identifies the most appropriate point to renew or replace an asset to ensure its risk remains below a defined threshold.
The TeleMARS team implemented the asset lifecycle models. The outcome demonstrates a long-term investment outlook based on asset degradation profiles, costs, and risk estimates.
We have learned valuable lessons through this work, and discovered opportunities to build sustainable models for achieving optimal asset planning and management.
Challenges:
Knowledge Gap: Asset lifecycle optimisation is complex, requiring deep expertise in the domain of asset management to understand the specific context of operational data and business logic. The data science team struggled to keep up with all the nuances despite having access to subject matter experts (SMEs). It heavily depended on individual capability to ensure the correct implementation of business context and logic.
Requirement Traceability: While the variables change across business scenarios, requirements for modelling vary accordingly and change from time to time. Without a traceable requirement management mechanism, the data science team struggled to keep up with requirement variations and changes. The project management team heavily relied on individual capability to ensure the implementation was on track.
Transparency and Explainability: Asset lifecycle modelling can be complex. SMEs often struggle to fully understand how the model works by simply reading the user manual or technical specifications. Many existing asset lifecycle solutions operate as black boxes, making them difficult to validate against specific requirements.
Poor Data Quality: The operational data from Enterprise Asset Management System (EAMS) was incomplete and low-quality. There weren’t sufficient data points to implement advanced algorithms.
Opportunities: Traceability, Transparency and Trust
A traceable requirement management mechanism translates the complex asset lifecycle nuances into technical language to guide and govern solution development, ensuring the project-specific variables are understood and implemented.
It also supports seamless collaboration between business and technical teams.
An automated proof-of-concept mechanism enables SMEs to rapidly and progressively validate their methods while reducing risk at a low cost.
Streamlined online validation enables SMEs to validate solutions at each step, ensuring the alignment with business requirements without navigating complex technical documents. This builds confidence and trust between SMEs and data teams.
A data contract engine enforces commitments from EAMS data producers to supply the required trustworthy data.
