Senior Asset Manager

You'll be configuring system settings, building custom reports, troubleshooting data integration issues, and designing new workflows within our EAM system. You'll also train others on its more complex features.

Running financial reports related to asset depreciation, reconciling asset register data between the EAM and ERP, and understanding the procurement-to-pay process for spares and services.

Developing new data models, connecting directly to EAM/ERP databases, and creating complex, multi-source reports and dashboards to visualise asset performance and identify trends. You'll be the go-to person for data visualisation.

Using Power Query for repeatable data transformation from various sources and VBA for automating routine reporting tasks. You'll build robust financial models for TCO analysis and other business cases.

Analysing historical sensor data (e.g., vibration, temperature, pressure) to identify failure patterns, working with Reliability Engineers to set alert thresholds, and interpreting IIoT data for insights.

• Maintenance Team Leads
• Production Managers
• Finance Business Partners
• Health & Safety Officers
• Procurement Specialists

• Equipment Vendors
• Maintenance Service Providers
• Auditors (occasionally)

While you're currently analysing sensor data, the next step is building and deploying machine learning models that automatically predict failures. This moves us from reactive to truly proactive, reducing human effort and increasing accuracy. You'll need to understand how these models work, not just use the outputs.

Supervised vs. unsupervised learning for anomaly detection · Feature engineering from sensor data · Model training, validation, and deployment · Interpreting model outputs and explainable AI (XAI)

• This month: Start learning Python (if you don't already) and explore libraries like scikit-learn for basic machine learning concepts.
• Next quarter: Take an online course on machine learning fundamentals, focusing on time-series data and anomaly detection.
• Within 6 months: Work with our data science team (if we have one) to understand how they build and deploy predictive models.
• Within 12 months: Experiment with building a simple predictive model for a non-critical asset using open-source tools and our historical data.

Quick win: Download a public dataset of sensor readings and try to identify anomalies using basic statistical methods in Excel or Python. It's a first step towards understanding patterns.

As we rely more on data for critical decisions, the quality and trustworthiness of that data become paramount. You'll need to play a more active role in defining data standards, ensuring consistency, and implementing processes to maintain high data quality across all asset systems. 'Garbage in, garbage out' becomes even more dangerous with AI.

Data lineage and source tracking · Data dictionaries and master data management · Automated data validation and cleansing rules · Roles and responsibilities for data ownership

• This month: Review our current EAM data entry processes. Where are the common inconsistencies or errors?
• Next quarter: Research best practices for data governance in asset management and propose some initial improvements.
• Within 6 months: Work with IT and the Asset Manager to define clear data ownership and validation rules for a critical data set.
• Within 12 months: Lead an initiative to improve the accuracy of a specific asset register field, demonstrating measurable improvement.

Quick win: Identify one recurring data quality issue in our EAM (e.g., inconsistent failure codes) and propose a simple, immediate fix or training for technicians.