An infrastructure operator approached Marketways with asset, field and safety evidence spread across maintenance, operations and workforce systems. The initial problem appeared to be maintenance prioritisation, but discovery showed that spares, field readiness, incident learning and changing load were equally important. We built a reliability programme around the consequence of failure and the organisation’s ability to respond.
The engagement objective
Through the initial discovery, Marketways defined the objective: connect condition evidence, maintenance priorities, field readiness and operational learning.
How Marketways translated the problem
We began with a practical question: Which assets need intervention, inspection or continued monitoring? The first analysis used condition, alarms, work orders, operating load, environment and failure consequence.
That evidence could not be read in isolation. Failure history is sparse and maintenance records may reflect interventions rather than natural deterioration. Skills, permits, geography, critical spares and simultaneous events constrain response.
Maintenance history was evidence of both asset condition and earlier intervention. Reading it as natural deterioration would have distorted failure estimates, so operating context and consequence remained in the model.
We did not judge each component by its isolated KPI. We examined how people, assets, decisions and constraints affected one another, then used the evidence to test whether an apparent improvement would strengthen the complete system or merely move cost, pressure or risk elsewhere.
How the engagement developed
The initial work on asset failure and maintenance prioritisation exposed dependencies with field workforce and spares readiness, safety and operational learning system, load, demand and capacity forecasting. Treating them as separate recommendations would have left the operating trade-offs unresolved.
- Asset failure and maintenance prioritisation: Reduce avoidable outages and direct maintenance to consequence-adjusted need.
- Field workforce and spares readiness: Improve restoration and maintenance readiness without excessive inventory.
- Safety and operational learning system: Turn incident and near-miss evidence into preventive action.
- Load, demand and capacity forecasting: Plan capacity, procurement and operations with visible uncertainty.
Evidence we examined
- Condition, alarms, work orders, operating load, environment and failure consequence.
- Work orders, competencies, rosters, travel, inventory and failure scenarios.
- Incidents, near misses, permits, maintenance, operating context and actions.
- Load, weather, tariffs, customer segments, outages and economic indicators.
Industry conditions we accounted for
- Failure history is sparse and maintenance records may reflect interventions rather than natural deterioration.
- Skills, permits, geography, critical spares and simultaneous events constrain response.
- Reporting behaviour changes the data, and rare severe events cannot be learned from frequency alone.
- Weather, tariffs, economic activity, distributed generation and behaviour interact.
How our engagement contributed to business impact
We connected every method to a decision and a business measure. The organisation could assess the engagement through operating results as well as model performance.
- Asset failure and maintenance prioritisation
- Method: Machine Learning & Predictive Analytics, Forecasting, Risk & Optimisation.
- Evidence: Condition, alarms, work orders, operating load, environment and failure consequence.
- Decision supported: Reduce avoidable outages and direct maintenance to consequence-adjusted need.
- Impact measure: Availability, avoided critical failure, maintenance value and lead time.
- Field workforce and spares readiness
- Method: Forecasting, Risk & Optimisation, Process, Workflow & Systems.
- Evidence: Work orders, competencies, rosters, travel, inventory and failure scenarios.
- Decision supported: Improve restoration and maintenance readiness without excessive inventory.
- Impact measure: Time to restore, first-time fix and critical-spares availability.
- Safety and operational learning system
- Method: Research & Evidence Collection, Data Foundations & Business Intelligence.
- Evidence: Incidents, near misses, permits, maintenance, operating context and actions.
- Decision supported: Turn incident and near-miss evidence into preventive action.
- Impact measure: Repeat-event reduction, action closure and leading-indicator value.
- Load, demand and capacity forecasting
- Method: Forecasting, Risk & Optimisation, Statistics & Econometrics.
- Evidence: Load, weather, tariffs, customer segments, outages and economic indicators.
- Decision supported: Plan capacity, procurement and operations with visible uncertainty.
- Impact measure: Forecast reliability, reserve adequacy and cost.
Implementation
The engagement was structured as phased diagnostic, pilot and operationalisation. We connected the analysis to the decisions, operating constraints and measures that the organisation would continue to use.
How success was assessed
The overall assessment considered availability, safety, restoration speed and maintenance value. The supporting measures included:
- Availability, avoided critical failure, maintenance value and lead time.
- Time to restore, first-time fix and critical-spares availability.
- Repeat-event reduction, action closure and leading-indicator value.
- Forecast reliability, reserve adequacy and cost.
Services and methods used
Services: Predictive Maintenance & Reliability, Decision Assurance, Workforce Planning & Capacity, Fleet & Logistics Optimisation, Risk Detection, Business Systems Design & Architecture, Sales Forecasting & Demand Planning, Risk & Uncertainty Modelling.
Methods: Machine Learning & Predictive Analytics, Forecasting, Risk & Optimisation, Process, Workflow & Systems, Research & Evidence Collection, Data Foundations & Business Intelligence, Statistics & Econometrics.