Building Equipment Maintenance Scheduling With Predictive Cost Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current maintenance strategies for building equipment, such as run-to-fail and preventative maintenance, lack precision in predicting the costs and benefits of maintenance tasks, making it difficult to optimize maintenance decisions effectively.
Innovation Solution
A Model Predictive Maintenance (MPM) system that includes an equipment controller, operational cost predictor, maintenance cost predictor, and objective function optimizer to determine an optimal maintenance strategy by predicting operating and maintenance costs over a specified period, using binary decision variables to indicate maintenance actions and updating the objective function dynamically based on real-time feedback.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If predictive maintenance uses feedback from building equipment to perform diagnostics and predict maintenance tasks, then maintenance effectiveness is improved, but difficulty in accurately predicting costs and benefits increases
Solution Approach 1:
The system changes parameters by introducing multiple cost predictors that estimate different cost components (maintenance costs, operational costs, capital costs) and combines them through an objective function. This transforms the difficult single-parameter cost prediction into a multi-parameter optimization problem that can be solved systematically using binary decision variables and optimization algorithms.
2Ease of operation
If maintenance tasks are performed at regular intervals based on elapsed time or run hours, then preventative maintenance is simplified, but maintenance precision and cost optimization deteriorate
Solution Approach 1:
The system transitions from static, fixed-interval maintenance scheduling to dynamic, adaptive scheduling. Binary decision variables allow the optimization algorithm to determine the optimal maintenance timing based on current equipment state, predicted costs, and operational requirements. This dynamic approach maintains simplicity through automated decision-making while achieving precision through real-time cost-benefit analysis.
3Ease of manufacture
If run-to-fail strategy is used allowing equipment to run until failure, then maintenance costs are reduced, but equipment reliability and performance deteriorate
Solution Approach 1:
The system performs preliminary action by predicting future maintenance costs and operational costs before failures occur. The objective function optimizer proactively determines the optimal maintenance timing by evaluating predicted costs, allowing maintenance to be performed just before it becomes economically necessary rather than waiting for actual failure. This prevents the performance deterioration associated with run-to-fail while avoiding unnecessary early maintenance.
Data Source
AI summary
A model predictive maintenance (MPM) system for building equipment includes an equipment controller configured to operate the building equipment to affect a variable state or condition in a building and an operational cost predictor configured to predict a cost of operating the building equipment over a duration of an optimization period. The MPM system includes a maintenance cost predictor configured to predict a cost of performing maintenance on the building equipment over the duration of the optimization period and an objective function optimizer configured to optimize an objective function to predict a total cost associated with the building equipment over the duration of the optimization period. The objective function includes the predicted cost of operating the building equipment and the predicted cost of performing maintenance on the building equipment.