Development of optimized maintenance scheduling model for coal-fired power plant boiler
Maintenance in power plants is crucial to extend the life and reducing the risk of sudden breakdown or outage of coal-fired power plant steam boilers. Traditionally, coal fired power plant boilers are scheduled for maintenance in periods to ensure that the demand of the system is fully met and the r...
Saved in:
| Main Author: | |
|---|---|
| Format: | text::Thesis |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Maintenance in power plants is crucial to extend the life and reducing the risk of sudden breakdown or outage of coal-fired power plant steam boilers. Traditionally, coal fired power plant boilers are scheduled for maintenance in periods to ensure that the demand of the system is fully met and the reliability of the system is maximized. However, in a deregulated power industry, the pressure of maintaining power generating units is also driven by the potential revenue received by participating in the power generation market. Therefore, determination of the optimum time periods for maintenance of generating units in power generation has become an important task from both a system reliability and an economic point of view. Due to the extremely large numbers of potential maintenance schedules, a systematic approach is required to ensure that optimal maintenance schedules are obtained within an acceptable timeframe. Computing intelligence is a soft-computing subset of artificial intelligence referring to the potential of a computer to gain knowledge from an experimental observations or specific task. Generally, optimization computational and mathematical methods are designed for finding the best solution of a certain problems that aiming for minimizing or maximizing the objective functions based on the variables and subject to a set of constraints. Literature revealed that mathematical methods and metaheuristic algorithms are common approaches in solving combinatorial optimization problems with a large search space in a reasonable computational run time. In this thesis, two different approaches, Mixed Integer Linear Programming (MILP) and Particle Swarm Optimization (PSO) were selected to solve the maintenance schedule and optimization problems in coal-fired power plant boilers. A set of mathematical formulations were developed in order to enable MILP and PSO to be applied to the adopted power plant maintenance optimization problem. The formulation caters for all constraints such as the operation duration for specific maintenance activities, manpower required for each activity, the preceding sequences, and the maintenance costs. As part of the formulation, MILP and PSO are developed and tested extensively on the actual maintenance scheduling from the adopted power plant and through the expert’s judgements. It was found that the MILP formulation resulted in significant improvement in performance in this study. The MILP and PSO models were linked with the Excel datasheet which contained required data for simulation to assess. The models will be generating and producing the optimal maintenance schedule with minimal maintenance costs. The optimal schedules obtained were compared with the actual based on parameters and judgement from power plant planning team. The MILP model was shown to be a useful decision-making tool for optimizing maintenance scheduling under different circumstances when tested with PSO and some trial simulations. In conclusion, the maintenance scheduling optimization models developed, tested and applied as a part of this thesis research provides a reliable and effective solution to the adopted power plant. |
|---|