Maintenance Scheduling of Rolling Stock Using a Genetic Algorithm

1998 ◽  
Vol 49 (11) ◽  
pp. 1130
Author(s):  
C. Sriskandarajah ◽  
A. K. S. Jardine ◽  
C. K. Chan
Keyword(s):  
Genetic Algorithm ◽  
Maintenance Scheduling ◽  
Rolling Stock

Maintenance scheduling of rolling stock using a genetic algorithm

1998 ◽  
Vol 49 (11) ◽  
pp. 1130-1145
Author(s):  
C Sriskandarajah ◽  
A K S Jardine ◽  
C K Chan
Keyword(s):  
Genetic Algorithm ◽  
Maintenance Scheduling ◽  
Rolling Stock

Maintenance scheduling of rolling stock using a genetic algorithm

1998 ◽  
Vol 49 (11) ◽  
pp. 1130-1145 ◽  
Author(s):  
C Sriskandarajah ◽  
A K S Jardine ◽  
C K Chan
Keyword(s):  
Genetic Algorithm ◽  
Maintenance Scheduling ◽  
Rolling Stock

Application of Improved Genetic Algorithm in Maintenance Decision for Turbine-Generator Unit

2010 ◽  
Vol 44-47 ◽  
pp. 2940-2944
Author(s):  
Qing He ◽  
Jian Ding Zhang
Keyword(s):  
Genetic Algorithm ◽  
Heuristic Algorithms ◽  
Maintenance Scheduling ◽  
Improved Genetic Algorithm ◽  
Turbine Generator ◽  
Executive Process ◽  
Generator Unit ◽  
Maintenance Decision ◽  
Constrained Conditions ◽  
Operating Unit

The complicated function relations are more prone to appear in the maintenance scheduling of steam-turbine generator unit. Many constrained conditions are often attendant with these function relations. In these situations, the traditional method often can not obtain the exact value. The genetic algorithm (GA), a kind of the heuristic algorithms, does not need the function own good analytic properties. In addition, as the operating unit of GA is the group, so it applies to the parallel computing process. In GA executive process, the offspring continually inherit the genes from the parents, so it is more prone to be involved in the local convergence. An improved genetic algorithm is proposed and used in the model of maintenance decision of turbine-generator unit under. The goal of the model is to seek to the rational maintenance scheduling of the generator unit, so as to minimize the sum of the maintenance expense, the loss of the profit on the generated energy, and the loss of the penalty. It is proved by the example that IGA is highly efficient.

scholarly journals Determining the Rational Motion Intensity of Train Traffic Flows on the Railway Corridors with Account for Balance of Expenses on Traction Resources and Cargo Owners

2019 ◽  
Vol 20 (3) ◽  
pp. 215-228 ◽  
Author(s):  
Tetiana Butko ◽  
Mykhailo Muzykin ◽  
Andrii Prokhorchenko ◽  
Halyna Nesterenko ◽  
Halyna Prokhorchenko
Keyword(s):  
Genetic Algorithm ◽  
Mathematical Model ◽  
Reference Station ◽  
Limited Resources ◽  
Rolling Stock ◽  
Traffic Flows ◽  
Railway Transport ◽  
Real Coded Genetic Algorithm ◽  
Cargo Transportation ◽  
Destination Point

Abstract The article proposes a method for determining the rational motion intensity of specific train traffic flows on railway transport corridors with account for balance of expenses on traction resources and cargo owners. A mathematical model based on stochastic optimization is developed, which allows to optimize, in the conditions of risks, the interval between trailing trains on the railway lines taking into account the limited resources of the traction rolling stock, the capacity of the stations and freight fronts at the cargo destination point. Solving this mathematical model allows to find a balance between the expenses for movement of train traffic flows from different railway lines to their terminal reference station and the expenses of a consignee, subject to the limitations of the technological logistics chain in cargo transportation. For the solution of this mathematical model, a Real-coded Genetic Algorithm (RGA) was used.

Sign in / Sign up

Export Citation Format

Share Document