Optimization of construction equipment utility using neural networks
By: Trivedi, Jyoti. S
.
Contributor(s): Kumar, Rakesh.
Publisher: Pune NICMAR 2013Edition: Vol.28(3), Jul-Sep.Description: 15-23p.Subject(s): Construction Engineering and Management (CEM)Online resources: Click here
In:
NICMAR Journal of construction managementSummary: Management of construction resources and time scheduling requires optimization, which focuses on assessment of the best possible utilization of equipments that are needed to achieve a predetermined goal. This study describes the performance optimization of hydraulic excavator equipment considering four variables i.e. class of the material, depth of the cut, cycle time and size of hauling equipment units at port construction for three distinct projects/scenarios. A three layer feed forward Neural Network (NN) model having four input neurons, two output neurons and five hidden neurons was developed in MATLAB (Visual Basic Compiled Programs) environment. The proposed model uses the productivity and operating cost that is subjected to multiple objective optimizations in order to predict output neurons. The learning of NN model was accomplished by back propagation algorithms and validation with remaining 25% of data sets. It was found that Pareto optimal solutions as compared to basic MS Project base scheduling were reduced relatively by 7 %. The explicit solution is a relatively simple means of predicting temporal variation of equipment use in port construction projects and may be further used by the researchers. The proposed formulation can also be used for identification of optimal operational scenarios.
| Item type | Current location | Call number | Status | Date due | Barcode | Item holds |
|---|---|---|---|---|---|---|
Articles Abstract Database
|
School of Engineering & Technology Archieval Section | Not for loan | 2024-0809 |
Management of construction resources and time scheduling requires optimization, which focuses on assessment of the best possible utilization of equipments that are needed to achieve a predetermined goal. This study describes the performance optimization of hydraulic excavator equipment considering four variables i.e. class of the material, depth of the cut, cycle time and size of hauling equipment units at port construction for three distinct projects/scenarios. A three layer feed forward Neural Network (NN) model having four input neurons, two output neurons and five hidden neurons was developed in MATLAB (Visual Basic Compiled Programs) environment. The proposed model uses the productivity and operating cost that is subjected to multiple objective optimizations in order to predict output neurons. The learning of NN model was accomplished by back propagation algorithms and validation with remaining 25% of data sets. It was found that Pareto optimal solutions as compared to basic MS Project base scheduling were reduced relatively by 7 %. The explicit solution is a relatively simple means of predicting temporal variation of equipment use in port construction projects and may be further used by the researchers. The proposed formulation can also be used for identification of optimal operational scenarios.
Click on an image to view it in the image viewer
There are no comments for this item.