Search engine for discovering works of Art, research articles, and books related to Art and Culture
ShareThis
Javascript must be enabled to continue!

PARAMETRIC STUDY OF WARREN STEEL TRUSS BRIDGE USING ARTIFICIAL NEURAL NETWORKS

View through CrossRef
Abstract   Steel truss bridges are a popular type of amongst several other standard bridges in Indonesia due to their lightweight yet robust and strong structure. In this study Artificial Neural Networks is used to optimize the dimensions of the steel truss bridge. The Artificial Neural Network method was chosen as it can handle complex and nonlinear problems, as well as its potential to generate accurate prediction models. Data of 319 existing constructed steel truss bridges in Indonesia were used to train the Artificial Neural Network model. The results show that the Artificial Neural Network model can predict the stress ratio of the structural elements of steel truss bridges with high accuracy (R2 > 0.99). The trained ANN model was then used to optimize the dimensions of the steel truss bridges with spans range from 40 meters to 60 meters with interval of 5 meters. The optimization results showed a 5.60% weight reduction compared to previous research results and a 20% less compared to the average weight of the existing bridge. This study contributes to improving the efficiency of development steel truss bridge in Indonesia.   Keywords: truss bridge; optimization; Artificial Neural Network; design efficiency     Abstrak   Jembatan rangka baja merupakan jenis jembatan standar yang populer di Indonesia karena struktur yang ringan namun kuat dan kokoh. Pada penelitian ini, Artificial Neural Network digunakan untuk mengoptimalkan dimensi jembatan rangka baja. Metode ini dipilih karena kemampuannya menangani masalah kompleks dan nonlinier, serta potensinya untuk menghasilkan model prediksi yang akurat. Data 319 jembatan rangka baja yang ada di Indonesia digunakan untuk melatih model Artificial Neural Network. Hasilnya menunjukkan bahwa model Artificial Neural Network dapat memprediksi rasio tegangan pada elemen struktural jembatan rangka baja dengan akurasi yang tinggi. Model Artificial Neural Network yang terlatih kemudian digunakan untuk mengoptimalkan dimensi jembatan rangka baja dengan rentang bentang 40 meter hingga 60 meter dengan interval 5 meter. Hasil optimasi menunjukkan efisiensi berat sebesar 5,60% dibandingkan dengan penelitian sebelumnya dan 20% lebih efisien dibandingkan dengan jembatan yang sudah ada. Penelitian ini berkontribusi dalam meningkatkan efisiensi pengembangan jembatan rangka baja di Indonesia.   Kata-kata kunci: jembatan rangka baja; optimasi; Artificial Neural Network; efisiensi desain
Title: PARAMETRIC STUDY OF WARREN STEEL TRUSS BRIDGE USING ARTIFICIAL NEURAL NETWORKS
Description:
Abstract   Steel truss bridges are a popular type of amongst several other standard bridges in Indonesia due to their lightweight yet robust and strong structure.
In this study Artificial Neural Networks is used to optimize the dimensions of the steel truss bridge.
The Artificial Neural Network method was chosen as it can handle complex and nonlinear problems, as well as its potential to generate accurate prediction models.
Data of 319 existing constructed steel truss bridges in Indonesia were used to train the Artificial Neural Network model.
The results show that the Artificial Neural Network model can predict the stress ratio of the structural elements of steel truss bridges with high accuracy (R2 > 0.
99).
The trained ANN model was then used to optimize the dimensions of the steel truss bridges with spans range from 40 meters to 60 meters with interval of 5 meters.
The optimization results showed a 5.
60% weight reduction compared to previous research results and a 20% less compared to the average weight of the existing bridge.
This study contributes to improving the efficiency of development steel truss bridge in Indonesia.
  Keywords: truss bridge; optimization; Artificial Neural Network; design efficiency     Abstrak   Jembatan rangka baja merupakan jenis jembatan standar yang populer di Indonesia karena struktur yang ringan namun kuat dan kokoh.
Pada penelitian ini, Artificial Neural Network digunakan untuk mengoptimalkan dimensi jembatan rangka baja.
Metode ini dipilih karena kemampuannya menangani masalah kompleks dan nonlinier, serta potensinya untuk menghasilkan model prediksi yang akurat.
Data 319 jembatan rangka baja yang ada di Indonesia digunakan untuk melatih model Artificial Neural Network.
Hasilnya menunjukkan bahwa model Artificial Neural Network dapat memprediksi rasio tegangan pada elemen struktural jembatan rangka baja dengan akurasi yang tinggi.
Model Artificial Neural Network yang terlatih kemudian digunakan untuk mengoptimalkan dimensi jembatan rangka baja dengan rentang bentang 40 meter hingga 60 meter dengan interval 5 meter.
Hasil optimasi menunjukkan efisiensi berat sebesar 5,60% dibandingkan dengan penelitian sebelumnya dan 20% lebih efisien dibandingkan dengan jembatan yang sudah ada.
Penelitian ini berkontribusi dalam meningkatkan efisiensi pengembangan jembatan rangka baja di Indonesia.
  Kata-kata kunci: jembatan rangka baja; optimasi; Artificial Neural Network; efisiensi desain.

Related Results

Economical Aspect of Truss Design Through Geometry Configuration
Economical Aspect of Truss Design Through Geometry Configuration
In engineering, truss structures are used extensively in bridge, tower, building, and numerous mechanical applications. Several studies have found that truss frames use the least s...
Fuzzy Chaotic Neural Networks
Fuzzy Chaotic Neural Networks
An understanding of the human brain’s local function has improved in recent years. But the cognition of human brain’s working process as a whole is still obscure. Both fuzzy logic ...
Study on Application and Practice of Variable Axial Force Cable in Reinforcement System of Powerhouse Truss
Study on Application and Practice of Variable Axial Force Cable in Reinforcement System of Powerhouse Truss
Long-span steel structure trusses are widely used in factory buildings, but with the growth of service time and the increase of dynamic load fatigue, a considerable part of the lon...
On the role of network dynamics for information processing in artificial and biological neural networks
On the role of network dynamics for information processing in artificial and biological neural networks
Understanding how interactions in complex systems give rise to various collective behaviours has been of interest for researchers across a wide range of fields. However, despite ma...
Study on elastic deformation calculation method of a composite-metal hybrid assembling stringed truss bridge
Study on elastic deformation calculation method of a composite-metal hybrid assembling stringed truss bridge
A composite-metal hybrid assembling stringed truss bridge which based on pre-tightened tooth connection can make full use of the strength of the FRP fiber in the direction of the f...
Construction Sequence Simulation for Partial Cable Stayed Truss Bridge with Single Pylon
Construction Sequence Simulation for Partial Cable Stayed Truss Bridge with Single Pylon
<p> Qiansimen Bridge, a part of Liangjiang Bridge in Chongqing city in China, is currently under construction by the Chinese contractor CCCC, Second Harbor Engineering Compan...
Behaviour and design of a double track open timber floor plate girder railway deck steel bridge
Behaviour and design of a double track open timber floor plate girder railway deck steel bridge
This paper discusses the nonlinear behaviour and design of a double track open timber floor plate girder railway deck steel bridge. A 3-D finite element model has been developed fo...
Robert Penn Warren
Robert Penn Warren
The life of Robert Penn Warren (b. 1905–d. 1989) spanned most of the 20th century, so that his varied and voluminous work engaged international modernism in many ways that evolved ...

Back to Top