Efficient distribution of backpropagation models on parallel architectures

This paper describes an innovative modeling, interfacing and training framework and application for microtunneling machines under heterogeneous gravel and sand soils, based on a machine simulator. It is initialized using a selective collection of skilled pilots' know-how during the performance of a pipe jacking microtunneling machine operation, generating a rule-based system based on grouped rules and states that replicate the machine's performance. The adjustment of these states and associated rules allows the creation, setup and analysis of a realistic functional model for tunneling machines. The developed system integrates a friendly Human-Machine Interface (HMI) that closely resembles real machines' pilot cabinets and allows natural interaction with the implemented inference engine through the simulated control panel. Additionally, the framework allows the training of tunneling machine operators by simulation and subsequent gathered data analysis, obviating or reducing mechanical movement times if desired. The virtual pilot's desk allows global training time and cost reductions, and increases safety for future operators and machinery. The HMI is divided into two screens, which replicate the data and the command panels of a real machine's control desk. The presented framework has allowed the first implementation of a jack piping microtunneling machine simulator by means of the developed pilots' steering know-how capture methodology.

show abstract

Experience acquisition simulator for operating microtuneling boring machines

Jardón

Victores

Martínez

et al. 2012

Automation in Construction

View full text Add to dashboard Cite

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

hi@scite.ai

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Efficient distribution of backpropagation models on parallel architectures

Cited by 1 publication

References 0 publications

Experience acquisition simulator for operating microtuneling boring machines

Experience acquisition simulator for operating microtuneling boring machines

Contact Info

Product

Resources

About