Tender Advertisement #1181958
This Opportunity Has ClosedThis opportunity has already closed and is no longer open for submissions.
Brief
AAM6201: Development of a machine learning based maintenance decision support tool guideline
Contract #
AAM6201Location
EverywhereClosed On
Tue 16/02/2021 - 05:00 PM AEDTTender Details
PURPOSE:
The purpose of this project is to develop a proof of concept of a decision support system that applies machine learning on the network condition and inventory data to replicate a human expert pavement asset manager.
Road transport and traffic agencies have spent significant efforts on collecting data, however the use of data in supporting maintenance and renewal decisions is considered a challenge, especially for new or inexperienced asset managers. This increases the risk of poor decisions and sub-optimal investment in maintenance and renewal programs. This is especially the case when combining the increasing amount of data available from the use of new and improved technology with the loss of corporate knowledge in road pavement asset management.
To address this issue, local governments and road transport and traffic agencies need a method of replicating expert human decision making on assessing pavement condition at network level and identifying candidate sites at project level.
This project will provide a practical guide to develop machine learning processes to reduce risk and improve the quality and efficiency in using data by capturing expert pavement asset managers decision making.
The project will improve capability in road transport and traffic agencies to draw insights from data, accelerate the rate of learning of inexperienced staff and capture corporate knowledge by transforming data into insights.
DELIVERABLES:
This project will produce the following final deliverables:
• Guidelines Report that provides a practical guide and case studies on the methodology, process, data requirement of developing a Machine Learning based maintenance decision support tool.
• Webinar.
Also included as part of this tender are the following documents:
• Instructions for Authors of Austroads Publications which sets out the writing and formatting standards for research, technical and internal reports.
• Master Services Agreement outlining our Terms and Conditions. Please note that our Terms and Conditions are not negotiable.
All submissions are to be submitted as a PDF at a maximum size of 10MB.
All submissions are to include a completed Tender Proposal Coversheet.
The naming convention for submissions is: [your Company name] – [Project No.] – [any internal reference numbers].
All submissions are to include a statement as to how the respondent proposes to undertake the work, and keep to the agreed deadlines, given the current and proposed requirements and restrictions due to COVID-19.
The purpose of this project is to develop a proof of concept of a decision support system that applies machine learning on the network condition and inventory data to replicate a human expert pavement asset manager.
Road transport and traffic agencies have spent significant efforts on collecting data, however the use of data in supporting maintenance and renewal decisions is considered a challenge, especially for new or inexperienced asset managers. This increases the risk of poor decisions and sub-optimal investment in maintenance and renewal programs. This is especially the case when combining the increasing amount of data available from the use of new and improved technology with the loss of corporate knowledge in road pavement asset management.
To address this issue, local governments and road transport and traffic agencies need a method of replicating expert human decision making on assessing pavement condition at network level and identifying candidate sites at project level.
This project will provide a practical guide to develop machine learning processes to reduce risk and improve the quality and efficiency in using data by capturing expert pavement asset managers decision making.
The project will improve capability in road transport and traffic agencies to draw insights from data, accelerate the rate of learning of inexperienced staff and capture corporate knowledge by transforming data into insights.
DELIVERABLES:
This project will produce the following final deliverables:
• Guidelines Report that provides a practical guide and case studies on the methodology, process, data requirement of developing a Machine Learning based maintenance decision support tool.
• Webinar.
Also included as part of this tender are the following documents:
• Instructions for Authors of Austroads Publications which sets out the writing and formatting standards for research, technical and internal reports.
• Master Services Agreement outlining our Terms and Conditions. Please note that our Terms and Conditions are not negotiable.
All submissions are to be submitted as a PDF at a maximum size of 10MB.
All submissions are to include a completed Tender Proposal Coversheet.
The naming convention for submissions is: [your Company name] – [Project No.] – [any internal reference numbers].
All submissions are to include a statement as to how the respondent proposes to undertake the work, and keep to the agreed deadlines, given the current and proposed requirements and restrictions due to COVID-19.
This information is not guaranteed to be accurate or complete. Please confirm all details with the Tendering Firm before responding.

Powered by Tenders.Net - Inventors Of E-Tendering