Dissertation > Industrial Technology > Automation technology,computer technology > Automated basic theory > Artificial intelligence theory > Artificial Neural Networks and Computing

Research on the Prediction of Construction Safety Based on the Rough Sets Theory and Neural Network

Author ZhuRui
Tutor LiShuQuan
School Tianjin University of Finance and Economics
Course Technology Economics and Management
Keywords Rough Sets Theory Neural Network Index system
Type Master's thesis
Year 2008
Downloads 284
Quotes 3
Download Dissertation

Because of the characteristics of construction, there is always full of the potential safety problems in the construction locale. All these kinds of factors may lead to accidents at any time, and threaten the lives safety of construction workers seriously, so the safety management becomes an important part of the project management.First of all, the papers talked about the security management, and then discussed the meaning and the characteristics construction safety management in China. After reading a lot of literature, the writer classified and summarized the current research content and methods of construction safety management in China, then a construction safety prediction model based on Rough Sets Theory and Neural Network was put forward.The Rough Sets was firstly used to reduce the elements of staff which influenced the construction safety. After the core personnel elements gained, the author set up a new construction safety assessment criteria system, which referred the“Safety Evaluation Criteria in Construction Enterprises”(JGJ/T77-2003) promulgated by China’s Ministry of Construction. Then, an investigating questionnaire was designed according to this index system, and after processing the original data by the method of Rough Set, we got 17 main safety indicators. Finally, a prediction model of Neural Network was established which used these 17 indicators as input variables. The results showed that this model could operate smoothly and forecast well, so there are some worth in application.

Related Dissertations
More Dissertations