This paper presents new method for analysis of a technical state of large-panel residential buildings.
This method is based on the extracted data processing by means of the artificial neural networks. The aim is to learn the artificial neural network configurations for a set of data containing values of the technical state and information about building repairs for last years (or other information and building parameters) and next to analyse new buildings by the instructed neural network. The second profit from using artificial neural networks is the reduction of number of parameters. Instead of more then 40 parameters describing building, about 6-12 are usually sufficient for satisfactory accuracy. This method could have lower accuracy but it is less prone to data errors.
The algorithm for obtaining results from artificial neural networks (ANN) consists of:
1. preparing full database in MS Excel,
2. selection of data for the next step of analysis,
3. data normalization for use in net – changing range of values from <0,N> to <0,1>,
4. selecting components from the records,
5. sorting and selecting records for groups of data: for training, for cross validation, for testing,
6. choosing the type of artificial neural net, selecting topology,
7. teaching net, verifying results,
8. repeating steps (5,6,7) for optimization of the network architecture,
9. analyzing new data with the optimal net.
Application of artificial neural networks for estimating the technical state of buildings:
- can work on incomplete data,
- is more resistant to errors in data,
- needs small range of data as an input,
- Multilayer Perceptron is type of net, which gives good results, the error is not significant,
- it can be applied as one from many methods for estimating technical state.
Financed by the National Centre for Research and Development under grant No. SP/I/1/77065/10 by the strategic scientific research and experimental development program:
SYNAT - “Interdisciplinary System for Interactive Scientific and Scientific-Technical Information”.