Artificial neural networks with ant colony optimization for assessing performance of residential buildings

This article established artificial neural networks based on improved ant colony optimization evaluation model for residential performance. Firstly, on the basis of comprehensive analysis of the effects factors of residential building's performance, considering of the advantages of dealing with non-linear object of neural network, the neural network is trained by the sample data. While training neural network, the BP algorithm has good local performance but it is easy to fall into local Minimum, and the ant colony algorithm has good global performance, so the following combinatorial method is put forward. Then, the neural network is trained based on ant colony algorithm (ACBP algorithm) in global space, the parameters of neural network is trained using BP algorithm in local space. At 1ast, a case study carried out on the performance assessment of sample residential buildings using the model shows that the ACBP neura1 network outperforms BP neural network and AC neural network in the aspect of dynamic error forecast is verified by computer emulation example, and related conclusions are given.