Research On Construction Engineering Evaluation Based On Artificial Intelligence

Determination of project cost is one of the important content of project management,but as a result of knowledge engineering project investment stage is very limited,general weakness of project valuation is error and the preparation of a long time.With the continuous development of computer science,intelligent optimization technology has penetrated into every field,and theory of artificial intelligence is a very hot research topic at present.This paper mainly studies the application of artificial intelligence in the field of architectural engineering evaluation,Using particle swarm optimization of artificial neural networks and case-based reasoning intelligent method,established.three kinds of artificial intelligence estimate model.This article system elaborated the theoretical basis of the particle swarm optimization(pso),and the BP neural network,and the RBF neural network,and case-based reasoning.Explain the basic principle of particle swarm optimization(pso)algorithm,and the algorithm flow,and the selection of control parameters in detail.To verify the good optimization performance of particle swarm optimization(pso),using two simple basic function test the performance of the algorithm,Test results show that the particle swarm algorithm has good global search ability;This paper introduces the basic principle,and the learning rule and the algorithm flow of BP neural network and RBF neural network,in order to verify the function approximation ability of artificial neural network.The results show that the artificial neural network has good function approximation ability,and the artificial neural network has ability to imulate any nonlinear mapping in reality.In order to improve the performance of neural network,the neural network parameters are optimized by particle swarm optimization(pso)with good global optimization ability,and by changing the number of particles,inertia weight and evolutionary algebra to optimize the structure parameters of the neural network,so as to get more scientific and reasonable parameters of neural network,and used in artificial intelligence evaluation model.Adopt the method of integrating theory with practice,analysis and building construction project evaluation model based on artificial intelligence methods.First collect 31 has built engineering information in Shenyang nearly a year for samples,SPSS software is used to analyze the relationship between the characteristics and the cost of the project,and through integrated analysis finally identifies 9 characteristics affecting factors.Second describes in detail application of MATLAB software to establish construction algorithm based on PSO to optimize the BP neural network model and RBF neural network are optimized based on PSO parameters of process evaluation model of construction project,using MATLAB software programming sample training and implementation,and verify the practicability of model,the test results show that the error of the two model is in the range of the requirements.The last,using the collected 31 already built engineering information to establish Access case base,and using VBA computer language programming to realize the case retrieval process,finally established a construction project evaluation model based on case-based reasoning,forecast construction project appraisal,the predicting result error is smaller,proved that the model has practical value.