Research On Construction Quality Control Of High Building Based On Artificial Neural Network

In recent years, with the rapid development of China’s economic construction and the progress of science and technology, the city scale and population grow rapidly and land resources become increasingly scarce, then to build an increasing number of high building has become an inevitable trend in the big city. High building construction’s quality directly related to the safety of people’s life and property, social stability and national economic development. The quality of the construction is a work which involves a wide range and have strong comprehensiveness. The factors which would impact the quality of the construction not only to meet the technical requirements, but also influenced by construction machinery, construction scheme, construction personnel quality and engineering cost. How can we make the prior control of the building construction quality to meets the requirements of quality standards for these factors, to avoid quality problems, become the primary task of quality control that has a strong practical significance.Construction quality control of high building is a complex and comprehensive problem which contains decision problem of multiple factors. In order to avoid the waste of resources and quality problems, the construction quality control should be strengthen in advance, to take preventive measures. Based on the quality control measures in advance to predict the quality level after the completion of the project,according to the forecast results to determine whether fully prepared beforehand control and take measures for improvement. The main research work is as follows:(1) Summarize the research status of construction quality control at home andabroad, the existing problems in the construction quality control of high building analyzed in our country. The basic concepts, related theories and basic principles of construction quality control is introduced in this paper.(2) The characteristics of the high building construction is expounded, the main content of construction quality control of high building are discussed in this paper, and emphatically analyzed the five influence factors of construction quality(people,material, machine, method, environment), forecast index system for high building construction quality is established according to the principle of index system construction.(3) The basic theory of artificial neural network and the basic principle of BP neural network are introduced, the feasibility of the BP neural network is analyzed which is used to solve the problem of construction quality control. The BP neural network is adopted to define the indexes’ weight, and established the BP neural network model by using MATLAB software. Then, 25 groups’ measured data of the high building is collected which used as the training sample and test sample to train and test the established model.(4) The quality control measures proposed building advance is expounded, the trained BP neural network model is used to predict the building construction quality level after the completion. According to the predicted results, that whether the construction process parameters meet with the quality objectives could determine in advance. Meanwhile, in the case the situation does not meet with the quality target,BP neural network model could use to adjust the process parameters, finding out the problem, and then put forward some improvement measures in order to achieve the construction quality control in advance.