Commanders A. Intelligent Tools of Support the Process of Assessing Technical Condition of Buildings

The dissertation research is devoted to the decision of an actual scientific and practical problem of creation of information intelligent systems, which are capable to solve a problem of an estimation of a technical condition of objects of construction as a whole of conditions at nonlinear influence of vibrodynamic loadings of the environment. To solve the problem of assessing the technical condition of the object as a whole, a hybrid system is propose, the work of which has based on the use of generalized expert experience and artificial neuro-fuzzy networks of the TakagiSugeno-Kanga category. The architecture and algorithm of training of an artificial neural network is describe. The possibility of applying the Bayesian logicalprobabilistic approach to the dephasification of the values of the output change is considered. The input data vectors that reflect the negative impact of vibrodynamic loads on the technical condition of structures and the adaptation of the model of neurofuzzy inference to solve the problem of assessing the technical condition of objects with accumulated physical wear. The mechanism of formation of the knowledge base of the system based on the results of construction and technical examinations is shown. Methodical recommendations on the assessment of the technical condition of construction objects in general with the use of a specialized intelligent system to support the process of assessing the technical condition of buildings and structures is propose. The introduction of this system will reduce the impact of the human factor on the implementation of construction and technical examinations, which are carried out in fuzzy conditions of nonlinear loads and environmental influences.