Unit dynamic fire risk assessment method based on neural network

Abstract

The invention discloses a unit dynamic fire risk assessment method based on a neural network, and the method comprises the following steps: S1, recognizing basic elements of building fire risk assessment according to the type of a building. According to the invention, the analytic hierarchy process AHP and the BP neural network are combined, and the invention can be applied to real-time evaluationof fire risks of various types of social units at the same time; the method not only keeps experts to quantify quantitative and non-quantitative evaluation factors in subjective understanding and judgment, but also keeps the nonlinear mapping capability of the BPNN neural network. By automatically determining the input dimension of the complex fire risk evaluation system, the learning rate of theneural network is improved, the convergence rate of the neural network is increased, the evaluation result is more accurate and credible, automatic fire risk prediction becomes possible, then a scientific basis is provided for preventing and controlling fire, and subjectivity and blindness during fire prevention are reduced.

Description

technical field [0001] The invention relates to the technical field of risk assessment, in particular to a neural network-based unit dynamic fire risk assessment method. Background technique [0002] At present, the fire risk assessment for social units (governments, groups, enterprises and institutions, hereinafter referred to as "units") is mainly semi-quantitative evaluation methods, including fire risk index method, Delphi method and analytic hierarchy process. It analyzes fire risk sources and other risk parameters, assigns appropriate indices to them according to certain principles, and then integrates them mathematically to obtain a subsystem or system index, which is quick and easy. Its shortcoming is that this kind of method ignores the in-depth study of various influencing factors and the mutual influence and restriction between various factors, and does not solve the nonlinear problem in the evaluation process. [0003] Neural network is a nonlinear system compos...

AI Technical Summary

Problems solved by technology

However, when studying the modeling of complex systems, due to the many influencing factors and complex relationships, if they are all used as the input of the neural network, it will obviously increase the complexity of the network, reduce the performance of the network, and affect the calculation accuracy.

Images