State evaluation method for complex task network models

Abstract

This paper focuses on the assessment of non-complete states in complex task networks and establishes an online capability boundary assessment model based on real-time feature parameters. By utilizing multivariate heterogeneous state features for data mining and pattern recognition, we delve into virtual sample generation technology using an overall diffusion trend approach. This starts by examining the validity of sample data and analyzing the relevance of data acquired within the feature space. Building on this foundation, the overall diffusion trend method is applied to generate virtual sample input that aligns with the sampling distribution characteristics of avionics system equipment. To address non-complete state evaluation in complex task networks, we design a comprehensive model. This model involves constructing a system signal flow block diagram and a structural diagram depicting the available capacity of subsystems and the overall system tasks. The establishment of unknown function relationships in signal connections is achieved through a fusion of neural network and fuzzy logic systems. Finally, an intelligent optimization algorithm is employed to determine system parameters. Utilizing this neuro-fuzzy system in simulation, we attain real-time system responses and evaluate the output regarding the available capacity of system tasks.