Two-stage diagnosis framework for heating pipeline system using improved group search optimizer

Abstract

This paper presents a two-stage framework for monitoring the decline of pipeline insulation and diagnosing leakage fault. The task of the first stage is to estimate the parameters of the pipeline network, so as to monitor the abnormal heat conduction data of pipelines, and use the estimation results to update the parameters of the pipeline model. The task of the second stage is to obtain the location and the water loss of after a leakage fault. In the framework, the tasks of the two stages are formulated into the problem of minimizing the divergence between the real system and the simulation system. And the problem is solved by the group search optimizer (GSO) algorithm with improved boundary search strategy in this paper. In the simulation tests, the framework is verified to be able to diagnose the faults. And in comparison with other heuristic algorithms, the GSO algorithm has the best ability to accurately diagnose the fault. Finally, the framework is applied in the cooling system, which shows that the framework has good migration capability.