本文针对某船用增压锅炉的缓变故障,开展了基于热经济学的诊断方法研究。首先,在GSE仿真平台上构建增压锅炉的仿真模型,参考常见故障机理及判断依据,对热力故障进行模拟。模拟了8类单一故障,采集故障工况数据建立了多程度缓变故障的样本库。其次,按照热经济学结构理论,将增压锅炉按照“产品”的定义划分为四个过程组元,建立了锅炉的生产结构图,并计算故障过程中每个组元额外的不可逆损失,作为故障定位及量化的依据。最后,针对故障引发的扩散效应,提出了基于神经网络的?补偿策略,经过叠加故障的对比,该方法能够有效增强结构理论的故障定位能力,允许设备的孤立诊断,还原叠加故障与外部冲击情况下过路内部设备的异常状况,对故障预防及量化有一定意义。

This article conducts a study on the diagnosis method based on thermoeconomics for the slowly changing faults of marine turbocharged boilers. Firstly, a simulation model of a pressurized boiler is constructed on the GSE simulation platform, referencing common fault mechanisms and judgment criteria to simulate thermal faults. Simulated 8 types of single faults, collected fault condition data, and established a sample library of multiple degrees of slowly changing faults. Secondly, according to the structural theory of thermoeconomics, the pressurized boiler is divided into four process components according to the definition of "product". A production structure diagram of the boiler is established, and the additional irreversible losses of each component during the fault process are calculated as the basis for fault localization and quantification. Finally, in response to the diffusion effect caused by faults, a neural network-based exergy compensation strategy is proposed, which enhances the fault localization ability of structural theory, allows for isolated diagnosis of equipment, and effectively restores the true abnormal situation of equipment under superimposed faults and external shocks.

U664.11

黑龙江省重点研发计划(No.JD22A020)