摘要
变风量空调系统的故障检测与诊断对于提高建筑环境质量和实现节能至关重要。该系统故障类型复杂、数据量巨大、非线性特性强,传统的基于模型和基于规则的方法较难应用。本文提出了一种基于数据驱动的L2-BP神经网络故障诊断方法,首先通过TRNSYS模拟软件建立VAV空调系统仿真模型,获得四种常见故障的仿真模拟数据,然后利用运行数据和实际数据对L2-BP神经网络故障诊断模型进行验证。结果表明,本文提出的故障诊断模型能够克服单一方法的局限性,针对单一故障进行有效识别。
Fault detection and diagnosis of variable air volume air conditioning systems is crucial to improving the quality of building environment and achieving energy conservation.The system has complex fault types,huge data volume,and strong nonlinear characteristics.Traditional model-based and rule-based methods are difficult to apply.This paper proposes a data-driven L2-BP neural network fault diagnosis method.First,a VAV air conditioning system simulation model is established through TRNSYS simulation software to obtain simulation data of four common faults.Then,the L2-BP neural network fault diagnosis model is verified using operating data and actual data.The results show that the fault diagnosis model proposed in this paper can overcome the limitations of a single method and effectively identify a single fault.
作者
龚婉婷
Wanting Gong(School of Environment and Architecture,University of Shanghai for Science and Technology,Shanghai)
出处
《建模与仿真》
2024年第6期6493-6502,共10页
Modeling and Simulation
关键词
TRNSYS仿真模型
L2正则化
BP神经网络
变风量空调系统
故障诊断
TRNSYS Simulation Model
L2 Regularization
BP Neural Network
Variable Air Volume Air Conditioning System
Fault Diagnosis
