基于一致损失生成对抗网络的冷水机组故障诊断  

Fault diagnosis of chillers based on consistency loss generative adversarial network

作　　者：高学金[1] 吴浩宁 高慧慧 齐咏生[2] Gao Xuejin;Wu Haoning;Gao Huihui;Qi Yongsheng(School of Information Science and Technology,Beijing University of Technology,Beijing 100124,China;School of Electric Power,Inner Mongolia University of Technology,Hohhot 010051,China)

机构地区：[1]北京工业大学信息科学技术学院,北京100124 [2]内蒙古工业大学电力学院,呼和浩特010051

出　　处：《仪器仪表学报》2025年第1期285-297,共13页Chinese Journal of Scientific Instrument

基　　金：北京市自然科学基金(4222041);北京市教育委员会科研计划(KM202410005034)项目资助。

摘　　要：冷水机组是供暖通风与空气调节系统的重要组成部分,当冷水机组发生故障时将造成能源浪费甚至安全事故。因此,针对冷水机组的故障诊断对于暖通风与空气调节等系统至关重要。基于数据驱动的故障诊断方法依赖大量历史数据,但带标签的故障数据往往难以收集,导致模型的诊断准确率下降。为此,提出了一种基于一致损失生成对抗网络(CLGAN)的故障诊断方法。首先,利用少量带标签样本和大量无标签样本训练CLGAN,并生成故障数据;然后,利用生成数据与历史数据构建一个包含各类故障的平衡数据集;最后,利用该数据集训练故障分类器并对冷水机组进行实时诊断。CLGAN通过在判别器中引入一致性损失函数,能够有效利用无标签数据辅助模型训练,提升了数据利用率。同时,CLGAN迫使生成器在多个尺度上满足判别器的要求,这种多维度的反馈机制使得模型在面对扰动时,依然能生成高质量的样本,进而提高故障诊断的准确性和鲁棒性。基于ASHRAE和HY-31C数据集的实验结果表明,在各类别仅有5个带标签样本的情况下,CLGAN分别获得了92.8%和95.9%的故障诊断准确率,展现了良好的故障诊断性能。此外,在噪声和跨工况实验中,CLGAN相比于其他对比方法也展现出了良好的鲁棒性和泛化性。A chiller is a critical component of heating,ventilation,and air conditioning(HVAC)systems.Faults in chillers can lead to energy waste and even safety incidents.Therefore,fault diagnosis for chillers is essential for HVAC systems.Data-driven fault diagnosis methods rely on large amounts of historical data,but labeled fault data is often difficult to collect,resulting in reduced diagnostic accuracy of models.To address this issue,this paper proposes a fault diagnosis method based on a consistency loss generative adversarial network(CLGAN).First,CLGAN is trained with a small number of labeled samples and a large amount of unlabeled data to generate realistic fault samples.Next,a balanced dataset containing multiple fault categories is constructed by combining both generated and historical data.Finally,a fault classifier is trained on this balanced dataset to perform real-time fault diagnosis.By introducing a consistency loss function into the discriminator,CLGAN effectively leverages unlabeled data,increasing data utilization.Meanwhile,the generator is guided at multiple scales to meet the discriminator′s requirements,enabling the model to produce high-quality samples even under various disturbances and thus enhancing diagnostic accuracy and robustness.Experimental results on the ASHRAE and HY-31C datasets demonstrate that,with only five labeled samples per class,CLGAN achieves fault diagnosis accuracies of 92.8%and 95.9%,respectively,illustrating its excellent performance.Moreover,in noise and cross-condition experiments,CLGAN shows superior robustness and generalization compared with other methods.Chiller is a critical component of heating,ventilation,and air conditioning(HVAC)systems.Faults in chiller can lead to energy waste and even safety incidents.Therefore,fault diagnosis for chillers is essential for HVAC systems.Data-driven fault diagnosis methods rely on large amounts of historical data,but labeled fault data is often difficult to collect,resulting in reduced diagnostic accuracy of models.To address th

关 键 词：故障诊断 生成对抗网络 冷水机组 一致损失函数 无标签数据 

分 类 号：TH17[机械工程—机械制造及自动化]