文章的主要内容
针对这些问题，提出了一种主动领域自适应智能故障检测框架LDE-ADA，该框架利用迁移学习和主动学习相结合的方法来解决标签域扩展问题，从而提高模型的检测性能。同时，提出了一种改进的主动学习查询策略，以准确选择目标域中新增加的健康类别样本来辅助模型训练，解决标签域扩展的问题。综述要点：主要介绍了机器学习在设备故障检测领域的应用，并提出了迁移学习和主动学习相结合的方法来解决标签的域扩展问题。
正文开始
Active Domain Adaptation Method for Intelligent Fault Detection with Label Expansion
As the scale of mechanical equipment continues to expand and its functions become more complex, in order to avoid unnecessary economic losses, more and more attention has been paid to effectively preventing equipment failures.1 The method of signal processing2 requires the detection personnel to have rich knowledge and experience, and it is difficult to perform real-time monitoring. The method of machine learning (ML)3 requires a lot of human resources for feature processing, and high-dimensional features are difficult to mine. In recent years, deep learning (DL) technology4 has been widely studied for equipment fault detection due to its powerful feature extraction capability. However, training a high-performance DL model requires a large number of labeled samples, but the cost of collecting these labeled samples is expensive, which is the essential reason why deep models are rarely successful. Meanwhile, most of the existing deep learning methods assume the same data distribution in the source and target domains. However, in actual operation of mechanical equipment, there are reasons such as changing working conditions (such as changes in the speed and load of the equipment) and sudden changes in temperature. This assumption is unrealistic. Therefore, the performance of well-trained deep models applied to practical work will be greatly compromised.
Transfer learning (TL) can mine domain invariant fundamental features and structures in two different but related domains, which enables the information learned from the source domain to be transferred and reused between domains.5 In recent years, transfer learning methods have been increasingly applied to the fault diagnosis of rotating machinery.6,7 Unsupervised domain adaptation (UDA) is a representative method in transfer learning. This method generally utilizes minimum domain spacing8,9 or adversarial strategies10,11 to apply the knowledge learned by the model from the source domain to the detection of the target domain, so as to solve the problem of mapping bias. In the past few years, unsupervised domain adaptation has been gradually applied and developed in the fields of image classification12,13 and mechanical fault detection.14–16
However, the detection method based on unsupervised domain adaptation still has some defects, and two problems are more prominent:
(1) Performance issues with unsupervised models. Domain adaptation enables cross-domain diagnosis by solving the problem of mapping bias between source and target domains. However, the diagnostic performance of the unsupervised domain adaptation models is far less than that of most supervised diagnostic models,17,18 and even a small number of target domain label samples can significantly improve the diagnostic performance of the model.
(2) Label domain expansion problem. Most of the current mainstream domain adaptation diagnosis methods assume that the source domain and the target domain have the same label domain space. However, when the target domain has more health categories than the source domain, it is difficult for the domain adaptation model to detect the newly added health categories.
Neglecting the above problems will cause the model to misdiagnose the health status of the equipment in practical applications, resulting in unnecessary economic losses. This problem occurs in the model due to the lack of transferable knowledge of the newly added health categories in the source domain during training, resulting in the domain invariant features extracted by the model only having strong correlation with the source domain health categories, and lack of key features that can identify the newly added health categories. We found that most of the prediction results of the model for the newly added health categories are distributed at the decision boundary of the source domain health category, so this means that the newly added health category has a higher amount of information in the mapped feature invariant space.
In recent years, some researchers have used sample selection algorithms to extract informative samples in the target domain to assist model training, which is used to improve the diagnostic performance of unsupervised models. Active learning (AL) aims to select the most valuable samples from a pool of unlabeled samples using a query strategy. Among them, the pool-based active learning (Pool-Based AL)19–21 sample selection method has been widely studied. Most previous active learning methods use a single query strategy to select samples and train models in the same domain.22,23 With the development of transfer learning techniques, active learning is applied to cross-domain sample selection, so active transfer learning24,25 has been intensively studied. Domain adaptation (DA), as a branch of transfer learning, combined with active learning is called active domain adaptation (ADA).26–28 ADA is similar to the basic AL model training steps, which are generally divided into two parts: model training and query strategy. Fu18 proposed a new transferable query selection (TQS) method for active domain adaptation, including transferable uncertainty, transferable domainness, and transferable committee. It is experimentally demonstrated that TQS can select the target samples with the largest amount of information under domain transfer. Su29 proposed an active learning method for transferring representations across domains. This active adversarial domain adaptation (AADA) method explores the duality between two related issues: adversarial domain alignment and importance sampling for cross-domain adaptation models. Zhou30 proposed a discriminative active learning method for domain adaptation to reduce the workload of data annotation, and demonstrated the effectiveness of this active domain adaptation algorithm. However, previous active domain adaptation do not consider the impact of label domain expansion on model diagnostic performance.
In view of the above problems, this paper considers that the newly added healthy category samples in the domain invariant space after marginal distribution alignment have a high amount of information. An active domain adaptation intelligent fault detection framework LDE-ADA is designed to deal with the label domain expansion problem, which is used to solve the label domain expansion problem in cross-domain fault diagnosis. The method firstly uses the UDA model to learn domain invariant features, which are used to solve the domain bias problem of ADA and improve the query accuracy of newly added healthy samples. Then use the improved active learning query strategy to select the most valuable samples from the target domain sample pool for labeling. Finally, use the labeled fusion sample set to train the model again, and repeat the above steps.
Chen X, Wang S, Qiao B, et al. Basic research on machinery fault diagnostics: past, present, and future trends. Front Mech Eng 2018; 13(2): 264–291.
Wang T, Han Q, Chu F, et al. Vibration based condition monitoring and fault diagnosis of wind turbine planetary gearbox: a review. Mech Syst Signal Process 2019; 126: 662–685.
Lei Y, Yang B, Jiang X, et al. Applications of machine learning to machine fault diagnosis: a review and roadmap. Mech Syst Signal Process 2020; 138: 106587.
Saufi SR, Ahmad ZAB, Leong MS, et al. Challenges and opportunities of deep learning models for machinery fault detection and diagnosis: a review. IEEE Access 2019; 7: 122644–122662.
Li C, Zhang SH, Qin Y, et al. A systematic review of deep transfer learning for machinery fault diagnosis. Neurocomputing 2020; 407: 121–135.
Shao S, Mcaleer S, Yan R, et al. Highly accurate machine fault diagnosis using deep transfer learning. IEEE Trans Ind Inform 2019; 15(4): 2446–2455.
Guo L, Lei Y, Xing S, et al. Deep convolutional transfer learning network: a new method for intelligent fault diagnosis of machines with unlabeled data. IEEE Trans Ind Electron 2019; 66(9): 7316–7325.
Tzeng E, Hoffman J, Zhang N, et al. Deep domain confusion: maximizing for domain invariance. arXiv preprint arXiv:14123474, 2014.
Yang B, Lei Y, Jia F, et al. A polynomial kernel induced distance metric to improve deep transfer learning for fault diagnosis of machines. IEEE Trans Ind Electron 2019; 67(11): 9747–9757.
Shoeleh F, Yadollahi MM and Asadpour M. Domain adaptation-based transfer learning using adversarial networks. Knowl Eng Rev 2020; 35: e7.
He Z, Yang B, Chen C, et al. CLDA: an adversarial unsupervised domain adaptation method with classifier-level adaptation. Multimed Tools Appl 2020; 79(45): 3397333991.
Chen Y, Yang C, Zhang Y, et al. Conditional adaptation deep networks for unsupervised cross domain image classification. In: Proceedings of the 2019 14th IEEE conference on industrial electronics and applications (ICIEA), F, 2019. New York, NY: IEEE.
Zhao F, Liu W and Wen C. A new method of image classification based on domain adaptation. Sensors 2022; 22(4): 1315.
Pandhare V, Li X, Miller M, et al. Intelligent diagnostics for ball screw fault through indirect sensing using deep domain adaptation. IEEE Trans Instrum Meas 2020; 70: 1–11.
Jiao J, Zhao M, Lin J, et al. A mixed adversarial adaptation network for intelligent fault diagnosis. J Intell Manuf 2022; 33: 2207–2222.
Zhao K, Jiang H, Wang K, et al. Joint distribution adaptation network with adversarial learning for rolling bearing fault diagnosis. Knowl Based Syst 2021; 222: 106974.
Chen Y, Li W, Sakaridis C, et al. Domain adaptive faster r-cnn for object detection in the wild. In: Proceedings of the IEEE conference on computer vision and pattern recognition, F, 2018. New York, NY: IEEE.
Fu B, Cao Z, Wang J, et al. Transferable query selection for active domain adaptation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Nashville, TN, 20–25 June 2021. New York, NY: IEEE.
Nigam K and Mccallum A. Pool-based active learning for text classification. In: Proceedings of the conference on automated learning and discovery (CONALD), San Francisco, CA, 24–27 July 1998. New York, NY: ACM.
Zhao L, Sukthankar G and Sukthankar R. Importanceweighted label prediction for active learning with noisy annotations. In: Proceedings of the 21st international conference on pattern recognition (ICPR2012), Tsukuba, Japan, 11–15 November 2012. New York, NY: IEEE.
Zhang S, Yin J and Guo W.Pool-based active learning with query construction. In: Wang Y and Li T (eds) Foundations of intelligent systems. Berlin, Heidelberg: Springer. 2011, pp.13–22.
Gu B, Zhai Z, Deng C, et al. Efficient active learning by querying discriminative and representative samples and fully exploiting unlabeled data. IEEE Trans Neural Netw Learn Syst 2020; 32(9): 4111–4122.
Joshi AJ, Porikli F and Papanikolopoulos N. Multi-class active learning for image classification. In: Proceedings of the 2009 IEEE conference on computer vision and pattern recognition, Miami, FL, 20–25 June 2009. New York, NY: IEEE.
Singh A and Chakraborty S. Deep active transfer learning for image recognition. In: Proceedings of the 2020 international joint conference on neural networks (IJCNN), Glasgow, UK, 19–24 July 2020. New York, NY: IEEE.
Oh S, Ashiquzzaman A, Lee D, et al. Study on human activity recognition using semi-supervised active transfer learning. Sensors 2021; 21(8): 2760.
Saha A, Rai P, Daum ́ e H, et al. Active supervised domain adaptation. In: Proceedings of the joint European conference on machine learning and knowledge discovery in databases, Athens, Greece, 5–9 September 2011. Berlin, Heidelberg: Springer.
Rai P, Saha A, Daum ́ e III H, et al. Domain adaptation meets active learning. In: Proceedings of the NAACL HLT 2010 workshop on active learning for natural language processing, Stroudsburg, PA, 6 June 2010. New York, NY: ACM.
Wu F, Huang Y and Yan J. Active sentiment domain adaptation. In: Proceedings of the 55th annual meeting of the association for computational linguistics (Volume 1: Long Papers), Vancouver, Canada, July 2017. New York, NY: ACM.
Su J-C, Tsai Y-H, Sohn K, et al. Active adversarial domain adaptation. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, Snowmass, CO, 1–5 March 2020. New York, NY: IEEE.
Zhou F, Shui C, Yang S, et al. Discriminative active learning for domain adaptation. Knowl Based Syst 2021; 222: 106986.
文献数量：30
语种分布：英语
时间跨度：1998-2022
文献类型：Research article 、Review article
综述思路与方法：首先介绍了传统故障检测方法的局限性，然后讨论了深度学习和迁移学习在这方面的潜力。然后，深入探讨了无监督域适应的检测方法存在的缺陷，即无监督模型的性能较差和标签域扩展问题。随后，引出了主动域适应方法。最后，介绍主动域适应方法，概述其步骤。
综述要点：主要介绍了机器学习在设备故障检测领域的应用，并提出了迁移学习和主动学习相结合的方法来解决标签的域扩展问题。文章指出，传统的无监督领域自适应模型虽然可以解决源域和目标域之间的映射偏差问题，但其检测性能仍远不如大多数监督诊断模型，并且当前主流的领域适应诊断方法假定源域和目标域具有相同的标签域空间，当目标域比源域具有更多的健康类别时，这种假定就会导致模型无法检测新添加的健康类别。针对这些问题，提出了一种主动领域自适应智能故障检测框架LDE-ADA，该框架利用迁移学习和主动学习相结合的方法来解决标签域扩展问题，从而提高模型的检测性能。此外，还介绍了一些相关的研究工作和方法，如基于样本选择算法的主动学习方法和基于最小域间距离或对抗策略的无监督领域适应方法等。总体来说，综述提供了一种新的思路和方法来解决设备故障检测中的标签的域扩展问题，并对目前的相关研究工作进行了全面的介绍和分析。
译文
随着机械设备规模的不断扩大，其功能也越来越复杂，为了避免不必要的经济损失，人们越来越重视对设备故障的有效预防。1信号处理的方法2需要检测人员有丰富的知识和经验，难以进行实时监控。机器学习（ML）3的方法需要大量的人力资源进行特征处理，而且高维度的特征难以挖掘。近年来，深度学习（DL）技术4因其强大的特征提取能力而被广泛研究用于设备故障检测。然而，训练一个高性能的DL模型需要大量的标注样本，但收集这些标注样本的成本很高，这是深度模型很少成功的根本原因。同时，现有的大多数深度学习方法都假设源域和目标域的数据分布相同。然而，在机械设备的实际运行中，存在着诸如工作条件变化（如设备的速度和负载的变化）和温度突然变化等原因。这种假设是不现实的。因此，训练有素的深度模型应用到实际工作中，其性能将大打折扣。
迁移学习（TL）可以在两个不同但相关的领域中挖掘领域不变的基本特征和结构，这使得从源领域学到的信息可以在领域之间转移和重用。5近年来，迁移6,7 无监督领域适应（UDA）是转移学习中的一个代表性方法。该方法一般利用最小域间隔8,9或对抗策略10,11将模型从源域学到的知识应用于目标域的检测，从而解决映射偏差的问题。在过去的几年中，无监督领域适应性在图像分类12,13和机械故障检测等领域逐渐得到应用和发展14-16。
但是，基于无监督领域适应的检测方法仍然存在一些缺陷，其中有两个问题比较突出：
（1）无监督模型的性能问题。域适应通过解决源域和目标域之间的映射偏差问题实现跨域诊断。然而，无监督的域适应模型的诊断性能远远低于大多数有监督的诊断模型17,18，即使是少量的目标域标签样本也能显著提高模型的诊断性能。
(2) 标签域扩展问题。目前主流的领域适应性诊断方法大多假定源域和目标域具有相同的标签域空间。然而，当目标域比源域有更多的健康类别时，域适应模型就很难检测到新增加的健康类别。
忽视上述问题，将导致模型在实际应用中对设备的健康状况做出错误诊断，造成不必要的经济损失。由于在训练过程中缺乏对源域中新增加的健康类别的可迁移知识，导致模型提取的领域不变特征只与源域健康类别有很强的相关性，而缺乏能够识别新增加的健康类别的关键特征，所以模型中出现了这个问题。我们发现，模型对新增加的健康类别的预测结果大多分布在源域健康类别的决策边界，所以这意味着新增加的健康类别在映射的特征不变空间中具有较高的信息量。
近年来，一些研究人员利用样本选择算法在目标域中提取信息量大的样本来辅助模型训练，用于提高无监督模型的诊断性能。主动学习（AL）旨在利用查询策略从未标记的样本池中选择最有价值的样本。其中，基于池的主动学习（Pool-Based AL）19-2样本选择方法已被广泛研究。以前的主动学习方法大多采用单一的查询策略，在同一领域选择样本和训练模型。22,23随着迁移学习技术的发展，主动学习被应用于跨领域的样本选择，所以主动迁移学习24,25得到了深入研究。领域适应（DA）作为迁移学习的一个分支，与主动学习相结合被称为主动领域适应（ADA）。26-28 ADA与基本的AL模型训练步骤类似，一般分为两部分：模型训练和查询策略。Fu18提出了一种新的主动领域适应的可转移查询选择（TQS）方法，包括可转移不确定性、可转移领域性和可转移委员会。实验证明，TQS可以选择领域转移下信息量最大的目标样本。Su等人29提出了一种主动学习方法，用于跨域转移表征。这种主动对抗性领域适应（AADA）方法探索了两个相关问题之间的二重性：对抗性领域对齐和跨领域适应模型的重要性采样。Zhou等人30提出了一种用于领域适应的判别性主动学习方法，以减少数据注释的工作量，并证明了这种主动领域适应算法的有效性。然而，以前的主动域适应并没有考虑标签域扩展对模型诊断性能的影响。
鉴于上述问题，本文认为边际分布配准后的域不变空间中新增加的健康类别样本具有较高的信息量。设计了一个主动域适应智能故障检测框架LDE-ADA，用于解决跨域故障诊断中的标签域扩展问题。该方法首先利用UDA模型学习领域不变的特征，用于解决ADA的领域偏差问题，提高新增加的健康样本的查询精度。然后使用改进的主动学习查询策略，从目标域样本库中选择最有价值的样本进行标注。最后，使用标记后的融合样本集再次训练模型，并重复上述步骤。同时，提出了一种改进的主动学习查询策略，以准确选择目标域中新增加的健康类别样本来辅助模型训练，解决标签域扩展的问题。该策略首先使用基于不确定性的抽样方法来选择模型无法区分的目标域样本。然后，通过聚类算法从上述样本中选出有代表性的样本。这种方法不仅可以选择信息量最大的样本，而且可以保证所选样本的代表性，从而使模型在每一轮训练中都能发挥最大的性能。