Fault diagnosis is an important measure to ensure the safety of production, and all kinds of fault diagnosis methods are of importance in actual production process. However, the complexity and uncertainty of productio...Fault diagnosis is an important measure to ensure the safety of production, and all kinds of fault diagnosis methods are of importance in actual production process. However, the complexity and uncertainty of production process often lead to the changes of data distribution and the emergence of new fault classes, and the number of the new fault classes is unpredictable. The reconstruction of the fault diagnosis model and the identification of new fault classes have become core issues under the circumstances. This paper presents a fault diagnosis method based on model transfer learning and the main contributions of the paper are as follows: 1) An incremental model transfer fault diagnosis method is proposed to reconstruct the new process diagnosis model. 2) Breaking the limit of existing method that the new process can only have one more class of faults than the old process, this method can identify M faults more in the new process with the thought of incremental learning. 3) The method offers a solution to a series of problems caused by the increase of fault classes. Experiments based on Tennessee-Eastman process and ore grinding classification process demonstrate the effectiveness and the feasibility of the method.展开更多
Aiming at the problems of lack of fault diagnosis samples and low model generalization ability of cross-working gear based on deep transfer learning, a fault diagnosis method based on improved deep residual network an...Aiming at the problems of lack of fault diagnosis samples and low model generalization ability of cross-working gear based on deep transfer learning, a fault diagnosis method based on improved deep residual network and transfer learning was proposed. Firstly, one-dimensional signal is transformed into two-dimensional time-frequency image by continuous wavelet transform. Then, a deep learning model based on ResNet50 is constructed. Attention mechanism is introduced into the model to make the model pay more attention to the useful features for the current task. The network parameters trained by ResNet50 network on ImageNet dataset were used to initialize the model and applied to the fault diagnosis field. Finally, to solve the problem of gear fault diagnosis under different working conditions, a small sample training set is proposed for fault diagnosis. The method is applied to gearbox fault diagnosis, and the results show that: The proposed deep model achieves 99.7% accuracy of gear fault diagnosis, which is better than the four models such as VGG19 and MobileNetV2. In the cross-working condition fault diagnosis, only 20% target dataset is used as the training set, and the proposed method achieves 93.5% accuracy.展开更多
针对高转速、高温升、大载荷等持续复杂的工况波动引起的航空发动机高速轴承故障诊断问题,提出了一种新型的深度图迁移学习算法,以及波动工况下基于图迁移卷积网络(graph transfer convolutional networks,简称GTCNs)的航空发动机高速...针对高转速、高温升、大载荷等持续复杂的工况波动引起的航空发动机高速轴承故障诊断问题,提出了一种新型的深度图迁移学习算法,以及波动工况下基于图迁移卷积网络(graph transfer convolutional networks,简称GTCNs)的航空发动机高速轴承故障智能诊断方法。首先,利用阶比分析对波动工况下航空发动机高速轴承振动信号进行重采样,将其转化为阶次谱信号作为目标域与源域数据集;其次,采用训练好的一维图卷积网络(onedimensional graph convolutional networks,简称1dGCNs)作为特征提取器,对其高层敏感特征计算其动态多核-最大均值散度(dynamic multiple kernel-maximum mean discrepancy,简称DMKMMD)距离,同时匹配高层与低层特征的边缘分布差异;然后,将对齐后的特征输入到分类器softmax中进行智能故障诊断;最后,在航空发动机高速轴承故障数据上验证了所提方法的有效性与先进性。结果表明,该方法具有更高的诊断准确率与鲁棒性,可以消除大波动工况下健康状态样本分布的差异性,提高诊断可迁移性。展开更多
Trend forecasting is an important aspect in fault diagnosis and work state supervision. The principle, where Grey theory is applied in fault forecasting, is that the forecast system is considered as a Grey system; the...Trend forecasting is an important aspect in fault diagnosis and work state supervision. The principle, where Grey theory is applied in fault forecasting, is that the forecast system is considered as a Grey system; the existing known information is used to infer the unknown information's character, state and development trend in a fault pattern, and to make possible forecasting and decisions for future development. It involves the whitenization of a Grey process. But the traditional equal time interval Grey GM (1,1) model requires equal interval data and needs to bring about accumulating addition generation and reversion calculations. Its calculation is very complex. However, the non equal interval Grey GM (1,1) model decreases the condition of the primitive data when establishing a model, but its requirement is still higher and the data were pre processed. The abrasion primitive data of plant could not always satisfy these modeling requirements. Therefore, it establishes a division method suited for general data modeling and estimating parameters of GM (1,1), the standard error coefficient that was applied to judge accuracy height of the model was put forward; further, the function transform to forecast plant abrasion trend and assess GM (1,1) parameter was established. These two models need not pre process the primitive data. It is not only suited for equal interval data modeling, but also for non equal interval data modeling. Its calculation is simple and convenient to use. The oil spectrum analysis acted as an example. The two GM (1,1) models put forward in this paper and the new information model and its comprehensive usage were investigated. The example shows that the two models are simple and practical, and worth expanding and applying in plant fault diagnosis.展开更多
文摘Fault diagnosis is an important measure to ensure the safety of production, and all kinds of fault diagnosis methods are of importance in actual production process. However, the complexity and uncertainty of production process often lead to the changes of data distribution and the emergence of new fault classes, and the number of the new fault classes is unpredictable. The reconstruction of the fault diagnosis model and the identification of new fault classes have become core issues under the circumstances. This paper presents a fault diagnosis method based on model transfer learning and the main contributions of the paper are as follows: 1) An incremental model transfer fault diagnosis method is proposed to reconstruct the new process diagnosis model. 2) Breaking the limit of existing method that the new process can only have one more class of faults than the old process, this method can identify M faults more in the new process with the thought of incremental learning. 3) The method offers a solution to a series of problems caused by the increase of fault classes. Experiments based on Tennessee-Eastman process and ore grinding classification process demonstrate the effectiveness and the feasibility of the method.
基金Supported by National Natural Science Foundation of P. R. China （60574083）, Key Laboratory of Process Industry Automation, State Education Ministry of China （PAL200514）
文摘Aiming at the problems of lack of fault diagnosis samples and low model generalization ability of cross-working gear based on deep transfer learning, a fault diagnosis method based on improved deep residual network and transfer learning was proposed. Firstly, one-dimensional signal is transformed into two-dimensional time-frequency image by continuous wavelet transform. Then, a deep learning model based on ResNet50 is constructed. Attention mechanism is introduced into the model to make the model pay more attention to the useful features for the current task. The network parameters trained by ResNet50 network on ImageNet dataset were used to initialize the model and applied to the fault diagnosis field. Finally, to solve the problem of gear fault diagnosis under different working conditions, a small sample training set is proposed for fault diagnosis. The method is applied to gearbox fault diagnosis, and the results show that: The proposed deep model achieves 99.7% accuracy of gear fault diagnosis, which is better than the four models such as VGG19 and MobileNetV2. In the cross-working condition fault diagnosis, only 20% target dataset is used as the training set, and the proposed method achieves 93.5% accuracy.
文摘高速列车在实际运营中的轴箱轴承故障数据及样本标签稀缺,极大限制了轴箱轴承故障诊断水平的提升。为此,本文提出了一种融合IFormer(inception transformer)与残差网络(ResNet)的多源域深度迁移学习方法ITRNet(inception transformer and ResNet)用于高速列车轴箱轴承故障诊断研究。该方法选择多种工况下的有监督标签数据作为多源域,首先采用连续小波变换获取轴承一维振动信号的时频谱图作为模型输入,在ITR-Net中构建IFormer网络和ResNet分别作为通用特征提取器和特定特征提取器,充分学习多源域与目标域数据的特征信息;同时,在迁移模型不同节点位置嵌入多核最大均值差异(MK-MMD)、局部最大均值差异(LMMD)与均方误差(MSE)损失函数,构建了一种新的多源域自适应迁移策略,有效减小多源域间及源域与目标域间的特征分布差异并增强多领域对齐程度。最后,通过分析不同载荷及不同转速下6类轴承故障迁移学习任务,对本文方法进行实验验证。结果表明,本文方法可以有效用于不同工况下轴承迁移学习故障诊断,多源域迁移故障诊断准确率显著高于单源域迁移,并且相比现有的深度适应网络(DAN)、联合适应网络(JAN)、相关对齐损伤(CORAL)网络、域对抗神经网络(DANN)、多特征空间适应网络(MFSAN),本文方法迁移学习诊断结果更为优异。研究结果将为迁移学习应用于轴箱轴承故障诊断提供一条新的途径。
文摘Trend forecasting is an important aspect in fault diagnosis and work state supervision. The principle, where Grey theory is applied in fault forecasting, is that the forecast system is considered as a Grey system; the existing known information is used to infer the unknown information's character, state and development trend in a fault pattern, and to make possible forecasting and decisions for future development. It involves the whitenization of a Grey process. But the traditional equal time interval Grey GM (1,1) model requires equal interval data and needs to bring about accumulating addition generation and reversion calculations. Its calculation is very complex. However, the non equal interval Grey GM (1,1) model decreases the condition of the primitive data when establishing a model, but its requirement is still higher and the data were pre processed. The abrasion primitive data of plant could not always satisfy these modeling requirements. Therefore, it establishes a division method suited for general data modeling and estimating parameters of GM (1,1), the standard error coefficient that was applied to judge accuracy height of the model was put forward; further, the function transform to forecast plant abrasion trend and assess GM (1,1) parameter was established. These two models need not pre process the primitive data. It is not only suited for equal interval data modeling, but also for non equal interval data modeling. Its calculation is simple and convenient to use. The oil spectrum analysis acted as an example. The two GM (1,1) models put forward in this paper and the new information model and its comprehensive usage were investigated. The example shows that the two models are simple and practical, and worth expanding and applying in plant fault diagnosis.
