Deep learning-based adversarial multi-classifier optimization for cross-domain machinery fault diagnostics

Despite the recent success in data-driven machinery fault diagnosis, cross-domain diagnostic tasks still remain challenging where the supervised training data and unsupervised testing data are collected under different operating conditions. In order to address the domain shift problem, minimizing the marginal domain distribution discrepancy is considered in most of the existing studies. While improvements have been achieved, the class-level alignments between domains are generally neglected, resulting in deteriorations in testing performance. This paper proposes an adversarial multi-classifier optimization method for cross-domain fault diagnosis based on deep learning. Through adversarial training, the overfitting phenomena of different classifiers are exploited to achieve class-level domain adaptation effects, facilitating extraction of domain-invariant features and development of cross-domain classifiers. Experiments on three rotating machinery datasets are carried out for validations, and the results suggest the proposed method is promising for cross-domain fault diagnostic tasks.     

Intelligent fault diagnosis for rotating machinery using deep Q-network based health state classification: A deep reinforcement learning approach

Fault diagnosis methods for rotating machinery have always been a hot research topic, and artificial intelligence-based approaches have attracted increasing attention from both researchers and engineers. Among those related studies and methods, artificial neural networks, especially deep learning-based methods, are widely used to extract fault features or classify fault features obtained by other signal processing techniques. Although such methods could solve the fault diagnosis problems of rotating machinery, there are still two deficiencies. (1) Unable to establish direct linear or non-linear mapping between raw data and the corresponding fault modes, the performance of such fault diagnosis methods highly depends on the quality of the extracted features. (2) The optimization of neural network architecture and parameters, especially for deep neural networks, requires considerable manual modification and expert experience, which limits the applicability and generalization of such methods. As a remarkable breakthrough in artificial intelligence, AlphaGo, a representative achievement of deep reinforcement learning, provides inspiration and direction for the aforementioned shortcomings. Combining the advantages of deep learning and reinforcement learning, deep reinforcement learning is able to build an end-to-end fault diagnosis architecture that can directly map raw fault data to the corresponding fault modes. Thus, based on deep reinforcement learning, a novel intelligent diagnosis method is proposed that is able to overcome the shortcomings of the aforementioned diagnosis methods. Validation tests of the proposed method are carried out using datasets of two types of rotating machinery, rolling bearings and hydraulic pumps, which contain a large number of measured raw vibration signals under different health states and working conditions. The diagnosis results show that the proposed method is able to obtain intelligent fault diagnosis agents that can mine the relationships between the raw vibration signals and fault modes autonomously and effectively. Considering that the learning process of the proposed method depends only on the replayed memories of the agent and the overall rewards, which represent much weaker feedback than that obtained by the supervised learning-based method, the proposed method is promising in establishing a general fault diagnosis architecture for rotating machinery.     

A bearing fault diagnosis method without fault data in new working condition combined dynamic model with deep learning

Bearing fault diagnosis plays an important role in rotating machinery equipment’s safe and stable operation. However, the fault sample collected from the equipment is seriously absent, which obstacles the establishment of the diagnostic model. In this paper, a novel false-real data synthesis method combined bearing dynamic model with a generated adversarial network is proposed to solve the problem of zero-shot in new condition. Firstly, the bearing dynamic model is constructed to simulate vibration data in different conditions. Secondly, the conversion model is trained by simulation data in different conditions, which will be employed to convert real-world data in the old condition into the conversion data in the new condition. Thirdly, the GAN model is trained by simulation data and real-world data in old condition and finetuned by simulation data and conversion data in the new condition. Finally, simulation data in the new condition are inputted to the finetuned GAN model to obtain generated data in the new condition, and the fault diagnosis model is trained by it. To validate the performance of the proposed method, various comparative experiments are carried out on one rolling bearing dataset. The results indicate that the proposed method can solve the problem of zero-shot in new condition with excellent diagnosis performance.     

Deep multi-scale adversarial network with attention: A novel domain adaptation method for intelligent fault diagnosis

Data driven-based intelligent fault diagnosis methods, as a promising approach, have been widely employed in the health management and maintenance decision of rotating machinery. However, the domain shift phenomenon caused by internal and external interference inevitably exists in practical application scenarios, which significantly deteriorates the performances of the intelligent diagnosis model. And the preparation of label information in real complex scenes is usually time-consuming and expensive. To overcome these challenges, a novel unsupervised domain adaptation framework named deep multi-scale adversarial network with attention (MSANA) is introduced for machinery fault diagnosis. It is established based on two main components, one is the shared feature generator, which is constructed by two novel multi-scale modules with attention mechanism, and the other part is a fault pattern recognition module composed of two differentiated discriminators. While the multi-scale module is used to obtain rich features through different internal perceptual scales, the attention mechanism determines the weights of different scales, which promotes the dynamic adjustment performance and adaptive ability of the model. Then, decision boundary assisted adversarial learning strategy is employed to eliminate domain distribution differences and obtain domain-invariant features. A total of ten rolling bearing-based transfer scenarios and six gearbox-based transfer scenarios are adopted to evaluate the transferability of the proposed MSANA model, and the cross-domain transfer results show that it has superior transferability and stability.     

Comparison of four direct classification methods for intelligent fault diagnosis of rotating machinery

Condition monitoring of rotating machinery is important to promptly detect early faults, identify potential problems, and prevent complete failure. Four direct classification methods were introduced to diagnose the regular condition, inner race defect, outer race defect, and rolling element defect of rolling bearings. These include the K-Nearest Neighbor algorithm (KNN), Probabilistic Neural Network (PNN), Particle Swarm Optimization optimized Support Vector Machine (PSO-SVM) and a Rule-Based Method (RBM) based on the MLEM2 algorithm and a new Rule Reasoning Mechanism (RRM). All of them can be run on the Fault Decision Table (FDT) containing numerical variables and output fault categories directly. The diagnosis results were discussed in terms of accuracy, time consumption, intelligibility, and maintainability. Especially, the interactions of the systems and human experts were compared in detail. It was concluded that all the four methods can work satisfactorily on accuracy, in an order of the PSO-SVM ranking the first, followed by the RBM that functioned the friendliest. Moreover, the RBM had the ability of feature reduction by itself, and would be most suitable for real-time applications.     

Attitude data-based deep hybrid learning architecture for intelligent fault diagnosis of multi-joint industrial robots

Monitoring the transmission status of multi-joint industrial robots is very important for the accuracy of the robot motion. The fault diagnosis information is an indispensable basis for the collaborative maintenance of the robots in industry 4.0. In this paper, an attitude data-based intelligent fault diagnosis approach is proposed for multi-joint industrial robots. Based on the analysis of the transmission mechanism, the attitude change of the last joint is employed to reflect the transmission fault of robot components. An economical data acquisition strategy is performed by only installing one attitude sensor on the last joint of the multi-joint robot. Considering the characteristics of attitude data, a hybrid sparse auto-encoder (SAE) and support vector machine (SVM) approach, namely SAE-SVM, is subsequently presented to construct an intelligent fault diagnosis model by learning from the attitude dataset with multiple fault information. Experimental results show that the proposed fault diagnosis approach has promising performance in identifying different faults related to the reducer of a 6-axial multi-joint industrial robot accurately and reliably.     

Multi-mode data augmentation and fault diagnosis of rotating machinery using modified ACGAN designed with new framework

As one of the representative unsupervised data augmentation methods, generative adversarial networks (GANs) have the potential to solve the problem of insufficient samples in fault diagnosis of rotating machinery. However, the existing unsupervised GANs are usually incapable of simultaneously generating multi-mode fault samples and have some shortcomings such as mode collapse and gradient vanishing. To overcome these deficiencies, a supervised model called modified auxiliary classifier GAN (MACGAN) designed with new framework is proposed in this paper. Firstly, a new ACGAN framework is developed by adding an independent classifier to improve the compatibility between the classification and discrimination. Secondly, the Wasserstein distance is introduced in the new loss functions to overcome mode collapse and gradient vanishing. Finally, to achieve stable training, a spectral normalization is used to replace the weight clipping to constrain the weight parameters of discriminator. The proposed method is applied to fault diagnosis of bearing and gear. Compared with the existing GANs, the proposed method can more efficiently generate multi-mode fault samples with higher qualities, which can be used to assist the training of deep learning-based fault diagnosis models with high accuracy and good stability.     

Intelligent machinery health prognostics under variable operation conditions with limited and variable-length data

High accuracy health prognostics are significant to machinery intelligent operation and maintenance. Current data-driven prognostics achieve great success that benefits from amply learning samples. In fact, data scarcity challenge widely exists in machinery prognostics and health management, especially for high-end equipment. This study aims to solve this dilemma and proposes a novel meta learning algorithm reconstructed by classic variable-length prediction mode and attention mechanism, namely meta attention recurrent neural network (MARNN). Specifically, we first develop the encoder-decoder with attention mechanism (EDA) cell to perform episodic learning for the subtask-level upgrade. Then multiple subtasks with EDA as prediction models are aggregated to accomplish meta-level upgrade, thus mining the general degradation knowledge from historical datasets. Finally, cross-domain prognostics tasks can be easily realized through fine-tuning tricks, and three rotating machinery run-to-failed experiments are conducted to prove the generalizations of MARNN, which can obtain desired results even when the on-site adaptation data is reduced to one-twentieth.     

A novel Brownian correlation metric prototypical network for rotating machinery fault diagnosis with few and zero shot learners

Due to the variability of working conditions and the scarcity of fault samples, the existing diagnosis models still have a big gap under the condition of covering more practical application scenarios. Therefore, it is of great significance to study an intelligent diagnosis scheme that takes few samples in the training source domain and zero samples in the test target domain (FST-ZST) into account. A Brownian correlation metric prototypical network (BCMPN) algorithm based on a multi-scale mask preprocessing mechanism is proposed for the above problem. First, this paper constructs a multi-scale mask preprocessing mechanism (MMP) to improve the optimization starting point. Second, the multi-scale feature embedding is realized through the dilation convolution module and the effective light channel attention (ELCA) module. Third, based on the Brownian distance similarity measurement, we learn the feature representation by measuring the difference between the joint feature function and the edge product in the field of diagnosis. Finally, based on the gear data set of the Connecticut university (UConn) and the data collected in the laboratory, it is proved that the BCMPN has better performance in the problem of FST-ZST.     

数据失衡下基于WGAN和GAPCNN的轴承故障诊断研究

针对轴承故障数据严重失衡导致所训练的模型诊断能力和泛化能力较差等问题,提出基于Wasserstein距离的生成对抗网络来平衡数据集的方法。该方法首先将少量故障样本进行对抗训练,待网络达到纳什均衡时,再将生成的故障样本添加到原始少量故障样本中起到平衡数据集的作用;提出基于全局平均池化卷积神经网络的诊断模型,将平衡后的数据集输入到诊断模型中进行训练,通过模型自适应地逐层提取特征,实现故障的精确分类诊断。实验结果表明,所提诊断方法优于其他算法和模型,同时拥有较强的泛化能力和鲁棒性。     

A reinforcement ensemble deep transfer learning network for rolling bearing fault diagnosis with Multi-source domains

Fault diagnosis with transfer learning has achieved great attention. However, existing methods mostly focused on single-source-single-target sceneries. In some cases, there may exist multiple source domains. Therefore, a reinforcement ensemble deep transfer learning network (REDTLN) is proposed for fault diagnosis with multi-source domains. Firstly, various new kernel maximum mean discrepancies (kMMDs) are used to construct multiple deep transfer learning networks (DTLNs) for single-source-single-target domain adaptation. The differences of kernel functions and source domains can help the DTLNs learn diverse transferable features. Secondly, a new unified metric is designed based on kMMD and diversity measures for unsupervised ensemble learning. Finally, using the unified metric as the reward, a reinforcement learning method is firstly explored to generate an effective combination rule for multi-domain-multi-model reinforcement ensemble. The proposed method is verified with experiment datasets, and the results empirically show its effectiveness and superiority compared with other methods.     

Making costly manufacturing smart with transfer learning under limited data: A case study on composites autoclave processing

The integration of advanced manufacturing processes with ground-breaking Artificial Intelligence methods continue to provide unprecedented opportunities towards modern cyber-physical manufacturing processes, known as smart manufacturing or Industry 4.0. However, the “smartness” level of such approaches closely depends on the degree to which the implemented predictive models can handle uncertainties and production data shifts in the factory over time. In the case of change in a manufacturing process configuration with no sufficient new data, conventional Machine Learning (ML) models often tend to perform poorly. In this article, a transfer learning (TL) framework is proposed to tackle the aforementioned issue in modeling smart manufacturing. Namely, the proposed TL framework is able to adapt to probable shifts in the production process design and deliver accurate predictions without the need to re-train the model. Armed with sequential unfreezing and early stopping methods, the model demonstrated the ability to avoid catastrophic forgetting in the presence of severely limited data. Through the exemplified industry-focused case study on autoclave composite processing, the model yielded a drastic (88%) improvement in the generalization accuracy compared to the conventional learning, while reducing the computational and temporal cost by 56%.     

Machine learning algorithm selection for windage alteration fault diagnosis of mine ventilation system

Machine learning algorithms have been widely used in mine fault diagnosis. The correct selection of the suitable algorithms is the key factor that affects the fault diagnosis. However, the impact of machine learning algorithms on the prediction performance of mine fault diagnosis models has not been fully evaluated. In this study, the windage alteration faults (WAFs) diagnosis models, which are based on K-nearest neighbor algorithm (KNN), multi-layer perceptron (MLP), support vector machine (SVM), and decision tree (DT), are constructed. Furthermore, the applicability of these four algorithms in the WAFs diagnosis is explored by a T-type ventilation network simulation experiment and the field empirical application research of Jinchuan No. 2 mine. The accuracy of the fault location diagnosis for the four models in both networks was 100%. In the simulation experiment, the mean absolute percentage error (MAPE) between the predicted values and the real values of the fault volume of the four models was 0.59%, 97.26%, 123.61%, and 8.78%, respectively. The MAPE for the field empirical application was 3.94%, 52.40%, 25.25%, and 7.15%, respectively. The results of the comprehensive evaluation of the fault location and fault volume diagnosis tests showed that the KNN model is the most suitable algorithm for the WAFs diagnosis, whereas the prediction performance of the DT model was the second-best. This study realizes the intelligent diagnosis of WAFs, and provides technical support for the realization of intelligent ventilation.     

A modeling and probabilistic reasoning method of dynamic uncertain causality graph for industrial fault diagnosis

Online automatic fault diagnosis in industrial systems is essential for guaranteeing safe, reliable and efficient operations.However, difficulties associated with computational overload, ubiquitous uncertainties and insufficient fault samples hamper the engineering application of intelligent fault diagnosis technology. Geared towards the settlement of these problems, this paper introduces the method of dynamic uncertain causality graph, which is a new attempt to model complex behaviors of real-world systems under uncertainties. The visual representation to causality pathways and self-relied "chaining" inference mechanisms are analyzed. In particular, some solutions are investigated for the diagnostic reasoning algorithm to aim at reducing its computational complexity and improving the robustness to potential losses and imprecisions in observations. To evaluate the effectiveness and performance of this method, experiments are conducted using both synthetic calculation cases and generator faults of a nuclear power plant. The results manifest the high diagnostic accuracy and efficiency, suggesting its practical significance in large-scale industrial applications.     

Intelligent fault diagnosis of mechanical equipment under varying working condition via iterative matching network augmented with selective Signal reuse strategy

Change of working condition leads to discrepancy in domain distribution of equipment vibration signals. This discrepancy poses an obstacle to application of deep learning method in fault diagnosis of wind turbine. When lacking domain adaptation ability, diagnostic accuracy of deep learning method applied to unseen condition will decrease significantly. To solve this problem, an iterative matching network augmented with selective sample reuse strategy is proposed. By generating pseudo labels for unlabeled signals from unseen condition and reusing these signals to iteratively update parameters, embedding space of matching network reduce discrepancy in domain distribution between different working conditions. This makes the model more adaptable to unseen condition. Specially designed filter is proposed for selecting pseudo-labeled signals to increase proportion of correctly labeled signals in iteration. By combing these two points, proposed algorithm can be updated iteratively based on selected pseudo-labeled signals and achieve higher accuracy when analyzing signals of unseen working conditions. Multiscale feature extractor is used to extract features at different scales and form embedding space. Effectiveness of the proposed algorithm is verified by four datasets. Experiments show that this algorithm not only has good performance under varying load and speed conditions but also surpasses other domain adaptation methods.     

On-line transfer learning for multi-fidelity data fusion with ensemble of deep neural networks

Deep Neural Network (DNN) is widely used in engineering applications for its ability to handle problems with almost any nonlinearities. However, it is generally difficult to obtain sufficient high-fidelity (HF) sample points for expensive optimization tasks, which may affect the generalization performance of DNN and result in inaccurate predictions. To solve this problem and improve the prediction accuracy of DNN, this paper proposes an on-line transfer learning based multi-fidelity data fusion (OTL-MFDF) method including two parts. In the first part, the ensemble of DNNs is established. Firstly, a large number of low-fidelity sample points and a few HF sample points are generated, which are used as the source dataset and target dataset, respectively. Then, the Bayesian Optimization (BO) is utilized to obtain several groups of hyperparameters, based on which DNNs are pre-trained using the source dataset. Next, these pre-trained DNNs are re-trained by fine-tuning on the target dataset, and the ensemble of DNNs is established by assigning different weights to each pre-trained DNN. In the second part, the on-line learning system is developed for adaptive updating of the ensemble of DNNs. To evaluate the uncertainty error of the predicted values of DNN and determine the location of the updated HF sample point, the query-by-committee strategy based on the ensemble of DNNs is developed. The Covariance Matrix Adaptation Evolutionary Strategies is employed as the optimizer to find out the location where the maximal disagreement is achieved by the ensemble of DNNs. The design space is partitioned by the Voronoi diagram method, and then the selected point is moved to its nearest Voronoi cell boundary to avoid clustering between the updated point and the existing sample points. Three different types of test problems and an engineering example are adopted to illustrate the effectiveness of the OTL-MFDF method. Results verify the outstanding efficiency, global prediction accuracy and applicability of the OTL-MFDF method.