Intelligent Diagnosis Method Research Articles

Network lightweight method based on knowledge distillation is applied to RV reducer fault diagnosis

As a core component of industrial robots, the RV reducer directly affects the normal operation of the robot, so it is of great significance to monitor its status and diagnose faults. In the field of fault diagnosis, intelligent diagnosis methods based on deep learning have shown great advantages in accuracy and efficiency. However, as the network depth and scale increase, the exponentially growing model computation and parameter amounts require higher hardware requirements for computers, making it difficult to deploy on embedded platforms with limited computing resources. This makes it difficult for deep learning-based fault diagnosis methods to be applied in practical industrial settings that emphasize real-time performance, portability, and accuracy. This paper proposes a network lightweight method based on knowledge distillation (KD). Using the two-dimensional time–frequency map of vibration signals as the model input, the improved MobileNet-V3 network is used as the teacher network, and the simplified convolutional neural network is used as the student network (SN). The method of KD is applied to condense the knowledge and transfer it to the SN. The proposed method is validated using an RV reducer fault simulation experiment platform, and the results show that the proposed method reduces computation and parameter amounts by about 170 times at an accuracy rate of 94.37%, and run time is shortened by nearly one-third, and a generalization verification was conducted using the rotating mechanical fault simulation experiment platform. The models were also deployed on embedded devices to verify that the method proposed in this paper effectively reduces the deep learning network model’s demand for hardware resources of the operating environment. This provides an effective reference for deploying and implementing deep learning-based fault diagnosis on embedded systems with lower hardware configurations.

Review of research on intelligent diagnosis of oil transfer pump malfunction

Oil transfer pump is the key dynamic equipment in the process of oil and gas gathering and transportation, and its working reliability directly affects the safety of oil and gas storage and transportation. Intelligent diagnosis is a key technical method to reduce failure rate of oil transfer pump, ensure the safety of gathering and transportation process, and avoid major safety accidents caused by oil transfer pump failure. Various oil transfer pumps have been emerged in recent decades, and the common fault types and characteristics of oil transfer pump have been brought out in the review. This article highlights on the research of the fault signal and processing methods of oil transfer pump. Firstly, the fault signal of the oil transfer pump is discussed and the advantages and disadvantages of different signal extraction are analyzed. Secondly, the intelligent diagnosis method of oil transfer pump and the shortcomings of the existing methods are pointed out. Finally, the conclusions are given and the future development perspectives of oil transfer pumps are suggested. The main contribution of this review is to give a syn-thetic understanding on oil transfer pumps.

A transfer learning strategy based on numerical simulation driving 1D Cycle-GAN for bearing fault diagnosis

Most transfer learning (TL) models generally need the fault data from similar scenarios to achieve cross-domain bearing fault diagnosis. However, due to the bearings are mostly in normal state and the fault experiment cost is high, it is hard to collect the complete fault data in any real scenario. Thus, the problem of no fault data still limits the application of various intelligent diagnosis methods, including TL methods. To solve this problem, this paper proposed a novel transfer learning (TL) strategy by driving the one-dimensional (1D) cycle-consistent generative adversarial network (Cycle-GAN) with numerical simulation. In this strategy, the bearing dynamic model is constructed to generate the simulated vibration signals under normal and fault states. Furthermore, a 1D Cycle-GAN is first devised as the TL model for signal-to-signal translation. By using all simulated signals (normal and fault) and real normal signals, this 1D Cycle-GAN is trained to translate each simulated signal into a nearly real signal. Two experiments indicate that this strategy can generate satisfactory fault signals to solve the problem of no fault data in bearing fault diagnosis.

Application of Deep Neural Network in Gearbox Compound Fault Diagnosis

Gearbox fault diagnosis is vital to ensure the efficient operation of rotating machinery, and most gearbox faults in industrial production occur in the form of compound faults. To realize the diagnosis of compound faults in gearboxes at different speeds, an “end-to-end” intelligent diagnosis method based on an efficient channel attention capsule network (ECA-CN) is proposed. First, the process uses a deep convolutional neural network to extract fault features from the collected raw vibration signals, embeds the efficient channel attention module to filter important fault features, uses the capsule network to vectorize the feature space information and, finally, calculates the correlation between different levels of capsules using a dynamic routing algorithm to achieve accurate gearbox compound fault diagnosis. The effectiveness of the proposed ECA-CN fault diagnosis method is verified using the composite fault dataset of the 2009 PHM Challenge gearbox, with an average accuracy of 99.63 ± 0.22%. In the comparison experiments using the traditional fault diagnosis method, the average accuracy of the ECA-CN method improved by 4.62%, and the standard deviation was reduced by 0.58%. The experimental results show that the ECA-CN has a more competitive diagnostic performance than traditional shallow machine learning models and CNNs.

Convolutional Neural Network-Based Transformer Fault Diagnosis Using Vibration Signals.

Fast and accurate fault diagnosis is crucial to transformer safety and cost-effectiveness. Recently, vibration analysis for transformer fault diagnosis is attracting increasing attention due to its ease of implementation and low cost, while the complex operating environment and loads of transformers also pose challenges. This study proposed a novel deep-learning-enabled method for fault diagnosis of dry-type transformers using vibration signals. An experimental setup is designed to simulate different faults and collect the corresponding vibration signals. To find out the fault information hidden in the vibration signals, the continuous wavelet transform (CWT) is applied for feature extraction, which can convert vibration signals to red-green-blue (RGB) images with the time-frequency relationship. Then, an improved convolutional neural network (CNN) model is proposed to complete the image recognition task of transformer fault diagnosis. Finally, the proposed CNN model is trained and tested with the collected data, and its optimal structure and hyperparameters are determined. The results show that the proposed intelligent diagnosis method achieves an overall accuracy of 99.95%, which is superior to other compared machine learning methods.

Ensemble Multiple Distinct ResNet Networks With Channel-Attention Mechanism for Multisensor Fault Diagnosis of Hydraulic Systems

Hydraulic systems are widely used in modern industries, and the study of efficient and accurate fault diagnosis techniques for hydraulic systems can help prevent accidents and reduce economic losses. Most of the existing deep learning-based intelligent diagnosis methods use only single-channel signals for diagnosis, which may ignore some important fault information. In addition, the existing deep learning algorithms cannot distinguish the sensitivity of inter-channel features, and the important features of the channel domain cannot be emphasized. To solve the above problems, this paper proposes a multi-channel data-driven framework integrated distinct ResNet networks with channel-attention mechanism (CM-ResNet) for fault diagnosis of hydraulic systems. Firstly, the multi-channel signals are converted into 2-dimensional feature maps by continuous wavelet transform. Then, multiple CM-ResNet are trained as base-learners based on the signals of each channel. Third, the category probabilities of each base-learner are concatenated into new feature vectors. Finally, the new feature vectors are used to train the meta-learner and perform fault diagnosis. The meta-learner can capture the complex nonlinear relationships between the base-learners and obtain a stronger learner. Experimental results show that the performance of our proposed method outperforms the comparison method and the already existing methods.

LN-Net: Perfusion Pattern-Guided Deep Learning for Lymph Node Metastasis Diagnosis Based on Contrast-Enhanced Ultrasound Videos.

The blood flow in lymph nodes reflects important pathological features. However, most intelligent diagnosis based on contrast-enhanced ultrasound (CEUS) video focuses only on CEUS images, ignoring the process of extracting blood flow information. In the work described here, a parametric imaging method for describing blood perfusion pattern was proposed and a multimodal network (LN-Net) to predict lymph node metastasis was designed. First, the commercially available artificial intelligence object detection model YOLOv5 was improved to detect the lymph node region. Then the correlation and inflection point matching algorithms were combined to calculate the parameters of the perfusion pattern. Finally, the Inception-V3 architecture was used to extract the image features of each modality, with the blood perfusion pattern taken as the guiding factor in fusing the features with CEUS by sub-network weighting. The average precision of the improved YOLOv5s algorithm compared with baseline was improved by 5.8%. LN-Net predicted lymph node metastasis with 84.9% accuracy, 83.7% precision and 80.3% recall. Compared with the model without blood flow feature guidance, accuracy was improved by 2.6%. The intelligent diagnosis method has good clinical interpretability. A static parametric imaging map could describe a dynamic blood flow perfusion pattern, and as a guiding factor, it could improve the classification ability of the model with respect to lymph node metastasis.

An Edge Intelligent Method for Bearing Fault Diagnosis Based on a Parameter Transplantation Convolutional Neural Network

A bearing is a key component in rotating machinery. The prompt monitoring of a bearings’ condition is critical for the reduction of mechanical accidents. With the rapid development of artificial intelligence technology in recent years, machine learning-based intelligent fault diagnosis (IFD) methods have achieved remarkable success in the field of bearing condition monitoring. However, most algorithms are developed based on computer platforms that focus on analyzing offline, rather than real-time, signals. In this paper, an edge intelligence diagnosis method called S-AlexNet, which is based on a parameter transplantation convolutional neural network (CNN), is proposed. The method deploys the lightweight IFD method in a low-cost embedded system to monitor the bearing status in real time. Firstly, a lightweight IFD algorithm model is designed for embedded systems. The model is trained on a PC to obtain optimal parameters, such as the model’s weights and bias. Finally, the optimal parameters are transplanted into the embedded system model to identify the bearing status on the edge side. Two datasets were used to validate the performance of the proposed method. The validation using the CWRU dataset shows that the proposed method achieves an average prediction accuracy of 94.4% on the test set. The validation using self-built data shows that the proposed method can identify bearing operating status in embedded systems with an average prediction accuracy of 99.81%. The results indicate that the proposed method has the advantages of high recognition accuracy, low model complexity, low cost, and high portability, which allow for the simple and effective implementation of the edge IFD of bearings in embedded systems.

An Enhanced Convolutional Neural Network for Accurate Classification of Grape Leaf Diseases

Grape leaf diseases can significantly reduce grape yield and quality, making accurate and efficient identification of these diseases crucial for improving grape production. This study proposes a novel classification method for grape leaf disease images using an improved convolutional neural network. The Xception network serves as the base model, with the original ReLU activation function replaced by Mish to improve classification accuracy. An improved channel attention mechanism is integrated into the network, enabling it to automatically learn important information from each channel, and the fully connected layer is redesigned for optimal classification performance. Experimental results demonstrate that the proposed model (MS-Xception) achieves high accuracy with fewer parameters, achieving a recognition accuracy of 98.61% for grape leaf disease images. Compared to other state-of-the-art models such as ResNet50 and Swim-Transformer, the proposed model shows superior classification performance, providing an efficient method for intelligent diagnosis of grape leaf diseases. The proposed method significantly improves the accuracy and efficiency of grape leaf disease diagnosis and has potential for practical application in the field of grape production.

Intelligent fault diagnosis of planetary gearboxes under time-varying conditions based on dynamic adversarial balance adaptation with multi-label information confusion

Intelligent diagnosis methods based on big data have been extensively applied in the fault diagnosis of rotating equipment such as planetary gearboxes. Most of these methods usually satisfy the condition of independent identically distribution among the training and diagnosis data. However, the data distribution in the actual diagnosis task struggles to satisfy the above conditions due to the lack of fault data, missing label information and the feature differences within different signals, thus increasing the difficulty of cross-condition fault diagnosis in small sample sets. Therefore, we propose a dynamic adversarial balance adaptation method with multi-label information confusion (MLC-DABA) for diagnosing planetary gearbox faults under time-varying conditions. In the signal preprocessing process, we transform the nonstationary timing signals into two-dimensional time-frequency matrices for the feature learning of networks, which avoids the frequency characteristic mess caused by frequency overlap. Moreover, we adopt a balance adaptation algorithm to dynamically evaluate the feature distribution between source and target tasks through the domain labels and category labels, thus establishing a balanced adaptation relationship between the feature distributions of both tasks. This dynamic adversarial training mechanism can tap more domain-invariant feature information to measure the distribution distance among tasks, thus closing the feature differences in different tasks and increasing the generalization of source tasks to the data distribution in target tasks. The proposed method is verified in planetary gearbox experiments. Experimental analysis results indicate that the diagnostic performance of MLC-DABA outperforms other comparison methods in terms of accuracy and training robustness.

A novel intelligent bearing fault diagnosis method based on signal process and multi-kernel joint distribution adaptation

The present research on intelligent bearing fault diagnosis assumes that the same feature distribution is used to obtain training and testing data. However, the domain shift (distribution discrepancy) issue generally occurs in both datasets because of different operational conditions. The domain adaptation techniques are preferably applied for fault diagnosis to handle the domain shift issue. Moreover, collecting sufficient testing data or labelled data in real industries is a challenging task. Therefore, the multi-kernel joint distribution adaptation (MKJDA) with dynamic distribution alignment is proposed for bearing fault diagnosis. This method dynamically joins both the marginal and conditional distributions and uses the multi-kernel to solve the non-linear problems to extract the most effective and robust representation for cross-domain issues. Moreover, it runs with the unlabelled task domain to perform the diagnosis by iteratively updating the pseudo code. The experimental results (two public datasets and one experimental dataset) demonstrated that the proposed method (MKJDA) exhibited stable and robust accuracy while conducting bearing fault diagnosis. It can effectively address the most crucial issue: intelligent diagnosis methods must re-train the model when the distribution differs between the source domain (the model is learned) and the target domain (the learned model is applied).

An Online Diagnosis Method for Sensor Intermittent Fault Based on Data-Driven Model

The intermittent fault (IF) is usually overlooked in power electronic applications. In this letter, an intelligent diagnosis method based on a data-driven model is proposed for sensor IFs. First, the manifestation of IF in the time domain is discussed to explore its distinctive characteristics. Then, a signal predictor is constructed in a data-driven way by utilizing the nonlinear autoregressive exogenous structure with the extreme learning machine algorithm. In addition, the residual is generated online by comparing the output of the devised data-driven predictor and that of the real sensor. The fault diagnosis decision-making scheme is finally designed based on the residual evaluation to identify the sensor IF and permanent fault simultaneously. The feasibility and effectiveness of the proposed method are demonstrated by offline tests and real-time experimental tests.

Automatic vertebral fracture and three-column injury diagnosis with fracture visualization by a multi-scale attention-guided network.

Deep learning methods have the potential to improve the efficiency of diagnosis for vertebral fractures with computed tomography (CT) images. Most existing intelligent vertebral fracture diagnosis methods only provide dichotomized results at a patient level. However, a fine-grained and more nuanced outcome is clinically needed. This study proposed a novel network, a multi-scale attention-guided network (MAGNet), to diagnose vertebral fractures and three-column injuries with fracture visualization at a vertebra level. By imposing attention constraints through a disease attention map (DAM), a fusion of multi-scale spatial attention maps, the MAGNet can get task highly relevant features and localize fractures. A total of 989 vertebrae were studied here. After four-fold cross-validation, the area under the ROC curve (AUC) of our model for vertebral fracture dichotomized diagnosis and three-column injury diagnosis was 0.884 ± 0.015 and 0.920 ± 0.104, respectively. The overall performance of our model outperformed classical classification models, attention models, visual explanation methods, and attention-guided methods based on class activation mapping. Our work can promote the clinical application of deep learning to diagnose vertebral fractures and provide a way to visualize and improve the diagnosis results with attention constraints.

A Multi-Task-Based Deep Multi-Scale Information Fusion Method for Intelligent Diagnosis of Bearing Faults

The use of deep learning for fault diagnosis is already a common approach. However, integrating discriminative information of fault types and scales into deep learning models for rich multitask fault feature diagnosis still deserves attention. In this study, a deep multitask-based multiscale feature fusion network model (MEAT) is proposed to address the limitations and poor adaptability of traditional convolutional neural network models for complex jobs. The model performed multidimensional feature extraction through convolution at different scales to obtain different levels of fault information, used a hierarchical attention mechanism to weight the fusion of features to achieve an accuracy of 99.95% for the total task of fault six classification, and considered two subtasks in fault classification to discriminate fault size and fault type through multi-task mapping decomposition. Of these, the highest accuracy of fault size classification reached 100%. In addition, Precision, ReCall, and Sacore F1 all reached the index of 1, which achieved the accurate diagnosis of bearing faults.

A novel intelligent diagnosis method of rolling bearing and rotor composite faults based on vibration signal-to-image mapping and CNN-SVM

The rolling bearing is a key element of rotating machine and its fault diagnosis is a research focus. When a single fault of a rolling bearing fails to be addressed in time, it will cause progressive composite faults between the bearing and other elements. In this paper, the different composite fault cases of bearing and rotor are considered. First, an information fusion-empirical mode decomposition-angle adaptive distribution of polar coordinates image method is proposed, which has an adaptive image expression ability for the tested vibration signal, and can provide high-quality vibration image samples for diagnosis model training. Second, an intelligent diagnosis model combining a convolutional neural network and a support vector machine is proposed, which has an excellent generalization ability to recognize the different composite faults. Third, the different composite faults between rolling bearing and rotor are fabricated, tested and then diagnosed. The results show the test accuracy of the proposed method is higher than the conventional method and simple in the image mapping, which proves that this work is effective for the composite fault diagnosis of a rolling bearing and rotor.

Intelligent Diagnosis Method of Data Center Precision Air Conditioning Fault Based on Knowledge Graph

This study first digitizes, rules and structures complex unstructured data such as massive historical operation and maintenance data and fault judgment experience of operation and maintenance engineering based on semi-automatic entity extraction method; annotate the association or indirect relationship between 63,724 types of faults among triads by means of decision trees. Bayesian algorithm is used to further explore the relationship between triples, the realizes knowledge fusion, knowledge reasoning and knowledge update, and completes knowledge graph construction; combines with fault intelligent diagnosis method, realizes fault prediction, fast discovery, locates fault, type and business impact reasoning, and provides solutions to assist decision making.

A new deep transfer learning method for intelligent bridge damage diagnosis based on muti-channel sub-domain adaptation

Deep learning has been successfully and widely used in the field of intelligent diagnosis to accurately identify damage. These successes are based on the assumption that the training and test data are independent and identically distributed. They ignore that there is a distribution discrepancy between training (source domain) and test data (target domain) obtained under different working environments, loads, or bridges. This distribution discrepancy leads to severe performance degradation of the diagnostic model. To address these problems, a novel intelligent diagnosis method is proposed for bridges, namely, the multi-channel subdomain adaptation based deep transfer learning network. In this network, a multi-scale-based parallel multi-channel feature extractor and a multi-kernel local maximum mean discrepancy-based multi-channel subdomain adaptation module are proposed to learn domain-invariant features. Data sets from three different bridges are used for transfer diagnosis experiments to verify the generality and superiority of the method. This study will further facilitate the intelligentisation of structural health monitoring systems in the field of bridges.

Intelligent personalized diagnosis modeling in advanced medical system for Parkinson's disease using voice signals.

Currently, machine learning methods have been utilized to realize the early detection of Parkinson's disease (PD) by using voice signals. Because the vocal system of each person is unique, and the same person's pronunciation can be different at different times, the training samples used in machine learning become very different from the speech signal of the patient to be diagnosed, frequently resulting in poor diagnostic performance. On this account, this paper presents a new intelligent personalized diagnosis method (PDM) for Parkinson's disease. The method was designed to begin with constructing new training data by assigning the best classifier to each training sample composed of features from the speech signals of patients. Subsequently, a meta-classifier was trained on the new training data. Finally, for the signal of each test patient, the method used the meta-classifier to select the most appropriate classifier, followed by adopting the selected classifier to classify the signal so that the more accurate diagnosis result of the test patient can be obtained. The novelty of the proposed method is that the proposed method uses different classifiers to perform the diagnosis of PD for diversified patients, whereas the current method uses the same classifier to diagnose all patients to be tested. Results of a large number of experiments show that PDM not only improves the performance but also exceeds the existing methods in speed.

Relational Conduction Graph Network for Intelligent Fault Diagnosis of Rotating Machines Under Small Fault Samples

Fault samples obtained in real-world environment are limited, which makes it hard to diagnose faults of rotating machines (RM) accurately by using the existing intelligent diagnosis methods. To solve the issue above, a new relational conduction graph network (RCGN) is proposed in this paper, which is trained on dataset produced in lab environment to identify fault types of the RM operated in real-world environments. First, feature extractor is constructed to mine fault features from input sample. Second, relational graph network is designed to treat each sample pair as a relational node, and then propagate and aggregate the similarities and relations between samples, so as to mine more discriminative relational characteristics from sample pairs. Moreover, a similarity function is introduced to assess whether the consisting samples in relational node are from the same class to determine fault types. Finally, extensive experiments on two datasets produced in real-world environments are used to validate the superior performance of the RCGN method. The results show that the RCGN method can correctly diagnose fault types of several RM operated in real-world environments, even when each fault type of these RM has only one sample. The diagnostic performance has been greatly improved as compared to state-of-the-art methods.

Dm-GAN: Distributed multi-latent code inversion enhanced GAN for fast and accurate breast X-ray image automatic generation.

Breast cancer seriously threatens women's physical and mental health. Mammography is one of the most effective methods for breast cancer diagnosis via artificial intelligence algorithms to identify diverse breast masses. The popular intelligent diagnosis methods require a large amount of breast images for training. However, collecting and labeling many breast images manually is extremely time consuming and inefficient. In this paper, we propose a distributed multi-latent code inversion enhanced Generative Adversarial Network (dm-GAN) for fast, accurate and automatic breast image generation. The proposed dm-GAN takes advantage of the generator and discriminator of the GAN framework to achieve automatic image generation. The new generator in dm-GAN adopts a multi-latent code inverse mapping method to simplify the data fitting process of GAN generation and improve the accuracy of image generation, while a multi-discriminator structure is used to enhance the discrimination accuracy. The experimental results show that the proposed dm-GAN can automatically generate breast images with higher accuracy, up to a higher 1.84 dB Peak Signal-to-Noise Ratio (PSNR) and lower 5.61% Fréchet Inception Distance (FID), as well as 1.38x faster generation than the state-of-the-art.