APHformerNET: A Gear Fault Diagnosis Model Based on Adaptive Prototype Hashing Optimisation Algorithm

Gear transmission system fault diagnosis is crucial for the reliability and safety of industrial machinery. The combination of mathematical signal processing methods with deep learning technology has become a research hotspot in fault diagnosis. Firstly, the development and status of gear transmission system fault diagnosis are outlined in detail. Secondly, the relevant research results on gear transmission system fault diagnosis are summarized from the perspectives of time-domain, frequency domain, and time-frequency-domain analysis. Thirdly, the relevant research progress in shallow learning and deep learning in the field of fault diagnosis is explained. Finally, future research directions for gear transmission system fault diagnosis are summarized and anticipated in terms of the sparsity of signal analysis results, separation of adjacent feature components, extraction of weak signals, identification of composite faults, multi-factor combinations in fault diagnosis, and multi-source data fusion technology.

The planetary gearbox is a key transmission apparatus used to change speed and torque. The planetary gear is one of the most failure-prone components in a planetary gearbox. Due to the complexity of working environments, collected vibration signals contain a lot of noise and interference; fault characteristic frequencies are usually submerged or even lost. Thus, feature extraction from the vibration signal is beneficial to subsequent fault diagnosis. As a fault identification approach that has been increasingly popular in the field of fault diagnosis, deep learning requires a large number of samples to train the model. Insufficient samples lead to low diagnostic accuracy for deep learning models. This paper proposes a novel fault diagnosis approach for planetary gears based on intrinsic feature extraction and deep transfer learning. The original vibration signals are decomposed into a series of band-limited intrinsic mode functions (BLIMFs) by variational mode decomposition. BLIMF with the most apparent fault characteristics is selected to generate two-dimensional time-frequency maps by continuous wavelet transform. The preprocessed time-frequency maps are adopted as the input of the pretrained VGG16 model. The bottom layers are frozen, and the top layers are fine-tuned to achieve fault diagnosis for planetary gears. Applications to planetary gear datasets verify the superiority of the proposed method.

Mechanical fault diagnosis is an important method to accurately identify the health condition of mechanical equipment and ensure its safe operation. With the advent of the era of ‘big data’, it is an inevitable trend to choose deep learning for mechanical fault diagnosis. At the same time, to improve the generalization ability of deep learning applications in different scenarios of fault diagnosis, mechanical diagnosis based on transfer learning has also been proposed and become an important branch in the field of mechanical fault diagnosis. This paper introduces the principle of transfer learning, summarizes the research and application of transfer learning in the field of fault diagnosis, discusses the shortcomings of transfer learning in the field of fault diagnosis, and discusses the future research direction of transfer learning in the field of fault diagnosis.

New procedure for gear fault detection and diagnosis using instantaneous angular speed

In modern industrial production, rotating machinery plays an important role. The gears in this machinery adjust the speed and transmission of torque. Therefore, when the gear fails, it is very important to be able to diagnose the fault quickly and accurately. Gear vibration signals are often used in gear fault diagnosis, but the fault signal is often overwhelmed by noises. To enable the scientific and efficient detection of faults, this study proposes a gear fault diagnosis method based on variational modal decomposition (VMD) and wide+narrow visual field neural networks (WNVNNs), namely VMD-WNVNN. VMD-WNVNN consists of two stages. In the feature extraction stage, VMD and Pearson correlation coefficients are used to decompose and reconstruct the original data to obtain the features of these data in the frequency domain. In the classification stage, WNVNN is used to classify the data based on features. The final results of the gear fault diagnosis experiments show that this method not only has higher classification accuracy but also has higher classification stability than other recently proposed methods. Note to Practitioners—The gearbox is composed of many mechanical parts, such as gears, shafts, and bearings. Therefore, the vibration signal collected by the vibration sensor on the gearbox housing will contain the vibration signal of each part and the noise caused by processing errors. Therefore, if some methods can be used to efficiently extract the characteristic signals required for diagnosis in the data processing stage, the efficiency of fault diagnosis will be greatly improved. This article takes the health of gears as the research object and proposes a method that combines adaptive signal decomposition and deep learning technology. Experimental results show that this method has higher classification accuracy and classification stability than other methods proposed recently.

Deep learning technology is increasingly used in the field of power system fault detection and diagnosis, and its powerful feature learning capability makes it play an important role in intelligent process control. In this paper, we propose a method for high resistance fault detection in power systems and design a CNN-Attention-LSTM fault diagnosis model using various deep learning models such as convolutional neural network. The model training and simulation experiments are carried out on the collected power fault dataset. The accuracy, reliability and security of the proposed power fault detection method for high resistance fault phase identification are 99.5%, 99.8% and 99.2%, respectively. The model can accurately classify cable faults in cable fault diagnosis, and also has better diagnostic effect on transformer faults in the power system, in which the diagnostic accuracy of harmonic faults is as high as 100%, showing better fault classification and diagnosis performance.

In gearbox gear fault diagnosis based on motor current signals, the gear fault characteristic frequency component is often overshadowed by the fundamental frequency component of the current. In addition, the complex working conditions during actual production and use make it difficult to collect gear operation monitoring data containing labeled feature information. To address the above problems, a semi-supervised learning method based on reactive power signals is proposed for gear fault diagnosis of gearboxes. First, the method utilizes the Hilbert transform to process the current signal of the drive motor in the mechanical system, from which the reactive power is constructed. Then, the reactive power signal is analyzed by spectral analysis as a basis for gear fault diagnosis. Subsequently, the GAF-CNN-MTDL(Gramian angular field—convolutional neural network-mean teacher deep learning) fault diagnosis model is proposed to convert the reactive power signal into a two-dimensional image by using the GAF, and the semi-supervised training method of the average teacher is applied to input the fault dataset into the gear fault diagnosis model which is based on the CNN as the main backbone after the fault dataset has been divided into the labeled and the unlabeled dataset in accordance with a certain ratio. Finally, the gear fault dataset is used for method validation. The experimental outcomes demonstrate the method’s proficiency in effectively emphasizing the fault feature information pertaining to the gear part, and the introduced GAF-CNN-MTDL fault diagnosis model enables the utilization of a minimal number of labeled samples to achieve highly accurate gear fault diagnosis.

Gears are the most common parts of a mechanical transmission system. Gear wearing faults could cause the transmission system to crash and give rise to the economic loss. It is always a challenging problem to diagnose the gear wearing condition directly through the raw signal of vibration. In this paper, a novel method named augmented deep sparse autoencoder (ADSAE) is proposed. The method can be used to diagnose the gear wearing fault with relatively few raw vibration signal data. This method is mainly based on the theory of wearing fault diagnosis, through creatively combining with both data augmentation ideology and the deep sparse autoencoder algorithm for the fault diagnosis of gear wear. The effectiveness of the proposed method is verified by experiments of six types of gear wearing conditions. The results show that the ADSAE method can effectively increase the network generalization ability and robustness with very high accuracy. This method can effectively diagnose different gear wearing conditions and show the obvious trend according to the severity of gear wear faults. This paper provides an important insight into the field of gear fault diagnosis based on deep learning and has a potential practical application value.

Semi-supervised gear fault diagnosis using raw vibration signal based on deep learning

Deep learning technology, with its exceptional nonlinear feature extraction capability, has been gradually accepted and widely adopted by the industry. This paper reviews the fault diagnosis techniques utilizing deep learning, emphasizing an in-depth analysis of two main deep learning models that are extensively applied in the current fault diagnosis domain: Autoencoder (AE) and Convolutional Neural Network(CNN). In addition, we also discuss the specific application cases of both algorithms, and introduce their specific principles of implementation. Through these in-depth analysis, it is intended to provide readers with the application overview and technical progress of deep learning technology in the field of fault diagnosis, so as to offer reference and enlightenment for related research.

Unknown environmental noise and varying operation conditions negatively affect gear fault diagnosis (GFD) performance. In this paper, the sample/feature hybrid transfer learning (TL) strategies are adopted for GFD under varying working conditions, where source working conditions are considered to help the learning of target working conditions. Here, a multiple domains-feature vector is extracted where certain insensitive features offset the adverse effects of varying working conditions on sensitive features, including time domain, frequency domain, noise domain, and torque domain. Before TL, the signed-rank and chi-square test-based similarity estimation frame is adopted to select source data sets, aiming to reduce the possibility of negative transfer. Then, the hybrid transfer model, including the fast TrAdaBoost and partial model-based transfer (PMT) algorithm, is carried out, whose weights are allocated in sample and feature, respectively. Related experiments were conducted on the drivetrain dynamics simulator, which proves that feature transfer is more suitable for low-quality source domains while sample transfer is more suitable for high-quality source domains. Compared with non-transfer strategy, transfer learning is a useful tool to solve a practical GFD problem when facing with multiple working conditions, thus enhancing the universality and application value in fault diagnosis field.

Deep learning can be applied in the field of fault diagnosis without an accurate mechanism model. However, the accurate diagnosis of minor faults using deep learning is limited by the training sample size. In the case that only a small number of noise-polluted samples is available, it is crucial to design a new learning mechanism for the training of deep neural networks to make it more powerful in feature representation. The new learning mechanism for deep neural networks model is accomplished by designing a new loss function such that accurate feature representation driven by consistency of trend features and accurate fault classification driven by consistency of fault direction both can be secured. In such a way, a more robust and more reliable fault diagnosis model using deep neural networks can be established to effectively discriminate those faults with equal or similar membership values of fault classifiers, which is unavailable for traditional methods. Validation for gearbox fault diagnosis shows that 100 training samples polluted with strong noise are adequate for the proposed method to successfully train deep neural networks to achieve satisfactory fault diagnosis accuracy, while more than 1500 training samples are required for traditional methods to achieve comparative fault diagnosis accuracy.

Deep learning technology has made significant progress in fault diagnosis. However, in real-world industrial settings, most existing methods require substantial labeled data for training, while harsh operating conditions and data collection constraints often result in scarce fault samples. This limitation significantly impairs their diagnostic performance in practical applications. To address this challenge, we propose a few-shot fault diagnosis approach based on a time-frequency contrastive learning (TF-CL) framework. The TF-CL framework adopts a pre-training and downstream task pipeline, enabling the model to automatically learn and extract multi-perspective features from unlabeled data in self-supervised conditions. During the pre-training, dedicated encoders separately extract time-domain and frequency-domain feature representations from abundant unlabeled samples. The extracted features are then projected into a shared time-frequency space using a projector. To ensure that multi-perspective features can be extracted from unlabeled data, this paper introduces a time-frequency consistency loss function, constructed using novel positive and negative sample pairs. In the downstream task, the TF-CL model is combined with a multilayer perceptron classifier and optimized fine-tuned end-to-end using the limited labeled data. Gradient updates during downstream training further refine the learned feature representations, enhancing their adaptability to target classification tasks. The superiority of TF-CL was demonstrated through a variety of fault diagnosis experiments conducted on both public and self-collected datasets.

Mechanical equipment is a vital foundational support for promoting national economic development and is widely utilized in key sectors such as aerospace, shipping, construction machinery, energy, petrochemicals, and robotics. With the advancement of artificial intelligence and industrial intelligence, industrial big data and its intelligent analysis provide robust support for fault prediction and health management of equipment. Building on existing research, intelligent diagnostics for mechanical equipment based on deep learning have gained significant attention and application. However, the success of big data relies on comprehensive fault data, which is challenging to obtain in practical applications where continuous equipment operation is essential. Moreover, mechanical equipment often operates under varying conditions, leading to different data distributions for training and testing. This discrepancy can result in low diagnostic accuracy or even failure of deep learning methods. Deep Transfer Learning (DTL) is an emerging machine learning paradigm that not only leverages the advantages of deep learning (DL) in feature representation but also harnesses the strengths of transfer learning (TL) in knowledge transfer. Consequently, DTL techniques can make deep learning-based fault diagnosis methods more reliable, robust, and applicable, leading to extensive development and research in the field of intelligent fault diagnosis. This paper primarily introduces adversarial-based deep transfer learning (ADTL) models, which are fundamentally based on Generative Adversarial Network (GAN). We provide a detailed discussion of the main applications of ADTL and its recent developments in intelligent fault diagnosis, along with some future challenges and prospects.

With the development of information theory and image analysis theory, the studies on fault diagnosis methods based on image processing have become a hot spot in the recent years in the field of fault diagnosis. The gearbox of wind turbine generator is a fault-prone subassembly. Its time frequency of vibration signals contains abundant status information, so this paper proposes a fault diagnosis method based on time-frequency image characteristic extraction and artificial immune algorithm. Firstly, obtain the time-frequency image using wavelet transform based on threshold denoising. Secondly, acquire time-frequency image characteristics by means of Hu invariant moment and correlation fusion gray-level co-occurrence matrix of characteristic value, thus, to extract the fault information of the gearing of wind turbine generator. Lastly, diagnose the fault type using the improved actual-value negative selection algorithm. The application of this method in the gear fault diagnosis on the test bed of wind turbine step-up gearbox proves that it is effective in the improvement of diagnosis accuracy.