Multisource Deep Adversarial Decoupled Autoencoder Network for State Recognition of High-Speed Train Brake Pads

With the rapid development of smart grid technology, a large amount of multi-source heterogeneous data has been generated in the power system, and its effective utilization is crucial for the optimization operation, demand prediction, and anomaly detection of the power system. However, the fusion processing of multi-source heterogeneous data faces many challenges, such as inconsistent data format, granularity, and quality, and direct fusion can easily lead to information redundancy and contradictions. A multi-source heterogeneous data fusion technology based on big data mining has been proposed to address the above issues. This method combines the advantages of convolutional neural networks and gated recurrent units to automatically extract features from image and sequence data and handle long-term dependency issues in time series data. Meanwhile, the K-means clustering algorithm is used to preprocess the data and train a specialized ConvGRU model. The results showed that in short-term load forecasting and abnormal electricity consumption behaviour detection tasks, the accuracy of this method reached 96.3% and 98.7%, respectively, with AUC values of 0.994 and 0.996. Compared to models that use only CNN or GRU, the performance is significantly improved. This method effectively solves the problem of integrating and processing multi-source heterogeneous power data, improves the accuracy and efficiency of power system data analysis, and provides strong support for the optimized operation of smart grids.

As the complexity of intelligent public transportation systems continues to increase and the degree of interconnection of equipment at all levels gradually deepens, building a digital twin system will generate a large amount of multi-source heterogeneous data. Effective processing and in-depth mining of data can provide real-time and intelligent decision-making optimization for the construction of digital twin systems, thereby efficiently handling complex emergencies. This paper conducts a systematic review on the processing methods and technologies of multi-source heterogeneous twin data in traffic dynamic scenarios. First, the content and classification of multi-source heterogeneous twin data in the operation process of intelligent bus systems are clarified; secondly, the multi-source The data processing methods and technologies applied in each stage of data collection, data storage, data fusion and data analysis in heterogeneous twin data processing are analyzed, and the advantages, disadvantages and applications of various methods and technologies are analyzed; finally, corresponding to the multiple This paper summarizes the methods and technologies for processing multi-source heterogeneous twin data, and points out the challenges and development trends faced by the current multi-source heterogeneous twin data processing methods and technologies.

Bearing is a key component of rotating machinery, thus the accurate and efficient fault diagnosis of bearing is critical to the safety and reliability of rotating machinery systems. In recent years, the intelligent fault diagnosis technology of bearing represented by deep learning has made rapid development. However, the stability and generalization performance of the fault diagnosis model of bearing under complex environmental noise and variable working conditions is not good. Fortunately, self-supervised learning represented by contrastive learning can provide a good solution. The current research on contrastive learning mainly focuses on self-supervised contrastive learning, but the lack of supervised learning of fault label information leads to the reduction of diagnostic accuracy and robustness under variable working conditions. To solve this problem, this paper proposes a supervised contrastive learning combined with multi-scale attention mechanism for fault diagnosis of bearing under variable operating conditions. Firstly, the preprocessing of bearing time-domain vibration data is completed, including data set division, data augmentation, and construction of “positive” or “negative” pairs for comparative learning. Then, a supervised learning network integrating multi-scale attention mechanism is constructed to complete bearing fault feature extraction. Finally, the model transfer fault diagnosis is completed under complex noise and variable working conditions. The performance of the proposed method is evaluated through a large number of noise and variable-condition experiments. The results show that the proposed method has high fault classification accuracy and robustness under the influence of complex noise and variable working conditions.

The study of the prediction of stock market volatility is of great significance to rationally control financial market risks and increase excessive investment returns and has received extensive attention from academic and commercial circles. However, as a dynamic and complex system, the stock market is affected by multiple factors and has a comprehensive capability to include complex financial data. Given that the explanatory variables of influencing factors are diverse, heterogeneous and complex, the existing intelligent algorithms have great limitations for the analysis and processing of multi-source heterogeneous data in the stock market. Therefore, this study adopts the edge weight and information transmission mechanism suitable for subgraph data to complete node screening, the gate recurrent unit (GRU) and long short-term memory (LSTM) to aggregate subgraph nodes. The compiled data contain the metapaths of three types of index data, and the introduction of the association relationship attention dimension effectively mines the implicit meanings of multi-source heterogeneous data. The metapath attention mechanism is combined with a graph neural network to complete the classification of multi-source heterogeneous graph data, by which the prediction of stock market volatility is realized. The results show that the above method is feasible for the fusion of heterogeneous stock market data and the mining of implicit semantic information of association relations. The accuracy of the proposed method for the prediction of stock market volatility in this study is 16.64% higher than that of the dimensional reduction index and 14.48% higher than that of other methods for the fusion and prediction of heterogeneous data using the same model.

It is considerable to solve practical fault diagnosis task of gearbox under variable working conditions by introducing sufficient auxiliary data. For this purpose, a new approach called improved deep transfer auto-encoder is proposed for intelligent diagnosis of gearbox faults under variable working conditions with small training samples. First, multi-wavelet is employed as activation function for effectively learning useful features hidden in the non-stationary vibration data. Second, correntropy is used to modify the cost function to enhance the reconstruction quality. Third, pre-train an improved deep auto-encoder using sufficient auxiliary data in the source domain, and transfer its parameters to the target model. Finally, the improved deep transfer should be fine-tuned by small training samples in the target domain to adapt to the characteristics of the rest testing data. The proposed approach is used to analyze two sets of experimental vibration data collected from gearbox under variable working conditions. The results show that the proposed approach can accurately diagnose different faults of gearbox even the working conditions have significant changes, which is superior to the existing methods.

With the development of deep learning methods, the data-driven fault diagnosis methods have attracted a great deal of interest. However, as for the data-driven fault diagnosis methods, technology has to overcome various difficulties in the practical industrial scenarios, such as variable working conditions, insufficient effective samples, and environmental noise interference. Combining with the time–frequency analysis of vibration signals, a domain adaptation fault diagnosis model based on ResNet and Transformer (DAFDMRT) is proposed in this work, aiming to solve the problems encountered by current rotating machinery fault diagnosis methods in the field of application. Firstly, the vibration signal is processed by wavelet packet transform and the time–frequency information grayscale maps is constructed. Next, a deep fusion feature extraction network combining ResNet and Transformer encoder, is designed for the extraction and fusion of the local and global features of multi-scale time–frequency information. Finally, the multi-kernel maximum mean discrepancy is applied to measure and minimize the distribution difference between the deep features of source and target domain, thereby improving the diagnostic performance of the diagnosis model in variable working conditions. In this work, comparative experiments are conducted as for bearing and gearbox datasets under variable working conditions. The results indicate that DAFDMRT can show excellent performances in terms of fault diagnosis and generalization ability.

Line spectra chaotification is a principal method to weaken or eliminate the line spectra feature of submarines. However, this method is difficult to obtain chaos under the variable working conditions and small amplitudes. Furthermore, there are multistable attractors in the nonlinear vibration isolation system simultaneously. So, the quality of chaos highly depends on initial conditions and systematic parameters. In this study, the attractor entrainment control and line spectra chaotification of a nonlinear vibration isolation system on the flexible foundation have been studied by using the open-plus-nonlinear-closed-loop method. First, the dynamic equation of the nonlinear vibration isolation system on the flexible foundation was formulated, and its exhaustive bifurcation characteristics were analyzed. The regulations of global characteristics and coexistent attractors were found out. Second, the entrainments between the different attractors were carried out under the open-plus-nonlinear-closed-loop control, which can ensure the system always works in the lowest line spectra intensity and the best overall vibration isolation performance. Finally, an open-plus-nonlinear-closed-loop coupling method was used to achieve generalized chaotic synchronization between the driving system and the response system, which effectively obtained sustainable chaos even under variable working conditions and small amplitudes. Simulation results validate the feasibility and validity of the open-plus-nonlinear-closed-loop method, which achieves the dual goals of effective vibration isolation in the low frequency range and line spectra chaotification under variable working conditions.

A robust construction of normalized CNN for online intelligent condition monitoring of rolling bearings considering variable working conditions and sources

A deep learning approach to estimate the state of health of lithium-ion batteries under varied and incomplete working conditions

Open-circuit fault under different load and variable working conditions is the most severe issue that affects the robustness of fault diagnosis algorithms. Considering this, this research work proposes a high-frequency fault diagnosis approach that is capable to detect and isolate a single open-switch fault in a single-phase five-level Packed U-Cell (PUC5) inverter, not only under stable conditions but also under different load and variable working conditions. Firstly, a high frequency model of the PUC5 inverter is proposed. Then, the conducted emissions, measured across the electromagnetic interferences filter resistor, are employed as a fault signature. Finally, simulation results are considered to verify the effectiveness of the proposed fault diagnosis method.

Due to the coupling and diversity of compound fault features, it is difficult to decoupling diagnose the compound fault under small datasets and variable working conditions. To enhance the compound fault diagnosis performance, this work proposed a compound fault transfer diagnosis method that uses the multi-label transformer-based transfer learning network. Initially, the 1-D signal is converted into 2-D image using CWT as the input of the constructed deep learning network; Subsequently, a CNN-Transformer network structure is constructed, which simultaneously utilizes convolutional operation and self-attention mechanism to comprehensively capture the multi-scale fault features. In addition, multi-label classification is adopted to identify specific single fault types in the compound fault and output corresponding fault labels. Finally, a transfer learning strategy with fine-tuning mechanism is creatively integrated to achieve the compound fault transfer diagnosis, which can learn fault knowledge from single fault samples in source domain for compound fault diagnosis in required target tasks. The experimental datasets of planetary gearbox and harmonic reducer were collected in our own laboratory to validate the diagnostic performance. The results show that our proposed method achieved 98% average decoupling identification accuracy in insufficient compound fault samples on both datasets, and the accuracy fluctuation was less than 1.5% in the six transfer tasks. It is verified that the proposed method achieved excellent decoupling identification accuracy and generalization ability in small datasets and variable working conditions, which has significant advantage over the traditional local convolution-based multi-label classification methods and domain adaptation -based transfer learning methods.

With the growing importance of the fuzzy spatiotemporal data in information application, there is an increasing need for researching on the integration method of multi-source heterogeneous fuzzy spatiotemporal data. In this paper, we first propose a fuzzy spatiotemporal RDF graph model based on RDF (Resource Description Framework) that proposed by the World Wide Web Consortium (W3C) to represent data in triples (subject, predicate, object). Secondly, we analyze and classify the related heterogeneous problems of multi-source heterogeneous fuzzy spatiotemporal data, and use the fuzzy spatiotemporal RDF graph model to define the corresponding rules to solve these heterogeneous problems. In addition, based on the characteristics of RDF triples, we analyze the heterogeneous problem of multi-source heterogeneous fuzzy spatiotemporal data integration in RDF triples, and provide the integration methods FRDFG in this paper. Finally, we report our experiments results to validate our approach and show its significant superiority.

Aiming at the low cleaning rate of the traditional multi-source heterogeneous power grid big data cleaning model, a multi-source heterogeneous power grid big data cleaning model based on machine learning classification algorithm is designed. By capturing high-quality multi-source heterogeneous power grid big data, weight labeling of data source importance measurement, data attributes and tuples, and constructing Tan network based on the idea of machine learning classification algorithm, the data probability value is finally used to complete the classification and cleaning of inaccurate data. Experiments show that the model based on machine learning classification algorithm can effectively improve the imprecise data cleaning rate compared with the traditional model to solve multi-source heterogeneous imprecise data cleaning.

In order to fully utilize the features of multi-source heterogeneous data and effectively improve the accuracy and efficiency of fault diagnosis of rotating machinery, a multi-source heterogeneous data diagnosis method based on parameter collaborative optimization multi-scale convolutional autoencoder (MSCAE) is proposed. Firstly, multi-scale information learning is integrated into the convolutional autoencoder (CAE) to consider the temporal and spatial feature information of the diagnostic object simultaneously. To improve the training and diagnostic efficiency of MSCAE, a quantum particle swarm optimization (QPSO) module is used to perform hyperparameter optimization on it using chaos initialization and dynamic weight strategy (DWS). Besides, the sparse attention mechanism is introduced into the MSCAE model to improve the recognition rate of key fault features hidden in the original heterogeneous signals. Finally, the confusion matrix and visualization techniques are used to achieve fault classification. The experimental results demonstrate that after 100 experiments, the proposed method has an average diagnostic accuracy of 98.5 % and strong robustness to noise, providing a new method for rotating machinery fault diagnosis based on multi-source heterogeneous data.

As a missile flies at high speed, the index and surface shape of the conformal dome will vary under the influence of the aero-optical effect, which will degenerate the performance of the seeker’s imaging detection system. However, many previous studies on aero-optical imaging deterioration of optical domes were usually carried out under fixed operating conditions, which are not in line with the real flight scene of the missile. In addition, the aero-optical imaging degeneration of the dome is diverse as the flight time increases. Therefore, it is of great significance to study the time characteristics of aero-optical imaging degradation of optical domes under variable work conditions. In this study, taking an air-to-air missile as an example, the Zernike polynomials, wavefront aberration, Strehl ratio, and image simulation are applied to evaluate the aero-optical imaging deterioration of an ellipsoidal dome in the flight time range of 0–10 s under variable working conditions. The simulation results show that, as the flight time increases, (1) the dynamic range of tilt, defocus, astigmatism, coma, and wavefront aberration increase; and (2) the Strehl ratio and the peak signal-to-noise ratio (PSNR) of the simulated images decrease. Therefore, the influence of flight time on the aero-optical image degradation of the ellipsoidal dome gradually becomes more serious.