In real engineering scenarios, it is difficult to collect adequate cases with faulty conditions to train an intelligent diagnosis system. To alleviate the problem of limited fault data, this paper proposes a fault diagnosis method combining a generative adversarial network (GAN) and stacked denoising auto-encoder (SDAE). The GAN approach augments the limited real measured data, especially in faulty conditions. The generated data are then transformed into the SDAE fault diagnosis model. The GAN-SDAE approach improves the accuracy of the fault diagnosis from the vibration signals, especially when the measured samples are few. The usefulness of this method is assessed through two condition-monitoring cases: one is a classic bearing example and the other is a more general gear failure. The results demonstrate that diagnosis accuracy for both cases is above 90% for various working conditions, and the GAN-SDAE system is stable.
9 July 2020 in Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science
Accurate fault prediction of rolling bearing can predict the operation condition in advance, which is an important means to ensure the safety and reliability of rotating machinery. Aimed at the data processing of rolling bearing vibration signal with multi-fault and long time series, an intelligent fault prediction model based on gate recurrent unit and hybrid autoencoder is proposed in this paper. Firstly, vibration signals of multi-faults are brought into multi-layer gate recurrent unit model for multi-step and multi-variable time series prediction. Secondly, variational autoencoder is used for data augmentation of fault samples. Thirdly, the augmented fault samples are brought into stacked denoising autoencoder for noise reduction and fault prediction. Finally, fault prediction results of rolling bearing can be achieved on the basis of gate recurrent unit and hybrid autoencoder of variational autoencoder and stacked denoising autoencoder. The bearing datasets of Case Western Reserve University are used to verify the effectiveness of the proposed method. Comparative experiment results show that the proposed fault prediction model has more accurate time series prediction result and higher fault prediction accuracy than other deep learning models. With 98.68% accuracy of fault prediction, the proposed fault prediction model can be taken as an effective tool for intelligent predictive maintenance of rolling bearing.
20 June 2019 in Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering
Evaluating the reliability of aeroengines with few or zero failures through the use of the Weibull distribution has become a key problem in aviation, as the difficulty of obtaining sufficient sample sizes of monitoring data limits the reliability of evaluations. This paper aims to solve this problem by using generative adversarial networks to generate aeroengine condition monitoring data and increase the volume of usable data. The experimental results show that after a large number of network training epochs, the generated data can reflect the regularity of empirical monitoring data. The relationship between monitoring parameters and Weibull distribution parameters is determined, the generated data are used to estimate Weibull parameters, and the Weibull distribution reliability function for aeroengines is established. The results indicate that the combined use of generative adversarial networks and the Weibull distribution reliability function can indeed solve the problem of limited data volume, and that this method can improve the accuracy of aeroengine reliability assessment. The effectiveness of the proposed method is verified by analyzing monitoring data and time on wing data of 30 aeroengines, calculating engine reliability, and comparing the results with those yielded from the generated data.
29 April 2021 in Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering
Accurate performance degradation prediction of aeroengines can ensure the safety and reliability of the aircraft. Based on the mass long time series data of multiple state parameters, a novel performance degradation prediction method based on attention model (AM) and support vector regression (SVR) is proposed in this article. The AM uses the attention mechanism between encoder and decoder to realize weight distribution of different source samples, so as to realize time series prediction of state parameters. The SVR model is used to mine the mapping relationship between multiple state parameters and performance degradation. The performance degradation prediction results can be achieved by putting the time series prediction results of multiple state parameters into the SVR model. The turbofan engine degradation simulation dataset carried out using commercial modular aero-propulsion system simulation (C-MAPSS) is used to verify the effectiveness of the proposed method. The results demonstrate that it can get accurate time series prediction and performance degradation analysis results. Compared with other methods, the proposed attention model and support vector regression (AM-SVR) model has lower prediction error and higher stability when dealing with noised samples.
25 June 2024 in Information Technology And Control
More than 220 enterprises in China's real estate industry have gone bankrupt, causing serious losses. The National Bureau of Statistics of China showed that the country's investment in property development fell by 8.5% year-on-year, while domestic lending dropped by 11.5% and the use of foreign capital fell by 43%. Upon this, the development of supply chain finance can alleviate the pressure on enterprise funds and stabilize the real estate market. However, risk in supply chain finance is the biggest obstacle to the development of supply chain finance and current researches on risk assessment of supply chain finance face problems such as imprecise classification, slow assessment speed, a small number of samples, and data that is easily tampered with. Therefore, this study integrated graph convolutional neural networks into the smart contracts of the contract layer of blockchain. This integration established a novel intelligent perception model for supply chain finance risk. Based on a consortium chain with the government and enterprises as nodes, the model was established, including risk monitoring, assessment, and categorized early warnings. In the risk assessment part, we compared the graph convolutional neural network with multilayer perceptron and support vector machine finding that the accuracy rate of the graphic convolutional neural network is 94%, which is higher than the above models. The intelligent risk-perception model proposed in this paper operates faster than expert judgment assessments used by banks. It also provides accurate risk levels and quantifies the probability of enterprises being classified as high-risk, offering technical support to regulatory authorities in controlling supply chain financial risk.
14 October 2025 in International Journal of Information Security