Inter-shaft Bearing Fault Diagnosis Based on Aero-engine System: A Benchmarking Dataset Study

Abstract

In this paper, the aero-engine test with inter-shaft bearing fault is carried out, and a dataset is proposed for the first time based on the vibration signal of rotors and casings. First, a test rig based on a real aero-engine is established, driven by motors and equipped with a lubricating system. Then, the aero-engine is disassembled and assembled following the specification process, and the inter-shaft bearing with artificial fault is replaced. Next, the aero-engine test is conducted at 28 groups of high and low pressure speeds. Six measuring points are arranged, including two displacement sensors to test the displacement vibration signals of the low pressure rotor and four acceleration sensors to test the acceleration vibration signals of the casing. The test results are integrated into an inter-shaft bearing fault dataset. Finally, based on the dataset in this paper, frequency spectrum, envelope spectrum, CNN, LSTM and TST are used for fault diagnosis, and the results are compared with those of CWRU and XJTU datasets. The results show that the characteristic fault frequency cannot be found directly in the spectrum and envelope spectrum corresponding to this paper's dataset but in CWRU and XJTU datasets. Using CNN, LSTM and TST for fault diagnosis of the dataset in this paper, the accuracy is 83.13%, 85.41% and 71.07%, respectively, much lower than the diagnosis results of CWRU and XJTU datasets. It can be seen that the dataset in this paper is closer to the actual fault diagnosis situation and is a more challenging dataset. This dataset provides a new benchmark for the validation of fault diagnosis methods. Mendeley data: https://github.com/HouLeiHIT/HIT-dataset.

A hybrid fault diagnosis method for rolling bearings based on GGRU-1DCNN with AdaBN algorithm under multiple load conditions

“…In the paper, two distinct bearing datasets, namely the XJTU-SY dataset [58] and the intershaft bearing failure dataset derived from an aero-engine system [59], in order to assess the universal applicability of the proposed model.…”

An Adaptive Multi-D-Norm-Driven Sparse Unfolding Deconvolutional Network for Bearing Fault Diagnosis

“…To further validate the feasibility of the proposed AMD-SUDN in the application of aero-engine bearing fault diagnosis, aero-engine inter-shaft bearing fault signals were analyzed. The aero-engine inter-shaft bearing fault signals were obtained from the Harbin Institute of Technology (HIT) [ 49 ], and in this subsection, a set of outer-ring fault signals are used to validate the proposed network, in which the low-pressure rotor rotates at a frequency of 50 Hz and the high-pressure rotor rotates at a frequency of 80 Hz, which is calculated to have an FCF of 195 Hz. A total of 12,500 data points are used as the raw signals to test the proposed method.…”

A Neural Network Weights Initialization Approach for Diagnosing Real Aircraft Engine Inter-Shaft Bearing Faults

“…Accordingly, this work is well-thought-out less generalized considering analysis criteria proposed in this section. In [8], an interesting work was carried out on a realistic test-bench aircraft engine. Adaptive learning features of LSTM network are involved in the case.…”

“…None of the discussed works consider realistic da stead, a test-bench is always used to generate these results cannot be projected in real-world circumsta 2. Only the works introduced in [6,8] consider the da in data change research is created by biasing pred seen data samples. 3.…”

“…1. In an attempt to reach more realistic c investigating new unseen samples, a used in this case [8]. This enables obt ones obtained from non-realistic test exploring a further challenging featur 2.…”