Development of damage detection parameters over the lifetime of a rolling element bearing

This paper presents the trends of damage detection parameters over the lifetime of a rolling element bearing. In the experimental part, a series of bearing tests was performed using the twin-disc test device, until the monitored bearing was severely worn. This was followed by the analysis of measured acceleration and acoustic emission data in a constant-load condition, but also as loaded with impact-type loading. The results showed that traditionally used parameters, such as kurtosis and RMS, can indicate whether the bearing is damaged or not in a non-impact load condition. However, especially under impact-loading, the parameters based on acoustic emission data showed good performance and enabled monitoring of progress of the bearing damage.

Weak feature extraction of rolling element bearing based on self-adaptive blind de-convolution and enhanced envelope spectral

As the most commonly used support component in engineering, rolling element bearing is also the most prone-to-failure part. The vibration signal of faulty bearing will take on repetitive impact and modulation characteristics, and the two features are often difficult to be extracted by conventional fault feature extraction methods such as envelope spectral. The main reasons are due to the influence of strong background noise, the signal attenuation of the acquisition path, and the early weak failure characteristics. To solve the above problem, a weak fault feature extraction method of rolling element bearing by combing improved minimum entropy de-convolution with enhanced envelope spectral is proposed in the paper. The enhancement effect of improved minimum entropy de-convolution on impact features and the satisfactory extraction effect of EES on repetitive impact and modulation features are utilized comprehensively by the proposed method. Firstly, improved minimum entropy de-convolution is used to filter the vibration signal of faulty bearing to enhance the impact characteristics, and the influence of signal acquisition path on the attenuation of the signal characteristics is also weakened at the same time. Then, enhanced envelope spectral is performed on the filtered signal, and the repetitive impact and modulation characteristics of vibration signal are extracted synchronously. In order to solve the shortcomings of the current commonly used de-convolution methods, an improved minimum entropy de-convolution method based on D-norm is proposed, which can solve the interference caused by random impulsive signals effectively. In addition, compared with the conventional method such as envelope spectral, the enhanced envelope spectral method could extract the repetitive impact and modulation characteristics of the faulty signal simultaneously much more effectively. Effectiveness and superiority of the proposed method are verified through simulation, experiment, and engineering application.

A new fault diagnosis model of rolling element bearing based on a recurrent neural network

The rolling element bearing is an important part of mechanical equipment, it has various kinds of malfunctions, the location of the fault may occur in the inner ring, outer ring, or rolling element of the bearing. Therefore, traditional methods of classification are difficult to classify and identify effectively. To improve the accuracy of bearing fault diagnosis, the deep learning method is used to diagnose the fault of the rolling element bearing. In this paper, the long short-term memory and gated recurrent unit are combined to build a bearing fault diagnosis model. On the other hand, this paper adjusts the hidden layer structure and optimizes the network parameters to establish a better long short-term memory–gated recurrent unit–long short-term memory diagnostic model and classify the fault types of bearings with Softmax. The model proposed in this paper can effectively diagnose the bearing fault under the bearing data set of Case Western Reserve University and the University of Cincinnati. Compared with the traditional long short-term memory and the gated recurrent unit, the model proposed in this paper has high accuracy in fault diagnosis as well as certain reliability and generalization ability.

Experimental Study of the Effect of Misalignment on Rolling Element Bearing

Any single machine rotary component in the process could result in downtime costs. It is necessary to monitor the overall machine health while it is in use. Bearing failure is one of the primary causes of machine breakdown in industry at high and low speeds. A vibration signature evaluation has historically determined misalignments in shafting systems. These misalignments are also responsible for the bearing increase in temperature. The purpose of this work is to undertake a comparative study to obtain the reliability of the effect of the amount of misalignment on bearing by using thermography measurement. An experimental study was performed in this paper to indicate the existence of machine misalignment at an early stage by measuring the bearing temperature using a thermal imaging camera. The effects of load, velocity, and misalignment on the bearings and their temperature increase have been investigated. The test bench's rolling-element bearing is an NTN UCP213-208 pillow block bearing. It has been observed that by tracking the change of temperature in bearings could lead to misalignment detection and the effect of the amount of misalignment on it.

Rolling Element Bearing Fault Time Series Prediction Using Optimized MCKD-LSTM Model

This paper realizes early bearing fault warning through bearing fault time series prediction, and proposes a bearing fault time series prediction model based on optimized maximum correlation kurtosis deconvolution (MCKD) and long short-term memory (LSTM) recurrent neural network to ensure bearings operation reliability. The model is based on lifecycle vibration signal of the bearing, to begin, the cuckoo search (CS) is utilized to optimize the parameter filter length L and deconvolution period T of MCKD, taking into account the influence and periodicity of the bearing time series, the fault impact component of the optimized MCKD deconvolution time series is improved. Then select the LSTM learning rate α depending on deconvolution time series. Finally, the dataset obtained through various preprocessing approaches are used to train and predict the LSTM model. The average prediction accuracy of the optimized MCKD-LSTM model is 26 percent higher than that of the original time series, proving the efficiency of this method, and the prediction results track the real fault data well, according to the XI'AN JIAOTONG University XJTU-SY bearing dataset.

An approach to investigating rolling element bearing damage under impact loading

This paper presents an approach to studying rolling element bearing damage under the interference of impact loading. In the experimental part, a series of bearing tests was performed by using the twin-disc test device with artificially damaged bearings. This was followed by analysis of the measured acceleration response data in impact-free condition as well as under the influence of the impact loading. The results showed successful detection of the bearing outer race damage by using typical bearing damage detection approaches regardless whether the impact loading was applied to the system or not. In turn, recognition of the bearing rolling element damage required specific signal processing.