Practical Investigation on Bearing Fault Diagnosis Using Massive Vibration Data and Artificial Neural Network

Khoualdia, Tarek; Lakehal, Abdelaziz; Chelli, Zoubir

doi:10.1007/978-3-030-23672-4_9

Cited by 5 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The current methods of adding irregular data include adding data with a specified distribution or setting specific data in the input data to 0. Noisereducing self-encoders are more effective than training without adding irregular noisy data, and the application of such data makes the data more diverse [8]. This method is similar to the function that humans have their own associative repair for broken images after learning knowledge for dimensionality reduction preextraction, and subsequent models also apply such methods to improve the robustness and generalization of the model.…”

Section: 𝐽(𝑊 𝑏mentioning

confidence: 99%

DAE-LSTM neural network-based prediction model for segmental line loss rate of low-voltage power grid

Lin,

Zhang,

et al. 2023

Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023)

View full text Add to dashboard Cite

The traditional low-voltage grid segmental line loss rate prediction is more often chosen from the tidal method, but the operational limitations of the method lead to the low prediction accuracy of the method. In this regard, a low-voltage grid segmental loss rate prediction model based on the combination of DAE and LSTM neural network is proposed. Firstly, the DAE is used to encode the input content and extract the main features of the input content, and secondly, the encoded input content is put into the LSTM model for training to obtain the low-voltage segmental line loss rate prediction model. In the experiments, the prediction accuracy of the model is verified. The experimental analysis shows that the model has high prediction accuracy when the proposed model is used for LVR segmented line loss rate prediction.

show abstract

Section: 𝐽(𝑊 𝑏mentioning

confidence: 99%

DAE-LSTM neural network-based prediction model for segmental line loss rate of low-voltage power grid

Lin,

Zhang,

et al. 2023

Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023)

View full text Add to dashboard Cite

show abstract

“…Condition monitoring (CM) is a crucial element of condition-based maintenance (CBM), as it assumes a major role in the proactive maintenance of machine components, effectively anticipating and preventing failure. Several indications have been examined in order to facilitate defect diagnosis in dynamic machinery [29][30][31][32][33][34][35][36]. The three fundamental phases comprising the CBM program.…”

Section: 𝑃𝑒𝑎𝑘 = (𝑚𝑎𝑥(𝑦𝑘) − 𝑚𝑖𝑛(𝑦𝑘)) (1)mentioning

confidence: 99%

Enhancing Rotary Machine Reliability Through Condition-Based Maintenance Optimization

Haq,

Akmal

2023

PJOSR

View full text Add to dashboard Cite

Rotary machines possess an inherent characteristic of generating vibrations, leading to the deterioration of critical components, particularly bearings and gears, ultimately failing the system. Vibration analysis is widely acknowledged as the predominant diagnostic technique employed for assessing the state of machinery and informing maintenance strategies. Condition-based maintenance (CBM) is a crucial component of proactive maintenance strategies that optimize machine availability by implementing timely interventions and minimizing costly breakdowns. This research endeavour aims to establish a comprehensive framework that enables evaluating the operational state of rotary machinery and its critical components, specifically emphasizing bearings. The interdependence between maintenance and machine health is evident, as a well-maintained machine requires minimal maintenance, while a machine undergoing deterioration requires immediate intervention. Rotary machines, which hold significant importance in various industrial processes, often face significant obstacles to bearing issues. These challenges lead to considerable disruptions in output and escalate maintenance costs. The current study examines the efficacy of CBM as a potential solution to the aforementioned issues. CBM is a maintenance strategy that utilizes real-time data on machine conditions to make informed decisions regarding maintenance interventions. By leveraging this approach, maintenance activities can be executed at the most opportune time, maximizing efficiency and effectiveness. CBM is a strategic approach that empowers enterprises to proactively mitigate failures, optimize maintenance schedules, and improve overall operational efficiency by accurately estimating the remaining usable life of machine components. This research study contributes to the growing body of knowledge on CBM, offering valuable insights into predictive maintenance and its potential to enhance the reliability and efficiency of rotary machinery.

show abstract

“…Each part of the bearing has an own frequency that depends of its geometry and dimensions. The fault frequency of the bearing operating at a given rotor speed is the product of multipliers with the speed of rotating shaft [24].…”

Section: Vibration Based Monitoring Of Induction Motorsmentioning

confidence: 99%

Optimized multi layer perceptron artificial neural network based fault diagnosis of induction motor using vibration signals

Khoualdia¹,

Lakehal²,

Chelli³

et al. 2021

Diagnostyka

View full text Add to dashboard Cite

Installations and the detection of their faults has become a major challenge. In order to develop a reliable approach for monitoring and diagnosis faults of these components, a test rig was mounted. In this article, a Multi Layer Perceptron (MLP) Artificial Neural Network (ANN) has been structured and optimized for online monitoring of induction motors. The input layer of our ANN used eight indicators calculated from the collected time signals and which represent the different states of the motor (Healthy, broken rotor bars, bearing fault and Misalignment) and the output layer used a codified matrix. However, based on L27 Taguchi design, the architecture for the hidden layers of our network is chosen, with the use of the Levenberg-Marquardt learning algorithm. Garson's algorithm and connection weight approach showed that there's a great sensitivity of the crest factor, the kurtosis and the variance on the effectiveness of our diagnostic system. Consequently, the obtained results are capable of detecting faults in the induction motor under different operating conditions.

show abstract

Practical Investigation on Bearing Fault Diagnosis Using Massive Vibration Data and Artificial Neural Network

Cited by 5 publications

References 8 publications

DAE-LSTM neural network-based prediction model for segmental line loss rate of low-voltage power grid

DAE-LSTM neural network-based prediction model for segmental line loss rate of low-voltage power grid

Enhancing Rotary Machine Reliability Through Condition-Based Maintenance Optimization

Optimized multi layer perceptron artificial neural network based fault diagnosis of induction motor using vibration signals

Contact Info

Product

Resources

About