Generative Adversarial Network and Fuzzy ARTMAP for imbalanced data classification in condition monitoring
Condition monitoring is a process of assessing the health status of a system, process, or machine. Monitoring and identifying any potential fault can be conducted by leveraging measurements from the installed sensors that provide information on the state of the system. In this respect, machine learn...
Saved in:
| 主要作者: | |
|---|---|
| 格式: | Thesis |
| 出版: |
2023
|
| 主題: | |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 總結: | Condition monitoring is a process of assessing the health status of a system, process, or machine. Monitoring and identifying any potential fault can be conducted by leveraging measurements from the installed sensors that provide information on the state of the system. In this respect, machine learning models are useful for processing and analysing the sensor data for fault detection. However, the imbalanced nature of these sensory data can cause misleading high accuracy scores. In this research, the highly imbalanced data classification problems are addressed using a deep learning method with the over-sampling method to handle industrial conditional monitoring and fault detection problems. Firstly, the Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP), an adversarial learning network is adopted for generating additional data samples to balance the numbers of samples between the majority and minority classes. Then, the Fuzzy ARTMAP (FAM) model is employed for data classification. A real-world condition monitoring problem is conducted as a case study to evaluate the usefulness of WGAN-GP-FAM in practical environments. |
|---|