Reciprocating compression machinery is the primary source of compressed air in the industry. Undiagnosed faults in the machinery's components produce a high rate of unplanned stoppage of production processes that can even result in catastrophic consequences. Fault diagnosis in reciprocating compressors requires complex and time-consuming feature-extraction processes because typical fault diagnosers cannot deal directly with raw signals. In this paper, we streamline the deep learning and optimization algorithms for effective fault diagnosis on these machines. The proposed approach iteratively trains a group of long short-term memory (LSTM) models from a time-series representation of the vibration signals collected from a compressor. The hyperparameter search is guided by a Bayesian approach bounding the search space in each iteration. Our approach is applied to diagnose failures in intake/discharge valves on double-stage machinery. The fault-recognition accuracy of the best model reaches 93% after statistical selection between a group of candidate models. Additionally, a comparison with classical approaches, state-of-the-art deep learning-based fault-diagnosis approaches, and the LSTM-based model shows a remarkable improvement in performance by using the proposed approach.
Bibliographical noteFunding Information:
The work was sponsored in part by Universidad Polité cnica Salesiana through the research group GIDTEC, the National Natural Science Foundation of China (51775112, 51605406), the MoST Science and Technology Partnership Program (KY201802006), and the Research Program of Higher Education of Guangdong (2016KZDXM054). The experimental work was developed at the GIDTEC Research Group Lab of the Universidad Politécnica Salesiana, Ecuador.
- Bayesian optimization
- Deep learning
- Reciprocating compressor
- Time-series dimensionality reduction