A Low-Cost, Scalable Approach for Compressor Fault Monitoring Using Deep Learning on Acoustic Signals
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
ABSTRACT
In chemical and process industries, reciprocating air compressors are critical single-line equipment whose unexpected failure can trigger plant-wide shutdowns.Legacy compressors often lack built-in monitoring systems, posing significant challenges for early fault detection.This study proposes a non-intrusive, deep learning-based framework for detecting compressor faults through acoustic signal analysis, aiming to retrofit predictive maintenance capabilities into aging assets.
A publicly available dataset of air compressor acoustic recordings was utilized, encompassing healthy and seven fault conditions.Sequential models based on Long Short-Term Memory (LSTM) and Bidirectional LSTM (BiLSTM) networks were first developed using manually extracted spectral features.Subsequently, a Convolutional Neural Network (CNN) was trained directly on mel-spectrogram representations of the sound signals.Data augmentation techniques were employed to improve model generalization.
Performance was evaluated through per-class precision, recall, F1-score, confusion matrices, and cross-validation.The LSTM model achieved a validation accuracy of 92%, which improved to 94% with the BiLSTM architecture.The CNN model achieved 96.6% validation accuracy, further increasing to 98.3% after augmentation, with a macro-F1 score of 98.6%.Cross-validation demonstrated stable performance (±0.4% deviation).
A real-world proof-of-concept test on 20 new compressor recordings achieved 95% accuracy, validating the model’s practical deployment capability.The proposed deep learning framework provides a scalable, cost-effective solution for sound-based fault diagnosis in compressors, eliminating the need for physical sensor installations.The CNN model trained on mel-spectrograms proved particularly effective, offering near-real-time prediction performance with minimal hardware requirements.
##plugins.themes.bootstrap3.article.details##
Compressor Fault Diagnosis, Acoustic Signal Analysis;, ; Deep Learning, Convolutional Neural Networks, Long Short-Term Memory, Spectrogram;, ; Predictive Maintenance, Industrial Condition Monitoring.
Cabrera, D., Medina, R., Cerrada, M., Sánchez, R. V., Estupiñan, E., & Li, C. (2024). Improved Mel Frequency Cepstral Coefficients for Compressors and Pumps Fault Diagnosis with Deep Learning Models. Applied Sciences, 14(5), 1710. https://doi.org/10.3390/app14051710
Dewangan, G., & Maurya, S. (2022). Fault Diagnosis of Machines Using Deep Convolutional Beta-Variational Autoencoder. IEEE Transactions on Artificial Intelligence, 3(2),287–296. https://doi.org/10.1109/TAI.2021.3110835
Guo, D., Ge, W., Li, B., & Gao, J. (2023). Identification of air compressor faults based on ViT and Mel spectrogram. 2023 2nd International Conference on Robotics, Artificial Intelligence and Intelligent Control (RAIIC), 246–251. https://doi.org/10.1109/RAIIC59453.2023. 10281191
Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.173 5
Jarwar, M. A., Khowaja, S. A., Dev, K., Adhikari, M., & Hakak, S. (2023). NEAT: A Resilient Deep Representational Learning for Fault Detection Using Acoustic Signals in IIoT Environment. IEEE Internet of Things Journal,10(4),28642871. https://doi.org/10.1109/JIOT.2021.310966 8
Mobtahej, P., Zhang, X., Hamidi, M., & Zhang, J. (2024, January). An LSTM-Autoencoder Architecture for Anomaly Detection Applied on Compressors Audio Data. Authorea, Inc. https://doi.org/10.22541/au.170669153.35 856456/v1
Safaei, M., Soleymani, S. A., Safaei, M., Chizari, H., & Nilashi, M. (2023). Deep learning algorithm for supervision process in production using acoustic signal. Applied Soft Computing, 146, 110682 https://doi.org/10.1016/j.asoc.2023.11068 2
Tsalera, E., Papadakis, A., & Samarakou, M. (2021). Comparison of pre-trained CNNs for audio classification using transfer learning. Journal of Sensor and Actuator Networks,10(4),72. https://doi.org/10.3390/jsan10040072
Verma, N. K., Sevakula, R. K., & Dixit, S. (2016). Intel-ligent condition-based monitoring using acoustic signals for air compressors. IEEE Transactions on Reliability, 65(1), 291–309. https://doi.org/10.1109/TR.2015.2452931
Wang, H., Zheng, H., Zhang, Z., & Wang, G. (2024). A deep learning-based acoustic signal analysis method for monitoring the distillation columns’ potential faults. Applied Sciences,14(16),7026. https://doi.org/10.3390/app14167026
Yong, L. Z., & Nugroho, H. (2022). Acoustic Anomaly Detection of Mechanical Failure: Time-Distributed CNN-RNN Deep Learning Models. In Lecture Notes in Computer Science (pp.662–672). https://doi.org/10.1007/978-981-19-3923 5_57
Yurdakul, M., & Taşdemir, Ş. (2023). Acoustic Signal Analysis with Deep Neural Network for Detecting Fault Diagnosis in Industrial Machines. In arXiv preprint arXiv: 2312.01062. https://doi.org/10.48550/arxiv.2312.01062
Zhang, S., Zhang, S., Wang, B., & Habetler, T. G. (2020). Deep Learning Algorithms for Bearing Fault Diagnostics—A Comprehensive Review. IEEE Access, 8, 29857–29881. https://doi.org/10.1109/ACCESS.202072859