Abstract
Deep learning is one of the emerging techniques that shows good failure modes classification prediction results due to its flexibility in recognizing patterns from raw sensor data. However, it requires complex hyperparameter optimization, high training time, and high computational hardware resources for neural network architecture. On the other hand, classical machine learning algorithms rely heavily on domain knowledge and manual feature engineering which is not always available in the industry. Therefore, we present an alternative method that learns characteristics of multivariate raw time series data to perform failure mode classification. The method is based on the deep forest algorithm, which is composed of two main processes: multi-grained scanning and cascade forest. The multi-grained scanning process windows the data and screens the times series to generate feature vectors automatically based on class probability distribution and hence recognize patterns from data. The cascade forest uses the output of the multi-grained scanning process and creates layers of random forests to make predictions. Each layer will perform fault classification, and the number of layers will increase until the accuracy of the classification does not improve. This layer-by-layer process is similar to deep learning, where the algorithm architecture is composed of different hidden layers. The presented methodology directly works with raw data in three domains: time, frequency, and time & frequency domain. Also, the method is validated using data provided by the Prognosis and Health Management (PHM) data challenge 2022 competition for hydraulic rock drill multiple failure mode classifications. The results show that the presented methodology is faster, less complex, and more accurate than deep learning algorithms.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
The data set used in this study was provided by the PHM Society Data Challenge Competition [https://data.phmsociety.org/2022-phm-conference-data-challenge/].
Code availability
Not applicable.
References
Akkad, K., & He, D. (2023). A dynamic mode decomposition based deep learning technique for prognostics. Journal of Intelligent Manufacturing, 34, 2207–2224. https://doi.org/10.1007/s10845-022-01916-1.
Ding, J., Luo, Q., Jia, L., & You, J. (2020). Deep forest-based fault diagnosis method for chemical process. Mathematical Problems in Engineering. https://doi.org/10.1155/2020/5281512
Guan, K., Yang, G., Du, L., Li, Z., & Yang, X. (2023). Method for fusion of neighborhood rough set and XGBoost in welding process decision-making. Journal of Intelligent Manufacturing, 34, 1229–1240. https://doi.org/10.1007/s10845-021-01844-6.
Huang, J., & Ting, C. (2022). Deep learning object detection applied to defect recognition of memory modules. International Journal of Advanced Manufacturing Technology, 121, 8433–8445. https://doi.org/10.1007/s00170-022-09716-w.
Jakobsson, E., Frisk, E., Krysander, M., & Pettersson, R. (2022). Time series fault classification for wave propagation systems with sparse fault data. https://doi.org/10.48550/arXiv.2203.16121.
Jia, Z., Liu, Z., Gan, Y., Vong, C., & Pecht, M. (2021). A deep forest-based fault diagnosis scheme for electronics-rich analog circuit systems. IEEE Transactions on Industrial Electronics, 68(10), 10087–10096. https://doi.org/10.1109/TIE.2020.3020252.
Khrunyk, R. (2000). Development of new low-alloy steels for rock roller drill bits. Materials Science, 36, 437–444. https://doi.org/10.1007/BF02769608.
Lai, Y. (2019). A comparison of traditional machine learning and deep learning in image recognition. Journal of Physics: Conference Series. https://doi.org/10.1088/1742-6596/1314/1/012148
Lecun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436–444. https://doi.org/10.1038/nature14539.
Li, W., Jia, X., Hsu, Y., Liao, C., Wang, Y., Lin, M., & Lee, J. (2023). A novel methodology for lens matching in compact lens module assembly. IEEE Transactions on Automation Science and Engineering, 20(2), 741–750. https://doi.org/10.1109/TASE.2022.3164831.
Li, X., Ding, Q., & Sun, J. Q. (2018). Remaining useful life estimation in prognostics using deep convolution neural networks. Reliability Engineering and System Safety, 172, 1–11. https://doi.org/10.1016/j.ress.2017.11.021.
Liu, C., Mauricio, A., Chen, Z., Declercq, K., Meerten, Y., Vonderscher, Y., & Gryllias, K. (2020). Gear grinding monitoring based on deep convolutional neural networks. IFAC-PapersOnLine, 53(2), 10324–10329. https://doi.org/10.1016/j.ifacol.2020.12.2768.
Lopez-del Rio, A., Martin, M., Perera-Lluna, A., & Saidi, R. (2020). Effect of sequence padding on the performance of deep learning models in archaeal protein functional prediction. Scientific Reports. https://doi.org/10.1038/s41598-020-71450-8
Ma, W., Geng, X., Jia, C., Gao, L., Liu, Y., & Tian, X. (2019). Percussion characteristic analysis for hydraulic rock drill with no constant-pressurized chamber through numerical simulation and experiment. Advances in Mechanical Engineering. https://doi.org/10.1177/1687814019841486
Oh, J., Song, C., Kim, D., Kim, J., Park, J., & Cho, J. (2016). Numerical investigation of performance of hydraulic percussion drifter. International Journal of Precision Engineering and Manufacturing, 17, 879–885. https://doi.org/10.1007/s12541-016-0107-8.
Pang, M., Ting, K. M., Zhao, P., & Zhou, Z. (2018). Improving deep forest by confidence screening. Proceedings-IEEE international conference on data mining 2018, 1194–1199. https://doi.org/10.1109/ICDM.2018.00158.
PHM Society (2022). 2022 PHM conference data challenge. PHM society data https://data.phmsociety.org/2022-phm-conference-data-challenge/.
Razdan, A., & Ravichandran, V. (2022). Fundamentals of Partial Differential Equations. Springer. https://doi.org/10.1007/978-981-16-9865-1
Schlosser, T., Friedrich, M., Beuth, F., & Kowerko, D. (2022). Improving automated visual fault inspection for semiconductor manufacturing using a hybrid multistage system of deep neural networks. Journal of Intelligent Manufacturing, 33, 1099–1123. https://doi.org/10.1007/s10845-021-01906-9.
Siahpour, S., Li, X., & Lee, J. (2020). Deep learning-based cross-sensor domain adaptation for fault diagnosis of electro-mechanical actuators. International Journal of Dynamics and Control, 8, 1054–1062. https://doi.org/10.1007/s40435-020-00669-0.
Taco, J., Gore, P., Minami, T., Kundu, P., Suer, A., & Lee, J. (2022). A novel methodology for health assessment in printed circuit boards. PHM Society European Conference, 7(1), 556–562. https://doi.org/10.36001/phme.2022.v7i1.3373.
Yang, Y., Liao, Y., Meng, G., & Lee, J. (2011). A hybrid feature selection scheme for unsupervised learning and its application in bearing fault diagnosis. Expert Systems with Applications, 38(9), 11311–11320. https://doi.org/10.1016/j.eswa.2011.02.181.
Yao, J., Lu, B., & Zhang, J. (2022). Tool remaining useful life prediction using deep transfer reinforcement learning based on long short-term memory networks. International Journal of Advanced Manufacturing Technology, 118, 1077–1086. https://doi.org/10.1007/s00170-021-07950-2.
Zhang, Y., Zhou, J., Zheng, W., Feng, J., Li, L., Liu, Z., Li, M., Zhang, Z., Chen, C., Li, X., Qi, Y., & Zhou, Z. (2019). Distributed deep forest and its application to automatic detection of cash-out fraud. ACM Transactions on Intelligent Systems and Technology. https://doi.org/10.1145/3342241
Zhou, Z. (2012). Ensemble Methods: Foundations and Algorithms. CRC Press.
Zhou, Z., & Feng, J. (2019). Deep forest. National Science Review, 6(1), 74–86. https://doi.org/10.1093/nsr/nwy108.
Zhou, F., Yang, S., Fujita, H., Chen, D., & Wen, C. (2020). Deep learning fault diagnosis method based on global optimization GAN for unbalanced data. Knowledge-Based Systems. https://doi.org/10.1016/j.knosys.2019.07.008
Zohuri, B., & Moghaddam, M. (2020). Deep learning limitations and flaws. Modern Approaches on Material Science. https://doi.org/10.32474/mams.2020.02.000138
Zuo, H., Luo, Z., Guan, J., & Wang, Y. (2014). Identification on rock and soil parameters for vibration drilling rock in metal mine based on fuzzy least square support vector machine. Journal of Central South University, 21, 1085–1090. https://doi.org/10.1007/s11771-014-2040-2.
Funding
Not applicable.
Author information
Authors and Affiliations
Contributions
JT: methodology, result analysis, and original draft writing; PK: methodology and proof reading; JL: methodology and proof reading.
Corresponding author
Ethics declarations
Conflict of interest
The authors have no relevant financial or non-financial interests to disclose.
Ethical approval
Not applicable.
Consent to participant
Not applicable.
Consent for publication
Not applicable.
Additional information
Publisher’s Note
Springer nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Taco, J., Kundu, P. & Lee, J. A novel technique for multiple failure modes classification based on deep forest algorithm. J Intell Manuf 35, 3115–3129 (2024). https://doi.org/10.1007/s10845-023-02185-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10845-023-02185-2