Skip to main content
SpringerLink
Log in

Recognition of Carbon Content of Pr-Nd Alloys Based on Mel-Frequency Cepstrum Coefficient of Force Signals

  • Machine Learning and New Paradigms in Computational Materials Research
  • Published:
JOM Aims and scope Submit manuscript

Abstract

The use of chemical analysis to detect the carbon content of praseodymium–neodymium (Pr-Nd) alloys in industrial production has several disadvantages. To overcome those shortcomings, this article proposes a method for recognizing the carbon content of Pr-Nd alloys based on the Mel-frequency cepstrum coefficient (MFCC) of force signals and verifies the method through a self-developed microhole drilling experimental device. The reliability of the hardware and the rationality of the signal data are verified through the dynamic drilling force model and the cantilever beam structure equation. The model solution results show that the combination of MFCC and long short-term memory network can effectively recognize force signals, with an improved accuracy of 97.26%. Thus, the requirements of industrial production quality inspection are confirmed to be met. The model evaluation results show high performance indicators of the model; thus, the model is sufficiently robust. The method effectively controls the sampling time between 5 and 10 s, and the model substantially shortens the detection time for the carbon content of the Pr-Nd alloy to only 0.024–0.059 s. Thus, the requirements of an online real-time detection system are satisfied.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Y. Wang, and M. Yue, Research progresses in preparation of 2:17 type Sm(CoCuFeZr)z permanent magnets with high magnetic properties. Chin. J. Rare Met. 43(11), 1210 (2019).

    Google Scholar 

  2. A. Hu, Q. Guo, S. Wang, L. Huang, Z. Wu, and J. Zhou, Theoretical investigation of 2.79 μm Er, Yb:GSGG mid-infrared laser. Infrared Laser Eng. 41(05), 1168 (2012).

    Google Scholar 

  3. H. Fang, G. Zhang, and L. Xia, Effects of rare earth on boriding strengthening property of iron-based powder metallurgy materials. China Surf. Eng. 33(05), 56 (2020).

    Article  Google Scholar 

  4. T. Wu, L. Wang, H. He, H. Wang, H. Shen, Q. Liu, and Y. Shi, Research progress of Lu3Al5O12-based scintillation ceramics. Chin. J. Lumin. 42(07), 917 (2021).

    Article  Google Scholar 

  5. W. Liu and Z. Lu, Application of pinacolborane in catalytic enantioselective hydroboration of ketones and imines. Chin. J. Org. Chem. 40(11), 3596 (2020).

    Article  Google Scholar 

  6. M. Sun, J. Zhuang, H. Deng, Z. Chen, S. Si, and R. Zhang, Reviews on the study of aluminum alloys and aluminum matrix composites with high-temperature anti-creep behavior. Mater. Rep. 35(11), 11138 (2021).

    Google Scholar 

  7. Y. Yu, S. Wang, and W. Li, Effect of Ce solid solution doping on work function of LaB6 cathode material. Rare Met. Mater. Eng. 50(06), 2201 (2021).

    Google Scholar 

  8. L. Sun, L. Chen, Y. Wang, X. Zhang, and D. Xu, Research progress on mechanical and corrosion properties of Zn-Cu-Ti alloys. Mater. Rep. 35(03), 3152 (2021).

    Google Scholar 

  9. K. Mu, F. Zhang, C. Wang, W. Zhang, and L. Hu, Advance in studies on rare earth against plant disease. J. Chin. Rare Earth Soc. 01, 1 (2003).

    Google Scholar 

  10. Y. Wang, S. Liu, Q. Qin, H. Liu, L. Zhang, T. Wei, H. Li, and X. Liu, Praseodymium iridium oxide as a competitive electrocatalyst for oxygen evolution reaction in acid media. Sci. China (Materials) 64(09), 2193 (2021).

    Article  Google Scholar 

  11. C. Chen, Y. Cao, S. Liu, J. Chen, and W. Jia, Review on the latest developments in modified vanadium-titanium-based SCR catalysts. Chin. J. Catal. 39(08), 1347. (2018).

    Article  Google Scholar 

  12. A. Trench and J.P. Sykes, Rare earth permanent magnets and their place in the future economy. Engineering 6(02), 34 (2020).

    Article  Google Scholar 

  13. Y. Chen, Research progress of preparation of rare earth metals by electrolysis in fluoride salt system. Chin. Rare Earths 35(02), 99 (2014).

    Google Scholar 

  14. L. Cheng, C. Chen, Y. Wen, Y. Peng, and G. Zheng, Determination of 17 rare earth impurities in high purity copper sulfate by ICP-MS. Chem. Reag. 42(10), 1196 (2020).

    Google Scholar 

  15. N. Yao, J. Chen, J. Li, and K. Hu, HCS-040 tube furnace infrared carbon and sulfur analyzer for determination of carbon and sulfur in rare earth metals. PTCA (Part B: Chemical Analysis) 38(05), 251 (2002).

    Google Scholar 

  16. F. Liu, B. Zeng, X. Wu, X. Chen, Y. Tu, and L. Cao, Research on drilling method for carbon content of PrNd alloy based on cutting force model. Chin. Rare Earths 43(02), 53 (2022).

    Google Scholar 

  17. J. Lin, Y. Chen, and Z. Xia, Electrical conductivity of fluoride melts in La-Nd cell electrolytes. Chin. Rare Earths 01, 27 (1998).

    Google Scholar 

  18. H.K. Lee, S.I. Chang, and E. Yoon, A flexible polymer tactile sensor: fabrication and modular expandability for large area deployment. J. Microelectromech. Syst. 15(6), 1681 (2006).

    Article  Google Scholar 

  19. C. Roberto, O. Andrew, J. Dinesh, J. Lin, W. Yuan, M. Jitendra, E.H. Adelson, and L. Sergey, More than a feeling: learning to grasp and regrasp using vision and touch. IEEE Robot. Autom. Lett. 3(4), 3300 (2018).

    Article  Google Scholar 

  20. B. Wu, I. Akinola, J. Varley, and P. Allen, MAT: Multi-fingered adaptive tactile grasping via deep reinforcement learning. (2019).

  21. H. Zheng, F. Lu, M. Ji, M. Strese, Y. Özer, and E. Steinbach, Deep learning for surface material classification using haptic and visual information. IEEE Trans. Multimed. 18(12), 2407 (2016).

    Article  Google Scholar 

  22. T. Miyagi and S. Katsura, Analysis and modeling based on cepstrum for haptic presentation considering frequency features of vibration in rubbing motion. IEEJ J. Ind. Appl. 4(2), 74 (2015).

    Google Scholar 

  23. T. Tsuji, K. Sato, and S. Sakaino, Contact feature recognition based on MFCC of force signals. IEEE Robot. Autom. Lett. PP(99), 1 (2021).

    Google Scholar 

  24. X. Wu, X. Chen, F. Liu, L. Wang, J. Li, and S. Chen, Research on classification of carbon content in Pr-Nd alloys based on MFCC and BP neural network. (2021). https://doi.org/10.1109/CAC53003.2021.9727226.

  25. R. Jiao, K. Peng, and J. Dong, Remaining useful life prediction for a roller in a hot strip mill based on deep recurrent neural networks. IEEE/CAA J. Autom. Sin. 8(7), 10 (2021).

    Google Scholar 

  26. R. Wang, F. Yan, J. Lu, and W. Yang, COVID-19 trend forecasting by using dropout—LSTM model. J. Univ. Electron. Sci. Technol. China 50(03), 414 (2021).

    Google Scholar 

  27. Y. Wang, S. Li, S. Kang, J. Xie, and V.I. Mikulovich, Method of predicting remaining useful life of rolling bearing combining CNN and LSTM. J. Vib. Meas. Diagn. 41(03), 439 (2021).

    Google Scholar 

  28. S. Huang, C. Shao, J. Li, X. Zhang, and J. Qian, Vehicle trajectory reconstruction and anomaly detection using deep learning. J. Transp. Syst. Eng. Inf. Technol. 21(03), 47 (2021).

    Google Scholar 

  29. R. Li, T. Ma, X. Zhang, X. Hui, Y. Liu, and X. Yin, Short-term wind power prediction based on convolutional long-short-term memory neural networks. Acta Energ. Sol. Sin. 42(06), 304 (2021).

    Google Scholar 

  30. D. Wang and F. Jiao, Study on critical feed rate of delamination based on thrust force of chisel edge during CFRP drilling. J. Mech. Eng. 57(03), 255 (2021).

    Article  MathSciNet  Google Scholar 

  31. T. Zhao, J. Xiao, S. Fan, Z. Yang, and F. Yang, Study on chip shapes and drilling forces of low frequency vibration drilling of TC4 titanium alloy. China Mech. Eng. 31(19), 2276 (2020).

    Google Scholar 

  32. L. Zhang, Y. Wang, H. Zhao, S. Zhao, and Y. Hu, Computational simulation and experimental research on cutting force during high-speed bone drilling. J. Central South Univ. (Science and Technology) 49(09), 2191 (2018).

    Google Scholar 

  33. X. Tu, Q. Yang, P. Song, M. Zheng, J. Shen, and X. Yang, A credit scoring model based on logistic regression and RONSA. J. Sichuan Univ. (Engineering Science Edition) 46(06), 19 (2014).

    Google Scholar 

  34. F. Zhang, M. Ge, Z. Guo, C. Xie, Z. Yang, and Z. Song, Study of multiscale entropy model to evaluate the cognitive behavior of healthy elderly people based on resting state functional magnetic resonance imaging. Acta Phys. Sin. 69(10), 291 (2020).

    Google Scholar 

  35. W. Wang, Z. He, Z. Han, and Y. Qian, Landslides susceptibility assessment based on deep belief network. J. Northeast. Univ. (Natural Science) 41(05), 609 (2020).

    Google Scholar 

  36. X. Zhou, J. Li, B. Fang, and H. Miao, Preparation method and technological condition effects of tce rare earth polishing powder. Rare Earth 06, 33 (2003).

    Google Scholar 

Download references

Funding

The funding was provided by Key Research and Development Program of Jiangxi Province (Grant No. 20192BBE50010). Project supported by the Jiangxi Province Key Innovation R&D Platform Plan (20181BCD40009).

Author information

Authors and Affiliations

  1. Jiangxi University of Science and Technology, Ganzhou, 341000, China

    Xinyu Chen, Xinyu Wu, Feifei Liu & Zixian Liu

  2. Jiangxi Ionic Rare Earth Engineering Research Co. Led, Ganzhou, 341000, China

    Xinyu Wu, Bohua Zeng & Xiangfei Dou

Authors
  1. Xinyu Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xinyu Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Feifei Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zixian Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Bohua Zeng
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Xiangfei Dou
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Feifei Liu.

Ethics declarations

Conflict of interest

On behalf of all authors, the corresponding author states that there is no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (PDF 969 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, X., Wu, X., Liu, F. et al. Recognition of Carbon Content of Pr-Nd Alloys Based on Mel-Frequency Cepstrum Coefficient of Force Signals. JOM 74, 3454–3465 (2022). https://doi.org/10.1007/s11837-022-05384-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11837-022-05384-z

Search

Navigation