A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Volume 8 Issue 5
May  2021

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 11.8, Top 4% (SCI Q1)
    CiteScore: 17.6, Top 3% (Q1)
    Google Scholar h5-index: 77, TOP 5
Turn off MathJax
Article Contents
J. Pan, C. B. Li, Y. Tang, W. Li, and X. O. Li, "Energy Consumption Prediction of a CNC Machining Process With Incomplete Data," IEEE/CAA J. Autom. Sinica, vol. 8, no. 5, pp. 987-1000, May. 2021. doi: 10.1109/JAS.2021.1003970
Citation: J. Pan, C. B. Li, Y. Tang, W. Li, and X. O. Li, "Energy Consumption Prediction of a CNC Machining Process With Incomplete Data," IEEE/CAA J. Autom. Sinica, vol. 8, no. 5, pp. 987-1000, May. 2021. doi: 10.1109/JAS.2021.1003970

Energy Consumption Prediction of a CNC Machining Process With Incomplete Data

doi: 10.1109/JAS.2021.1003970
Funds:  This work was supported in part by the National Natural Science Foundation of China (51975075), Chongqing Technology Innovation and Application Program (cstc2018jszx-cyzdX0183)
More Information
  • Energy consumption prediction of a CNC machin- ing process is important for energy efficiency optimization strategies. To improve the generalization abilities, more and more parameters are acquired for energy prediction modeling. While the data collected from workshops may be incomplete because of misoperation, unstable network connections, and frequent transfers, etc. This work proposes a framework for energy modeling based on incomplete data to address this issue. First, some necessary preliminary operations are used for incomplete data sets. Then, missing values are estimated to generate a new complete data set based on generative adversarial imputation nets (GAIN). Next, the gene expression programming (GEP) algorithm is utilized to train the energy model based on the generated data sets. Finally, we test the predictive accuracy of the obtained model. Computational experiments are designed to investigate the performance of the proposed framework with different rates of missing data. Experimental results demonstrate that even when the missing data rate increases to 30%, the proposed framework can still make efficient predictions, with the corresponding RMSE and MAE 0.903 kJ and 0.739 kJ, respectively.

     

  • loading
  • [1]
    M. Bornschlegl, S. Kreitlein, M. Bregulla, and J. Franke, “A method for forecasting the running costs of manufacturing technologies in automotive production during the early planning phase,” Procedia CIRP, vol. 26, pp. 412–417, 2015. doi: 10.1016/j.procir.2014.07.103
    [2]
    Z. M. Bi and L. Wang, “Energy modeling of machine tools for optimization of machine setups,” IEEE Trans. Automation Science and Engineering, vol. 9, no. 3, pp. 607–613, 2012. doi: 10.1109/TASE.2012.2195173
    [3]
    N. Diaz, K. Ninomiya, J. Noble, and D. Dornfeld, “Environmental impact characterization of milling and implications for potential energy savings in industry,” Procedia CIRP, vol. 1, pp. 518–523, 2012. doi: 10.1016/j.procir.2012.04.092
    [4]
    M. Mori, M. Fujishima, Y. Inamasu, and Y. Oda, “A study on energy efficiency improvement for machine tools,” CIRP Annals, vol. 60, no. 1, pp. 145–148, 2011. doi: 10.1016/j.cirp.2011.03.099
    [5]
    Y. He, F. Liu, T. Wu, F.-P. Zhong, and B. Peng, “Analysis and estimation of energy consumption for numerical control machining,” Proc. the Institution of Mechanical Engineers,Part B:Journal of Engineering Manufacture, vol. 226, no. 2, pp. 255–266, 2012.
    [6]
    G. Tian, M. Zhou, and P. Li, “Disassembly sequence planning considering fuzzy component quality and varying operational cost,” IEEE Trans. Automation Science and Engineering, vol. 15, no. 2, pp. 748–760, 2018. doi: 10.1109/TASE.2017.2690802
    [7]
    Q. Xiao, C. Li, Y. Tang, L. Li, and L. Li, “A knowledge-driven method of adaptively optimizing process parameters for energy efficient turning,” Energy, vol. 166, pp. 142–156, 2019. doi: 10.1016/j.energy.2018.09.191
    [8]
    P. S. Bilga, S. Singh, and R. Kumar, “Optimization of energy consumption response parameters for turning operation using Taguchi method,” J. Cleaner Production, vol. 137, pp. 1406–1417, 2016. doi: 10.1016/j.jclepro.2016.07.220
    [9]
    S. A. Bagaber and A. R. Yusoff, “Multi-objective optimization of cutting parameters to minimize power consumption in dry turning of stainless steel 316,” J. Cleaner Production, vol. 157, pp. 30–46, 2017. doi: 10.1016/j.jclepro.2017.03.231
    [10]
    Y. Jiang, S. Yin, and O. Kaynak, “Optimized design of parity relation-based residual generator for fault detection: Data-driven approaches,” IEEE Trans. Industrial Informatics, vol. 17, no. 2, pp. 1449–1458, 2021. doi: 10.1109/TII.2020.2987840
    [11]
    Y. Jiang and S. Yin, “Recent advances in key-performance-indicator oriented prognosis and diagnosis with a MATLAB toolbox: DB-KIT,” IEEE Trans. Industrial Informatics, vol. 15, no. 5, pp. 2849–2858, 2019. doi: 10.1109/TII.2018.2875067
    [12]
    P. Zhang, X. Shi, and S. U. Khan, “QuantCloud: Enabling big data complex event processing for quantitative finance through a data-driven execution,” IEEE Trans. Big Data, vol. 5, no. 4, pp. 564–575, 2019. doi: 10.1109/TBDATA.2018.2847629
    [13]
    Y. Zhang, B. Xu, and T. Zhao, “Convolutional multi-head self-attention on memory for aspect sentiment classification,” IEEE/CAA J. Autom. Sinica, vol. 7, no. 4, pp. 1038–1044, 2020. doi: 10.1109/JAS.2020.1003243
    [14]
    P. M. Kebria, A. Khosravi, S. M. Salaken, and S. Nahavandi, “Deep imitation learning for autonomous vehicles based on convolutional neural networks,” IEEE/CAA J. Autom. Sinica, vol. 7, no. 1, pp. 82–95, 2020. doi: 10.1109/JAS.2019.1911825
    [15]
    R. Bhinge, J. Park, K. H. Law, D. A. Dornfeld, M. Helu, and S. Rachuri, “Toward a generalized energy prediction model for machine tools,” Journal of Manufacturing Science and Engineering-Transactions of the ASME, vol. 139, no. 4, Article No. 041013, Apr. 2017.
    [16]
    C. Zhang, Z. Zhou, G. Tian, Y. Xie, W. Lin, and Z. Huang, “Energy consumption modeling and prediction of the milling process: A multistage perspective,” Proc. the Institution of Mechanical Engineers,Part B:Journal of Engineering Manufacture, vol. 232, no. 11, pp. 1973–1985, 2016.
    [17]
    Q. Xiao, C. Li, Y. Tang, and X. Chen, “Energy efficiency modeling for configuration-dependent machining via machine learning: A comparative study,” IEEE Trans. Automation Science and Engineering, pp. 1–14, 2020. DOI: 10.1109/TASE.2019.2961714
    [18]
    Z. Guo, Y. Wan, and H. Ye, “A data imputation method for multivariate time series based on generative adversarial network,” Neurocomputing, vol. 360, pp. 185–197, 2019. doi: 10.1016/j.neucom.2019.06.007
    [19]
    K. Zhang, R. Gonzalez, B. Huang, and G. Ji, “Expectation–maximization approach to fault diagnosis with missing data,” IEEE Trans. Industrial Electronics, vol. 62, no. 2, pp. 1231–1240, 2015. doi: 10.1109/TIE.2014.2336635
    [20]
    T. Liu, H. Wei, and K. Zhang, “Wind power prediction with missing data using Gaussian process regression and multiple imputation,” Applied Soft Computing, vol. 71, pp. 905–916, 2018. doi: 10.1016/j.asoc.2018.07.027
    [21]
    F. Li, Z. Gui, H. Wu, J. Gong, Y. Wang, S. Tian, and J. Zhang, “Big enterprise registration data imputation: Supporting spatiotemporal analysis of industries in China,” Computers,Environment and Urban Systems, vol. 70, pp. 9–23, 2018. doi: 10.1016/j.compenvurbsys.2018.01.010
    [22]
    R. W. Krause, M. Huisman, C. Steglich, and T. Snijders, “Missing data in cross-sectional networks – An extensive comparison of missing data treatment methods,” Social Networks, vol. 62, pp. 99–112, 2020. doi: 10.1016/j.socnet.2020.02.004
    [23]
    A. P. Afghari, S. Washington, C. Prato, and M. M. Haque, “Contrasting case-wise deletion with multiple imputation and latent variable approaches to dealing with missing observations in count regression models,” Analytic Methods in Accident Research, vol. 24, Article No. 100104, Dec. 2019.
    [24]
    G. E. A. P. A. Batista, and M. C. Monard, “An analysis of four missing data treatment methods for supervised learning,” Applied Artificial Intelligence, vol. 17, no. 5-6, pp. 519–533, 2003/05/01 2003. doi: 10.1080/713827181
    [25]
    T. D. Pigott, “A review of methods for missing data,” Educational Research and Evaluation, vol. 7, no. 4, pp. 353–383, 2001/12/01 2001. doi: 10.1076/edre.7.4.353.8937
    [26]
    M. Cheliotis, C. Gkerekos, I. Lazakis, and G. Theotokatos, “A novel data condition and performance hybrid imputation method for energy efficient operations of marine systems,” Ocean Engineering, vol. 188, Article No. 106220 , Sept. 2019.
    [27]
    M. J. Azur, E. A. Stuart, C. Frangakis, and P. J. Leaf, “Multiple imputation by chained equations: What is it and how does it work?” Int J. Methods Psychiatr Res, vol. 20, no. 1, pp. 40–9, Mar. 2011. doi: 10.1002/mpr.329
    [28]
    R. Ratolojanahary, R. Houé Ngouna, K. Medjaher, J. Junca-Bourié, F. Dauriac, and M. Sebilo, “Model selection to improve multiple imputation for handling high rate missingness in a water quality dataset,” Expert Systems with Applications, vol. 131, pp. 299–307, 2019. doi: 10.1016/j.eswa.2019.04.049
    [29]
    D. J. Stekhoven and P. Buhlmann, “MissForest–non-parametric missing value imputation for mixed-type data,” Bioinformatics, vol. 28, no. 1, pp. 112–118, Jan. 2012. doi: 10.1093/bioinformatics/btr597
    [30]
    M. Resche-Rigon and I. R. White, “Multiple imputation by chained equations for systematically and sporadically missing multilevel data,” Statistical Methods in Medical Research, vol. 27, no. 6, pp. 1634–1649, 2018/06/01 2016. doi: 10.1177/0962280216666564
    [31]
    A. D. Stead and P. Wheat, “The case for the use of multiple imputation missing data methods in stochastic frontier analysis with illustration using English local highway data,” European J. Operational Research, vol. 280, no. 1, pp. 59–77, 2020. doi: 10.1016/j.ejor.2019.06.042
    [32]
    Q. Xiao, C. Li, Y. Tang, Y. Du, and Y. Kou, “Deep learning based modeling for cutting energy consumed in CNC turning process,” in Proc. IEEE Int. Conf. Systems, Man, and Cybernetics, 2018.
    [33]
    L. Gondara and K. Wang, “MIDA: Multiple imputation using denoising autoencoders,” in Proc. 22nd Pacific-Asia Conf. Advances in Knowledge Discovery and Data Mining, pp. 260–272, 2018.
    [34]
    X. Lai, X. Wu, L. Zhang, W. Lu, and C. Zhong, “Imputations of missing values using a tracking-removed autoencoder trained with incomplete data,” Neurocomputing, vol. 366, pp. 54–65, 2019. doi: 10.1016/j.neucom.2019.07.066
    [35]
    K. Wang, C. Gou, Y. Duan, Y. Lin, X. Zheng, and F.-Y. Wang, “Generative adversarial networks: introduction and outlook,” IEEE/CAA J. Autom. Sinica, vol. 4, no. 4, pp. 588–598, 2017. doi: 10.1109/JAS.2017.7510583
    [36]
    J. Yoon, J. Jordon, and M. Van Der Schaar, “GAIN: Missing data imputation using generative adversarial nets,” in Proc. 35th Int. Conf. Machine Learning, vol. 13, pp. 9042–9051, 2018.
    [37]
    P. Dey and A. K. Das, “A utilization of GEP (gene expression programming) metamodel and PSO (particle swarm optimization) tool to predict and optimize the forced convection around a cylinder,” Energy, vol. 95, pp. 447–458, 2016. doi: 10.1016/j.energy.2015.12.021
    [38]
    B. Choi and S.-U. Choi, “Physical habitat simulations of the Dal River in Korea using the GEP model,” Ecological Engineering, vol. 83, pp. 456–465, 2015. doi: 10.1016/j.ecoleng.2015.06.042
    [39]
    H. Shayeghi, A. Pirayeshnegab, A. Jalili, and H. A. Shayanfar, “Application of PSO technique for GEP in restructured power systems,” Energy Conversion and Management, vol. 50, no. 9, pp. 2127–2135, 2009. doi: 10.1016/j.enconman.2009.04.018
    [40]
    S. Mahdinia, H. Eskandari-Naddaf, and R. Shadnia, “Effect of cement strength class on the prediction of compressive strength of cement mortar using GEP method,” Construction and Building Materials, vol. 198, pp. 27–41, 2019. doi: 10.1016/j.conbuildmat.2018.11.265
    [41]
    S. Emamgolizadeh, S. M. Bateni, D. Shahsavani, T. Ashrafi, and H. Ghorbani, “Estimation of soil cation exchange capacity using genetic expression programming (GEP) and multivariate adaptive regression splines (MARS),” J. Hydrology, vol. 529, pp. 1590–1600, 2015. doi: 10.1016/j.jhydrol.2015.08.025
    [42]
    D. He, Z. Wang, L. Yang, and W. Dai, “Study on missing data imputation and modeling for the leaching process,” Chemical Engineering Research and Design, vol. 124, pp. 1–19, 2017.
    [43]
    F. Lobato, C. Sales, I. Araujo, V. Tadaiesky, L. Dias, L. Ramos, and A. Santana, “Multi-objective genetic algorithm for missing data imputation,” Pattern Recognition Letters, vol. 68, pp. 126–131, 2015. doi: 10.1016/j.patrec.2015.08.023
    [44]
    R. Little and D. Rubin, “Statistical analysis with missing data,” Journal of Marketing Research, vol. 26, no. 3, pp. 374–375, 1989.
    [45]
    S. J. Hadeed, M. K. O’Rourke, J. L. Burgess, R. B. Harris, and R. A. Canales, “Imputation methods for addressing missing data in short-term monitoring of air pollutants,” Sci Total Environ, vol. 730, Article No. 139140, Aug 15. 2020. doi: 10.1016/j.scitotenv.2020.139140
    [46]
    L. Chao, J. Zhipeng, and Z. Yuanjie, “A novel reconstructed training-set SVM with roulette cooperative coevolution for financial time series classification,” Expert Systems with Applications, vol. 123, pp. 283–298, 2019. doi: 10.1016/j.eswa.2019.01.022
    [47]
    J.-H. Chen and J.-Z. Lin, “Developing an SVM based risk hedging prediction model for construction material suppliers,” Automation in Construction, vol. 19, no. 6, pp. 702–708, 2010. doi: 10.1016/j.autcon.2010.02.014

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(7)  / Tables(11)

    Article Metrics

    Article views (1236) PDF downloads(75) Cited by()

    Highlights

    • Missing mechanism of energy modeling data for the Machining process is analyzed.
    • A framework for energy modeling based on incomplete data is proposed.
    • General and useful tips for utilizing the incomplete data sets are derived.

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return