Abstract
Modern manufacturing systems are increasingly equipped with sensors and communication capabilities, and data-driven intelligence is gaining more popularity to analyze big manufacturing data. This paper presents a new deep neural network model based on Gaussian–Bernoulli deep Boltzmann machine (GDBM) for optimized condition prognosis. GDBM firstly uses Gaussian neurons to normalize the sequential input. Then, Extremum Disturbed and Simple Particle Swarm Optimization (tsPSO) method is introduced to optimize the model hyperparameters. Finally, a hybrid modified Liu–Storey conjugate gradient (MLSCG) algorithm is utilized to get a better rate of convergence, which makes the prognosis process being more computational efficient. Experimental study is conducted on condition prediction of a compressor in field, and the experimental results have shown that the presented model is able to obtain better performance over conventional data driven approaches.
Similar content being viewed by others
References
Bajaber F, Awan I (2010) Energy efficient clustering protocol to enhance lifetime of wireless sensor network. J Ambient Intell Humaniz Comput 1(4):239–248
Camacho D, Novais P (2017) Innovations and practical applications of intelligent systems in ambient intelligence and humanized computing. J Ambient Intell Humaniz Comput 8:155–156
Cao LJ, Tay FEH (2003) Support vector machine with adaptive parameters in financial time series forecasting. IEEE Trans Neural Netw 14(6):1506–1518
Cho KH, Raiko T, Ilin A (2013) Gaussian–Bernoulli deep Boltzmann machine. In: IEEE international joint conference on neural networks, pp 1–7
Gao R, Wang L, Teti R, Dornfeld D, Kumara S, Mori M, Helu M (2015) Cloud-enabled prognosis for manufacturing. Cirp Ann Manuf Technol 64(2):749–772
Hager WW, Zhang H (2006) A survey of nonlinear conjugate gradient methods. Pac J Optim 2(1):35–58
Helu M, Libes D, Lubell J, Lyons K, Morris K (2016) Enabling smart manufacturing technologies for decision-making support. In: AMSE proceedings of the ASME international design engineering technical conferences and computers and information in engineering conference, pp 1–10
Hinton GE, Osindero S, Teh YW (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554
Hu T, Li P, Zhang C et al (2013) Design and application of a real-time industrial ethernet protocol under Linux using RTAI. Int J Comput Integr Manuf 26(5):429–439
Islam MMM, Kim JM (2017) Time–frequency envelope analysis-based sub-band selection and probabilistic support vector machines for multi-fault diagnosis of low-speed bearings. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-017-0585-2
Ji S, Hu T, Zhang C, Sun S (2012) A parametric hardware fine acceleration/deceleration algorithm and its implementation. Int J Adv Manuf Technol 63(9–12):1109–1115
Kennedy J, Eberhart RC (1995) Particle swarm optimization. In: proceedings of the IEEE international conference on neural networks, pp 1942–1948
Keronen S, Cho K, Raiko T et al (2013) Gaussian–Bernoulli restricted Boltzmann machines and automatic feature extraction for noise robust missing data mask estimation. In: Proceedings of 2013 IEEE international conference on acoustics, speech and signal processing. IEEE, pp 6729–3733. https://doi.org/10.1109/ICASSP.2013.6638964
Kusiak A (2017) Smart manufacturing must embrace big data. Nature 544(7648):23–25
Le Roux N, Bengio Y (2008) Representational power of restricted Boltzmann machines and deep belief networks. Neural Comput 20(6):1631–1649
Lee H, Grosse R, Ranganath R, Ng AY (2009) Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: ACM international conference on machine learning, pp 609–616
Li H, Luo Y, Huang J et al (2013) New acoustic monitoring method using cross-correlation of primary frequency spectrum. J Ambient Intell Humaniz Comput 4(3):293–301
Li C, Senchez R, Zurita G, Cerrada M, Cabrera D, Vásquez R (2015) Multimodal deep support vector classification with homologous features and its application to gearbox fault diagnosis. Neurocomputing 168:119–127
Maachou A, Malti R, Melchior P, Battaglia JL, Oustaloup A, Hay B (2011) Application of fractional Volterra series for the identification of thermal diffusion in an ARMCO iron sample subject to large temperature variations. IFAC Proc Vol 44(1):5621–5626
Meng JD, DU X (2012) Global convergence of a modified LS conjugate gradient method with an Armijo-type line search. J Chongqing Norm Univ (Nat Sci) 6:003
Peng Y, Dong M, Zuo MJ (2010) Current status of machine prognostics in condition-based maintenance: a review. Int J Adv Manuf Technol 50:297–313
Rigatos G, Siano P, Zervos N (2013) An approach to fault diagnosis of nonlinear systems using neural networks with invariance to Fourier transform. J Ambient Intell Humaniz Comput 4(6):621–639
Sorjamaa A, Hao J, Reyhani N, Ji Y, Lendasse A (2007) Methodology for long-term prediction of time series. Neurocomputing 70(16–18):2861–2869
Srivastava N, Salakhutdinov RR, Hinton GE (2013) Modeling documents with deep boltzmann machines. arXiv:1309.6865
Suk HI, Lee SW, Shen D (2014) Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis. NeuroImage 101:569–582
Tamilselvan P, Wang P (2013) Failure diagnosis using deep belief learning based health state classification. Reliab Eng Syst Saf 115:124–135
Tao F, Qi Q (2017) New IT driven service-oriented smart manufacturing: framework and characteristics. IEEE Trans Syst Man Cybern Syst 99:1–11
Tao F, Qi Q, Liu A, Qi Q, Kusiak A (2018) Data-driven smart manufacturing. J Manuf Syst. https://doi.org/10.1016/j.jmsy.2018.01.006
Telgarsky M (2015) Representation benefits of deep feedforward networks. arXiv:1509.08101
Teti R, Kumara S (1997) Intelligent computing methods for manufacturing systems. Cirp Ann Manuf Technol 46(2):629–652
Tonshoff HK, Wulfsberg JP, Kals HJJ, Konig W, van Luttervelt CA (1988) Development and trends in monitoring and control of machining process. CIRP Ann Manuf Technol 37(2):611–622
Wang P, Gao RX, Fan Z (2015) Cloud computing for cloud manufacturing: benefits and limitations. J Manuf Sci Eng 137:1–10
Wang J, Zhang L, Duan L, Gao RX (2017) A new paradigm of cloud-based predictive maintenance for intelligent manufacturing. J Intell Manuf 28(5):1125–1137
Wang J, Ma Y, Zhang L, Gao RX, Wu D (2018) Deep learning for smart manufacturing: methods and applications. J Manuf Syst. https://doi.org/10.1016/j.jmsy.2018.01.003
Wuest T, Weimer D, Irgens C, Klaus DT (2016) Machine learning in manufacturing: advantages, challenges, and applications. Prod Manuf Res 4(1):23–45
Yang BS, Oh MS, Tan ACC (2008) Machine condition prognosis based on regression trees and one-step-ahead prediction. Mech Syst Signal Process 22(5):1179–1193
Yuan M, Tang H, Li H (2014) Real-time keypoint recognition using restricted Boltzmann machine. IEEE Trans Neural Netw Learn Syst 25(11):2119–2126
Zhang CY, Chen CLP, Gan M et al (2015) Predictive deep Boltzmann machine for multiperiod wind speed forecasting. IEEE Trans Sustain Energy 6(4):1416–1425
Zhang N, Ding S, Zhang J, Xue Y (2018) An overview on restricted Boltzmann machines. Neurocomputing 275:1186–1199
Acknowledgements
This research acknowledges the financial support provided by National Key Research and Development Program of China (No. 2016YFC0802103), National Science Foundation of China (No. 51504274) and Science Foundation of China University of Petroleum (Beijing).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wang, J., Wang, K., Wang, Y. et al. Deep Boltzmann machine based condition prediction for smart manufacturing. J Ambient Intell Human Comput 10, 851–861 (2019). https://doi.org/10.1007/s12652-018-0794-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-018-0794-3