A fusion data preprocessing method and its application in complex industrial power consumption prediction

Abstract Data-driven prediction methods often encounter problems in industrial applications due to noise, data redundancy, and insufficient labeled data. Preprocessing the data is required to improve prediction accuracy. At present, most data preprocessing methods are independent of each other and the correlation between methods is relatively small, resulting in repeated redundancy and reduced efficiency. To address this problem, this work proposes a fusion data preprocessing method based on a stacked denoising auto-encoders network (SDAE) and generative adversarial networks (GANs). This method reconstructs the noise reduction link in the SDAE network, improves the noise reduction effect of the model and extracts the main features of the data; the GANs is used to avoid overfitting caused by insufficient training data. Finally, the proposed method is applied to power consumption prediction in the metallurgical industry. Experiments show that the proposed method effectively reduces the model calculation time and improves the overall prediction accuracy.

[1]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[2]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[3]  Qi Li,et al.  Electricity consumption forecasting method based on MPSO-BP neural network model , 2016, ArXiv.

[4]  Dimitris Kanellopoulos,et al.  Data Preprocessing for Supervised Leaning , 2007 .

[5]  Iveta Zolotova,et al.  Comparison between multi-class classifiers and deep learning with focus on industry 4.0 , 2016, 2016 Cybernetics & Informatics (K&I).

[6]  Hao Ren,et al.  Prediction of early stabilization time of electrolytic capacitor based on ARIMA-Bi_LSTM hybrid model , 2020, Neurocomputing.

[7]  Taghi M. Khoshgoftaar,et al.  The pairwise attribute noise detection algorithm , 2007, Knowledge and Information Systems.

[8]  Mianxiong Dong,et al.  Deep Learning for Smart Industry: Efficient Manufacture Inspection System With Fog Computing , 2018, IEEE Transactions on Industrial Informatics.

[9]  Xuhua Yang,et al.  Circuit reliability prediction based on deep autoencoder network , 2019, Neurocomputing.

[10]  Francisco Herrera,et al.  Data Preprocessing in Data Mining , 2014, Intelligent Systems Reference Library.

[11]  Luis Perez,et al.  The Effectiveness of Data Augmentation in Image Classification using Deep Learning , 2017, ArXiv.

[12]  Peijun Du,et al.  Predicting soil heavy metal based on Random Forest model , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[13]  Hakki Ozgur Unver,et al.  An ISA-95-based manufacturing intelligence system in support of lean initiatives , 2013 .

[14]  Yuval Elovici,et al.  DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GAN , 2018, 2018 IEEE International Conference on Data Mining (ICDM).

[15]  Jiuwen Cao,et al.  Imbalanced learning algorithm based intelligent abnormal electricity consumption detection , 2020, Neurocomputing.

[16]  Zhen Li,et al.  Towards Better Analysis of Deep Convolutional Neural Networks , 2016, IEEE Transactions on Visualization and Computer Graphics.

[17]  Oludolapo A. Olanrewaju.  Predicting Industrial Sector's Energy Consumption: Application of Support Vector Machine , 2019, 2019 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM).

[18]  Tian Huixin,et al.  A novel improved data-driven subspace algorithm for power load forecasting in iron and steel enterprise , 2015, The 27th Chinese Control and Decision Conference (2015 CCDC).

[19]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[20]  Qiong Wang,et al.  A Short-term Load Forecasting Method Based on Fuzzy Neural RBF Network Adaptive Control , 2019 .

[21]  Gaoliang Peng,et al.  Rolling Element Bearings Fault Intelligent Diagnosis Based on Convolutional Neural Networks Using Raw Sensing Signal , 2017 .

[22]  Quoc V. Le,et al.  AutoAugment: Learning Augmentation Strategies From Data , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Manoj Kumar Tiwari,et al.  Data mining in manufacturing: a review based on the kind of knowledge , 2009, J. Intell. Manuf..

[24]  Dazhong Wu,et al.  Deep learning for smart manufacturing: Methods and applications , 2018, Journal of Manufacturing Systems.

[25]  K. Jing,et al.  Time Prediction Model for Pipeline Leakage Based on Grey Relational Analysis , 2012 .

[26]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[27]  Bogdan Gabrys,et al.  Data-driven Soft Sensors in the process industry , 2009, Comput. Chem. Eng..

[28]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[29]  Fei Tao,et al.  Digital Twin and Big Data Towards Smart Manufacturing and Industry 4.0: 360 Degree Comparison , 2018, IEEE Access.

[30]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..