|
|
Soft Measurement Method for Cement Clinker fCaO Based on Time Series Single-dimensional Convolutional Neural Network |
ZHAO Yan-tao,HE Yong-qiang,JIA Li-ying,YANG Li-ming,HAO Xiao-chen |
Institute of Electrical Engineering, Yanshan University, Qinhuangdao, Hebei 066004, China |
|
|
Abstract The content of free calcium oxide (fCaO) in cement clinker has an important impact on cement quality and production energy consumption.At this stage, the fCaO content of cement clinker is measured offline by chemical analysis method, but this method has obvious hysteresis for the operation guidance of the production process.Aiming at the problem that clinker fCaO could not be monitored online, a soft measurement modeling method of clinker fCaO based on multi-variable time series single-dimensional convolutional neural network (TS-CNN) was proposed.The time series of a certain historical time period that affects multiple variables of clinker fCaO was used as the models input, and the cement data was combined to extract the characteristics of each variable by using single-dimensional convolution pooling method to reduce the complexity of the network, and finally the extracted local information was integrated by the fully connected layer.Through the experimental comparison, the results show that the soft measurement method based on TS-CNN has higher prediction accuracy and more generalization ability.
|
Received: 30 August 2018
Published: 28 August 2020
|
|
Fund:Foundation of Hebei Educational Committee. |
|
|
|
[1]Nawaz A, Julnipitawong P, Krammart P, et al. Effect and limitation of free lime content in cement-fly ash mixtures[J]. Construction & Building Materials, 2016, 102: 515-530.
[2]刘彬,赵朋程,高伟, 等. 基于粒子群算法与连续型深度信念网络的水泥熟料游离氧化钙预测[J]. 计量学报, 2018, 39(3): 420-424.
Liu B, Zhao P C, Gao W, et al. Prediction of Cement fCaO Based on Particle Swarm Optimization and Continuous Deep Belief Network[J]. Acta Metrologica Sinica, 2018, 39(3): 420-424.
[3]Yang K, Jin H, Chen X, et al. Soft sensor development for online quality prediction of industrial batch rubber mixing process using ensemble just-in-time Gaussian process regression models[J]. Chemometrics & Intelli-gent Laboratory Systems, 2016, 155(7):170-182.
[4]Jin H, Chen X, Yang J, et al. Multi-model adaptive soft sensor modeling method using local learning and online support vector regression for nonlinear time-variant batch processes[J]. Chemical Engineering Science, 2015, 131(7): 282-303.
[5]Yuan X, Ye L, Bao L, et al. Nonlinear feature extraction for soft sensor modeling based on weighted probabilistic PCA[J]. Chemometrics & Intelligent Laboratory Systems, 2015, 147(10): 167-175.
[6]Yu Q, He J J. Temperature Soft Sensor Method for Molded Aging Ovens[J]. Information & Control, 2017, 46(3): 328-334.
[7]赵彦涛, 单泽宇, 常跃进, 等. 基于MI-LSSVM的水泥生料细度软测量建模[J]. 仪器仪表学报, 2017, 38(2): 487-496.
Zhao Y T, Shan Z Y, Chang Y J, et al. Soft sensor modeling for cement fineness based on least squares support vector machine and mutual information[J]. Chinese Journal of Scientific Instrument, 2017, 38(2): 487-496.
[8]He Y L, Geng Z Q, Zhu Q X. Data driven soft sensor development for complex chemical processes using extre-me learning machine[J]. Chemical Engineering Research & Design, 2015, 102(10): 1-11.
[9]Fernandez d C J, Del Saz-Orozco P, Baratti R, et al. Soft-sensing estimation of plant effluent concentrations in a biological wastewater treatment plant using an optimal neural network[J]. Expert Systems with Applications, 2016, 63(C): 8-19.
[10]Shang C, Huang X, Suykens J A K, et al. Enhancing dynamic soft sensors based on DPLS: A temporal smoo-thness regularization approach[J]. Journal of Process Control, 2015, 28(4): 17-26.
[11]Lv Y, Yang T, Liu J. An adaptive least squares support vector machine model with a novel update for NOx emission prediction[J]. Chemometrics & Intelligent Laboratory Systems, 2015, 145(7): 103-113.
[12]Ahmed F, Cho H J, Jin K K, et al.
A real-time model based on least squares support vector machines and output bias update for the prediction of NOx emission from coal-fired power plant[J]. Korean Journal of Chemical Engineering, 2015, 32(6): 1029-1036.
[13]赵朋程, 刘彬, 高伟, 等. 用于水泥熟料fCaO预测的多核最小二乘支持向量机模型[J]. 化工学报, 2016, 67(6): 2480-2487.
Zhao P C, Liu B, Gao W, et al. Multiple kernel least square support vector machine model for prediction of cement clinker lime content[J]. CIESC Jorunal, 2016, 67(6): 2480-2487.
[14]王秀莲, 孙旭晨. 基于局部PSO-LSSVM的水泥fCaO测量方法研究[J]. 控制工程, 2014, 21(6): 807-811.
Wang X L, Sun X C. Measurement Method Research for Cement fCaO Based on Local PSO-LSSVM[J]. Control Engineering of China, 2014, 21(6): 807-811.
[15]蒋妍妍, 李洪林. 基于改进粒子群优化LSSVM的水泥熟料fCaO软测量[J]. 现代化工, 2014, 34(6): 152-155.
Jiang Y Y, Li H L. Soft measurement of cement clinker fCaO by improved particle swarm optimization based LSSVM[J]. Modern Chemical Industry, 2014, 34(6): 152-155.
[16]赵朋程, 刘彬, 孙超, 等. 基于IQPSO优化ELM的熟料质量指标软测量研究[J]. 仪器仪表学报, 2016, 37(10): 2243-2250.
Zhao P C, Liu B, Sun C, et al. Soft sensor for cement clinker quality indicator based on IQPSO optimize ELM[J]. Chinese Journal of Scientific Instrument, 2016, 37(10): 2243-2250.
[17]Li W, Wang D, Chai T. Multisource Data Ensemble Modeling for Clinker Free Lime Content Estimate in Rotary Kiln Sintering Processes[J]. IEEE Transactions on Systems Man & Cybernetics Systems, 2017, 45(2): 303-314.
[18]Shang C, Yang F, Huang D, et al. Data-driven soft sensor development based on deep learning technique[J]. Journal of Process Control, 2014, 24(3): 223-233.
[19]Liu Y, Fan Y, Chen J. Flame Images for Oxygen Content Prediction of Combustion Systems Using DBN[J]. Energy & Fuels, 2017, 31(8):8776-8783.
[20]Yan W, Tang D, Lin Y. A Data-Driven Soft Sensor Modeling Method Based on Deep Learning and its Application[J]. IEEE Transactions on Industrial Electr-onics, 2017, 64(5):4237-4245.
[21]Qiu Y, Liu Y, Huang D. Date-Driven Soft-Sensor Design for Biological Wastewater Treatment Using Deep Neural Networks and Genetic Algorithms[J]. Journal of Chemical Engineering of Japan, 2016, 49(10): 925-936.
[22]Yann L C, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Procee-dings of the IEEE 1998, 86(11): 2278-2324.
[23]Yann L C, Boser B, Denker J S, et al. Backpropagation Applied to Handwritten Zip Code Recognition[J]. Neural Computation, 2014,1(4): 541-551.
[24]程淑红,张仕军,赵考鹏. 基于卷积神经网络的生物式水质监测方法[J]. 计量学报, 2019, 40(4): 721-727.
Cheng S H, Zhang S J, Zhao K P. Biological Water Quality Monitoring Method Based on Convolution Neural Network[J]. Acta Metrologica Sinica, 2019, 40(4): 721-727.
[25]Hinton G E.Deep belief networks[J]. Scholarpedia, 2009, 4(6): 786-804.
[26]Tivive F H C, Bouzerdoum A. A new class of convolutional neural networks (SICoNNets) and their application of face detection[C]// IEEE. International Joint Conference on Neural Networks. Portland, Oregon, USA,2003: 2157-2162.
[27]Ciresan D, Meier U, Masci J, et al. A committee of neural networks for traffic sign classification[C]//IEEE. International Joint Conference on Neural Networks. Dallas, Texas, USA, 2013: 1918-1921.
[28]Swietojanski P, Ghoshal A, Renals S. Convolutional Neural Networks for Distant Speech Recognition[J]. IEEE Signal Processing Letters, 2014, 21(9): 1120-1124.
[29]张浩, 刘振娟, 李宏光, 等. 基于关联变量时滞分析卷积神经网络的生产过程时间序列预测方法[J]. 化工学报, 2017, 68(9): 3501-3510.
Zhang H, Liu Z J, Li H G, et al. Process time series prediction based on application of correlated process variables to CNN time delayed analyses[J]. CIESC Jorunal, 2017, 68(9): 3501-3510.
[30]段友祥, 李根田, 孙歧峰. 卷积神经网络在储层预测中的应用研究[J]. 通信学报, 2016, 37(Z1): 1-9.
Duan Y X, Li G T, Sun Q F. Research on convolutional neural network for reservoir parameter prediction[J]. Journal on Communications, 2016, 37(Z1): 1-9.
[31]李海涛. 新型干法水泥生产技术与设备[M]. 北京: 化学工业出版社, 2013.
[32]Qiao J, Chai T, Wang H. Intelligent Setting Control for Clinker Calcination Process[J]. Asian Journal of Control, 2014, 16(1): 243-263.
[33]Yoo H J. Deep Convolution Neural Networks in Computer Vision[J]. IEIE Transactions on Smart Proc-essing & Computing, 2015, 4(1): 35-43.
[35]Zhang R, Shen F, Zhao J. A model with Fuzzy Granulation and Deep Belief Networks for exchange rate forecasting[C]// IEEE. International Joint Conference on Neural Networks. Beijing, China,2014: 366-373. |
|
|
|