- ISSN 0258-2724
- CN 51-1277/U
- EI Compendex
- Scopus
- Indexed by Core Journals of China, Chinese S&T Journal Citation Reports
- Chinese S&T Journal Citation Reports
- Chinese Science Citation Database
| Citation: | ZHANG Min, YUAN Yi, LI Xianjun. Multi-stage Quality Prediction of Batch Process Based on KECA and MBA-NARX[J]. Journal of Southwest Jiaotong University, 2023, 58(3): 685-695. doi: 10.3969/j.issn.0258-2724.20200382
|
The product quality of batch process is closely related to the process characteristics or the process reaction principle. In order to solve the problems of multistage, time sequence and dynamics of batch process data, a multistage quality prediction method based on nonlinear autoregressive with exogeneous inputs (NARX) neural network is proposed. First, the batch process data are divided into stages by the K-means, and the data dimension is reduced using the kernel entropy component analysis (KECA). These works can improve the prediction efficiency of the subsequent process while ensuring the stage characteristics of the input data. Then, the NARX prediction model is constructed in each stage, and the number of hidden layer nodes of the network is optimized by using the improved bat algorithm (MBA) to realize the online quality prediction of batch processes. The penicillin simulation data is used to verify the effectiveness of the proposed method. The results show that the open-loop structure of the NARX neural network has a good prediction effect, and the data dimensionality reduction method of the KECA is more conducive to subsequent quality prediction research. MBA optimizes the number of hidden layer nodes in the network with higher efficiency and better stability. The stage division can improve the prediction performance of the batch process to a certain extent. The proposed multi-stage quality prediction model has higher prediction performance, its root means square error and the mean absolute percentage error reached 0.02 and 1.48%.
| [1] |
王普,曹彩霞,高学金. 基于扩展得分矩阵的多阶段间歇过程质量预测[J]. 高校化学工程学报,2019,33(3): 664-671. doi: 10.3969/j.issn.1003-9015.2019.03.021
WANG Pu, CAO Chaixia, GAO Xuejin. Quality prediction of multistage batch processes based on extended score matrices[J]. Journal of Chemical Engineering of Chinese Universities, 2019, 33(3): 664-671. doi: 10.3969/j.issn.1003-9015.2019.03.021
|
| [2] |
ALSHAWARGHI H, ELKAMEL A, MOSHIRI B, et al. Predictive models and detection methods applicable in water detection framework for industrial electric arc furnaces[J]. Computers & Chemical Engineering, 2019, 128(6): 285-300.
|
| [3] |
李和平. 基于核函数的间歇过程软分段建模方法研究[D]. 北京: 北京化工大学, 2015.
|
| [4] |
王新普,周想凌,邢杰,等. 一种基于改进灰色BP神经网络组合的光伏出力预测方法[J]. 电力系统保护与控制,2016,44(18): 81-87. doi: 10.7667/PSPC151675
WANG Xinpu, ZHOU Xiangling, XING Jie, et al. A prediction method of PV output power based on the combination of improved grey back propagation neural network[J]. Power System Protection and Control, 2016, 44(18): 81-87. doi: 10.7667/PSPC151675
|
| [5] |
HUANG Y S, HU J J, LIU H, LIU S J. Research on price forecasting method of China's carbon trading market based on PSO-RBF algorithm[J]. Systems Science & Control Engineering, 2019, 7(2): 40-47.
|
| [6] |
李应求,安勃,李恒通. 基于NARX及混沌支持向量机的短期风速预测[J]. 电力系统保护与控制,2019,47(23): 65-73.
LI Yingqiu, AN Bo, LI Hengtong. Short-term wind speed prediction based on NARX and chaos-support vector machine[J]. Power System Protection and Control, 2019, 47(23): 65-73.
|
| [7] |
庞学苗. 基于人工神经网络的轮轨力预测[D]. 南京: 南京理工大学, 2012.
|
| [8] |
吴启蒙,魏明,庞雷. 基于NARX神经网络的电子电路电磁脉冲响应建模[J]. 高压电器,2013,49(11): 62-68.
WU Qimeng, WEI Ming, PANG Lei. Modelling electromagnetic pulse response of electronic circuits based on NARX neural network[J]. High Voltage Apparatus, 2013, 49(11): 62-68.
|
| [9] |
MAHDI S, MOHAMMAD B. Real-time estimation of break sizes during LOCA in nuclear power plants using NARX neural network[J]. Nuclear Engineering and Technology, 2019, 51(1): 702-708.
|
| [10] |
CARLOS A, JUAN P, MARTI N, et al. Recurrent neural network model with Bayesian training and mutual information for response prediction of large buildings[J]. Engineering Structures, 2019, 178(1): 603-615.
|
| [11] |
焦博隆,钟志贤,刘翊馨,等. 基于蝙蝠算法优化的变分模态分解的转子裂纹检测方法[J]. 振动与冲击,2020,39(6): 98-103.
JIAO Bolong, ZHONG Zhixian, LIU Yuxin, et al. Rotor crack detection method based on variational mode decomposition based on optimization parameters of bat algorithm[J]. Journal of Vibration and Shock, 2020, 39(6): 98-103.
|
| [12] |
王仲,顾煜炯,韩旭东,等. 基于历史数据聚类的火电机组工况划分[J]. 仪器仪表学报,2019,40(2): 90-95.
WANG Zhong, GU Yujiong, HAN Xudong, et al. Operating condition classification of thermal power unit based on historical data clustering[J]. Chinese Journal of Scientific Instrument, 2019, 40(2): 90-95.
|
| [13] |
张朝龙,何怡刚,袁莉芬,等. 基于核熵成分分析的模拟电路早期故障诊断方法[J]. 仪器仪表学报,2015,36(3): 675-684.
ZHANG Chaolong, HE Yigang, YUAN Lifeng, et al. Approach for analog circuit incipient fault diagnosis based on KECA[J]. Chinese Journal of Scientific Instrument, 2015, 36(3): 675-684.
|
| [14] |
惠永永,赵小强. 基于WICA-WGNPE的高斯-非高斯联合指标间歇过程监控[J]. 仪器仪表学报,2018,39(1): 190-199.
HUI Yongyong, ZHAO Xiaoqiang. Batch process monitoring with Gaussian and non-Gaussian joint indicator based on WICA-WGNPE[J]. Chinese Journal of Scientific Instrument, 2018, 39(1): 190-199.
|
| [15] |
WANG H, JIN H, WANG J, et al. Optimization approach for multi-scale segmentation of remotely sensed imagery under k-means clustering guidance[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(5): 526-532.
|
Figures(10) / Tables(6)
DownLoad:
