锻压技术

基于ARIMA模型的压力机打击能量精准控制与预测的研究与应用

英文标题：Research and application on accurate control and prediction for press strike energy based on ARIMA model

作者：黄达力孙勇徐超凌云汉邓盛彪

分类号：TP23

出版年,卷(期):页码：2021,46(3):174-179

摘要：

针对某型号80 MN电动螺旋压力机实际生产过程中打击能量设定值与实际值误差较大，导致能耗增高、影响设备寿命的现象，提出了一种打击能量的优化计算方法。在对该压力机进行系统结构分析与运行原理分析之后，在原有打击能量计算公式的前提下，综合考虑滑块自重、能量衰减等因素，针对不同使用情况，得到优化后的打击能量计算公式。并利用ARIMA模型，对公式中的关键参数——能量衰减系数进行准确的短期预测。结果表明：经过优化后的打击能量计算公式，显著减小了设定值与实际值的误差，实现了降低设备能耗、延长设备使用寿命的目的。

In the actual production process for a certain type of 80 MN electric screw press, there is a large error between setting and actual values of strike energy, which leads to the increasing of energy consumption and affects the life of equipment. Therefore, an optimized calculation method for the strike energy was proposed. After analyzing the system structure and the operating principle of this press, under the premise for the original calculation formula of the strike energy, comprehensively considering the slider weight, energy attenuation and other factors, the optimized calculation formula of the strike energy was obtained for different usage conditions, and the key parameter in the formula of energy attenuation coefficient was accurately predicted in the short term by ARIMA model. The results show that the optimized calculation method for the strike energy greatly reduces the error between the setting and actual values and realizes the purpose of reducing the energy consumption and increasing the service life of equipment.

基金项目：

国家科技重大专项（2018ZX04044-001）

黄达力（1996-），男，硕士研究生 E-mail：18256002511@163.com 通讯作者：孙勇（1971-），男，博士，研究员 E-mail：sun_yong_89@163.com

参考文献：

[1]冯仪. 数控电动螺旋压力机控制与检测技术研究[D].武汉：华中科技大学,2009.

Feng Y. Research on Control and Testing Technology of CNC Electric Screw Press[D]. Wuhan: Huazhong University of Science and Technology,2009.

[2]朱元胜, 栾翼展, 朱冠宇. 万吨电动螺旋压力机的研究及应用[J].锻压装备与制造技术,2014,49(1):37-39.

Zhu Y S, Luan Y Z, Zhu G Y. Research and application of ton-ton electric swing press[J]. China Metalforming Equipment & Manufacturing Technology,2014,49(1):37-39.

[3]李军超. 数控电动螺旋压力机控制关键技术研究[D].武汉：华中科技大学,2008.

Li J C. Research on Control Key Technology of CNC Electric Screw Press [D]. Wuhan: Huazhong University of Technology,2008.

[4]何晰浩,李金龙,郝占武, 等.基于ARIMA模型的制动摩擦衬片磨损预测[J].汽车文摘,2020,(12):39-42.

He X H, Li J L, Hao Z W, et al. Wear prediction of braking friction lining based on ARIMA model[J]. Automotive Abstracts,2020,(12):39-42.

[5]林思睿. 机场出租车运力需求预测技术研究[D].成都：电子科技大学,2018.

Lin S R. Research on Forecasting Technology of Airport Taxi Transport Demand [D]. Chengdu: University of Electronic Science and Technology of China,2018.

[6]汤岩. 时间序列分析的研究与应用[D].哈尔滨：东北农业大学,2007.

Tang Y. Research and Application of Time Series Analysis [D]. Harbin: Northeast Agricultural University,2007.

[7]王鹏,徐圣法,刘杰强,等.基于ARIMA模型的环境监测系统设计与实现[J].计算机测量与控制,2020,28(11):27-31,36.

Wang P, Xu S F, Liu J Q,et al. Design and implementation of environmental monitoring system based on ARIMA model [J]. Computer Measurement and Control,2020,28(11):27-31,36.

[8]Pagach D P, Warr R S. Analysts versus time-series forecasts of quarterly earnings: A maintained hypothesis revisited[J]. Advances in Accounting,2020,51(11): 100497.

[9]文豪,陈昊.基于LSTM循环神经网络的税收预测[J].计算机科学,2020,47(S2):437-443.

Wen H, Chen H. Tax forecasting based on LSTM cyclic neural network[J]. Computer Science,2020,47(S2):437-443.

[10]翟静,曹俊.基于时间序列ARIMA与BP神经网络的组合预测模型[J].统计与决策,2016,(4):29-32.

Cui J, Cao J. Combination prediction model based on time series ARIMA and BP neural network[J]. Statistics and Decision,2016, (4):29-32.

[11]Belmahdi B, Louzazni M, Bouardi A E. A hybrid ARIMA-ANN method to forecast daily global solar radiation in three different cities in Morocco[J]. European Physical Journal Plus,2020,135(11):925.

[12]Ahzam S, Shamshad A, Saif S. Spatial forecasting of solar radiation using ARIMA model[J]. Remote Sensing Applications: Society and Environment,2020,20：100427.

服务与反馈：

【文章下载】【加入收藏】