| 引用本文: | 曹雷,董梓硕,李晓华,李旭,张殿华.数据驱动与机理耦合的冷轧电机功率智能预测方法[J].哈尔滨工业大学学报,2024,56(5):28.DOI:10.11918/202206124 |
| CAO Lei,DONG Zishuo,LI Xiaohua,LI Xu,ZHANG Dianhua.Intelligent prediction method for cold rolling motor power based on data-driven and mechanism coupling[J].Journal of Harbin Institute of Technology,2024,56(5):28.DOI:10.11918/202206124 |
|
| 摘要: |
| 电机功率计算在保证生产安全、制定轧制规程以及发挥设备能力等方面起到了重要作用。为提高计算精度,本文提出一种机理模型与数据驱动方法相结合的电机功率预测模型。首先,机理模型部分采用上界法得到解析解,然后将部分功率解析解（塑性变形功率、张力功率和剪切功率）与相关变量输入长短时记忆（long short-term memory, LSTM）网络中训练,以提取变量数据之间的深度特征和时序相关性。结果表明:本文提出的时序耦合预测模型相对误差不超过±3.9%,且在相邻卷带钢轧制规程变化较大时,预测效果明显优于上界法和人工神经网络（artificial neural networks, ANN）；从残差分布直方图中可以看到,上界法由于遗漏了摩擦系数和损失功率与其他参数间的强耦合关系,导致残差集中在±50 kW附近且不符合正态分布,而ANN和本模型均基本遵循正态分布,但本模型拟合精度更高；对比更广泛的模型评估指标,本模型具有更好的综合预测性能。此外,通过模型输出结果分析了电机功率与轧制长度、轧制速度之间的关系,表明本模型除具有高预测精度外,还与已知的参数间物理规律有较强一致性。 |
| 关键词: 冷轧 电机功率 长短时记忆网络 工业大数据 上界法 数学模型 |
| DOI：10.11918/202206124 |
| 分类号:TG335.5 |
| 文献标识码:A |
| 基金项目:国家自然科学基金(U20A20187)；辽宁省“兴辽英才计划”资助(XLYC2007087)；中央高校基本科研业务费资助(N2107010) |
|
| Intelligent prediction method for cold rolling motor power based on data-driven and mechanism coupling |
|
CAO Lei,DONG Zishuo,LI Xiaohua,LI Xu,ZHANG Dianhua
|
|
（State Key Laboratory of Rolling and Automation (Northeastern University), Shenyang 110819, China）
|
| Abstract: |
| Motor power calculation plays an important role in ensuring production safety, formulating rolling schedule, and leveraging equipment capabilities. In order to improve calculation accuracy, a motor power prediction model combining mechanism model and data-driven method was proposed. The mechanism model was analytically solved by upper bound method, and then parts of the power analytical solutions (plastic deformation power, tension power, and shear power) and related variables were input into long short-term memory (LSTM) network for training, so as to extract depth characteristics and temporal correlations between variable data. Results show that the relative error of the proposed time series coupling prediction model was less than ±3.9%, and the prediction effect was obviously better than that of the upper bound method and artificial neural network (ANN) when the rolling schedule of adjacent strips changed greatly. According to the residual distribution histogram, the residual of upper bound method was concentrated around ±50 kW and deviating from a normal distribution, as it ignored the strong relationship between friction coefficient, loss power, and other parameters. Both ANN and the proposed model basically followed normal distribution, but the proposed model had higher fitting accuracy. In comparison with broader model evaluation indicators, the proposed model had better comprehensive prediction performance. Besides, the relationship between motor power, rolling length, and rolling speed was analyzed based on model output results, which indicated that the model not only has high prediction accuracy, but also strong consistency with known physical law between parameters. |
| Key words: cold rolling motor power long short-term memory industrial big data upper bound method mathematical model |
