-
摘要: 為提高熱軋換規格首塊鋼頭部卷取溫度命中率，采用數據挖掘技術，從歷史帶鋼冷卻數據中推斷出與實際帶鋼相匹配的卷取溫度模型水冷換熱學習系數，并將其應用于模型預設定計算。首先，對冷卻特征參數進行識別，按照相對型、絕對型、相等型和策略型四種方式進行定義，并對實際帶鋼與歷史帶鋼的各項冷卻特征參數進行相似距離計算。當歷史帶鋼的總相似距離滿足要求時，將其聚類為實際帶鋼的相似卷，并考慮各相似卷的時間影響，計算相似權重值；隨后，基于相似帶鋼的頭部和尾部信息，建立由卷取溫度預報誤差、偏離學習系數回歸值懲罰項和偏離默認值懲罰項等構成的目標函數以及相應的約束條件，采用梯度下降法求解該二次規劃問題，通過三次優化逐步計算出學習系數參考值和表征學習系數與帶鋼速度及目標卷取溫度呈雙線性關系的兩個參數；最后，根據實際帶鋼的穿帶速度、目標卷取溫度等冷卻條件計算冷卻設定所需的學習系數。現場應用表明：基于十萬塊歷史帶鋼冷卻數據驅動的模型參數即時自適應設定算法可增強卷取溫度模型對帶鋼頭部冷卻的預設定能力，學習系數即時自適應設定能力隨著內存中保存的歷史帶鋼冷卻數據的多樣性和檢索出的相似卷數量的增加而提升。Abstract: To improve the coiling temperature control accuracy for change-over strip or the first coil of batch hot-rolling, data mining technology was adopted to infer the water cooling learning coefficient which is used in coiling temperature model preset for actual rolling strip from massive production data. Firstly, cooling feature parameters were recognized and defined respectively as absolute, relative, equal and tactical type. Then, the similar distance of each feature parameter between actual rolling strip and each historical rolled strip was calculated and summed. When the total similar distance of each rolled strip met the requirement, the produced strip was clustered as similar with actual rolling strip. Meanwhile, the weight value of the similar strip was calculated by considering its time effect. Secondly, based on the cooling information of the head and tail ends of each similar rolled strip, three object functions which are respectively composed of temperature predictive error and related penalty items such as a penalty deviated from regression learning coefficient and a penalty departed from the default learning coefficient were created and the corresponding constraints were also given. Gradient descent method was utilized to solve the quadratic programming problem. After three mathematical optimization calculations, a referenced learning coefficient and two parameters reflecting the relationship between the learning coefficient with rolling speed and target coiling temperature were obtained and then used to compute the learning coefficient needed in the cooling schedule calculation according to thread speed and target coiling temperature of the actual rolling strip. Application results show that the presented model’s adaptive parameter setting algorithm, based on the cooling data of 100,000 rolled strips can enhance the pre-setup ability of the coiling temperature model for strip head end. The adaptive setting ability of the learning coefficient will increase with the diversity of the strip cooling data stored in the memory and the number of similar strips retrieved.
-
Key words:
- cooling feature parameter /
- clustering /
- self-adaptation /
- parameter estimation /
- coiling temperature
-
圖 1 基于即時自適應的卷取溫度自動控制系統
Figure 1. Schematic of automatic control system for coiling temperature based on just-in-time adaptation
圖 2 熱軋帶鋼層流冷卻即時自適應位置示意
Figure 2. Schematic of the position of just-in-time adaptation segment for hot strip cooling
圖 4 卷取溫度模型水冷學習系數即時自適應優化計算流程
Figure 4. Just-in-time adaptation optimization procedure for water-cooling learning coefficient of coiling temperature model
圖 5 自變量X與因變量Y的對數呈線性關系示意
Figure 5. Schematic of linear relationship between independent variable X and logarithm of dependent variable Y
圖 6 相似帶鋼的相似距離、權值及其頭/尾部水冷學習系數
Figure 6. Similar distance and weight calculated for similar strips including its self-learning coefficients for head/tail end
圖 8 厚2.65 mm的Gr50鋼卷取溫度控制效果
Figure 8. Coiling temperature control effect of Gr50 steel grade with 2.65 mm thickness
表 1 三次優化計算采用的初值及計算結果
Table 1. Initial value and results of three optimal computation
Optimization Initial value of iterative computation Optimized calculation results x0(ζ) y0 z0 x*(ζ) y* z* Opt1 1.138 — — 1.1771 — — Opt2 ln(1.1771) 0 0 ln(1.1676) ln(1.405) ln(0.683) Opt3 ln(1.1676) — — ln(1.2117) — — 
下載: 導出CSV
表 2 卷取溫度控制精度統計結果
Table 2. Statistical result of coiling temperature control accuracy
Coil type Number of coils Rolled-strip length/km Coiling temperature control accuracy/% Control deviation/℃ Sequential coil 10278 7048.875 93.978 ±16 Change-over coil 1684 980.500 92.088 ±18 First coil 183 97.533 90.832 ±18 Total 12145 8126.908 95.134 ±20
下載: 導出CSV
259luxu-164<th id="5nh9l"></th> <strike id="5nh9l"></strike> <th id="5nh9l"><noframes id="5nh9l"><th id="5nh9l"></th> <strike id="5nh9l"></strike> <th id="5nh9l"><noframes id="5nh9l"> <th id="5nh9l"></th> <strike id="5nh9l"><noframes id="5nh9l"><span id="5nh9l"></span> <span id="5nh9l"><noframes id="5nh9l"><span id="5nh9l"></span> <strike id="5nh9l"><noframes id="5nh9l"><strike id="5nh9l"></strike> <span id="5nh9l"><noframes id="5nh9l"> <span id="5nh9l"><noframes id="5nh9l"> <span id="5nh9l"></span> <span id="5nh9l"><video id="5nh9l"></video></span> <th id="5nh9l"><noframes id="5nh9l"><th id="5nh9l"></th> -
參考文獻
[1] Li W G, Xu W S, Ma W, et al. Optimization for steel grade family of model based on measured data during hot continuous rolling. Iron Steel, 2018, 53(10): 54李維剛, 徐文勝, 馬威, 等. 基于熱連軋實測數據的模型鋼族層別優化. 鋼鐵, 2018, 53(10):54 [2] Zhang D H, Peng W, Sun J, et al. Key intelligent technologies of steel strip rolling process. J Iron Steel Res, 2019, 31(2): 174張殿華, 彭文, 孫杰, 等. 板帶軋制過程中的智能化關鍵技術. 鋼鐵研究學報, 2019, 31(2):174 [3] Li W G, Deng K, Zhao Y T, et al. Self-learning method for rolling model based on continuous surface. Iron Steel, 2017, 52(12): 61李維剛, 鄧肯, 趙云濤, 等. 基于連續曲面的軋制模型自學習方法. 鋼鐵, 2017, 52(12):61 [4] Liu X H, Zhao Q L, Huang Z Y. Prospect of artificial intelligent application in rolling. Steel Roll, 2017, 34(4): 1劉相華, 趙啟林, 黃貞益. 人工智能在軋制領域中的應用進展. 軋鋼, 2017, 34(4):1 [5] Edalatpour S, Saboonchi A, Hassanpour S. Effect of phase transformation latent heat on prediction accuracy of strip laminar cooling. J Mater Process Tech, 2011, 211: 1776 doi: 10.1016/j.jmatprotec.2011.05.027 [6] Hashimoto T, Yoshioka Y, Ohtsuka T. Model predictive control for hot strip mill cooling system //2010 IEEE International Conference on Control Applications. Yokohama, 2010: 646 [7] Xu X Q, Hao X D, Fu S L, et al. Cooling route control based on temperature observer for laminar cooling process. J Iron Steel Res, 2017, 29(1): 81徐小青, 郝曉東, 傅松林, 等. 基于溫度觀測器的層流冷卻路徑控制. 鋼鐵研究學報, 2017, 29(1):81 [8] Song Y, Jing F W, Yin S, et al. High-precision coiling temperature control model for heavy gauge strip steel. Chin J Eng, 2015, 37(1): 106宋勇, 荊豐偉, 殷實, 等. 厚規格熱軋帶鋼高精度卷取溫度控制模型. 工程科學學報, 2015, 37(1):106 [9] Schlang M, Lang B, Poppe T, et al. Current and future development in neural computation in steel processing. Control Eng Pract, 2001, 9(9): 975 doi: 10.1016/S0967-0661(01)00086-7 [10] Han B, Peng L G, Wang G D, et al. Calculation of basic heat-flux density for hot strip laminar cooling system using artificial neural networks. Iron Steel, 2004, 39(3): 29 doi: 10.3321/j.issn:0449-749X.2004.03.008韓斌, 彭良貴, 王國棟, 等. 基于神經網絡的熱帶層流基本熱流密度的計算. 鋼鐵, 2004, 39(3):29 doi: 10.3321/j.issn:0449-749X.2004.03.008 [11] Sun T J, Yang W D, Cheng Y M, et al. Study on multi-objective optimization strategy of strip steel laminar-cooling system. Control Eng China, 2016, 23(1): 117孫鐵軍, 楊衛東, 程艷明, 等. 帶鋼層流冷卻系統多目標優化策略的研究. 控制工程, 2016, 23(1):117 [12] Jeong S Y, Lee M, Lee S Y, et al. Improving lookup table control of a hot coil strip process with online retrained RBF network. IEEE Trans Ind Electron, 2000, 47(3): 679 doi: 10.1109/41.847908 [13] Fan X M, Zhang L, Cai X H, et al. Hot strip coiling temperature control based on CMAC network. J Northeast Univ Nat Sci, 2000, 21(6): 662范曉明, 張利, 蔡曉輝, 等. 小腦模型連接控制(CMAC)網絡用于熱軋帶鋼卷取溫度控制. 東北大學學報: 自然科學版, 2000, 21(6):662 [14] Sun T J, Yang W D, Cheng Y M, et al. Improved genetic algorithm for optimizing prediction model of strip coiling temperature. Control Theory Appl, 2015, 32(8): 1106 doi: 10.7641/CTA.2015.50041孫鐵軍, 楊衛東, 程艷明, 等. 用改進遺傳算法優化的帶鋼卷取溫度預報模型. 控制理論與應用, 2015, 32(8):1106 doi: 10.7641/CTA.2015.50041 [15] Pian J X, Zhu Y L. A hybrid soft sensor for measuring hot-rolled strip temperature in the laminar cooling process. Neurocomputing, 2015, 169: 457 doi: 10.1016/j.neucom.2014.09.089 [16] Sato Y, Izui K, Yamada T, et al. Data mining based on clustering and association rule analysis for knowledge discovery in multi-objective topology optimization. Expert Syst Appl, 2019, 119: 247 doi: 10.1016/j.eswa.2018.10.047 [17] He A R, Shao J, Sun W Q, et al. Key precise control technologies of rolling for smart manufacturing. Metall Ind Autom, 2016, 40(5): 1何安瑞, 邵健, 孫文權, 等. 適應智能制造的軋制精準控制關鍵技術. 冶金自動化, 2016, 40(5):1 -
點擊查看大圖
計量
- 文章訪問數: 1728
- HTML全文瀏覽量: 2082
- PDF下載量: 57
- 被引次數: 0
