Big Data Driven Real-time Energy Efficiency Analysis Method of Discrete Manufacturing Workshops
-
摘要: 为实现生产过程的节能减排,提出一种大数据驱动的离散制造车间实时能效分析方法。首先,从能耗数据与工艺数据两个方面构建了制造数据封装模型,以实现制造大数据的采集与存储;其次,通过数据聚类与数据关联分析,建立了制造大数据分析方法,实现了能耗数据的特征提取及其与工艺数据的关联融合,并据此建立了离散制造车间多层次实时能效分析指标。该方法将大数据处理与制造车间能效分析相结合,通过能耗数据的挖掘分析与可视化展示,为智能车间的节能控制提供了决策依据。Abstract: In order to realize the energy saving and emission reduction in the production process, a big data-driven real-time energy efficiency analysis method of discrete manufacturing workshops was proposed in this paper. Firstly, the manufacturing data models which include energy data and process data were constructed to realize their acquisition and storage. Then, through data clustering and data correlation analysis, a manufacturing big data analysis method was established to realize the feature extraction of energy consumption data and their association with process data. Finally, multi-level real-time energy efficiency analysis index of discrete manufacturing workshops was provided. This method combines big data processing with energy efficiency analysis of manufacturing workshop, and provides a decision basis for energy saving control of intelligent workshop by analyzing and visualizing energy consumption data.
-
Key words:
- big data /
- energy efficiency analysis /
- discrete manufacturing workshop /
- data association /
- model /
- method
-
表 1 制造车间多层次能效分析指标
分析层次 分析指标 计算方法 单台机床 能耗利用率 等待能耗比率 加工能效 单个工件 能耗利用率 等待能耗比率 生产能效 经济能效 整个车间 能耗利用率 经济能效 注:Vk为第k道工序的材料切除体积; MTEk为第k道工序的总能耗; WECi为第i个工件的总能耗; Qi为第i个工件的加工数量; Pi为第i个工件的单位收益; WSEC为车间总体能耗。 表 2 所加工蜗杆的具体参数
参数 蜗杆1 蜗杆2 蜗杆3 蜗杆头数 2 2 2 模数/mm 8 6.3 9 分度圆直径/mm 72 63 81 分度圆导程角/(°) 12.53 11.31 12.53 蜗杆材料 20Cr 45钢 20Cr 利润/元 45 36 51 生产率/(根/时) 8 11 6 表 3 能耗大数据特征提取算法的测试结果
编号 样本数据量 平均计算时间/s 平均精度/% 1 2 170 0.014 99.7 2 4 730 0.039 98.9 3 9 210 0.092 98.5 -
[1] Liu N, Zhang Y F, Lu W F. A hybrid approach to energy consumption modelling based on cutting power:a milling case[J]. Journal of Cleaner Production, 2015, 104:264-272 doi: 10.1016/j.jclepro.2015.05.049 [2] Peng T, Xu X, Wang L H. A novel energy demand modelling approach for CNC machining based on function blocks[J]. Journal of Manufacturing Systems, 2014, 33(1):196-208 doi: 10.1016/j.jmsy.2013.12.004 [3] Ciceri N D, Gutowski T G, Garetti M. A tool to estimate materials and manufacturing energy for a product[C]//Proceedings of the 2010 IEEE International Symposium on Sustainable Systems and Technology. Arlington: IEEE, 2010: 1-6 [4] Wang Q L, Liu F, Li C B. An integrated method for assessing the energy efficiency of machining workshop[J]. Journal of Cleaner Production, 2013, 52:122-133 doi: 10.1016/j.jclepro.2013.03.020 [5] Chen X Z, Li C B, Tang Y, et al. An Internet of Things based energy efficiency monitoring and management system for machining workshop[J]. Journal of Cleaner Production, 2018, 199:957-968 doi: 10.1016/j.jclepro.2018.07.211 [6] Wang W B, Yang H D, Zhang Y F, et al. IoT-enabled real-time energy efficiency optimisation method for energy-intensive manufacturing enterprises[J]. International Journal of Computer Integrated Manufacturing, 2018, 31(4-5):362-379 doi: 10.1080/0951192X.2017.1337929 [7] Xu X Y, Hua Q S. Industrial big data analysis in smart factory:current status and research strategies[J]. IEEE Access, 2017, 5:17543-17551 doi: 10.1109/ACCESS.2017.2741105 [8] Zhong R Y, Huang G Q, Lan S L, et al. A big data approach for logistics trajectory discovery from RFID-enabled production data[J]. International Journal of Production Economics, 2015, 165:260-272 doi: 10.1016/j.ijpe.2015.02.014 [9] Ren S, Zhang Y F, Liu Y, et al. A comprehensive review of big data analytics throughout product lifecycle to support sustainable smart manufacturing:A framework, challenges and future research directions[J]. Journal of Cleaner Production, 2019, 210:1343-1365 doi: 10.1016/j.jclepro.2018.11.025 [10] 张洁, 汪俊亮, 吕佑龙, 等.大数据驱动的智能制造[J].中国机械工程, 2019, 30(2):127-133, 158 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgjxgc201902001Zhang J, Wang J L, Lv Y L, et al. Big data driven intelligent manufacturing[J]. China Mechanical Engineering, 2019, 30(2):127-133, 158(in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgjxgc201902001 [11] Zhang Y F, Ma S Y, Yang H D, et al. A big data driven analytical framework for energy-intensive manufacturing industries[J]. Journal of Cleaner Production, 2018, 197:57-72 doi: 10.1016/j.jclepro.2018.06.170 [12] Wang S, Liang Y C, Li W D, et al. Big Data enabled Intelligent Immune System for energy efficient manufacturing management[J]. Journal of Cleaner Production, 2018, 195:507-520 doi: 10.1016/j.jclepro.2018.05.203 [13] Zhang Y F, Ma S Y, Yang H D, et al. A big data driven analytical framework for energy-intensive manufacturing industries[J]. Journal of Cleaner Production, 2018, 197:57-72 doi: 10.1016/j.jclepro.2018.06.170 [14] Zhang C Y, Jiang P Y. RFID-driven energy-efficient control approach of CNC machine tools using deep belief networks[J]. IEEE Transactions on Automation Science and Engineering, 2020, 17(1):129-141 doi: 10.1109/TASE.2019.2909043 [15] Zhang C Y, Jiang P Y. Sustainability evaluation of process planning for single CNC machine tool under the consideration of energy-efficient control strategies using random forests[J]. Sustainability, 2019, 11(11):3060 doi: 10.3390/su11113060