数据与模型混合驱动的箱体零件加工能耗预测  

A Data and Model Hybrid Driven Method for Machining Energy Consumption Prediction of Boxy Parts

作　　者：张华[1,2] 李曙光 鄢威 江志刚[1,5] 朱硕[1,5] 马峰[1,3] ZHANG Hua;LI Shuguang;YAN Wei;JIANG Zhigang;ZHU Shuo;MA Feng(Key Laboratory of Metallurgical Equipment and Control Technology,Ministry of Education,Wuhan University of Science and Technology,Wuhan 430081;Academy of Green Manufacturing Engineering,Wuhan University of Science and Technology,Wuhan 430081;Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering,Wuhan University of Science and Technology,Wuhan 430081;School of Automotive and Traffic Engineering,Wuhan University of Science and Technology,Wuhan 430081;Precision Manufacturing Institute,Wuhan University of Science and Technology,Wuhan 430081)

机构地区：[1]武汉科技大学冶金装备及控制教育部重点实验室,武汉430081 [2]武汉科技大学绿色制造工程研究院,武汉430081 [3]武汉科技大学机械传动与制造工程湖北省重点实验室,武汉430081 [4]武汉科技大学汽车与交通工程学院,武汉430081 [5]武汉科技大学精密制造研究院,武汉430081

出　　处：《机械工程学报》2023年第12期97-108,共12页Journal of Mechanical Engineering

基　　金：国家自然科学基金(51975432,51775392);武汉科技大学机械传动与制造工程湖北省重点实验室开放基金(MTMEOF2019B06)资助项目。

摘　　要：箱体零件是机械产品与部件的载体和安装基础件,其制造过程耗费大量的资源和能源。加工能耗预测作为能效评估与优化的前置技术,具有积极的意义。然而,由于箱体零件往往具有复杂的加工特征,且特征间耦合关系复杂,导致现有基于加工特征的方法难以准确预测其加工能耗。基于此,提出一种数据与模型混合驱动的箱体零件加工能耗预测方法。首先,基于箱体零件结构组成,对其加工特征及其间耦合关系、以及加工能耗特性进行分析;其次,针对箱体零件加工特征的相交与非相交关系,分别构建数据驱动的非相交特征加工能耗预测模型与模型驱动的相交特征加工能耗预测模型,进而实现箱体零件加工能耗的准确预测;最后,以某箱体零件加工为例对所提方法的有效性进行验证,并通过与纯数据驱动和纯模型驱动能耗预测方法的横向对比,说明所提方法的优越性。Boxy parts are the carrier and installation base of mechanical products and components,and their manufacturing process consumes a lot of resources and energy.As a leading technology for energy efficiency assessment and optimization,it is of great significance to predict the energy consumption in machining process.However,due to the various features and their complicated relationship of boxy parts,it is difficult to predict the machining energy consumption accurately.In order to fill this gap,a data and model hybrid driven method for machining energy consumption prediction of boxy parts is proposed.Firstly,the structure of boxy parts is analyzed,on this basis,the machining energy consumption characteristics of machining features and their coupling relationship are analyzed.Then,according to the intersecting and non-intersecting relationship of boxy parts,in order to realize the machining energy consumption prediction of boxy parts,a data-driven energy consumption prediction model for non-intersecting feature and a model-driven energy consumption prediction model for intersecting feature are established respectively.Finally,the validity of the proposed model and method are verified by an example of machining a boxy part,at the same time,compared with the energy consumption prediction method of pure data-driven and pure model-driven,the superiority of the proposed method is illustrated.

关 键 词：箱体零件 能耗预测 数据与模型混合驱动 特征 特征耦合 

分 类 号：TG501[金属学及工艺—金属切削加工及机床]