基于改进神经网络和Fluent的气液固技术的内表面处理

doi:10.13229/j.cnki.jdxbgxb.20230025

摘要/Abstract

摘要：

针对目前航空、航天工件内孔表面有凸起毛刺且不容易去除的问题，提出一种气液固多相流技术方法。基于Fluent数值分析对多相流下的不同气体压力、水流速度和磨粒浓度参数进行流体仿真，得到影响加工的近壁区内表面处的磨粒速度、相对压力及磨粒体积分数参数，采用MATLAB软件利用BP神经网络对各参数进行拟合，通过BP预测模型再运用PSO（粒子群算法）在支配解集中求解满足约束数学模型的气液固三相流最优输入值，基于最优输入值搭建试验平台并设计L₉（3³）正交试验对工件内表面进行加工，最后通过白光干涉仪测量加工前后的内孔表面精度，验证了仿真最优参数与试验加工最优参数的一致性，运用最优参数值下的气液固流体对工件内表面加工，经测量显示，内表面精度提高了75%，满足航空航天工件的应用要求。

关键词: 机械制造工艺与设备, 气液固技术, 流体仿真, 神经网络, 粒子群算法, 正交试验

Abstract:

At present， the manufacturing methods of complex multi-bore workpieces in aviation and aerospace often have raised burrs on the inner bore surface of the workpieces， which are not easy to remove. In view of this situation， a gas-liquid-solid multiphase flow technology is proposed to treat the inner surface of complex workpieces. Based on fluent numerical analysis， different gas pressure， water velocity and abrasive particle concentration parameters under multiphase flow are simulated. The parameters of abrasive particle velocity， relative pressure and abrasive particle volume fraction at the inner surface of the near-wall area which affect the machining are obtained. The parameters are fitted by using BP neural network with MATLAB software， and the optimal input value of gas-liquid-solid three-phase flow satisfying the constraint mathematical model is solved by using the BP prediction model and PSO （Particle Swarm Optimization） in the dominant solution set. Based on the optimal input value， an experimental platform is built and L₉（3³） orthogonal experiment is designed to machine the inner surface of the workpiece. Finally， the surface accuracy of the inner hole before and after machining is measured by a white light interferometer， which verifies the consistency between the simulation optimal parameters and the experimental optimal parameters. The inner surface of the workpiece is machined by using the gas-liquid-solid three-phase flow with the optimal parameters. The measurement shows that the inner surface accuracy is increased by 75%， which meets the application requirements of aerospace workpieces.

Key words: machinery manufacturing technology and equipment, gas-solid technology, fluid simulation, neural network, particle swarm optimization： orthogonal experiment

中图分类号:

TG664

李光保,高栋,路勇,平昊,周愿愿. 基于改进神经网络和Fluent的气液固技术的内表面处理[J]. 吉林大学学报(工学版), 2024, 54(6): 1537-1547.

Guang-bao LI,Dong GAO,Yong LU,Hao PING,Yuan-yuan ZHOU. Internal surface treatment of gas-liquid-solid technology based on improved neural network and Fluent[J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(6): 1537-1547.

图/表 21

图 1

图2

图3

图4

图5

图6

表1

图7

图8

图9

图10

图11

图12

表2

表3

表4

表5

图13

图14

图15

表6

参考文献 18

1	王杰,李爱蓉.小波包分析识别气液固三相流流型[J].石油化工,2020(1):62-69.
	Wang Jie, Li Ai-rong. Identification of gas-liquid-solid three-phase flow pattern by wavelet packet analysis[J]. Petrochemical Industry, 2020(1):62-69.
2	辛亚男,张建文,姜爱国.一种新型螺旋内槽管的气液固三相流数值模拟研究[J].计算力学学报,2018(2):238-248.
	Xin Ya-nan, Zhang Jian-wen, Jiang Ai-guo. Numerical simulation of gas-liquid-solid three-phase flow of a new type of spiral inner groove tube[J]. Journal of Computational Mechanics, 2018(2):238-248.
3	黄豆豆,计时鸣,陈国达,等.气液固三相湍流环境中气泡破裂对SiC颗粒的影响研究[J].机电工程,2017,34(9):965-970.
	Huang Dou-dou,Timing, Chen Guo-da,et al. Study on the influence of bubble burst on SiC particles in gas-liquid-solid three-phase turbulent environment[J]. Electromechanical Engineering, 2017,34(9):965-970.
4	杨建.水力空化气液固三相磨粒流抛光工具及系统研究[D].杭州:浙江工业大学机械工程学院,2019.
	Yang Jian. Study on polishing tools and systems of hydraulic cavitation gas-liquid-solid three-phase abrasive flow[D]. Hangzhou:College of Mechanical Engineering,Zhejiang University of Technology, 2019.
5	胡焰.基于气液固混合的磨料射流加工系统及实验研究[D].南京:南京航空航天大学机电学院,2019.
	Hu Yan. Abrasive jet machining system and experimental study based on gas-liquid-solid mixing[D].Nanjing: School of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, 2019.
6	李瑞光,丁宇亭,杨增辉,等.航天伺服阀阀套相交孔磨粒流工艺技术研究[J].液压气动与密封,2022,42(7):109-112.
	Li Rui-guang, Ding Yu-ting, Yang Zeng-hui,et al. Study on abrasive flow technology of intersecting hole of aerospace servo valve sleeve[J]. Hydraulic Pneumatic and Sealing, 2022,42(7):109-112.
7	计时鸣,曹慧强,赵军,等.三相磨粒流文丘里管结构空化辅助抛光机理与试验[J].农业工程学报,2018,34(16):71-79.
	Timing, Cao Hui-qiang, Zhao Jun,et al. Cavitation-assisted polishing mechanism and experiment of three-phase abrasive flow venturi tube structure[J]. Journal of Agricultural Engineering, 2018,34(16):71-79.
8	王景坡,宋超,凌洋,等.多通管接头磨粒流光整均匀性研究[J].表面技术,2022,(4):299-307.
	Wang Jing-po, Song Chao, Ling Yang,et al. Study on abrasive particle polishing uniformity of multi-port pipe joints[J]. Surface Technology, 2022(4):299-307.
9	李晓波,魏武,才冬涛,等.基于磨粒流技术的阀块内孔道光整加工[J].金属加工(冷加工),2022(3):20-24.
	Li Xiao-bo, Wei Wu, Cai Dong-tao,et al. Finishing of inner bore of valve block based on abrasive flow technology[J]. Metalworking (Cold Working), 2022(3):20-24.
10	王卫东.自激振荡脉冲空化射流喷嘴多目标优化研究[D].秦皇岛:燕山大学机械工程学院,2021.
	Wang Wei-dong. Study on multi-objective optimization of self-excited oscillation pulsed cavitation jet nozzle[D]. Qinghuangd:School of Mechanical Engineering, Yanshan University, 2021.
11	褚聪,戴勇,沈明,等.基于Fluent仿真的强约束磨粒射流抛光特性[J].表面技术,2016(6):198-204.
	Chu Cong, Dai Yong, Shen Ming,et al. The polishing characteristics of strongly constrained abrasive jet based on Fluent simulation[J]. Surface Technology, 2016(6):198-204.
12	刘江,黄晓斌,何吕,等.基于Fluent的喷油嘴倒锥孔磨粒流加工数值模拟[J].机械制造与自动化,2021,50(2):40-42, 50.
	Liu Jiang, Huang Xiao-bin, He Lyu,et al. Numerical simulation of abrasive flow machining in the inverted cone hole of fuel injector based on Fluent[J]. Machinery Manufacturing and Automation, 2021,50(2):40-42, 50.
13	李研彪,陈强,张利.钛合金薄壁曲面液态金属-磨粒流加工仿真与试验研究[J].机械工程学报,2021(23):220-231.
	Li Yan-biao, Chen Qiang, Zhang Li. Simulation and experimental study on liquid metal-abrasive flow machining of titanium alloy thin-walled curved surface[J]. Journal of Mechanical Engineering, 2021(23):220-231.
14	刘洋,李俊烨,苏宁宁,等.磨粒流抛光弯管的数值模拟与试验优化[J].机械设计与制造,2021(7):137-140.
	Liu Yang, Li Jun-ye, Su Ning-ning,et al. Numerical simulation and experimental optimization of abrasive flow polishing bend[J]. Mechanical Design and Manufacturing, 2021(7):137-140.
15	计时鸣,葛江勤,谭大鹏,等.三相磨粒流抛光及其气泡溃灭分布特性[J].光学精密工程,2018(2):388-398.
	Timing, Ge Jiang-qin, Tan Da-peng,et al. Three-phase abrasive flow polishing and bubble collapse distribution characteristics[J]. Optical Precision Engineering, 2018(2):388-398.
16	姚燕生,周瑞根,张成林,等.增材制造复杂金属构件表面抛光技术[J].航空学报,2022(4):244-256.
	Yao Yan-sheng, Zhou Rui-gen, Zhang Cheng-lin,et al. Surface polishing technology of complex metal components manufactured by additives[J]. Acta Aeronautical, 2022(4):244-256.
17	李光保.基于三相流技术的零件内表面毛刺处理的系统研究[D].哈尔滨:哈尔滨工业大学机电工程学院,2019.
	Li Guang-bao. Systematic research on burr treatment of parts inner surface based on three-phase flow technology[D]. Harbin:School of Mechanical and Electrical Engineering, Harbin Institute of Technology, 2019.
18	张方东.磨料流加工工件表面粗糙度研究[J].现代制造技术与装备,2020,56(10):162-163.
	Zhang Fang-dong. Study on the surface roughness of abrasive flow machining workpiece[J]. Modern Manufacturing Technology and Equipment, 2020,56(10):162-163.

相关文章 15

[1]	黄玲,崔躜,游峰,洪佩鑫,钟浩川,曾译萱. 适用于多车交互场景的车辆轨迹预测模型[J]. 吉林大学学报(工学版), 2024, 54(5): 1188-1195.
[2]	张西广,张龙飞,马钰锡,樊银亭. 基于密度峰值的海量云数据模糊聚类算法设计[J]. 吉林大学学报(工学版), 2024, 54(5): 1401-1406.
[3]	陈涛,周志刚,雷楠南. 粒子群算法下汽车机械式自动变速系统参数多目标优化[J]. 吉林大学学报(工学版), 2024, 54(5): 1214-1220.
[4]	夏超,王梦佳,朱剑月,杨志刚. 基于分层卷积自编码器的钝体湍流流场降阶分析[J]. 吉林大学学报(工学版), 2024, 54(4): 874-882.
[5]	刘元义,于圣洁,胥备,王宪良,宋发成. 基于离散元的设施农业就地翻土犁的研究与试验[J]. 吉林大学学报(工学版), 2024, 54(4): 1153-1165.
[6]	杨国俊,齐亚辉,石秀名. 基于数字图像技术的桥梁裂缝检测综述[J]. 吉林大学学报(工学版), 2024, 54(2): 313-332.
[7]	高海龙,徐一博,刘坤,李春阳,卢晓煜. 基于多源数据融合的高速公路路网短时交通流参数实时预测[J]. 吉林大学学报(工学版), 2024, 54(1): 155-161.
[8]	李义,吕晨阳,梁继才,梁策. 不规则Y形铝型材多点拉弯成形截面变形分析[J]. 吉林大学学报(工学版), 2024, 54(1): 105-113.
[9]	李爽,林子瑞,叶松,刘旭,赵吉松. 运载火箭推力下降时入轨能力评估与轨迹重构方法[J]. 吉林大学学报(工学版), 2023, 53(8): 2245-2253.
[10]	车翔玖,徐欢,潘明阳,刘全乐. 生物医学命名实体识别的两阶段学习算法[J]. 吉林大学学报(工学版), 2023, 53(8): 2380-2387.
[11]	刘鹏举. 基于深度神经网络的物联网安全态势自动辨识算法设计[J]. 吉林大学学报(工学版), 2023, 53(7): 2121-2126.
[12]	吕锋,李念,冯壮壮,张杨航. 面向用户的个性化产品服务系统协同过滤推介方法[J]. 吉林大学学报(工学版), 2023, 53(7): 1935-1942.
[13]	李岩,张久鹏,陈子璇,黄果敬,王培. 基于PCA-PSO-SVM的沥青路面使用性能评价[J]. 吉林大学学报(工学版), 2023, 53(6): 1729-1735.
[14]	刘洋,刘吉成. 基于大数据与粒子群的清洁能源协同优化调度方法[J]. 吉林大学学报(工学版), 2023, 53(5): 1443-1448.
[15]	刘培勇,董洁,谢罗峰,朱杨洋,殷国富. 基于多支路卷积神经网络的磁瓦表面缺陷检测算法[J]. 吉林大学学报(工学版), 2023, 53(5): 1449-1457.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

序号	气相压力/MPa	液相速度/（m·s^-1）	磨粒浓度/%	壁面压力/MPa	磨粒速度/（m·s^-1）	体积分数/%	仿真均匀度/%
1	0.1	5	1	0.122	3.589	1	62
2	0.2	10	5	2.126	5.012	6	68
3	0.3	15	10	5.336	8.742	13	53
4	0.4	20	15	12.461	11.641	16	32
5	0.5	25	20	20.174	12.347	18	69

编号	气体压力/MPa	水流速度/（m·s^-1）	固相浓度/%	加工时间/min	粗糙度/μm	加工均匀度/%
1	0.4	19	9	30	0.422	31.2
2	0.5	20	9	30	0.314	25.6
3	0.6	21	9	30	0.452	30.3
4	0.6	20	10	30	0.322	24.5
5	0.5	19	10	30	0.317	24.3
6	0.4	21	10	30	0.351	28.8
7	0.4	20	11	30	0.348	29.1
8	0.5	21	11	30	0.352	28.9
9	0.6	19	11	30	0.455	32.1

水平	因素
水平	气体压力/MPa	水流速度/（m·s^-1）	磨粒浓度/%
1	0.374	0.398	0.396
2	0.327	0.328	0.33
3	0.409	0.385	0.385

水平	因素
水平	气体压力/MPa	水流速度/（m·s^-1）	磨粒浓度/%
1	29.7	29.2	29.1
2	26.2	26.4	25.8
3	28.9	29.3	30.1

测量位置		粗糙度算术平均高度s_a/μm	粗糙度均方根高度s_q/μm	粗糙度最大高度s_z/μm
监视面1	测量点1	0.231	0.328	13.423
	测量点2	0.266	0.360	9.907
	测量点3	0.219	0.323	13.542
监视面2	测量点1	0.334	0.433	8.004
	测量点2	0.373	0.566	17.047
	测量点3	0.262	0.377	19.611
监视面3	测量点1	0.303	0.417	12.864
	测量点2	0.271	0.368	15.857
	测量点3	0.221	0.282	6.169
监视面4	测量点1	0.174	0.254	7.422
	测量点2	0.231	0.413	18.624
	测量点3	0.322	0.537	8.340