基于最小二乘支持向量机的机枪加速寿命建模

doi:10.3969/j.issn.1000-1093.2012.01.011

摘要/Abstract

摘要： 加速寿命试验可以在短时间内对产品寿命进行有效评定。针对以往机枪加速寿命模型预测能力较差的问题，提出了基于最小二乘支持向量机（LS-SVM）建立加速寿命模型的方法。以机枪寿终射弹量为寿命特征，以试验环境温度、枪管最大温度、射击间隔时间以及最大膛压为加速应力建立了机枪加速寿命模型。由于LS-SVM的参数选取是决定建立模型优劣的关键因素，因此采用遗传算法对LS-SVM参数进行优化选取。通过分析比较LS-SVM与常规变换方法和BP神经网络建立的机枪加速寿命模型精度，结果表明利用LS-SVM方法建立的模型明显优于其他2种方法，验证了LS-SVM在机枪加速寿命预测应用中的有效性。

关键词: 系统工程, 最小二乘支持向量机, 神经网络, 遗传算法, 加速寿命试验

Abstract: Product life can be assessed effectively in the short period of time by using accelerated life test. Aimed at problems resulted from poor predictive ability of the previous accelerated life model, a method to establish accelerated life model for machine guns based on LS-SVM was proposed. It took the machine gun’s shooting ammunition quantity before the life end as the life feature and selected the test ambient temperature, barrel’s maximum temperature, shooting interval, maximum pressure in bore as the accelerated stresses. A genetic algorithm was adopted to determine the optimal parameters of LS-SVM. The prediction results show that the model established in this paper are better than the general transformation and BP neural network models obviously, and the LS-SVM method are effective on accelerated life prediction for machine guns.

Key words: system engineering, LS-SVM, neural network, genetic algorithm, accelerated life test

中图分类号:

TJ25

张军，单永海，曹殿广，郑玉新，葛欣鑫. 基于最小二乘支持向量机的机枪加速寿命建模[J]. 兵工学报, 2012, 33(1): 63-68.

ZHANG Jun, SHAN Yong-hai, CAO Dian-guang, ZHENG Yu-xin, GE Xin-xin. Accelerated Life Modeling for Machine Gun Based on LS-SVM[J]. Acta Armamentarii, 2012, 33(1): 63-68.

参考文献

［1］董志明，高世峰，杨磊，等. 关于机枪加速寿命试验的建模[J]. 火力与指挥控制，2009,34(增刊):132-134.
DONG Zhi-ming, GAO Shi-feng, YANG Lei, et al. Research on modeling of accelerated life test about machine gun[J]. Fire Control and Command Control, 2009, 34(suppl): 132-134. (in Chinese)
[2] 刘斌，苏宏业，褚键. 一种基于最小二乘支持向量机的预测控制算法[J]. 控制与决策，2004,19(12):1399-1402.
LIU Bin, SU Hong-ye, CHU Jian. Predictive control algorithm based on least squares support vector machines [J]. Control and Decision,2004,19(12):1399-1402. (in Chinese)
[3] 刘涵，刘丁，郑岗，等. 基于最小二乘支持向量机的天然气负荷预测[J]. 化工学报，2004,55(5):828-832.
LIU Han, LIU Ding, ZHENG Gang, et al. Natural gasload forecasting based on least squares support vector machine [J]. Journal of Chemical Industry and Engineering, 2004, 55(5):828-832. (in Chinese)
[4] 卓穗如. 机枪枪管的寿终机理[C]∥机枪枪管寿命预测技术论文集.北京：中国兵器工业第208研究所，1996.
ZHUO Sui-ru. Mechanism of the life termination for machine gun barrel [C]∥Corpus of barrel lifetime prediction technology of machine gun. Beijing: No.208 Research Institute of China North Industries Group,1996. (in Chinese)
[5] 单永海，卓穂如，孙国基. 射击规范与枪械寿命相关性技术分析[J]. 南京理工大学学报，2005, 29(4):417-419, 424.
SHAN Yong-hai, ZHUO Sui-ru, SUN Guo-ji. Technical analysis of relativity of shooting criterions and firearms lifetime[J]. Journal of Nanjing University of Science and Technology, 2005,29(4):417-419,424. (in Chinese)
[6] 单永海，孙国基. 枪械寿命实验温度研究[J]. 南京理工大学学报，2005,29(3):791、792、892、992.
SHAN Yong-hai, SUN Guo-ji. Firearms lifetime test temperatures[J]. Journal of Nanjing University of Science and Technology, 2005, 29(3):791-792、892、992. (in Chinese)
[7] 单永海，孙国基. 枪械射击寿命试验中擦拭与冷却周期射弹量的确定[J]. 兵工学报，2006,27(5):940-943.
SHAN Yong-hai, SUN Guo-ji. The establishment on projectile amounts of cleaning and cooling cycle in firearm shooting lifetime tests[J]. Acta Armamentarii, 2006,27(5): 940-943. (in Chinese)
[8] 樊磊，刘恩锦，刘卫明，等. 大口径机枪枪管寿命趋势分析[J]. 弹道学报，2009,21(3):39-43.
FAN Lei, LIU En-jin, LIU Wei-ming, et al. Performance decay analysis of a large caliber machine gun barrel in lifetime[J]. Journal of Ballistics, 2009,21(3):39-43. (in Chinese)
[9] 李伟如. 射击与命中的科学[M]. 北京：兵器工业出版社，1994.
LI Wei-ru. Science of shooting and hitting[M]. Beijing: The
Publishing House of Ordnance Industry, 1994. (in Chinese)
[10] Vapnik V. The nature of statistical learning theory[M]. New York: Springer-Verlag,1995.
[11] Cortes C, Vapnik V. Support vector networks[J]. Machine Learning,1995,20(1):273-297.
[12] Smola A, Scholkopf B. Tutorial on support vector regression[J]. Statistics and Computing, 2004,14:199-222.
[13] 司刚全，曹晖，张彦斌，等. 一种基于密度加权的最小二乘支持向量机稀疏化算法[J].西安交通大学学报，2009, 43(10):11-15.
SI Gang-quan, CAO Hui, ZHANG Yan-bin, et al. Density weighted pruning method for sparse least squares support vector machines[J]. Journal of Xi’an Jiaotong University, 2009,43(10):11-15. (in Chinese)
[14] 周明，孙树栋.遗传算法原理及应用[M].北京：国防工业出版社，2001.
ZHOU Ming, SUN Shu-dong. Principle and application of genetic algorithms[M]. Beijing: National Defense Industry Press,2001. (in Chinese)
[15] 王克奇，杨少春，戴天虹，等. 采用遗传算法优化最小二乘支持向量机参数的方法[J]. 计算机应用与软件，2009，26(7):109-111.
WANG Ke-qi, YANG Shao-chun, DAI Tian-hong, et al. Method of optimizing parameter of least squares support vector machines by genetic algorithm[J]. Computer Applications and Software, 2009，26(7): 109-111. (in Chinese)
[16] 孙云普，王云飞，郑晓娟. 基于遗传—支持向量机法的煤层顶板导水断裂带高度的分析[J]. 煤炭学报，2009,34 (12):1610-1615.
SUN Yun-pu, WANG Yun-fei, ZHENG Xiao-juan. Analysis the height of water conducted zone of coal seam roof based on GA-SVR[J]. Journal of China Coal Society, 2009,34(12): 1610-1615. (in Chinese)
[17] 崔正斌，汤光明，乐峰. 遗传优化支持向量机的软件可靠性预测模型[J]. 计算机工程与应用，2009,45(36):71-74.
CUI Zheng-bin, TANG Guang-ming, YUE Feng. Sofeware reliability prediction model based on support vector machine optimized by genetic algorithm[J]. Computer Engineering and Applications, 2009,45(36):71-74. (in Chinese)

[1]	王尔烈，王帅，皮大伟，王洪亮，王显会，谢伯元. 某纯电驱动重载车辆能耗预测模型[J]. 兵工学报, 2024, 45(4): 1229-1236.
[2]	苏胜，顾森，宋志强，刘萍. 基于深度表征学习和遗传算法的军用座舱色彩设计方法[J]. 兵工学报, 2024, 45(4): 1060-1069.
[3]	刘梦真, 黄广炎, 张宏, 周宏元, 刘思宇. 小样本驱动特征分段网络的防护材料折痕检测[J]. 兵工学报, 2024, 45(3): 963-974.
[4]	马维宁, 胡起伟, 陈静, 贾希胜. 装备群选择性维修决策与任务分配联合优化[J]. 兵工学报, 2024, 45(2): 407-416.
[5]	秦国华, 娄维达, 林锋, 徐勇. 基于Cotes求积法和神经网络的稳定域判断及铣削参数优化新方法[J]. 兵工学报, 2024, 45(2): 516-526.
[6]	刘子昌, 李思雨, 裴模超, 刘洁, 孟硕, 吴巍屹. 基于纹理分析的柴油发动机故障诊断方法[J]. 兵工学报, 2024, 45(2): 684-694.
[7]	吕卫民, 孙晨峰, 任立坤, 赵杰, 李永强. 一种基于TCN-LGBM的航空发动机气路故障诊断方法[J]. 兵工学报, 2024, 45(1): 253-263.
[8]	方秋雨, 张蕴霖, 麻壮壮, 邵晋梁. 未知环境下基于控制障碍函数的无人车轨迹规划[J]. 兵工学报, 2023, 44(S2): 90-102.
[9]	刘畅, 雷红波, 林时尧, 范世鹏, 王江. 基于多模型网络的激光末制导炮弹诸元解算方法[J]. 兵工学报, 2023, 44(9): 2745-2755.
[10]	叶闻语, 王春阳, 于金阳, 拓明侃, 王子硕. 基于贪心遗传算法的液晶光学相控阵多光束扫描[J]. 兵工学报, 2023, 44(9): 2650-2660.
[11]	张凯歌, 卢志刚, 聂天常, 李志伟, 郭宇强. 面向无人装备的智能边缘计算软技术分析[J]. 兵工学报, 2023, 44(9): 2611-2621.
[12]	陈松, 朱东升, 左钦文, 韩朝帅. 基于GA-PS的三维空间源项反演算法[J]. 兵工学报, 2023, 44(8): 2503-2520.
[13]	刘冰, 郝新红, 周文, 杨瑾. 基于BAS-BPNN的调频无线电引信目标与扫频干扰识别方法[J]. 兵工学报, 2023, 44(8): 2391-2403.
[14]	张安, 徐双飞, 毕文豪, 徐晗. 空地多目标攻击武器-目标分配与制导序列优化[J]. 兵工学报, 2023, 44(8): 2233-2244.
[15]	周宇, 曹荣刚, 栗苹, 马啸. 一种用于外场试验图像的引信炸点检测方法[J]. 兵工学报, 2023, 44(8): 2453-2464.