一种坦克炮长瞄准镜系统状态评估的方法

doi:10.12382/bgxb.2022.0291

摘要/Abstract

摘要：

针对目前坦克炮长瞄准镜系统在健康状态评估工作中存在的单一信号阈值确定、各级指标权重确定和评估结果判定3个方面的不足,提出一种基于改进评价云的坦克炮长瞄准镜系统健康状态的评估方法。通过改进模糊层次分析法和改进熵权法相结合的组合赋权法,计算出系统各层信号指标的权重;使用自组织映射神经网络确定指标阈值并确定云化区间;建立基于改进云模型的状态评估模型。通过实例验证结构表明,该评估模型合理有效,其评估结果与系统实际状态符合,可促进炮长瞄准镜系统健康管理体系的革新。

关键词: 炮长瞄准镜系统, 组合赋权法, 自组织映射神经网络, 云模型, 状态评估

Abstract:

Aiming at the limitations of single signal threshold determination, the determination of the weights of indicators at all levels and the determination of the evaluation results in the health status assessment of the tank gunner’s scope system, a tank gunner’s scope system based on an improved evaluation cloud is proposed. First, the weights of the signal indicators of each layer of the system are calculated by the combination of subjective and objective weights combining the improved fuzzy analytic hierarchy process and the improved entropy weighting method. Then, self-organizing mapping neural network (SOM) is used to determine the index threshold and the cloud interval. Finally, according to the comprehensive weights and the improved cloud model, a state evaluation model is established. Through an example, we demonstrate that the evaluation model is reasonable and effective, yielding results consistent with the actual system state. This approach contributes to the innovation of the health management of the gunner’s sight system.

Key words: gunner sight system, coined empowerment method, self-organizing mapping neural network, cloud model, state assessment

中图分类号:

TJ811⁺.2

解宝琦, 李英顺, 王德彪, 隋欢欢. 一种坦克炮长瞄准镜系统状态评估的方法[J]. 兵工学报, 2023, 44(8): 2414-2423.

XIE Baoqi, LI Yingshun, WANG Debiao, SUI Huanhuan. Method for Evaluating Tank Gunner’s Sight System[J]. Acta Armamentarii, 2023, 44(8): 2414-2423.

图/表 14

参考文献 34

[1]	高美娟. 复杂机电装备健康管理系统研究[D]. 西安: 西安工业大学, 2015.
	GAO M J. Research on health management system of com-plex electromechanical equipment[D]. Xi'an: Xi'an University of Technology, 2015. (in Chinese)
[2]	CHANG J, WEI F. Prognostics and health management of mechanical systems[J]. Advanced Materials Research, 2013, 694/695/696/697: 872-875.
[3]	赵丽琴, 刘昶, 曹明生, 等. 复杂装备健康度评估方法研究综述[J]. 计算机测量与控制, 2021, 29(11): 1-7, 17.
	ZHAO L Q, LIU C, CAO M S, et al. A review of research on health assessment methods for complex equipment[J]. Computer Measurement & Control, 2021, 29(11): 1-7, 17. (in Chinese)
[4]	陈作炳, 印世杰, 项勤. 立式辊磨机健康状态综合评价与预测研究[J]. 机械设计与制造, 2019(6): 252-255.
	CHEN Z B, YIN S J, XIANG Q. Research on comprehensive evaluation and prediction of health Status of vertical roller mill[J]. Machinery Design & Manufacture, 2019 (6): 252-255. (in Chinese)
[5]	TECHANE A W, WANG Y F, WELDEGIORGIS B H. Rotating machinery prognostics and application of machine learning algorithms: use of deep learning with similarity index measure for health status prediction[C]// Proceedings of the Annual Conference of the Prognostics and Health Management Society. Philadelphia, PA, US: K Reichard,C Byington, 2018: 24.
[6]	PAN H, GUI G, LIN Z, et al. Deep BBN learning for health assessment toward decision-making on structures under uncertainties[J]. KSCE Journal of Civil Engineering, 2018, 22(3): 928-940. doi: 10.1007/s12205-018-1301-2
[7]	吴魁, 孙洁, 蒋波, 等. 基于LSTM的风洞设备健康状态评估方法研究[J]. 计算机测量与控制, 2018, 26(3): 288-291.
	WU K, SUN J, JIANG B, et al. Research on LSTM-based wind tunnel equipment health status assessment method[J]. Computer Measurement & Control, 2018, 26(3): 288-291. (in Chinese)
[8]	曹惠玲, 黄乐腾, 李志伟, 等. 基于SOM神经网络的航空发动机滑油系统健康评估[J]. 中国民航大学学报, 2014, 32(6): 19-22.
	CAO H L, HUANG L T, LI Z W, et al. Aero-engine lubricating oil system health assessment based on SOM neural network[J]. Journal of Civil Aviation University of China, 2014, 32(6): 19-22. (in Chinese)
[9]	方博. 滚动轴承健康状态评估方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2019.
	FANG B. Research on the evaluation method of rolling bearing health status[D]. Harbin: Harbin Institute of Technology, 2019. (in Chinese)
[10]	彭炎亮, 李汪根, 刘娇, 等. 基于动态权重和模糊综合评判法的健康评估模型[J]. 计算机系统应用, 2017, 26(1): 37-43.
	PENG Y L, LI W G, LIU J, et al. Health assessment model based on dynamic weights and fuzzy comprehensive evaluation[J]. Computer Systems & Applications, 2017, 26(1): 37-43. (in Chinese)
[11]	黄治国, 刘雯静, 夏骏, 等. 基于改进证据理论与健康指数的变压器评估与预测[J]. 河北电力技术, 2019, 38(1): 1-4, 12.
	HUANG Z G, LIU W J, XIA J, et al. Transformer evaluation and prediction based on improved evidence theory and health index[J]. Hebei Electric Power Technology, 2019, 38(1): 1-4, 12. (in Chinese)
[12]	XING X M, XU H R, LIAO M G, et al. Comprehensive assessment method of distribution terminal health status based on cloud model and D-S evidence theory[J]. Power System Protection and Control, 2021, 49(13): 72-81. (in Chinese)
[13]	COELLO C A. A comprehensive survey of evolutionary-based multiobjective optimization techniques[J]. Knowledge and Information systems, 1999, 1(3): 269-308. doi: 10.1007/BF03325101 URL
[14]	JOHNSON G R, COOK W H. A constitutive model and data for metals subjected to large strains, high strain rates and high temperatures[C]// Proceedings of the 7th International Symposium on Ballistics. Hague, the Netherlands: IBC, 1983: 541-547.
[15]	李清, 程阳, 于强, 等. 基于改进层次分析法的爆破效果影响因素[J]. 工程爆破, 2017, 23(3): 1-4.
	LI Q, CHENG Y, YU Q, et al. Influencing factors of blasting effect based on improved AHP[J]. Engineering Blasting, 2017, 23(3): 1-4. (in Chinese)
[16]	杨延超, 李英顺, 李茂, 等. 装甲装备观瞄系统状态评估的方法研究[J]. 火炮发射与控制学报, 2020, 41(4): 80-86.
	YANG Y C, LI Y S, LI M, et al. Research on method of status evaluation of wepon eqipment sighting system[J]. Journal of Gun Launch & Control, 2020, 41(4): 80-86.
[17]	张文. 基于改进熵权法和可变模糊集法的岸桥安全性评价[D]. 武汉: 武汉理工大学, 2020.
	ZHANG W. Safety evaluation of crane crane based on Improved entropy weight method and variable fuzzy set method[D]. Wuhan: Wuhan University of Technology, 2020. (in Chinese)
[18]	SUN L J, LIU Y Y, ZHANG B Y, et al. An integrated decision-making model for transformer condition assessment using game theory and modified evidence combination extended by D numbers[J]. Energies, 2016, 9(9): 697. doi: 10.3390/en9090697 URL
[19]	李爱华. 岸边集装箱起重机安全评价方法研究[D]. 武汉: 武汉理工大学, 2017.
	LI A H. Research on safety evaluation method of quayside container crane[D]. Wuhan: Wuhan University of Technology, 2017. (in Chinese)
[20]	南东亮, 王维庆, 张陵, 等. 基于关联规则挖掘与组合赋权-云模型的电网二次设备运行状态风险评估[J]. 电力系统保护与控制, 2021, 49(10): 67-76.
	NAN D L, WANG W Q, ZHANG L, et al. Risk assessment of power grid secondary equipment operation status based on association rule mining and combined weighting-cloud model[J]. Power System Protection and Control, 2021, 49(10): 67-76. (in Chinese)
[21]	丛林虎, 肖支才, 陈育良, 等. 基于改进云模型的某型反舰导弹状态评估方法[J]. 兵器装备工程学报, 2021, 42(8): 85-93.
	CONG C H, XIAO Z C, CHEN Y L, et al. State assessment method of a certain type of anti-ship missile based on improved cloud model[J]. Journal of Ordnance Equipment Engineering, 2021, 42(8): 85-93. (in Chinese)
[22]	刘禹, 李德毅. 正态云模型雾化性质统计分析[J]. 北京航空航天大学学报, 2010, 36(11): 1320-1324.
	LIU Y, LI D Y. Statistical analysis of atomization properties in normal cloud model[J]. Journal of Beijing University of Aeronautics and Astronautics, 2010, 36(11): 1320-1324. (in Chinese)
[23]	刘月, 刘铁林, 姜相争, 等. 基于径向基函数和自组织映射的导弹控制系统健康状态评估[J]. 兵工学报, 2022, 43(4): 931-939. doi: 10.12382/bgxb.2021.0219
	LIU Y, LIU T L, JIANG X Z, et al. Evaluation of missile control system health status based on radial basis function and self-organizing map[J]. Acta Armamentarii, 2022, 43(4): 931-939. (in Chinese)
[24]	LI D Y, LIU C Y, GAN W Y. A new cognitive model: cloud model[J]. International journal of intelligent systems, 2009, 24(3): 357. doi: 10.1002/int.v24:3 URL
[25]	谭丕成, 冯方, 刘宇, 等. 基于变权云模型的灯泡贯流式水轮机状态评估方法[J]. 排灌机械工程学, 2022, 40(8): 807-813
	TAN P C, FENG F, LIU Y, et al. State evaluation method of bulb tubular Turbine based on variable weight cloud model[J]. Journal of Drainage andIrrigation Machinery Engineering, 2022, 40(8): 807-813. (in Chinese)
[26]	吴宗兵, 刘洋洋, 李正天, 等. 基于改进云理论算法的中压电缆运行状态评估新策略[J]. 电线电缆, 2022(3): 1-7, 41.
	WUZ B, LIU Y Y, LI Z T, et al. A new strategy for medium voltage cable operating state evaluation based on improved cloud theory algorithm[J]. Wire & Cable. 2022(3): 1-7, 41. (in Chinese)
[27]	刘文宇, 刘璐, 刘馨然, 等. 基于改进BP神经网络的低压配电台区智能电能表误差状态评估模型[J]. 电测与仪表, 2022(11):176-181. (in Chinese)
	LIU W Y, LIU L, LIU X R, et al. Error state evaluation model of intelligent watt-hour meter in low voltage distribution area based on improved BP neural network[J]. Electrical Measurement & Instrumentation, 2022(11):176-181. (in Chinese)
[28]	张冀, 张亚静, 仇向东. 基于博弈组合赋权的变压器差异化状态评估[J]. 高压电器, 2022, 58(4): 205-212.
	ZHANG Y, ZHANG Y J, QIU X D. Evaluation of transformer differential state based on game combination weighting[J]. High Voltage Apparatus, 2022, 58(4): 205-212. (in Chinese)
[29]	贾晋峰, 程超贻, 周欣, 等. 基于模糊矩阵的计量装置状态评估方法[J]. 电力科学与技术学报, 2022, 37(2): 164-172.
	JIA P F, CHENG C Y, ZHOU X, et al. State evaluation method of metering equipment based on fuzzy matrix[J]. Journal of Electric Power Science and Technology, 2022, 37(2): 164-172. (in Chinese)
[30]	高书垚, 安泰, 宋剑. 基于熵权-正态云模型的智能电能表状态评估研究[J]. 电测与仪表, 2022, 59(1): 190-194.
	GAO S Y, AN T, SONG J. State evaluation of smart electricity meter based on entropy-normal cloud model[J]. Electrical Measurement & Instrumentation, 2022, 59(1): 190-194. (in Chinese)
[31]	杨晓昕. 基于云模型的智能变电站二次设备状态评估[D]. 南宁: 广西大学, 2021.
	YANG X X. State Evaluation of secondary Equipment in Smart Substation based on Cloud Model[D]. Nanjing: Guangxi University, 2021. (in Chinese)
[32]	朱晓荣, 刘亚维. 基于模糊综合评判的光伏阵列状态评估[J]. 太阳能学报, 2020, 41(11): 103-111.
	ZHU X R, LIU Y W. Evaluation of photovoltaic array state based on fuzzy comprehensive Evaluation[J]. Acta Energiae Solaris Sinica, 2020, 41(11): 103-111. (in Chinese)
[33]	章亮, 杨俊杰. 基于多维正态云模型的电力变压器状态评估[J]. 电测与仪表, 2020, 57(4): 129-135.
	ZHANG L, YANG J J. Power Transformer State Evaluation based on multidimensional normal cloud model[J]. Electrical Measurement & Instrumentation, 2020, 57(4): 129-135. (in Chinese)
[34]	王泉, 姚俊伟, 智李, 等. 基于矩估计法和模糊-证据融合的电力变压器套管状态评估[J]. 电力科学与技术学报, 2020, 35(1): 130-136.
	WANG Q, YAN J W, ZHI L, et al. Power transformer casing State evaluation based on moment estimation method and fuzzy-evidence fusion[J]. Journal of Electric Power Science and Technology, 2020, 35(1): 130-136. (in Chinese)

状态等级	具体描述
健康	装备运行过程中,各指标测试数据均在可接受范围内,且均远离阈值或标准值。
良好	装备运行过程中各指标的测试数据均在允许范围内,部分指标的测试数据在参考值上下一定范围内波动,但远未达到阈值。
注意	装备运行过程中的各项指标在运行过程中的测试数据均在允许范围内,部分参数的测试数据与标准值有较大偏差,达到了规定的注意值,但与临界值相差甚远。
恶化	装备运行过程中各指标的测试数据均在允许范围内,但部分指标的测试数据接近或者达到阈值,劣化趋势明显。
故障	装备运行过程中的各指标的测试数据达到或超过注意值,且多个指标的测试数据接近或达到阈值。

状态等级	具体描述
健康	装备运行过程中,各指标测试数据均在可接受范围内,且均远离阈值或标准值。
良好	装备运行过程中各指标的测试数据均在允许范围内,部分指标的测试数据在参考值上下一定范围内波动,但远未达到阈值。
注意	装备运行过程中的各项指标在运行过程中的测试数据均在允许范围内,部分参数的测试数据与标准值有较大偏差,达到了规定的注意值,但与临界值相差甚远。
恶化	装备运行过程中各指标的测试数据均在允许范围内,但部分指标的测试数据接近或者达到阈值,劣化趋势明显。
故障	装备运行过程中的各指标的测试数据达到或超过注意值,且多个指标的测试数据接近或达到阈值。

等级	定义	区间
1	健康	[0,a)
2	良好	[a,b)
3	注意	[b,c)
4	恶化	[c,d)
5	故障	[d,1]

等级	定义	区间
1	健康	[0,a)
2	良好	[a,b)
3	注意	[b,c)
4	恶化	[c,d)
5	故障	[d,1]

组数	I₁	I₂	I₃	I₄	I₅	I₆	I₇	I₈	I₉	I₁₀	I₁₁	I₁₂
1	0.45	0.35	0.42	0.25	0.04	0.16	0.33	0.24	0.73	0.85	0.66	0.58
2	0.53	0.55	0.35	0.37	0.12	0.19	0.12	0.25	0.55	0.64	0.85	0.65
3	0.37	0.82	0.55	0.75	0.00	0.03	0.49	0.54	0.32	0.93	0.78	0.73
4	0.80	0.74	0.76	0.33	0.44	0.33	0.20	0.51	0.66	0.57	0.75	0.67
5	0.65	0.95	0.68	0.42	0.35	0.44	0.45	0.01	0.83	0.55	0.63	0.90
6	0.90	0.36	0.73	0.65	0.27	0.32	0.38	0.00	0.95	0.32	0.95	0.75
7	0.44	0.41	0.92	0.74	0.18	0.38	0.09	0.44	0.66	0.74	0.54	0.80
8	0.22	0.63	0.81	0.90	0.42	0.41	0.35	0.05	0.43	0.65	0.42	0.45
9	0.72	0.75	0.65	0.83	0.21	0.18	0.18	0.25	0.82	0.82	0.35	0.50
10	0.74	0.66	0.33	0.55	0.35	0.16	0.24	0.11	0.74	0.41	0.65	0.85