面向数字装备性能鉴定的试验样本量确定方法

doi:10.12305/j.issn.1001-506X.2026.06.17

摘要/Abstract

摘要：

装备试验鉴定发挥着严把定型关口的作用，性能鉴定是其中的一个环节。数字化技术的发展带来了数字化试验的新形式，即研发数字装备随实装交付。针对数字装备的性能鉴定，确定试验样本量是试验方案设计的基础，由于数字装备的多输出参数和多鉴定方式，现有方法不能直接确定样本量，为此首先提出基于数字装备输出参数和实装等试验数据一致性检验的数字装备鉴定框架，然后给出只考虑实装试验方式下的最小试验样本量，再根据各种试验方式的关系进行样本等效和合并，最终得到鉴定所需的试验样本量。通过算例分析，说明了所提方法的有效性。

关键词: 数字装备, 性能鉴定, 试验样本量, 样本等效, 样本合并

Abstract:

Equipment test evaluation is to strictly control the type-approval processand the performance evaluation is one of the procedures to test the performance. With the development of digital technology, a new way is digital testing to deliver digital equipment together with the physical equipment. The sample size determination is basic for test design aimming at performance evaluation of digital equipment. Due to the huge output parameters and various testing ways, the existing methods fail to determine the sample size. Aiming at this problem, firstly, a framework for digital model identification is proposed based on the consistency test of digital equipment output and test data. Then, the minimum test sample size is calculated only considering the physical test. Next, sample equivalence and merging are performed based on the relationship between various test methods. Finally, the test sample size is obtained to support the evaluation. The effectiveness of the proposed method is demonstrated through example analysis.

Key words: digital equipment, performance evaluation, sample size, sample equivalence, sample merging

中图分类号:

TP 141

贾祥, 潘正强, 程志君. 面向数字装备性能鉴定的试验样本量确定方法[J]. 系统工程与电子技术, 2026, 48(6): 1965-1971.

Xiang JIA, Zhengqiang PAN, Zhijun CHENG. Determination method of sample size for digital equipment performance evaluation[J]. Systems Engineering and Electronics, 2026, 48(6): 1965-1971.

图/表 6

图1

表1

图2

图3

表2

表3

参考文献 30

1	武小悦, 金光, 李革, 等. 装备性能试验 [M]. 北京: 国防工业出版社, 2022.
	WU X Y, JIN G, LI G, et al. Equipment performance test [M]. Beijing: National Defense Industry Press, 2022.
2	徐涛, 宋敬华, 李亮, 等. 装备数字化试验发展研究[J]. 新技术新工艺, 2022 (9): 15- 19. doi: 10.16635/j.cnki.1003-5311.2022.09.009
	XU T, SONG J H, LI L, et al. Research on development of the equipment digital test[J]. New Technology & New Process, 2022 (9): 15- 19. doi: 10.16635/j.cnki.1003-5311.2022.09.009
3	党宏杰, 余文广, 杨华晖. 基于数字孪生与平行试验的装备体系试验鉴定数字化应用[J]. 系统仿真学报, 2024, 36 (7): 1729- 1736. doi: 10.16182/j.issn1004731x.joss.23-0433
	DANG H J, YU W G, YANG H H. Digital application of equipment system test and evaluation based on digital twin and parallel experiment theory[J]. Journal of System Simulation, 2024, 36 (7): 1729- 1736. doi: 10.16182/j.issn1004731x.joss.23-0433
4	白春玉, 梁森, 宋巧治. 全尺寸飞行器地面振动试验数字化协同探索与实践[J]. 航空工程进展, 2024, 15 (2): 90- 100. doi: 10.16615/j.cnki.1674-8190.2024.02.10
	BAI C Y, LIANG S, SONG Q Z. Digital collaborative exploration and practice of ground vibration test for full-scale aircraft[J]. Advances in Aeronautical Science and Engineering, 2024, 15 (2): 90- 100. doi: 10.16615/j.cnki.1674-8190.2024.02.10
5	刘秀罗, 王佳, 尚国强, 等. 航天发射场数字孪生技术初探[J]. 西北工业大学学报, 2019, 37 (S1): 114- 119.
	LIU X L, WANG J, SHANG G Q, et al. The primary exploration to digital twin technology of launching site[J]. Journal of Northwestern Polytechnical University, 2019, 37 (S1): 114- 119.
6	LUAN J Q, LI S Y, CAO Y P, et al. Application of a surrogate model for condition monitoring of a digital twin gas turbine [J]. Applied Mathematical Modelling, 2025, 137: 115683.
7	YIN Y X, MA B W, MENG Z J, et al. Construction method and case study of digital twin system for combine harvester[J]. Computers and Electronics in Agriculture, 2024, 226, 109395. doi: 10.1016/j.compag.2024.109395
8	赫赤, 董光玲, 史睿冰, 等. 试验鉴定数字化转型模式研究 [C]// 第23届中国系统仿真技术及其应用学术年会, 2022: 45−49.
	HE C, DONG G L, SHI R B, et al. Research on digital transformation mode of test and evaluation [C]//Proc. of the 23th Chinese Simulation Technology and Application Annuals, 2022: 45−49.
9	潘岳松, 金奥铭, 王梦星. 临床研究样本量的估计方法和常见错误[J]. 中国卒中杂志, 2022, 17 (1): 31- 35. doi: 10.3969/j.issn.1673-5765.2022.01.004
	PAN Y S, JIN A M, WANG M X. Methods and common pitfalls of sample size estimation in clinical studies[J]. Chinese Journal of Stroke, 2022, 17 (1): 31- 35. doi: 10.3969/j.issn.1673-5765.2022.01.004
10	曹策, 李玲美, 訾明杰, 等. 医学研究中动物实验样本量的确定方法[J]. 中国比较医学杂志, 2023, 33 (2): 99- 105.
	CAO C, LI L M, ZI M J, et al. Methods for determining animal sample sizes in medical experimental studies[J]. Chinese Journal of Comparative medicine, 2023, 33 (2): 99- 105.
11	王黎明, 刘青松, 张晓良, 等. 部分核实数据下基于比例差的置信区间宽度的样本量确定[J]. 重庆理工大学学报（自然科学）, 2021, 33 (5): 280- 294. doi: 10.3969/j.issn.1674-8425(z).2021.05.035
	WANG L M, LIU Q S, ZHANG X L, et al. Sample size determination based on the width of confidence intervals for proportion difference with partially validated series[J]. Journal of Chongqing University of Technology （Natural Science）, 2021, 33 (5): 280- 294. doi: 10.3969/j.issn.1674-8425(z).2021.05.035
12	冯国双. 临床研究中非劣效性和等效性试验的样本量估算[J]. 慢性病学杂志, 2022, 23 (7): 1006- 1009，1014. doi: 10.16440/J.CNKI.1674-8166.2022.07.14
	FENG G S. The sample size determination[J]. Chronic Pathematology, 2022, 23 (7): 1006- 1009，1014. doi: 10.16440/J.CNKI.1674-8166.2022.07.14
13	薄云, 廖学军, 白洪波, 等. 面向贝叶斯方法的作战试验样本量估算研究[J]. 火力与指挥控制, 2022, 47 (3): 162- 166. doi: 10.3969/j.issn.1002-0640.2022.03.027
	BO Y, LIAO X J, BAI H B, et al. Sample size estimation for Bayesian methods based operational tests[J]. Fire Control & Command Control, 2022, 47 (3): 162- 166. doi: 10.3969/j.issn.1002-0640.2022.03.027
14	董正琼, 袁顺, 刘佳, 等. 雷达发射机测试性验证试验方案样本量优化[J]. 电子测量技术, 2022, 45 (2): 154- 158. doi: 10.19651/j.cnki.emt.2107963
	DONG Z Q, YUAN S, LIU J, et al. Sample size optimization of test scheme in radar transmitter testability verification[J]. Electronic Measurement Technology, 2022, 45 (2): 154- 158. doi: 10.19651/j.cnki.emt.2107963
15	王康, 史贤俊, 肖支才, 等. 基于后验分布的限制型故障样本量确定方法 [J]. 振动、测试与诊断, 2020, 40(6): 1156−1164, 1234−1235.
	WANG K, SHI X J, XIAO Z C, et al. Restricted fault sample size determination method based on posterior distribution [J]. Journal of Vibration, Measurement & Diagnosis, 2020, 40(6): 1156−1164, 1234−1235.
16	刘琦, 许芝芹, 霍志玮, 等. 基于试验费用的指数分布产品可靠性试验样本量优选方法[J]. 现代机械, 2020 (5): 35- 42. doi: 10.13667/j.cnki.52-1046/th.2020.05.009
	LIU Q, XU Z Q, HUO Z W, et al. Optimization method of sample size calculation for reliability test of exponential distributed products based on test cost[J]. Modern Machinery, 2020 (5): 35- 42. doi: 10.13667/j.cnki.52-1046/th.2020.05.009
17	HE Y L, CHEN J Q, SHEN J X, et al. Density estimation-based method to determine sample size for random sample partition of big data[J]. Frontiers of Computer Science, 2024, 18 (5): 185322. doi: 10.1007/s11704-023-2356-x
18	SIEDLECKI S L. How to determine when your sample size is big enough but not too big[J]. Clinical Nurse Specialist, 2024, 38 (5): 205- 207. doi: 10.1097/nur.0000000000000844
19	SHU D, ZOU G Y. Sample size planning for estimating the global win probability with precision and assurance [J]. Contemporary Clinical Trials, 2024, 146: 107665.
20	HUO Y, YANG Y, HALLORAN M E, et al. Hypothesis testing and sample size considerations for the test-negative design[J]. BMC Medical Research Methodology, 2024, 24 (1): 151. doi: 10.1186/s12874-024-02277-4
21	PAVLOU M, AMBLER G, QU C, et al. An evaluation of sample size requirements for developing risk prediction models with binary outcomes[J]. BMC Medical Research Methodology, 2024, 24 (1): 146. doi: 10.1186/s12874-024-02268-5
22	MONTI C B, AMBROGI F, SARDANELLI F. Sample size calculation for data reliability and diagnostic performance: a go-to review[J]. European Radiology Experimental, 2024, 8 (1): 79. doi: 10.1186/s41747-024-00474-w
23	GANESH V, SAHNI N. Reviewing research reporting in randomised controlled trials–the sample size calculation[J]. Indian Journal of Anaesthesia, 2024, 68 (7): 662- 663. doi: 10.4103/ija.ija_443_24
24	BHARDWAJ R, AGRAWAL U, VASHIST P, et al. Determination of sample size for various study designs in medical research: a practical primer[J]. Journal of Family Medicine and Primary Care, 2024, 13 (7): 2555- 2561. doi: 10.4103/jfmpc.jfmpc_1675_23
25	孙旭涛, 郭小威, 王志佳. 基于模型验证数据的仿真模型可信度计算方法[J]. 计算机仿真, 2022, 39 (12): 73- 76. doi: 10.3969/j.issn.1006-9348.2022.12.014
	SUN X T, GUO X W, WANG Z J. Credibility calculation method of simulation model based on model validation data[J]. Computer Simulation, 2022, 39 (12): 73- 76. doi: 10.3969/j.issn.1006-9348.2022.12.014
26	李伟, 周玉臣, 林圣琳, 等. 仿真模型验证方法综述[J]. 系统仿真学报, 2019, 31 (7): 1249- 1256. doi: 10.3969/j.issn.1672-9668.2023.10.007
	LI W, ZHOU Y C, LIN S L, et al. Review of simulation model validation methods[J]. Journal of System Simulation, 2019, 31 (7): 1249- 1256. doi: 10.3969/j.issn.1672-9668.2023.10.007
27	沈春林. 两总体等效性检验的样本量确定及模拟研究 [D]. 武汉: 华中师范大学, 2011.
	SHEN C L. The sample size requirement of equivalence test of the two population and simulation study [D]. Wuhan: Central China Normal University, 2011.
28	董光玲. 基于贝叶斯理论的靶场试验综合设计方法研究 [D]. 哈尔滨: 哈尔滨工业大学, 2015.
	DONG G L. Research on integrated design methods of range test based on Bayesian theory [D]. Harbin: Harbin Institute of Technology, 2015.
29	刘瑛, 刘冠军, 邱静, 等. 基于 Bayesian 的测试性虚实一体化试验方案的设计[J]. 测试技术学报, 2014, 28 (6): 461- 466. doi: 10.3969/j.issn.1671-7449.2014.06.001
	LIU Y, LIU G J, QIU J, et al. Design of testability virtual-physical integrated test scheme based on Bayesian[J]. Journal of Test and Measurement Technology, 2014, 28 (6): 461- 466. doi: 10.3969/j.issn.1671-7449.2014.06.001
30	宁小磊, 吴颖霞. 基于等效样本和实仿融合的现场小子样试验制导精度评估方法[J]. 中国惯性技术学报, 2021, 29 (2): 264- 272. doi: 10.13695/j.cnki.12-1222/o3.2021.02.018
	NING X L, WU Y X. Guidance accuracy evaluation method of field small sample test based on equivalent sample and real simulation fusion[J]. Journal of Chinese Inertial Technology, 2021, 29 (2): 264- 272. doi: 10.13695/j.cnki.12-1222/o3.2021.02.018

分系统模型	分模型输出参数	鉴定方法	试验方式
模型1	参数L₁₁	xx方法	W₁₁
	参数L₁₂	xx方法	W₁₂
	$ \vdots $	$ \vdots $	$ \vdots $
	参数$ {L}_{1{{k}_{1}}} $	xx方法	$ {W}_{1{{k}_{1}}} $
$ \vdots $	$ \vdots $	$ \vdots $	$ \vdots $
模型i	参数L_ij	xx方法	W_ij
$ \vdots $	$ \vdots $	$ \vdots $	$ \vdots $
模型M	参数L_M1	xx方法	W_M1
	参数L_M2	xx方法	W_M2
	$ \vdots $	$ \vdots $	$ \vdots $
	参数$ {L}_{M{{k}_{M}}} $	xx方法	$ {W}_{M{{k}_{M}}} $

分系统模型	输出参数	参数类型	试验方式
模型1	L₁₁	时序	a, b
	L₁₂	时序	a, b
	L₁₃	静态	a, b
模型2	L₂₁	静态	c, d
模型3	L₃₁	静态	a, b, c
模型3	L₃₂	静态	a, b, d

输出参数	所需参数	最小实装试验样本量	试验方式
输出参数	所需参数	最小实装试验样本量	a	b	c	d
L₁₁	p₀=0.85，	29	7	28	−	−
L₁₁	p_a=0.7	29	7	28	−	−
L₁₂	p₀=0.89，	21	7	19	−	−
L₁₂	p_a=0.7	21	7	19	−	−
L₁₃	$ {\delta }_{m}=-2 $，	6	6	0	−	−
	$ {\delta }_{M}=2 $，
	$ \delta =1.1 $，
	$ s $=1
L₂₁	$ {\delta }_{m}=-0.8 $，	9	−	−	9	0
	$ {\delta }_{M}=0.8 $，
	$ \delta =0.2 $，
	$ s $=0.85
L₃₁	$ {\delta }_{m}=-1.5 $，	12	7	9	0	−
	$ {\delta }_{M}=1.5 $，
	$ \delta =0.95 $，
	$ s $=0.96
L₃₂	$ {\delta }_{m}=-2.5 $，	7	7	0	−	0
	$ {\delta }_{M}=2.5 $，
	$ \delta =1.11 $，
	$ s $=1.8