• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.6
• /
• pp.374-382
• /
• 2020

The purpose of this study is to improve the learning speed of an ammunition stockpile reliability classification artificial neural network model by proposing a normalization method that reduces the number of input variables based on the characteristic of Ammunition Stockpile Reliability Program (ASRP) data without loss of classification performance. Ammunition's performance requirements are specified in the Korea Defense Specification (KDS) and Ammunition Stockpile reliability Test Procedure (ASTP). Based on the characteristic of the ASRP data, input variables can be normalized to estimate the lot percent nonconforming or failure rate. To maintain the unitary hypercube condition of the input variables, min-max normalization method is also used. Area Under the ROC Curve (AUC) of general min-max normalization and proposed 2-step normalization is over 0.95 and speed-up for marching learning based on ASRP field data is improved 1.74 ~ 1.99 times depending on the numbers of training data and of hidden layer's node.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.8 no.4 s.23
• /
• pp.32-40
• /
• 2005

The ASRP(Ammunition Stockpile Reliability Program) is a overall evaluation system of ammunitions to improve the combat strength, having a short history. The storage lifetime of ammunitions, more than 20 years since being produced, differs according to storage circumstance and period. And it shows the different reliability for munitions. Because most ammunitions in military have been stored for a long time, these ammunitions need to be evaluated to maintain Serviceability, Reliability, Safety and Performance for the use of military. In this paper, it suggested the need to develop the techniques for ourselves, to make more laboratories for surveillance and testing and to extend research funds & concerns.

• Journal of Applied Reliability
• /
• v.16 no.3
• /
• pp.208-215
• /
• 2016

Purpose: ASRP for the domestic development guided missiles requires not only for the reliability evaluation of the products in storage but also for the life cycle management of the products including development prototypes and initial production items. Methods: For this purpose, it should be performed to build a performance database before and after the accelerated aging test with shelf life items including development prototypes and initial production items, based on which the lifetime prediction should also be carried out. In addition, HILS must be applied for the acceptance test with the initial and follow-up production items, and also for ASRP for the long-term storage products in order to secure systematic quality assurance. Results: The results for the life cycle reliability Improving of domestic development of guided missiles are DB building of prescription Item performance, active application of HILS, Management associated with guided missiles life cycle and to Secure technology data about the introduction of foreign guided missiles. Conclusion: Furthermore, it is demanded that DTaQ, the managing agency of ASRP, actively take part in the process to maintain reliability engagement consistency over the life cycle of guided missiles.