A Reliability Evaluation Method for Multi-performance Degradation Products Based on Accelerated Degradation Testing

Pan, Guangze; Li, Dan; Li, Qian; Huang, Chuangmian; Mo, Bing

doi:10.1109/itaic54216.2022.9836924

Cited by 2 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Current research methods on system reliability with fusion models are on the one hand in data fusion [11][12][13] ; on the other hand, traditional reliability prediction based on fault diagnosis 14 and multiple performance degradation methods for product reliability assessment 15 . While research on interpretability has been emphasized 16 , however, there is a lack of reliability impact analysis specifically for the field of deep learning model fusion.…”

Section: Introductionmentioning

confidence: 99%

Deep learning fusion model and reliability analysis

Cai,

Gao

2023

Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023)

View full text Add to dashboard Cite

With the widespread use of big data and artificial intelligence technologies, the complexity of prediction problems such as classification, clustering, and regression is increasing, and the requirements for prediction models generally call for the fusion of different individual learners to achieve these goals. Although the prediction accuracy of the new fusion model can be improved to some extent by model fusion, the structure of the fusion model is more complex, the computationally intensive prediction time increases, and the reliability suffers. In this paper, we firstly systematically sort out the deep learning model fusion methods, secondly, analyze the coupling types of different model fusion methods and the impact on the reliability of the prediction system, and finally construct a fusion model for false information multimodal detection using model fusion methods for the needs of false information multimodal detection application scenarios and analyze its reliability impact.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep learning fusion model and reliability analysis

Cai,

Gao

2023

Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023)

View full text Add to dashboard Cite

show abstract

“…Характеристика современного бортового оборудования как интегрированной модульной авионики дана в [1]. Актуальные исследования в области достоверности контроля приведены в работах отечественных ученых [2][3][4][5][6][7][8][9][10] и зарубежных авторов [11][12][13][14][15][16].…”

Section: Introductionunclassified

Characteristics of operational control reliability of aircraft functional systems and avionics suites

Kuznetsov

2023

Naučn. vestn. MGTU GA

View full text Add to dashboard Cite

The operational control system (OCS) of civil aircraft (A/C) airborne equipment is an important component of its technical operation system (TOS). Operational control is an integral part of the technical operation process. It makes it possible to assess the technical conditions (TC) of the objects to be monitored in various states of airborne equipment operation, aircraft preparation for flight, various types of maintenance and recovery. The main property of operational control is the reliability of control. The key task of operational control is not only to determine the type of technical condition, but also to quantify the correctness or erroneousness of decision-making. Control reliability characteristics (CRC) are quantitative indicators of the degree of objectivity in decision-making. Depending on the level of task details, it is necessary to distinguish the control reliability characteristics of units, functional systems (FS) and avionics suites for various means of operational control: built-in test equipment (BITE), on-board self-contained, ground-onboard and ground systems. The choice of the control reliability characteristics is based on the system analysis and the mathematical apparatus of logic, probability theory and mathematical statistics. Rational sets of technical states and decision-making about the technical conditions of functional systems and avionics suites are formed. Based on these sets, three groups of control reliability characteristics were identified. The first group consists of conditional probabilities of transitions in the operational control process under various types of control. The second group consists of unconditional probabilities of transitions in the operational control process under various types of control. The third group consists of a posteriori decision-making probability in the operational control process under various types of control. Analytical dependences for calculating the control reliability characteristics of three groups for functional systems and avionics suites and relationships between them are determined. The air-conditioning system was used to calculate the reliability of the control.

show abstract

A Reliability Evaluation Method for Multi-performance Degradation Products Based on Accelerated Degradation Testing

Cited by 2 publications

References 11 publications

Deep learning fusion model and reliability analysis

Deep learning fusion model and reliability analysis

Characteristics of operational control reliability of aircraft functional systems and avionics suites

Contact Info

Product

Resources

About