SYSTEM AND METHOD FOR GENERATING AN AIRCRAFT FAULT PREDICTION CLASSIFIER

    公开(公告)号:EP3660751A1

    公开(公告)日:2020-06-03

    申请号:EP19210309.1

    申请日:2019-11-20

    IPC分类号: G06N20/20 B64F5/60 G05B23/02

    摘要: A method includes receiving input data including a plurality of feature vectors and labeling each feature vector based on a temporal proximity of the feature vector to occurrence of a fault. Feature vectors that are within a threshold temporal proximity to the occurrence of the fault are labeled with a first label value and other feature vectors are labeled with a second label value. The method includes determining, for each feature vector of a subset, a probability that the label associated with the feature vector is correct. The subset includes feature vectors having labels that indicate the first label value. The method includes reassigning labels of one or more feature vectors of the subset having a probability that fails to satisfy a probability threshold and, after reassigning the labels, training an aircraft fault prediction classifier using supervised training data including the plurality of feature vectors and the labels.

    SYSTEM AND METHOD FOR AIRCRAFT FAULT DETECTION

    公开(公告)号:EP3460611A1

    公开(公告)日:2019-03-27

    申请号:EP18194089.1

    申请日:2018-09-12

    IPC分类号: G05B23/02

    摘要: An aircraft fault detection system (110) including at least one aircraft data logging device (120) configured to capture parametric flight data (111) from at least one aircraft subsystem (101), and an aircraft controller (121) coupled to the data logging device (120). The controller (121) being configured to group the parametric flight data (111) from the at least one aircraft subsystem (101) into a plurality of test states (125), one or more of the test states (125A-125n) being different from other test states (125A-125n) in the plurality of states (125), generate at least one test transition matrix (126) based on the plurality of test states (125) and determine anomalous behavior of the at least one aircraft subsystem (101) based on the at least one test transition matrix (126), and forecast faults (127) within the at least one aircraft subsystem (101) based on the anomalous behavior of the at least one aircraft subsystem (101) determined from the at least one test transition matrix (126).

    REAL TIME INCONSISTENCY DETECTION DURING COMPOSITE MATERIAL MANUFACTURING

    公开(公告)号:EP4450265A1

    公开(公告)日:2024-10-23

    申请号:EP24167279.9

    申请日:2024-03-28

    IPC分类号: B29C70/38 G05B19/418 G06T7/00

    摘要: A method, apparatus, system, and computer program product for detecting inconsistencies in an unconsolidated composite material (3005, 3021). Fiber inconsistencies (3002) are detected (3700) in sections (3030) of the fibers (3003, 3111, 3201, 3505) input into a composite material manufacturing system (3023) in real time during operation of the composite material manufacturing system (3023). Material inconsistencies (3004) are detected (3702) in the unconsolidated composite material (3005, 3121) in real time as the unconsolidated composite material (3005, 3121) is being manufactured by the composite material manufacturing system (3023) using the fibers (3003, 3111, 3201, 3505). A determination (3704) is made as to whether the material inconsistencies are present in a number of the sections (3030) in which the fiber inconsistencies are detected in real time as the unconsolidated composite material is being manufactured by the composite material manufacturing system. The fiber inconsistencies in the number of the sections in which the fibers with fiber inconsistencies resulted in the material inconsistencies in the number of the sections in the unconsolidated composite material are tracked (3706).