Abstract: The present invention relates to method for monitoring an engine (1) of an aircraft (2) operating in a given environment. The invention is characterized in that it comprises the implementation, via means for data processing (31), of the steps of: (a) receiving a sequence of n-tuples (x1-exec. . . xn-exec; yexec) of physical-parameter values relating to said aircraft (2) engine (1), including at least one endogenous parameter specific to the operation of the engine (1) and at least one exogenous parameter specific to said environment; (b) For each n-tuple (x1-exec. . . xn-exec, yexec) of the received sequence, calculating, according to a regression model, a standardized value (yexec-norm) of the endogenous parameter in relation to the exogenous parameters; (c) identifying at least one stabilized phase in said normalized sequence of n-tuples (x1-exec. . .

Abstract: A method of creating a database of operating states of an aircraft fleet, in which a computer executes the steps of acquiring parameters wherein a state of operation of an aircraft of the aircraft fleet; acquiring at least one item of degradation information indicative of a level of degradation of at least one aircraft from among the fleet of aircraft; storing series of parameters in said database, each series of parameters including parameters wherein a state of operation of one of the aircraft and if the item of degradation information has been acquired, at least one item of degradation information indicative of a level of degradation of the aircraft.

Abstract: A method and a system for monitoring an aircraft engine (2), including: acquisition and processing part (11) configured to collect a time signal of the exhaust gas temperature residual margin of the aircraft engine (2), acquisition and processing part (11) configured to smooth the time signal thus forming a first curve representing the temperature residual margin, acquisition and processing part (11) configured to identify decreasing pieces in the first curve, acquisition and processing part (11) configured to construct a second curve by concatenation of the decreasing pieces, the second curve being continuous while being restricted to the decreasing pieces of the first curve, acquisition and processing part (11) configured to construct a prediction model from the second curve to determine at least one failure forecast indicator.

Abstract: A system of non-regression tests of a designing tool including modules used to build a monitoring device of an aircraft engine is provided. The system includes a processor configured to automatically create an experience base by instrumenting behavior tests upon executing the modules, the experience base including reference input signals, sets of reference parameters, reference output signals, and collections of results of reference executions relating to the modules; start again the behavior tests on the modules depending on the corresponding reference input signals and the corresponding sets of reference parameters thus generating test output signals and collections of results of test executions; and compare the test output signals with the corresponding reference output signals and the collections of results of test execution with the corresponding collections of results of reference executions in order to test the non-regression of the designing tool.

Abstract: A method for assessing whether or not the character of a value, measured by a sensor, of a physical parameter of a device is normal. The method includes implementing steps of calculating, on the basis of a regression model associated with the plurality of pairs, an estimated value of the physical parameter; calculating a related remainder calculating, on the basis of a variance model related to the plurality of pairs, an estimated value of a variance in the physical parameter; calculating an anomaly score of the measured value on the basis of the remainder, calculating the estimated value of the variance, and calculating a mean remainder value for the plurality of pairs; comparing the anomaly score of the measured value with a standard deviation threshold; and if the anomaly score is greater than the threshold, identifying the measurement as abnormal on the interface.

Abstract: The present invention relates to method for monitoring an engine (1) of an aircraft (2) operating in a given environment. The invention is characterized in that it comprises the implementation, via means for data processing (31), of the steps of: (a) receiving a sequence of n-tuples (x1-exec . . . xn-exec; yexec) of physical-parameter values relating to said aircraft (2) engine (1), including at least one endogenous parameter specific to the operation of the engine (1) and at least one exogenous parameter specific to said environment; (b) For each n-tuple (x1-exec . . . xn-exec, yexec) of the received sequence, calculating, according to a regression model, a standardized value (yexec-norm) of the endogenous parameter in relation to the exogenous parameters; (c) identifying at least one stabilized phase in said normalized sequence of n-tuples (x1-exec . . .

Abstract: A flight data evaluation system to optimise operations of an aircraft, comprising: an acquisition circuit (3) configured to collect observation data (D1?Dn) related to a fleet of aircraft, and a processing circuit (5) configured: to assign quality values (Qi) to the observation data by applying predetermined learning models (M1?Mn) to them corresponding to their contexts, thus generating observation data enriched with quality values, to define indicators (21, 23) relative to specific elements of the aircraft, to compare the quality value (Qi) of each observation data (Di) with a predetermined threshold (S), and to analyse the observation data as a function of their quality values so as to optimise aircraft operations.

Abstract: A method for assessing whether or not the character of a value, measured by a sensor, of a physical parameter of a device is normal. The method includes implementing steps of calculating, on the basis of a regression model associated with the plurality of pairs, an estimated value of the physical parameter; calculating a related remainder; calculating, on the basis of a variance model related to the plurality of pairs, an estimated value of a variance in the physical parameter; calculating an anomaly score of the measured value on the basis of the remainder, calculating the estimated value of the variance, and calculating a mean remainder value for the plurality of pairs; comparing the anomaly score of the measured value with a standard deviation threshold; and if the anomaly score is greater than the threshold, identifying the measurement as abnormal on the interface.

Abstract: A normalization method includes: normalizing a current value of each operating parameter relative to exogenous variables using a first regression model defined on a space generated by the exogenous variables; associating the vector formed by the normalized current values of the parameters with at least one vector class of a set of predefined classes; using at one second regression model defined on the space generated by the exogenous variables for the at least one class associated with the vector to construct, for each parameter, a third regression model onto the space; and normalizing the normalized current value of each parameter relative to the exogenous variables using the third regression model.

Abstract: A method and a system for monitoring an aircraft engine (2), including: acquisition and processing part (11) configured to collect a time signal of the exhaust gas temperature residual margin of the aircraft engine (2), acquisition and processing part (11) configured to smooth the time signal thus forming a first curve representing the temperature residual margin, acquisition and processing part (11) configured to identify decreasing pieces in the first curve, acquisition and processing part (11) configured to construct a second curve by concatenation of the decreasing pieces, the second curve being continuous while being restricted to the decreasing pieces of the first curve, acquisition and processing part (11) configured to construct a prediction model from the second curve to determine at least one failure forecast indicator.

Abstract: A method of creating a database of operating states of an aircraft fleet, in which a computer executes the steps of acquiring parameters wherein a state of operation of an aircraft of the aircraft fleet; acquiring at least one item of degradation information indicative of a level of degradation of at least one aircraft from among the fleet of aircraft; storing series of parameters in said database, each series of parameters including parameters wherein a state of operation of one of the aircraft and if the item of degradation information has been acquired, at least one item of degradation information indicative of a level of degradation of the aircraft.

Abstract: The normalization method comprises: normalizing a current value of each operating parameter relative to exogenous variables with the help of a first regression model defined on a space generated by the exogenous variables; associating the vector formed by the normalized current values of the parameters with at least one vector class of a set of predefined classes; using at least one second regression model defined on the space generated by the exogenous variables for said at least one class associated with the vector to construct for each parameter a third regression model onto said space; and normalizing the normalized current value of each parameter relative to the exogenous variables with the help of the third regression model.

Abstract: The invention relates to a system of non-regression tests of a designing tool including modules (13) used to build a monitoring device (11) of an aircraft engine (7), said system of tests including: processing means (9) configured to automatically create an experience base (9e) by instrumenting behaviour tests upon executing the modules, said experience base including reference input signals (SIN—ref), sets of reference parameters, reference output signals (SOUT—ref), and collections of results of reference executions relating to said modules, processing means (9) configured to start again said behaviour tests on said modules (13) depending on the corresponding reference input signals and the corresponding sets of reference parameters thus generating test output signals (SOUT—test) and collections of results of test executions, and processing means (9) configured to compare said test output signals with the corresponding reference output signals and said collections of results of test execution with said c