IMPROVED METHOD FOR FAULT DETECTION IN AN AIRCRAFT AND SYSTEM CONFIGURED TO EXECUTE THE METHOD.

Abstract

The invention relates to a method for detecting and locating a fault in an input sensor (10a) of a flight control computer (1000) of an aircraft. The method comprises a step of comparing a first piece of information representing a probability of occurrence of said fault, provided by a neural network, with a second piece of information representing a probability of occurrence of said fault, provided by a classifier trained to detect and locate said fault. It is thus advantageously possible to optimize fault diagnosis and fault localization of an input sensor useful for determining flight controls. Fig. 2

Description

Title of the invention: IMPROVED METHOD FOR FAULT DETECTION IN AN AIRCRAFT AND CONFIGURED SYSTEM TO CARRY OUT THE PROCESS. technical field

[0001] The present invention relates to a method for detecting faults in an aircraft system. More specifically, the invention relates to a method for detecting and locating a fault in a sensor connected to an input of an aircraft flight control computer. PREVIOUS STATE OF THE ART

[0002] Modern aircraft include numerous onboard devices and systems, including flight control computers. An aircraft flight control computer operates the control of aircraft actuators, such as control surfaces (ailerons, elevator, rudder, for example). The flight commands issued by such a computer are defined based on command instructions as well as information provided by sensors associated with the controlled elements. For example, a flight control computer controls a control surface actuator by taking into account the detected position of the control surface, which is obtained via a position sensor for that surface. To ensure the aircraft's operational safety, a flight control computer monitors the various sensors in order to detect and report any sensor malfunctions.Given the very high reliability and availability required of a flight control computer, it is standard practice to dedicate the processing power of a flight control computer to aircraft control alone. Consequently, sensor monitoring by a flight control computer is limited to detecting and reporting faults, without locating or identifying the specific fault. A maintenance technician must then troubleshoot the fault, which may, for example, be related to the sensor itself or to the wiring between the sensor and the flight control computer. This troubleshooting process can be particularly time-consuming, as the sensors used are generally passive and not designed to transmit information about potential faults.It would be desirable to be able to efficiently identify and locate a fault in order to optimize the execution of maintenance operations and reduce the downtime of an aircraft undergoing maintenance. Description of the invention

[0003] An object of the present invention is to propose an improved method for detecting and locating faults in sensors providing information signals to a flight control computer of an aircraft.

[0004] To this end, a method for detecting and locating a fault in an input sensor of an aircraft flight control computer is proposed, the method being executed by a fault detection and location module comprising electronic circuitry configured to execute the steps of said method, which includes:

[0005] - a shaping of at least a first signal delivered to said sensor by said cal flight control computer and a shaping of at least a second signal delivered to said computer by said sensor, according to a predetermined format,

[0006] - a step of analyzing said first and second signals shaped by a neural network trained to detect and locate said fault from said first and second signals representative of said formatted signals delivered by said flight control computer,

[0007] - a step of comparing a first representative piece of information to a pro probability of occurrence of said fault, delivered by said neural network and, with a second piece of information representing a probability of occurrence of said fault, delivered by a classifier trained to detect and locate said fault, from signals representative of said signals formatted, then,

[0008] - a provision of a third piece of information representative of a probability occurrence of said failure based on said first and second pieces of information.

[0009] It is thus advantageously possible to optimize a fault diagnosis and a localization or an estimation of the location of a fault of an input sensor useful for determining flight controls.

[0010] Furthermore, when the fault detection and localization module comprising said electronic circuitry is independent of the main processor or main processors of the flight control computer, the computing capacity of these processors remains dedicated to the determination of flight control signals and the performance and safety of the flight controls are increased.

[0011] The fault detection and localization method according to the invention may further comprise the following features, considered individually or in combination:

[0012] - The method further includes a comparison of the third piece of information by relative to at least one predetermined threshold value.

[0013] - The method further comprises filtering the third piece of information and a provision of a fourth piece of information representing a probability of occurrence of said failure based on the third filtered piece of information.

[0014] The invention also relates to a device for assisting in the detection and localization of a fault in an input sensor of an aircraft flight control computer, the device comprising a fault detection and localization module including electronic circuitry configured to operate: - a formatting of at least a first signal delivered to said sensor by said flight control computer and a formatting of at least a second signal delivered to said computer by said sensor, according to a predetermined format, - an analysis step of said first and second signals formatted by a neural network trained to detect and locate said fault from said first and second signals representative of said formatted signals delivered by said flight control computer, - a step of comparing a first piece of information representing a probability of occurrence of said fault, delivered by said neural network, with a second piece of information representing a probability of occurrence of said fault, delivered by a classifier trained to detect and locate said fault, from signals representative of said signals in format, then, - a provision of at least one third piece of information representative of a probability of occurrence of said failure based on said first and second pieces of information.

[0015] The fault detection and localization device according to the invention may further comprise the following features, considered individually or in combination: - The device further includes electronic circuitry configured to perform a comparison of the third piece of information against at least one predetermined threshold value. - The device further includes electronic circuitry configured to filter said third information and to provide a fourth piece of information representing a probability of occurrence of said failure from the filtered third information.

[0016] The invention also relates to a flight control computing device comprising a first, main processor configured to determine flight control signals and a device for assisting in the detection and localization of a fault as previously described, comprising a detection and localization module fault calibration, which module includes said electronic circuitry, which circuitry being independent of said first processor.

[0017] The invention also relates to an aircraft comprising a device for assisting in the detection and localization of faults or a flight control computer as previously described.

[0018] The invention finally relates to a computer program product comprising program code instructions for executing the steps of a fault detection and localization method as previously described, and a storage medium comprising a computer program product as above. Brief description of the drawings

[0019] The features of the invention mentioned above, as well as others, will become clearer upon reading the following description of an exemplary embodiment, said description being made in relation to the accompanying drawings:

[0020] [Fig-1] illustrates an aircraft comprising a device for assisting in the detection and localization of a fault in an input sensor of a flight control computer according to an embodiment of the invention;

[0021] [Fig.2] schematically illustrates a device for assisting in the detection and location sizing of a failure of an input sensor of a flight control computer according to an embodiment of the invention;

[0022] [Fig.3] schematically illustrates a method for assisting in the detection and localization of a failure of an input sensor of a flight control computer executed by the device for assisting and localizing a failure already illustrated on [Fig.2];

[0023] [Fig.4] schematically illustrates an internal architecture of the fault assistance and localization device already illustrated in [Fig.2].

[0024] [Fig. 5] schematically illustrates internal details of the fault assistance and localization device already illustrated in [Fig. 2], comprising a post-processing unit; and,

[0025] [Fig.6] schematically illustrates details of the post-processing unit already illustrated on [Fig.5] of the fault assistance and localization device.

[0026] DETAILED STATEMENT OF IMPROVEMENTS

[0027] Figure 1 schematically and symbolically represents an aircraft 1 comprising a device (not detailed in Figure 1) for assisting in the detection and localization of faults in input sensors of a flight control computer of the aircraft 1. Advantageously, such a device installed in the aircraft 1 optimizes the detection and localization of a specific fault in a sensor connected to a flight control computer of the aircraft 1. More generally, the device assisting in the fault detection and localization 10 is configured to detect a plurality of fault types and a plurality of faults, as well as the at least approximate, if not more precise, localization of each of the detectable and detected faults for the set of sensors connected to one or more inputs of an aircraft flight control computer 1.

[0028] In the following description, the terms "connection link carrying a signal," "signal carried by said connection link," and "information encoded by this signal carried by this connection link" are used interchangeably. For example, a reference "P" designates both an electrical signal P and a connection link P that carries the signal P, as well as information P carried (or encoded) by the signal P on the connection link that carries the signal P.

[0029] Figure 2 schematically and symbolically represents a flight control computer 1000 of aircraft 1, whose inputs are connected to sensors, for example, control surface position sensors of aircraft 1, and whose outputs are connected to actuators, for example, control surface actuators of aircraft 1. For the sake of simplification, a single sensor 10a is shown in Figure 2, although many sensors of different types can be connected to the input of the flight control computer 1000. For the same reason of simplifying the description of the invention, a single flight control actuator control signal 1001 is shown in Figure 2, although many actuators of different types can be connected to the output of the flight control computer 1000.

[0030] According to the example described, the sensor 10a is connected to the flight control computer 1000 by a first connection carrying a first signal 10b delivered by the flight control computer 1000 to the sensor 10a, and by a second connection carrying a second signal 10c delivered to the flight control computer 1000 by the sensor 10a when the first signal 10b has a predetermined shape. The signal 10b is, for example, a power supply signal for the sensor 10a, or an electrical excitation signal for the sensor 10a, useful for its nominal operation. Such an excitation signal makes it possible, for example, to power a moving element whose movement causes a variation in an output signal of the sensor 10a, such as the signal 10c, for example. Obviously, depending on the nature and type of sensor, additional connections may exist and several signals of one or more types may be delivered by the computer 1000 to the sensor 10a, and vice versa.

[0031] Advantageously, the flight control computer 1000 includes a fault detection and localization assistance device 10 for, in particular, the detection and localization of faults in sensor 10a. To this end, the first and second signals 10b and 10c are connected to the fault detection and localization assistance device 10. Fault localization is performed within the flight control computer 10. In other words, the connections between the flight control computer 10 and the sensor 10a pass through the fault detection and localization assistance device 10. More broadly, this is also true for all connections between the flight control computer 1000 and the various sensors connected to it, at the input of the flight control computer 1000. Thus, since the fault detection and localization assistance device 10 is integrated into the flight control computer 1000, its operation does not require the installation of any specific wiring.On the one hand, this helps maintain operational safety; on the other hand, it even allows for the implementation of such a fault detection and localization assistance device 10 in an existing aircraft flight control computer simply by replacing said flight control computer. The flight control computer 1000 also includes a flight control control unit 100, also referred to here as the "main processor 100" of the flight control computer. The main processor 100 is configured to determine the state of the flight control outputs to the flight control actuators, based on the setpoint inputs and the information and signals from the various sensors connected to the flight control computer.The command signals applied to the flight control computer may originate from command devices (e.g., a control stick or steering wheel in the cockpit of aircraft 1), and / or from a flight assistance device (e.g., a flight control correction system or an automated air navigation aid system).

[0032] According to one embodiment, the fault detection and localization assistance device 10 delivers to the main processor 100 input information in the form of a signal 12, which is representative of the state of the signal 10c provided by the sensor 10a as input to the flight control computer 1000, as well as information 11 (also in the form of a signal) representing a probability of failure of a predefined type of sensor 10a at a predefined location of the aircraft's onboard systems 1. According to one embodiment, the information 11, carried by a coded signal, is composite digital information, that is to say, it comprises a plurality of fields each representing an element of information relating to the probability of a failure in relation to a type of failure of the sensor 10a.For example, one information field codes a fault type from a list of predetermined fault types, another information field codes a fault from a list of predetermined faults, and yet another field codes a fault zone or location within the aircraft systems from a list of predetermined zones or locations. In one embodiment, the processor 100 generates a signal. information 1002 on at least one of its outputs, from the internal signal 12, aimed at notifying a third-party system of the presence of a failure of a flight control sensor, for example an internal warning device in aircraft 1 or a ground station configured to supervise the condition of aircraft 1 and any maintenance operations to be carried out.

[0033] According to one embodiment, the information 11 is an analog or digital signal associated with two predetermined states, one state encoding a fault detection and the other state encoding the absence of a fault. According to this example, the same applies to the signal 1002.

[0034] Cleverly and advantageously, the fault detection and localization assistance device 10 of the flight control computer 1000 includes a neural network NN and a classifier CLASS as well as a shaping module PRE configured to operate a normalization of the signals transmitted from the flight control computer 1000 to the sensors connected to it and from these sensors to the flight control computer 1000.

[0035] Advantageously, the neural network NN is configured to be able to provide a probability of occurrence of sensor failure, and in particular, among all the sensors that are connected to the input of the flight control computer 1000, to provide information representative of a probability of occurrence of failures of sensor 10a. A failure of sensor 10a can be a power supply failure of sensor 10a, due to a fault in the connection carrying the signal 10b, or a fault in the connection at the output of sensor 10a, i.e. a fault in the link carrying the signal 10c, or even an internal fault in sensor 10a, for example a fault in an internal transducer or any other internal element or component of sensor 10a.To provide information on the probability of fault occurrence, the neural network NN is first trained using predetermined signals corresponding to a plurality of scenarios or configurations related to normal operating states and abnormal states, i.e., malfunction states. This corresponds, for example, to supervised learning. In one embodiment, the neural network NN is trained before being integrated into the aircraft systems for operational use. In another variant, the neural network NN is used for fault detection and localization during certain flight and ground taxiing periods of aircraft 1, while simultaneously being used in training mode during other flight and taxiing periods of aircraft 1.

[0036] The normalization operations of the signals applied as input to the NN neural network ensure that the format of these signals conforms to the signals previously applied during a training phase (in particular supervised learning) of the NN neural network prior to its use. on board the aircraft. The CLASS classifier of the fault detection and localization assistance device 10 of the flight control computer 1000 is implemented in a unit (or module) called "post processing" POST, which allows, from the same signals as those applied to the input of the neural network NN, to obtain a second information of the probability of failure of the sensor 10a, as well as of the other sensors connected to the input of the flight control computer 1000 not shown in the figures.

[0037] Advantageously and cleverly, it is then possible to verify the consistency of two pieces of information representing the probability of a failure obtained by two different means, namely on the one hand a neural network, for example a fully connected neural network (FCNN) and a classifier connected to a database of failure information, and then to provide a third piece of information on the probability of occurrence of a failure of a sensor connected to the input of the flight control computer 1000. This makes it possible to achieve a desired performance of the device for assisting in the detection and localization of failures 10 using a less complex neural network than if the neural network were used alone (without a classifier).This also simplifies the training of the neural network, for example by using a more restricted training dataset, the classifier making it possible to compensate for unlikely scenarios for which the neural network would not have been trained.

[0038] It should be noted that the learning phase(s) of the neural network NN, as well as the structure of the classifier CLASS associated with a database DB, are such that probability information for a failure includes, or is associated with, information on the location of said failure. For example, the scenarios chosen to simulate or reproduce failures of the input sensors of the flight control computer 1000 or of related circuits useful for the operation of the sensors, include reproductions or simulations of failures of the same type at different locations. For example, in the case of leakage current, the fault inducing such leakage current is created at several points along the same electrical equipotential bonding, so as to obtain diverse and varied configurations of the other signals related to the same sensor as the one for which a failure is simulated.

[0039] According to one embodiment, the fault detection and localization assistance device 10 of a sensor is independent of the main processor 100 in the flight control computer 1000. In other words, this means that, apart from the signals delivered by the device 10 to the main processor 100, these two elements do not share their respective computing power to perform processing. In other words, fault detection and / or localization is performed by the device 10 and notified to the main processor 100 which can take it into account for determining the flight controls, but the computing power of the main processor 100 is not made available to the method of detecting and locating faults of an input sensor of the flight control computer 1000, in order to optimize safety in determining the flight controls of the aircraft 1.

[0040] The [Fig.3] is a flowchart illustrating steps in a process for providing information representative of a probability of occurrence of a failure of the sensor 10a connected to the input of the flight control computer 1000, from two other intermediate pieces of information representative of a probability of occurrence of a failure of the sensor 10a respectively obtained using a network of the neural network NN of the device for assisting the detection and localization of a failure 10 and the classifier CLASS of this same device for assisting the detection and localization of a failure 10. .

[0041] An initial step S0 is an initialization step for all the systems described, at the end of which all the aircraft systems are correctly initialized, configured, and ready to operate nominally. During a step S1, the fault detection and localization assistance device 10 performs a shaping, also called normalization or conformity, of the signals related to sensor 10a, whether signals coming from sensor 10a or signals destined for sensor 10a. The signals thus shaped are applied to the input of the neural network NN on the one hand and to the input of the classifier CLASS on the other. Then, during a step S2, the neural network NN determines and provides initial information PI representing a probability of a fault based on an analysis of the shaped signals 10b and 10c applied to the input of the neural network NN.

[0042] Signals 10b and 10c being further applied to the input of the CLASS classifier, a second information P2 representing a probability of failure is determined by the CLASS classifier connected to its database DB, from the signals 10b and 10c which have been formatted and then applied to the input of the CLASS classifier, so as to compare, in a step S3, the first information PI representing a probability of failure and the second information P2 representing a probability of failure thus obtained.A third piece of information P3, representing a probability of occurrence of a failure of sensor 10a, resulting from the comparison between the first piece of information PI, representing a probability of a failure, and the second piece of information P2, representing a probability of a failure, is then determined during step S3, so as to implement a classification step, and then provided as output of the device assisting in the detection and localization of a failure during a step S4.

[0043] In one embodiment, the information signal 11 delivered by the fault detection and localization assistance device 10 is a signal carrying or encoding the information P3. In one embodiment, an additional step of comparing the information P3 with one or more threshold values ​​T is performed so as to implement an improved decision step for detecting a fault in the sensor 10a. In one embodiment, a final time filtering is performed at the output of the fault detection and localization assistance device so as to eliminate accidental transients and to confirm over time the state of the final information representing a probability of occurrence of a fault, provided at the output of the device 10.

[0044] Figure 5 schematically illustrates internal details of the fault detection and localization assistance device 10 connected to the sensor 10a via the connecting links carrying the signals 10b and 10c. The PRE preprocessing module is configured to perform the shaping or normalization of the signals 10b and 10c and to deliver at its output as many normalized signals as input signals applied to it. The set of output signals applied to the input of the neural network NN is called I and is also applied to the input of the POST post-processing module, which performs subsequent processing after the determination of the PI information, namely the operations carried out during steps S3 and S4 of the process described in relation to Figure 3. The information signals 11 and 12 delivered at the output of the device 10 originate from the POST post-processing module.

[0045] Fig. 6 schematically and symbolically illustrates an internal electronic circuitry of the POST post-processing module configured to operate the aforementioned steps S3 and S4 in which the PI and P2 information are compared by a comparator circuit Cl to generate an information signal P3, as well as a comparator circuit C2 used to compare the P3 information with one or more threshold values ​​T, optional, and a time filtering circuit F, also optional, to perform time filtering of the output signal, if necessary.

[0046] Thus, the PI information corresponds to a probability of occurrence of a failure of the sensor 10a as provided by the neural network NN, the classifier CLASS determines a statistical membership P2 of a failure to a type of failure among predefined failure types stored in the database DB of predefined failures, and the comparison stage C2 and the filter F jointly or separately define a final decision module, when implemented.

[0047] Figure 4 is a schematic representation of an example of the internal architecture of the fault detection and localization assistance device 10. For illustrative purposes, Figure 4 shows an internal arrangement of the fault detection and localization assistance device 10 as installed in aircraft 1. Note that [Fig.4] could also schematically illustrate an example of hardware architecture of the internal fault detection and localization module of the fault detection and localization assistance device 10.

[0048] According to the hardware architecture example shown in [Fig.4], the fault detection and localization device 10 then comprises, connected by a communication bus 10-9: a processor or CPU (Central Processing Unit) 10-1; a RAM (Random Access Memory) 10-2; a ROM (Read Only Memory) 10-3; a storage unit such as a hard disk drive (or a storage media reader, such as an SD card reader (Secure Digital)) 10-4; a communication interface module 10-5 enabling the system of the fault detection and localization assistance device 10 to communicate with remote devices, such as other on-board systems of the aircraft 1, including elements related to the CLASS classifier and the NN neural network used.

[0049] The processor 10-1 of the fault detection and localization assistance device 10 is capable of executing instructions loaded into RAM 10-2 from ROM 10-3, external memory (not shown), a storage medium (such as an SD card), or a communication network. When the fault detection and localization assistance device 10 is powered on, the processor 10-1 is capable of reading instructions from RAM 10-2 and executing them. These instructions form a computer program causing the processor 10-1 to implement all or part of a fault detection and localization assistance method described in relation to [Fig. 3] or described variants of this method.

[0050] All or part of the method described in relation to [Fig. 4] or its described variants can be implemented in software form by executing a set of instructions by a programmable machine, for example a DSP (Digital Signal Processor) or a microcontroller, or be implemented in hardware form by a dedicated machine or component, for example a FPGA (Field-Programmable Gate Array) or an ASIC (Application-Specific Integrated Circuit). In general, the system for assisting in the detection and localization of a sensor fault 10 comprises electronic circuitry configured to implement the described method in relation to itself.Obviously, the fault detection and location assistance device 10 also includes all the elements usually present in a system comprising a control unit and its peripherals, such as, a power supply circuit, a power supply monitoring circuit, one or more clock circuits, a reset circuit, input / output ports, interrupt inputs, bus drivers, this list being non-existent. exhaustive.

[0051] In one embodiment, the signals processed by the neural network correspond to analog signals. In another embodiment, the signals processed by the neural network correspond to digital signals. In yet another embodiment, the signals processed by the neural network correspond to a combination of analog and digital signals.

Claims

Demands

1. A method for detecting and locating a fault in an input sensor (10a) of a flight control computer (1000) of an aircraft (1), the method being carried out by a fault detection and location module (10) comprising electronic circuitry configured to carry out the steps of said method, which includes: - a shaping (S1) of at least a first signal (10b) delivered to said sensor (10a) by said flight control computer (1000) and a shaping of at least a second signal (10c) delivered to said computer (1000) by said sensor (10a), according to a predetermined format, - an analysis (S2) of said first (10b) and second (10c) shaped signals, by a neural network trained to perform a detection and location of said fault from said first (10a) and second (10b) signals representative of said shaped signals delivered by said flight control computer (1000),- a comparison (S3) of a first piece of information representing a probability of occurrence of said fault, delivered by said neural network, with a second piece of information representing a probability of occurrence of said fault, delivered by a classifier trained to detect and locate said fault, from signals representative of said signals (10b, 10c) in format, then, - a provision (S4) of at least a third piece of information (11) representing a probability of occurrence of said fault from said first and second pieces of information.

2. A method for detecting and locating a fault according to claim 1, further comprising a comparison of said third information (11) with respect to at least one predetermined threshold value (T).

3. A method for detecting and locating a fault according to claim 1 or 2, further comprising filtering (S4a) said third piece of information and providing a fourth piece of information (lia) representing sensing a probability of occurrence of said failure from the third filtered information.

4. Device for assisting in the detection and localization of a fault (10) in an input sensor of an aircraft flight control computer, the device comprising a fault detection and localization module including electronic circuitry configured to perform: - a shaping of at least a first signal delivered to said sensor by said flight control computer and a shaping of at least a second signal delivered to said computer by said sensor, according to a predetermined format, - an analysis of said first and second shaped signals, by a neural network trained to perform a detection and localization of said fault from said first and second signals representative of said shaped signals delivered by said flight control computer, - a comparison of a first piece of information with a probability of occurrence of said fault,delivered by said neural network, with a second piece of information representing a probability of occurrence of said fault, delivered by a classifier trained to detect and locate said fault, from signals representative of said signals in their formatted form, and then - the provision of at least a third piece of information representing a probability of occurrence of said fault from said first and second pieces of information.

5. Device for assisting in the detection and localization of a fault (10) according to claim 4, further comprising electronic circuitry configured to operate a filtering of said third information and to operate a provision of a fourth information representative of a probability of occurrence of said fault from the filtered third information.

6. Flight control computing device (1000) comprising a first, main processor (100) configured to determine flight control signals and a detection assistance device and to the localization of a fault (10) according to any one of claims 4 to 5 comprising a fault detection and localization module comprising said electronic circuitry, which is independent of said first processor.

7. Aircraft comprising a fault detection and localization assistance device according to any one of claims 4 to 5 or a flight control computer device according to claim 6.

8. Product computer program comprising program code instructions for executing the steps of a process according to any one of claims 1 to 3 when said instructions are executed by a processor of a fault detection and localization assistance device.

9. Storage medium comprising a computer program product according to claim 8.

Images