Method for monitoring brake wear

Abstract

The invention relates to a method (100) for monitoring wear of a heat sink of an aircraft brake, the method being implemented by a monitoring device comprising electronic circuitry suitable for implementing the method. The method comprises at least the following steps: - (Step 0) Initializing an environmental model, step 0 comprising the following phases: o (Phase 0.1) Constructing a dataset comprising a plurality of cooling profiles associated with cooling environmental conditions; o (Phase 0.2) Preprocessing the dataset with a view to extracting a characteristic cooling time from each cooling profile; o (Phase 0.3) Training the environmental model to predict an impact of the environmental conditions on a cooling time. - (Step 1) Collecting temperature data from at least one temperature sensor of the heat sink; - (Step 2) Determining a cooling time of the heat sink based on the collected temperature data and using the environmental model, with a view to determining the impact of the environmental conditions on the cooling time; - (Step 3) Alerting and / or scheduling and / or carrying out a maintenance action on the heat sink.

Description

[0001] METHOD FOR CONTROLLING BRAKE WEAR

[0002] TECHNICAL FIELD

[0003] The invention relates to the field of aircraft brake wear control.

[0004] STATE OF PRIOR ART

[0005] The heat sink is the overlapping of discs at the landing gear wheels which, when brought into contact with each other, allow the aircraft to brake. It is known that aircraft brake heat sinks are important safety components, but they are also subject to wear. It is well known that brakes wear down with each braking operation. Therefore, it is essential to be able to perform preventative maintenance on an aircraft's brakes. The goal is to replace the brakes at the most opportune time, that is, to avoid replacing brakes that are not sufficiently worn, or conversely, to avoid leaving brakes in place that are excessively worn.

[0006] Typically, brake wear monitoring is now carried out by an operator during ground maintenance operations. This operator performs a visual inspection of a wear indicator, also known as a wear pin. This indicator is mounted on the fixed part of the brake and moves as the discs wear. It allows the operator to assess the remaining thickness of the heat sink and thus determine the degree of wear.

[0007] Document FR3068098 describes the use of a camera that allows the maintenance operator to photograph the wear indicator, facilitating wear monitoring. This photograph is then used to determine the remaining thickness of the brake heat sink.

[0008] The drawback of this method is that it requires ground maintenance, thus increasing the aircraft's time on the ground. Since these checks are sporadic, they do not allow for continuous monitoring of heat sink wear. Therefore, maintenance may be performed either prematurely—resulting in a loss of efficiency for the operator—or too late—leading to a risk of further damage to the heat sink. Because anticipating heat sink replacements is more difficult, optimizing inventory is more challenging.

[0009] In this context, it is necessary to provide a method for monitoring the wear of a heat well, enabling the planning and execution of heat well maintenance when necessary.

[0010] DESCRIPTION OF THE INVENTION

[0011] To this end, according to a first aspect, a method for monitoring the wear of a brake heat sink on an aircraft is proposed. The method is implemented by a control device comprising electronic circuitry adapted to implement the method. The method includes at least the following steps:

[0012] (Step 0) Initialize an environmental model, step 0 comprising the following phases:

[0013] (Phase 0.1) Construct a dataset comprising a plurality of cooling profiles associated with environmental cooling conditions;

[0014] (Phase 0.2) Preprocess the dataset to extract a characteristic cooling time for each cooling profile;

[0015] (Phase 0.3) Train the environmental model to predict the impact of environmental conditions on a cooling time.

[0016] (Step 1) collect temperature data from at least one temperature sensor of the heat sink;

[0017] (Step 2) determine a cooling time of the heat sink from the collected temperature data and using the environmental model to determine the impact of environmental conditions on the cooling time;

[0018] (Step 3) alert, and / or plan, and / or perform heat well maintenance action.

[0019] Thus, the control method cleverly automates and schedules the maintenance of aircraft brake heat sinks. The method according to the invention allows for the automatic and individualized monitoring of heat sink wear on different aircraft, enabling maintenance to be tailored to each aircraft.

[0020] According to a particular arrangement, step 2 includes modeling a cooling time according to: r=-t*log [((T(0)- T_env) / (T(t)-T_env )) ] with T the cooling time of the heat sink.

[0021] According to a specific provision, in step 2, the impact of environmental conditions is subtracted from the cooling time to determine a corrected cooling time.

[0022] According to a specific provision, the dataset acquired during phase 0.1 includes on the one hand a list of neighboring pairs of successive flight cooling profiles and on the other hand an environmental dataset.

[0023] According to a specific provision, phase 0.2 includes concatenating the environmental characteristics of the arrival airports of neighboring pairs.

[0024] According to a specific provision, phase 0.2 includes calculating a difference between the environmental characteristics of each neighboring pair.

[0025] According to a specific provision, phase 0.3 includes predicting a difference in cooling time between two successive flights of the same aircraft to predict the impact of environmental conditions on cooling time.

[0026] In another aspect, a control device is also proposed, comprising electronic circuitry adapted to implement the control process, which includes at least the following steps:

[0027] (Step 0) Initialize an environmental model, step 0 comprising the following phases:

[0028] (Phase 0.1) Construct a dataset comprising a plurality of cooling profiles associated with environmental cooling conditions; (Phase 0.2) Preprocess the dataset to extract a characteristic cooling time for each cooling profile;

[0029] (Phase 0.3) Train the environmental model to predict the impact of environmental conditions on a cooling time.

[0030] (Step 1) Collect temperature data from at least one temperature sensor in the heat sink;

[0031] (Step 2) Determine a cooling time for the heat sink from the collected temperature data and using the environmental model to determine the impact of environmental conditions on the cooling time;

[0032] (Step 3) Alert, and / or plan, and / or perform heat well maintenance action.

[0033] According to another aspect, a computer program product is also proposed, comprising program code instructions to execute the control process, when said program product is executed by a processor.

[0034] According to another aspect, it is also proposed a non-transient storage medium on which is stored a computer program comprising program code instructions to execute the control process, when said instructions are read from said non-transient storage medium and executed by a processor.

[0035] BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The features of the invention mentioned above, as well as others, will become clearer upon reading the following description of at least one exemplary embodiment, said description being made in relation to the accompanying drawings, among which:

[0037] [Fig. 1] schematically illustrates the sequence of a control process;

[0038] [Fig. 2] schematically illustrates a computer system adapted to implement the process.

[0039] DETAILED DESCRIPTION OF IMPLEMENTATION METHODS

[0040] Control Method. With reference to Fig. 1, a method 100 for monitoring the wear of a brake heat sink on an aircraft is proposed in its first aspect. The method 100 is implemented by a control device comprising electronic circuitry 200 adapted to implement the method 100. The electronic circuitry 200 will be described below.

[0041] Process 100 includes at least the following steps:

[0042] - (Step 0) Initialize an environmental model,

[0043] - (Step 1) Collect temperature data from at least one temperature sensor of the heat sink;

[0044] - (Step 2) Determine a cooling time for the heat sink from the collected temperature data and using the environmental model to determine the impact of environmental conditions on the cooling time;

[0045] - (Step 3) Alert, and / or plan, and / or perform maintenance action on the heat well.

[0046] Step 0 - Initialization

[0047] Process 100 includes a step 0 for initializing the environmental model.

[0048] Stage 0 includes the following phases:

[0049] - (Phase 0.1) Construct a dataset comprising a plurality of cooling profiles associated with environmental cooling conditions;

[0050] - (Phase 0.2) Preprocess the dataset to extract a characteristic cooling time for each cooling profile;

[0051] - (Phase 0.3) Train the environmental model to predict the impact of environmental conditions on a cooling time.

[0052] According to a specific provision, phase 0.3 involves predicting the difference in cooling time between two successive flights of the same aircraft to predict the impact of environmental conditions on cooling time. In other words, the objective of the environmental model is to predict how the encountered environmental conditions accelerated or slowed down cooling relative to the median environmental conditions of the dataset. By being able to predict the contribution of the environment to cooling, it is possible to subtract this contribution from the observed cooling time and thus obtain a corrected characteristic cooling time, independent of environmental conditions and more closely correlated with the level of wear.

[0053] The environmental model can be trained by teaching it to predict the difference in cooling time caused by variations in environmental conditions between two successive flights. In a specific scenario, it is assumed that the difference in wear between two successive flights is negligible. Thus, only differences in environmental conditions can explain a variation in the characteristic cooling time between these two flights.

[0054] According to a specific provision, the criteria used to determine whether two flights are consecutive are:

[0055] - The flights involve the same aircraft and the same heat well,

[0056] - There are less than seven days between the two flights,

[0057] There are fewer than ten flights separating these two flights. We chose to consider flights as successive even if they are not directly following each other in order to increase the size of our dataset. We believe that the impact of wear and tear should be negligible over ten flights.

[0058] Thus, according to this provision, the environmental model learns to predict the impact of variations in environmental conditions on cooling time.

[0059] According to an example implementation, the environmental model used is an XGBoost type regression model.

[0060] According to a specific provision, the dataset acquired during phase 0.1 comprises, on the one hand, a list of neighboring pairs of successive flight cooling profiles and, on the other hand, an environmental dataset. According to this provision, phase 0.2 involves concatenating the environmental characteristics of the arrival airports of the neighboring pairs. Then, phase 0.2 involves calculating the difference between the environmental characteristics of each neighboring pair.

[0061] Step 1 - Data Collection

[0062] As previously stated, process 100 includes a step of collecting temperature data from at least one temperature sensor in the heat sink.

[0063] In a particularly advantageous way, temperature data is collected during a parking phase after an aircraft landing.

[0064] As will be described below, analyzing brake cooling well temperature data to deduce brake wear is particularly effective. Indeed, it has been observed that brake wear is characterized by a loss of mass in its heat sink. This results in a change in the heat sink's heat capacity and a modification of the heat exchange geometry.

[0065] In addition, brake temperature data can be collected on most aircraft.

[0066] Step 2 - Determining the cooling time

[0067] Process 100 then includes a step 2 which consists of determining the cooling time of the heat sink from the collected temperature data.

[0068] According to a specific provision, step 2 involves modeling the cooling time according to: t = — t * log I — — — — 1 with T the cooling time of the heat sink.

[0069] \ T(t)-T env /

[0070] More specifically, according to this provision, the level of wear is quantified from the temperature profile by determining a characteristic brake cooling time. To determine this characteristic time (also called T), the cooling process is modeled by a physical law.

[0071] According to the arrangement presented here, the chosen physical law is the cooling law of

[0072] Newton:

[0073] Thus, the characteristic cooling time is obtained by solving the following linear system:

[0074] T = — t * log

[0075] The resulting value T represents the brake cooling time. Under a specific arrangement, this linear system can be solved using the least squares method.

[0076] Furthermore, brake wear is not the only parameter that can affect the characteristic cooling time. Other influencing parameters can also include:

[0077] - Wear and tear.

[0078] - Environmental cooling conditions (ambient temperature, pressure, humidity, wind, etc.).

[0079] - The use of BCF (Brake Control Fan). The BCF is a ventilation system placed in the wheels to accelerate the cooling of the heat sink.

[0080] - The use of external ventilation systems.

[0081] To avoid considering the impact of ventilation systems on cooling rate, the cooling phases during which the BCF (Body Controlled Cooling) is activated are not taken into account. Furthermore, to avoid considering the impact of environmental conditions on cooling rate, step 2 involves using an environmental model to determine the impact of environmental conditions on cooling time.

[0082] According to a specific provision, as detailed previously, the environmental model takes as input, during training, the concatenation of conditions encountered during two adjacent flights (training data). When used on a new flight (outside of training), the model can take as input the concatenation of the environmental conditions of that flight t and the median environmental conditions of the training data. Since the model has been trained to predict the impact of a deviation in environmental conditions on the characteristic cooling time, using the training data, the environmental model is able to determine the environmental impact on brake cooling during a new flight.

[0083] According to a specific provision, step 2 involves subtracting the impact of environmental conditions from the cooling time to determine a corrected cooling time. Determining the corrected cooling time is a particularly ingenious feature of the invention. Indeed, a correlation can be observed between the corrected T value and brake wear. In other words, the more worn the brake, the shorter the cooling time. A threshold can therefore be defined beforehand to determine when it seems appropriate to perform maintenance.

[0084] According to a particular provision, the environmental model used in step 2 is a learning model that is trained to predict the gain / loss of time induced by the environment relative to an average environment.

[0085] Step 3 - Alert and maintenance

[0086] The process then includes a step of alerting, and / or planning, and / or performing maintenance on the heat well.

[0087] More specifically, according to a particular provision, if the cooling time determined in step 2 indicates that brake wear is approaching the acceptable limit, an alert is issued to schedule and perform maintenance. (Computer program product)

[0088] In another aspect, a computer program product is proposed, comprising program code instructions to execute the control process.

[0089] Storage media

[0090] According to another aspect, a non-transient storage medium is proposed on which is stored a computer program comprising program code instructions to execute the detection process 100, when said instructions are read from said non-transient storage medium and executed by a processor.

[0091] Control device

[0092] According to another aspect, a control device is proposed comprising electronic circuitry (computer system 200) adapted to implement a process 100.

[0093] As shown schematically in Fig. 2, the computer system 200 can include, connected by a communication bus 210: a processor 201; a random access memory 202; a read-only memory 203, for example of type ROM (“Read Only Memory”) or EEPROM (“Electrically-Erasable Programmable Read Only Memory”); a storage unit 204, such as a hard disk drive (HDD) or a storage media reader, such as an SD card reader (“Secure Digital”); and an input / output interface manager 205.

[0094] The processor 201 is capable of executing instructions loaded into RAM 202 from ROM 203, external memory, a storage medium (such as an SD card), or a communication network. When the computer system 200 is powered on, the processor 201 can read instructions from RAM 202 and execute them. These instructions form a computer program that allows the processor 201 to implement process 100.

[0095] All or part of process 100 can thus 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 an FPGA (Field Programmable Gate Array) or ASIC (Application-Specific Integrated Circuit). Generally speaking, the computer system 200 includes electronic circuitry adapted and configured to implement, in software and / or hardware form, the process in relation to the computer system 200 in question.

Claims

DEMANDS 1. A method (100) for controlling the wear of a heat sink in an aircraft brake, the method being implemented by a control device comprising electronic circuitry adapted to implement the method, the method being characterized in that it comprises at least the following steps: - (Step 0) Initialize an environmental model, step 0 comprising the following phases: o (Phase 0.1) Build a dataset comprising a plurality of cooling profiles associated with environmental cooling conditions; o (Phase 0.2) Preprocess the dataset to extract a characteristic cooling time for each cooling profile; o (Phase 0.3) Train the environmental model to predict an impact of environmental conditions on a cooling time. - (Step 1) Collect temperature data from at least one temperature sensor of the heat sink; - (Step 2) Determine a cooling time for the heat sink from the collected temperature data and using the environmental model to determine the impact of environmental conditions on the cooling time; - (Step 3) Alert, and / or plan, and / or perform maintenance action on the heat well.

2. A method (100) according to claim 1, wherein step 2 comprises modeling a cooling time according to: T = — t * log ( — — — — I with T the cooling time of the heat sink; \ T(tj— T env / 3. A method according to any one of the preceding claims, wherein in step 2, the impact of environmental conditions is subtracted from the cooling time to determine a corrected cooling time.

4. A method according to any one of the preceding claims, wherein the dataset acquired during phase 0.1 comprises on the one hand a list of neighboring pairs of successive flight cooling profiles and on the other hand an environmental dataset.

5. A method according to claim 4 in which phase 0.2 comprises concatenating the environmental characteristics of the arrival airports of neighboring pairs.

6. A method according to claim 5 wherein phase 0.2 comprises calculating a difference between the environmental characteristics of each neighboring pair.

7. A method according to any one of the preceding claims, wherein phase 0.3 comprises predicting a difference in cooling time between two successive flights of the same aircraft to predict the impact of environmental conditions on cooling time.

8. Control device comprising electronic circuitry suitable for implementing the control process which includes at least the following steps: - (Step 0) Initialize an environmental model, step 0 comprising the following phases: o (Phase 0.1) Build a dataset comprising a plurality of cooling profiles associated with environmental cooling conditions; o (Phase 0.2) Preprocess the dataset to extract a characteristic cooling time for each cooling profile; o (Phase 0.3) Train the environmental model to predict an impact of environmental conditions on a cooling time. - (Step 1) Collect temperature data from at least one temperature sensor of the heat sink; - (Step 2) Determine a cooling time for the heat sink from the collected temperature data and using the environmental model to determine the impact of environmental conditions on the cooling time; - (Step 3) Alert, and / or plan, and / or perform maintenance action on the heat well.

9. Computer program product comprising program code instructions to execute the process (100) according to any one of claims 1 to 7, when said program product is executed by a processor.

10. Non-transient storage medium on which is stored a computer program comprising program code instructions to execute the method (100) according to any one of claims 1 to 7, when said instructions are read from said non-transient storage medium and executed by a processor.

Images