SYSTEM FOR DISCRIMINATING DROPLET SIZE IN SUPERCOOLING FOR AN AIRCRAFT AND METHOD FOR USING THE SYSTEM
The system employs a laser-based interference method with a neural network for accurate and economical droplet size differentiation, addressing the limitations of existing systems by enhancing precision and reducing sensitivity to solar radiation.
Patent Information
- Authority / Receiving Office
- FR · FR
- Patent Type
- Applications
- Current Assignee / Owner
- SAFRAN AEROSYST
- Filing Date
- 2024-11-29
- Publication Date
- 2026-06-05
AI Technical Summary
Existing systems for discriminating supercooled droplets in aircraft icing conditions are expensive, sensitive to solar radiation, and limited to small volumes, lacking the ability to accurately differentiate droplets based on size without interference.
A system using a laser source to generate optical back-injection interference signals and a convolutional neural network for droplet size classification, utilizing a compact laser diode and amplifier to process interference signals for accurate droplet size discrimination.
Enables cost-effective, solar radiation-resistant droplet size differentiation, overcoming volume limitations and improving accuracy in distinguishing supercooled droplets without edge detection reliance.
Smart Images
Figure 00000000_0000_ABST
Abstract
Description
Title of the invention: SYSTEM FOR DISCRIMINATING DROPLET SIZE IN SUPERCOOLING FOR AN AIRCRAFT AND METHOD FOR USING THE SYSTEM technical field
[0001] The invention relates to the field of analyzing the environmental flight conditions of an aircraft. It relates in particular to a system for discriminating the size of supercooled droplets for an aircraft and to a method of using this system. Previous technique
[0002] In the aeronautical field, regulations define icing conditions (likely to impair flight) in which certain aircraft (airplane, helicopter, drone...) are certified to fly.
[0003] These icing conditions (or icing conditions) exist when the air contains droplets in a supercooled state (or supercooled droplets), that is to say, droplets of liquid water at a negative temperature.
[0004] The “Code of Federal Regulation” precisely defines three categories of icing conditions in its annexes. Annex C describes the case of supercooled water droplets with a diameter less than 100 µm and for which the average diameter is generally on the order of 100 µm. Annex O concerns supercooled water droplets with a diameter greater than 100 µm. Finally, Annex D concerns ice crystals.
[0005] In addition, the differentiation of these categories by the diameter of the drops is linked to the area where the layer of frost appears: drops with a diameter less than 100pm form frost on the leading edge, those with a diameter greater than 100pm cause it to appear further on the aerodynamic surface of the aircraft (which deteriorates its aerodynamic performance), and the crystals of Annex D can obstruct sensors such as pitot probes or cool the engines which deteriorates flight performance.
[0006] Thus, the existence of these categories presupposes the ability to equip aircraft with systems capable of distinguishing each of these icing conditions within their environment. In particular, in order to distinguish the icing conditions falling under Annex O from those falling under Annex C, it is necessary to use systems capable of discriminating supercooled water droplets based on their size (i.e., their diameter).
[0007] There are currently two main types of sensor: atmospheric or accretion. The first detects icing conditions by detecting droplets or crystals in the atmosphere. The second detects the accretion of frost on a surface.
[0008] These sensors are based on different measurement principles (mechanical, acoustic, thermal, optical...) but despite their great diversity, only two technologies have demonstrated the ability to discriminate between the conditions covered by Annex O and those covered by Annex C: optical interferometry and light scattering.
[0009] Both of these technologies perform detection on a small volume, allowing them to isolate the signal from large individual droplets. They rely on the use of high-speed, high-frequency, and sensitive optoelectronic components and therefore involve expensive systems. Furthermore, they use a detector and a light source that are separate from each other, making them very sensitive to solar radiation, which can interfere with the measurement. Summary of the invention
[0010] The present invention proposes a solution to these drawbacks.
[0011] Thus, one objective of the invention is to propose a simple, economical system capable of detecting small scattering signals coming specifically from supercooled droplets without being dazzled by ambient light.
[0012] To this end, the invention, according to a first aspect, relates to a system for discriminating the size of supercooled droplets for an aircraft, said system comprising at least one laser source configured to emit a laser beam and a focusing device, intended to focus the laser beam into a cloud of supercooled droplets,
[0013] said system being characterized in that the laser source is configured to generate an optical back-injection type interference signal from a reflection of the laser beam in the cloud of supercooled droplets and in that it further comprises a processing unit configured to perform the acquisition of the interference signal and the analysis of the amplitude variations of said interference signal by a convolutional neural network so as to classify the droplets of the cloud according to their size.
[0014] The system according to the invention may comprise one or more of the following features, taken individually or in combination with each other:
[0015] - the laser source comprises a power supply unit and a laser diode, of which the The wavelength is preferably between 1520nm and 1580nm.
[0016] - the system further comprises an amplifier, positioned between the laser source and the processing unit, and configured to amplify the interference signal from the laser source.
[0017] - the convolutional neural network has an architecture comprising a stack of one-dimensional convolutional layers with pooling layers between two convolutional layers.
[0018] - the convolutional neural network has an "inception" type architecture comprising several layers of convolutional networks, each layer comprising convolutions at different spatial scales.
[0019] - the system further comprises a second laser source, the second source laser being associated with a second focusing device and being configured to generate a second optical back-injection type interference signal from a second reflection of a second laser beam emitted by said second laser source in the supercooled droplet cloud, the processing unit being configured to acquire all interference signals and analyze the amplitude variations of said interference signals by the convolutional neural network so as to classify the droplets in the cloud according to their size.
[0020] - the convolutional neural network comprises several corresponding channels respectively to the different interference signals and the processing unit is configured so that, a first convolutional layer operates on all channels and merges resulting kernels into a single output space.
[0021] - the convolutional neural network has an architecture comprising a stack of one-dimensional convolutional layers with pooling layers between two convolutional layers.
[0022] - the convolutional neural network (has an "inception" type architecture) comprising several layers of convolutional networks, each layer comprising convolutions at different spatial scales.
[0023] The invention according to a second aspect also relates to a method of using a supercooled droplet size discrimination system for an aircraft according to the first aspect, said method comprising the following steps:
[0024] - acquisition, by the processing unit, of the feedback-injection type interference signal optics from the laser source; and,
[0025] - analysis, by the processing unit, via a convolutional neural network, of the variations the amplitude of said interference signal so as to classify the cloud droplets according to their size. Brief description of the drawings
[0026] The invention will be better understood with the aid of the following description, given solely by way of example and made with reference to the accompanying drawings in which:
[0027] [Fig.1] is a schematic representation of a supercooled droplet size discrimination system for an aircraft according to a first embodiment of the invention;
[0028] [Fig.2] is a functional diagram illustrating the analysis carried out by the processing unit of the system according to the first embodiment of the invention;
[0029] [Fig.3] is a schematic representation of a supercooled droplet size discrimination system for an aircraft according to a second embodiment of the invention;
[0030] [Fig.4] is a functional diagram illustrating the analysis carried out by the processing unit of the system according to the second embodiment of the invention;
[0031] [Fig.5] is a set of optical back-injection type interferometry signals according to examples of signals acquired by a processing unit of a system according to the invention;
[0032] [Fig. 6] is an example of the result of classifying supercooled droplets according to their size as obtained by a system according to the invention; and,
[0033] [Fig.7] is a step diagram of a method of use according to an implementation of the invention. Description of the implementation methods
[0034] With reference to [Fig.1], we will now describe an embodiment of a system 101 for discriminating the size of supercooled droplets for an aircraft according to the invention.
[0035] Such a system can be installed in any type of aircraft such as, for example, an airplane, a drone or a helicopter. In the example shown, the system 101 includes a laser source 103 configured to emit a laser beam 105 and a focusing device 107 designed to focus the laser beam 105 into a cloud 109 of supercooled droplets. For example, the focusing device could be a lens with a numerical aperture between 0.5 and 0.8, for instance, 0.68.
[0036] Such a cloud may, for example, include fog and a mixture of supercooled droplets of variable size (i.e. diameter) or only supercooled droplets of identical size.
[0037] The term "droplets" used here and in what follows refers to water droplets. The term SLD (from the English "Supercooled Large Droplets") also refers to supercooled water droplets with a diameter greater than 50 µm.
[0038] In the non-limiting example shown in [Fig.1], the laser source 103 comprises a power supply unit 103a and a laser diode 103b, the wavelength of which can be, for example, between 1520nm and 1580nm.
[0039] Advantageously, this type of laser source is compact, inexpensive, and allows the generation of a Self-Mixing type interference signal (i.e. an interference signal obtained by optical back-injection, also called optical back-injection type, which is described in more detail later) which corresponds to a voltage and which is directly usable by a processing unit.
[0040] Indeed, in the invention, the laser source 103 is configured to generate a Self-Mixing type interference signal from a reflection of the laser beam 105 in the cloud 109 of supercooled droplets.
[0041] In particular, the system uses Self-Mixing Interferometry (SMI), the principle of which is based on the dynamic regime of a laser source subjected to feedback. Specifically, in the example shown, a portion of the laser beam 105 that is reflected, in this case by a droplet, is reinjected into the cavity of the laser source 103 and disturbs it, generating interference. This interference, which corresponds to fluctuations in the voltage across the laser diode 103b in the example shown, depends directly on the relative displacements of the droplet with respect to the laser source 103 and makes it possible to determine the size of this droplet through its analysis.
[0042] In the non-limiting example shown in [Fig.1] also, the system 101 further includes a processing unit 113 which is configured to acquire the interference signal and analyze the amplitude variations of this interference signal by a convolutional neural network so as to classify the droplets of the cloud 109 according to their size.
[0043] Fig. 2 illustrates in more detail the processing of an interference signal 115 which is carried out by the processing unit 113 via the use of a convolutional neural network 117 whose output data 119 correspond to a classification of the cloud droplets 109 according to their size.
[0044] In particular, this classification makes it possible to establish for each droplet whether its diameter is less than or greater than 100pm and therefore whether it falls under Annex C or Annex O of the “Code of Federal Regulation”. Advantageously, using a convolutional neural network avoids the need to identify rising or falling edges in the interference signal (which is unreliable) to discriminate droplet size. Indeed, through learning based on known data (i.e., specific signals associated with droplets of known size), the processing unit (e.g., a computer) can deduce rules for identifying the size droplets from a new interference signal. In other words, training the convolutional neural network allows us to establish a statistical model capable of predicting new outcomes based on new input data (i.e., new interference signals).
[0045] By way of non-limiting example, clouds of water droplets analogous to those of icing conditions can be generated. The signals from the interferometer at the side of these clouds are recorded and labeled according to the observed scene with a unique label:
[0046] - no icing condition: no cloud in front of the laser beam which is labeled 0;
[0047] - Annex C: cloud composed of drops with a diameter less than 100 pm which is labeled 1;
[0048] - Annex O freezing drizzle: cloud composed of water droplets between 0 and 500 pm diameter which is labeled 2; and,
[0049] - Annex O Freezing rain: cloud composed of water droplets between 0 and 3 mm diameter which is labeled 3.
[0050] The signals and labels thus form two corresponding sets of data which are used to feed the neural network for its training.
[0051] By way of further example, [Fig. 5] shows four self-mixing interference signals from the same laser source, each corresponding to a different scene (i.e., a different environment in which the measurement is performed). More specifically, from top to bottom, [Fig. 5] shows a first interference signal corresponding to the measurement by system 101 of a cloud comprising fog and a first set of droplets having a first diameter, a second interference signal corresponding to the measurement by system 101 of a cloud comprising fog and a second set of droplets having a second diameter different from the first diameter, a third interference signal corresponding to the measurement by system 101 of fog alone, and a fourth interference signal corresponding to the measurement by system 101 of air.
[0052] Fig. 6 (described in more detail later) shows the results of classification of supercooled droplets according to their size obtained by the convolutional neural network 117 (implemented by the processing unit 113) for each of the interference signals shown in Fig. 5.
[0053] Furthermore, in the non-limiting example described here, the interference signals 115 acquired by the processing unit 113 correspond to the voltage across the laser diode 103b, which has been amplified by an amplifier 121. Indeed, the system 101 further includes an amplifier 121, which is positioned between the laser source 103 and the processing unit 113, and which is configured to amplify the interference signal 115 from the laser source 103. The amplifier 121 may, for example, have a bandwidth of several MegaHertz and a gain of around 80 dB. The amplifier thus allows the processing unit 113 to acquire an interference signal with an amplitude sufficient for processing.
[0054] In a particular embodiment of the invention, the convolutional neural network 117 has an architecture comprising a stack of one-dimensional convolutional layers with pooling layers between two convolutional layers. Advantageously, the low computing power required to implement such processing allows the use of a low-power embedded component-type processing unit.
[0055] In another particular embodiment, the convolutional neural network 117 features an "inception" type architecture comprising several layers of convolutional networks, each layer of which includes convolutions at different spatial scales. Such processing requires greater computing power and therefore the use of a more expensive component, but in return allows for better performance in the implementation of the convolutional neural network and consequently in the classification of droplets according to their size.
[0056] Figure 3 shows another embodiment of the system 101 according to the invention. In this embodiment, the system 101 comprises a plurality (i.e., at least two) of laser sources 103. Each laser source 103 is also associated with a focusing device 105 and is configured to generate a self-mixing interference signal 115 from a reflection of the laser beam 105 emitted by the laser source 103 in the cloud 109 of supercooled droplets.
[0057] The system is therefore similar to that shown in [Fig.1] with the difference that several interference signals 115 are generated by several laser sources 103 (which are all focused in the cloud 109) to then be analyzed by the processing unit 113.
[0058] Fig. 4 illustrates in more detail the processing of a plurality of interference signals 115 which is carried out by the processing unit 113 via the use of a convolutional neural network 117 whose output data 119 correspond to a classification of the cloud droplets 109 according to their size.
[0059] Thus, the processing unit 113 is configured to acquire all the interference signals 115 and to analyze the amplitude variations of these interference signals 115 by a convolutional neural network 117 in order to classify the droplets of the cloud 109 according to their size.
[0060] Advantageously, this embodiment allows the convolutional neural network 117 to extract useful information (relating to droplet size) from several interference signals. The possible variation of the conditions of Backscattering for each droplet, which can have an unpredictable effect on the acquired interference signal, does not then impact the performance of the system.
[0061] In particular, the speckles, resulting from the scattering of the laser beam 105 by the droplets and seen by the laser source 103, are different for each laser source 103. Thus, based on its training, the convolutional neural network 117 can be able to exploit only the interference signals 115 relevant to the impact of these speckles. Furthermore, this embodiment also avoids the impact of a possible failure of a laser source whose interference signal is not taken into account.
[0062] In a particular embodiment, the convolutional neural network 117 comprises several channels which correspond respectively to the different interference signals and the processing unit 113 is configured so that a first convolutional layer operates on all the channels and merges the resulting kernels into a single output space.
[0063] Once this processing step has been carried out, as in the case of the embodiment described with reference to [Fig.1], the convolutional neural network 117 can have an architecture comprising a stack of one-dimensional convolutional layers with pooling layers (also called maximum pooling layers, which is a translation from the English of the so-called "maxPooling" neural layer) between two convolutional layers or an "inception" type architecture comprising several layers of convolutional networks, each layer comprising convolutions at different spatial scales.
[0064] As mentioned above, [Fig. 6] shows an example of supercooled droplet classification results based on their size (i.e., output data from the convolutional neural network) as obtained by the convolutional neural network for each of the interference signals shown in [Fig. 5]. These different signals (i.e., those in [Fig. 5]) were previously obtained from a system such as the one shown in [Fig. 1] for different predetermined icing conditions (i.e., different scenes).
[0065] In particular, these results are shown in the form of a confusion matrix 119 in which each row corresponds to a real scene (among the four scenes corresponding to the four interference signals 115 of [Fig. 5]) and each column corresponds to a scene determined by the convolutional neural network. This matrix illustrates the reliability of the prediction model established by the convolutional neural network.
[0066] Finally, [Fig. 7] shows a step diagram of a method 701 for using the system 101 (regardless of its embodiment). Thus, the method 701 comprises a step 703 of acquisition, by the processing unit 113, of the Self-Mixing type interference signal 115 from the laser source 103 and an analysis step 705, by the unit processing 113, via a convolutional neural network 117, of the amplitude variations of the interference signal 115 in order to classify the droplets of the cloud 109 according to their size.
[0067] Finally, thanks to the invention, it is possible to classify supercooled droplets according to their size in a given environment without solar radiation altering the performance of the system and without the back-diffusion conditions of the droplets also altering the performance of the system.
Claims
Demands
1. A system (101) for discriminating the size of supercooled droplets for an aircraft, said system (101) comprising at least one laser source (103) configured to emit a laser beam (105) and a focusing device (107) for focusing the laser beam (105) into a cloud (109) of supercooled droplets, said system (101) being characterized in that the laser source (103) is configured to generate an optical back-injection interference signal (115) from a reflection of the laser beam (105) into the cloud (109) of supercooled droplets, and in that it further comprises a processing unit (113) configured to acquire the interference signal (115) and analyze the amplitude variations of said interference signal (115) by a convolutional neural network (117) so as to classify the droplets of the cloud (109) depending on their size.
2. System according to claim 1, wherein the laser source (103) comprises a power supply housing (103a) and a laser diode (103b), the wavelength of which is preferably between 1520nm and 1580nm.
3. System according to claim 1 or claim 2, further comprising an amplifier (121), positioned between the laser source (103) and the processing unit (113), and configured to amplify the interference signal (115) from the laser source (103).
4. System according to any one of claims 1 to 3, wherein the convolutional neural network (117) has an architecture comprising a stack of one-dimensional convolutional layers with pooling layers between two convolutional layers.
5. System according to any one of claims 1 to 3, wherein the convolutional neural network (117) has an "inception" type architecture comprising several layers of convolutional networks, each layer comprising convolutions at different spatial scales.
6. A system according to any one of claims 1 to 3, further comprising a second laser source (103), the second laser source (103) being associated with a second focusing device (107) and being configured to generate a second interference signal (115) of optical back-injection type from a second reflection of a second laser beam (105) emitted by said second laser source (103) in the cloud (109) of supercooled droplets, the processing unit (113) being configured to acquire all interference signals (115) and to analyze the amplitude variations of said interference signals (115) by the convolutional neural network (117) so as to classify the droplets of the cloud (109) according to their size.
7. System according to claim 6, wherein the convolutional neural network (117) comprises several channels corresponding respectively to the different interference signals and the processing unit (113) is configured such that a first convolutional layer operates on all channels and merges the resulting kernels into a single output space.
8. System according to claim 7, wherein the convolutional neural network (117) has an architecture comprising a stack of one-dimensional convolutional layers with pooling layers between two convolutional layers.
9. System according to claim 7, wherein the convolutional neural network (117) has an "inception" type architecture comprising several layers of convolutional networks, each layer comprising convolutions at different spatial scales.
10. A method (701) for using a supercooled droplet size discrimination system (101) for an aircraft according to any one of the preceding claims, said method (701) comprising the following steps: - acquisition (703), by the processing unit (113), of the optical back-injection interference signal (115) from the laser source (103); and, - analysis (705), by the processing unit (113), via a convolutional neural network (117), of the amplitude variations of said interference signal (115) so as to classify the droplets of the cloud (109) according to their size.