Acoustic diagnostics of aerosol generator operation

Abstract

The present invention relates to an aerosol generating device comprising a controller for controlling the operation of the aerosol generating device, an acoustic source connected to the controller and configured to generate an acoustic signal in use, and an acoustic sensor connected to the controller and configured to detect the acoustic signal generated by the acoustic source. The controller is configured to monitor the operating status of the aerosol generating device based on the detected acoustic signal. The present invention also relates to a method of controlling an aerosol generating device.

Description

[Technical Field]

[0001] The present invention relates to an aerosol generating device and a method of operating an aerosol generating device. [Background technology]

[0002] Several types of aerosol generating systems are currently commercially available. These devices may heat the aerosol-forming substrate to a temperature at which one or more components of the aerosol-forming substrate volatilize, without burning the aerosol-forming substrate. Other devices, often referred to as nebulizers, typically generate aerosols by mechanical action, such as a vibrating mesh module. Vibrating mesh nebulizers use deformation or vibration of a mesh to force a liquid through the mesh.

[0003] In a typical vibrating mesh nebulizer, a piezoelectric element in contact with the mesh is used to generate vibrations of the mesh. The mesh is adjacent to and in direct contact with a substrate containing the liquid medication. Mesh deformation in the vibrating mesh generates a pressure field within the liquid, thereby forcing and filling the holes. The liquid forced through the holes breaks into droplets and is released into an aerosol formation chamber. Upon inhalation, ambient air passes through the aerosol formation chamber, carrying the aerosol to the user.

[0004] Various factors can affect the aerosol spray throughput of an aerosol generator equipped with a vibrating mesh. For example, if the vibrating mesh does not have optimal mechanical contact with the piezoelectric element, or if the vibrating mesh comes into contact with the cartridge holding the liquid to be vaporized, changes in the membrane's resonant frequency can occur. Additional factors that can affect the aerosol spray throughput of an aerosol generator can include changes in liquid viscosity, changes in the carrier material's performance, membrane aging, airflow turbulence during puffing, or the orientation of the device during aerosol generation. While changes in the membrane's resonant frequency can be detected by monitoring the piezoelectric element's impedance, most of the above-mentioned factors affecting aerosol spray throughput cannot be detected by impedance measurements alone.

[0005] It is therefore desirable to provide an aerosol generating device that can detect and identify the cause of variations in aerosol spray throughput.

[0006] Additionally, it would be desirable to provide an aerosol generating device that is capable of generating and collecting data regarding the performance of the aerosol generating device that can be used to enhance the user experience during operation or in subsequent analytical steps. Summary of the Invention

[0007] According to one embodiment of the present invention, there is provided an aerosol generating device comprising: a controller for controlling operation of the aerosol generating device; an acoustic source connected to the controller and configured to generate an acoustic signal in use; and an acoustic sensor connected to the controller and configured to detect the acoustic signal generated by the acoustic source, wherein the controller is configured to monitor the operational status of the aerosol generating device based on the detected acoustic signal.

[0008] The aerosol-generating device may comprise an aerosol-generating unit configured to aerosolize the aerosol-forming substrate. The aerosol-generating unit may be configured to aerosolize the aerosol-forming substrate primarily by mechanical action. The aerosol-generating unit may comprise a vibrating element. The aerosol-generating unit may comprise a vibrating mesh.

[0009] As used herein, the term "vibrating mesh" refers to any vibrating element that can be used to generate an inhalable aerosol. The vibrating element may be formed from any type of perforated membrane that serves the purpose of aerosolization.

[0010] The vibrating mesh may be an acoustic source in the aerosol generating device. The vibrating mesh may be used in the aerosol generating device as both part of the aerosol generating unit and as an acoustic source at the same time. The vibrating mesh element may operate over a wide range of frequencies. The vibrating mesh element may operate in the radio frequency range. The vibrating mesh element may operate in the range of 20 kilohertz to 300 gigahertz. The vibrating mesh element may operate in the range of 1 kilohertz to 1000 kilohertz. The vibrating mesh element may operate in the range of 10 kilohertz to 500 kilohertz. The vibrating mesh element may operate at a frequency of approximately 100 kilohertz.

[0011] During operation, the vibrating mesh may generate an aerosol as described in the introductory section of this specification. Simultaneously, the vibrating mesh generates an acoustic signal corresponding to the mechanical vibration. Depending on the vibration frequency, the generated acoustic signal may be primarily in the ultrasonic range. Such an acoustic signal may be detected with an appropriate acoustic sensor. Additionally, the mechanical vibration of the vibrating mesh may generate subharmonics within the audible acoustic range at frequencies below 20 kilohertz.

[0012] During operation of the vibrating mesh, acoustic signals generated by the vibration of the mesh may be measured with a suitable acoustic sensor. The signature of the detected acoustic signal may be analyzed to verify the operating condition of the device. In particular, the operating condition of the vibrating mesh may be verified by analysis of the acoustic signal generated by the vibrating mesh during aerosol generation. In this way, it may be verified whether the device is operating in normal or fault mode. Analysis of the acoustic signal may also identify depletion of the supply of aerosol-forming substrate. Such information may be used to inform the user of the operating status of the aerosol-generating device. Such information may also be used to adjust the operating parameters of the aerosol-generating device, thereby enhancing the overall user experience.

[0013] The aerosol generation unit may comprise one or more electromechanical elements in mechanical contact with the vibrating element, the electromechanical elements being controlled by a controller. The electromechanical element may be an annular piezoelectric mechanical element. The electromechanical element may include a plurality of piezoelectric mechanical elements. The electromechanical element may be connected to a controller of the aerosol generation device. The controller may be configured to control operation of the one or more electromechanical elements such that the vibrating mesh is excited to vibrate at a desired vibration frequency and a desired amplitude.

[0014] The vibrating element may be integrally formed with an electromechanical piezoelectric element. To this end, the vibrating element may be manufactured using microelectromechanical systems (MEMS) manufacturing techniques. Such manufacturing techniques include process techniques used in semiconductor device manufacturing. These techniques include deposition of material layers, photolithographic patterning, and etching of the material to produce the required shape. MEMS technology allows for the precision manufacturing of vibrating mesh elements.

[0015] The acoustic sensor used in the aerosol generating device may be any suitable acoustic sensor known to those skilled in the art. The acoustic sensor may be a microphone. The acoustic sensor may be a MEMS microphone. The MEMS microphone may operate based on the principle of capacitance. MEMS microphones are microscale devices that offer significant advantages. MEMS microphones have a relatively high signal-to-noise ratio (SNR), low power consumption, high sensitivity, and strong vibration resistance. Furthermore, MEMS microphones are small enough to be incorporated into highly integrated electronic products.

[0016] The acoustic sensor may be positioned at any suitable location within the aerosol generating device. The acoustic sensor may be positioned within an airflow path defined within the aerosol generating device. The acoustic sensor may be positioned at a mouthpiece portion of the aerosol generating device. The acoustic sensor may be positioned within the airflow path of the aerosol generating device and may be positioned near the vibrating mesh to ensure good acoustic conditions for detecting the acoustic signal.

[0017] The acoustic sensor may be placed in contact with a surface of the aerosol-generating device. The acoustic sensor may be placed in contact with a surface of the housing of the aerosol-generating device. By placing the acoustic sensor in contact with a surface of the aerosol-generating device, the acoustic sensor may detect acoustic signals transmitted through the material of each surface of the aerosol-generating device.

[0018] The acoustic sensor may also be positioned away from the surface of the aerosol-generating device. For example, the acoustic sensor may be suspended in an open space within the aerosol-generating device. By positioning the acoustic sensor away from the interior surface of the aerosol-generating device, the acoustic sensor may be mechanically isolated from the surface of the aerosol-generating device. In such a configuration, the acoustic sensor may be particularly sensitive to acoustic signals transmitted from the vibrating mesh to the acoustic sensor through the air in the interior volume of the aerosol-generating device.

[0019] Multiple acoustic sensors may be used to detect the acoustic signal. Using multiple acoustic sensors may increase the sensitivity of the acoustic detection. The acoustic sensors may be provided at multiple different locations within the aerosol generating device. The acoustic sensors may be the same or different types. Using different types of acoustic sensors and locating the acoustic sensors at different locations may enable the detection of the acoustic signal to cover a wider dynamic range. Using multiple acoustic sensors may also improve the spatial resolution of the detection.

[0020] The acoustic signal may be transmitted to one or more acoustic sensors via a rigid connector provided in contact with the vibrating element, which may be in direct mechanical contact with both the vibrating element and the acoustic sensor to directly transmit the acoustic signal, which may further increase the sensitivity of acoustic detection.

[0021] The acoustic signal may also be transmitted through the air within the tube. The tube may be a hollow flexible tube. One end of the tube may be provided near or in contact with the vibrating element.

[0022] The acoustic sensor may be directly connected to the electronics board. This is particularly suitable when the acoustic sensor is a MEMS microphone. The MEMS microphone may be integrated into the electronics of the electronics board. Such a system allows for sufficient amplification and noise reduction, which can be beneficial for subsequent signal processing.

[0023] The aerosol generating device includes an electronic circuit including a controller for processing the acoustic signal detected by the acoustic sensor. Processing and evaluation of the acoustic signal may include any method suitable for frequency analysis. Such methods may include frequency analysis by spectral analysis of the recorded acoustic signal. Such methods may also include amplitude analysis of the recorded acoustic signal. Spectral analysis may detect the occurrence of specific frequencies, such as subharmonics of the main vibration frequency of the vibrating mesh. The occurrence of such vibration frequencies may indicate malfunction or aging of the vibrating mesh. A low amplitude of the acoustic signal may indicate increased damping of the vibrating mesh, which may also indicate an undesirable operating condition.

[0024] The aerosol generating device may further include a memory unit. The memory unit may be used to store previously recorded acoustic signals or characteristics of previously recorded acoustic signals. Additionally or alternatively, the memory unit may be used to store a standard acoustic signal. Such a standard acoustic signal may be a calibrated acoustic signal. A standard acoustic signal is an acoustic signal that is expected or desired to be detected by one or more acoustic sensors of the aerosol generating device. A plurality of such standard acoustic signals may be stored in the memory unit.

[0025] The controller may be configured to evaluate the acoustic signal detected by the acoustic sensor by comparing the detected signal to an expected acoustic signal stored in the memory unit.

[0026] The evaluation of the acoustic signal may be performed using a predetermined diagnostic model. The classifier used to evaluate the acoustic signal may be a purely statistical model. The classifier may be a simple threshold algorithm. The evaluation of the acoustic signal may be performed using a traditional machine learning model. The traditional machine learning model may include Gaussian Mixture Modeling (GMM) or Support Vector Machine (SVM) algorithms. More recently developed models, such as deep learning models, may also be used. The machine learning model may be an image-based algorithm that uses a convolutional neural network on acoustic spectral patterns.

[0027] Such a predetermined diagnostic model may be developed based on machine learning techniques. For this purpose, the model may be trained using a dataset of experimentally recorded acoustic signals, including desired and undesired acoustic signals. A portion of this dataset may be used as a training set for tuning the controller. Once the controller used is sufficiently tuned, a further portion of the dataset may be used to verify and validate the model settings. A validation dataset is used to further tune the model parameters and repeat the training until a diagnostic model that performs well on the validation dataset is obtained. A final test set may be used to finally evaluate the performance of the diagnostic model.

[0028] The diagnostic model can not only distinguish between good and bad acoustic signals, but also identify the primary cause of an aerosol generating device malfunction. Each cause of malfunction can result in a unique response detectable in the acoustic signal. For example, a change in the resonant frequency of the vibrating element can indicate a change in the clamping force on the membrane. If the device uses a replaceable cartridge, such a change can be caused by the user during cartridge replacement. Low liquid flow onto the cartridge can also cause a resulting change in the vibration state of the vibrating element. This reduction in liquid flow can be caused by a change in the viscosity of the liquid substrate or a reduction in the performance of the conveying material. The specific cause of the performance fluctuation can be indicated to the user. If the liquid supply is depleted, the membrane dries out, which further affects its vibration characteristics. By analyzing the vibrating element's acoustic signal, depletion of the liquid supply can be identified. Therefore, by using such a predetermined diagnostic model, which can be developed based on machine learning techniques, the aerosol generating device can be trained to control and adjust its operation. Thus, the aerosol generating device can be used to enhance the overall user experience.

[0029] The aerosol generating device may be configured to monitor operational conditions of the aerosol generating device, which may include smoke puff detection, airflow condition characterization, dry mesh detection, normal mode detection, and failure mode detection.

[0030] The controller of the aerosol generating device may be configured to take at least one action based on the result of an evaluation of the acoustic signal detected by the acoustic sensor. The controller may be configured to control the acoustic source based on the evaluation of the acoustic signal detected by the acoustic sensor. The controller may be configured to prevent aerosol generation by the aerosol generating device if a malfunction that prevents reliable operation of the aerosol generating device is detected.

[0031] Monitoring the acoustic signal may be performed during use of the aerosol generating device, particularly during the nebulization process in which the aerosol is generated.

[0032] However, acoustic monitoring may be performed not only during puffs, but also between puffs. For example, a vibrating element may be intentionally activated to monitor the general operating state of the device. In this way, abnormal functioning of the device may be detected in advance before it is experienced by the user.

[0033] The present invention further relates to an aerosol generation system comprising an aerosol-generating device as described herein and a cartridge containing an aerosol-forming substrate. The cartridge may comprise a liquid reservoir.

[0034] As used herein, the term "aerosol-forming substrate" may relate to a substrate capable of emitting a volatile compound that can form an aerosol or vapor. The term "aerosol-forming substrate" may also relate to a substrate that can be mechanically atomized. The aerosol-forming substrate may be in gel or liquid form. The terms "aerosol" and "vapor" are used interchangeably.

[0035] The aerosol-forming substrate may comprise nicotine. The nicotine-containing aerosol-forming substrate may be a nicotine salt matrix.

[0036] The aerosol-forming substrate may comprise a plant-derived material.The aerosol-forming substrate may comprise tobacco.

[0037] The aerosol generating device may include a housing. The housing may be elongated. The housing may comprise any suitable material or combination of materials. Examples of suitable materials include metals, alloys, plastics, or composites containing one or more of these materials, or thermoplastics suitable for food or pharmaceutical applications, such as polypropylene, polyetheretherketone (PEEK), and polyethylene. The material is preferably lightweight and not brittle. The housing may include a user interface for activating the aerosol generating device, such as a button to initiate heating of the aerosol generating device, or a display to display the status of the aerosol generating device or the aerosol-forming substrate.

[0038] The aerosol generating device may include a power source. The power source may require recharging and may have a capacity that allows for storage of energy sufficient for one or more user experiences; for example, the power source may have a capacity sufficient to continuously generate aerosol for a period of approximately six minutes, or a multiple of six minutes. In another embodiment, the power source may have a capacity sufficient to provide a predetermined number of puffs. The aerosol generating device may include a charging port for recharging the power source.

[0039] The power source may be a direct current (DC) power source. In one embodiment, the power source is a DC power source having a DC supply voltage in the range of 2.5 volts to 4.5 volts and a DC supply current in the range of 1 ampere to 10 amperes (corresponding to a DC power range of 2.5 watts to 45 watts). Advantageously, the aerosol generating device may comprise a direct current to alternating current (DC / AC) inverter for converting the DC current provided by the DC power source into alternating current. The DC / AC converter may comprise a class D, class C, or class E power amplifier. The AC power output of the DC / AC converter is provided to the induction coil.

[0040] According to one embodiment of the present invention, there is provided a method of controlling an aerosol generating device using a controller, an acoustic source, and an acoustic sensor, the method comprising controlling operation of the aerosol generating device by the controller, generating an acoustic signal in use by the acoustic source, detecting the acoustic signal generated by the acoustic source with the acoustic sensor, and monitoring, by the controller, the operating status of the aerosol generating device based on the detected acoustic signal.

[0041] Analysis of such acoustic signals makes it possible to detect undesirable operating conditions, which may result in uncontrolled fluctuations in aerosol throughput. The proposed method may be used in development activities to improve device control and handling. The method may also assist in manufacturing quality control or provide a diagnostic tool integrated into commercial products.

[0042] The evaluation of the acoustic signals detected by the acoustic sensors may be based on a predetermined diagnostic model, which may be developed based on the machine learning techniques described above.

[0043] The aerosol generating device may comprise a memory unit. The method may include storing and reading data from the memory unit. To this end, the controller may be configured to perform an evaluation of the acoustic signal detected by the acoustic sensor by comparing the detected signal with expected acoustic signal signatures stored in the memory unit.

[0044] The controller may be further configured to store the detected acoustic signals in the microcontroller's memory. The stored acoustic signals may be used for subsequent data analysis. Such data analysis may include evaluating the operation of the aerosol generating device. The data analysis may be utilized to further develop a data model that can be used to evaluate the detected acoustic signals. The stored dataset may be used in a machine learning context to develop an evaluation strategy. The stored dataset may also be used as a training dataset in a machine learning context during training and testing of a predetermined diagnostic model for acoustic signal evaluation.

[0045] The method may include controlling the aerosol generating device, or more specifically, controlling an acoustic source of the aerosol generating device, based on an evaluation of the acoustic signal detected by the acoustic sensor.

[0046] Additionally, evaluation of the generated acoustic signals may enable monitoring of the operating conditions of the aerosol generating device. The monitored operating conditions of the aerosol generating device may include smoke puff detection, characterization of airflow conditions, dry mesh detection, normal mode detection, and failure mode detection. [Example]

[0047] The following provides a non-exhaustive list of non-limiting examples, any one or more of the features of which may be combined with any one or more features of another example, embodiment, or aspect described herein.

[0048] Example 1: An aerosol generating device, comprising: a controller for controlling the operation of the aerosol generating device; an acoustic source connected to the controller and configured, in use, to generate an acoustic signal; an acoustic sensor coupled to the controller and configured to detect an acoustic signal generated by the acoustic source; An aerosol generating device, wherein the controller is configured to monitor an operational state of the aerosol generating device based on the detected acoustic signal. Example 2: 10. The aerosol-generating apparatus of example 1, wherein the aerosol-generating apparatus comprises an aerosol-generating unit configured to aerosolize the aerosol-forming substrate. Example 3: 3. The aerosol generation device of example 2, wherein the aerosol generation unit comprises a vibrating element, preferably a vibrating mesh. Example 4: 4. An aerosol generation device according to any one of claims 2 to 3, wherein the aerosol generation unit comprises an electromechanical element in mechanical contact with the vibration element, the electromechanical element being controlled by the controller. Example 5: 5. The aerosol generating device according to any one of Examples 1 to 4, wherein the acoustic sensor is a microphone, preferably a MEMS microphone. Example 6: 6. An aerosol generating device according to any one of Examples 1 to 5, further comprising a mouthpiece portion, wherein the acoustic sensor is provided within the mouthpiece portion. Example 7: 7. An aerosol generating device according to any one of Examples 1 to 6, further comprising one or more additional acoustic sensors. Example 8: The aerosol generating device according to any one of Examples 1 to 7, wherein the acoustic sensors are provided at different positions on the aerosol generating device. Example 9: 9. An aerosol-generating device according to any one of Examples 1 to 8, wherein the acoustic sensor is provided in contact with a surface of the aerosol-generating device. Example 10: 10. An aerosol generating device according to any one of Examples 1 to 9, wherein the acoustic signal is transmitted to the acoustic sensor via a rigid connector provided in contact with the vibrating element. Example 11: 11. The aerosol generation device according to any one of Examples 1 to 10, further comprising an electronic circuit for processing the acoustic signal detected by the acoustic sensor. Example 12: 12. The aerosol generating device of any one of Examples 1 to 11, wherein the electronic circuitry is configured for amplification and noise reduction of the detected acoustic signal. Example 13: An aerosol generating device described in any one of Examples 11 or 12, wherein the electronic circuit is provided integrally with the acoustic sensor. Example 14: An aerosol generating device described in any one of Examples 1 to 13, wherein the aerosol generating device comprises a memory unit and the controller is configured to evaluate the acoustic signal detected by the acoustic sensor by comparing the signal with expected acoustic signal signatures stored in the memory unit. Example 15: 15. An aerosol generation device according to any one of Examples 1 to 14, wherein the controller is configured to perform at least one action based on an evaluation of the acoustic signal detected by the acoustic sensor. Example 16: 16. An aerosol generating device according to any one of Examples 1 to 15, wherein the controller is configured to control the acoustic source based on an evaluation of the acoustic signal detected by the acoustic sensor. Example 17: 17. The aerosol generating device of any one of Examples 1 to 16, wherein monitoring the operational status of the aerosol generating device includes smoke puff detection, airflow condition characterization, dry mesh detection, normal mode detection, and failure mode detection. Example 18: 1. A method of controlling an aerosol generating device, the aerosol generating device comprising a controller, an acoustic source, and an acoustic sensor, the method comprising: Controlling the operation of the aerosol generating device with a controller; In use, causing an acoustic source to generate an acoustic signal; detecting, with an acoustic sensor, an acoustic signal produced by an acoustic source; and monitoring, by the controller, the operational status of the aerosol generating device based on the detected acoustic signal. Example 19: 19. The method of example 18, wherein the controller is configured to evaluate the acoustic signal detected by the acoustic sensor. Example 20: 20. The method according to any one of Examples 18-19, wherein the controller is configured to evaluate the acoustic signal based on a predetermined diagnostic model. Example 21: The method according to any one of Examples 18 to 20, wherein the predetermined diagnostic model is developed based on the use of machine learning techniques. Example 22: 22. The method of any one of Examples 18 to 21, wherein the aerosol generating device comprises a memory unit, and the controller is configured to evaluate the acoustic signal detected by the acoustic sensor by comparing the signal with expected acoustic signal signatures stored in the memory unit. Example 23: 23. The method of any one of Examples 18-22, wherein the controller is configured to perform at least one action based on an evaluation of the acoustic signal detected by the acoustic sensor. Example 24: 24. The method of any one of Examples 18 to 23, wherein the controller is configured to control the acoustic source based on an evaluation of the acoustic signal detected by the acoustic sensor. Example 25: 25. The method of any one of Examples 18 to 24, wherein monitoring the operational status of the aerosol generating device includes smoke puff detection, airflow condition characterization, dry mesh detection, normal mode detection, and failure mode detection. Example 26: 26. The method of any one of Examples 18 to 25, wherein the controller is configured to store the detected acoustic signal in a memory of the microcontroller. Example 27: The method of example 26, wherein the stored acoustic signals are used for subsequent data analysis.

[0049] Features described with respect to one embodiment may be equally applied to other embodiments of the invention.

[0050] The invention will now be further described, by way of example only, with reference to the accompanying drawings in which: [Brief explanation of the drawings]

[0051] [Figure 1] FIG. 1 shows a vibrating mesh nebulizer. [Figure 2] Figure 2 shows the frequency spectrum of sound. [Figure 3] Figure 3 shows two acoustic signatures of a vibrating mesh nebulizer. [Figure 4] FIG. 4 shows the FFT spectrum of the acoustic signal of FIG. [Figure 5] Figure 5 shows two acoustic signatures of a vibrating mesh nebulizer. [Figure 6] FIG. 6 shows the FFT spectrum of the acoustic signal of FIG. [Figure 7] FIG. 7 shows the scheme of training the controller to obtain the diagnostic model. [Figure 8] FIG. 8 shows the acoustic spectrogram of a properly functioning vibrating element. [Figure 9] FIG. 9 shows an acoustic spectrogram of an abnormally functioning vibrating element. DETAILED DESCRIPTION OF THE INVENTION

[0052] 1 shows a schematic diagram of an aerosol generating device 10 comprising a housing 12 having a mouthpiece 14 at its proximal end. The aerosol generating device 10 further comprises a liquid reservoir 16, a controller 18, a power source 19, and a vibrating mesh element 20. The aerosol generating device 10 may also be referred to as a vibrating mesh nebulizer.

[0053] The vibrating mesh element 20 comprises a perforated circular membrane 22 surrounded by an annular electromechanical piezoelectric element 24. An acoustic sensor in the form of a MEMS microphone 26 is provided within the mouthpiece 14. The power source 19, the vibrating mesh element 20, and the MEMS microphone 26 are connected to a controller 18.

[0054] The perforated membrane 22 of the vibrating mesh element 20 is in contact with a liquid suction material (not shown) that transports the liquid aerosol-forming substrate 17 from the liquid storage portion 16 to the vibrating mesh element 20. The use of the liquid suction material ensures that the perforated membrane 22 is constantly supplied with liquid aerosol-forming substrate 17.

[0055] In use, the vibrating mesh element 20 is controlled by a controller 18. The controller 18 is configured to drive the piezoelectric element 24 with an adjustable frequency signal such that the perforated membrane 22 is excited to vibrate.

[0056] The perforated membrane 22 is adjacent to and in direct contact with the liquid aerosol-forming substrate 17. During vibration, the pores in the membrane 22 are filled with the liquid substrate 17. The liquid substrate 17 is then forced through the pores and ejected as droplets into the aerosol-forming chamber 28 of the mouthpiece 14. In this manner, the vibrating mesh element 20 serves to aerosolize the liquid substrate 17. The vibrating mesh element 20 also generates an acoustic signal during vibration. Thus, the vibrating mesh element 20 also functions as an acoustic source for the aerosol-generating device 10.

[0057] During a user experience, an airflow is generated from the air inlet 30 of the mouthpiece 14 through the aerosol formation chamber 28 adjacent the vibrating mesh element 20 toward the outlet 32. Aerosol droplets generated by the vibrating mesh element 20 are entrained in the airflow and are then inhaled by the user.

[0058] The MEMS microphone 26 is used to detect acoustic signals generated by the vibrating mesh element 20 during operation of the aerosol generating device 10. The detected acoustic signals are evaluated by the controller 18 and used to verify the operating status of the aerosol generating device 10. If the controller 18 detects an abnormal or undesirable operating condition, the controller 18 is configured to take appropriate action or notify a user.

[0059] Figure 2 shows the FFT frequency spectrum of a vibration signal, with the x-axis representing frequency and the y-axis representing the magnitude of each frequency signal in arbitrary units. The main peak in the center of the spectrum is associated with the main frequency signal, which in this case corresponds to a frequency of approximately 80 kilohertz. In addition to the main frequency peak, additional peaks are observed. These additional peaks are associated with higher harmonics and subharmonics of the main frequency. Harmonics can occur at multiples of the main frequency. Subharmonics occur at frequencies resulting from integer divisions of the main frequency. Such frequency spectra can be evaluated to derive information about the quality of the original vibration signal. In an aerosol generating device, evaluation of the acoustic signal emitted from a vibrating mesh element allows for the derivation of information about the vibration of the mesh element and, therefore, the operating state of the aerosol generating device.

[0060] Figure 3 shows acoustic signals VM_01 and VM_02 recorded by two different devices over a 25-second period. During these 25 seconds, three puffs are taken with each aerosol generator. Each puff lasts approximately 3 seconds. During the puffs, the vibrating mesh element is activated so that the amplitude of the recorded acoustic signal increases significantly. Between puffs, the vibrating mesh element is deactivated, so that no acoustic signal is detectable between puffs. The quality of the signals is very similar, making it possible to determine that the operating conditions of these aerosol generators are similar.

[0061] The operating conditions of these aerosol generators can be further assessed by analyzing the recorded acoustic signals using FFT spectral analysis. Figure 4 shows the FFT spectrum of the acoustic signal in Figure 3. As can be seen from the large-scale FFT spectrum in Figure 4, the acoustic signal has a dominant frequency of approximately 65 kHz. Several subharmonics are visible at half and one-third of the dominant frequency. As can be seen from the zoomed-in view of the dominant FFT peak at approximately 65 kHz, the dominant FFT peak has a well-defined single frequency with an exponentially decaying shoulder. From these spectra, we can conclude that the vibrating mesh is freely vibrating and that the operating conditions of the aerosol generator are normal.

[0062] Figure 5 shows a comparison of acoustic signals recorded under similar conditions to those shown in Figure 3. Signal VM_01 is identical to the corresponding signal in Figure 3. The other acoustic signal, VM_03, was recorded under dry mesh conditions, which means that the liquid reservoir in that case has been depleted.

[0063] The acoustic signal VM_03 recorded under dry mesh conditions is clearly distinguishable from the acoustic signal VM_01 recorded under normal conditions. The oscillations in the "dry mesh" signal begin and end with a stronger overshoot than the acoustic signal VM_01. Furthermore, the oscillations during puffs are more irregular, with detectable acoustic signals between puffs.

[0064] This unclear frequency response can also be detected by comparing the corresponding FFT spectra of the acoustic signals, as shown in Figure 6. While signal VM_01 exhibits a well-defined single frequency with an exponentially decaying shoulder, the FFT spectrum of dry mesh signal VM_03 shows at least two clearly discernible differences. First, the main peak is significantly shifted to higher frequencies, located precisely at 66 kHz. Second, an additional peak appears, indicating that the frequency response of the vibrating mesh element is sparse and somewhat unclear.

[0065] Given these clearly identifiable differences, the controller may be configured to interpret the occurrence of such changes in the FFT spectrum as a depletion of the liquid supply. Under such operating conditions, the controller may prevent further actuation of the vibrating mesh element. Furthermore, the controller may notify the user of the need to replace or refill the liquid supply of the aerosol generating device.

[0066] The evaluation of the acoustic signals may be performed using a predetermined diagnostic model. Such a predetermined diagnostic model may be developed based on machine learning techniques. To this end, the controller may be trained using a dataset 40 of experimentally recorded acoustic signals, as shown in FIG. 7.

[0067] A dataset 40 of experimentally recorded acoustic signals is randomly divided into a training set 42, a validation set 44, and a test set 46. In the model of Figure 7, the training set 42 contains 60 percent of the entries in the initial dataset 40. The validation set 44 and the test set 46 each contain 20 percent of the entries in the initial dataset 40.

[0068] The data in the training set 42 is used to train and establish a raw diagnostic model 48. The parameters are adjusted until the raw model 48 can correctly process the data in the training set 42. In a next step, the raw model 48 is verified and validated using a validation set 44. The validation set 44 is used to further adjust the controller parameters and repeat the training until a final diagnostic model 50 is obtained that performs well on the data in the validation set 44.

[0069] In a final step, the final model 50 is validated again using data from the test set 46. This test set 46 may be used to finally evaluate the performance of the final diagnostic model 50.

[0070] The diagnostic model 50 allows the controller to verify the operating status of the aerosol generating device. In the event of a malfunction, the diagnostic model 50 can identify the primary cause. The diagnostic model 50 may be used to detect smoke puffs, characterize airflow conditions, detect dry mesh, or generally distinguish between normal and fault mode operation.

[0071] Figure 8 shows an example acoustic spectrogram recorded by the acoustic sensor of a vibrating mesh nebulizer. The acoustic spectrogram shows the amplitude and frequency of the acoustic signal generated by the vibrating element and recorded over time by the acoustic sensor. The acoustic spectrogram shows three consecutive nebulization pulses. The vibrating mesh nebulizer used to record the spectrogram in Figure 8 was used under normal operating conditions. In particular, the vibrating mesh element used therein was functioning normally. The signal recorded during the nebulization pulse shows a prominent maximum in amplitude at approximately 66 kilohertz and several less prominent local maxima in the lower frequency range of 10 to 50 kilohertz.

[0072] Figure 9 shows another acoustic spectrogram similar to that of Figure 8, but recorded with an erratically operating vibrating mesh element. Notably, the vibrating mesh used to record the acoustic spectrogram of Figure 9 produced anomalously low spray. Such anomalously low spray can occur when the liquid reservoir is depleted. The spectrogram of Figure 9 shows a notable difference from the spectrogram of Figure 8. The high-frequency peak at approximately 66 kilohertz is still visible. However, that peak is less pronounced compared to the peak in the spectrogram of Figure 8. Furthermore, local maxima at lower frequencies are barely discernible, and the overall amplitude level across all frequencies has increased. This sparse, somewhat unclear frequency response of the vibrating mesh element again indicates an abnormal operating condition of the vibrating mesh.

[0073] The acoustic spectrograms shown in Figures 8 and 9 may be used in the image-based machine learning algorithms described herein. The spectral patterns of such spectrograms may be classified according to their key features, such as the presence of prominent frequency peaks or the overall noise level recorded. Such machine learning algorithms may preferably use convolutional neural network models. Such convolutional neural network models are well suited for image and video recognition, particularly for image classification, which is required to evaluate acoustic spectrograms recorded with the aerosol generating devices described herein.

Claims

1. An aerosol generating device, comprising: a controller for controlling the operation of the aerosol generating device; an acoustic source connected to the controller and configured, in use, to generate an acoustic signal; an acoustic sensor coupled to the controller and configured to detect the acoustic signal generated by the acoustic source; The controller is configured to monitor the operating status of the aerosol generating device based on the detected acoustic signal, the aerosol generating device comprising an aerosol generating unit configured to aerosolize an aerosol-forming substrate, and the aerosol generating unit comprising a vibrating mesh.

2. 2. The aerosol generating device of claim 1, wherein the aerosol generating unit comprises an electromechanical element in mechanical contact with the vibration element, the electromechanical element (preferably a piezoelectric element) being controlled by the controller.

3. 3. The aerosol generating device according to claim 1, wherein the acoustic sensor is a microphone, preferably a MEMS microphone.

4. 4. The aerosol generating device according to claim 1, further comprising a mouthpiece portion, wherein the acoustic sensor is provided within the mouthpiece portion.

5. 5. The aerosol generating device according to claim 1, wherein the acoustic sensor is provided in contact with a surface of the aerosol generating device.

6. 6. An aerosol generating device according to claim 1, wherein the acoustic signal is transmitted to the acoustic sensor via a rigid connector provided in contact with the vibrating element.

7. 7. The aerosol generating device of claim 1, wherein the aerosol generating device comprises a memory unit, and the controller is configured to evaluate the acoustic signal detected by the acoustic sensor by comparing the signal with expected acoustic signal signatures stored in the memory unit.

8. An aerosol generating device as described in any one of claims 1 to 7, wherein a controller is configured to take at least one action based on the result of the evaluation of the acoustic signal detected by the acoustic sensor.

9. 1. A method of controlling an aerosol generating device, the aerosol generating device comprising a controller, an acoustic source, and an acoustic sensor, the method comprising: controlling the operation of the aerosol generating device by the controller; In use, causing said acoustic source to generate an acoustic signal; detecting the acoustic signal produced by the acoustic source with the acoustic sensor; monitoring, by the controller, the operational status of the aerosol generating device based on the detected acoustic signal; The method, wherein the aerosol-generating device comprises an aerosol-generating unit configured to aerosolize an aerosol-forming substrate, the aerosol-generating unit comprising a vibrating mesh.

10. The method of claim 9 , wherein the controller is configured to evaluate the acoustic signal detected by the acoustic sensor.

11. 11. The method according to any one of claims 9 to 10, wherein the controller is configured to evaluate the acoustic signal based on a predetermined diagnostic model, the predetermined diagnostic model being developed based on machine learning techniques.

12. 12. The method of any one of claims 9 to 11, wherein the aerosol generating device comprises a memory unit, and the controller is configured to evaluate the acoustic signal detected by the acoustic sensor by comparing the signal with expected acoustic signal signatures stored in the memory unit.

13. The method of any one of claims 9 to 12, wherein the controller is configured to take at least one action based on the result of the evaluation of the acoustic signal detected by the acoustic sensor.

Images