Self-powered gas sensing device, system and method

Abstract

Disclosed are a self-powered gas sensing system, device, and method for identifying the properties of a gas in a gas environment to be measured. The self-powered gas sensing system comprises: a self-powered gas sensing device, comprising: an energy harvester configured to acquire mechanical energy and convert the mechanical energy into electrical energy; a breakdown discharger disposed in the gas environment to be measured, the breakdown discharger configured to acquire the electrical energy, wherein the electrical energy causes the breakdown discharger to perform breakdown discharge in the gas environment to be measured, the current generated by the breakdown discharge causing the emission of an electromagnetic wave signal, and wherein the electromagnetic wave signal carries information associated with the properties of the gas in the gas environment to be measured; and a gas property identification device configured to receive the electromagnetic wave signal from the self-powered gas sensing device and identify the properties of the gas in the gas environment to be measured based on the electromagnetic wave signal.

Description

Technical Field

[0001] The present disclosure relates to the field of sensing technology, and more particularly, to a self-powered gas sensing device, system, and method. Background Art

[0002] Gas sensors play a vital role in industrial exhaust and indoor environmental monitoring, enjoying a wide range of applications. Traditional gas sensors, such as catalytic combustion gas sensors, semiconductor gas sensors, thermal conductivity gas sensors, and infrared gas sensors, typically rely on external power supplies. This reliance on external power significantly limits their application. Even with the emergence of wireless energy transmission, this power supply method is limited by its limited transmission distance and still requires an external power source to power the energy transmission component.

[0003] Self-powered technology is a technology that harvests other forms of energy from the surrounding environment (such as solar, wind, mechanical, and thermal energy) and converts it into electricity, providing a safe, stable, and efficient power supply for electronic devices without requiring an external power source. However, due to the varying impedance and output characteristics of energy harvesters, this self-powered approach often requires the inclusion of energy management circuitry, which in turn introduces additional energy requirements and increases the overall system size.

[0004] At the same time, existing gas sensors often have limited detection ranges and other drawbacks. For example, catalytic combustion gas sensors are limited to testing combustible gases and pose a risk of ignition and explosion. Semiconductor gas sensors are significantly affected by background gas interference and are susceptible to temperature. Thermal conductivity gas sensors are significantly affected by temperature, have poor detection accuracy, and low sensitivity. Infrared gas sensors are expensive, complex, and limited to testing gases that absorb infrared radiation. Furthermore, many gas sensors cannot be separated too far from subsequent sensor data analysis devices (e.g., no more than 1 meter). This is because, for example, if a transmission medium such as a wire is required to transmit the sensor signal, an excessively long wire will have excessive impedance, thereby affecting the effectiveness of the sensor signal and increasing the system size. However, in some applications, due to space limitations or the inability of the data analysis device to move, it is impossible to place the gas sensor and sensor data analysis device close enough together.

[0005] To this end, there is an urgent need for a self-powered gas sensor that can integrate energy collection and conversion functions and gas detection functions, is small in size, can be used to safely sense various types of gases, has high sensing accuracy, and has a long transmission distance for sensing signals. Summary of the Invention

[0006] According to one aspect of the present disclosure, a self-powered gas sensing system is provided for identifying the properties of a gas in a gas environment to be measured, comprising: a self-powered gas sensing device, comprising: an energy harvester, configured to acquire mechanical energy and convert the mechanical energy into electrical energy; a breakdown discharger, disposed in the gas environment to be measured, the breakdown discharger configured to acquire the electrical energy, wherein the electrical energy causes the breakdown discharger to perform breakdown discharge in the gas environment to be measured, the current generated by the breakdown discharge causing emission of an electromagnetic wave signal, and wherein the electromagnetic wave signal carries information associated with the properties of the gas in the gas environment to be measured; and a gas property identification device, configured to receive the electromagnetic wave signal from the self-powered gas sensing device, and identify the properties of the gas in the gas environment to be measured based on the electromagnetic wave signal.

[0007] According to an embodiment of the present disclosure, the breakdown discharger includes a first electrode and a second electrode insulated and isolated by gas in the gas environment to be measured, and the first electrode and the second electrode have opposite discharge tips with a discharge gap between the opposite discharge tips. The electric energy forms an electric field between the tips of the first electrode and the second electrode, and the electric field causes the gas in the gas environment to be measured to be broken down between the discharge gaps of the discharge tips of the first electrode and the second electrode to perform breakdown discharge.

[0008] According to an embodiment of the present disclosure, the properties of the gas include at least one of the following: gas composition, gas concentration, and gas pressure.

[0009] According to an embodiment of the present disclosure, the gas property identification device includes: a signal receiving unit, configured to receive the electromagnetic wave signal from the self-powered gas sensing device and convert the electromagnetic wave signal into a timing signal of a predetermined electrical parameter; and an identification unit, configured to identify the property of the gas in the gas environment to be measured based on the timing signal of the predetermined electrical parameter.

[0010] According to an embodiment of the present disclosure, the gas property identification device further includes: a signal processing unit configured to perform signal processing on the timing signal of the predetermined electrical parameter to obtain a processed signal, wherein the identification unit identifies the properties of the gas in the gas environment to be measured based on the processed signal; wherein the signal processing includes at least one of the following operations: removing noise signals or intercepting effective signals; and extracting spectral signals.

[0011] According to an embodiment of the present disclosure, the identification unit includes a machine learning model, which is trained to generate an identification result indicating the properties of the gas in the gas environment to be measured for the processed signal, wherein the machine learning model is trained on a training set to obtain a trained machine learning model, and the training set includes multiple processed signals and the true labels of the gas properties corresponding to each of the multiple processed signals.

[0012] According to an embodiment of the present disclosure, the training set is obtained in the following manner: selecting a first number of reference gas environments with different gas properties; obtaining a second number of processed signals for each reference gas environment; for each reference gas environment, using the second number of processed signals and the true labels of the respective corresponding gas properties as a training subset; and using the training subsets for all reference gas environments together as a training set.

[0013] According to an embodiment of the present disclosure, a second number of processed signals for each reference gas environment is obtained in the following manner: for the reference gas environment, the breakdown discharger placed in a closed gas chamber filled with gas in the reference gas environment performs breakdown discharge in the reference gas environment based on the electrical energy obtained from the energy collector, wherein the current generated by the breakdown discharge causes the emission of an electromagnetic wave signal; the electromagnetic wave signal is obtained and converted into a second number of timing signals of predetermined electrical parameters; and each timing signal of the predetermined electrical parameters is processed to obtain the second number of processed signals.

[0014] According to an embodiment of the present disclosure, each of the processed signals included in the training set is a time domain signal, and the machine learning model is a bidirectional long short-term memory recurrent neural network (bi-LSTM) model, wherein the machine learning model is trained in the following manner: each time domain signal included in the training set is forwardly input and reversely input into the bi-LSTM model to obtain a predicted label corresponding to each of the time domain signals, and based on the difference between each predicted label and the true label of the corresponding time domain signal, the model parameters of the bi-LSTM model are updated by the error back propagation method and the gradient descent method until the model parameters converge relative to the training set.

[0015] According to an embodiment of the present disclosure, each of the processed signals included in the training set is a spectrum image signal, and the machine learning model is a convolutional neural network (CNN) model, wherein the machine learning model is trained in the following manner: each spectrum image signal included in the training set is input into the CNN model to obtain a predicted label corresponding to each spectrum image signal, and based on the difference between each predicted label and the true label of the corresponding spectrum image signal, the model parameters of the CNN model are updated by the error back propagation method and the gradient descent method until the model parameters converge relative to the training set.

[0016] According to another aspect of the present disclosure, a self-powered gas sensing device is provided, comprising: an energy harvester configured to acquire mechanical energy and convert the mechanical energy into electrical energy; a breakdown discharger disposed in the gas environment to be measured, the breakdown discharger configured to acquire the electrical energy, wherein the electrical energy causes the breakdown discharger to perform a breakdown discharge in the gas environment to be measured, and the current generated by the breakdown discharge causes the emission of an electromagnetic wave signal, wherein the electromagnetic wave signal carries information associated with properties of the gas in the gas environment to be measured.

[0017] According to an embodiment of the present disclosure, the breakdown discharger includes a first electrode and a second electrode insulated and isolated by the gas in the gas environment to be measured, and the first electrode and the second electrode have opposite discharge tips with a discharge gap between the discharge tips. The electric energy forms an electric field between the tips of the first electrode and the second electrode, and the electric field breaks down the gas in the gas environment to be measured between the discharge gaps of the discharge tips of the first electrode and the second electrode to perform breakdown discharge.

[0018] According to another aspect of the present disclosure, a self-powered gas sensing method is provided for identifying the properties of a gas in a gas environment to be measured, comprising: placing a breakdown discharger in the gas environment to be measured; utilizing an energy harvester to obtain mechanical energy and converting the mechanical energy into electrical energy; utilizing the breakdown discharger to obtain the electrical energy, wherein the electrical energy causes the breakdown discharger to perform a breakdown discharge in the gas environment to be measured, and the current generated by the breakdown discharge causes the emission of an electromagnetic wave signal, and wherein the electromagnetic wave signal carries information associated with the properties of the gas in the gas environment to be measured; and utilizing a gas property identification device to identify the properties of the gas in the gas environment to be measured based on the electromagnetic wave signal.

[0019] According to an embodiment of the present disclosure, a gas property identification device is used to identify the properties of the gas in the gas environment to be measured based on the electromagnetic wave signal, including: receiving the electromagnetic wave signal and converting the electromagnetic wave signal into a timing signal of a predetermined electrical parameter; performing signal processing on the timing signal of the predetermined electrical parameter to obtain a processed signal; and identifying the properties of the gas in the gas environment to be measured based on the processed signal.

[0020] According to an embodiment of the present disclosure, wherein the gas property identification device includes a machine learning model, the self-powered gas sensing method further includes: obtaining a plurality of processed signals and true labels of gas properties corresponding to each of the plurality of processed signals as a training set; and using the training set to train the machine learning model, so that the trained machine learning model can generate an identification result indicating the properties of the gas in the gas environment to be measured for the processed signals.

[0021] According to the self-powered gas sensing device, system and method of the embodiments of the present disclosure, it is possible to identify the properties of the gas in the gas environment where the self-powered gas sensing device is located, such as gas composition, concentration, air pressure and other information. Compared with the current gas sensing technology, it is possible to sense most gases without the need for external power supply. The generated sensing signal itself is a wireless signal and is not constrained by the signal transmission line, and does not require an additional energy management module and a wireless signal transmission module. It is small in size and has high accuracy in identifying gas properties, which makes the self-powered gas sensing system have a wider range of applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some exemplary embodiments of the present disclosure, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0023] Figure 1 A schematic structural block diagram of a self-powered gas sensing system according to an embodiment of the present disclosure is shown.

[0024] Figure 2 A schematic structural block diagram of a self-powered gas sensing device according to an embodiment of the present disclosure is shown.

[0025] Figures 3A-3B An example structure of a triboelectric nanogenerator is shown.

[0026] Figure 4 Shown Figure 2 Equivalent circuit model of the self-powered gas sensing device.

[0027] Figure 5A A schematic structural block diagram of a gas property identification device according to an embodiment of the present disclosure is shown.

[0028] Figure 5B A schematic structural diagram of obtaining a second number of processed signals based on a self-powered gas sensing device is shown.

[0029] Figure 5C A schematic diagram showing the voltage-time time series obtained for 10 reference gas environments is shown.

[0030] Figure 5D A flow chart is shown for obtaining multiple processed signals for each reference gas environment.

[0031] Figure 6 A schematic diagram illustrating the effectiveness of the self-powered gas sensing system based on a confusion matrix is shown.

[0032] Figure 7 A schematic flow chart of a self-powered gas sensing method according to an embodiment of the present disclosure is shown.

[0033] Figure 8 A schematic structural block diagram of a computing device that can be used to implement an identification unit according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0034] The following is a detailed description of the embodiments of the present invention. It should be emphasized that the following description is only exemplary and is not intended to limit the scope of the present invention and its application.

[0035] In order to make the purpose, technical solutions and advantages of the present disclosure more apparent, the following will describe in detail exemplary embodiments of the present disclosure with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described herein.

[0036] In this specification and the accompanying drawings, steps and elements that are substantially the same or similar are denoted by the same or similar reference numerals, and repeated descriptions of these steps and elements will be omitted. The terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Thus, features defined as "first" and "second" may explicitly or implicitly include one or more embodiments of the invention, and "plurality" means two or more, unless otherwise specifically defined.

[0037] Figure 11 is a schematic block diagram of a self-powered gas sensing system 100 according to an embodiment of the present disclosure.

[0038] like Figure 1 As shown, the self-powered gas sensing system 100 may include a self-powered gas sensing device 110 and a gas property identification device 120 .

[0039] The self-powered gas sensing device 110 can be used to obtain mechanical energy and convert it into electrical energy, thereby achieving self-power. Furthermore, the self-powered gas sensing device 110 can sense the properties of gas in the gas environment to be measured and generate an electromagnetic wave signal that carries information related to the properties of the gas in the gas environment to be measured.

[0040] For example, gas properties may include at least one of the following: gas composition, gas concentration, and gas pressure. Gas composition can refer to either a pure gas environment or a mixed gas environment. In a mixed gas environment, gas composition refers not only to the type of gas components but also to their respective gas concentrations.

[0041] For example, mechanical energy can come from human-applied forces, wind, forces exerted by waves, forces exerted by vehicle motion, raindrops, liquid flow, and so on.

[0042] The gas property identification device 120 may be configured to receive an electromagnetic wave signal from the self-powered gas sensing device 110 and identify the properties of the gas in the gas environment to be measured based on the electromagnetic wave signal.

[0043] Because electromagnetic wave signals are transmitted between the self-powered gas sensing device 110 and the gas attribute identification device 120, they can be separated by a considerable distance without requiring wires. For example, they can be separated by 30 meters, and the gas attribute identification device 120 can still receive the electromagnetic wave signals and identify the gas attributes. Therefore, this device is particularly suitable for use in specific scenarios, such as where space is limited or the movement of the gas attribute identification device is unsuitable.

[0044] More details of the self-powered gas sensing device 110 and the gas attribute identification device 120 will be described in detail later.

[0045] According to the above-mentioned self-powered gas sensing system, the properties of the gas in the gas environment where the self-powered gas sensing device is located can be realized, and most gases can be sensed without the need for external power supply. The generated sensing signal itself is a wireless signal and is not constrained by the signal transmission line, and no additional energy management module and wireless signal transmission module are required. Therefore, the structure is simple and the size is small, and the accuracy of identifying gas properties is high, which makes the self-powered gas sensing system have a wider range of applications.

[0046] The following combination Figure 2-4 right Figure 1 The self-powered gas sensing device in the self-powered gas sensing system 100 is described in detail.

[0047] Figure 2 A structural block diagram of a self-powered gas sensing device according to an embodiment of the present disclosure is shown.

[0048] like Figure 2 As shown, the self-powered gas sensing device 110 includes an energy harvester 110 - 1 and a breakdown arrester 110 - 2 .

[0049] The energy harvester 110 - 1 is configured to capture mechanical energy and convert the mechanical energy into electrical energy.

[0050] The energy harvester 110 - 1 can be placed in the gas environment to be measured or outside the gas environment to be measured. Regardless of where it is placed, the energy harvester 110 - 1 needs to obtain mechanical energy and convert the mechanical energy into electrical energy to achieve self-powered gas sensing device 110 .

[0051] By way of example and not limitation, as described in the context of the present disclosure, the energy harvester 110 - 1 may be a triboelectric nanogenerator.

[0052] The working principle of the triboelectric nanogenerator is introduced below. It should be understood that the working principle described below is exemplary only and is only to help better understand the embodiments of the present disclosure. Different triboelectric nanogenerators have different working principles.

[0053] The triboelectric nanogenerator 110-1 may include a triboelectric layer, a first output electrode, and a second output electrode (not shown). The triboelectric layer is used to form charges of opposite polarity on the first and second output electrodes based on the mechanical energy obtained, thereby forming an electric field between the first and second electrodes of a breakdown discharger connected to the first and second output electrodes, as described later (providing electrical energy to the breakdown discharger). Of course, if other types of energy harvesters are used, first and second output electrodes are also present to form an electric field between the first and second electrodes of the breakdown discharger.

[0054] An example structure of the triboelectric nanogenerator 110-1 can be as follows: Figures 3A-3B As shown, it includes a sliding friction nanogenerator (FS-TENG) ( Figure 3A ), and contact-separation triboelectric nanogenerator (CS-TENG) ( Figure 3B ), the specific work process will refer to Figures 3A-3BOf course, the following example structures are only for helping to better understand the present disclosure and are not intended to be limiting. Any other suitable structure of the triboelectric nanogenerator may be used.

[0055] The triboelectric nanogenerator can be a sliding triboelectric generator, such as Figure 3A As shown. The sliding friction generator is composed of two different thin film polymers with metal electrode materials on the back, or thin film polymers and electrodes. From top to bottom, it includes a top electrode, a first type of material thin film layer and a second type of material thin film layer with opposite friction polarity, and a bottom electrode. The sliding friction generator receives an external force (mechanical energy), causing the first type of material thin film layer and the second type of material thin film layer to move relative to each other. Due to the triboelectric effect, charge transfer occurs, forming a potential difference (voltage difference) between the top electrode and the bottom electrode, thereby forming an electric field between the first electrode and the second electrode of the breakdown discharger connected to the top electrode and the bottom electrode (providing electrical energy to the breakdown discharger).

[0056] For example, Figure 3A This figure shows a generator made of polytetrafluoroethylene (PTFE) and nylon, two materials with opposite triboelectric polarity, and its operating mechanism. When PTFE and nylon come into contact, because PTFE attracts electrons more strongly than nylon, a negative charge is generated on the PTFE surface and a positive charge on the nylon surface. When the PTFE and nylon are completely aligned, there is no potential difference between the electrode on the nylon and the electrode below the PTFE. However, when the two electrodes are displaced by an external force (mechanical energy), the frictional charges in the dislocated area cannot completely cancel each other out, resulting in a potential difference between the two electrodes. When the PTFE and nylon are aligned again, the dislocated area disappears, and the potential difference caused by the frictional charges also disappears, allowing free electrons to flow from the electrode on the nylon to the electrode on the PTFE. Electrical energy, converted from mechanical energy, can be output between the two electrodes.

[0057] Another example of a triboelectric nanogenerator is a contact-separation triboelectric nanogenerator (CS-TENG). Figure 3B As shown, the friction nanogenerator includes, from top to bottom, a first electrode layer, a first friction material layer, a second friction material layer made of a material with different electronegativity from the first friction material layer, and a second electrode layer. The material of at least one of the first friction material layer and the second friction material layer is an insulating material (for maintaining friction charge for a long time). For example, the material of the first friction material layer can be a polyimide (PI) film (Kapton), and the material of the second friction material layer can be polymethyl methacrylate (PMMA).

[0058] When pressure (mechanical energy) is applied to the first electrode layer, the first friction material layer and the second friction material layer contact each other. Due to the triboelectric effect, the surfaces where the first friction material layer and the second friction material layer contact each other will carry charges of different polarities. However, the charge is only formed on the contact surface and the positive and negative charges can offset each other. Therefore, no potential difference is formed between the first electrode layer and the second electrode layer at this time.

[0059] Once the surfaces of the first friction material layer and the second friction material layer in contact with each other are released and separated, a potential difference will be generated between the electrodes on the upper and lower surfaces of the first friction material layer and the second friction material layer. During the release process, the potential difference can form an electric field between the first electrode and the second electrode of the breakdown discharger connected to the first electrode layer and the second electrode layer (providing electrical energy to the breakdown discharger).

[0060] That is, when there is no pressure signal input, no induced charge is generated on the two electrode layers of the triboelectric nanogenerator, resulting in no potential difference between the two layers and, therefore, no electrical energy can be supplied to the breakdown discharger. When there is a pressure signal input, induced charge is generated between the first and second friction material layers. When the pressure signal input stops (as in the release process described above), induced charge is generated on the first and second electrode layers, forming a potential difference between the two electrode layers. Further, the generated electrical energy is supplied to the breakdown discharger.

[0061] The working principle of the breakdown arrester 110 - 2 is introduced below. It should be understood that the working principle described below is exemplary and is only for the purpose of helping to better understand the embodiments of the present disclosure.

[0062] The breakdown discharger 110-2 is arranged in the gas environment to be tested, and the breakdown discharger is configured to obtain electrical energy obtained by converting the mechanical energy obtained by the friction nanogenerator 110-1, wherein the electrical energy enables the breakdown discharger to perform breakdown discharge in the gas environment to be tested, and the current generated by the breakdown discharge causes the emission of electromagnetic wave signals.

[0063] Because the characteristics of the electromagnetic wave signal generated for different test gas environments (with different gas properties), such as waveform, amplitude, and spectral characteristics, vary, the electromagnetic wave signal can carry information related to the properties of the gas in the test gas environment. Based on analysis of the electromagnetic wave signal, the properties of the gas in the test gas environment can be identified.

[0064] The breakdown discharger 110-2 may include a first electrode and a second electrode insulated and isolated by the gas in the gas environment to be measured, and wherein the first electrode and the second electrode have relative discharge tips with a discharge gap between the relative discharge tips, the electric energy forms an electric field between the discharge tips of the first electrode and the second electrode, and the electric field causes the gas in the gas environment to be measured to be broken down between the discharge gaps of the discharge tips of the first electrode and the second electrode to perform breakdown discharge.

[0065] For example, the discharge tip can be a metal structure and can be manufactured using an electron beam evaporation process. The minimum spacing between the two metal structures is controlled to be 5-500 microns, a spacing that can be observed under a microscope. When electrical energy is obtained from the triboelectric nanogenerator 110-1, an electric field is formed between the first and second electrodes of the breakdown discharger. The electric field intensity reaches its maximum at the discharge tip. When the electric field intensity at the discharge tip is sufficiently high, the gas in the gas environment to be measured is broken down between the discharge gap between the discharge tips of the first and second electrodes, resulting in a breakdown discharge.

[0066] The breakdown discharge will form a current between the discharge tips, and this current will cause the emission of electromagnetic wave signals.

[0067] Specifically, a strong electric field is generated between the opposing discharge tips of the first and second electrodes of the breakdown discharger, causing electrons to move from the cathode to the anode. During this movement, electrons collide with air molecules at high speed, resulting in the generation of new electrons, positive ions, and negative ions, causing an electron avalanche and further generating plasma. This plasma can be viewed as a collective oscillation of clusters of charged particles, creating a zero-impedance region that acts as a conductor for electrons. As a result, a pulse current is generated in the emission system, whose amplitude and pulse rise time are related to the voltage, gap width, and gas properties (gas composition, pressure, concentration, etc.). Ultimately, as the electric field weakens, the weakened electron avalanche can no longer support the path, causing the circuit to return to an open state.

[0068] Will combine Figure 4 Describe in detail the process of generating electromagnetic wave signals.

[0069] Figure 4 Shown Figure 2-3B An equivalent circuit model of the self-powered gas sensing device (including an energy collector and a breakdown discharger).

[0070] like Figure 4As shown, the voltage source Vi and the equivalent capacitor Ci correspond to the equivalent circuit model of the energy harvester (e.g., a triboelectric nanogenerator). C, R, and L are the capacitance, inductance, and resistance of the energy harvester and the breakdown discharger, which can be derived from parasitic capacitance, parasitic self-inductance, parasitic resistance, etc. That is, during breakdown discharge, the electrodes of the energy harvester (e.g., a triboelectric nanogenerator) (such as the first and second output electrodes described above) and the first and second electrodes of the breakdown discharger form a conductive loop. Once the pulse current during breakdown discharge occurs, it generates an underdamped oscillating current signal in the transmitting system composed of the triboelectric nanogenerator and the breakdown discharge device. This oscillation can generate a changing magnetic field and electric field in the surrounding area, generating an omnidirectional electromagnetic wave signal, which is ultimately transmitted to the gas attribute identification device for reception. Optionally, the gas attribute identification device can receive the electromagnetic wave signal using a receiving coil or a receiving capacitor.

[0071] Research can be conducted to evaluate the relationship between the output performance of the electromagnetic wave signal caused by the breakdown and the factors affecting it. The main influencing factors can be determined empirically to include the breakdown discharge voltage (U), the gap distance between the breakdown discharge electrodes (d), the direction of motion of the triboelectric nanogenerator (-), the length of the connecting wire between the energy harvester (such as the triboelectric nanogenerator) and the breakdown discharger (l), the spatial conductor distribution (a), the distance between the breakdown discharger and the receiver (D), the gas composition (N), the gas pressure (P), the gas concentration (C), the temperature (T), and the humidity (H).

[0072] By sequentially changing the parameter values of the influencing factors while keeping the parameters of the other influencing factors unchanged, we can conclude that changes in most of the aforementioned influencing factors will alter the amplitude of the electromagnetic wave signal but will not affect the waveform and spectrum. However, changes in the length (l) of the connecting wire between the energy harvester (e.g., the triboelectric nanogenerator) and the breakdown discharger, as well as the gas composition (N), gas pressure (P), and gas concentration (C) will cause changes in the waveform and spectrum of the electromagnetic wave signal. This also shows that if the structure of the same self-powered gas sensing system remains unchanged, that is, if the length (l) of the connecting wire between the energy harvester (e.g., the triboelectric nanogenerator) and the breakdown discharger is fixed, the properties of the gas in the gas environment to be measured by the self-powered gas sensing system can be identified through the electromagnetic wave signal.

[0073] By reference Figure 2-4The self-powered gas sensing device described can sense the properties of the gas in the gas environment in which the self-powered gas sensing device is located, and can sense most gases without the need for external power supply. The generated electromagnetic wave signal is itself a wireless signal and is not constrained by the signal transmission line and can carry information about the gas properties. Therefore, the properties of the gas can be determined by analyzing the electromagnetic wave signal.

[0074] The following combination Figures 5A-5D right Figure 1 The composition and working process of the gas property identification device in the self-powered gas sensing system are described in detail.

[0075] Figure 5A A schematic structural block diagram of a gas property identification device according to an embodiment of the present disclosure is shown.

[0076] like Figure 5A As shown, the gas property identification device 120 may include: a signal receiving unit 120 - 1 and an identification unit 120 - 2 .

[0077] The signal receiving unit 120 - 1 is configured to receive the electromagnetic wave signal from the self-powered gas sensing device 110 and convert the electromagnetic wave signal into a time series signal of an electrical parameter, that is, a time series signal in which the electrical parameter changes with time.

[0078] For example, the signal receiving unit 120-1 may include an electromagnetic wave receiving circuit and a sampling circuit. The electromagnetic wave receiving circuit may convert the electromagnetic wave signal into a predetermined electrical parameter signal (for example, the predetermined electrical parameter may be voltage or current), and the sampling circuit may sample the predetermined electrical parameter signal at a predetermined sampling frequency to obtain a time series signal of the predetermined electrical parameter. An example of the electromagnetic wave receiving circuit may be at least one of a receiving coil and a receiving antenna.

[0079] The identification unit 120 - 2 is configured to identify the properties of the gas in the gas environment to be measured based on the time series signal of the predetermined electrical parameter.

[0080] As mentioned above, if the properties of the gas are different, the waveform and spectral characteristics of the electromagnetic wave signal will also be correspondingly different. Therefore, by analyzing the timing signal of the predetermined electrical parameters obtained after receiving and sampling the electromagnetic wave signal, the properties of the gas in the gas environment to be measured can be obtained by obtaining the electromagnetic wave signal.

[0081] Since the time series signal of the predetermined electrical parameter obtained after receiving and sampling the electromagnetic wave signal may include some redundant signals and noise signals. In addition, considering that multiple influencing factors will affect the characteristics of the electromagnetic wave signal (waveform, amplitude or spectrum), for example, even for the same gas environment, the difference in the size of the mechanical energy will also cause the amplitude of the electromagnetic wave signal to be different, but this will not affect the waveform and spectrum characteristics, so the spectrum signal can also be extracted during the signal processing process, and optionally, as described later, it is necessary to perform identification based on the spectrum signal. Therefore, in some cases, the gas attribute identification device may also include a signal processing unit 120-3 for preprocessing the time series signal of the predetermined electrical parameter to obtain a processed signal, and then the identification unit 120-2 will perform identification based on the processed signal. Of course, the signal processing unit 120-3 can also be included in the identification unit 120-2.

[0082] For example, the signal processing unit 120-3 may remove noise signals and / or intercept valid signals from the time series signal of the predetermined electrical parameter output by the electromagnetic wave receiving circuit to obtain a processed signal. Specifically, to improve sensing accuracy and / or facilitate identification, the time series signal of the predetermined electrical parameter is first processed (e.g., removing noise signals, intercepting valid signals, and extracting spectrum signals) before being input into the identification unit 120-2 for identification. The properties of the gas in the gas environment to be measured are then determined based on the processed signal.

[0083] Optionally, regarding the way in which the identification unit 120-2 identifies gas properties, one way may include: the identification unit 120-2 may analyze the changing trend of the value of the predetermined electrical parameter in the acquired timing signal of the predetermined electrical parameter over time (the changing trend can reflect the waveform), and according to the changing trend, it may be determined which gas environment the gas environment to be measured corresponds to or is closest to (one of the reference gas environments, and the possible gas environment is pre-determined as the reference gas environment according to the application scenario (for example, industry, automobile exhaust, indoor environment, etc.)).

[0084] In addition, another method may include: the identification unit 120-2 may also obtain a spectrum signal (such as a spectrum image) based on the timing signal of the predetermined electrical parameter, and determine which gas environment the gas environment to be measured corresponds to or is closest to by analyzing the spectrum signal.

[0085] Optionally, the identification unit 120 - 2 may obtain the properties of the gas in the gas environment to be measured based on a time series signal of a predetermined electrical parameter based on machine learning.

[0086] That is, the identification unit 120 - 2 may include a machine learning model that is trained to generate an identification result indicating the properties of the gas based on a timing signal of a predetermined electrical parameter (in order to improve identification accuracy, a processed signal after signal processing is generally used).

[0087] As mentioned above, for the first approach, the processed signal is a time domain signal, so the type of machine learning model suitable for training time domain signals can be selected.

[0088] For the second approach, the processed signal is a frequency domain signal (spectral image), so the type of machine learning model suitable for image classification can be selected.

[0089] Of course, in addition to using a machine learning model, the identification unit 120-2 may also identify the properties of the gas in the gas environment to be measured by other means, and the present disclosure is not limited thereto. For example, according to the application scenario, the characteristics of the electromagnetic wave signal for each of the various common reference gas environments (e.g., the trend of change of the value of the electrical parameter with respect to time, the spectral characteristics) may be stored in advance, and the electromagnetic wave signal in the gas environment to be measured may be sampled and the characteristics of the processed signal after signal processing are compared with the stored characteristics to determine the gas environment corresponding to or closest to the characteristic.

[0090] Next, a detailed description will be given of how the identification unit 120 - 2 identifies the properties of the gas in the gas environment to be measured based on the machine learning model.

[0091] The machine learning model is trained on a training set to obtain a trained machine learning model, and the training set includes multiple processed signals and true labels of gas properties corresponding to each of the multiple processed signals.

[0092] For example, for time domain signals, the machine learning model may be a bidirectional long short-term memory recurrent neural network (bi-LSTM) model.

[0093] The bidirectional long short-term memory recurrent neural network (bi-LSTM) model can be trained as follows: Each time domain signal included in the training set is input forward and backward to the bi-LSTM model to obtain a predicted label corresponding to each time domain signal, and based on the difference between each predicted label and the true label of the corresponding time domain signal, the model parameters of the bi-LSTM model are updated by error backpropagation and gradient descent until the model parameters converge with respect to the training set. The method for obtaining the training set will be described later.

[0094] For example, in this bi-LSTM model, the bidirectional LSTM layer is configured with 50 neurons in each direction, for a total of 100 neurons. The output after the bidirectional LSTM layer is then connected to a fully connected layer (comprising 32 neurons), which undergoes batch normalization (with momentum set to 0.8) and is activated by an activation function (e.g., ReLu). The layer is then connected to a fully connected layer in the model output structure, where the number of neurons is set based on the number of classifications (e.g., if the model is trained to identify gases in ten gas environments, the number of neurons is set to 10). Finally, the layer is activated by a softmax function, resulting in a predicted label for each training sample (processed signal) in the training set. The predicted label may differ from the true label of the training sample, so this difference can be used to update the model parameters. This means that during the model parameter update process, the error backpropagation method and gradient descent method can be used to update the model parameters.

[0095] For example, for a spectral signal, the machine learning model may be a machine learning model such as a convolutional neural network model that can be used for image classification.

[0096] This machine learning model, such as a convolutional neural network model, which can be used for image classification, can be trained as follows: each spectral image signal included in the training set is input into the CNN model to obtain a predicted label corresponding to each spectral image signal. Based on the difference between each predicted label and the true label of the corresponding spectral image signal, the model parameters of the CNN model are updated using error backpropagation and gradient descent until the model parameters converge with respect to the training set. Similarly, the method for obtaining the training set will be described later.

[0097] For example, a convolutional neural network can employ a common architecture such as AlexNet or ResNet, and similarly outputs a predicted label for each training sample (processed signal) in the training set. The predicted label may differ from the actual label of the training sample, and this difference can be exploited to update model parameters. Specifically, error backpropagation and gradient descent can be used to update the model parameters.

[0098] Typically, a machine learning model is trained on a training set. Therefore, before training a machine learning model, you need to obtain a training set.

[0099] As previously mentioned, each processed signal is obtained by processing a received electromagnetic wave signal, and the characteristics of the electromagnetic wave signals generated by the breakdown discharge process in different gas environments are different. Therefore, the electromagnetic wave signals in different gas environments can be used to obtain multiple processed signals. Therefore, the training set can be obtained in the following manner.

[0100] First, a first number of reference gas environments having different gas properties are selected.

[0101] As an example and not a limitation, 10 reference gas environments are used in the embodiments of the present disclosure (as shown in Table 1). Depending on the specific application scenario (for example, industry, automobile exhaust, indoor environment, etc.) that requires actual identification of the gas environment, different and more reference gas environments can be selected to generate a training set. Among them, in the following content of the present disclosure, the air pressure of the 10 reference gas environments is a standard atmospheric pressure. Of course, if the machine learning model finally trained needs to identify the gas pressure of the gas environment to be tested, then identifying the gas pressure should also be used as a training target. At this time, the gas pressure can also be used as a variable. For example, the gas pressure of at least two reference gas environments can be set to be different, but the gas composition and gas concentration are the same.

[0102]

Table 1

[0103]

[0104]

[0105] A second number of processed signals is then obtained for each reference gas environment.

[0106] Figure 5B The structure of the self-powered gas sensing device to identify the gas environment to be measured is selected, that is, the structure and parameters of the energy harvester (such as the triboelectric nanogenerator) and the breakdown discharger are selected. Figure 2-4The structure of the self-powered gas sensing device described in the present invention is such that the first output electrode and the second output electrode of the energy harvester are connected to the first electrode and the second electrode of the breakdown discharger, respectively, to provide electrical energy to the breakdown discharger. That is, after determining the structure of the self-powered gas sensing device to be used to identify the properties of the gas in the gas environment to be measured, the structure of the self-powered gas sensing device based on which the training set is generated based on the reference gas environment, as will be described later, also needs to be the same structure (different structures (for example, the length (l) of the connecting wire between the energy harvester and the breakdown amplifier may be different) will result in different waveforms and spectral characteristics of the electromagnetic wave signal generated for the same gas environment), so that the machine learning model can be trained most accurately.

[0107] Optionally, for each reference gas environment, the following operations i-iii are performed in sequence to obtain a second number of processed signals.

[0108] In operation i, the breakdown arrester is placed in a sealed chamber filled with the gas in the reference gas environment. For example, the sealed chamber can be evacuated first and then filled with the gas corresponding to the reference gas environment. When the reference gas environment is subsequently changed, the sealed chamber can be evacuated again and then filled with the gas corresponding to the next reference gas environment.

[0109] Operation ii, mechanical energy is obtained by an energy harvester (for example, a friction nanogenerator) to convert the mechanical energy into electrical energy, wherein the breakdown discharger performs breakdown discharge in the reference gas environment based on the electrical energy obtained from the energy harvester, and the current generated by the breakdown discharge causes the emission of an electromagnetic wave signal.

[0110] In operation iii, after the electromagnetic wave signal is transmitted, the electromagnetic wave receiving circuit may acquire the electromagnetic wave signal and convert the electromagnetic wave signal into a second number of time series signals of electrical parameters (for example, a plurality of sampling points of a second number of time periods of the same length and corresponding electrical parameter values are converted into a second number of time series signals of predetermined electrical parameters), for example, Figure 5C As shown, as an example, the number of reference gas environment types (a first number) is 10, and the number of voltage time series signals obtained for each reference gas environment is 100. As described later, this includes a second number 80 for the training set plus a third number 20 for the test set. Subsequently, the time series signal of each predetermined electrical parameter is processed to obtain the second number of processed signals.

[0111] In order to more clearly illustrate the process of obtaining the second number of processed signals, Figure 5D Also shown is a flow chart for obtaining a second number of processed signals for each reference gas environment.

[0112] like Figure 5D As shown, the initial state of the gas chamber is an air environment. First, the gas chamber is evacuated to 0.001 MPa, and the gas corresponding to the reference gas environment (target gas) is injected to 0.1 MPa (one atmosphere), and the process is repeated multiple times (5 times in this example) to ensure that the target gas fills the gas chamber and no other gas exists in the gas chamber. Then, the electric energy output by the energy collector (for example, a friction nanogenerator) causes the breakdown discharger to perform breakdown discharge to realize the emission of an electromagnetic wave signal. Then, when receiving the electromagnetic wave signal, the electromagnetic wave signal is also converted into a timing signal of predetermined electrical parameters and a processed signal is further obtained. When the number of timing signals of predetermined electrical parameters reaches a preset number of 100 (as described later, the second number 80 for the training set plus the third number 20 for the test set), the acquisition of the processed signal for the current reference gas environment is stopped, the gas chamber is re-evacuated to 0.001MPa, and the gas corresponding to the next reference gas environment (shown as an air environment in the figure) is injected to 0.1MPa (one atmosphere), and the process is repeated multiple times (here 5 as an example) to obtain the second number of processed signals for the next reference gas environment.

[0113] Next, for each reference gas environment, the second number of processed signals and the true labels of the gas properties corresponding thereto are used as a training subset of the reference gas environment.

[0114] Finally, the training subsets of the first number of reference gas environments are collectively used as a training set.

[0115] For example, when the second number is 80, the 80 processed signals obtained for each reference gas environment (of course, 80 here is just an example) and the true labels of the gas properties corresponding to these 80 processed signals (for example, air, nitrogen, helium, etc., which can be marked with the numbers (1, 2, 3...10) in the table) are used together as a training set. In this example, the training set includes 800 groups of training data.

[0116] Optionally, the 80 processed signals (which may be time domain signals or spectrum signals) may be in image form. That is, after obtaining a time domain signal or spectrum signal from each time series signal of a predetermined electrical parameter, a time domain image or spectrum image may be further generated to facilitate training of a machine learning model.

[0117] In addition, after the machine learning model training is completed, a test set is generally used to evaluate the performance of the trained machine learning model, that is, training samples that the model has not seen are used to test the performance of the trained machine learning model.

[0118] In an embodiment of the present disclosure, the performance of the trained machine learning model, that is, the effectiveness of the self-powered gas sensing system, can be verified in the following manner.

[0119] First, for each reference gas environment, a third number of processed signals is additionally acquired when acquiring the second number of processed signals, and the third number of processed signals and their respective corresponding true labels of gas properties are used as a test subset.

[0120] Then, the test subsets of the first number of reference gas environments are collectively used as a test set.

[0121] For example, 100 processed signals are acquired for each reference gas environment and divided into a first portion and a second portion. The first portion includes the second number of 80 processed signals (and their labels as 80 sets of training data) as described above, and the second portion includes the third number of 20 processed signals (and their labels as 20 sets of test data). For example, since there are 10 reference gas environments, there are 10 test subsets that together constitute the test set, for a total of 200 sets of test data.

[0122] Next, all processed signals in the test set are input into the trained machine learning model, and recognition results (predicted labels) are obtained from the trained machine learning model.

[0123] For example, the test data in the test set can be input into the trained machine learning model sequentially or randomly according to the true label type, and the recognition result (predicted label) can be obtained from the trained machine learning model.

[0124] Finally, the effectiveness of the self-powered gas sensing system is obtained based on the recognition results (predicted labels) of each processed signal obtained from the trained machine learning model and the true labels of the gas properties corresponding to the processed signals.

[0125] For example, taking the 200 sets of test data in the test set as an example, if the recognition results and labels of 197 sets of test data (processed signals) are consistent, and the recognition results and labels of 3 sets of test data (processed signals) are inconsistent, it can be determined that the effectiveness of the self-powered gas sensing system is 98.5%.

[0126] In machine learning, this effectiveness can also be automatically obtained through the confusion matrix based on the test set.

[0127] Figure 6 A schematic diagram showing the effectiveness based on the confusion matrix is shown. Still taking the training set and the data set as an example, both are obtained for the above 10 reference gas environments.

[0128] from Figure 6 The confusion matrix shown shows that for all test data in the 7 test subsets obtained for the reference gas environments numbered 1, 2, and 4-8, the predicted labels (recognition results of the trained machine learning model) are consistent with the true labels, for example, all are 1, all are 2, all are one of 4-8, and so on. It can also be understood that the recognition results of the 20 test data in the test subsets obtained for each of the reference gas environments numbered 1, 2, and 4-8 are all correct. On the other hand, for some test data in the 3 test subsets obtained for the reference gas environments numbered 3 and 9-10, the predicted labels (recognition results of the trained machine learning model) are inconsistent with the true labels. For example, in the test subset obtained for the reference gas environment numbered 3, the predicted label (recognition result) of one test data is 2, but the true label should be 3. Therefore, the accuracy of the recognition results of the test subset obtained for the reference gas environment numbered 3 is 95%, and the error rate is 5%.

[0129] Based on the comparison results of the predicted labels and the real labels of all the test data obtained for all reference gas environments numbered 1-10, it can be determined based on the confusion matrix that the effectiveness of the self-powered gas sensing system is 98.5%, which can achieve successful recognition of the input signal.

[0130] Through the above reference Figure 5A-6 The gas property identification device described can identify the properties of the gas in the gas environment where the self-powered gas sensing device (or the breakdown amplifier included therein) is located. The properties of the gas can be determined by analyzing the electromagnetic wave signal, and the sensing of most gases can be achieved. In addition, the specific identification process of the gas properties can be identified by a machine learning model, and the training set of the machine learning model can be obtained by electromagnetic wave signals generated for different gas environments. In addition, a test set is also obtained at the same time as the training set, which can be used to test the effectiveness of the self-powered gas sensing system.

[0131] According to another aspect of the present disclosure, a self-powered gas sensing method is provided, which can be used to identify properties of gas in a gas environment to be measured.

[0132] Figure 7 A schematic flow chart of a self-powered gas sensing method according to an embodiment of the present disclosure is shown, where the method is used to identify properties of a gas in a gas environment to be measured.

[0133] like Figure 7 As shown, in step S710, the breakdown arrester is placed in a gas environment to be tested.

[0134] Alternatively, the breakdown arrester may be as shown in FIG. Figure 2-4 A spark gapper in a self-powered gas sensing device is described.

[0135] In step S720 , mechanical energy is acquired by using an energy harvester, and the mechanical energy is converted into electrical energy.

[0136] Alternatively, the energy harvester may be a triboelectric nanogenerator. The triboelectric nanogenerator may be as shown in FIG. Figure 2-4 Furthermore, more details of step S720 have been described above and will not be repeated here.

[0137] Optionally, the triboelectric nanogenerator can be placed together with the breakdown discharger in the gas environment to be measured. However, sometimes, such as under space limitations, the triboelectric nanogenerator may not be placed in the gas environment to be measured (the breakdown amplifier needs to be placed in the gas environment to be measured).

[0138] In step S730, the electrical energy is obtained by using the breakdown discharger, wherein the electrical energy causes the breakdown discharger to perform breakdown discharge in the gas environment to be measured, and the current generated by the breakdown discharge causes the emission of an electromagnetic wave signal, and wherein the electromagnetic wave signal carries information associated with the properties of the gas in the gas environment to be measured.

[0139] As previously described, the first and second output electrodes of the energy harvester (e.g., a triboelectric nanogenerator) are connected to the first and second electrodes of the breakdown discharger to provide electrical energy to the breakdown discharger, thereby forming an electric field between the first and second electrodes. When the intensity of the electric field is sufficiently large, the breakdown amplifier can perform breakdown discharge, thereby forming a current loop. Due to the presence of inductance and capacitance in this current loop, oscillations occur, which can generate a changing magnetic field and a changing electric field in the surrounding area to generate an omnidirectional electromagnetic wave signal, which is ultimately transmitted to the gas attribute identification device for reception. In addition, the amplitude and spectrum of the electromagnetic wave signal will be different for different gas environments. Therefore, the gas attribute identification device can determine the properties of the gas in the gas environment at that time based on the analysis of the emitted electromagnetic wave signal.

[0140] In step S740, a gas property identification device is used to identify the properties of the gas in the gas environment to be measured based on the electromagnetic wave signal.

[0141] Optionally, step S740 may include performing the following sub-steps using the gas property identification device.

[0142] In sub-step S740 - 1 , the electromagnetic wave signal is received and converted into a timing signal of predetermined electrical parameters.

[0143] For example, an electromagnetic wave signal may be received by a receiving coil and converted into a predetermined electrical parameter signal, and a timing signal of the predetermined electrical parameter may be obtained by a sampling circuit.

[0144] In sub-step S740 - 2 , signal processing is performed on the timing signal of the predetermined electrical parameter to obtain a processed signal.

[0145] For example, signal processing may include at least one of the following operations: removing noise signals; intercepting effective signals; and extracting spectrum signals.

[0146] In sub-step S740 - 3 , based on the processed signal, the properties of the gas in the gas environment to be measured are identified.

[0147] For example, a trained machine learning model may be used to identify properties of the gas in the gas environment to be measured based on the processed signal.

[0148] The training set used to train the machine learning model and the test set used to test the performance of the machine learning model can be obtained by referring to the following: Figures 5B-5D Description of the process.

[0149] More details of the self-powered gas sensing method are similar to those of the self-powered gas sensing device and system described above, and therefore will not be repeated here.

[0150] Similarly, through the above-mentioned self-powered gas sensing method, it is possible to identify the properties of the gas in the gas environment in which the self-powered gas sensing device is located, and it is possible to sense most gases without the need for external power supply. The electromagnetic wave signal generated is itself a wireless signal and is not constrained by the signal transmission line and can carry information about the gas properties, so that the properties of the gas can be determined by analyzing the electromagnetic wave signal. In addition, the specific identification process of the gas properties can be identified by a machine learning model, and the training set of the machine learning model can be obtained by electromagnetic wave signals generated for different gas environments. In addition, when obtaining the training set, a test set is also obtained, which can be used to test the effectiveness of the self-powered gas sensing system.

[0151] According to another aspect of the present disclosure, a computing device is provided. This computing device can be used to implement the identification unit in the gas property identification device described above or to perform various operations of the identification unit. Furthermore, the computing device can also implement at least a portion of the operations of the signal processing unit in the gas property identification device.

[0152] Figure 8 FIG. 8 is a block diagram of a computing device 800 according to an embodiment of the present disclosure.

[0153] The computer device includes: a processor; and a memory on which instructions are stored. When the instructions are executed by the processor, the processor executes various operations involved in the process of identifying the properties of the gas in the gas environment to be measured based on machine learning performed by the identification unit.

[0154] The computing device may be a computer terminal, a mobile terminal or other devices.

[0155] The processor can be an integrated circuit chip with signal processing capabilities. The above-mentioned processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The steps and logic block diagrams of the operations performed by the identification unit and, optionally, the signal processing unit in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor, etc., and can be an X84 architecture or an ARM architecture.

[0156] The memory may be a non-volatile memory such as a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or flash memory. It should be noted that the memory of the methods described in the present disclosure is intended to include, but is not limited to, these and any other suitable types of memory.

[0157] The display screen of the computing device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the terminal housing, or an external keyboard, touchpad or mouse.

[0158] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the module, program segment, or part of the code contains at least one executable instruction for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0159] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuitry, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the embodiments of the present disclosure are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented, as non-limiting examples, in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or a controller or other computing device, or some combination thereof.

[0160] The exemplary embodiments of the present disclosure described in detail above are merely illustrative and not restrictive. Those skilled in the art will appreciate that various modifications and combinations may be made to these embodiments or their features without departing from the principles and spirit of the present disclosure, and such modifications should fall within the scope of the present disclosure.

Claims

1. A self-powered gas sensing system for identifying properties of a gas in a gas environment to be measured, comprising: A self-powered gas sensing device comprising: an energy harvester configured to capture mechanical energy and convert the mechanical energy into electrical energy; a breakdown discharger disposed in the gas environment to be measured, the breakdown discharger being configured to obtain the electrical energy, wherein the electrical energy causes the breakdown discharger to perform a breakdown discharge in the gas environment to be measured, the current generated by the breakdown discharge causing emission of an electromagnetic wave signal, and wherein the electromagnetic wave signal carries information associated with properties of the gas in the gas environment to be measured; and a gas property identification device configured to wirelessly receive the electromagnetic wave signal from the self-powered gas sensing device and identify the property of the gas in the gas environment to be measured based on the electromagnetic wave signal; Wherein, no wire connection is required between the self-powered gas sensing device and the gas property identification device.

2. The self-powered gas sensing system according to claim 1, wherein: The breakdown arrester comprises a first electrode and a second electrode which are isolated by gas insulation in the gas environment to be measured, and The first electrode and the second electrode have opposing discharge tips with a discharge gap between them. The electric energy forms an electric field between the discharge tips of the first electrode and the second electrode, and the electric field causes the gas in the gas environment to be measured to be broken down between the discharge gaps between the discharge tips of the first electrode and the second electrode, thereby performing breakdown discharge.

3. The self-powered gas sensing system according to claim 1, wherein: The gas properties include at least one of the following: gas composition, gas concentration, and gas pressure.

4. The self-powered gas sensing system according to any one of claims 1 to 3, wherein: The gas attribute identification device comprises: a signal receiving unit configured to receive the electromagnetic wave signal from the self-powered gas sensing device and convert the electromagnetic wave signal into a time sequence signal of a predetermined electrical parameter; and The identification unit is configured to identify the properties of the gas in the gas environment to be measured based on the time sequence signal of the predetermined electrical parameter.

5. The self-powered gas sensing system according to claim 4, wherein: The gas attribute identification device further includes: a signal processing unit configured to perform signal processing on the timing signal of the predetermined electrical parameter to obtain a processed signal, wherein the identification unit identifies the properties of the gas in the gas environment to be measured based on the processed signal; The signal processing includes at least one of the following operations: removing noise signals; intercepting effective signals; and extracting spectrum signals.

6. The self-powered gas sensing system according to claim 5, wherein: The recognition unit includes a machine learning model, wherein the machine learning model is trained to generate a recognition result indicating a property of the gas in the gas environment to be measured for the processed signal. The machine learning model is trained on a training set to obtain a trained machine learning model, and the training set includes multiple processed signals and true labels of gas properties corresponding to each of the multiple processed signals.

7. The self-powered gas sensing system according to claim 6, wherein: The training set is obtained in the following way: selecting a first number of reference gas environments having different gas properties; obtaining a second number of processed signals for each reference gas environment; For each reference gas environment, using the second number of processed signals and the true labels of the gas properties corresponding thereto as a training subset of the reference gas environment; as well as The training subsets of the first number of reference gas environments are collectively used as a training set.

8. The self-powered gas sensing system according to claim 7, wherein: A second number of processed signals for each reference gas environment is obtained by: for said reference gas environment, The breakdown discharger is placed in a sealed gas chamber filled with gas in the reference gas environment, and performs breakdown discharge in the reference gas environment based on the electrical energy obtained from the energy harvester, wherein the current generated by the breakdown discharge causes emission of an electromagnetic wave signal; Acquire the electromagnetic wave signal, and convert the electromagnetic wave signal into a second number of time series signals of predetermined electrical parameters; as well as Each time series signal of the predetermined electrical parameter is processed to obtain the second number of processed signals.

9. The self-powered gas sensing system according to claim 7, wherein: Each of the processed signals included in the training set is a time domain signal, and the machine learning model is a bidirectional long short-term memory recurrent neural network bi-LSTM model. The machine learning model is trained in the following way: Each time domain signal included in the training set is input forward and backward to the bi-LSTM model to obtain the prediction label corresponding to each time domain signal, and Based on the difference between each predicted label and the true label of the corresponding time domain signal, the model parameters of the bi-LSTM model are updated by error back propagation and gradient descent until the model parameters converge with respect to the training set.

10. The self-powered gas sensing system according to claim 7, wherein: Each of the processed signals included in the training set is a spectrum image signal, and the machine learning model is a convolutional neural network (CNN) model. The machine learning model is trained in the following way: Input each spectrum image signal included in the training set into the CNN model to obtain a prediction label corresponding to each spectrum image signal, and Based on the difference between each predicted label and the true label of the corresponding spectrum image signal, the model parameters of the CNN model are updated by error back propagation method and gradient descent method until the model parameters converge with respect to the training set.

11. A self-powered gas sensing device comprising: an energy harvester configured to capture mechanical energy and convert the mechanical energy into electrical energy; A breakdown discharger is provided in the gas environment to be measured, and is configured to obtain the electrical energy, wherein the electrical energy causes the breakdown discharger to perform breakdown discharge in the gas environment to be measured, and the current generated by the breakdown discharge causes the emission of an electromagnetic wave signal. The electromagnetic wave signal carries information associated with the properties of the gas in the gas environment to be measured, and is wirelessly transmitted to a gas property identification device for use in identifying the properties of the gas in the gas environment to be measured.

12. The self-powered gas sensing device according to claim 11, wherein: The breakdown arrester comprises a first electrode and a second electrode which are isolated by gas insulation in the gas environment to be measured, and The first electrode and the second electrode have opposite discharge tips with a discharge gap between the discharge tips. The electric energy forms an electric field between the tips of the first electrode and the second electrode, and the electric field breaks down the gas in the gas environment to be measured between the discharge gaps of the discharge tips of the first electrode and the second electrode to perform breakdown discharge.

13. A self-powered gas sensing method for identifying properties of a gas in a gas environment to be measured, comprising: placing the breakdown arrester in the gas environment to be tested; harvesting mechanical energy using an energy harvester and converting the mechanical energy into electrical energy; Obtaining the electrical energy using the breakdown discharger, wherein the electrical energy causes the breakdown discharger to perform a breakdown discharge in the gas environment to be measured, and the current generated by the breakdown discharge causes the emission of an electromagnetic wave signal, and wherein the electromagnetic wave signal carries information associated with properties of the gas in the gas environment to be measured; and using a gas property identification device to identify the properties of the gas in the gas environment to be measured based on the wirelessly received electromagnetic wave signal; Wherein, no wire connection is required between the breakdown arrester and the gas property identification device.

14. The self-powered gas sensing method according to claim 13, wherein: Identifying the properties of the gas in the gas environment to be measured based on the electromagnetic wave signal using a gas property identification device includes: receiving the electromagnetic wave signal and converting the electromagnetic wave signal into a timing signal of predetermined electrical parameters; performing signal processing on the timing signal of the predetermined electrical parameter to obtain a processed signal; and Based on the processed signal, properties of the gas in the gas environment to be measured are identified.

15. The self-powered gas sensing method according to claim 13, wherein: The gas attribute recognition device includes a machine learning model, and the self-powered gas sensing method further includes: Obtaining a plurality of processed signals and true labels of gas properties corresponding to the plurality of processed signals as a training set; and The machine learning model is trained using the training set, so that the trained machine learning model can generate an identification result indicating the property of the gas in the gas environment to be measured for the processed signal.

Images