CN115575491A - Self-powered gas sensing device, system and method - Google Patents

Abstract

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

Description

Self-powered gas sensing device, system and method

Technical Field

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

Background

The gas sensor plays an important role in the fields of industrial exhaust, indoor environment detection and the like, and has a wide application background. Conventional gas sensors typically rely on an external power source to provide energy, such as catalytic combustion gas sensors, semiconductor gas sensors, thermal conductivity gas sensors, infrared gas sensors, and the like. The need to rely on an external power source to supply power greatly limits the range of applications for gas sensors. Even though wireless energy transfer has now occurred, this way of supplying power is limited to a limited transmission distance and there is still a need for an external power source to supply power to the energy transmitting part.

The self-powered technology is a safe, stable and efficient electric energy supply technology which is used for collecting other forms of energy (such as solar energy, wind energy, mechanical energy, heat energy and the like) in the surrounding environment without an external power supply and converting the energy into electric energy so as to provide electronic equipment. However, such a power supply based on self-powered technology usually requires the introduction of energy management circuits due to the different impedance and output characteristics of the energy harvester, which in turn introduces additional energy requirements and increases the overall system size.

Meanwhile, the existing gas sensors also often have limitations of detection range and other defects, for example, the catalytic combustion gas sensor is limited to testing combustible gas and has danger of ignition and explosion, the semiconductor gas sensor is greatly interfered by background gas and is easily influenced by temperature, the thermal conductivity gas sensor is obviously influenced by temperature, the detection precision is poor, the sensitivity is low, and the infrared gas sensor has high cost and complex system, and is limited to testing gas absorbing infrared radiation, etc. Furthermore, many gas sensors cannot be spaced too far apart from the subsequent sensor data analysis device (e.g., not more than 1 m) because, for example, if a transmission medium such as a wire is required to transmit the sensing signal, the lengthy wire may present excessive impedance and thus affect the effectiveness of the sensing signal and increase the system volume, but certain application scenarios may not place the gas sensor and the sensor data analysis device close enough due to, for example, space constraints or the inability of the data analysis device to move.

Therefore, there is a need for a self-powered gas sensor that integrates an energy collection and conversion function and a gas detection function, has a small size, is suitable for safely sensing various types of gases, has high sensing accuracy, and has a long transmission distance for sensing signals.

Disclosure of Invention

According to an aspect of the present disclosure, there is provided a self-powered gas sensing system for identifying properties of a gas in a gas environment under test, comprising: a self-powered gas sensing device comprising: an energy harvester configured to take mechanical energy and convert the mechanical energy into electrical energy; a breakdown discharger disposed in the gas environment to be tested, 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 tested, a current generated by the breakdown discharge causes 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 tested; and a gas property identification device configured to receive the electromagnetic wave signal from the self-powered gas sensing device and identify a property of the gas in the gas environment to be measured based on the electromagnetic wave signal.

According to an embodiment of the disclosure, the breakdown discharger comprises a first electrode and a second electrode which are insulated and isolated via a gas in the gas environment to be measured, and wherein the first electrode and the second electrode have opposite discharge tips with a discharge gap therebetween, the electrical energy forms an electric field between the tips of the first electrode and the second electrode, and the electric field causes breakdown of 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 for breakdown discharge.

According to an embodiment of the present disclosure, wherein the properties of the gas comprise at least one of: gas composition, gas concentration, gas pressure.

According to an embodiment of the present disclosure, wherein 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 a property of the gas in the gas environment to be measured based on the timing signal of the predetermined electrical parameter.

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

According to an embodiment of the present disclosure, the recognition unit includes a machine learning model trained to generate, for the processed signals, recognition results indicating properties of the gas in the gas environment to be measured, wherein the machine learning model is trained on a training set resulting in a trained machine learning model, and the training set includes a plurality of processed signals and real labels of the gas properties corresponding to the plurality of processed signals, respectively.

According to an embodiment of the present disclosure, the training set is obtained by: 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, taking the second number of processed signals and the respective corresponding real labels of the gas attributes as a training subset; and using the training subsets for all reference gas environments together as a training set.

According to an embodiment of the disclosure, wherein the second number of processed signals for each reference gas environment is obtained by: performing, by the breakdown discharger placed in a closed gas chamber filled with a gas in the reference gas environment, a breakdown discharge in the reference gas environment based on the electric energy obtained from the energy collector, for the reference gas environment, wherein a current generated by the breakdown discharge causes emission of an electromagnetic wave signal; acquiring the electromagnetic wave signals and converting the electromagnetic wave signals into a second number of time sequence signals of preset electrical parameters; and processing each timing signal of the predetermined electrical parameter to obtain the second number of processed signals.

According to an embodiment of the present disclosure, wherein each of the processed signals comprised by the training set is a time domain signal, the machine learning model is a bidirectional long-and-short memory recurrent neural network (bi-LSTM) model, wherein the machine learning model is trained by: and updating model parameters of the bi-LSTM model by an error back propagation method and a gradient descent method based on the difference of each prediction label and a true label of the corresponding time domain signal until the model parameters converge relative to the training set.

According to an embodiment of the present disclosure, wherein each of the processed signals comprised by the training set is a spectral image signal, the machine learning model is a Convolutional Neural Network (CNN) model, wherein the machine learning model is trained by: inputting each spectral image signal included in the training set into the CNN model to obtain a prediction label corresponding to each spectral image signal, and updating model parameters of the CNN model by an error back propagation method and a gradient descent method based on the difference between each prediction label and a real label of the corresponding spectral image signal until the model parameters converge relative to the training set.

According to another aspect of the present disclosure, there is provided a self-powered gas sensing device comprising: an energy harvester configured to take mechanical energy and convert the mechanical energy into electrical energy; a breakdown discharger arranged in the gas environment to be tested, the breakdown discharger being configured to obtain the electrical energy, wherein the electrical energy causes the breakdown discharger to perform breakdown discharge in the gas environment to be tested, and a current generated by the breakdown discharge causes 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 tested.

According to an embodiment of the disclosure, the breakdown discharger comprises a first electrode and a second electrode insulated and isolated via a gas in the gas environment to be measured, and wherein the first electrode and the second electrode have opposing discharge tips with a discharge gap therebetween, the electrical 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 for breakdown discharge.

According to yet another aspect of the present disclosure, there is provided a self-powered gas sensing method for identifying properties of a gas in a gas environment to be measured, comprising: placing a breakdown discharger in the gas environment to be tested; acquiring mechanical energy by using an energy collector, and converting the mechanical energy into electric energy; acquiring the electric energy by using the breakdown discharger, wherein the electric energy enables the breakdown discharger to perform breakdown discharge in a gas environment to be tested, and current generated by the breakdown discharge causes emission of an electromagnetic wave signal, and the electromagnetic wave signal carries information related to the property of the gas in the gas environment to be tested; and identifying the attribute of the gas in the gas environment to be detected by utilizing a gas attribute identification device based on the electromagnetic wave signal.

According to the embodiment of the present disclosure, identifying the property of the gas in the gas environment to be measured based on the electromagnetic wave signal by using a gas property identification device includes: receiving the electromagnetic wave signal and converting the electromagnetic wave signal into a time sequence signal of a preset electrical parameter; performing signal processing on the time sequence signal of the predetermined electrical parameter to obtain a processed signal; and identifying a property of the gas in the gas environment to be measured based on the processed signal.

According to an embodiment of the present disclosure, wherein the gas property identification device comprises a machine learning model, the self-powered gas sensing method further comprises: acquiring a plurality of processed signals and real labels of gas attributes corresponding to the plurality of processed signals respectively to serve as a training set; and training the machine learning model with the training set such that the trained machine learning model is capable of generating, for the processed signals, recognition results indicative of attributes of the gas in the gas environment under test.

According to the self-powered gas sensing device, the self-powered gas sensing system and the self-powered gas sensing method, the properties of the gas in the gas environment where the self-powered gas sensing device is located, such as the identification of information of gas components, concentration, gas pressure and the like, can be identified.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings used in the description of the embodiments will be briefly introduced below. It should be apparent that the drawings in the following description are merely exemplary embodiments of the disclosure and that other drawings may be derived from those drawings by one of ordinary skill in the art without inventive effort.

FIG. 1 shows a schematic block diagram of a self-powered gas sensing system in accordance with an embodiment of the present disclosure.

FIG. 2 shows a schematic block diagram of a self-powered gas sensing device according to an embodiment of the present disclosure.

Fig. 3A-3B illustrate example structures of triboelectric nanogenerators.

Fig. 4 shows an equivalent circuit model of the self-powered gas sensing device described in fig. 2.

Fig. 5A shows a schematic block diagram of a gas property identification apparatus according to an embodiment of the present disclosure.

Fig. 5B shows a schematic of a configuration based on the second number of processed signals obtained from the self-powered gas sensing device.

Fig. 5C shows a schematic of the resulting voltage-time series for a 10 reference gas environment.

Fig. 5D shows a flow chart for obtaining multiple processed signals for each reference gas environment.

FIG. 6 illustrates a schematic diagram showing the effectiveness of a self-powered gas sensing system based on a confusion matrix.

FIG. 7 shows a schematic flow diagram of a self-powered gas sensing method according to an embodiment of the disclosure.

FIG. 8 shows a schematic block diagram of a computing device that may be used to implement a recognition unit according to an embodiment of the present disclosure.

Detailed Description

The embodiments of the present invention will be described in detail below. It should be emphasized that the following description is merely exemplary in nature and is not intended to limit the scope of the invention or its application.

In order to make the objects, technical solutions and advantages of the present disclosure more apparent, exemplary embodiments according to the present disclosure will be described in detail below with reference to the accompanying drawings. It is to be understood that the described embodiments are merely a subset of the embodiments of the present disclosure and not all embodiments of the present disclosure, with the understanding that the present disclosure is not limited to the example embodiments described herein.

In the present specification and the drawings, steps and elements having substantially the same or similar characteristics are denoted by the same or similar reference numerals, and repeated description of the steps and elements will be omitted. The terms "first", "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying a number of indicated technical features. Thus, where a feature defined as "first" or "second" may explicitly or implicitly include one or more of the description of an embodiment of the invention, the meaning of "a plurality" is two or more unless specifically defined otherwise.

Fig. 1 shows a schematic block diagram of a self-powered gas sensing system 100 in accordance with an embodiment of the present disclosure.

As shown in fig. 1, the self-powered gas sensing system 100 may include two parts, a self-powered gas sensing device 110 and a gas attribute identification device 120.

The self-powered gas sensing device 110 may be used to obtain mechanical energy and self-power by converting the mechanical energy into electrical energy. In addition, the self-powered gas sensing device 110 is also capable of sensing properties of gas in a gas environment under test and generating electromagnetic wave signals that carry information related to the properties of the gas in the gas environment under test.

For example, the properties of the gas may include at least one of: gas composition, gas concentration, gas pressure. The gas composition may be for a pure gas environment or for a mixed gas environment. In a mixed gas environment, gas components refer not only to the types including gas components but also to their respective gas concentrations.

For example, the mechanical energy may come from artificially applied forces, wind forces, wave-applied forces, vehicle motion-applied forces, rain drops, liquid flow, and the like.

The gas property identification device 120 may be configured to receive electromagnetic wave signals from the self-powered gas sensing device 110 and identify properties of gas in the gas environment under test based on the electromagnetic wave signals.

Since the self-powered gas sensing device 110 and the gas property identification device 120 are in electromagnetic wave signal transmission, they can be separated by a long distance and do not need to be connected by wires, for example, they can be separated by 30m, and the gas property identification device 120 can also receive the electromagnetic wave signal and identify the gas property. Thus, there may be better applications in specific scenarios, for example, where space is limited or the gas property identification device is not easily handled.

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

According to the self-powered gas sensing system, the attribute of the gas in the gas environment where the self-powered gas sensing device is located can be realized, most of the gas can be sensed, external power supply is not needed, the generated sensing signal is a wireless signal and is not limited by a signal transmission line, and an additional energy management module and a wireless signal transmitting module are not needed, so that the self-powered gas sensing system is simple in structure, small in size and high in accuracy in identification of the gas attribute, and the self-powered gas sensing system has a larger application range.

The self-powered gas sensing device in the self-powered gas sensing system 100 described in fig. 1 is described in detail below in conjunction with fig. 2-4.

FIG. 2 illustrates a block diagram of a self-powered gas sensing device according to an embodiment of the present disclosure.

As shown in FIG. 2, self-powered gas sensing device 110 includes an energy harvester 110-1 and a breakdown discharge 110-2.

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

The energy collector 110-1 may be placed in the gas environment to be measured or outside the gas environment to be measured. Wherever placed, the energy harvester 110-1 needs to take mechanical energy and convert the mechanical energy into electrical energy to achieve self-powering of the self-powered gas sensing device 110.

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

The operation principle of the friction nanogenerator is described below. It is to be understood that the working principles to be described below are exemplary only to help better understand the embodiments of the present disclosure, and that different triboelectric nanogenerators have different working principles.

The triboelectric nanogenerator 110-1 may include a triboelectric generation layer for forming charges of opposite polarities on the first output electrode and the second output electrode based on the acquired mechanical energy, thereby forming an electric field between the first electrode and the second electrode of the breakdown discharger connected to the first output electrode and the second output electrode as described later (supplying electric energy to the breakdown discharger), a first output electrode, and a second output electrode (not shown). Of course, in case of other types of energy collectors, there are also a first output electrode and a second output electrode to form an electric field between the first electrode and the second electrode of the breakdown discharger.

An exemplary structure of the triboelectric nanogenerator 110-1 may include a sliding triboelectric nanogenerator (FS-TENG) (fig. 3A) and a contact separation triboelectric nanogenerator (CS-TENG) (fig. 3B), as shown in fig. 3A-3B, and a specific operation process will be described with reference to fig. 3A-3B. Of course, the following example structures are merely to facilitate a better understanding of the present disclosure, and are not intended to be limiting. Any other suitable configuration of the triboelectric nanogenerator may be used.

The triboelectric nanogenerator may be a sliding triboelectric generator, as shown in fig. 3A. The sliding friction type generator is composed of two film polymers with different back surfaces plated with metal electrode materials or the film polymer and an electrode, and sequentially comprises a top electrode, a first type material film layer and a second type material film layer with opposite friction polarities and a bottom electrode from top to bottom. The sliding friction type generator receives external force (mechanical energy), so that the first type material film layer and the second type material film layer generate relative motion, and charge transfer occurs due to a triboelectric effect, so that an electric potential difference (voltage difference) is formed between the top electrode and the bottom electrode, and an electric field can be formed between the first electrode and the second electrode of the breakdown discharger (the breakdown discharger is provided with electric energy) which are connected with the top electrode and the bottom electrode.

By way of example, fig. 3A shows a generator made of PTFE (polytetrafluoroethylene), a fluorocarbon solid (PTFE), and nylon (nylon), which are two materials with opposite friction polarities, and the mechanism of operation thereof. When PTFE and nylon are in contact, a negative charge is created on the PTFE surface and a positive charge is created on the nylon surface because PTFE gets electrons stronger than nylon. When PTFE and nylon are completely heavy, no potential difference is generated between the electrode on the nylon and the electrode under the PTFE, and when the two have dislocation motion under the action of external force (mechanical energy), frictional charges on a dislocation area cannot be completely offset, and at the moment, a potential difference is generated between the two electrodes. When PTFE and nylon are again brought together, the dislocation area will disappear, the potential difference created by the triboelectric charges will also disappear, and free electrons will again flow from the electrode on nylon to the electrode on PTFE. Electric energy converted from mechanical energy can be output from between the two electrodes.

Another exemplary triboelectric nanogenerator may be a contact-split triboelectric nanogenerator (CS-TENG). As shown in fig. 3B, the friction nanogenerator includes, in order from top to bottom, a first electrode layer, a first friction material layer, a second friction material layer and a second electrode layer, wherein the first friction material layer and the second friction material layer have different electronegativity from the first friction material layer, and the material of at least one of the first friction material layer and the second friction material layer is an insulating material (for maintaining triboelectric charge for a long time), for example, the material of the first friction material layer may be a Polyimide (PI) film (Kapton), and the material of the second friction material layer may be polymethyl methacrylate (PMMA).

In the case where pressure (mechanical energy) is applied to the first electrode layer, the first friction material layer and the second friction material layer are in contact with each other, and due to a triboelectric effect, charges of different polarities are charged on the surfaces where the first friction material layer and the second friction material layer are in contact with each other, but the charges are formed only on the contact surfaces and the positive and negative charges can be cancelled out, so that a potential difference is not formed between the first electrode layer and the second electrode layer at this time.

Once the surfaces of the first and second friction material layers that are in contact with each other are released and separated, a potential difference is generated between the electrodes on the upper and lower surfaces of the first and second friction material layers, which potential difference can form an electric field between the first and second electrodes of the breakdown discharger (supply electric energy to the breakdown discharger) connected to the first and second electrode layers during the release.

That is, when no pressure signal is input, no induced charge is generated on the two electrode layers of the friction nanogenerator, so that no potential difference exists between the two electrode layers, and thus no electric energy can be supplied to the breakdown discharger. When the pressure signal is input, the first friction material layer and the second friction material layer generate induced charges, so that when the pressure signal stops being input (during the releasing process as described above), the induced charges are generated on the first electrode layer and the second electrode layer, so that a potential difference is formed between the two electrode layers, and further, the generated electric energy is provided to the breakdown discharger.

The operation of the breakdown voltage arrester 110-2 will be described below. It is to be understood that the principles of operation that will be described below are exemplary only to facilitate a better understanding of embodiments of the present disclosure.

The breakdown discharger 110-2 is arranged in the gas environment to be tested and is configured to obtain electric energy obtained by converting the obtained mechanical energy by the friction nanometer generator 110-1, wherein the electric 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.

Since the characteristics of the generated electromagnetic wave signal, e.g. waveform, amplitude, spectral characteristics, etc., are different for different gas environments under test (having different gas properties), the electromagnetic wave signal can carry information associated with the properties of the gas in the gas environment under test. Based on the analysis of the electromagnetic wave signal, the properties of the gas in the gas environment to be measured can be identified.

The breakdown discharger 110-2 may include a first electrode and a second electrode isolated via gas insulation in the gas environment to be measured, and wherein the first electrode and the second electrode have opposing discharge tips with a discharge gap therebetween, the electrical energy forms an electric field between the discharge tips of the first electrode and the second electrode, and the electric field causes breakdown of 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 the breakdown discharge.

For example, the discharge tip may be a metal structure and may be formed by an electron beam evaporation process. The minimum spacing between the two metal structures is controlled to be 5-500 microns, which can be observed by a microscope. When electric energy is acquired from the friction nano-generator 110-1, an electric field is formed between the first electrode and the second electrode of the breakdown discharger, the electric field strength reaches the maximum at the discharge tip, and when the electric field strength at the discharge tip is large enough, gas in the gas environment to be measured is broken down between discharge gaps of the discharge tips of the first electrode and the second electrode to perform breakdown discharge.

The breakdown discharge will create a current between the discharge tips that will result in the emission of an electromagnetic wave signal.

Specifically, a strong electric field is generated between the opposing discharge tips of the first and second electrodes of the breakdown voltage device, causing electrons to move from the cathode to the anode. During the movement, the electrons collide with air molecules at high speed, so that new electrons, positive ions and negative ions are generated, the electrons are broken and plasma is further generated. The plasma can be viewed as a collective oscillation of clusters of charged particles, creating a region of zero impedance to act as a conductor of electrons. Thus, a pulse current is generated in the transmission system, the amplitude and pulse rise time of which are related to the voltage, gap width and gas properties (gas composition, gas pressure, concentration, etc.), etc. Eventually, as the electric field weakens, the weakened electron avalanche cannot continue to support the via, so that the circuit continues back to the open state.

The generation process of the electromagnetic wave signal will be described in detail with reference to fig. 4.

Fig. 4 shows an equivalent circuit model of the self-powered gas sensing device (including the energy harvester and the breakdown discharger) depicted in fig. 2-3B.

As shown in fig. 4, the voltage source Vi and the equivalent capacitance Ci correspond to an equivalent circuit model of an energy collector (e.g., a tribo nanogenerator); C. r and L are capacitances, inductances and resistances of the energy collector and the breakdown discharger, which may be derived from parasitic capacitances, parasitic self-inductances, parasitic resistances, etc., that is, when the breakdown discharge occurs, the electrodes (such as the first output electrode and the second output electrode as described above) of the energy collector (e.g., the tribo-nanogenerator) and the first electrode and the second electrode of the breakdown discharger form a conducting loop. Once the pulse current appears in the breakdown discharge, the pulse current generates a current signal of underdamped oscillation in a transmitting system consisting of the friction nanometer generator and the breakdown discharge device. The oscillation may generate a varying magnetic field and a varying electric field around to generate an omni-directionally propagating electromagnetic wave signal that is ultimately transmitted to and received by the gas property identification device. Alternatively, the gas property identification apparatus may receive the electromagnetic wave signal through a receiving coil or a receiving capacitor.

It is possible to conduct a study for evaluating the output performance of an electromagnetic wave signal due to the breakdown and the relationship of the influencing factors. The main influencing factors can be determined empirically as the voltage (U) of the breakdown discharger, the gap distance (D) between the breakdown discharger electrodes, the movement direction (-) of the friction nanogenerator, the length (l) of the connecting wire between the energy collector (e.g. the friction nanogenerator) and the breakdown discharger, the spatial conductor distribution (a), the distance (D) between the breakdown discharger and the receiver, the gas composition (N), the gas pressure (P), the gas concentration (C), the temperature (T) and the humidity (H).

By sequentially changing the parameter value of one influencing factor while keeping the parameter values of the other influencing factors unchanged, the following conclusions can be drawn: most of the above-mentioned influencing factors change the amplitude of the electromagnetic wave signal, but do not affect the waveform and the frequency spectrum, but the change of the length (l) of the connecting wire between the energy collector (such as a friction nano generator) and the breakdown discharger, as well as the gas composition (N), the gas pressure (P) and the gas concentration (C) causes the waveform and the frequency spectrum of the electromagnetic wave signal to change. This also shows that, under the condition that the structure of the same self-powered gas sensing system is not changed, i.e. under the condition that the length (l) of the connecting wire between the energy collector (such as a friction nano generator) and the breakdown discharger is fixed, the property of the gas in the gas environment to be measured in which the self-powered gas sensing system is located can be identified through the electromagnetic wave signal.

By means of the self-powered gas sensing device as described with reference to fig. 2-4, sensing of properties of the gas in the gas environment in which the self-powered gas sensing device is located can be achieved, sensing of most gases can be achieved without external power supply, the generated electromagnetic wave signal itself is a wireless signal and thus not bound by a signal transmission line and can carry information of the gas properties, so that the properties of the gas can be determined by analyzing the electromagnetic wave signal.

The construction and operation of the gas property identification device in the self-powered gas sensing system described in fig. 1 will be described in detail below with reference to fig. 5A-5D.

Fig. 5A shows a schematic block diagram of a gas property identification apparatus according to an embodiment of the present disclosure.

As shown in fig. 5A, the gas property identification device 120 may include: a signal receiving unit 120-1 and an identification unit 120-2.

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, i.e., a time-series signal of a change in the electrical parameter with time.

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 a voltage or a current), and the sampling circuit may sample the predetermined electrical parameter signal at a predetermined sampling frequency, thereby obtaining a timing 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.

The identification unit 120-2 is configured to identify a property of the gas in the gas environment to be measured based on the timing signal of the predetermined electrical parameter.

As described above, if the properties of the gas are different, the waveform and the spectrum characteristics of the electromagnetic wave signal are correspondingly different, so that the properties of the gas in the gas environment to be measured can be obtained by analyzing the time-series signal of the predetermined electrical parameter obtained after the electromagnetic wave signal is received and sampled.

Some redundant signals as well as noise signals may be included in the timing signal of the predetermined electrical parameter obtained by receiving and sampling the electromagnetic wave signal. Furthermore, considering that a plurality of influencing factors all influence the characteristics (waveform, amplitude or frequency spectrum) of the electromagnetic wave signal, for example, even for the same gas environment, the difference of the magnitude of the mechanical energy will cause the amplitude of the electromagnetic wave signal to be different, but this will not influence the waveform and the frequency spectrum characteristics, so the frequency spectrum signal can also be extracted in the signal processing process and optionally identified based on the frequency spectrum signal as described later, therefore, in some cases, the gas property identification apparatus may further include a signal processing unit 120-3 for preprocessing the time sequence 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 may also be included in the recognition unit 120-2.

For example, the signal processing unit 120-3 may remove a noise signal and/or intercept a valid signal with respect to the timing signal of the predetermined electrical parameter output by the electromagnetic wave receiving circuit to obtain a processed signal. That is, in order to improve sensing accuracy and/or facilitate identification, before the time-series signal of the predetermined electrical parameter is input to the identification unit 120-2 for identification, the time-series signal of the predetermined electrical parameter is subjected to signal processing (e.g., removing a noise signal, intercepting a valid signal, extracting a spectrum signal, etc.), and then the property of the gas in the gas environment to be measured is obtained based on the processed signal.

Alternatively, regarding the manner in which the identifying unit 120-2 identifies the gas property, one manner may include: the identification unit 120-2 may analyze a trend of change of the value of the predetermined electrical parameter over time in the acquired time-series signal of the predetermined electrical parameter, which trend can reflect a waveform, and may determine which gas environment the to-be-measured gas environment corresponds to or is closest to (one of reference gas environments, a possible gas environment is predetermined as a reference gas environment according to an application scenario (e.g., industry, automobile exhaust, indoor environment, etc.) according to the trend of change.

Furthermore, another approach may include: the identification unit 120-2 may also obtain a spectrum signal (e.g., a spectrum image) according to the time-series signal of the predetermined electrical parameter, and determine which gas environment corresponds to or is closest to the gas environment to be measured by analyzing the spectrum signal.

Alternatively, the identification unit 120-2 may derive the properties of the gas in the gas environment to be measured based on the timing signals of the predetermined electrical parameters based on machine learning.

That is, the recognition unit 120-2 may include a machine learning model trained to generate recognition results indicative of properties of the gas for time-series signals of predetermined electrical parameters (typically, processed signals after signal processing are employed to improve recognition accuracy).

As described above, with the first approach, the processed signal is a time-domain signal, and thus the type of machine learning model that is suitable for training the time-domain signal can be selected.

With the second approach, the processed signal is a frequency domain signal (spectral image), and thus the type of machine learning model suitable for image classification can be selected.

Of course, the identifying unit 120-2 may identify the properties of the gas in the gas environment to be measured by other means besides using a machine learning model, and the disclosure is not limited thereto. For example, characteristics (for example, a change trend of the electrical parameter value with respect to time and a spectrum characteristic) of the electromagnetic wave signal for each of the various common reference gas environments may be stored in advance in association with each other according to an application, and characteristics of the processed signal obtained by sampling and signal processing the electromagnetic wave signal in the gas environment to be measured may be compared with each of the stored characteristics to determine the gas environment corresponding to or closest to the characteristics.

The following description is mainly made in detail with respect to the recognition unit 120-2 recognizing the property of the gas in the gas environment to be measured based on the machine learning model.

The machine learning model is trained on a training set to obtain a trained machine learning model, and the training set includes a plurality of processed signals and a true label of a gas attribute corresponding to each of the plurality of processed signals.

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

The bi-directional long-and-short memory recurrent neural network (bi-LSTM) model can be trained as follows: and updating model parameters of the bi-LSTM model by an error back propagation method and a gradient descent method based on the difference of each prediction label and a real label of the corresponding time domain signal until the model parameters converge relative to the training set. The way of acquiring the training set will be described later.

For example, with respect to the bi-LSTM model, there are 50 neurons per direction for the bi-directional LSTM layer, for a total of 100 neurons; the output after the bi-directional LSTM layer is then connected to a fully-connected layer (containing 32 neurons), activated by an activation function (e.g., reLu) after Batch Normalization (momentum set to 0.8), then connected to a fully-connected layer in the model output structure, which sets the number of neurons according to the number of classifications (e.g., if the model is trained to recognize gases in ten gas environments, the number of neurons is set to 10), and finally activated by a softmax function, resulting in a predictive label for each training sample (processed signal) in the training set. The prediction label and the real label of the training sample may have a difference, so that the model parameter can be updated by using the difference, that is, in the process of updating the model parameter, the model parameter can be updated by adopting an error back propagation method and a gradient descent method.

For example, for spectral signals, the machine learning model may be, for example, a convolutional neural network model or the like that may be used for image classification.

The machine learning model, e.g., a convolutional neural network model, etc., that may be used for image classification may be trained as follows: inputting each spectral image signal included in the training set into the CNN model to obtain a prediction label corresponding to each spectral image signal, and updating model parameters of the CNN model through an error back propagation method and a gradient descent method based on the difference between each prediction label and a true label of the corresponding spectral image signal until the model parameters converge relative to the training set. Also, the way of acquiring the training set will be described later.

For example, a convolutional neural network may employ a general-purpose architecture, such as the AlexNet, resNet architecture, and likewise output a prediction label for each training sample (processed signal) in the training set. The prediction label and the real label of the training sample may have a difference, so the model parameter can also be updated by using the difference, that is, in the process of updating the model parameter, the model parameter can be updated by using an error back propagation method and a gradient descent method.

Typically, the machine learning model is trained on a training set, and thus the training set needs to be acquired before the machine learning model is trained.

Since each processed signal is obtained by signal processing the received electromagnetic wave signal as described above, and characteristics of the electromagnetic wave signal generated based on the breakdown discharge process are different in different gas environments, the electromagnetic wave signal based on different gas environments can be used to obtain a plurality of processed signals. Therefore, the training set can be obtained in the following manner.

First, a first number of reference gas atmospheres having different gas properties are selected.

By way of example and not limitation, in embodiments of the present disclosure 10 reference gas environments (as shown in table 1) are used, and different more reference gas environments may be selected to generate the training set depending on the gas environment that the particular application scenario (e.g., industrial, automotive exhaust, indoor environment, etc.) requires to actually identify. Wherein, in the following of the present disclosure, the gas pressures of the 10 reference gas environments are all one standard atmospheric pressure. Of course, if the finally trained machine learning model needs to identify the gas pressure of the gas environment to be tested, then the identified gas pressure should also be used as a training target, and at this time, the gas pressure may also be used as a variable, for example, the gas pressures of at least two reference gas environments may be set to be different, but the gas components and the gas concentrations are the same.

[ TABLE 1 ] 10 reference gas atmosphere

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

FIG. 5B shows a schematic of a configuration based on a second number of processed signals obtained from the self-powered gas sensing device. The configuration of the self-powered gas sensing device to be used for identifying the gas environment to be measured, i.e. the configuration and parameters of the energy collector (e.g. friction nanogenerator) and the breakdown arrestor, are selected. As with the self-energized gas sensing device configuration described above with reference to fig. 2-4, the first and second output electrodes of the energy collector are connected to the first and second electrodes of the breakdown discharger, respectively, to provide electrical power to the breakdown discharger. That is, after the structure of the self-powered gas sensing device to be used for identifying the properties of the gas in the gas environment to be measured is determined, 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, there may be a difference in the length (l) of the connection wires of the energy collector and the breakdown amplifier) may cause the waveform and spectral characteristics of the electromagnetic wave signal generated for the same gas environment to be different), so that the machine learning model can be trained most accurately.

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

And i, placing the breakdown discharger in a closed gas chamber filled with the gas in the reference gas environment, for example, vacuumizing the closed gas chamber, and then injecting the gas corresponding to the reference gas environment. When the reference gas environment is replaced subsequently, the closed gas chamber can be vacuumized again, and then gas corresponding to the next reference gas environment is injected.

Operation ii, mechanical energy is captured by an energy collector (e.g., a triboelectric nanogenerator) to convert the mechanical energy into electrical energy, wherein the breakdown discharger performs a breakdown discharge in the reference gas environment based on the electrical energy captured from the energy collector, and a current generated by the breakdown discharge causes emission of an electromagnetic wave signal.

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 timing signals of the electrical parameter (for example, a second number of timing signals of a predetermined electrical parameter are formed by a plurality of sampling points of a second number of time periods of the same time length and corresponding electrical parameter values), for example, as shown in fig. 5C, as an example, the number of types (first number) of the reference gas environment is 10, and the number of timing signals of the voltage obtained for each reference gas environment is 100, as described later, including the second number 80 for the training set plus the third number 20 for the test set. Thereafter, the timing signal for each predetermined electrical parameter is processed to obtain the second number of processed signals.

To more clearly illustrate the process of obtaining the second number of processed signals described above, fig. 5D also shows a flow chart of obtaining the second number of processed signals for each reference gas environment.

As shown in fig. 5D, the chamber is initially an air environment, the chamber is first evacuated to 0.001 megapascal (MPa), and the gas corresponding to the reference gas environment (target gas) is injected to 0.1MPa (one atmosphere) this time, and the process is repeated multiple times (exemplified here as 5) to ensure that the target gas fills the chamber and no other gas is present in the chamber. Then, the electrical energy output by the energy collector (e.g., friction nano generator) causes the breakdown discharger to perform breakdown discharge to achieve the emission of the electromagnetic wave signal, and then converts the electromagnetic wave signal into a timing signal of a predetermined electrical parameter and further obtains a processed signal when receiving the electromagnetic wave signal, stops the acquisition of the processed signal for the current reference gas environment when the number of timing signals of the predetermined electrical parameter reaches a preset number 100 (as described later, the second number 80 for the training set plus the third number 20 for the test set), evacuates the gas cell again to 0.001MPa, and injects a gas corresponding to the next reference gas environment (shown as the air environment in the figure) to 0.1MPa (one atmosphere), and repeats the process multiple times (here, for example, 5) to perform the obtaining of the second number of the processed signal for the next reference gas environment.

Next, for each reference gas environment, the second number of processed signals and the respective corresponding real labels of the gas properties are taken as a training subset of the reference gas environment.

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

For example, in the case of the second number of 80, 80 processed signals obtained for each reference gas environment (of course, 80 is merely an example here) and a true label of the gas property (e.g., whether air, nitrogen, helium, or the like, which may be labeled with a number (1, 2, 3 \823010) in a table) corresponding to each of the 80 processed signals are taken together as a training set, which in this example includes 800 sets of training data.

Alternatively, the 80 processed signals (possibly time domain signals and possibly spectral signals) may be in the form of images. That is, after a time domain signal or a frequency spectrum signal is obtained from each timing signal of a predetermined electrical parameter, a time domain image or a frequency spectrum image may be further generated to facilitate training of the machine learning model.

In addition, after the training of the machine learning model is finished, the performance of the trained machine learning model is generally evaluated by using the test set, that is, the performance of the trained machine learning model is tested by using the training samples which are not seen by the model.

In embodiments of the present disclosure, the performance of the trained machine learning model, i.e., the effectiveness of the self-powered gas sensing system, may be verified in the following manner.

First, for each reference gas environment, a third number of processed signals is additionally acquired while acquiring the second number of processed signals, and the third number of processed signals and the authentic tags of the respective corresponding gas properties are taken as a test subset.

The test subsets of the first number of reference gas environments are then collectively referred to as a test set.

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

All of the processed signals in the test set are then input into a trained machine learning model, and recognition results (predictive labels) are derived from the trained machine learning model.

For example, the test data in the test set may be sequentially or randomly input to the trained machine learning model according to the genuine label type, and the recognition result (predictive label) is obtained from the trained machine learning model.

Finally, the effectiveness of the self-energizing gas sensing system is derived based on the recognition results (predictive signatures) of each processed signal from the trained machine learning model and the true signatures of the gas properties to which the processed signal corresponds.

For example, taking 200 sets of test data in the test set as an example, if the identification result of each of the 197 sets of test data (processed signals) is consistent with the tag and the identification result of each of the 3 sets of test data (processed signals) is inconsistent with the tag, then the self-powered gas sensing system may be determined to be 98.5% effective.

In machine learning, the validity may also be derived automatically through a confusion matrix based on the test set.

Fig. 6 shows a schematic diagram illustrating effectiveness based on a confusion matrix. Again, the training set and the data set were both obtained for the above 10 reference gas environments.

From the confusion matrix shown in fig. 6, it can be understood that the predicted label (the recognition result of the trained machine learning model) is consistent with the true label for all the test data in the 7 test subsets obtained for the reference gas environments numbered 1, 2, 4-8, e.g., all 1, all 2, all 4-8, etc., and that the recognition results for the 20 test data in the test subsets obtained for each of the reference gas environments numbered 1, 2, 4-8 are correct. On the other hand, for some of the test data in the 3 test subsets obtained for reference gas environments numbered 3, 9-10, the predicted tag (recognition result of the trained machine learning model) is inconsistent with the authentic tag. For example, in the test subset obtained for the reference gas environment numbered 3, the predicted label (identification result) of one test datum is 2, but the true label should be 3, so the identification result of the test subset obtained for the reference gas environment numbered 3 has a correct rate of 95% and an error rate of 5%.

By integrating the comparison results of the prediction tags and the real tags of all the test data obtained for all the reference gas environments with the numbers of 1-10, the validity of the self-powered gas sensing system can be determined to be 98.5% based on the confusion matrix, and the successful identification of the input signals can be realized.

By the gas property identification means described above with reference to fig. 5A-6, identification of the property of the gas in the gas environment in which the self-powered gas sensing means (or the breakdown amplifier it comprises) is located can be achieved, the property of the gas can be determined by analysis of the electromagnetic wave signal, and sensing of most gases can be achieved. Furthermore, the specific identification process of the gas properties may be identified by a machine learning model, and a training set of machine learning models may be obtained by electromagnetic wave signals generated for different gas environments. In addition, a test set is obtained at the same time as the training set, and can be used for testing the effectiveness of the self-powered gas sensing system.

According to yet another aspect of the present disclosure, a self-powered gas sensing method is also provided that can be used to identify properties of a gas in a gas environment under test.

FIG. 7 shows a schematic flow diagram of a self-powered gas sensing method for identifying properties of a gas in a gas environment under test, in accordance with an embodiment of the present disclosure.

As shown in fig. 7, in step S710, a breakdown discharger is placed in a gas environment to be measured.

Alternatively, the breakdown arrestor may be a breakdown arrestor in a self-powered gas sensing device as described with reference to fig. 2-4.

In step S720, mechanical energy is captured by the energy harvester and converted into electrical energy.

Alternatively, the energy collector may be a triboelectric nanogenerator. The triboelectric nanogenerator may be a triboelectric nanogenerator in a self-powered gas sensing device as described with reference to fig. 2-4. Also, more details of step S720 have been described in detail above, and therefore will not be repeated here.

Alternatively, the friction nanogenerator may be placed in the gas environment to be measured together with the breakdown voltage divider, but sometimes, for example, in the case of space limitation, the friction nanogenerator may not be placed in the gas environment to be measured (the breakdown voltage divider needs to be placed in the gas environment to be measured).

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 a current generated by the breakdown discharge causes 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.

As mentioned above, the first output electrode and the second output electrode of the energy collector (e.g. a friction nanogenerator) are connected with the first electrode and the second electrode of the breakdown discharger to provide electric energy to the breakdown discharger to form an electric field between the first electrode and the second electrode, and when the strength of the electric field is large enough, the breakdown amplifier can perform breakdown discharge, so that a current loop is formed, and due to the existence of inductance and capacitance, oscillation occurs in the current loop, and the oscillation can generate a changing magnetic field and a changing electric field around to generate an omnidirectional electromagnetic wave signal, and finally the omnidirectional electromagnetic wave signal is transmitted to the gas property identification device to be received. In addition, the amplitude and the frequency spectrum of the electromagnetic wave signal are different for different gas environments, so the gas property identification device can know the property of the gas in the gas environment at the moment based on the analysis of the transmitted electromagnetic wave signal.

In step S740, a gas attribute recognition device is used to recognize the attribute of the gas in the gas environment to be measured based on the electromagnetic wave signal.

Optionally, step S740 may include performing the following sub-steps with the gas property identification device.

In sub-step S740-1, the electromagnetic wave signal is received and converted into a time sequence signal of a predetermined electrical parameter.

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.

In sub-step S740-2, the time series signal of the predetermined electrical parameter is signal processed to obtain a processed signal.

For example, the signal processing may include at least one of: removing noise signals; intercepting a valid signal; and extracting the spectral signal.

In sub-step S740-3, based on the processed signal, a property of a gas in the gas environment under test is identified.

For example, a trained machine learning model may be utilized to identify properties of the gas in the gas environment under test based on the processed signals.

The training set used to train the machine learning model and the test set used to test the performance of the machine learning model may be obtained as described with reference to fig. 5B-5D.

Further details of the self-powered gas sensing method are similar to those described above for the self-powered gas sensing apparatus and system and therefore will not be repeated here.

Similarly, by the self-powered gas sensing method, the attribute of the gas in the gas environment where the self-powered gas sensing device is located can be identified, most of the gas can be sensed, external power supply is not needed, the generated electromagnetic wave signal is a wireless signal, is not limited by a signal transmission line and can carry the information of the gas attribute, and the attribute of the gas can be determined by analyzing the electromagnetic wave signal. Furthermore, the specific identification process of the gas properties may be identified by a machine learning model, and a training set of machine learning models may be obtained by electromagnetic wave signals generated for different gas environments. In addition, a training set is acquired along with a test set, which can be used to test the effectiveness of the self-powered gas sensing system.

According to yet another aspect of the present disclosure, a computing device is also provided. The computing device may be used to implement or perform various operations of the identification unit in the gas property identification apparatus as described above. Furthermore, the computing device may also implement at least a portion of the operations of the signal processing unit in the gas property identification apparatus.

Fig. 8 illustrates a block diagram of a computing device 800, according to an embodiment of the disclosure.

The computer device includes: a processor; and a memory having instructions stored thereon that, when executed by the processor, cause the processor to perform various operations involved in a process of identifying properties of a gas in a gas environment under test based on machine learning performed by an identification unit.

The computing device may be a computer terminal, mobile terminal, or other device.

The processor may be an integrated circuit chip having signal processing capabilities. The processor may be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The steps and logic block diagrams of the operations performed by the identification unit and, optionally, the signal processing unit in embodiments of the present disclosure may be implemented or performed. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, either of the X84 architecture or the ARM architecture.

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 a flash memory. It should be noted that the memories of the methods described in this disclosure are intended to comprise, without being limited to, these and any other suitable types of memories.

The display screen of the computing equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computing equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on a terminal shell, an external keyboard, a touch pad or a mouse and the like.

It is to be noted that the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises at least one executable instruction for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In general, the various example embodiments of this disclosure may be implemented in hardware or special purpose circuits, software, firmware, logic or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. While aspects of embodiments of the disclosure have been illustrated or described as block diagrams, flow charts, or using some other pictorial representation, it is well understood that the blocks, apparatus, systems, techniques or methods described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

The exemplary embodiments of the present disclosure, which are described in detail above, are merely illustrative, and not restrictive. It will be appreciated by those skilled in the art that various modifications and combinations of these embodiments or the features thereof are possible without departing from the spirit and scope of the disclosure, and that such modifications are intended to be included within the scope of the disclosure.

Claims (15)

1. A self-powered gas sensing system for identifying properties of a gas in a gas environment under test, 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 tested, 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 tested, a current generated by the breakdown discharge causes 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 tested; and

a gas property identification device configured to receive the electromagnetic wave signal from the self-powered gas sensing device and identify a property of gas in the gas environment under test based on the electromagnetic wave signal.

2. The self-powered gas sensing system of claim 1, wherein the surge arrestor comprises first and second electrodes isolated via gas insulation in the gas environment under test, and

the first electrode and the second electrode are provided with opposite discharge tips, a discharge gap is arranged between the opposite 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 enables gas in the gas environment to be detected to be broken down between the discharge gaps of the discharge tips of the first electrode and the second electrode, so that breakdown discharge is carried out.

3. The self-powered gas sensing system of claim 1, wherein the property of the gas comprises at least one of: gas composition, gas concentration, gas pressure.

4. A self-powered gas sensing system according to any of claims 1 to 3 wherein the gas property identification means 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 series signal of a predetermined electrical parameter; and

an identification unit configured to identify a property of the gas in the gas environment to be measured based on the timing signal of the predetermined electrical parameter.

5. The self-powered gas sensing system of claim 4, wherein the gas property identification device further comprises:

a signal processing unit configured to perform signal processing on the time-series signal of the predetermined electrical parameter resulting in a processed signal,

wherein the identification unit identifies a property of the gas in the gas environment to be measured based on the processed signal;

wherein the signal processing comprises at least one of: removing noise signals; intercepting a valid signal; and extracting the spectral signal.

6. The self-powered gas sensing system of claim 5, wherein the recognition unit comprises a machine learning model trained to generate recognition results indicative of properties of gas in the gas environment under test 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 a plurality of processed signals and real labels of gas attributes corresponding to the plurality of processed signals.

7. The self-powered gas sensing system of claim 6, wherein the training set is derived by:

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, taking the second number of processed signals and the respective corresponding real label of the gas property as a training subset of the reference gas environment; and

and taking the training subsets of the first number of reference gas environments together as a training set.

8. A self-powered gas sensing system according to claim 7, wherein the second number of processed signals for each reference gas environment is derived by: with respect to the reference gas environment, the gas environment,

performing, by the breakdown discharger placed in a closed gas chamber filled with a gas in the reference gas environment, breakdown discharge in the reference gas environment based on the electric energy obtained from the energy collector, wherein a current generated by the breakdown discharge causes emission of an electromagnetic wave signal;

acquiring the electromagnetic wave signals, and converting the electromagnetic wave signals into a second number of time sequence signals of a preset electrical parameter; and

each time series signal of a predetermined electrical parameter is processed to obtain the second number of processed signals.

9. The self-powered gas sensing system of claim 7, wherein each of the processed signals comprised by the training set is a time domain signal, the machine learning model is a bi-directional long-short-term memory recurrent neural network (bi-LSTM) model,

wherein the machine learning model is trained by:

respectively inputting each time domain signal included in the training set to the bi-LSTM model in a forward direction and in a reverse direction to obtain a prediction label corresponding to each time domain signal, and

updating model parameters of the bi-LSTM model by an error backpropagation method and a gradient descent method based on a difference of each predicted label and a true label of a corresponding time domain signal until the model parameters converge with respect to the training set.

10. The self-powered gas sensing system of claim 7, wherein each of the processed signals included in the training set is a spectral image signal, the machine learning model is a Convolutional Neural Network (CNN) model,

wherein the machine learning model is trained by:

inputting each spectral image signal included in the training set into the CNN model to obtain a prediction label corresponding to each spectral image signal, and

updating model parameters of the CNN model by an error back propagation method and a gradient descent method based on a difference of each predicted label and a true label of a corresponding spectral image signal until the model parameters converge with respect to the training set.

11. A self-powered gas sensing device comprising:

an energy harvester configured to take mechanical energy and convert the mechanical energy into electrical energy;

a breakdown discharger disposed in the gas environment to be tested, the breakdown discharger configured to obtain the electrical energy, wherein the electrical energy causes the breakdown discharger to perform breakdown discharge in the gas environment to be tested, and a current generated by the breakdown discharge causes emission of an electromagnetic wave signal,

wherein the electromagnetic wave signal carries information associated with a property of a gas in the gas environment to be measured.

12. The self-powered gas sensing device of claim 11, wherein the breakdown discharger comprises a first electrode and a second electrode separated via gas insulation in the gas environment to be tested, and

the first electrode and the second electrode are provided with opposite discharge tips, a discharge gap is arranged 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 gas in the gas environment to be detected between the discharge gaps of the discharge tips of the first electrode and the second electrode so as to carry out breakdown discharge.

13. A self-powered gas sensing method for identifying properties of a gas in a gas environment to be measured, comprising:

placing a breakdown discharger in the gas environment to be tested;

acquiring mechanical energy by using an energy collector, and converting the mechanical energy into electric energy;

acquiring the electric energy by using the breakdown discharger, wherein the electric 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 an electromagnetic wave signal, and the electromagnetic wave signal carries information related to the property of the gas in the gas environment to be tested; and

and identifying the attribute of the gas in the gas environment to be detected based on the electromagnetic wave signal by using a gas attribute identification device.

14. The self-powered gas sensing method of claim 13, wherein identifying the property of the gas in the gas environment under test based on the electromagnetic wave signal with a gas property identification device comprises:

receiving the electromagnetic wave signal, and converting the electromagnetic wave signal into a time sequence signal of a preset electrical parameter;

performing signal processing on the time sequence signal of the preset electrical parameter to obtain a processed signal; and

based on the processed signals, attributes of gas in the gas environment to be measured are identified.

15. The self-powered gas sensing method of claim 13, wherein the gas property identification device comprises a machine learning model, the self-powered gas sensing method further comprising:

acquiring a plurality of processed signals and real labels of gas attributes corresponding to the plurality of processed signals respectively to serve as a training set; and

training the machine learning model with the training set such that the trained machine learning model is capable of generating, for the processed signals, recognition results indicative of attributes of the gas in the gas environment under test.

Images