Gas detection system and gas detection method

Abstract

A gas detection system (100) comprises: a plurality of sensor circuits (10); an AC signal source (30) that supplies an AC signal to each of the plurality of sensor circuits (10); and a measurement circuit (32) that measures the complex impedance of each of the plurality of sensor circuits (10). Each of the plurality of sensor circuits (10) has a sensor body (11) in which real and imaginary parts of impedance change according to gas to which the sensor body is exposed.

Description

Gas detection system and gas detection method

[0001] The present disclosure relates to gas detection systems and methods.

[0002] Known methods for detecting and identifying gases include, for example, a method for detecting and identifying gases based on a signal obtained from a sensor exposed to the gas (see, for example, Patent Document 1).

[0003] In the invention described in Patent Document 1, an AC signal is applied to a sensor exposed to a gas, and the imaginary part of the impedance of the sensor (i.e., the imaginary component of the impedance) is determined, and a specific gas is identified with high sensitivity based on the imaginary part of the impedance of the sensor.

[0004] Japanese Patent Application Laid-Open No. 2002-139468

[0005] However, there is a demand for greater accuracy in gas identification.

[0006] Therefore, the present disclosure provides a gas detection system and the like that can improve the accuracy of gas identification.

[0007] A gas detection system according to one aspect of the present disclosure includes a plurality of sensor circuits, an AC signal source that supplies an AC signal to each of the plurality of sensor circuits, and a measurement circuit that measures the complex impedance of each of the plurality of sensor circuits, each of the plurality of sensor circuits having a sensor body whose real impedance part and imaginary impedance part change depending on the gas to which it is exposed.

[0008] A gas detection method according to one aspect of the present disclosure is a gas detection method for detecting a gas to which a plurality of sensor circuits are exposed, and includes an AC signal supply step of supplying an AC signal to each of the plurality of sensor circuits, an exposure step of exposing each of the plurality of sensor circuits to a sample gas, and a measurement step of measuring the complex impedance of each of the plurality of sensor circuits, wherein each of the plurality of sensor circuits has a sensor body whose impedance real part and impedance imaginary part change depending on the gas to which it is exposed.

[0009] These comprehensive or specific aspects may be realized by a system, a method, an integrated circuit, a computer program, or a recording medium such as a computer-readable CD-ROM (Compact Disc-Read Only Memory), or may be realized by any combination of a system, a method, an integrated circuit, a computer program, and a recording medium.

[0010] According to the gas detection system and the like according to one aspect of the present disclosure, it is possible to improve the accuracy of gas identification.

[0011] 1 is a block diagram showing a schematic configuration of a gas detection system according to an embodiment. FIG. 2 is a circuit diagram showing an equivalent circuit of a sensor circuit according to an embodiment. FIG. 3 is a schematic diagram showing an example of the configuration of an exposed portion according to an embodiment. FIG. 4 is a flowchart showing a gas detection method according to an embodiment. FIG. 5 is a flowchart showing a measurement method in a measurement step according to an embodiment. FIG. 6 is a graph showing the frequency characteristics of the real part of the impedance when a switch is open in the sensor circuit according to an embodiment. FIG. 7 is a graph showing the frequency characteristics of the imaginary part of the impedance when a switch is open in the sensor circuit according to an embodiment. FIG. 8 is a graph showing the frequency characteristics of the phase difference between current and voltage when a switch is open in the sensor circuit according to an embodiment. FIG. 9 is a graph showing the frequency characteristics of the real part of the impedance when a switch is shorted in the sensor circuit according to an embodiment. FIG. 10 is a graph showing the frequency characteristics of the imaginary part of the impedance when a switch is shorted in the sensor circuit according to an embodiment. FIG. 11 is a graph showing the frequency characteristics of the phase difference between current and voltage when a switch is shorted in the sensor circuit according to an embodiment. FIG. 12 is a graph showing the time waveform of the real part of the impedance when the switch of the sensor circuit according to an embodiment is open. FIG. 13 is a graph showing the time waveform of the imaginary part of the impedance when the switch of the sensor circuit according to an embodiment is open. 10 is a graph showing the time waveform of the real part of the impedance when a switch of the sensor circuit according to the embodiment is short-circuited. FIG. 11 is a graph showing the time waveform of the imaginary part of the impedance when a switch of the sensor circuit according to the embodiment is short-circuited. FIG. 12 is a graph showing the time waveform of the phase difference between current and voltage when a switch of the sensor circuit according to the embodiment is short-circuited. FIG. 13 is a graph showing the time waveform of the real part of the impedance measured using an AC signal having a frequency shifted from the resonance frequency when a switch of the sensor circuit according to the embodiment is short-circuited. FIG. 14 is a graph showing the time waveform of the imaginary part of the impedance measured using an AC signal having a frequency shifted from the resonance frequency when a switch of the sensor circuit according to the embodiment is short-circuited.10 is a graph showing a time waveform of the phase difference between current and voltage measured using an AC signal having a frequency shifted from the resonant frequency when a switch of the sensor circuit according to the embodiment is short-circuited.

[0012] A gas detection system according to aspect 1 of the present disclosure comprises a plurality of sensor circuits, an AC signal source that supplies an AC signal to each of the plurality of sensor circuits, and a measurement circuit that measures the complex impedance of each of the plurality of sensor circuits, each of the plurality of sensor circuits having a sensor body whose real part of impedance (i.e., the real component of the complex impedance) and imaginary part of impedance (i.e., the imaginary component of the complex impedance) change depending on the gas to which it is exposed.

[0013] The time waveforms of the real part and the imaginary part of the complex impedance measured by such a gas detection system are different. In other words, by measuring the complex impedance, two different sets of information about the sample gas can be obtained. Therefore, by using this information, more feature quantities can be extracted. By identifying the sample gas using more feature quantities, it is possible to improve the accuracy of identifying the sample gas.

[0014] Furthermore, in this embodiment, the complex impedance of each of the multiple sensor circuits is measured. If the multiple sensor circuits have different configurations, more information about the sample gas can be obtained. Therefore, more feature quantities can be obtained, which further improves the accuracy of identifying the sample gas. On the other hand, if the multiple sensor circuits have the same configuration, measuring the complex impedance of each of the multiple sensor circuits can improve the reliability of the measurement results.

[0015] A gas detection system according to a second aspect of the present disclosure is the gas detection system according to the first aspect of the present disclosure, wherein each of the plurality of sensor circuits further has an inductor connected in parallel to the sensor body, and the sensor body and the inductor connected in parallel to the sensor body form a parallel resonant circuit that resonates at the frequency of the AC signal.

[0016] This makes it possible to suppress noise components contained in the measurement results of the real part of the impedance, thereby improving the accuracy of the information on the sample gas and further increasing the accuracy of identifying the sample gas.

[0017] A gas detection system according to a third aspect of the present disclosure is the gas detection system according to the second aspect of the present disclosure, wherein each of the plurality of sensor circuits further includes a switch connected in series with the inductor, and the switch is short-circuited when the measurement circuit measures the real part of the impedance of the complex impedance, and the switch is open when the measurement circuit measures the imaginary part of the impedance of the complex impedance.

[0018] This makes it possible to suppress noise components contained in the measurement results of the real impedance part and the imaginary impedance part, thereby improving the accuracy of the information on the sample gas and further improving the accuracy of identifying the sample gas.

[0019] A gas detection system according to aspect 4 of the present disclosure is a gas detection system according to any one of aspects 1 to 3 of the present disclosure, in which the plurality of sensor circuits include a first sensor circuit and a second sensor circuit, the first sensor circuit has a first sensor body, the second sensor circuit has a second sensor body, and the characteristics of the second sensor body are different from the characteristics of the first sensor body.

[0020] By having the first sensor circuit and the second sensor circuit have different configurations, more information about the sample gas can be obtained, and therefore more feature quantities can be obtained, further improving the accuracy of identifying the sample gas.

[0021] A gas detection system according to aspect 5 of the present disclosure is a gas detection system according to aspect 3 or 4 of the present disclosure, wherein the plurality of sensor circuits include a first sensor circuit and a second sensor circuit, the first sensor circuit having a first sensor body and a first inductor, the second sensor circuit having a second sensor body and a second inductor, the characteristics of the second sensor body being different from the characteristics of the first sensor body, and the inductance of the second inductor being different from the inductance of the first inductor.

[0022] In this way, the first sensor circuit and the second sensor circuit have different configurations, so that more information about the sample gas can be obtained, and therefore, more feature quantities can be obtained, which further improves the accuracy of identifying the sample gas.

[0023] A gas detection system according to aspect 6 of the present disclosure is a gas detection system according to aspect 5 of the present disclosure, in which the frequency of the AC signal supplied to the second sensor circuit is different from the frequency of the AC signal supplied to the first sensor circuit.

[0024] In this way, by providing AC signals of different frequencies to the first sensor circuit and the second sensor circuit, more information about the sample gas can be obtained, and therefore more feature quantities can be obtained, further improving the accuracy of identifying the sample gas.

[0025] A gas detection system according to aspect 7 of the present disclosure is a gas detection system according to any one of aspects 2, 3, 5, and 6 of the present disclosure, in which the frequency of the AC signal supplied to each of the plurality of sensor circuits is 0.8 times or more and 1.2 times or less the resonant frequency of each of the plurality of sensor circuits.

[0026] In this way, by setting the frequency of the AC signal to a frequency close to the resonant frequency of the sensor circuit, it is possible to suppress noise components contained in the measurement results of the real part of the impedance.

[0027] A gas detection system according to an eighth aspect of the present disclosure is a gas detection system according to any one of the first to seventh aspects of the present disclosure, further comprising: an extraction circuit that extracts one or more feature quantities corresponding to the real impedance part and the imaginary impedance part of the complex impedance of each of the plurality of sensor circuits measured by the measurement circuit; a memory that stores a learned logical model that identifies a gas to which each of the plurality of sensor circuits is exposed; and an identification circuit that uses the learned logical model to identify a gas to which each of the plurality of sensor circuits is exposed based on the extracted one or more feature quantities.

[0028] This makes it possible to easily and accurately identify the gas.

[0029] A gas detection method according to aspect 9 of the present disclosure is a gas detection method for detecting a gas to which a plurality of sensor circuits are exposed, and includes an AC signal supply step of supplying an AC signal to each of the plurality of sensor circuits, an exposure step of exposing each of the plurality of sensor circuits to a sample gas, and a measurement step of measuring the complex impedance of each of the plurality of sensor circuits, wherein each of the plurality of sensor circuits has a sensor body whose impedance real part and impedance imaginary part change depending on the gas to which it is exposed.

[0030] This provides the same effects as the gas detection system according to aspect 1 of the present disclosure.

[0031] These comprehensive or specific aspects may be realized as a system, a method, an integrated circuit, a computer program, or a computer-readable recording medium such as a CD-ROM, or may be realized as any combination of a system, a method, an integrated circuit, a computer program, or a recording medium.

[0032] Hereinafter, the embodiments will be specifically described with reference to the drawings.

[0033] The embodiments described below are all comprehensive or specific examples. The numerical values, shapes, materials, components, component placement and connection configurations, steps, and step order shown in the following embodiments are merely examples and are not intended to limit the present disclosure. Furthermore, among the components in the following embodiments, components that are not described in the independent claims that represent the highest concepts are described as optional components.

[0034] Furthermore, in this specification, terms indicating relationships between elements such as "identical" and numerical ranges are not expressions that only express a strict meaning, but are expressions that also include a range that is substantially equivalent, for example, a difference of about a few percent.

[0035] In addition, the drawings are not necessarily strict illustrations, and the same reference numerals are used to designate substantially the same components in the drawings, and redundant explanations are omitted or simplified.

[0036] (Embodiments) A gas detection system and a gas detection method according to embodiments will be described.

[0037] [Configuration] The configuration of a gas detection system according to this embodiment will be described with reference to FIG.

[0038] FIG. 1 is a block diagram showing a schematic configuration of a gas detection system 100 according to this embodiment.

[0039] As shown in FIG. 1 , a gas detection system 100 according to this embodiment includes a plurality of sensor circuits 10, an AC signal source 30, and a measurement circuit 32. In this embodiment, the gas detection system 100 further includes an exposure unit 20, a control circuit 31, an extraction circuit 33, an identification circuit 34, and a memory 40. The gas detection system 100 identifies the sample gas based on the output of the sensor circuit 10 exposed to the sample gas. The sample gas includes, for example, a chemical substance to be identified. The sample gas may be, for example, a gas collected from food, exhaled breath collected from a human body, air surrounding a human body, or air collected from a room in a building.

[0040] The gas detection system 100 identifies, for example, chemical substances contained in the sample gas. Specifically, the gas detection system 100 identifies which of a plurality of target substances to be identified is contained in the sample gas as a chemical substance. The gas detection system 100 may also identify whether or not the target substance to be identified is contained in the sample gas.

[0041] The substance to be identified is, for example, a volatile organic compound, but may also be an inorganic gas such as ammonia or carbon monoxide. The gas detection system 100 is used, for example, to identify odors. In this case, the volatile organic compound is, for example, a molecule that becomes an odor component.

[0042] Each of the plurality of sensor circuits 10 is a sensor that outputs a signal corresponding to the gas to which it is exposed, and may be, for example, an electrochemical type, a semiconductor type, a field effect transistor type, a surface acoustic wave type, a quartz oscillator type, or a resistance change type sensor.

[0043] The sensor circuit 10 according to this embodiment will be described below with reference to Fig. 2. Fig. 2 is a circuit diagram showing an equivalent circuit of the sensor circuit 10 according to this embodiment.

[0044] 2, each of the plurality of sensor circuits 10 has a sensor main body 11. In this embodiment, each of the plurality of sensor circuits 10 further has an inductor 12 and a switch 13.

[0045] The sensor body 11 is a sensor whose real and imaginary impedance parts change depending on the gas to which it is exposed. The sensor body 11 has, for example, a sensing unit and a pair of electrodes electrically connected to the sensing unit. The impedance of the sensing unit changes depending on, for example, the adsorption concentration of the gas. A signal corresponding to the impedance of the sensing unit of the sensor body 11 is measured by the measurement circuit 32 as, for example, a voltage signal or a current signal via the pair of electrodes.

[0046] In this embodiment, a mixture of 1-butyl-3-methylimidazolium bis(trifluoromethanesulfonyl)imide, polyethylene glycol, and ethyl cellulose is used as the sensing unit. However, the configuration of the sensing unit is not limited to this. For example, a mixture of polyvinyl formal, carbon black with a particle diameter of approximately 15 nm (e.g., Mitsubishi Chemical's carbon black #2300), a functional additive (e.g., Nagase & Co., Ltd.'s Synergist El-N6S), and a wetting and dispersing agent (e.g., BYK's DISPERBYK-2200) may also be used as the sensing unit.

[0047] As shown in FIG. 2, the equivalent circuit of the sensor body 11 has terminals 10Ta and 10Tb, resistive elements 10Ra and 10Rb, and a capacitive element 10C.

[0048] The terminals 10Ta and 10Tb correspond to a pair of electrodes of the sensor body 11.

[0049] The resistor element 10Ra is connected to the terminal 10Ta and is connected in parallel to the capacitor element 10C. The resistor element 10Ra is also connected in series to the resistor element 10Rb.

[0050] The capacitance element 10C is connected to the terminal 10Ta, and is connected in parallel to the resistance element 10Ra, and is also connected in series to the resistance element 10Rb.

[0051] The resistor element 10Rb is connected to the terminal 10Tb, and is connected in series with the resistor element 10Ra and the capacitor element 10C. If the resistor element 10Rb is sufficiently smaller than the resistor element 10Ra, the resistor element 10Rb may be ignored.

[0052] In this way, the sensor body 11 has a capacitance component, and therefore has not only a real part of impedance but also an imaginary part of impedance.

[0053] In this embodiment, the sensor circuit 10 further includes an inductor 12 and a switch 13. The inductor 12 is connected in parallel to the sensor main body 11. In this embodiment, the inductor 12 has an inductance of 100 mH. The switch 13 is connected in series to the inductor 12. The switch 13 may be controlled by, for example, a control circuit 31.

[0054] The sensor main body 11 and the inductor 12 connected in parallel to the sensor main body 11 constitute a parallel resonant circuit that resonates at the frequency of the AC signal supplied by the AC signal source 30 when the switch 13 is short-circuited. In this specification, resonating at the frequency of the AC signal does not necessarily mean that the frequency of the AC signal exactly matches the resonant frequency of the parallel resonant circuit. Resonating at the frequency of the AC signal means that the difference between the frequency of the AC signal and the resonant frequency of the parallel resonant circuit is 20% or less of the resonant frequency of the parallel resonant circuit.

[0055] At least two of the plurality of sensor circuits 10 may have different configurations.

[0056] The sensing units of the multiple sensor circuits 10 may be made of, for example, different types of materials. Different types of materials exhibit different adsorption behaviors with respect to the same chemical substance. Therefore, the multiple sensor circuits 10 output different signals with respect to the same chemical substance. This allows different feature quantities to be extracted from the outputs of the multiple sensor circuits 10, thereby improving the identification accuracy of the gas detection system 100.

[0057] The plurality of sensor circuits 10 may include, for example, a first sensor circuit and a second sensor circuit, where the first sensor circuit has a first sensor body and the second sensor circuit has a second sensor body, and the characteristics of the second sensor body may be different from the characteristics of the first sensor body.

[0058] The first sensor circuit may include a first sensor body and a first inductor, and the second sensor circuit may include a second sensor body and a second inductor. The characteristics of the second sensor body may be different from the characteristics of the first sensor body, and the inductance of the second inductor may be different from the inductance of the first inductor. In this case, the frequency of the AC signal supplied to the second sensor circuit may be different from the frequency of the AC signal supplied to the first sensor circuit.

[0059] The AC signal source 30 is a signal source that supplies an AC signal to each of the plurality of sensor circuits 10. The AC signal source 30 may supply the AC signal to each of the plurality of sensor circuits 10 sequentially, or may supply the AC signal to each of the plurality of sensor circuits 10 simultaneously. In the present embodiment, the frequency of the AC signal supplied to each of the plurality of sensor circuits 10 is 0.8 to 1.2 times the resonant frequency of each of the plurality of sensor circuits 10. The frequency of the AC signal supplied to each of the plurality of sensor circuits 10 may be 0.9 to 1.1 times, or may be 0.95 to 1.05 times the resonant frequency of each of the plurality of sensor circuits 10.

[0060] The frequency of the AC signals supplied by the AC signal source 30 according to this embodiment is 1 kHz or more and 1 MHz or less. The frequency of the AC signals may be 100 Hz or more and 100 MHz or less.

[0061] The AC signal source 30 may supply AC signals having the same frequency to each of the multiple sensor circuits 10, or may supply AC signals having different frequencies to at least two of the multiple sensor circuits 10.

[0062] The exposure unit 20 is an exposure mechanism that exposes the sensor circuit 10 to a gas under the control of the control circuit 31. Specifically, the exposure unit 20 exposes the sensor circuit 10 to the sample gas only during the second period of a measurement period consisting of a first period, a second period following the first period, and a third period following the second period. The exposure unit 20 may also expose the sensor circuit 10 to a reference gas during the first and third periods. The reference gas is a gas that serves as a reference for measurement, such as a gas that does not contain the target substance. The reference gas is also a gas that is less likely to be adsorbed by the sensing unit of the sensor circuit 10 than the target substance. Specific examples of reference gases include inert gases such as air and nitrogen, and gases obtained by removing chemical substances from the sample gas using a filter or the like. By outputting a signal from the sensor circuit 10 exposed to the reference gas during the first and third periods, a reference signal corresponding to the ambient environment for each measurement can be obtained even when the ambient environment changes, and using such a signal can improve the accuracy of gas identification.

[0063] Here, a specific configuration of the exposure unit 20 will be described with reference to Fig. 3. Fig. 3 is a schematic diagram showing an example of the configuration of the exposure unit 20 according to this embodiment. Fig. 3 also shows a control circuit 31 and a sensor circuit 10. As shown in Fig. 3, the exposure unit 20 has, for example, a storage unit 21, a three-way electromagnetic valve 22, an intake pump 23, and a plurality of pipes 25a, 25b, 25c, 25d, and 25e.

[0064] One end of the pipe 25a is provided with an intake port 26a for introducing a sample gas. The intake port 26a is provided, for example, in a space filled with the sample gas. One end of the pipe 25b is provided with an intake port 26b for introducing a reference gas. The intake port 26b is provided, for example, in a space filled with the reference gas. One end of the pipe 25e is provided with an exhaust port 26e for discharging the introduced sample gas and reference gas.

[0065] The accommodation unit 21 is a box-shaped container that accommodates the sensor circuits 10. For example, a plurality of sensor circuits 10 are arranged in an array inside the accommodation unit 21. One end of each of the pipes 25c and 25d is connected to the accommodation unit 21. When the intake pump 23 (described later) is operated, gas flows from one end of the pipe 25c to one end of the pipe 25d. The plurality of sensor circuits 10 are arranged in the flow path through which the gas flows.

[0066] The sample gas introduced through intake port 26a is introduced into the storage section 21 via pipe 25a, three-way solenoid valve 22, and pipe 25c. The reference gas introduced through intake port 26b is introduced into the storage section 21 via pipe 25b, three-way solenoid valve 22, and pipe 25c. The sample gas and reference gas introduced into the storage section 21 are exhausted from exhaust port 26e via pipe 25d, intake pump 23, and pipe 25e.

[0067] The three-way solenoid valve 22 is a solenoid valve for switching the gas introduced into the storage section 21. The three-way solenoid valve 22 has an input port P1 connected to the other end of the pipe 25a, an input port P2 connected to the other end of the pipe 25b, and an output port P3 connected to the other end of the pipe 25c. The opening and closing of each port of the three-way solenoid valve 22 is controlled by the control circuit 31. The three-way solenoid valve 22 is switched, under the control of the control circuit 31, between a first state in which the input port P1 and the output port P3 are electrically connected and a second state in which the input port P2 and the output port P3 are electrically connected. In the first state, the input port P1 and the output port P3 are open, and the input port P2 is closed. In the second state, the input port P2 and the output port P3 are open, and the input port P1 is closed.

[0068] The intake pump 23 is a pump for introducing the sample gas and the reference gas into the storage section 21 and discharging the introduced sample gas and reference gas from the exhaust port 26e. The operation of the intake pump 23 is controlled by the control circuit 31. The intake port of the intake pump 23 is connected to the other end of the pipe 25d. The exhaust port of the intake pump 23 is connected to the other end of the pipe 25e.

[0069] With this configuration, when the intake pump 23 is operating and the three-way solenoid valve 22 is in the first state, the sample gas is introduced into the storage unit 21. As a result, the exposure unit 20 exposes the plurality of sensor circuits 10 to the sample gas. Also, when the intake pump 23 is operating and the three-way solenoid valve 22 is in the second state, the reference gas is introduced into the storage unit 21. As a result, the exposure unit 20 exposes the plurality of sensor circuits 10 to the reference gas.

[0070] The configuration of the exposure unit 20 is not limited to the configuration shown in FIG. 3 , and is not particularly limited as long as it can expose the sensor circuit 10 to the sample gas. The exposure unit 20 may be configured, for example, such that the sample gas and the reference gas are introduced into the storage unit 21 through separate pipes without passing through the three-way solenoid valve 22. The exposure unit 20 may also be configured without the intake pump 23, such that a carrier gas is constantly flowing into the storage unit 21 to mix the sample gas into the carrier gas. Alternatively, the reference gas may not be introduced, and the storage unit 21 may be evacuated by the intake pump 23 after the sensor circuit 10 is exposed to the sample gas. The exposure unit 20 may further include various removal filters for removing moisture or particles from the sample gas and the reference gas, electromagnetic adjustment valves for adjusting the flow rate of each pipe, check valves for preventing backflow in each pipe, and the like.

[0071] In this embodiment, the exposure unit 20 exposes the sensor circuit 10 to the reference gas in a first period and a third period, and exposes the sensor circuit 10 to the sample gas in a second period. In the gas detection system 100 according to this embodiment, the first period to the third period are repeated. That is, the period in which the sensor circuit 10 is exposed to the reference gas (the first period and the third period) and the period in which the sensor circuit 10 is exposed to the sample gas (the second period) are alternately repeated.

[0072] 1 , as described above, the control circuit 31 controls the operation of the exposure unit 20, specifically, the operation of the three-way solenoid valve 22 and the intake pump 23. The control circuit 31 may also output information indicating the timing of the operation of the exposure unit 20 to the measurement circuit 32. The control circuit 31 also controls the operation of the AC signal source 30. Specifically, the control circuit 31 controls the sensor circuit 10 to which the AC signal source 30 supplies an AC signal and the frequency of the AC signal. The control circuit 31 may also control the switch 13 of each of the multiple sensor circuits 10.

[0073] The measurement circuit 32 is a circuit that measures the complex impedance of each of the multiple sensor circuits 10 corresponding to each of the multiple AC signals. In this embodiment, the measurement circuit 32 measures the real impedance part and the imaginary impedance part of each of the multiple sensor circuits 10 based on the signals output from each of the multiple sensor circuits 10 during a measurement period. The measurement circuit 32 acquires, for example, the time waveform of the real impedance part and the time waveform of the imaginary impedance part of each of the multiple sensor circuits 10. The measurement circuit 32 acquires, for example, a voltage signal and a current signal as signals corresponding to the impedance of the sensor circuit 10. Note that the measurement circuit 32 may acquire only one of the voltage signal and the current signal as signals corresponding to the impedance of the sensor circuit 10. The measurement circuit 32 may include, for example, an LCR meter as a circuit for measuring the real impedance part and the imaginary impedance part. The measurement circuit 32 acquires information indicating the timing of controlling the exposure unit 20 from the control circuit 31. The measurement circuit 32 outputs the acquired signals and information to the extraction circuit 33.

[0074] The real and imaginary impedance parts of the complex impedance measured by the measurement circuit 32 may be the real and imaginary impedance parts of a normalized impedance. For example, the real and imaginary impedance parts may be normalized to 50 Ω.

[0075] The measurement circuit 32 may also measure the absolute value and phase of the complex impedance as the complex impedance. The measurement circuit 32 also includes a circuit for measuring a numerical value corresponding to the complex impedance. For example, the measurement circuit 32 may measure a complex admittance corresponding to the complex impedance. More specifically, the measurement circuit 32 may measure the real part and imaginary part of the complex admittance, the absolute value and phase of the complex admittance, or a normalized complex admittance.

[0076] The extraction circuit 33 extracts one or more feature quantities corresponding to the real impedance part and the imaginary impedance part of the complex impedance of each of the plurality of sensor circuits 10 measured by the measurement circuit 32. When there are a plurality of sensor circuits 10, the extraction circuit 33 extracts one or more feature quantities from the signals output by each of the plurality of sensor circuits 10. The one or more feature quantities include, for example, the difference in shape between the time waveform of the impedance real part and the time waveform of the impedance imaginary part of the sensor circuit 10.

[0077] The identification circuit 34 identifies the gas (i.e., sample gas) to which each of the multiple sensor circuits 10 is exposed based on one or more feature quantities extracted by the extraction circuit 33. In the present embodiment, the identification circuit 34 uses a trained logical model to identify the gas to which each of the multiple sensor circuits 10 is exposed based on one or more feature quantities extracted by the extraction circuit 33. The identification circuit 34, for example, identifies which of multiple identification target substances is contained in the sample gas. The identification circuit 34 may also identify whether or not the identification target substance is contained in the sample gas. The identification circuit 34 receives one or more feature quantities as input and outputs an identification result. The identification circuit 34 outputs, for example, information for displaying the identification result on a display (not shown) or the like provided in the gas detection system 100. The identification circuit 34 may output information indicating the identification result to the memory 40 and store the information in the memory 40. The identification circuit 34 may also output information indicating the identification result to an external device.

[0078] The control circuit 31, the measurement circuit 32, the extraction circuit 33, and the identification circuit 34 are realized by a microcomputer or a processor that has a built-in program for performing the above-mentioned processing. The control circuit 31, the measurement circuit 32, the extraction circuit 33, and the identification circuit 34 may each be realized by a dedicated logic circuit that performs the above-mentioned processing.

[0079] The memory 40 is a storage device that stores the trained logic model used in the classification circuit 34. The memory 40 is realized by, for example, a semiconductor memory.

[0080] The trained logical model is a logical model that identifies the gas to which each of the multiple sensor circuits 10 is exposed. Specifically, the trained logical model is, for example, a logical model that identifies which of multiple identification target substances is contained in the sample gas. The trained logical model, for example, receives as input one or more feature quantities extracted by the extraction circuit 33, and outputs which of multiple identification target substances is contained in the sample gas. The trained logical model may also output whether or not the sample gas contains the identification target substance.

[0081] The trained logical model is constructed by performing machine learning using, for example, a known substance to be identified and one or more feature quantities extracted by the extraction circuit 33 using the known substance to be identified as training data. The method used to construct the logical model in machine learning is not particularly limited. For example, a neural network is used to construct the logical model in machine learning. That is, the trained logical model includes, for example, a neural network. For constructing the logical model in machine learning, a random forest, a support vector machine, a self-organizing map, or the like may also be used.

[0082] When the trained logical model includes a neural network, for example, one or more feature quantities are input to an input node of the neural network, and the output node outputs the probability that each of a plurality of identification target substances is contained in the sample gas. That is, the number of input nodes is the number of one or more feature quantities input, and the number of output nodes is the number of a plurality of identification target substances to be identified. The trained logical model outputs the identification target substance that has the highest probability of being output from the output node among the plurality of identification target substances. Furthermore, the trained logical model may output whether or not the identification target substance is contained in the sample gas based on the probability output from the output node, for example, based on whether or not the probability is equal to or greater than a threshold value.

[0083] Note that the gas detection system 100 may be configured, for example, as a single gas identification device including the above-described components, but may also be configured as a plurality of devices. When the gas detection system 100 is configured as a plurality of devices, the components of the gas detection system 100 may be distributed in any manner among the plurality of devices. For example, the gas detection system 100 may be configured as a measurement device including the sensor circuit 10, the exposure unit 20, the AC signal source 30, the control circuit 31, and the measurement circuit 32, and an identification device including the extraction circuit 33, the identification circuit 34, and the memory 40. In this case, the measurement device and the identification device may be connected via a communication network such as the Internet.

[0084] [Gas Detection Method] Next, a gas detection method executed in gas detection system 100 according to this embodiment will be described with reference to Fig. 4. Fig. 4 is a flowchart showing the gas detection method according to this embodiment.

[0085] The gas detection method according to this embodiment is a method for detecting a gas to which a plurality of sensor circuits 10 are exposed. In the gas detection method according to this embodiment, first, a plurality of AC signals having different frequencies are supplied to each of the plurality of sensor circuits 10 using AC signal source 30 (AC signal supply step S10).

[0086] Next, while the AC signals are being supplied to each of the sensor circuits 10, the exposure unit 20 is used to expose each of the sensor circuits 10 to the sample gas (exposure step S20). In this embodiment, as described above, each of the sensor circuits 10 is alternately exposed to the sample gas and the reference gas.

[0087] Next, the measurement circuit 32 measures the complex impedance of each of the sensor circuits 10 corresponding to the plurality of AC signals while each of the sensor circuits 10 is exposed to the sample gas (measurement step S30). In this embodiment, in the measurement step S30, the measurement circuit 32 acquires the time waveform of the impedance real part and the time waveform of the impedance imaginary part of each of the sensor circuits 10.

[0088] The measuring step S30 according to this embodiment will be described with reference to Fig. 5. Fig. 5 is a flowchart showing the measuring method in the measuring step S30 according to this embodiment.

[0089] 5, first, the switch 13 of each of the plurality of sensor circuits 10 is opened (opening step S32). In this embodiment, the control circuit 31 maintains the switch 13 in an open state. In other words, the inductor 12 is not connected in parallel to the sensor main body 11 of the sensor circuit 10.

[0090] Next, the measurement circuit 32 measures the complex impedance of each of the plurality of sensor circuits 10 (first measurement step S34). Since the inductor 12 is not connected in parallel to the sensor main body 11, the real part of the impedance and the imaginary part of the impedance of the sensor main body 11 are measured here.

[0091] Next, the switch 13 of each of the plurality of sensor circuits 10 is short-circuited (short-circuit step S36). In this embodiment, the control circuit 31 maintains the switch 13 in a short-circuited state. That is, the inductor 12 is connected in parallel to the sensor body 11 of the sensor circuit 10.

[0092] Next, the measurement circuit 32 measures the complex impedance of each of the plurality of sensor circuits 10 (second measurement step S38). Because the inductor 12 is connected in parallel to the sensor main body 11, the real part and imaginary part of the impedance of the parallel resonant circuit including the sensor main body 11 and the inductor 12 are measured here.

[0093] As described above, in the measuring step S30 according to this embodiment, the impedance is measured in each of the two states.

[0094] 4, the extraction circuit 33 extracts one or more feature quantities corresponding to the real part and imaginary part of the impedance of each of the plurality of sensor circuits 10 measured by the measurement circuit 32 (extraction step S40). In this embodiment, the one or more feature quantities include a difference in shape between the time waveform of the real part of the impedance and the time waveform of the imaginary part of the impedance.

[0095] Next, the identification circuit 34 uses the learned logical model to identify the gas to which each of the plurality of sensor circuits 10 is exposed based on the one or more extracted feature quantities (identification step S50).

[0096] As described above, the gas detection method according to this embodiment detects and identifies the sample gas.

[0097] [Effects, etc.] The effects, etc. of the gas detection system 100 and the gas detection method according to this embodiment will be described.

[0098] First, the frequency characteristics of the impedance of the sensor circuit 10 according to this embodiment will be described with reference to FIGS. 6 to 11. FIGS. 6, 7, and 8 are graphs showing the frequency characteristics of the real part of the impedance, the imaginary part of the impedance, and the phase difference between the current and the voltage when the switch 13 is open in the sensor circuit 10 according to this embodiment. That is, FIGS. 6 to 8 show the frequency characteristics of the sensor main body 11. FIGS. 9, 10, and 11 are graphs showing the frequency characteristics of the real part of the impedance, the imaginary part of the impedance, and the phase difference between the current and the voltage when the switch 13 is shorted in the sensor circuit 10 according to this embodiment. That is, FIGS. 9 to 11 show the frequency characteristics of the parallel resonant circuit of the sensor main body 11 and the inductor 12.

[0099] As shown in Fig. 6, the real part of the impedance of the sensor body 11 decreases and asymptotically approaches a predetermined value as the frequency of the AC signal supplied to the sensor body 11 increases. As shown in Fig. 7, the imaginary part of the impedance of the sensor body 11 increases and asymptotically approaches a predetermined value as the frequency of the AC signal supplied to the sensor body 11 increases. As shown in Fig. 8, the phase difference between the current and voltage of the sensor body 11 decreases and asymptotically approaches a predetermined value as the frequency of the AC signal supplied to the sensor body 11 increases.

[0100] In contrast, as shown in Fig. 9, the real part of the impedance of the parallel resonant circuit formed by the sensor main body 11 and the inductor 12 is maximized at 143.9 kHz, which is the resonant frequency of the parallel resonant circuit. As shown in Fig. 10, the imaginary part of the impedance of the parallel resonant circuit formed by the sensor main body 11 and the inductor 12 is positive when the frequency of the AC signal is less than 143.9 kHz, is zero when the frequency of the AC signal is 143.9 kHz, and is negative when the frequency of the AC signal is greater than 143.9 kHz. The imaginary part of the impedance is maximized at frequencies less than 143.9 kHz and in the vicinity of 143.9 kHz, and is minimized at frequencies greater than 143.9 kHz and in the vicinity of 143.9 kHz.

[0101] In this embodiment, the frequency of the AC signal supplied to the sensor circuit 10 is 0.8 to 1.2 times the resonant frequency of 143.9 kHz.

[0102] 12 to 14, the results of measuring the impedance when an AC signal with a resonant frequency of 143.9 kHz is supplied to the sensor circuit 10. Figures 12, 13, and 14 are graphs showing the time waveforms of the real part of the impedance, the imaginary part of the impedance, and the phase difference between the current and the voltage, respectively, when the switch 13 of the sensor circuit 10 according to this embodiment is open.

[0103] In this embodiment, nitrogen (N ２ ) was used, and benzaldehyde was used as the sample gas. The sensor circuit 10 was repeatedly exposed to the reference gas and the sample gas, alternating between them, for 30 seconds each. In this case, as shown in FIGS. 12 to 14, both the real and imaginary impedance parts of the sensor circuit 10 increased upon exposure to the sample gas. In FIGS. 12 to 14 and the following graphs, the period during which the reference gas was supplied is represented by RG, and the period during which the sample gas was supplied is represented by SG.

[0104] As described above, in this embodiment, the real part and imaginary part of the impedance of the sensor circuit 10 are measured. As shown in FIGS. 12 and 13, the time waveforms of the measured real part and imaginary part of the impedance are different. In other words, by measuring the real part and imaginary part of the impedance, two different sets of information about the sample gas can be obtained. Therefore, by using this information, more feature quantities can be extracted. By identifying the sample gas using more feature quantities, it is possible to improve the accuracy of identifying the sample gas.

[0105] In this embodiment, the real and imaginary impedance parts of each of the multiple sensor circuits 10 are measured. The multiple sensor circuits 10 have different configurations. That is, the multiple sensor circuits 10 include a first sensor circuit and a second sensor circuit, where the first sensor circuit has a first sensor body and the second sensor circuit has a second sensor body, and the characteristics of the second sensor body are different from the characteristics of the first sensor body. In this case, more information about the sample gas can be obtained. Therefore, since more features can be obtained, the accuracy of identifying the sample gas can be further improved.

[0106] The plurality of sensor circuits 10 may have the same configuration. In this case, by measuring the real part of the impedance and the imaginary part of the impedance of each of the plurality of sensor circuits 10, the reliability of the measurement results can be improved.

[0107] Furthermore, for example, when measuring the impedance of the sensor circuit 10 by supplying a DC signal, the sensor circuit 10 may have a high impedance, which may result in a large amount of noise. In this embodiment, the S / N ratio can be increased by measuring the impedance of the sensor circuit 10 by supplying an AC signal. For example, the S / N ratio of the real part of the impedance shown in FIG. 12 was approximately 16.

[0108] 14, the measurement circuit 32 may measure the phase difference between the current and voltage of the sensor circuit 10. This allows even more information about the sensor circuit 10 to be obtained.

[0109] Next, measurement results when switch 13 of sensor circuit 10 according to this embodiment is short-circuited will be described with reference to Figs. 15 to 17. Figs. 15, 16, and 17 are graphs showing the time waveforms of the real part of impedance, the imaginary part of impedance, and the phase difference between current and voltage when switch 13 of sensor circuit 10 according to this embodiment is short-circuited. The frequency of the AC signal is the resonant frequency of 143.9 kHz.

[0110] As shown in Figures 15 to 17, both the real and imaginary impedance parts of the sensor circuit 10 decrease when exposed to a sample gas. In this way, measuring the real and imaginary impedance parts results in different time waveforms. In other words, different information about the sample gas can be obtained. Therefore, by using this information, it is possible to improve the accuracy of identifying the sample gas.

[0111] 15 to 17 are also different from the time waveforms shown in FIGS. 12 to 14. Therefore, by measuring the real part and imaginary part of the impedance of the sensor main body 11 in which the inductor 12 is connected in parallel, more information about the sample gas can be obtained. Therefore, by using this information, it is possible to further improve the accuracy of identifying the sample gas.

[0112] Furthermore, when comparing the time waveform of the impedance real part shown in Fig. 15 with the time waveform of the impedance real part shown in Fig. 12, it is found that the time waveform shown in Fig. 15 has a more suppressed noise component (i.e., the amplitude of minute oscillations in the time waveform). The S / N ratio of the time waveform shown in Fig. 15 is approximately 42, which is about 2.5 times better than the S / N ratio (approximately 16) of the time waveform shown in Fig. 12. Therefore, when measuring the impedance real part, switch 13 may be short-circuited. This increases the accuracy of the information on the sample gas, thereby further improving the accuracy of identifying the sample gas.

[0113] On the other hand, when the time waveform of the imaginary part of the impedance shown in Fig. 16 is compared with the time waveform of the imaginary part of the impedance shown in Fig. 13, the noise component is suppressed in the time waveform shown in Fig. 13. Therefore, when measuring the imaginary part of the impedance, switch 13 may be opened. This increases the accuracy of the information on the sample gas, thereby further increasing the accuracy of identifying the sample gas.

[0114] For example, switch 13 may be shorted when measurement circuit 32 measures the real part of the complex impedance of sensor circuit 10, and may be open when measurement circuit 32 measures the imaginary part of the complex impedance of sensor circuit 10. This makes it possible to suppress noise components contained in the measurement results of the real part and imaginary part of the impedance of sensor circuit 10. Also, for example, it is possible to measure the real part of the impedance of sensor circuit 10 using a DC signal and measure the imaginary part of the impedance using an AC signal, but in this embodiment, the configuration required for measurement can be simplified compared to such a measurement method.

[0115] 17, the measurement circuit 32 may measure the phase difference between the current and voltage of the sensor circuit 10. This makes it possible to obtain even more information about the sensor circuit 10.

[0116] Next, measurement results when the frequency of the AC signal of the sensor circuit 10 according to this embodiment is shifted from the resonant frequency will be described with reference to Figures 18 to 20. Figures 18, 19, and 20 are graphs showing the time waveforms of the real part of the impedance, the imaginary part of the impedance, and the phase difference between current and voltage, respectively, measured using an AC signal having a frequency shifted from the resonant frequency when the switch 13 of the sensor circuit 10 according to this embodiment is short-circuited. The frequency of the AC signal used in these measurements was 147.0 kHz.

[0117] As shown in Figures 18 to 20, both the real part and imaginary part of the impedance of the sensor circuit 10 decrease when exposed to a sample gas. In this way, measuring the real part and imaginary part of the impedance results in different time waveforms. In other words, different information about the sample gas can be obtained. Therefore, by using this information, it is possible to improve the accuracy of identifying the sample gas.

[0118] 20, the measurement circuit 32 may measure the phase difference between the current and voltage of the sensor circuit 10. This makes it possible to obtain even more information about the sensor circuit 10.

[0119] The frequency of the AC signal used in this measurement was 0.8 to 1.2 times the resonant frequency, and was the frequency at which the slope (i.e., the differential coefficient with respect to frequency of the impedance real part) of the frequency characteristic graph of the impedance real part of the sensor circuit 10, as shown in Figure 9, was maximum.

[0120] By using an AC signal of such a frequency, the S / N ratio of the signal obtained in the measurement circuit 32 can be improved. As a result, the proportion of noise components in the time waveform of the real part of the impedance can be further reduced, as shown in Fig. 18. This increases the accuracy of the information on the sample gas, thereby further increasing the accuracy of identifying the sample gas.

[0121] In this measurement, the frequency at which the slope is maximum in the graph of the frequency characteristics of the real part of the impedance of the sensor circuit 10 is used, but the frequency used in the measurement may be any frequency at which the absolute value of the slope is maximum. For example, the frequency used in the measurement may be a frequency at which the slope is a negative value and minimum.

[0122] Furthermore, the frequency of the AC signal supplied to the sensor circuit 10 is not limited to the frequency in the above-described measurement example. For example, the frequency of the AC signal supplied to the sensor circuit 10 may be 0.8 times or more and 1.2 times or less the resonant frequency of the sensor circuit 10.

[0123] In this way, by setting the frequency of the AC signal to a frequency close to the resonant frequency of the sensor circuit 10, it is possible to suppress noise components contained in the measurement results of the real part of the impedance.

[0124] Furthermore, although the above measurement results show the measurement results of only one sensor circuit 10, the multiple sensor circuits 10 may have different inductors. For example, the multiple sensor circuits 10 may include a first sensor circuit and a second sensor circuit, the first sensor circuit having a first sensor body and a first inductor, and the second sensor circuit having a second sensor body and a second inductor, and the characteristics of the second sensor body may be different from the characteristics of the first sensor body, and the inductance of the second inductor may be different from the inductance of the first inductor.

[0125] In this way, the first sensor circuit and the second sensor circuit have different configurations, so that more information about the sample gas can be obtained, and therefore, more feature quantities can be obtained, which further improves the accuracy of identifying the sample gas.

[0126] While the gas detection system 100 and the gas detection method according to the present disclosure have been described above based on the embodiments, the present disclosure is not limited to these embodiments. As long as they do not deviate from the gist of the present disclosure, various modifications that would occur to a person skilled in the art to the embodiments, as well as other forms constructed by combining some of the components of the embodiments, are also included in the scope of the present disclosure.

[0127] In the above embodiment, the exposure unit 20 exposes the sensor circuit 10 to the reference gas, but the configuration of the exposure unit 20 is not limited to this. The exposure unit 20 may have a period during which the sensor circuit 10 is not exposed to the sample gas. For example, the sample gas may be drawn in between two periods during which the sensor circuit 10 is exposed to the sample gas, exposing the sensor circuit 10 to a vacuum atmosphere.

[0128] In each of the above embodiments, each component may be configured with dedicated hardware, or may be realized by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU or processor reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory.

[0129] Furthermore, some or all of the functions of the gas detection system 100 according to each of the above-described embodiments may be realized by a processor such as a CPU executing a program.

[0130] Some of the components constituting the gas detection system 100 described above may be configured as an IC card or a standalone module that can be attached to or detached from each device. The IC card or the module is a computer system composed of a microprocessor, ROM, RAM, etc. The IC card or the module may include the ultra-multifunctional LSI described above. The IC card or the module achieves its functions when the microprocessor operates according to a computer program. The IC card or the module may be tamper-resistant.

[0131] The present disclosure may be the above-described methods. It may also be a computer program for implementing these methods on a computer, or a digital signal comprising the computer program. The present disclosure may also be a computer program or a digital signal recorded on a computer-readable non-transitory recording medium, such as a flexible disk, hard disk, CD-ROM, MO, DVD, DVD-ROM, DVD-RAM, BD (Blu-ray (registered trademark) Disc), semiconductor memory, or the like. It may also be a digital signal recorded on such a recording medium. The present disclosure may also be a computer program or a digital signal transmitted via a telecommunications line, a wireless or wired communication line, a network such as the Internet, data broadcasting, or the like. The present disclosure may also be a computer system including a microprocessor and a memory, in which the memory stores the computer program, and the microprocessor operates in accordance with the computer program. The present disclosure may also be implemented by another independent computer system by recording the program or the digital signal on the recording medium and transferring it, or by transferring the program or the digital signal via the network, or the like.

[0132] The gas detection system and gas detection method according to the present disclosure are useful for identifying chemical substances and the like in gas.

[0133] 10 Sensor circuit 10C Capacitive element 10Ra, 10Rb Resistive element 10Ta, 10Tb Terminal 11 Sensor body 12 Inductor 13 Switch 20 Exposed portion 21 Housing portion 22 Three-way solenoid valve 23 Intake pump 25a, 25b, 25c, 25d, 25e Piping 26a, 26b Intake port 26e Exhaust port 30 AC signal source 31 Control circuit 32 Measuring circuit 33 Extraction circuit 34 Identification circuit 40 Memory 100 Gas detection system P1, P2 Input port P3 Output port

Claims

1. A gas detection system comprising: a plurality of sensor circuits; an AC signal source that supplies an AC signal to each of the plurality of sensor circuits; and a measurement circuit that measures the complex impedance of each of the plurality of sensor circuits, wherein each of the plurality of sensor circuits has a sensor body whose real impedance part and imaginary impedance part change depending on the gas to which it is exposed.

2. The gas detection system according to claim 1, wherein each of the plurality of sensor circuits further has an inductor connected in parallel to the sensor body, and the sensor body and the inductor connected in parallel to the sensor body form a parallel resonant circuit that resonates at the frequency of the AC signal.

3. The gas detection system according to claim 2, wherein each of the plurality of sensor circuits further comprises a switch connected in series with the inductor, the switch being short-circuited when the measurement circuit measures the real impedance part of the complex impedance, and the switch being open when the measurement circuit measures the imaginary impedance part of the complex impedance.

4. A gas detection system according to any one of claims 1 to 3, wherein the plurality of sensor circuits include a first sensor circuit and a second sensor circuit, the first sensor circuit having a first sensor body, the second sensor circuit having a second sensor body, and the characteristics of the second sensor body being different from the characteristics of the first sensor body.

5. The gas detection system according to claim 2 or 3, wherein the plurality of sensor circuits include a first sensor circuit and a second sensor circuit, the first sensor circuit having a first sensor body and a first inductor, the second sensor circuit having a second sensor body and a second inductor, the characteristics of the second sensor body being different from the characteristics of the first sensor body, and the inductance of the second inductor being different from the inductance of the first inductor.

6. The gas detection system according to claim 5, wherein the frequency of the AC signal supplied to the second sensor circuit is different from the frequency of the AC signal supplied to the first sensor circuit.

7. A gas detection system according to any one of claims 1 to 3, wherein the frequency of the AC signal supplied to each of the plurality of sensor circuits is 0.8 times or more and 1.2 times or less the resonant frequency of each of the plurality of sensor circuits.

8. The gas detection system according to any one of claims 1 to 3, further comprising: an extraction circuit that extracts one or more feature quantities corresponding to the real impedance part and the imaginary impedance part of the complex impedance of each of the plurality of sensor circuits measured by the measurement circuit; a memory that stores a trained logical model that identifies the gas to which each of the plurality of sensor circuits is exposed; and an identification circuit that uses the trained logical model to identify the gas to which each of the plurality of sensor circuits is exposed based on the one or more extracted feature quantities.

9. A gas detection method for detecting a gas to which a plurality of sensor circuits are exposed, comprising: an AC signal supply step of supplying an AC signal to each of the plurality of sensor circuits; an exposure step of exposing each of the plurality of sensor circuits to a sample gas; and a measurement step of measuring the complex impedance of each of the plurality of sensor circuits, wherein each of the plurality of sensor circuits has a sensor body whose impedance real part and impedance imaginary part change depending on the gas to which it is exposed.

Images