A machine learning-assisted flexible wearable hydrogen sulfide detection device

Abstract

The present application provides a flexible wearable hydrogen sulfide detection device assisted by machine learning. It includes a flexible substrate, an indium oxide / polyaniline composite material, a conductive terminal, and a power supply and current test unit connected thereto through an electrical path. The present application utilizes the gas-induced resistance effect of the indium oxide / polyaniline composite material to produce a resistance value change that matches the concentration of hydrogen sulfide gas, and calculates the concentration of hydrogen sulfide gas according to the change in resistance through the current detection unit, thereby realizing the identification of the concentration of hydrogen sulfide. The flexible substrate of the present application can be bent arbitrarily, and the influence of its bending curvature on the resistance can be normalized by the machine learning algorithm set in the central computing unit, thereby obtaining the hydrogen sulfide concentration that matches the current bending deformation state of the flexible substrate. The hydrogen sulfide detection device of the present application has advantages of low price, simple process, reliability, high flexibility, lightness, air permeability, etc., and is more convenient for the wide application of sensors for the Internet of Things.

Description

Technical Field

[0001] The present application relates to the field of gas sensing detection technology, and in particular to a flexible wearable hydrogen sulfide detection device assisted by machine learning. Background Art

[0002] As society progresses, people have higher and higher requirements for the air quality of living and industrial production environments. Hydrogen sulfide is a common hazardous chemical gas near chemical plants. In order to prevent hydrogen sulfide gas from threatening human life and health, it is necessary to identify low-concentration hydrogen sulfide gas in the early stages of a leakage accident to prevent nearby residents from being exposed to excessive hydrogen sulfide and causing life-threatening conditions.

[0003] There are many ways to detect hydrogen sulfide, the most common ones are gas-sensitive, capacitive, photoelectric, ion migration, chromatograph and other types. The disadvantage of the capacitive detection method is that it responds slowly to hydrogen sulfide and has low sensitivity; the disadvantage of the photoelectric detection method is that the equipment is expensive and bulky, which is not conducive to widespread promotion and use; the disadvantage of the ion detection method is that an additional ion source is required to achieve detection, which leads to a large size of the detection device; the disadvantage of the chromatograph detection method is also that it is expensive and not conducive to widespread industrial use. The gas-sensitive detection method is cheap and can be produced and used in large quantities. However, the existing sensor devices need to be set on a rigid circuit board structure. When it is worn directly on the human body, the circuit board hardware devices are often subjected to stress due to the bending of the human body wearing position. The deformation due to stress will inevitably cause the resistance of the device to change, thereby causing the device concentration test to fail. Summary of the invention

[0004] In view of the deficiencies of the prior art, the present application provides a flexible wearable hydrogen sulfide detection device assisted by machine learning. The present application implements a wearable hydrogen sulfide detection device through a flexible substrate, and uses a machine learning algorithm to identify the detection values ​​corresponding to the device under different bending deformation degrees, thereby achieving early detection of hydrogen sulfide gas concentration. The present application specifically adopts the following technical solutions.

[0005] Firstly, to achieve the above-mentioned purpose, a machine learning-assisted flexible wearable hydrogen sulfide detection device is proposed, which includes: a flexible substrate; an indium oxide / polyaniline composite material, which is fixedly attached to the surface of the flexible substrate and generates a resistance change matching the concentration of hydrogen sulfide gas based on the gas-induced resistance effect; conductive terminals, which are arranged at both ends of the flexible substrate and are electrically connected to the indium oxide / polyaniline composite material to provide a conductive path for detecting the resistance of the indium oxide / polyaniline composite material; a power supply, which is connected in series in the conductive path for detecting the resistance of the indium oxide / polyaniline composite material through a wire to provide a detection power supply; a current testing unit, which is connected to the conductive path for detecting the resistance of the indium oxide / polyaniline composite material to detect the resistance of the indium oxide / polyaniline composite material; a central computing unit, which is electrically connected to the current testing unit, and normalizes the resistance detected by the current testing unit according to different bending deformation states of the flexible substrate based on a machine learning algorithm to obtain a hydrogen sulfide concentration matching the current bending deformation state of the flexible substrate.

[0006] Optionally, in the machine learning-assisted flexible wearable hydrogen sulfide detection device as described above, the flexible substrate is cloth or paper having a micro-nano three-dimensional structure.

[0007] Optionally, in a machine learning-assisted flexible wearable hydrogen sulfide detection device as described above, the indium oxide / polyaniline composite material is a mixture obtained by uniformly stirring indium oxide, polyaniline, and N,N-dimethylformamide (DMF) solution for 4-8 hours, which is patterned by dripping on the surface of a flexible substrate through a test tube or by spraying on the surface of a flexible substrate.

[0008] Optionally, in the machine learning-assisted flexible wearable hydrogen sulfide detection device as described above, the volume ratio of indium oxide, polyaniline, and N,N-dimethylformamide (DMF) in the indium oxide / polyaniline composite material is: (1~10):10:1000.

[0009] Optionally, a flexible wearable hydrogen sulfide detection device assisted by machine learning as described above, wherein the preparation step of the indium oxide / polyaniline composite material includes: taking 1-10g of indium oxide powder, 10g of polyaniline powder, and adding 1000ml of dimethylformamide (DMF) to the powder, mixing evenly in a hot bath at 50-90°C for 4-8 hours, and then dripping on the surface of the flexible substrate with the same dropper time or spraying on the surface of the flexible substrate in the same spraying manner, after the indium oxide / polyaniline composite material on the surface of the flexible substrate is dried at room temperature, conductive terminals are further provided at both ends thereof, and the wires are connected through the two conductive terminals to form a conductive path.

[0010] Optionally, a flexible wearable hydrogen sulfide detection device assisted by machine learning as described above, wherein the flexible substrate is a breathable material with a thickness of 10μm-1cm, and a 1um-200um thick indium oxide / polyaniline composite material is evenly sprayed in the detection area of ​​the flexible substrate, and the two ends of the detection area are connected to the wire terminals to form a current closed loop.

[0011] Optionally, a flexible wearable hydrogen sulfide detection device assisted by machine learning as described above, wherein the particle size range of indium oxide powder and polyaniline powder in the indium oxide / polyaniline composite material is between 200nm-20um, and they are sprayed between two conductive terminals to form a PN junction, and the cathode of the PN junction is connected to the positive electrode of the power supply through the first conductive terminal in the conductive path, and the anode of the PN junction is connected to the negative electrode of the power supply through the second conductive terminal in the conductive path.

[0012] Optionally, in a machine learning-assisted flexible wearable hydrogen sulfide detection device as described above, the test data is normalized by a central processing unit to achieve effective identification of hydrogen sulfide concentrations under different bending deformations.

[0013] Optionally, a flexible wearable hydrogen sulfide detection device assisted by machine learning as described above, wherein the central processing unit first calculates the bending shape based on the resistance baseline between the conductive terminals, and then corrects the detection parameters of the sensitive material according to the bending deformation, and identifies the concentration of hydrogen sulfide gas under different degrees of bending deformation by normalizing the test data and reducing the dimension through machine learning.

[0014] Beneficial Effects

[0015] The present application proposes a flexible wearable hydrogen sulfide device assisted by machine learning, which utilizes the gas-induced resistance effect of indium oxide / polyaniline composite materials to produce a resistance change that matches the concentration of hydrogen sulfide gas, and calculates the concentration of hydrogen sulfide gas according to the change in resistance through a current detection unit, thereby realizing the identification of the concentration of hydrogen sulfide. The flexible substrate of the present application can be bent arbitrarily, and the effect of its bending curvature on the resistance can be normalized through a machine learning algorithm set in a central computing unit, thereby obtaining a hydrogen sulfide concentration that matches the current bending deformation state of the flexible substrate. The hydrogen sulfide detection device of the present application has advantages of low price, simple process, reliability, high flexibility, lightness, breathability, and other sensing carriers, and is more convenient for the widespread application of sensors for the Internet of Things.

[0016] In order to enhance the recognition of low-concentration hydrogen sulfide gas by the device, the present application preferably sets the wearable flexible substrate material to a cloth or paper with a micro-nano structure, thereby increasing the specific surface area of ​​the device for hydrogen sulfide gas reaction through the absorption and fusion of the indium oxide / polyaniline composite material by the material. As a result, the present application can sensitively detect the resistance change of the indium oxide / polyaniline composite material resistance effect in the sensor device caused by low-concentration hydrogen sulfide, thereby improving the sensitivity of hydrogen sulfide concentration recognition.

[0017] In addition, in order to further enhance the recognition of low-concentration hydrogen sulfide by the device of the present application, the indium oxide / polyaniline composite material in the present application is preferably heated for 4 to 8 hours to uniformly stir the indium oxide, polyaniline and DMF solution, preferably in a ratio of (1 to 10): 10: 1000, which will cause the material to produce different effects on hydrogen sulfide gas, and its response resistance changes in the range of 1%-8%. Therefore, the present application utilizes the indium oxide / polyaniline composite material and integrates it into the three-dimensional micro-nano structure of the flexible substrate to provide a larger reaction area. Compared with the common hydrogen sulfide sensor with high production cost and complex system defects, the detection device of the present invention can be directly attached to the fiber surface of the wearable cloth. It is low in price, simple in process, reliable in detection, and has the advantages of high flexibility, lightness, breathability and other sensing carriers. The present application is more convenient for the widespread application of sensors for the Internet of Things.

[0018] In order to further overcome the problem of wearable flexible substrates identifying low-concentration hydrogen sulfide gas in a bending deformation state, the present invention further uses a machine learning algorithm to assist in correcting the change in detection resistance caused by deformation of the flexible wearable hydrogen sulfide sensor. The present application uses a central processing unit to normalize the raw data obtained from the detection according to the different bending degrees of the flexible substrate, thereby achieving effective identification of hydrogen sulfide concentrations under different bending deformations.

[0019] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent from the description, or may be understood by practicing the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are used to provide a further understanding of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings:

[0021] Figure 1 It is a schematic diagram of the overall structure of the flexible wearable hydrogen sulfide detection device assisted by machine learning of the present application;

[0022] Figure 2 is a schematic diagram of the preparation process of the flexible wearable hydrogen sulfide detection device of the present application;

[0023] Figure 3This is the current and hydrogen sulfide response curve of the flexible wearable hydrogen sulfide detection device under low indium oxide ratio;

[0024] Figure 4 This is the current and hydrogen sulfide response curve of the flexible wearable hydrogen sulfide detection device under high indium oxide ratio;

[0025] Figure 5 It is the current and hydrogen sulfide response curve of the flexible wearable hydrogen sulfide detection device under the ratio of 0.02: 0.04: 4ml indium oxide;

[0026] Figure 6 It is the current and hydrogen sulfide response curve of the flexible wearable hydrogen sulfide detection device under the indium oxide ratio of 0.01: 0.04: 4ml;

[0027] Figure 7 This is a schematic diagram of the steps of machine learning assistance in this application;

[0028] Figure 8 This is a schematic diagram of the results of the flexible wearable hydrogen sulfide detection device of the present application assisted by machine learning;

[0029] Fig. 9 is a schematic diagram of a PN junction structure formed in the flexible wearable hydrogen sulfide detection device of the present application;

[0030] Fig.10 It is a microscopic magnified image of the micro-nano three-dimensional structure formed by the flexible substrate of the present application.

[0031] In the figure, 1 represents a flexible substrate; 2 represents a first conductive terminal; 3 represents a wire; 4 represents a power supply; 5 represents a current testing unit; 6 represents a central computing unit; 7 represents a second conductive terminal; and 8 represents an indium oxide / polyaniline composite material. DETAILED DESCRIPTION

[0032] In order to make the purpose and technical solution of the embodiment of the present application clearer, the technical solution of the embodiment of the present application will be clearly and completely described in conjunction with the drawings of the embodiment of the present application. Obviously, the described embodiment is a part of the embodiment of the present application, not all of the embodiments. Based on the described embodiment of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0033] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as generally understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless defined as herein.

[0034] The meaning of "and / or" described in this application means that the situations where each exists alone or both exist at the same time are included.

[0035] The meaning of "inside" and "outside" in this application refers to the direction from the outer edge of the flexible substrate to the inside of the indium oxide / polyaniline composite material relative to the device itself, and the opposite direction is outside; it is not a specific limitation on the device structure of this application.

[0036] The meaning of "left and right" in this application refers to that when the user is facing the device itself, the left side of the user is left and the right side of the user is right, rather than a specific limitation on the device mechanism of this application.

[0037] The term “connection” as used in this application may mean a direct connection between components or an indirect connection between components via other components.

[0038] The meaning of "up" and "down" in this application refers to the direction from the flexible substrate to the connection position of the conductive terminal wire when the user is facing the device itself, which is up, and the opposite direction is down, rather than a specific limitation on the device mechanism of this application.

[0039] Figure 1 A machine learning-assisted flexible wearable hydrogen sulfide detection device according to the present application comprises:

[0040] Flexible substrate 1;

[0041] The indium oxide / polyaniline composite material 8 is fixedly attached to the surface of the flexible substrate 1 and generates a resistance value change matching the concentration of hydrogen sulfide gas based on the gas-induced resistance effect;

[0042] Conductive terminals are disposed at both ends of the flexible substrate 1 and are electrically connected to the indium oxide / polyaniline composite material 8 to provide a conductive path for detecting the resistance of the indium oxide / polyaniline composite material 8;

[0043] A power source 4, which is connected in series to a conductive path for detecting the resistance of the indium oxide / polyaniline composite material 8 through a conductor 3, to provide a detection power source;

[0044] A current testing unit 5 connected to a conductive path for detecting the resistance of the indium oxide / polyaniline composite material 8 to detect the resistance of the indium oxide / polyaniline composite material 8;

[0045] The central computing unit 6 is electrically connected to the current testing unit 5 , and normalizes the resistance detected by the current testing unit 5 according to different bending deformation states of the flexible substrate based on a machine learning algorithm to obtain a hydrogen sulfide concentration matching the current bending deformation state of the flexible substrate 1 .

[0046] In the specific implementation process, the above-mentioned flexible substrate 1 can be arbitrarily selected to have a similar Fig.10 The indium oxide / polyaniline composite material 8 in the device is used as a sensitive material, and its test data is calibrated by the central computing unit, so there is no need to impose special restrictions on the substrate material or bending conditions. The fiber structure of general cloth or paper itself can meet the requirements of the present application for the micro-nano three-dimensional structure of the substrate material.

[0047] Specific reference Figure 2 As shown, in the wearable hydrogen sulfide detection device of the present application, the indium oxide / polyaniline composite material 8 can be prepared by the following method: indium oxide, polyaniline, and N,N-dimethylformamide (DMF) solution are uniformly stirred for 4-8 hours to obtain a mixture, and the mixture is dripped onto the surface of the flexible substrate 1 through a test tube or sprayed on the surface of the flexible substrate 1 to achieve patterning, forming a sensitive material connected between the first conductive terminal 2 and the second conductive terminal 7.

[0048] The volume ratio of indium oxide, polyaniline, and N,N-dimethylformamide (DMF) in the indium oxide / polyaniline composite material 8 is (1-10):10:1000, preferably (1-8):8:800.

[0049] The test signal graphs of indium oxide / polyaniline composite material 8 under different ratios can be referred to Figures 3 to 8 As shown. The molecular response of the indium oxide and polyaniline powder mixture beyond the above ratio range is saturated and cannot reach a higher resistance change. In order to sensitively detect hydrogen sulfide gas, the ratio of the indium oxide / polyaniline composite material 8 in this application requires the greater the resistance change, the better. If the ratio is too low, the PN junction will not be well combined, either biased to P type or biased to N type. Only with a certain ratio can a complete PN junction mixture be formed. (1~8): The optimal ratio of 8:800 can be obtained by Figures 3 to 8The resistance pattern achieves a large resistance change. The larger the response resistance change, the easier it is to detect, so the better the detection effect. However, the molecular absorption saturation does not exceed 8%, so in this application, 1~10g of indium oxide powder and 10g of polyaniline powder are generally taken, and 1000ml of dimethylformamide (DMF) is added to the powder, and mixed evenly in a hot bath at 50-90°C for 4-8 hours, and then the same dropper time is controlled to be dripped on the surface of the flexible substrate 1 or sprayed on the surface of the flexible substrate 1 in the same spraying manner. After the indium oxide / polyaniline composite material 8 on the surface of the flexible substrate 1 is dried at room temperature, conductive terminals are further set at both ends, and the wires are connected through the two conductive terminals to form a conductive path.

[0050] Figure 3 As shown, when the ratio of Indium Oxide: Pani polyaniline: DMF (N,N-dimethylformamide) is 0.005:0.04:4ml, the gas response sensitivity is 3%, and the resistance curve changes significantly and regularly, so the detection effect is good. Figure 4 In the test, the gas response sensitivity is 1.3% under the ratio of 0.04:0.04:4ml, which can also realize the detection of hydrogen sulfide gas. Figure 5 It is shown that a gas response sensitivity of 1.5% can be achieved at a ratio of 0.02: 0.04: 4ml.

[0051] The reason why the present application uses the indium oxide / polyaniline composite material 8 as the sensitive material is that the molecular structure of indium oxide has extra free electrons, so it is an N-type material; the molecular structure of polyaniline has holes, so it is a P-type material. The two are mixed together, and the ratio of 0.004:0.04:4ml can be passed Fig. 9 A PN junction structure is formed in this way, so that the effect current on hydrogen sulfide is significantly enhanced through the exponential response curve of the PN junction structure, thereby achieving an enhancement effect.

[0052] Generally, in practice, the present application usually uses a breathable material with a thickness of 10μm-1cm as the flexible substrate 1. A 1um-200um thick indium oxide / polyaniline composite material 8 is uniformly sprayed in the detection area of ​​the flexible substrate 1. The particle size range of the indium oxide powder and the polyaniline powder in the indium oxide / polyaniline composite material 8 is between 200nm-20um. It is sprayed between two conductive terminals to form a PN junction. The negative pole of the PN junction is connected to the positive pole of the power supply 4 through the first conductive terminal 2 in the conductive path, and the positive pole of the PN junction is connected to the negative pole of the power supply 4 through the second conductive terminal 2 in the conductive path, so that the two ends of the detection area are connected to the wire terminals to form a current closed loop to obtain the resistance or current curve in response to different hydrogen sulfide gas concentrations. By normalizing the test data through the central processing unit, the effective identification of hydrogen sulfide concentrations under different bending deformations can be achieved.

[0053] During the detection process of the central processing unit, the resistance obtains the bending deformation amplitude of the material corresponding to different resistance baselines. By identifying the resistance baseline, the bending deformation amount of the head-shaped base material can be determined, and then the detection parameters of the sensitive material can be corrected according to the bending deformation amount. By normalizing the test data and reducing the dimension through machine learning, it can be obtained through Figure 7 The conventional machine learning algorithm in the recognition Figure 8 The concentration data of hydrogen sulfide gas under different bending deformation degrees are shown.

[0054] In the present application, the flexible substrate 1 is mainly used to provide a flexible carrier. The properties of the substrate do not affect the detection effect. Therefore, the flexible carrier is preferably selected as a low-cost, highly flexible, lightweight, breathable, micro-nano three-dimensional structure cloth or paper as a carrier. This type of material can greatly increase the relative specific surface area of ​​gas contact, thereby greatly increasing the sensitivity of gas detection; in addition, this type of flexible material is a breathable material, which can realize double-sided gas detection, and the thickness of this type of material can be 10μm-1cm. In the embodiment, the power supply 4 provides a power supply for testing the resistance change of the indium oxide / polyaniline composite material 8, which can be any conventional battery or an external stable power supply. The central computing unit 6 is mainly used for machine learning to calculate the normalized test data, which can be a computer, a notebook, or other central computing unit, which can realize the algorithm processing of machine learning. The wire material of the metal wire 1 can be any conductive material such as aluminum (Al), gold (Au), copper (Cu), silver (Ag), etc.

[0055] In summary, the flexible wearable hydrogen sulfide detection device based on machine learning assistance provided by the present application is composed of: a flexible substrate 1, a first conductive terminal 2, a wire 3, a power supply 4, a current test unit 5, a central computing unit 6, a second conductive terminal 7, and an indium oxide / polyaniline composite material 8. It uses the sensitive material of the indium oxide / polyaniline composite material 8 as an important unit of the device, and uses hydrogen sulfide to react with the composite material indium oxide / polyaniline when it encounters it. Based on the gas-induced resistance effect, the resistance of the sensitive material changes accordingly, thereby affecting the current in the conductive path of the detection device. The present application detects the corresponding change in the current in the conductive path of the device as the concentration of hydrogen sulfide gas changes through the current test unit, and cooperates with the machine learning algorithm to correct the measured resistance according to the bending degree of the flexible substrate to which the indium oxide / polyaniline composite material is attached, thereby accurately realizing the identification of the hydrogen sulfide concentration. Since the present application normalizes the measured value in a machine learning manner through the central computing unit, the identification of the hydrogen sulfide gas concentration of the device in a bent state is realized, so the detection device using the flexible substrate of the present application can be worn at will without affecting the measurement accuracy of hydrogen sulfide gas. The present application preferably uses a breathable substrate with a three-dimensional micro-nano structure, and increases the effective release area of ​​the indium oxide / polyaniline composite material and hydrogen sulfide gas fused therein through the porous structure of the substrate material itself, thereby further improving the detection sensitivity of the device.

[0056] The purpose of the flexible substrate 1 in the present application is to provide a flexible carrier. Usually, the flexible carrier is selected from low-cost, highly flexible, lightweight, breathable, micro-nano three-dimensional structured cloth or paper as a carrier. The micro-nano three-dimensional structure can increase the contact area with hydrogen sulfide and realize the identification of low-concentration hydrogen sulfide. The purpose of using the wire 3 is to output a current signal. The purpose of the first conductive terminal 2 and the second conductive terminal 7 is to provide a signal output port. The purpose of the power supply 4 is to provide a power supply for detecting the indium oxide / polyaniline composite material 8. The purpose of the current test unit 5 is to indirectly reflect the change in hydrogen sulfide concentration through changes in current. The purpose of the central computing unit 6 is to use machine learning to calculate the normalized test data, which can reflect the quantitative identification of the hydrogen sulfide concentration of the flexible substrate 1 in different bending deformation states. The present application can realize the identification of low-concentration hydrogen sulfide gas concentration, and effectively identify the concentration of hydrogen sulfide gas when the device is in a bent state, thereby truly realizing the effective detection of wearable hydrogen sulfide devices.

[0057] The above is only an implementation method of the present application, and its description is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present application. It should be pointed out that for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present application, which all belong to the protection scope of the present application.

Claims

1. A machine learning-assisted flexible wearable hydrogen sulfide detection device, characterized in that: include: Flexible substrate (1); An indium oxide / polyaniline composite material (8) is fixedly attached to the surface of a flexible substrate (1) and generates a resistance value change that matches the concentration of hydrogen sulfide gas based on the gas-induced resistance effect; Conductive terminals are arranged at two ends of the flexible substrate (1) and are electrically connected to the indium oxide / polyaniline composite material (8) to provide a conductive path for detecting the resistance value of the indium oxide / polyaniline composite material (8); A power source (4) is connected in series to a conductive path for detecting the resistance of the indium oxide / polyaniline composite material (8) through a conductor (3) to provide a detection power source; A current testing unit (5) connected to a conductive path for detecting the resistance of the indium oxide / polyaniline composite material (8) to detect the resistance of the indium oxide / polyaniline composite material (8); A central computing unit (6) is electrically connected to the current testing unit (5), and performs normalization processing on the resistance value detected by the current testing unit (5) according to different bending deformation states of the flexible substrate based on a machine learning algorithm, so as to obtain a hydrogen sulfide concentration matching the current bending deformation state of the flexible substrate (1); The indium oxide / polyaniline composite material (8) is a mixture obtained by uniformly stirring indium oxide, polyaniline, and N,N-dimethylformamide (DMF) solution for 4-8 hours, and is patterned by dripping on the surface of the flexible substrate (1) through a test tube or by spraying on the surface of the flexible substrate (1); The volume ratio of indium oxide, polyaniline and N,N-dimethylformamide (DMF) in the indium oxide / polyaniline composite material (8) is: (1-10):10:1000; The flexible substrate (1) is a breathable material with a thickness of 10 μm-1 cm. A 1 μm-200 μm thick indium oxide / polyaniline composite material (8) is evenly sprayed in the detection area of ​​the flexible substrate (1), and the two ends of the detection area are connected to the wire terminals to form a current closed loop; The particle size of the indium oxide powder and the polyaniline powder in the indium oxide / polyaniline composite material (8) is between 200 nm and 20 um. The indium oxide powder and the polyaniline powder are sprayed between two conductive terminals to form a PN junction. The negative electrode of the PN junction is connected to the positive electrode of the power source (4) through the first conductive terminal (2) in the conductive path, and the positive electrode of the PN junction is connected to the negative electrode of the power source (4) through the second conductive terminal (7) in the conductive path.

2. The machine learning-assisted flexible wearable hydrogen sulfide detection device according to claim 1, characterized in that: The flexible substrate (1) is cloth or paper having a micro-nano three-dimensional structure.

3. The machine learning-assisted flexible wearable hydrogen sulfide detection device according to claim 1, characterized in that: The preparation steps of the indium oxide / polyaniline composite material (8) include: Take 1-10g of indium oxide powder and 10g of polyaniline powder, add 1000ml of dimethylformamide (DMF) to the powder, heat-bathe at 50-90°C for 4-8 hours to mix evenly, then drip on the surface of the flexible substrate (1) with a dropper for the same time or spray on the surface of the flexible substrate (1) in the same spraying manner. After the indium oxide / polyaniline composite material (8) on the surface of the flexible substrate (1) is dried at room temperature, conductive terminals are further provided at both ends thereof, and conductive wires are connected through the two conductive terminals to form a conductive path.

4. The machine learning-assisted flexible wearable hydrogen sulfide detection device according to any one of claims 1 to 3, characterized in that: The test data is normalized by the central processing unit, thereby achieving effective identification of hydrogen sulfide concentrations under different bending deformations.

5. The machine learning-assisted flexible wearable hydrogen sulfide detection device according to claim 4, characterized in that: The central processing unit first calculates the bending shape based on the resistance baseline between the conductive terminals, and then corrects the detection parameters of the sensitive material based on the bending deformation. By normalizing the test data and reducing the dimension through machine learning, the concentration of hydrogen sulfide gas under different degrees of bending deformation is identified.

Images