Emulsion flexible pressure sensor for high-altitude low-pressure mine

Abstract

The invention relates to the technical field of sensors, in particular to an emulsion flexible pressure sensor for a high-altitude low-pressure mine, which is composed of an aerogel heat insulation layer, a microstructure electrode layer, a rigidity adjusting layer and a wire, the sensor sequentially comprises an aerogel heat insulation layer, a microstructure electrode layer and a rigidity adjusting dielectric layer from outside to inside along a center shaft, a wire is led out of the microstructure electrode layer, all the parts are symmetrically distributed along the center shaft from the side section, and the whole sensor is in a cylindrical shape. And a lead led out from the microstructure electrode layer is used as an output pin of a measurement signal. The sensor has two working modes of capacitance sensing and resistance sensing. According to the sensor, the function of measuring the liquid pressure is achieved, and the purpose of preparing the mine liquid pressure sensor with more excellent performance is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of sensors, and specifically to an emulsion flexible pressure sensor for high-altitude and low-pressure mines. Background Technique

[0002] With the continuous progress of mine mining technology, among the equipment underground in mines, hydraulic detection devices play a key role. The sensors in traditional hydraulic detection devices are usually made of metal materials. However, due to environmental problems underground in mines, metal sensors are prone to be affected by temperature changes when working underground. Moreover, over time, metal fatigue will cause the performance of the sensors to decline and they are vulnerable to liquid erosion.

[0003] In contrast, flexible liquid pressure sensors have superior heat insulation performance and mechanical properties, and can effectively overcome these deficiencies of traditional metal sensors, thereby improving the stability and reliability of the sensors in harsh environments. Summary of the Invention

[0004] The purpose of this part is to outline some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this part, as well as in the abstract and title of the specification of this application, to avoid obscuring the purpose of this part, the abstract, and the title of the invention. However, such simplifications or omissions shall not be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed.

[0006] To solve the above technical problems, the present invention provides the following technical solution: An emulsion flexible pressure sensor for high-altitude and low-pressure mines, comprising:

[0007] The sensor is composed of an aerogel heat insulation layer, a microstructured electrode layer, a stiffness adjustment layer, and a wire; the sensor is overall cylindrical, and the structure of the sensor from the outside to the inside along the central axis is successively an aerogel heat insulation layer, a microstructured electrode layer, and a stiffness adjustment dielectric layer, wherein the microstructured electrode layer leads out a wire; each part in the sensor is symmetrically distributed along the central axis, and the wire led out by the microstructured electrode layer is used as the output pin for measuring signals; the sensor has two working modes: capacitance sensing and resistance sensing. According to the set pressure threshold, when the pressure received is less than the pressure threshold, the sensor works in the capacitance mode, and when the pressure received is greater than the pressure threshold, the sensor works in the resistance mode.

[0008] Preferably, the aerogel heat insulation layer is located on the outermost layer of the sensor, covering the whole sensor; the material of the aerogel heat insulation layer is aerogel doped with carbon nanotubes.

[0009] Preferably, the microstructured electrode layer and the stiffness adjustment layer are in a sandwich structure. In this sandwich structure, the microstructured electrode layers are on both sides, and the stiffness adjustment layer is in the middle.

[0010] Preferably, the microstructured electrode layer is a multi-layer pyramid structure. The pyramid part is a 3×3 pyramid matrix and is porous, and the base part is a non-porous solid in a compact disc shape.

[0011] Preferably, the materials used for the microstructured electrode layer are polyurethane (PU), N,N-dimethylformamide (DMF), citric acid, ethanol, and carbon black (CB);

[0012] The manufacturing method of the microstructured electrode layer includes: using a mold with a multi-layer pyramid structure, which has two parts: the pyramid and the base; injecting the mixture of PU, DMF, citric acid, ethanol, and CB into the pyramid part of the mold, and injecting the mixture of PU, DMF, and CB into the base part of the mold. The mass of CB in both the pyramid and the base is 5% of the mass of PU. Mix and heat to dissolve, so that the citric acid in PDMS first crystallizes and then dissolves in the pyramid part of the mold, forming a pyramid structure with tiny holes, and at the same time curing the base part, finally making a conductive microstructured electrode layer.

[0013] Preferably, the microstructured electrode layer leads out a wire. The wire material is copper, with a diameter of 0.5 mm, and the wire passes through the aerogel thermal insulation layer to connect to external equipment.

[0014] Preferably, the stiffness adjustment layer is cylindrical and uses Ecoflex as the material.

[0015] A method for processing pressure data of an emulsion flexible pressure sensor for high-altitude and low-pressure mines, including: the sensor collects pressure value electrical signals to obtain electrical signal data of either capacitance value or resistance value;

[0016] Process the collected electrical signal data, including processing steps of amplifying, filtering, and A / D converting the data;

[0017] Input the processed electrical signal data into a pressure calculation model, and convert the change electrical signal data of either capacitance value or resistance value into the corresponding pressure value through the pressure calculation model;

[0018] Perform filtering processing on the calculated pressure value to eliminate noise interference in the data and obtain the pressure measurement result.

[0019] Preferably, the pressure calculation model is constructed using a BP neural network, and the specific steps are as follows:

[0020] Collect the changing electrical signal data of either the capacitance value or the resistance value of the sensor under different pressure conditions and the corresponding standard pressure values, and establish a training data set and a test data set;

[0021] Determine the structure of the BP neural network, including the number of neurons in the input layer, the number of hidden layers and neurons, the number of neurons in the output layer, and the parameters of the activation function;

[0022] Use the training data set to train the BP neural network, and adjust the network weights w and thresholds b so that the network output The mean square error E between and the standard pressure value y meets the requirements. The calculation formula for the mean square error is:

[0023]

[0024] where n is the number of training samples, y i is the standard pressure value of the i-th sample, is the predicted output value of the BP neural network for the i-th sample;

[0025] Use the test data set to test the trained BP neural network, evaluate the accuracy and generalization ability of the model, and adjust the network parameters;

[0026] Use the trained pressure calculation model to calculate the pressure value for the changing electrical signal data x of either the capacitance value or the resistance value. The calculation formula is:

[0027]

[0028] where f(·) is the activation function, m is the dimension of the input features, w j is the weight corresponding to the j-th input feature, and b is the bias term.

[0029] Preferably, perform filtering processing on the calculated pressure value to eliminate noise interference in the data and obtain the pressure measurement result. The specific steps are as follows:

[0030] Step a: Perform wavelet decomposition on the calculated pressure value sequence x(n), select the db4 wavelet as the wavelet basis function ψ(t), and perform 4-layer wavelet decomposition on the pressure value sequence;

[0031] Use the Mallat algorithm to perform wavelet decomposition to obtain 1 4-layer low-frequency approximation coefficient a4(n) and 4 4-layer high-frequency detail coefficients d1(n), d2(n), d3(n), d4(n);

[0032] Step b: Perform threshold processing on the wavelet decomposition coefficients, and use the soft threshold function η λ ​(x) Threshold processing is performed on the four-layer high-frequency detail coefficients respectively, and the soft threshold function is defined as:

[0033]

[0034] Among them, λ is the threshold value, which is adaptively calculated according to the standard deviation σ of the detail coefficients of each layer and the decomposition level j, and the calculation formula is:

[0035]

[0036] Among them, N j is the length of the detail coefficients of the j-th layer; the detail coefficients less than the threshold are set to zero to remove the high-frequency noise components;

[0037] Step c: Use the wavelet coefficients after threshold processing for wavelet reconstruction. Starting from the fourth layer, the processed wavelet coefficients are used for wavelet reconstruction layer by layer until the denoised pressure value sequence is obtained The reconstruction formula is:

[0038]

[0039] Among them, φ 4,k (n) is the scaling function corresponding to the fourth-layer low-frequency approximation coefficient, and ψ j,k (n) is the wavelet function corresponding to the high-frequency detail coefficients of the j-th layer, is the k-th detail coefficient of the j-th layer after threshold processing;

[0040] Step d: Post-process the reconstructed pressure value sequence, and use the N-point moving average algorithm to smooth the denoised pressure value sequence;

[0041] Step e: Evaluate the filtering effect, optimize the filtering parameters, calculate the signal-to-noise ratio SNR and mean square error MSE of the pressure value sequence before and after filtering, evaluate the effect of wavelet threshold denoising, and the calculation formulas for the signal-to-noise ratio and mean square error are respectively:

[0042]

[0043] According to the evaluation results, adjust the parameters of the wavelet basis function, decomposition level, threshold function and threshold value, and repeat steps a to d until a filtering effect meeting the standard is obtained, and output the final pressure measurement result.

[0044] The beneficial effects of the present invention: The aerogel thermal insulation layer in the present invention is an aerogel doped with carbon nanotubes (CNTs); for the aerogel thermal insulation layer, the addition of CNTs not only changes the structure of the aerogel but also makes the aerogel have high water drainage, so that its water absorption is less than 10%, and at the same time, it also improves the mechanical properties of the aerogel, enabling it to better withstand liquid pressure.

[0045] The microstructured electrode layer of the present invention is a multi-layer pyramid structure, and the pyramid part as a whole presents a porous structure. For the microstructured electrode layer, the introduction of the pyramid microstructure and the porous structure effectively increases the change in the relative permittivity of the sensor, and at the same time increases the change in the resistance when the two electrodes are in contact, thereby improving the performance of the sensor.

[0046] The stiffness adjustment layer of the present invention uses Ecoflex as the material and plays a role in adjusting the stiffness of the sensor. Combining the above points greatly improves the electrical and mechanical properties of the sensor, namely the capacitance value and the change in capacitance when stressed, and greatly optimizes the performance of the sensor.

[0047] The wavelet transform of the present invention can effectively separate the noise and trend components in the pressure signal and adaptively achieve the separation of the signal and noise; the adaptive soft threshold processing can effectively remove the high-frequency noise while retaining the important detailed features of the pressure signal and avoiding signal distortion.

[0048] The wavelet reconstruction process in the present invention can accurately restore the original form of the pressure signal, ensuring the reversibility and data integrity of the filtering process; by evaluating the filtering effect and optimizing the key parameters, the optimal performance and self-adaptability of the wavelet threshold denoising method are guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. Among them:

[0050] Figure 1 is a side sectional view of the pressure sensor provided by the present invention.

[0051] Figure 2 is a cross-sectional view of the pressure sensor provided by the present invention.

[0052] Figure 3 is a flowchart of the data processing method of an emulsion flexible pressure sensor for high-altitude and low-pressure mines provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] In order to make the above objects, features, and advantages of the present invention more understandable, the following will give a detailed description of the specific embodiments of the present invention with reference to the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0054] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, the present invention may be practiced in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0055] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that exclude each other with other embodiments.

[0056] The present invention will be described in detail in conjunction with the schematic diagrams. When detailing the embodiments of the present invention, for the convenience of explanation, the cross-sectional views showing the device structure will be enlarged locally in a non-general proportion, and the schematic diagrams are only examples and should not limit the scope of protection of the present invention herein. In addition, in actual production, three-dimensional spatial dimensions including length, width, and depth should be included.

[0057] Meanwhile, in the description of the present invention, it should be noted that the orientation or positional relationship indicated by terms such as "upper, lower, inner, and outer" is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be construed as a limitation to the present invention. In addition, the terms "first, second, or third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0058] Unless otherwise clearly defined and limited in the present invention, the terms "mounted, connected, and coupled" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can also be a mechanical connection, an electrical connection, or a direct connection, and can also be indirectly connected through an intermediate medium, or can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0059] Embodiment 1

[0060] As Figure 1 and Figure 2 shown, an emulsion flexible pressure sensor for high-altitude and low-pressure mines is composed of an aerogel thermal insulation layer (1), a microstructural electrode layer (2), a stiffness adjustment layer (3), and a wire (4).

[0061] The overall shape of the sensor is cylindrical. When viewed from the side cross-section, the structure of the sensor from the outside to the inside along the central axis is successively an aerogel thermal insulation layer (1), a micro-structured electrode layer (2), and a stiffness adjustment layer (3); when viewed from the cross-section, the stiffness adjustment layer (3), the micro-structured electrode layer (2), and the aerogel thermal insulation layer (1) are coaxially distributed. The aerogel thermal insulation layer (1) wraps the stiffness adjustment layer (3) and the micro-structured electrode layer (2) on the outside, and a wire (4) is led out from the micro-structured electrode layer (3) therein.

[0062] When the sensor is working, it should be used to replace the sensor in the hydraulic detection device, that is, the sensor itself does not directly contact the liquid.

[0063] When the external liquid pressure changes, mechanical deformation occurs through the hydraulic detection device, causing the stiffness adjustment layer (3) and the micro-structured electrode layer (2) to be compressed and thinned. The distance between the two micro-structured electrode layers (2) decreases, and ultimately the capacitance of the sensor changes; when the liquid pressure further increases, the distance between the two micro-structured electrode layers (2) continues to decrease until they come into contact. At this time, the liquid pressure reaches the threshold, and the sensor changes to the resistance working mode, and the resistance value further changes as the pressure increases. The change amounts of capacitance and resistance are transmitted to the external device as parameters through the wire (4), and the liquid pressure is measured after being processed.

[0064] The sensor realizes the function of measuring the liquid pressure and achieves the purpose of preparing a mine liquid pressure sensor with better performance.

[0065] Embodiment 2

[0066] As Figure 3 shown, it is a data processing method flow of an emulsion flexible pressure sensor for high-altitude and low-pressure mines.

[0067] The sensor collects the pressure value electrical signal and obtains the electrical signal data of any one of the capacitance value and the resistance value.

[0068] The collected electrical signal data is processed, including the processing steps of amplifying, filtering, and A / D converting the data.

[0069] The processed electrical signal data is input into the pressure calculation model, and the change electrical signal data of any one of the capacitance value and the resistance value is converted into the corresponding pressure value through the pressure calculation model.

[0070] The pressure calculation model is constructed by using a BP neural network, and the specific steps are as follows:

[0071] Collect the change electrical signal data of any one of the capacitance value and the resistance value of the sensor under different pressure conditions and the corresponding standard pressure values, and establish a training data set and a test data set.

[0072] Determine the structure of the BP neural network, including the number of neurons in the input layer, the number of hidden layers and neurons, the number of neurons in the output layer, and the parameters of the activation function.

[0073] Use the training dataset to train the BP neural network, and adjust the network weights w and thresholds b to make the network output The mean square error E between and the standard pressure value y meets the requirements. The calculation formula for the mean square error is:

[0074]

[0075] where n is the number of training samples, y i is the standard pressure value of the i-th sample, is the predicted output value of the BP neural network for the i-th sample.

[0076] Use the test dataset to test the trained BP neural network, evaluate the accuracy and generalization ability of the model, and adjust the network parameters.

[0077] Adopt the trained pressure calculation model to calculate the pressure value for the change electrical signal data x of either the capacitance value or the resistance value. The calculation formula is:

[0078]

[0079] where f(·) is the activation function, m is the dimension of the input features, w j is the weight corresponding to the j-th input feature, and b is the bias term.

[0080] Perform filtering on the calculated pressure value to eliminate the noise interference in the data and obtain the pressure measurement result. The specific steps are as follows:

[0081] Perform filtering on the calculated pressure value to eliminate the noise interference in the data and obtain the pressure measurement result. The specific steps are as follows:

[0082] Step a: Perform wavelet decomposition on the calculated pressure value sequence x(n), select the db4 wavelet as the wavelet basis function ψ(t), and perform 4-layer wavelet decomposition on the pressure value sequence.

[0083] Use the Mallat algorithm to perform wavelet decomposition to obtain 1 4-layer low-frequency approximation coefficient a4(n) and 4 4-layer high-frequency detail coefficients d1(n), d2(n), d3(n), d4(n).

[0084] Step b: Perform threshold processing on the wavelet decomposition coefficients, and use the soft threshold function η λ (x) to perform threshold processing on the 4-layer high-frequency detail coefficients respectively. The soft threshold function is defined as:

[0085]

[0086] Among them, λ is the threshold value, which is adaptively calculated according to the standard deviation σ of the detail coefficients of each layer and the decomposition level j. The calculation formula is:

[0087]

[0088] Among them, N j is the length of the detail coefficients of the j-th layer; the detail coefficients smaller than the threshold are set to zero to remove the high-frequency noise components.

[0089] Step c: Perform wavelet reconstruction using the wavelet coefficients after threshold processing. Starting from the 4th layer, use the processed wavelet coefficients layer by layer for wavelet reconstruction until the denoised pressure value sequence is obtained. The reconstruction formula is:

[0090]

[0091] Among them, φ 4,k (n) is the scaling function corresponding to the low-frequency approximation coefficients of the 4th layer, and ψ j,k (n) is the wavelet function corresponding to the high-frequency detail coefficients of the j-th layer, is the k-th detail coefficient of the j-th layer after threshold processing.

[0092] Step d: Post-process the reconstructed pressure value sequence, and use the N-point moving average algorithm to smooth the denoised pressure value sequence.

[0093] Step e: Evaluate the filtering effect, optimize the filtering parameters, calculate the signal-to-noise ratio SNR and mean square error MSE of the pressure value sequences before and after filtering, evaluate the effect of wavelet threshold denoising. The calculation formulas for the signal-to-noise ratio and mean square error are respectively:

[0094]

[0095] According to the evaluation results, adjust the parameters of the wavelet basis function, decomposition level, threshold function, and threshold value, and repeat steps a to d until a filtering effect that meets the standard is obtained, and output the final pressure measurement result.

[0096] Embodiment 3

[0097] The third embodiment of the present invention is different from the previous embodiment in that:

[0098] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs, Read-Only Memories), random access memories (RAMs, Random Access Memories), magnetic disks, or optical discs that can store program codes.

[0099] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in combination with an instruction execution system, apparatus, or device.

[0100] More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection parts with one or more wirings (electronic devices), portable computer disk cartridges (magnetic devices), random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), fiber optic devices, and portable compact disc read-only memories (CDROMs). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or otherwise processing it as appropriate, and then storing it in a computer memory.

[0101] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0102] In addition, to provide a concise description of exemplary embodiments, all features of the actual embodiments may not be described (i.e., those features that are not relevant to the currently contemplated best mode of carrying out the present invention, or those features that are not relevant to the implementation of the present invention).

[0103] It should be understood that in the development of any actual implementation, as in any engineering or design project, numerous specific implementation decisions may be made. Such development efforts may be complex and time-consuming, but for those of ordinary skill in the art who benefit from this disclosure, without undue experimentation, such development efforts will be a routine task of design, fabrication, and production.

[0104] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. An emulsion flexible pressure sensor for high altitude low pressure mines, characterized in that: include: The sensor is composed of an aerogel insulation layer, a microstructure electrode layer, a stiffness adjustment layer and a conductor; The sensor is cylindrical in shape as a whole, and the structure of the sensor from outside to inside along the central axis is an aerogel insulation layer, a microstructure electrode layer and a stiffness adjustment dielectric layer, wherein the microstructure electrode layer leads out a wire; The various parts of the sensor are symmetrically distributed along the central axis, and the wires led out through the microstructure electrode layer are used as output pins of the measurement signal; The sensor has two working modes: capacitive sensing and resistive sensing. According to the set pressure threshold, when the pressure is less than the pressure threshold, the sensor works in the capacitive mode, and when the pressure is greater than the pressure threshold, the sensor works in the resistive mode.

2. The emulsion flexible pressure sensor for high altitude and low pressure mines according to claim 1, characterized in that: The aerogel heat insulation layer is located at the outermost layer of the sensor and covers the entire sensor; the material of the aerogel heat insulation layer is aerogel doped with carbon nanotubes.

3. The emulsion flexible pressure sensor for high altitude and low pressure mines according to claim 2, characterized in that: The microstructure electrode layer and the stiffness adjustment layer form a sandwich structure. In the sandwich structure, the microstructure electrode layers are located on both sides and the stiffness adjustment layer is located in the middle.

4. The emulsion flexible pressure sensor for high altitude and low pressure mines according to claim 3, characterized in that: The microstructure electrode layer is a multi-layer pyramid structure, the pyramid part is a 3×3 pyramid matrix and is porous, and the base part is a non-porous compact disc-shaped solid.

5. The emulsion flexible pressure sensor for high altitude and low pressure mines according to claim 4, characterized in that: The materials used in the microstructure electrode layer are polyurethane (PU), N,N-dimethylformamide (DMF), citric acid, ethanol and carbon black (CB); The method for making the microstructure electrode layer includes: using a multi-layer pyramid structure mold, wherein the multi-layer pyramid structure mold has two parts, a pyramid and a base; injecting a mixture of PU, DMF, citric acid, ethanol and CB into the pyramid part of the mold, injecting PU mixed with DMF and CB into the base part of the mold, wherein the mass of the CB mixed in the pyramid and the base is 5% of the mass of PU, mixing, heating and then dissolving, so that the citric acid in the PDMS first crystallizes and then dissolves in the pyramid part of the mold to form a pyramid structure with tiny holes, and simultaneously solidifies the base part to finally make a conductive microstructure electrode layer.

6. The emulsion flexible pressure sensor for high altitude and low pressure mines according to claim 5, characterized in that: The microstructure electrode layer leads out a wire made of copper with a diameter of 0.5 mm. The wire passes through the aerogel insulation layer to connect to external equipment.

7. The emulsion flexible pressure sensor for high altitude low pressure mines according to claim 6, characterized in that: The stiffness adjustment layer is cylindrical and is made of Ecoflex.

8. A pressure data processing method for an emulsion flexible pressure sensor for a high-altitude low-pressure mine, used to implement an emulsion flexible pressure sensor for a high-altitude low-pressure mine as claimed in any one of claims 1 to 7, characterized in that: include: The sensor collects pressure value electrical signals to obtain electrical signal data of any one of capacitance value and resistance value; Processing the collected electrical signal data, including the steps of amplifying, filtering, and A / D conversion of the data; The processed electrical signal data is input into the pressure calculation model, and the change electrical signal data of any one of the capacitance value and the resistance value is converted into the corresponding pressure value through the pressure calculation model; The calculated pressure value is filtered to eliminate noise interference in the data and obtain the pressure measurement result.

9. The pressure data processing method of the emulsion flexible pressure sensor used in high-altitude low-pressure mines according to claim 8 is characterized in that: The pressure calculation model is constructed using a BP neural network, and the specific steps are as follows: Collect the changing electrical signal data of any one of the capacitance and resistance values ​​of the sensor under different pressure conditions and the corresponding standard pressure values, and establish training data sets and test data sets; Determine the structure of the BP neural network, including the number of neurons in the input layer, the number of layers and neurons in the hidden layer, the number of neurons in the output layer, and the parameters of the activation function; Use the training data set to train the BP neural network, adjust the network weight w and threshold b so that the network output The mean square error E between the pressure value and the standard pressure value y meets the requirements, and the mean square error calculation formula is: Where n is the number of training samples, y i is the standard pressure value of the i-th sample, is the predicted output value of the BP neural network for the i-th sample; Use the test data set to test the trained BP neural network, evaluate the accuracy and generalization ability of the model, and adjust the network parameters; The trained pressure calculation model is used to calculate the pressure value of the change electrical signal data x of any one of the capacitance value and the resistance value. The calculation formula is: Among them, f(·) is the activation function, m is the dimension of the input feature, and w j is the weight corresponding to the jth input feature, and b is the bias term.

10. The pressure data processing method of the emulsion flexible pressure sensor used in high-altitude low-pressure mines according to claim 9 is characterized in that: The calculated pressure value is filtered to eliminate the noise interference in the data and obtain the pressure measurement result. The specific steps are as follows: Step a: Perform wavelet decomposition on the calculated pressure value sequence x(n), select db4 wavelet as the wavelet basis function ψ(t), and perform 4-layer wavelet decomposition on the pressure value sequence; Use Mallat algorithm to perform wavelet decomposition to obtain a 4-layer low-frequency approximation coefficient a4(n) and 4 4-layer high-frequency detail coefficients d1(n), d2(n), d3(n), d4(n); Step b: Threshold processing is performed on the wavelet decomposition coefficients using the soft threshold function η λ (x) Threshold processing is performed on the high-frequency detail coefficients of the four layers respectively, and the soft threshold function is defined as: Among them, λ is the threshold value, which is adaptively calculated according to the standard deviation σ of the detail coefficient of each layer and the number of decomposition layers j. The calculation formula is: Among them, N j is the length of the detail coefficient of the jth layer; the detail coefficients less than the threshold are set to zero to remove the high-frequency noise component; Step c: Use the wavelet coefficients after threshold processing to perform wavelet reconstruction. Starting from the 4th layer, use the processed wavelet coefficients layer by layer to perform wavelet reconstruction until the denoised pressure value sequence is obtained. The reconstruction formula is: Among them, φ 4,k (n) is the scaling function corresponding to the low-frequency approximation coefficient of the fourth layer, ψ j,k (n) is the wavelet function corresponding to the high-frequency detail coefficient of the jth layer, is the kth detail coefficient of the jth layer after threshold processing; Step d: post-processing the reconstructed pressure value sequence, and smoothing the denoised pressure value sequence using an N-point moving average algorithm; Step e: Evaluate the filtering effect, optimize the filtering parameters, calculate the signal-to-noise ratio (SNR) and mean square error (MSE) of the pressure value sequence before and after filtering, and evaluate the effect of wavelet threshold denoising. The calculation formulas for signal-to-noise ratio and mean square error are: According to the evaluation results, adjust the parameters of the wavelet basis function, the number of decomposition layers, the threshold function and the threshold size, and repeat steps a to d until a filtering effect that meets the standards is obtained and the final pressure measurement result is output.

Images