Anti-seismic hysteresis pressure transmitter based on intelligent control

Abstract

The present invention discloses a seismic hysteresis pressure transmitter based on intelligent control, which relates to the technical field of pressure transmitters, and comprises a display module, on which a display screen and an external port are provided, a control module is fixedly connected to the bottom of the display module, and a collection module is connected to the bottom of the control module; the control module collects a historical training data set in advance, and trains a machine learning model for predicting the friction resistance applied by the control module to the collection module based on the historical training data set; the collection module collects pressure data, temperature data and friction coefficient in real time, and uses the machine learning model to predict the friction resistance applied by the control module to the collection module based on the pressure data, temperature data and friction coefficient; the displacement of the piston rod sliding in the friction block is changed by the friction resistance, so as to offset the influence of the ambient temperature of the seismic hysteresis pressure transmitter, and ensure the accuracy of the pressure data collected by the metal film piezoresistive sheet.

Description

Technical Field

[0001] The invention relates to the technical field of pressure transmitters, and in particular to a seismic hysteresis pressure transmitter based on intelligent control. Background Art

[0002] Pressure transmitter is a device that converts pressure into pneumatic or electric signals for control and remote transmission. It can convert physical pressure parameters such as gas and liquid sensed by the pressure measuring element sensor into standard electrical signals to supply secondary instruments such as indicator alarms, recorders, regulators, etc. for measurement, indication and process regulation.

[0003] Existing seismic hysteresis pressure transmitters, such as a seismic intelligent pressure transmitter with adjustable hysteresis disclosed in Chinese patent publication number CN116147830A, cannot be adaptively adjusted based on temperature changes during use, resulting in low accuracy of pressure data output by the seismic hysteresis pressure transmitter. Summary of the invention

[0004] In order to overcome the above-mentioned technical problems, the present invention provides a seismic hysteresis pressure transmitter based on intelligent control to solve the problem in the prior art that the seismic hysteresis pressure transmitter cannot be adaptively adjusted based on temperature changes during use, resulting in the pressure data output by the pressure transmitter being inaccurate.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] Specifically, a seismic hysteresis pressure transmitter based on intelligent control is provided, including a display module, which is provided with a display screen and an external port, a control module is fixedly connected to the bottom of the display module, and an acquisition module is connected to the bottom of the control module; the control module collects a historical training data set in advance, and trains a machine learning model for predicting the friction resistance applied by the control module to the acquisition module based on the historical training data set; the acquisition module collects pressure data, temperature data and friction coefficient in real time, and uses a machine learning model based on the pressure data, temperature data and friction coefficient to predict the friction resistance applied by the control module to the acquisition module, and calibrates the pressure data output by the acquisition module based on the friction resistance.

[0007] As a further solution of the present invention: a driving mechanism is provided inside the control module, and a friction block is provided inside the driving mechanism.

[0008] As a further solution of the present invention: a metal film piezoresistive sheet is provided at the bottom end of the acquisition module.

[0009] As a further solution of the present invention: a cylinder sleeve is provided inside the acquisition module, and a piston rod is inserted into the top of the cylinder sleeve.

[0010] As a further solution of the present invention: the historical training data set includes N groups of training data, N is a positive integer, each group of training data includes feature data and label data, wherein the feature data includes pressure data, temperature data and friction coefficient;

[0011] The pressure data is the pressure value collected by the metal film piezoresistive sheet when collecting each set of training data;

[0012] The temperature data is the ambient temperature value of the metal film piezoresistive sheet when collecting each set of training data;

[0013] The friction coefficient is the friction coefficient between the friction block and the piston rod when collecting each set of training data;

[0014] The label data is the friction resistance when the piston rod moves on the surface of the friction block when each set of training data is collected.

[0015] As a further solution of the present invention, the control module trains a machine learning model for predicting the friction resistance applied by the control module to the acquisition module based on the historical training data set as follows:

[0016] The feature data in each set of training data is converted into a feature vector, and the feature vector is used as the input of the machine learning model. The friction resistance predicted by the machine learning model for the feature data is used as the output. The friction resistance in the label data corresponding to each set of feature data is used as the prediction target. The training target is to minimize the sum of all prediction accuracies. The calculation formula for prediction accuracy is: ɡi=(αi-βi) 2 , where ɡi is the prediction accuracy, αi is the predicted friction resistance corresponding to the i-th group of feature data, and βi is the friction resistance in the i-th group of label data; i represents the group number of the training data, i≤N; the machine learning model is trained until the sum of the prediction accuracies reaches convergence and the training is stopped.

[0017] As a further solution of the present invention: a temperature sensor is provided inside the acquisition module, and the temperature sensor is used to collect temperature data.

[0018] As a further solution of the present invention: the control module pre-generates a friction resistance change curve based on the pressure data, the temperature data and the friction coefficient.

[0019] As a further solution of the present invention: the control module pre-generates the friction resistance change curve in a manner comprising the following steps:

[0020] S1: first apply a stable pressure P to the metal film piezoresistive sheet;

[0021] S2: applying different ambient temperature values ​​T1 and T2 to the metal film piezoresistive sheet;

[0022] S3: driving the friction block through the driving mechanism so that the pressure of the friction block on the side of the piston rod is F0, and collecting the displacement L1 of the piston rod at the ambient temperature value T1 and the displacement L2 at the ambient temperature value T2;

[0023] S4: Calculate the force F that needs to be adjusted for the friction block based on the displacement difference of the piston rod at ambient temperature values ​​T1 and T2 调节 , so that the pressure of the friction block on the side of the piston rod is F0+F 调节 Afterwards, the displacement of the piston rod at the ambient temperature value T2 is collected as L1;

[0024] S5: Force F based on the difference between T1 and T2 and adjustment 调节 , generating F 调节 Friction resistance variation curve with ambient temperature.

[0025] As a further solution of the present invention: one end of the oil cylinder sleeve is connected to the metal film piezoresistive sheet, the inner cavity of the oil cylinder sleeve is filled with hydraulic oil, and when the metal film piezoresistive sheet is deformed by pressure, it will compress the hydraulic oil in the inner cavity of the oil cylinder sleeve.

[0026] Beneficial effects of the present invention:

[0027] 1. In the present invention, the deformation of the metal film piezoresistive sheet can be controlled by pressure through the provided driving mechanism and friction block. When the pressure to be measured by the seismic hysteresis pressure transmitter is within a relatively low range, the force of the friction block on the piston rod can be appropriately reduced, so that the metal film piezoresistive sheet can generate a larger deformation when subjected to pressure, and the larger deformation can ensure the measurement accuracy of the metal film piezoresistive sheet;

[0028] When the pressure that the seismic hysteresis pressure transmitter needs to measure is within a relatively high range, that is, the seismic hysteresis pressure transmitter needs to measure the pressure in a high-pressure environment, the force of the friction block on the piston rod can be appropriately increased at this time, so that the metal film piezoresistive sheet can still produce deformation when subjected to pressure, ensuring that the seismic hysteresis pressure transmitter can be applied to different environments, thereby improving the applicability of the seismic hysteresis pressure transmitter;

[0029] When the pressure measured by the pressure transmitter approaches the ambient temperature value, the position of the piston rod in the friction block will be fixed. If the environment in which the intelligently controlled seismic hysteresis pressure transmitter is located vibrates at this time, since the static friction between the piston rod and the friction block is greater than the sliding friction, the piston rod will remain stable in the friction block, and no error in the collected data will occur due to the vibration of the environment in which the intelligently controlled seismic hysteresis pressure transmitter is located, so that the intelligently controlled seismic hysteresis pressure transmitter has excellent seismic resistance.

[0030] 2. In the present invention, through the set control module, a machine learning model for predicting the friction resistance applied by the control module to the acquisition module can be trained. Through the machine learning module, the friction resistance applied by the control module to the acquisition module can be accurately predicted, and the displacement of the piston rod sliding in the friction block can be changed through the friction resistance, thereby offsetting the influence of the ambient temperature of the anti-seismic hysteresis pressure transmitter and ensuring the accuracy of the pressure data collected by the metal film piezoresistive plate. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The present invention will be further described below in conjunction with the accompanying drawings.

[0032] Figure 1 It is a structural schematic diagram of the seismic hysteresis pressure transmitter of the present invention;

[0033] Figure 2 is a front view of the seismic hysteresis pressure transmitter of the present invention;

[0034] Figure 3 It is a structural schematic diagram of the acquisition module in the seismic hysteresis pressure transmitter of the present invention;

[0035] Figure 4 It is a structural schematic diagram of the driving mechanism in the seismic hysteresis pressure transmitter of the present invention;

[0036] Figure 5 is a cross-sectional view of a driving mechanism in the seismic hysteresis pressure transmitter of the present invention;

[0037] Figure 6 It is a flow chart of a method for a control module of the present invention to generate a friction resistance variation curve.

[0038] In the figure: 1. display module; 2. control module; 21. driving mechanism; 22. friction block; 3. acquisition module; 31. metal film piezoresistive sheet; 32. cylinder sleeve; 33. piston rod; 4. external port; 5. mounting seat. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] Example 1

[0041] like Figure 1 - Figure 5As shown, the present invention discloses a seismic hysteresis pressure transmitter based on intelligent control, including a display module 1, which is provided with a display screen and an external port 4. It should be noted that the display module 1 has a built-in microprocessor, the display screen is connected to the microprocessor through a wire, and a power module is also required to be arranged inside the display module 1. The display screen is fixed to the front position of the display module 1 by bolts or other connection methods. A control module 2 is fixedly connected to the bottom of the display module 1, and an acquisition module 3 is connected to the bottom of the control module 2. A mounting seat 5 is fixedly connected to the side of the control module 2, and a threaded groove is passed through the surface of the mounting seat 5. The seismic hysteresis pressure transmitter can be installed at a set position through the mounting seat 5 and bolts; a temperature sensor is arranged inside the acquisition module 3, and the temperature sensor is used to collect temperature data.

[0042] A driving mechanism 21 is provided inside the control module 2, and a friction block 22 is provided on the inner side of the driving mechanism 21. It should be noted that the driving mechanism 21 can be a hydraulic push rod, an electric push rod or a pneumatic push rod. The selection of the driving mechanism 21 is adaptively selected by technical personnel in this field according to the space inside the control module 2 and the force range of the friction block 22.

[0043] For example, the driving mechanism 21 can be an electric push rod, and the output end of the electric push rod is directly fixedly connected to one side of the friction block 22. The technicians in this field have collected the relationship between the power of the electric push rod and the force of the friction block 22 in advance. The two are in a proportional relationship, that is, the greater the power of the electric push rod, the greater the force of the friction block 22.

[0044] A metal film piezoresistive sheet 31 is disposed at the bottom of the acquisition module 3 , and the specifications of the metal film piezoresistive sheet 31 are adaptively selected by those skilled in the art according to the specific use environment of the seismic hysteresis pressure transmitter.

[0045] A cylinder sleeve 32 is provided inside the acquisition module 3, a piston rod 33 is inserted at the top of the cylinder sleeve 32, one end of the cylinder sleeve 32 is connected to the metal film piezoresistive sheet 31, and the inner cavity of the cylinder sleeve 32 is filled with hydraulic oil. When the metal film piezoresistive sheet 31 is deformed by pressure, the hydraulic oil in the inner cavity of the cylinder sleeve 32 will be compressed.

[0046] It should be noted that one side of the metal film piezoresistive sheet 31 is used to sense pressure changes in the external environment, and the other side of the metal film piezoresistive sheet 31 is directly in contact with the inner cavity of the cylinder sleeve 32. When the metal film piezoresistive sheet 31 is subjected to pressure from the external environment, the metal film piezoresistive sheet 31 will be deformed, specifically, deformed toward the inner cavity of the cylinder sleeve 32. During the deformation of the metal film piezoresistive sheet 31, the metal film piezoresistive sheet 31 will squeeze the hydraulic oil in the inner cavity of the cylinder sleeve 32. When the hydraulic oil in the inner cavity of the cylinder sleeve 32 is squeezed, since the inner cavity of the cylinder sleeve 32 is in a sealed state, the hydraulic oil in the inner cavity of the cylinder sleeve 32 will squeeze the piston rod 33 at the other end of the cylinder sleeve 32. It should be noted that the diameter of the piston rod 33 is controlled to ensure that the volume of the hydraulic oil squeezed by the deformation of the metal film piezoresistive sheet 31 can enable the piston rod 33 to produce effective displacement. For example, the maximum volume that can be produced by the deformation of the metal film piezoresistive sheet 31 is Vmm 3 , then the bottom area of ​​the piston rod 33 can be set to Smm 2 , where S = 0.1V, it can be concluded that the maximum displacement of the piston rod 33 is 10 mm.

[0047] The above is only one way to set the specifications of the piston rod 33. Those skilled in the art can make an adaptive selection based on the internal space of the control module 2 and the required accuracy of the piston rod 33. When high-precision displacement of the piston rod 33 is required, the position of the piston rod 33 can be increased.

[0048] It should also be noted that the deformation of the metal film piezoresistive sheet 31 can be controlled by pressure through the arranged driving mechanism 21 and the friction block 22. When the pressure to be measured by the seismic hysteresis pressure transmitter is within a lower range, the force of the friction block 22 on the piston rod 33 can be appropriately reduced. This ensures that the metal film piezoresistive sheet 31 can produce a larger deformation when subjected to pressure, and the larger deformation can ensure the measurement accuracy of the metal film piezoresistive sheet 31.

[0049] When the pressure that the seismic hysteresis pressure transmitter needs to measure is within a higher range, that is, the seismic hysteresis pressure transmitter needs to measure the pressure in a high-pressure environment, the force of the friction block 22 on the piston rod 33 can be appropriately increased. This can ensure that the metal film piezoresistive plate 31 can still produce deformation when subjected to pressure, thereby ensuring that the seismic hysteresis pressure transmitter can be used in different environments, thereby improving the applicability of the seismic hysteresis pressure transmitter.

[0050] When the pressure measured by the pressure transmitter approaches the temperature value, the position of the piston rod 33 in the friction block 22 will be fixed. If the environment in which the intelligently controlled seismic hysteresis pressure transmitter is located vibrates at this time, since the static friction between the piston rod 33 and the friction block 22 is greater than the sliding friction, the piston rod 33 will remain stable in the friction block 22, and no error in the collected data will occur due to the vibration of the environment in which the intelligently controlled seismic hysteresis pressure transmitter is located, so that the intelligently controlled seismic hysteresis pressure transmitter has excellent seismic resistance.

[0051] Example 2

[0052] like Figure 1 - Figure 6 As shown, the control module 2 pre-collects a historical training data set, which is collected by a person skilled in the art during the test or use of the seismic hysteresis pressure transmitter.

[0053] The historical training data set includes N groups of training data, where N is a positive integer. It should be noted that the amount of the historical training data set is set by technical personnel in this field according to the specific model training situation. Each group of training data includes feature data and label data, wherein the feature data includes pressure data, temperature data and friction coefficient.

[0054] The pressure data is the pressure value collected by the metal film piezoresistive sheet 31 when collecting each set of training data. Specifically, the acquisition module 3 can be installed in a container where pressure data needs to be collected. The container can apply external pressure to the acquisition module 3. When the metal film piezoresistive sheet 31 is subjected to the pressure applied in the container, the metal film piezoresistive sheet 31 will be deformed, so that the resistance of the metal film piezoresistive sheet 31 will change. The microprocessor derives the pressure value of the metal film piezoresistive sheet 31 based on the resistance change of the metal film piezoresistive sheet 31, and converts the pressure value into an electrical signal, which can be transmitted to the outside through the external port 4.

[0055] When collecting each set of training data, the temperature data is the ambient temperature value of the metal film piezoresistive sheet 31, and the external port 4 transmits it to the control backend. The control backend can be a terminal PC or a mobile terminal. The transmission method of the electrical signal can be wired transmission or wireless transmission, which is selected by technical personnel in the field according to the specific conditions of the specific site to ensure that the control backend can monitor the pressure changes in the container in real time.

[0056] The friction coefficient is the friction coefficient between the friction block 22 and the piston rod 33 when collecting each set of training data. It should be noted that Figure 5As shown, the top end of the piston rod 33 is fixedly connected to the sliding block, specifically, the inner side surface of the friction block 22 adopts an arc surface, the sliding block is cylindrical in shape and matches the inner side surface of the friction block 22, and the sliding block and the friction block 22 are both made of wear-resistant materials, such as ceramic materials or metal materials, to provide a stable friction coefficient between the friction block 22 and the sliding block.

[0057] The label data is the friction resistance of the piston rod 33 when it moves on the surface of the friction block 22 when each set of training data is collected. It should be noted that if the friction coefficient of the piston rod 33 is μ, and the force of the friction block 22 on the piston rod 33 in the vertical direction is F0, then the friction resistance f of the piston rod 33 when it moves on the surface of the friction block 22 is f=F0×μ, thereby obtaining F0=f / μ. Therefore, based on the friction resistance f when the piston rod 33 moves on the surface of the friction block 22, the magnitude of the force F0 of the friction block 22 on the piston rod 33 in the vertical direction can be directly obtained.

[0058] A machine learning model for predicting the frictional resistance applied by the control module 2 to the acquisition module 3 is trained based on a historical training data set.

[0059] The control module 2 trains a machine learning model for predicting the friction resistance applied by the control module 2 to the acquisition module 3 based on the historical training data set as follows:

[0060] The feature data in each set of training data is converted into a feature vector, and the feature vector is used as the input of the machine learning model. The friction resistance predicted by the machine learning model for the feature data is used as the output. The friction resistance in the label data corresponding to each set of feature data is used as the prediction target. The training target is to minimize the sum of all prediction accuracies. The calculation formula for prediction accuracy is: ɡi=(αi-βi) 2 , where ɡi is the prediction accuracy, αi is the predicted friction resistance corresponding to the i-th group of feature data, βi is the friction resistance in the i-th group of label data; i represents the group number of the training data, i≤N; the machine learning model is trained until the sum of the prediction accuracies converges and the training is stopped. It should be noted that the convergence standard is set by technical personnel in this field according to the specific model training situation. For example, if the required prediction accuracy ɡi≤0.001, that is, when the square of the difference between the friction resistance predicted by the machine model and the friction resistance in the corresponding label data is less than 0.001, the training of the machine learning model is considered to be completed, and then the trained machine learning model can be applied to the seismic hysteresis pressure transmitter.

[0061] The acquisition module 3 collects pressure data, temperature data and friction coefficient in real time, and uses a machine learning model to predict the friction resistance applied by the control module 2 to the acquisition module 3 based on the pressure data, temperature data and friction coefficient, and calibrates the pressure data output by the acquisition module 3 based on the friction resistance.

[0062] It should be noted that, through the setting of the control module 2, a machine learning model for predicting the friction resistance applied by the control module 2 to the acquisition module 3 can be trained. Through this machine learning module, the friction resistance applied by the control module 2 to the acquisition module 3 can be accurately predicted, and the displacement of the piston rod 33 sliding in the friction block 22 can be changed through the friction resistance, thereby offsetting the influence of the ambient temperature of the anti-seismic hysteresis pressure transmitter and ensuring the accuracy of the pressure data collected by the metal film piezoresistive plate 31.

[0063] Example 3

[0064] like Figure 1-Figure 6 As shown, the control module pre-generates a friction resistance change curve based on pressure data, temperature data and friction coefficient. The method in which the control module pre-generates the friction resistance change curve includes the following steps:

[0065] S1: firstly apply a stable pressure P to the metal film piezoresistive sheet 31 . The pressure P is applied by a person skilled in the art using a pressurizing device to keep the pressure on the metal film piezoresistive sheet 31 at a stable value, thereby improving the accuracy of subsequent data collection.

[0066] S2: Different ambient temperature values ​​T1 and T2 are applied to the metal film piezoresistive sheet 31. It should be noted that the ambient temperature values ​​T1 and T2 are set by technicians in this field according to the specific conditions on site, for example, T1 = 0°C, T2 = 100°C, or T1 = -20°C, T2 = 200°C.

[0067] S3: The friction block 22 is driven by the driving mechanism 21, so that the pressure of the friction block 22 on the side of the piston rod 33 is F0. The driving mechanism 21 is controlled by a technician in the display module 1 through the microprocessor. The driving mechanism 21 can push the friction block 22, so that the friction block 22 acts on the side of the piston rod 33. The magnitude of the pressure F0 is controlled based on the power of the driving mechanism 21, so that the magnitude of the pressure F0 is at a set value, and the displacement L1 of the piston rod 33 at the ambient temperature value T1 and the displacement L2 at the ambient temperature value T2 are collected, that is, when the metal film piezoresistive sheet 31 is in the environment of the ambient temperature value T1 and the pressure P, it is deformed. As the metal film piezoresistive sheet 31 is deformed, specifically, it is deformed toward the inner cavity side of the cylinder sleeve 32. During the deformation of the metal film piezoresistive sheet 31, the metal film piezoresistive sheet 31 will squeeze the hydraulic oil in the inner cavity of the cylinder sleeve 32. When the hydraulic oil in the inner cavity of the cylinder sleeve 32 is squeezed, since the inner cavity of the cylinder sleeve 32 is in a sealed state, the hydraulic oil in the inner cavity of the cylinder sleeve 32 will squeeze the piston rod 33 at the other end of the cylinder sleeve 32, causing the piston rod 33 to displace L1. Similarly, by changing the ambient temperature, the metal film piezoresistive sheet 31 is deformed under the environment of ambient temperature T2 and pressure P, and the piston rod 33 is displaced L2.

[0068] It should be noted that, at the ambient temperature T1, the work done by the piston rod 33 is G1 = F0×μ×L1.

[0069] At the ambient temperature T2, the work done by the piston rod 33 is G2 = F0×μ×L2.

[0070] S4: Calculate the force F that needs to be adjusted for the friction block 22 based on the displacement difference between the ambient temperature values ​​T1 and T2 of the piston rod 33 调节 , so that the pressure of the friction block 22 on the side of the piston rod 33 is F0+F 调节 After that, the displacement of the piston rod 33 at the ambient temperature value T2 is collected as L1, that is:

[0071] Assume that the pressure that the friction block 22 needs to increase is F 调节 When the ambient temperature is T2, the displacement of the piston rod 33 is L1.

[0072] Since the work done by the piston rod 33 is constant at the ambient temperature T2, we have:

[0073] (F0+F 调节 )×μ×L1=G2=F0×μ×L2;

[0074] By transforming the above formula, we can get:

[0075] F 调节 =F0×L2 / L1-F0;

[0076] S5: Force F based on the difference between T1 and T2 and adjustment 调节 Generate F 调节 The friction resistance curve y=f(x) with the change of ambient temperature is:

[0077] f(x)=F 调节 / (T2-T1)×x;

[0078] Where y represents the force of the friction block 22 on the piston rod 33 that needs to be adjusted based on temperature changes, and x represents the temperature value; for example, when T1 = 0°C, T2 = 100°C, and the measured F 调节 =50N, y=f(x)=0.5x, that is, for every 1°C increase in ambient temperature, the force of the friction block 22 on the piston rod 33 needs to be increased by 0.5N. This ensures that the pressure data output by the seismic hysteresis pressure transmitter is accurate and offsets the error caused by temperature changes.

[0079] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. The seismic hysteresis pressure transmitter based on intelligent control is characterized by: include: A display module (1) having a display screen and an external port (4); A control module (2) fixedly connected to the bottom of the display module (1); A collection module (3) connected to the bottom of the control module (2); The control module (2) collects a historical training data set in advance, and trains a machine learning model for predicting the friction resistance applied by the control module (2) to the acquisition module (3) based on the historical training data set; The acquisition module (3) acquires pressure data, temperature data and friction coefficient in real time, uses a machine learning model to predict the friction resistance applied by the control module (2) to the acquisition module (3) based on the pressure data, temperature data and friction coefficient, and calibrates the pressure data output by the acquisition module (3) based on the friction resistance; A driving mechanism (21) is provided inside the control module (2), and a friction block (22) is provided inside the driving mechanism (21); A metal film piezoresistive sheet (31) is provided at the bottom end of the acquisition module (3); The collection module (3) is provided with a cylinder sleeve (32) inside, and a piston rod (33) is inserted into the top of the cylinder sleeve (32); One end of the oil cylinder sleeve (32) is connected to the metal film piezoresistive sheet (31), and the inner cavity of the oil cylinder sleeve (32) is filled with hydraulic oil. When the metal film piezoresistive sheet (31) is deformed by pressure, it compresses the hydraulic oil in the inner cavity of the oil cylinder sleeve (32).

2. The seismic hysteresis pressure transmitter based on intelligent control according to claim 1 is characterized in that: The historical training data set includes N groups of training data, where N is a positive integer, and each group of training data includes feature data and label data, wherein the feature data includes pressure data, temperature data and friction coefficient; The pressure data is the pressure value collected by the metal film piezoresistive sheet (31) when collecting each set of training data; The temperature data is the ambient temperature value of the metal film piezoresistive sheet (31) when collecting each set of training data; The friction coefficient is the friction coefficient between the friction block (22) and the piston rod (33) when collecting each set of training data; The label data is the friction resistance of the piston rod (33) when it moves on the surface of the friction block (22) when collecting each set of training data.

3. The seismic hysteresis pressure transmitter based on intelligent control according to claim 2 is characterized in that: The control module (2) trains a machine learning model for predicting the friction resistance applied by the control module (2) to the acquisition module (3) based on the historical training data set in the following manner: The feature data in each set of training data is converted into a feature vector, and the feature vector is used as the input of the machine learning model. The friction resistance predicted by the machine learning model for the feature data is used as the output. The friction resistance in the label data corresponding to each set of feature data is used as the prediction target. The training target is to minimize the sum of all prediction accuracies. The calculation formula for prediction accuracy is: ɡi=(αi-βi) 2 , where ɡi is the prediction accuracy, αi is the predicted friction resistance corresponding to the i-th group of feature data, βi is the friction resistance in the i-th group of label data; i represents the group number of the training data, i≤N; The machine learning model is trained until the sum of prediction accuracies reaches convergence.

4. The seismic hysteresis pressure transmitter based on intelligent control according to claim 3 is characterized in that: The acquisition module (3) is provided with a temperature sensor inside, and the temperature sensor is used to acquire temperature data.

5. The seismic hysteresis pressure transmitter based on intelligent control according to claim 4 is characterized in that: The control module (2) generates a friction resistance variation curve in advance based on pressure data, temperature data and friction coefficient.

6. The seismic hysteresis pressure transmitter based on intelligent control according to claim 5 is characterized in that: The control module (2) pre-generates a friction resistance change curve based on pressure data, temperature data and friction coefficient, comprising the following steps: S1: first applying a stable pressure P to the metal film piezoresistive sheet (31); S2: applying different ambient temperature values ​​T1 and T2 to the metal film piezoresistive sheet (31); S3: driving the friction block (22) through the driving mechanism (21) so that the pressure exerted by the friction block (22) on the side of the piston rod (33) is F0, and collecting the displacement L1 of the piston rod (33) at the ambient temperature value T1 and the displacement L2 at the ambient temperature value T2; S4: Calculate the force F that needs to be adjusted by the friction block (22) based on the displacement difference of the piston rod (33) at the ambient temperature values ​​T1 and T2 调节 , so that the pressure exerted by the friction block (22) on the side of the piston rod (33) is F0+F 调节 Afterwards, the displacement of the piston rod (33) at the ambient temperature value T2 is collected as L1; S5: Force F based on the difference between T1 and T2 and adjustment 调节 , generating F 调节 Friction resistance variation curve with ambient temperature.

Images