High-precision anti-interference pressure transmitter

Abstract

The invention discloses a high-precision anti-interference pressure transmitter, and relates to the technical field of anti-interference pressure transmitters. Comprising a pressure data acquisition module, a data preprocessing and integration module, a pressure fluctuation feature extraction and quantification module, an intelligent evaluation and deep learning analysis module and a dynamic adaptive monitoring regulation and control module, the pressure transmitter firstly continuously detects the fluid pressure in the earth crust fracture according to a preset initial detection threshold value, and recorded and collected pressure data serve as the basis of all subsequent analysis. According to the method, deep learning analysis and dynamic threshold adjustment are combined, transient pressure fluctuation and magma rising premonition are intelligently distinguished, and the risk of false alarm and missing alarm is reduced. By improving the sampling frequency and optimizing data analysis, a complete pressure change track is formed, the volcano monitoring precision and the anti-interference capability are improved, and efficient technical support is provided for geological safety early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of anti-interference pressure transmitters, and particularly to a high-precision anti-interference pressure transmitter. Background Art

[0002] A high-precision anti-interference pressure transmitter is a sensing device used to accurately measure pressure and convert it into a standard signal (such as 4-20 mA, 0-10 V or digital signal), with high precision and strong anti-interference ability. Its high precision usually depends on high-quality sensitive elements (such as diffused silicon, ceramic or thin-film pressure sensors) and advanced signal processing technologies (such as temperature compensation, non-linear correction and digital filtering). The anti-interference performance is achieved through shielding design, signal isolation, electromagnetic interference (EMI) resistance technology and digital filtering algorithms, etc., enabling it to work stably in complex industrial scenarios such as strong electromagnetic environments, high temperatures, humidity or vibrations. This kind of transmitter is widely used in fields such as petroleum, chemical industry, water treatment, volcano monitoring, aerospace, etc., and is particularly suitable for occasions with high requirements for measurement accuracy and signal stability.

[0003] In the field of volcano monitoring, high-precision anti-interference pressure transmitters are mainly used to measure and analyze the pressure changes inside and around volcanoes, providing key data for volcanic eruption prediction. Specifically, it can be used to monitor the pressure changes in underground magma chambers, detect the pressure fluctuations during volcanic gas (such as sulfur dioxide, carbon dioxide, water vapor, etc.) eruptions, and measure the fluid pressure in crustal fractures, thereby judging the depth, movement direction and possible eruption time of magma activities. In addition, this sensor needs to have strong anti-interference ability and be able to work stably in extreme environments such as strong electromagnetic interference (such as lightning, geothermal anomalies), high temperature and high pressure, and strongly corrosive gases. It is widely used in key monitoring points such as volcanic craters, seismic faults, hot spring geothermal areas, etc., providing accurate real-time data support for the global volcanic disaster warning system, and helping to reduce the casualties and economic losses caused by volcanic eruptions.

[0004] The prior art has the following deficiencies: The prior art uses a high-precision anti-interference pressure transmitter to measure the fluid pressure in the crustal fissures, and usually adopts a preset detection threshold to improve the monitoring accuracy. However, underground magma activity may transiently increase the local gas pressure, which is often caused by the magma heat flow heating the fluid and does not necessarily mean an impending eruption. Since the pressure fluctuations are affected by rock porosity, permeability, and fracture connectivity, there may be a risk of false judgment in fixed-threshold detection. If the detection threshold is too sensitive, it may lead to false alarms of volcanic eruptions, triggering unnecessary emergency warnings, causing large-scale evacuations, traffic chaos, economic losses, and even affecting the government's credibility. At the same time, key infrastructure (such as hospitals, power plants, and communication centers) may be shut down due to excessive precautions, affecting the normal operation of society. More seriously, frequent false alarms will weaken the public's trust in the warning system, resulting in the neglect of alarms during a real eruption and increasing the disaster risk.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The object of the present invention is to provide a high-precision anti-interference pressure transmitter, which combines deep learning analysis and dynamic threshold adjustment to intelligently distinguish between transient pressure fluctuations and precursors of magma ascent, reducing the risk of false alarms and missed detections. By increasing the sampling frequency and optimizing data analysis, a complete pressure change trajectory is formed, improving the accuracy and anti-interference ability of volcanic monitoring, and providing efficient technical support for geological safety warnings to solve the problems in the above background art.

[0007] To achieve the above object, the present invention provides the following technical solution: A high-precision anti-interference pressure transmitter, comprising a pressure data acquisition module, a data preprocessing and integration module, a pressure fluctuation feature extraction and quantification module, an intelligent evaluation and deep learning analysis module, and a dynamic adaptive monitoring and control module: The pressure data acquisition module: The pressure transmitter first continuously detects the fluid pressure in the crustal fissures according to a preset initial detection threshold, and the recorded and collected pressure data will be used as the basis for all subsequent analyses; The data preprocessing and integration module: Integrates the real-time fluid pressure data collected by the high-precision anti-interference pressure transmitter according to time sequence and spatial position to form a systematic data set, and preprocesses the pressure data in the data set; The pressure fluctuation feature extraction and quantification module: Extracts key features associated with transient local gas pressure increase from the preprocessed data, analyzes and processes the extracted key features under a detection window, and quantifies the current abnormal degree of pressure fluctuation; The intelligent evaluation and deep learning analysis module takes the quantified key features as feature vectors and inputs them into a pre-trained deep learning model. The deep learning model determines whether the current pressure increase belongs to a transient local gas pressure increase based on its learning from historical data. The dynamic adaptive monitoring and regulation module, when the deep learning model determines that the current pressure change is only a transient local increase, automatically reduces the detection threshold, broadens the capture range of minute pressure fluctuations, and simultaneously increases the pressure detection frequency to refine the time scale of pressure evolution.

[0008] Preferably, the specific steps for the pressure transmitter to continuously detect the fluid pressure in the crustal fracture according to a preset initial detection threshold are as follows: First, activate the high-precision anti-interference pressure transmitter according to the set initial threshold, and simultaneously enable the pressure data acquisition function at multiple monitoring points in the crustal fracture. Then, the transmitter uses its high-sensitivity sensor to continuously sense the pressure of the fluid in the fracture and converts the pressure signal into an electrical signal or a digital signal. Subsequently, continuously record it in the monitoring database through the data transmission system. Meanwhile, mark the time of the data to ensure that each pressure value has an accurate time stamp for subsequent analysis.

[0009] Preferably, key features associated with transient local gas pressure increases are mined from the preprocessed data. The mined features include the time correlation between microseismic activities and fluid pressure changes in the crustal fracture area and the non-linear fitting between pressure increase per unit time and crustal temperature changes. Analyze the time correlation between microseismic activities and fluid pressure changes in the crustal fracture area and the non-linear fitting between pressure increase per unit time and crustal temperature changes under the detection window, respectively generate a microseismic-pressure synchronization reference value and a thermosensitive compression reference value, and quantify the current pressure fluctuation anomaly degree through the microseismic-pressure synchronization reference value and the thermosensitive compression reference value.

[0010] Preferably, the specific steps for analyzing the time correlation between microseismic activities and fluid pressure changes in the crustal fracture area under the detection window to generate a microseismic-pressure synchronization reference value are as follows: First, construct time series of microseismic events and fluid pressure changes and perform time alignment to ensure comparison within the same detection window. Since microseismic waves spread in space and affect fluid pressure, a time alignment function needs to be defined to quantify the impact of microseismic events on fluid pressure and serve as the basis for subsequent calculations. The calculation expression is as follows: , where is the microseismic-pressure time alignment coupling degree, is the instantaneous fluid pressure, representing the spatial position The fluid pressure value at is the microseismic energy release amount, indicating the energy released by microseismic events at the spatial position ; is the spatial distance from the seismic source to the measurement point, is the spatial attenuation weight, is the natural base, is the spatial attenuation factor, is the integration region, representing the entire monitoring area, including the set of spatial positions of all pressure monitoring points ; Due to the change in fluid pressure caused by microseismic events, accompanied by a propagation time delay during the process, it is necessary to further calculate the matching degree in spatial propagation. For this purpose, a propagation rate matching function is defined to analyze how the energy released by microseismic activities propagates in space and to determine whether the change in fluid pressure conforms to this propagation mode. The calculation expression is as follows: , where in the formula, is the matching degree of the microseismic-pressure propagation rate, is the gradient field of the fluid pressure, is the second-order spatial derivative of the microseismic energy, is a very small positive number, is the propagation rate matching adjustment factor, is the natural base, is the wave speed difference within the local area, is the propagation rate matching adjustment factor, is the exponential adjustment parameter of the pressure gradient, is the exponential adjustment parameter of the second-order derivative of the microseismic energy release; The comprehensive microseismic-pressure time alignment coupling degree and the microseismic-pressure propagation rate matching function are used to generate a microseismic-pressure synchronization reference value to finally quantify the time correlation between microseismic activities and changes in fluid pressure. The calculation expression is as follows: , where in the formula, is the microseismic-pressure synchronization reference value, is the time decay factor, measuring the time difference between the peak time of the microseismic event occurrence and the peak time of the fluid pressure, is the time synchronization control parameter, is the peak time of the microseismic event, is the peak time of the fluid pressure change, is the smoothing factor.

[0011] Preferably, the specific steps for analyzing the non-linear fitting of the pressure rise per unit time and the crust temperature change under the detection window to generate the thermosensitive compression reference value are as follows: First, construct a function that describes the non-linear interaction between the pressure change rate and the crust temperature change to reflect the true state of the fluid pressure in the crustal fracture under thermosensitive compression, as expressed below: , where is the non-linear coupling function, is the non-linear amplification coefficient, is the pressure-temperature change power exponent, is the reference baseline correction factor, is the temperature sensitivity adjustment factor, is the high-order non-linear adjustment exponent, is the pressure change rate, is the fluid pressure, is the crust temperature; Substitute the result of the non-linear coupling function into the adaptive non-linear enhancement formula to generate the thermosensitive compression reference value to amplify the characteristic signal difference of the transient local pressure rise. The calculation expression is as follows: , where is the thermosensitive compression reference value, is the non-linear exponential amplification parameter, is the enhancement balance parameter, is the non-linear enhancement adjustment parameter, is the baseline suppression parameter, is the sine amplitude adjustment parameter, is the periodic interference regulation parameter.

[0012] Preferably, the quantified microseismic-pressure synchronous reference value and the thermosensitive compression reference value are used as feature vectors and input into a pre-trained deep learning model. The deep learning model generates a pressure fluctuation anomaly coefficient, and the fluid pressure in the current crustal fracture is intelligently evaluated through the pressure fluctuation anomaly coefficient to determine whether the current pressure rise belongs to a transient local gas pressure rise.

[0013] Preferably, the pressure fluctuation anomaly coefficient generated when the fluid pressure in the current crustal fracture is intelligently evaluated by the pre-trained deep learning model is compared and analyzed with the pre-set pressure fluctuation anomaly coefficient reference threshold to classify the current abnormal pressure change. The classification steps are as follows: If the pressure fluctuation anomaly coefficient is greater than the pressure fluctuation anomaly coefficient reference threshold, the current pressure rise is classified as a short-term local gas pressure rise; if the pressure fluctuation anomaly coefficient is less than or equal to the pressure fluctuation anomaly coefficient reference threshold, the current pressure change is classified as a normal change.

[0014] Preferably, when the deep learning model determines that the current pressure change is only a short-term local rise, the specific steps of automatically lowering the detection threshold and increasing the pressure detection frequency are as follows: When the deep learning model determines that the current pressure fluctuation is a short-term local anomaly, the detection threshold is dynamically lowered to enhance the perception of small pressure fluctuations. The detection threshold adjustment formula is as follows: , where is the adjusted detection threshold, is the preset fluid pressure abnormality detection threshold, is the threshold sensitivity coefficient, is the reference threshold of the pressure fluctuation anomaly coefficient, is the anomaly intensity index, is the benchmark normalized index, is a very small positive number, is the pressure change rate adjustment factor, is the gradient of pressure over space, is a nonlinear adjustment index used to enhance the effect of the local pressure change rate; After adjusting the detection threshold, the detection frequency is increased synchronously to ensure that the dynamic evolution of pressure changes can be accurately tracked. The adjustment formula for the detection frequency is as follows; , where is the adjusted pressure detection frequency, is the detection frequency before adjustment, is the detection frequency adjustment coefficient, and are index adjustment factors, Used to adjust the pressure fluctuation abnormal coefficient The degree of influence in the calculation, Used to adjust the reference threshold of the pressure fluctuation abnormal coefficient The degree of influence in the calculation, Spatial second-order pressure gradient adjustment factor, is the second-order spatial derivative of pressure, is the high-order gradient influence index, is the temperature compensation term, is the temperature regulation coefficient, is the natural base, is the temperature attenuation factor, is the current crustal fracture temperature.

[0015] In the above technical solution, the technical effects and advantages provided by the present invention are: The present invention effectively solves the problems of false alarms and missed alarms that may be caused by traditional fixed threshold detection methods by combining deep learning intelligent analysis with dynamic threshold adjustment. Through technical means such as continuous pressure detection, data preprocessing, key feature extraction, intelligent identification and dynamic adjustment, the scheme can intelligently distinguish short-term pressure fluctuations caused by magma heat flow from real precursors of magma rise when the local gas pressure rises briefly. When the system detects a short-term local pressure change, it automatically lowers the detection threshold and increases the sampling frequency, further refining the time scale of pressure evolution, thereby forming a more complete pressure change trajectory. This not only improves the sensitivity to tiny pressure fluctuations, but also ensures timely warning when there is real danger while preventing false alarms, greatly improving the accuracy and reliability of volcano monitoring. The intelligent and adaptive characteristics of the present invention enable it to adapt to different geological environments, improve the system's anti-interference ability and data analysis accuracy, and provide more scientific and efficient technical support for volcanic disaster warning and geological safety monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0017] Figure 1 The module schematic diagram of a high-precision anti-interference pressure transmitter of the present invention. DETAILED DESCRIPTION

[0018] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0019] The present invention provides Figure 1 A high-precision anti-interference pressure transmitter shown includes a pressure data acquisition module, a data preprocessing and integration module, a pressure fluctuation feature extraction and quantification module, an intelligent evaluation and deep learning analysis module, and a dynamic adaptive monitoring and control module: In the pressure data acquisition module, the pressure transmitter first continuously detects the fluid pressure in the crustal fracture according to the preset initial detection threshold. The recorded and collected pressure data will serve as the basis for all subsequent analyses; The specific steps for the pressure transmitter to continuously detect the fluid pressure in the crustal fracture according to the preset initial detection threshold are as follows: First, activate the high-precision anti-interference pressure transmitter according to the set initial threshold, and simultaneously turn on the pressure data acquisition function at multiple monitoring points in the crustal fracture; then, the transmitter uses its highly sensitive sensor to continuously sense the pressure of the fluid in the fracture and convert the pressure signal into an electrical signal or a digital signal; subsequently, continuously record it to the monitoring database through the data transmission system; at the same time, mark the data with time to ensure that each pressure value has an accurate timestamp for subsequent analysis. During the acquisition process, the system will also perform basic data integrity checks, such as identifying invalid signals, removing interference data, and preliminarily screening the data to ensure that subsequent analysis is based on high-quality pressure information. In addition, the pressure data is usually recorded in a streaming data storage manner to ensure continuous data collection when the pressure is continuously changing, forming a complete time series, and finally building a stable and reliable pressure data foundation to provide accurate input for subsequent feature extraction, trend analysis, and deep learning evaluation.

[0020] The continuous detection of the fluid pressure in the crustal fracture by the pressure transmitter according to the preset initial detection threshold means that in a volcanic monitoring or geological monitoring system, the high-precision anti-interference pressure transmitter continuously and uninterruptedly measures the fluid pressure inside the crustal fracture according to the preset initial threshold (i.e., the reference pressure range). This means that the system will automatically detect whether the fluid pressure exceeds the safe range and record and store the collected data in real time as the basis for subsequent analysis.

[0021] Establish baseline data: Through the initial detection threshold, establish a normal pressure range so that subsequent data changes can be reasonably evaluated and misjudgments can be avoided.

[0022] Monitor fluid pressure changes: Continuously track the pressure in the crustal fracture to ensure that corresponding pressure change trends can be captured during magma activity, gas overflow, or fracture movement.

[0023] Trigger subsequent intelligent analysis: The system will judge whether the pressure exceeds the range according to the set initial threshold and input this data into preprocessing, feature analysis, and deep learning models to further evaluate the internal state of the crust.

[0024] Ensure the normal operation of the early warning system: Continuous detection can ensure the integrity of pressure data, avoid information loss caused by intermittent sampling, and improve the accuracy and reliability of monitoring.

[0025] The setting of the initial detection threshold enables the pressure transmitter to stably and efficiently monitor the pressure evolution in the crustal fracture, providing key data support and laying a foundation for volcanic activity prediction and geological disaster early warning.

[0026] A data preprocessing and integration module integrates the real-time fluid pressure data collected by a high-precision anti-interference pressure transmitter according to time sequence and spatial position to form a systematic data set, and preprocesses the pressure data in the data set; The data set not only includes the pressure value itself, but may also contain auxiliary information such as timestamps, geographical locations, temperatures, and humidities. Then, necessary cleaning, denoising, and normalization processes are performed on the data: 1. Data cleaning: Eliminate obviously abnormal or missing records, such as invalid data during sensor failures or occasional extreme interference data (such as impacts caused by electromagnetic pulse transients).

[0027] 2. Denoising process: Use filtering algorithms (such as Kalman filtering, wavelet transform, or moving average filtering) to smooth the data curve to reduce the interference caused by environmental noise.

[0028] 3. Normalization process: By standardizing or normalizing the data, the data collected from different sections and different sensors can be made comparable, laying a foundation for subsequent feature extraction and model evaluation.

[0029] A pressure fluctuation feature extraction and quantification module extracts key features associated with short-term local gas pressure rises from the preprocessed data, analyzes and processes the extracted key features under a detection window, and quantifies the current pressure fluctuation anomaly degree; Extract key features associated with short-term local gas pressure rises from the preprocessed data. The extracted features include the time correlation between microseismic activities in the crust fracture area and fluid pressure changes, and the non-linear fitting between pressure rise per unit time and crust temperature changes. Analyze the time correlation between microseismic activities in the crust fracture area and fluid pressure changes, and the non-linear fitting between pressure rise per unit time and crust temperature changes under a detection window, respectively generate a microseismic-pressure synchronization reference value and a thermosensitive compression reference value, and quantify the current pressure fluctuation anomaly degree through the microseismic-pressure synchronization reference value and the thermosensitive compression reference value.

[0030] Microseismic activity in the crustal fracture zone appears synchronously with fluid pressure changes, but then the pressure drops rapidly, indicating that the fluid pressure in the current crustal fractures is in a transient local gas pressure rise. This phenomenon is usually caused by the heating of the fluid in the fractures by magmatic heat flow, resulting in the evaporation of water to form high-pressure steam, or the sudden release of dissolved gases (such as CO2, CH4), triggering a sudden local pressure increase in a short time. When the pressure rise occurs synchronously with microseismicity, it indicates that the crustal fractures have received a transient energy input, and the microseismicity itself may be due to the rapid release of gas, changes in fluid infiltration, or fine-tuning of the fractures caused by thermal expansion stress. However, if this pressure rise does not persist but drops rapidly in a short time, it indicates that the fracture system has high permeability or connectivity, allowing excess gas or steam to quickly diffuse into the surrounding area, thus causing the pressure to return to normal levels. This feature is different from the continuous pressure accumulation caused by magma ascent, which is usually accompanied by long-term pressure growth and larger-scale seismic activity. Therefore, the pattern of synchronous microseismic-pressure rise followed by a rapid decline is a typical feature of transient local gas pressure rise, indicating that this pressure change is mainly caused by local thermal disturbances rather than a precursor to continuous magma upwelling.

[0031] The specific steps to generate the microseismic-pressure synchronization reference value by analyzing the time correlation between microseismic activity and fluid pressure changes in the crustal fracture zone under the detection window are as follows: First, construct the time series of microseismic events and fluid pressure changes and perform time alignment to ensure comparison within the same detection window. The microseismic data includes magnitude, energy release rate, focal depth, etc., while the fluid pressure data includes instantaneous pressure, pressure change rate, and pressure gradient. Since microseismic waves spread in space and affect fluid pressure, it is necessary to define a time alignment function to quantify the impact of microseismic events on fluid pressure and use it as the basis for subsequent calculations. The calculation expression is as follows: , where is the microseismic-pressure time alignment coupling degree, representing the overall coupling strength between microseismic activity and fluid pressure changes, is the instantaneous fluid pressure, representing the fluid pressure value at spatial position , is the microseismic energy release, representing the energy released by the microseismic event at spatial position , is the spatial distance from the focal point to the measuring point, representing the spatial distance between the microseismic focal point and the fluid pressure monitoring point, used to measure the impact intensity of microseismic events on pressure measuring points at different positions, is the spatial attenuation weight, representing the influence degree of microseismic energy release on pressure monitoring points at different positions, which decays with the increase of distance, is the natural base, is the spatial attenuation factor, controlling the influence of microseismicity with distance The attenuation rate is the integration region, representing the entire monitoring area, which contains the spatial positions of all pressure monitoring points set; The function of the above steps is to quantify the preliminary correlation between microseismic energy release and fluid pressure fluctuations. If significant pressure fluctuations occur at multiple monitoring points within the fracture after a microseismic event, then takes a higher value, indicating that there may be a strong time synchronization between the two, laying a foundation for subsequent calculations.

[0032] Due to the change in fluid pressure caused by microseismic events, accompanied by a propagation time delay during the process, it is necessary to further calculate the matching degree in spatial propagation. Therefore, a propagation rate matching function is defined to analyze how the energy released by microseismic activities propagates in space and to determine whether the fluid pressure change conforms to this propagation mode. The calculation expression is as follows: , where is the matching degree of the microseismic-pressure propagation rate. The higher the value, the higher the degree of matching between the spatial change trend of the fluid pressure fluctuation and the energy release mode of microseismic is the gradient field of the fluid pressure, describing how the pressure changes with spatial coordinates, is the second-order spatial derivative of microseismic energy, is a very small positive number to prevent the denominator from approaching zero numerically and ensure calculation stability, is the propagation rate matching adjustment factor, used to measure the matching degree between the microseismic wave speed and the propagation rate of fluid pressure fluctuations, is the natural base, is the wave speed difference within the local area, measuring the matching degree between the microseismic wave propagation speed and the fluid pressure diffusion speed, is the propagation rate matching adjustment factor, used to control the matching degree between the microseismic wave propagation speed and the propagation rate of fluid pressure fluctuations, is the exponential adjustment parameter of the pressure gradient, controlling the contribution degree of the severity of fluid pressure change in the matching degree calculation, is the exponential adjustment parameter of the second derivative of microseismic energy release, controlling the influence of the spatial change degree of microseismic energy release in the matching calculation; The function of this step is to determine whether the microseismic energy propagation rate is consistent with the fluid pressure fluctuation rate. If the spatial propagation rates of the two are highly matched, it further supports that microseismic may be the triggering factor for the increase in fluid pressure.

[0033] Comprehensive microseismic-pressure time alignment coupling degree and microseismic-pressure propagation rate matching function , generate a microseismic-pressure synchronization reference value to finally quantify the temporal correlation between microseismic activity and fluid pressure changes. The calculation expression is as follows: , where is the microseismic-pressure synchronization reference value, is the time decay factor, measuring the peak time of microseismic events and the peak time of fluid pressure The time difference between them, is the time synchronization control parameter, is the peak time of microseismic events, is the peak time of fluid pressure changes, is the smoothing factor, preventing the denominator from having extremely small values and ensuring the stability of the calculation.

[0034] The function of this step is to comprehensively consider the temporal alignment degree between microseismic and pressure, the matching degree of spatial propagation rate, and the time lag relationship, and finally generate a microseismic-pressure synchronization reference value . If is relatively high, it indicates that the matching degree between microseismic activity and fluid pressure changes in time and space is high, suggesting that the fluid pressure in the crustal fracture area is more likely to be in a state of short-term local gas pressure increase. And if is relatively low, it means that there is no obvious correlation between microseismic and fluid pressure changes, and the fluid pressure in the fracture remains in a normal state.

[0035] The larger the microseismic-pressure synchronization reference value generated by analyzing the temporal correlation between microseismic activity and fluid pressure changes in the crustal fracture area under the detection window, the more likely it is that the fluid pressure in the current crustal fracture is in a state of short-term local gas pressure increase. This reference value quantifies their synchronization degree by analyzing the temporal correlation between microseismic activity and fluid pressure changes. When the reference value is relatively high, it means that within the monitoring window, the occurrence of microseismic events is highly consistent with the short-term fluctuations of pressure, indicating that the fluid in the crustal fracture is being locally disturbed, such as water evaporation, gas overflow, or fracture fine-tuning caused by magmatic heat flow. Since these phenomena are usually short-lived, they do not lead to continuous pressure accumulation, but rather show a sudden increase in pressure followed by a rapid decline, conforming to the typical characteristics of short-term local gas pressure increase. When the microseismic-pressure synchronization reference value is relatively low, it means that there is no obvious correlation between microseismic activity and fluid pressure changes, indicating that the fluid pressure in the fracture remains stable and is not significantly affected by magmatic heat flow or other short-term factors, so the pressure is in a normal state.

[0036] When the non - linear fitting curve of the pressure rise per unit time and the crust temperature change shows a trend of instantaneous sharp increase followed by a rapid decline, and the pressure also drops rapidly, this usually indicates that the fluid pressure in the current crustal fracture is in a state of transient local gas pressure rise, rather than a continuous pressure accumulation caused by magma ascent. The main reason is that the transient local gas pressure rise is usually caused by the heating of the fluid in the fracture by the magma heat flow. When the local water body or dissolved gas is heated, gas - liquid phase change occurs, resulting in a sharp increase in pressure within an extremely short time. However, since this phase change is limited to a local area and the magma itself does not rise massively or continuously release pressure, once the heat diffuses and the gas redissolves or escapes, the pressure drops rapidly, forming a high - pressure peak within a short time, but the overall trend does not show continuous growth. If the pressure increase is caused by magma ascent, it usually shows a long - term stable high pressure or a slowly increasing pressure curve, rather than a rapid decline. Therefore, when both the pressure - temperature non - linear fitting curve and the pressure curve show an instantaneous sharp increase but a rapid recovery, it indicates that this pressure change is dominated by transient heat conduction and gas expansion effects, rather than a long - term pressure accumulation caused by deep magma movement, belonging to a transient local phenomenon.

[0037] The specific steps to generate the thermosensitive compression reference value by analyzing the non - linear fitting of the pressure rise per unit time and the crust temperature change under the detection window are as follows: First, construct a function that describes the non - linear interaction between the pressure change rate and the crust temperature change to reflect the true state of the fluid pressure in the crustal fracture being thermosensitively compressed, expressed as follows: , where is the non - linear coupling function, used to measure the pressure change rate per unit time and the crust temperature change to judge whether the fluid pressure in the current crustal fracture is in a state of transient local gas pressure rise, is the non - linear amplification coefficient, controlling the amplification intensity of the exponential function, used to enhance the influence of smaller changes on the overall exponent, so that even a weak thermosensitive compression effect can be significantly amplified during the calculation process, is the pressure - temperature change power exponent, controlling the power influence of so that small - range pressure - temperature changes can show a non - linear amplification effect, improving the sensitivity to local subtle perturbations, is the reference baseline correction factor, used to provide a fixed baseline value to prevent the denominator from approaching zero, and at the same time used to adjust the calculation benchmark of the exponent to make it more in line with the background pressure - temperature relationship of the geological environment, is the temperature sensitivity adjustment factor, adjusting The degree of influence on the overall calculation result of the formula determines the contribution of temperature change to the exponential value. is a high-order nonlinear adjustment exponent, which determines the high-order nonlinear contribution in the denominator, enabling the pressure-temperature changes in different regions to affect the overall exponent calculation in different ways. is the rate of pressure change, is the fluid pressure, is the crustal temperature; Substitute the result of the nonlinear coupling function into the adaptive nonlinear enhancement formula to generate a thermosensitive compression reference value to amplify the characteristic signal difference of a transient local pressure rise. The calculation expression is as follows: , where, is the thermosensitive compression reference value, is the nonlinear exponential amplification parameter, used to control the sensitivity during small-amplitude changes, is the enhancement balance parameter, used to balance the two nonlinear exponential terms and prevent one of them from overly dominating the calculation result. is the nonlinear enhancement adjustment parameter, used to adjust the response mode during large-range changes, is the baseline suppression parameter, used to suppress background noise, ensure that the denominator of the exponent does not approach zero, and prevent the calculation result from being abnormally amplified. is the sine amplitude adjustment parameter, which controls the amplification degree of the sine function term, ensures a moderate adjustment range of the denominator, and avoids nonlinear distortion of the calculation result. is the periodic interference regulation parameter, which affects the frequency response ability of the sine function and adjusts the sensitivity of the exponent to short-term periodic fluctuations.

[0038] The larger the thermosensitive compression reference value generated by analyzing the nonlinear fitting of the pressure rise per unit time and the crustal temperature change under the detection window, the more it indicates that the instantaneous change in pressure is mainly affected by geothermal anomaly heating rather than the continuous pressure accumulation driven by deep magma. This usually means that the fluid in the fracture is undergoing a transient gas-liquid phase change or thermal expansion, resulting in a transient local pressure rise without long-term accumulation effect. Therefore, a larger thermosensitive compression reference value indicates that the pressure rise is a local transient phenomenon induced by the heat conduction effect, which conforms to the characteristics of a transient local gas pressure rise. On the contrary, when the thermosensitive compression reference value is small, it indicates that the change trend of the fluid pressure is relatively stable, not significantly affected by thermal expansion, and the pressure in the fracture is still within the normal range without any abnormality.

[0039] The intelligent evaluation and deep learning analysis module inputs the quantified key features as feature vectors into a pre-trained deep learning model. The deep learning model determines whether the current pressure increase belongs to a transient local gas pressure increase based on its learning from historical data. Input the quantified microseismic-pressure synchronization reference value and thermosensitive compression reference value as feature vectors into a pre-trained deep learning model. Generate a pressure fluctuation anomaly coefficient through the deep learning model, and use the pressure fluctuation anomaly coefficient to intelligently evaluate the fluid pressure in the current crustal fracture to determine whether the current pressure increase belongs to a transient local gas pressure increase.

[0040] The pre-trained deep learning model refers to a neural network model that has been trained with a large amount of historical data and can autonomously identify the change patterns of crustal fracture fluid pressure, and is used to judge whether the current pressure increase belongs to a transient local gas pressure increase. This model is usually trained based on supervised learning or semi-supervised learning. With the support of a large amount of crustal pressure data, microseismic activity data, temperature change data, and other geological parameter data, the deep learning model will automatically learn the characteristic patterns of different types of pressure changes. For example, during the model training stage, researchers will input a large amount of known pressure data and label whether it belongs to a transient local gas pressure increase, long-term pressure accumulation caused by magmatic activity, fracture expansion effect, or other geological phenomena. Through feature extraction, pattern recognition, and time series analysis of a multi-layer neural network, the model can capture the laws of different types of pressure changes and form a highly generalized discrimination ability. Long Short-Term Memory (LSTM) or Recurrent Neural Network (RNN) may be used during model training because these models can process time series data and learn the dynamic trends of pressure changes, rather than just static data points. In addition, during the model optimization process, methods such as Stochastic Gradient Descent (SGD, Adam), Bayesian optimization, etc. may be adopted to improve the prediction accuracy and prevent overfitting, so that it can be applied to different crustal environments and volcanic systems.

[0041] In practical applications, a pre-trained deep learning model can accept the quantized microseismic-pressure synchronization reference value and the thermosensitive compression reference value as inputs, and based on these feature vectors, calculate the pressure fluctuation anomaly coefficient to quantify the anomaly degree of the current pressure change. This coefficient reflects whether the current pressure increase belongs to a short-term local gas pressure increase or a more long-term and dangerous magma pressure accumulation. For example, if the deep learning model detects a high synchronization between microseismic activity and pressure change, but the pressure fluctuation recovery time is short, then the model will classify it as a short-term local gas disturbance and give a lower pressure fluctuation anomaly coefficient. On the contrary, if the model finds that the pressure continues to accumulate and the microseismic-pressure synchronization reference value shows a long-term stable increase, it may indicate that magma is rising. The model will calculate a higher pressure fluctuation anomaly coefficient and may trigger further volcanic warnings. In addition, the model can also perform multi-modal fusion analysis by combining other geological monitoring data (such as volcanic gas emissions, surface deformation data) to further improve the accuracy of intelligent evaluation. In this way, the pre-trained deep learning model can not only reduce false alarms caused by short-term local pressure increases, but also effectively improve the early warning ability of volcanic monitoring, providing more scientific and accurate data support for geological disaster prediction and prevention and control.

[0042] The deep learning model is not limited here. Any deep learning model that can synthesize and analyze the microseismic-pressure synchronization reference value and the thermosensitive compression reference value to generate the pressure fluctuation anomaly coefficient is acceptable. To implement the technical solution of the present invention, the present invention provides a specific implementation method; The pressure fluctuation anomaly coefficient is generated according to the following formula: , where, and are respectively the preset proportional coefficients of the microseismic-pressure synchronization reference value and the thermosensitive compression reference value , and and are both greater than 0.

[0043] The preset proportional coefficient (Preset Proportional Coefficient) in this formula refers to and these two parameters used to adjust (the microseismic-pressure synchronization reference value) and (the thermosensitive compression reference value) on the final (pressure fluctuation anomaly coefficient). Their role is to provide weight control during the PFA calculation process to ensure and Participate in the calculation according to an appropriate ratio during comprehensive analysis, so as to optimize the prediction ability of the deep learning model.

[0044] Specifically, and are preset values, usually determined based on historical data analysis, geological environment characteristics, and experimental verification. Their values determine and 's contribution degree to the calculation. For example: If is larger, it indicates that in the calculation, the influence of is relatively weak, and the system is more inclined to rely on for anomaly detection.

[0045] If is larger, it means that 's influence is weak, while mainly relies on for calculation.

[0046] By adjusting these two parameters, it is possible to adapt to the monitoring requirements under different volcanoes or geological environments, enabling the model to more accurately distinguish between short-term local gas pressure increases and long-term magma pressure accumulations.

[0047] Therefore, the core role of the preset proportional coefficient is to ensure the rationality and applicability of different characteristic parameters in pressure anomaly detection, enabling to flexibly adjust the calculation method under different circumstances and improve the accuracy and stability of the monitoring system From the pressure fluctuation anomaly coefficient, the larger the microseismic-pressure synchronization reference value generated by analyzing the time correlation between microseismic activities in the crust fracture area and fluid pressure changes under the detection window, and the larger the thermosensitive compression reference value generated by analyzing the non-linear fitting of pressure rise per unit time and crust temperature changes under the detection window, the larger the pressure fluctuation anomaly coefficient generated when the fluid pressure in the current crust fracture is intelligently evaluated by a pre-trained deep learning model, indicating that the fluid pressure in the current crust fracture is in a short-term local gas pressure rise. Conversely, it means that the change trend of the fluid pressure is relatively stable, not significantly affected by thermal expansion, and the pressure in the fracture is still within the normal range.

[0048] Compare and analyze the pressure fluctuation anomaly coefficient generated when the fluid pressure in the current crust fracture is intelligently evaluated by a pre-trained deep learning model with the preset pressure fluctuation anomaly coefficient reference threshold to classify the current abnormal pressure change. The classification steps are as follows: If the pressure fluctuation anomaly coefficient is greater than the reference threshold of the pressure fluctuation anomaly coefficient, the current pressure rise is classified as a transient local gas pressure rise; if the pressure fluctuation anomaly coefficient is less than or equal to the reference threshold of the pressure fluctuation anomaly coefficient, the current pressure change is classified as a normal change.

[0049] The dynamic adaptive monitoring and control module, when the deep learning model determines that the current pressure change is only a transient local rise, automatically reduces the detection threshold, broadens the capture range of minute pressure fluctuations, and simultaneously increases the pressure detection frequency to refine the time scale of pressure evolution. When the deep learning model determines that the current pressure change is only a transient local rise, the specific steps to automatically reduce the detection threshold and simultaneously increase the pressure detection frequency are as follows: When the deep learning model determines that the current pressure fluctuation belongs to a transient local anomaly, it dynamically reduces the detection threshold to enhance the perception ability of minute pressure fluctuations, so as to more sensitively capture minute pressure changes. The detection threshold adjustment formula is as follows: , where is the adjusted detection threshold, that is, the adjusted fluid pressure detection sensitivity, is the preset fluid pressure anomaly detection threshold, is the threshold sensitivity coefficient, and the value range is , which controls the threshold decline amplitude, is the reference threshold of the pressure fluctuation anomaly coefficient, is the anomaly intensity index, which controls the influence of the pressure fluctuation anomaly coefficient on the threshold adjustment, is the reference normalization index, which controls the normalization influence of the reference threshold of the pressure fluctuation anomaly coefficient in the threshold adjustment to ensure that abnormal fluctuations at different levels are reasonably amplified or reduced, is a very small positive number to prevent the denominator from approaching zero in value and ensure calculation stability, is the pressure change rate adjustment factor, which controls the contribution of the historical trend to the threshold adjustment, is the gradient of the pressure change with space, representing the unevenness of the local fracture fluid pressure. If the gradient is large, it indicates abnormal pressure distribution in the area, and the threshold is appropriately reduced to enhance the monitoring ability, is the non - linear adjustment index, which is used to enhance the influence of the local pressure change rate; The function of the above steps is to dynamically reduce the detection threshold to improve the system's sensitivity to minute pressure fluctuations, enabling it to accurately capture transient local anomalies and ensuring that potential crustal activity signals are not missed. When the pressure fluctuation anomaly coefficient exceeds the set reference threshold When an anomaly occurs, the system adaptively reduces the detection threshold according to the degree of anomaly, thereby broadening the pressure monitoring range so that even subtle pressure changes can be recognized and further analyzed.

[0050] After adjusting the detection threshold, the detection frequency is synchronously increased to ensure that the dynamic evolution process of pressure changes can be accurately tracked. The adjustment formula for the detection frequency is as follows: , where is the adjusted pressure detection frequency, is the detection frequency before adjustment, is the detection frequency adjustment coefficient, which controls the amplitude of the increase in the detection frequency, , and are both exponential adjustment factors, used to adjust the influence degree of the pressure fluctuation anomaly coefficient in the calculation. Usually, it is greater than 1 to enhance the influence in high-anomaly situations, used to adjust the influence degree of the reference threshold of the pressure fluctuation anomaly coefficient in the calculation. Usually, it is less than to avoid too rapid frequency changes in low-anomaly situations, The spatial second-order pressure gradient adjustment factor controls the sampling density in the high-order pressure mutation region, is the second-order spatial derivative of pressure, indicating the degree of rapid change in the local pressure field. If the second-order gradient is high, it indicates that the pressure changes rapidly in this region, and the sampling frequency needs to be increased to obtain more refined data, is the high-order gradient influence index, which adjusts the influence of local abnormal pressure changes on the detection frequency, is the temperature compensation term, is the temperature adjustment coefficient, which controls the contribution of temperature influence to the sampling frequency. Usually, it is taken between 0.1 and 1, is the natural base, is the temperature decay factor, which controls the exponential decay rate of temperature influence. Usually, it is taken between 0.01 and 0.1, is the current temperature of the crustal crack.

[0051] The above steps dynamically increase the pressure detection frequency to ensure that finer pressure change trends can be captured in a short time, avoiding missing key data due to too long sampling intervals.

[0052] When the deep learning model determines that the current pressure change is only a short-term local increase, the system will automatically lower the detection threshold to enhance the ability to capture minor pressure fluctuations and increase the pressure detection frequency, thereby refining the time scale of pressure evolution. The core function of this step is to enhance the system's sensitivity to the dynamic changes in fluid pressure, ensuring that even the slightest pressure fluctuations can be monitored. Through higher-frequency data collection, a more complete pressure change trend graph can be constructed to accurately distinguish short-term fluctuations from long-term trends and improve the reliability of volcanic activity prediction.

[0053] First of all, lowering the detection threshold can broaden the system's perception range of pressure changes, enabling fluctuations smaller than the original threshold to be detected and ensuring that potential weak precursor signals are not missed. If the pressure returns to normal in a short time, the system can automatically callback the threshold to maintain monitoring stability. Secondly, increasing the pressure detection frequency means that the system collects more samples in a short time, making the time series of pressure data more continuous and avoiding information loss caused by low-frequency monitoring. High-frequency detection makes key features such as the peak value, duration, and recovery time of short-term fluctuations clearer, thus better distinguishing the true signals of short-term gas disturbances from deep magma activities.

[0054] In addition, this step can also optimize the system's dynamic response ability. If subsequent pressure data still shows short-term local fluctuations, the system can continue to maintain a lower detection threshold and a higher detection frequency. However, if the pressure rising trend continues and even breaks through a higher threshold, the system will automatically adjust to a higher-level monitoring mode and conduct a more in-depth assessment by combining multi-dimensional data such as seismic, crustal deformation, and gas composition to determine whether a volcanic eruption warning needs to be issued.

[0055] Through this dynamic adjustment mechanism, the system can effectively reduce the false alarm rate, avoid unnecessary alarms caused by short-term local pressure increases, and at the same time accurately capture potential volcanic activity trends, ensuring that when real volcanic activities occur, the warning system can respond in a timely manner and reduce the losses caused by disasters.

[0056] The present invention effectively solves the problems of false alarms and missed alarms that may be caused by traditional fixed threshold detection methods by combining deep learning intelligent analysis with dynamic threshold adjustment. Through technical means such as continuous pressure detection, data preprocessing, key feature extraction, intelligent identification and dynamic adjustment, the scheme can intelligently distinguish short-term pressure fluctuations caused by magma heat flow from real precursors of magma rise when the local gas pressure rises briefly. When the system detects a short-term local pressure change, it automatically lowers the detection threshold and increases the sampling frequency, further refining the time scale of pressure evolution, thereby forming a more complete pressure change trajectory. This not only improves the sensitivity to tiny pressure fluctuations, but also ensures timely warning when there is real danger while preventing false alarms, greatly improving the accuracy and reliability of volcano monitoring. The intelligent and adaptive characteristics of the present invention enable it to adapt to different geological environments, improve the system's anti-interference ability and data analysis accuracy, and provide more scientific and efficient technical support for volcanic disaster warning and geological safety monitoring.

[0057] In an experiment simulating volcanic activity, the high-precision anti-interference pressure transmitter recorded the following key data at the crustal fracture monitoring point: at T = 0min, the initial fluid pressure stabilized at 3.2MPa, and then quickly rose to 4.8MPa within T = 5min. At the same time, the microseismic-pressure synchronization reference value is 0.25, indicating that the correlation between microseismicity and pressure change is low, while the thermal compression reference value As high as 0.87, indicating that pressure fluctuations are mainly affected by thermal expansion. Further analysis of the pressure recovery showed that at T=10min, the pressure dropped to 3.5MPa, and the recovery rate reached 0.13MPa / min. The deep learning model determined that this pressure fluctuation was a short-term local gas pressure increase, so the system lowered the detection threshold to 2.8MPa and increased the sampling frequency to once every 30 seconds to track subsequent changes more finely, ultimately avoiding false alarms caused by short-term gas disturbances, while continuously monitoring the evolution trajectory of fracture pressure to ensure accurate identification of true precursors of volcanic activity.

[0058] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0059] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0060] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0061] It should be understood that in various embodiments of the present application, the magnitude of the serial numbers of the above processes does not imply the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0062] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0063] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0064] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0065] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0066] As described above, this is only the specific implementation manner of the present application. However, the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims described above.

[0067] Only some exemplary embodiments of the present invention have been described above by way of illustration. Without doubt, for those of ordinary skill in the art, the described embodiments can be modified in various different ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the protection scope of the claims of the present invention.

Claims

1. A high-precision anti-interference pressure transmitter, characterized in that: It includes pressure data acquisition module, data preprocessing and integration module, pressure fluctuation feature extraction and quantification module, intelligent evaluation and deep learning analysis module and dynamic adaptive monitoring and control module: In the pressure data acquisition module, the pressure transmitter first continuously detects the fluid pressure in the crustal fracture according to the preset initial detection threshold. The recorded and collected pressure data will serve as the basis for all subsequent analyses; The data preprocessing and integration module integrates the real-time fluid pressure data collected by the high-precision anti-interference pressure transmitter according to the time sequence and spatial position to form a systematic data set, and preprocesses the pressure data in the data set; The pressure fluctuation feature extraction and quantification module mines the key features associated with the short-term local gas pressure rise from the preprocessed data, analyzes and processes the mined key features under the detection window, and quantifies the current pressure fluctuation abnormality; The intelligent evaluation and deep learning analysis module inputs the quantified key features as feature vectors into the pre-learned deep learning model. The deep learning model determines whether the pressure rise at this time is a short-term local gas pressure rise based on its learning on historical data; The dynamic adaptive monitoring and control module automatically lowers the detection threshold when the deep learning model determines that the current pressure change is only a short-term local rise, broadens the range of capturing tiny pressure fluctuations, and at the same time increases the pressure detection frequency and refines the time scale of pressure evolution.

2. A high-precision anti-interference pressure transmitter according to claim 1, characterized in that: The specific steps for the pressure transmitter to continuously detect the fluid pressure in the crustal cracks according to the preset initial detection threshold are as follows: First, the high-precision anti-interference pressure transmitter is activated according to the set initial threshold, and the pressure data collection function is simultaneously turned on at multiple monitoring points in the crustal cracks; Then, the transmitter senses the pressure of the fluid in the crack in real time through its highly sensitive sensor and converts the pressure signal into an electrical signal or a digital signal; It is then continuously recorded into the monitoring database via a data transmission system; At the same time, the data is time-stamped to ensure that each pressure value has an accurate timestamp for subsequent analysis.

3. A high-precision anti-interference pressure transmitter according to claim 1, characterized in that: Key features associated with short-term local gas pressure rise are mined from the preprocessed data. The mined features include the time correlation between microseismic activity in the crustal fracture area and fluid pressure changes, and the nonlinear fitting of pressure rise and crustal temperature changes per unit time. The time correlation between microseismic activity in the crustal fracture area and fluid pressure changes, and the nonlinear fitting of pressure rise and crustal temperature changes per unit time are analyzed under the detection window, and microseismic-pressure synchronization reference values ​​and thermal compression reference values ​​are generated respectively. The current degree of pressure fluctuation abnormality is quantified by the microseismic-pressure synchronization reference values ​​and the thermal compression reference values.

4. A high-precision anti-interference pressure transmitter according to claim 3, characterized in that: The specific steps of analyzing the time correlation between microseismic activity and fluid pressure changes in the crustal fracture area under the detection window to generate microseismic-pressure synchronization reference values ​​are as follows: First, the time series of microseismic events and fluid pressure changes are constructed and time aligned to ensure comparison within the same detection window. Since microseismic waves diffuse in space and affect fluid pressure, it is necessary to define a time alignment function to quantify the impact of microseismic events on fluid pressure and serve as the basis for subsequent calculations. The calculation expression is as follows: , where is the microseismic-pressure time-aligned coupling, is the instantaneous fluid pressure, indicating the spatial position The fluid pressure value at is the amount of microseismic energy released, expressed in terms of spatial position The energy released by the microseismic event is is the spatial distance from the earthquake source to the measuring point, is the spatial attenuation weight, is the natural base, is the spatial attenuation factor, is the integral area, representing the entire monitoring area, including the spatial locations of all pressure monitoring points A collection of; Since microseismicity causes changes in fluid pressure, the process is accompanied by a propagation time delay, so it is necessary to further calculate the degree of matching in spatial propagation. To this end, a propagation rate matching function is defined to analyze how the energy released by microseismic activity propagates in space and to determine whether the fluid pressure change conforms to the propagation mode. The calculation expression is as follows: , where is the matching degree of microseismic-pressure propagation rate, is the gradient field of fluid pressure, is the second-order spatial derivative of the microseismic energy, is a very small positive number, is the propagation rate matching adjustment factor, is the natural base, is the difference in wave velocity in the local area, is the propagation rate matching adjustment factor, is the exponential adjustment parameter of the pressure gradient, is the exponential adjustment parameter of the second-order derivative of microseismic energy release; Comprehensive microseismic-pressure time alignment coupling and microseismic-pressure propagation rate matching function , generate a microseismic-pressure synchronization reference value to ultimately quantify the temporal correlation between microseismic activity and fluid pressure changes. The calculation expression is as follows: , where is the microseismic-pressure synchronization reference value, is the time decay factor, which measures the peak time of microseismic events Fluid pressure peak time The time difference between is the time synchronization control parameter, is the peak time of the microseismic event, is the peak time of fluid pressure change, is the smoothing factor.

5. The high-precision anti-interference pressure transmitter according to claim 3 is characterized in that: The specific steps of analyzing the nonlinear fitting of the pressure rise per unit time and the crust temperature change under the detection window to generate the thermosensitive compression reference value are as follows: First, a function describing the nonlinear interaction between the pressure change rate and the crust temperature change is constructed to reflect the true state of the fluid pressure in the crustal cracks under thermal compression, which is expressed as follows: , where is the nonlinear coupling function, is the nonlinear amplification factor, is the pressure-temperature variation power exponent, is the reference baseline correction factor, is the temperature sensitivity adjustment factor, is the high-order nonlinear adjustment exponent, is the rate of change of pressure, is the fluid pressure, is the crust temperature; Will Nonlinear coupling function results Substitute it into the adaptive nonlinear enhancement formula to generate a thermal compression reference value to amplify the characteristic signal difference of the transient local pressure rise. The calculation expression is as follows: , where is the thermal compression reference value, is the nonlinear exponential amplification parameter, is the enhanced balance parameter, is the nonlinear enhancement adjustment parameter, is the baseline suppression parameter, is the sine amplitude adjustment parameter, is the periodic interference control parameter.

6. A high-precision anti-interference pressure transmitter according to claim 3, characterized in that: The quantized microseismic-pressure synchronization reference value and the thermal-sensitive compression reference value are input as feature vectors into the pre-learned deep learning model. The pressure fluctuation anomaly coefficient is generated by the deep learning model. The fluid pressure in the current crustal cracks is intelligently evaluated by the pressure fluctuation anomaly coefficient to determine whether the pressure rise at this time is a short-term local gas pressure rise.

7. A high-precision anti-interference pressure transmitter according to claim 6, characterized in that: The pressure fluctuation anomaly coefficient generated by the intelligent evaluation of the fluid pressure in the current crustal fractures by the pre-learned deep learning model is compared and analyzed with the pre-set pressure fluctuation anomaly coefficient reference threshold, and the current abnormal pressure changes are divided. The division steps are as follows: If the pressure fluctuation anomaly coefficient is greater than the pressure fluctuation anomaly coefficient reference threshold, the current pressure rise is classified as a short-term local gas pressure rise; if the pressure fluctuation anomaly coefficient is less than or equal to the pressure fluctuation anomaly coefficient reference threshold, the current pressure change is classified as a normal change.

8. A high-precision anti-interference pressure transmitter according to claim 7, characterized in that: When the deep learning model determines that the current pressure change is only a short-term local increase, the specific steps to automatically lower the detection threshold and increase the pressure detection frequency are as follows: When the deep learning model determines that the current pressure fluctuation is a short-term local anomaly, the detection threshold is dynamically lowered to enhance the perception of small pressure fluctuations. The detection threshold adjustment formula is as follows: , where is the adjusted detection threshold, is the preset fluid pressure abnormality detection threshold, is the threshold sensitivity coefficient, is the reference threshold of the pressure fluctuation anomaly coefficient, is the anomaly intensity index, is the benchmark normalized index, is a very small positive number, is the pressure change rate adjustment factor, is the gradient of pressure over space, is a nonlinear adjustment index used to enhance the effect of the local pressure change rate; After adjusting the detection threshold, the detection frequency is increased synchronously to ensure that the dynamic evolution of pressure changes can be accurately tracked. The adjustment formula for the detection frequency is as follows; , where is the adjusted pressure detection frequency, is the detection frequency before adjustment, is the detection frequency adjustment coefficient, and are index adjustment factors, Used to adjust the pressure fluctuation abnormal coefficient The degree of influence in the calculation, Used to adjust the reference threshold of the pressure fluctuation abnormal coefficient The degree of influence in the calculation, Spatial second-order pressure gradient adjustment factor, is the second-order spatial derivative of pressure, is the high-order gradient influence index, is the temperature compensation term, is the temperature regulation coefficient, is the natural base, is the temperature attenuation factor, is the current crustal fracture temperature.

Images