Intelligent core barrel content state monitoring system and method based on intelligent sensing

Abstract

The invention discloses an intelligent core barrel content state monitoring system and method based on intelligent sensing, and relates to the technical field of intelligent sensing, and the method comprises the steps: deploying a sensor array in an intelligent core barrel; when it is detected that the liquid height change rate, the barrel bottom pressure change rate or the liquid mass change rate exceed a preset trigger threshold value, monitoring data of all sensors are collected and transmitted to an edge computing terminal; based on the collected data, verifying the data accuracy through a physical association relationship; when the verification result shows that the data is inaccurate, the working weight of each sensor is dynamically adjusted according to the environmental parameters; when the physical rationality verification result does not meet the preset requirement, sensor optimization configuration is automatically executed; and performing credibility grading on the data according to the final verification result, and performing grading processing according to the credibility grade. Through a cross validation mechanism, the data consistency is verified in combination with the physical association relationship, and the credibility of the monitoring data is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent sensing technology, and in particular to a system and method for monitoring the status of contents in a smart barrel based on intelligent sensing. Background Art

[0002] In industrial logistics and hazardous chemical transportation, monitoring the contents of intelligent carrier drums is crucial for ensuring transportation safety. Traditional monitoring systems rely primarily on single sensors (such as level gauges or pressure sensors) for independent measurement, resulting in low data reliability and insufficient compensation for environmental interference.

[0003] In existing technologies, multi-sensor data fusion algorithms have been used to improve monitoring accuracy, but they rely on complex machine learning models, resulting in high computing resource consumption and poor model interpretability. Data verification methods based on weighted averages do not consider the coupling effects of changes in sensor dynamic performance and environmental parameters, and errors increase significantly under complex working conditions such as vibration and tilt. In addition, existing systems generally lack effective self-verification mechanisms. When sensors drift or fail, it is difficult to identify and correct erroneous data in a timely manner. In particular, in the case of changes in liquid density or phase change, the traditional volume-to-mass conversion method will produce systematic errors. Although attempts have been made to introduce environmental compensation coefficients, their fixed weight distribution mode cannot adapt to dynamic environmental changes during transportation. These technical defects have led to the existing monitoring systems still having high false alarm rates and insufficient reliability in the transportation of sensitive materials such as chemical raw materials and liquid foods. Summary of the Invention

[0004] The purpose of the present invention is to provide a system and method for monitoring the status of contents in a smart barrel based on intelligent sensing to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a method for monitoring the contents status of a smart barrel based on intelligent sensing, the method comprising: A sensor array is deployed in the iCore barrel; the sensor array includes a barrel bottom pressure sensor, an environmental monitoring sensor, a quality sensor, and a liquid height sensor; When the rate of change of liquid height, barrel bottom pressure or liquid mass exceeds the preset trigger threshold, the monitoring data of each sensor is collected and transmitted to the edge computing terminal; Based on the bottom pressure data, liquid mass data, liquid height data, pre-stored liquid density parameters, and the internal bottom area parameters of the smart core barrel, the accuracy of the bottom pressure data, liquid mass data, and liquid height data is verified through physical correlation. When the verification results show that the data is inaccurate, the working weight of each sensor is dynamically adjusted according to the environmental parameters, the data is re-collected and the physical correlation verification is performed; when the physical rationality verification results do not meet the preset requirements, the sensor optimization configuration is automatically executed; The data is graded for credibility based on the final verification results, and graded according to the credibility level to generate a data package containing sensor combination information, environmental compensation parameters and data quality identification.

[0006] According to the above scheme, the pressure sensor collects the bottom pressure data and the bottom pressure change rate data; the mass sensor collects the liquid mass data and the liquid mass change rate data; the liquid height sensor collects the liquid height data and the liquid height change rate data; the environmental monitoring sensor includes a temperature sensor, a vibration sensor and a tilt sensor, the temperature sensor collects the ambient temperature data, the vibration sensor collects the vibration intensity data, and the tilt sensor collects the tilt angle data; When it is detected that the liquid height change rate, the barrel bottom pressure change rate or the liquid mass change rate exceeds the preset trigger threshold, the data collection instruction is automatically started, and the collection instruction is sent to the pressure sensor, environmental monitoring sensor, quality sensor and liquid height sensor at the same time; the pressure sensor responds to the instruction, outputs the current barrel bottom pressure data and the historical barrel bottom pressure data; the quality sensor responds to the instruction, outputs the current liquid mass data and the historical liquid mass data; the liquid height sensor responds to the instruction, outputs the current liquid height data and the historical liquid height data; the environmental monitoring sensor responds to the instruction, outputs the current ambient temperature data, vibration intensity data and tilt angle data; Each sensor encapsulates the collected monitoring data in the data frame format of the preset communication protocol and transmits it to the edge computing terminal; after receiving the data, the edge computing terminal performs data integrity verification and timestamp alignment.

[0007] According to the above scheme, the accuracy of the barrel bottom pressure data, liquid mass data, and liquid height data is verified through physical association, including: Based on the liquid height data h and liquid density ρ, the theoretical pressure value at the bottom of the barrel is obtained using the following formula: P l =ρ×g×h; Among them, P l It is expressed as the theoretical pressure value at the bottom of the barrel; g is the acceleration due to gravity; The bottom pressure data P collected by the pressure sensor s The theoretical pressure value P at the bottom of the barrel l Make a comparison; Based on the liquid height data h, the internal bottom area S of the smart core barrel, and the liquid density ρ, the theoretical mass of the liquid is calculated using the following formula: m l =ρ×S×h; Among them, m l Expressed as the theoretical mass value of liquid; The liquid mass data m collected by the mass sensor s and the theoretical mass of the liquid m l Make a comparison; Based on liquid mass data m s , liquid density ρ and the internal bottom area S of the smart core barrel, calculate the theoretical height of the liquid using the following formula: h l =m s / (ρ×S); Among them, h l Expressed as the theoretical height of liquid; The liquid height data h collected by the liquid height sensor s and the theoretical height of the liquid h l Make a comparison.

[0008] According to the above scheme, calculate the deviation rate of the barrel bottom pressure data δP=|P s -P l | / P l ×100%, the deviation rate of liquid mass data δm=|m s -m l | / m l ×100%, the deviation rate of liquid height data δh=|h s -h l | / h l ×100%; Preset pressure deviation threshold δP0, mass deviation threshold δm0 and height deviation threshold δh0; The pressure, mass, and height parameters are set independently. The pressure deviation threshold δP0 is determined by the rated working pressure range of the smart core tank and the measurement accuracy level of the pressure sensor. The mass deviation threshold δm0 is determined by the rated mass range of the contents and the range error range of the mass sensor. The height deviation threshold δh0 is determined by the internal height of the smart core tank and the resolution parameter of the liquid height sensor. When δP≤δP0, δm≤δm0 and δh≤δh0, the barrel bottom pressure data, liquid mass data and liquid height data are judged to be accurate; when any deviation rate exceeds the corresponding threshold, the corresponding data is judged to be inaccurate.

[0009] According to the above scheme, environmental parameters include ambient temperature data, vibration intensity data, and tilt angle data; the real-time credibility coefficient of each sensor is calculated based on the environmental parameters, and a sensor weight distribution model is established; Based on the credibility coefficient, dynamic weight values ​​are assigned to the pressure sensor, mass sensor and liquid height sensor respectively, among which the sensors that are more affected by the environment are assigned lower weights; The adjusted working weight of the pressure sensor is as follows: Wp=Wp0×(1-Kt p ×Dt-Kv p ×Dv-Kθ p ×Dθ); Where Wp0 represents the initial working weight of the pressure sensor; Kt p It is the influence coefficient of ambient temperature on pressure sensor; Dt is the ambient temperature deviation; Kv p It is expressed as the influence coefficient of vibration intensity on pressure sensor; Dv is expressed as the deviation of vibration intensity; Kθ p It is expressed as the influence coefficient of the tilt angle on the pressure sensor; Dθ is expressed as the deviation of the tilt angle; The work weight after quality sensor adjustment is as follows: Wm=Wm0×(1-Kt m ×Dt-Kv m ×Dv-Kθ m ×Dθ); Where Wm0 represents the initial working weight of the mass sensor; Kt m Expressed as the influence coefficient of ambient temperature on the mass sensor; Kv m Expressed as the influence coefficient of vibration intensity on mass sensor; Kθ m Expressed as the influence coefficient of the tilt angle on the mass sensor; The adjusted working weight of the liquid height sensor is as follows: Wh=Wh0×(1-Kt h ×Dt-Kv h ×Dv-Kθ h ×Dθ); Where Wh0 represents the initial working weight of the liquid height sensor; Kt h Expressed as the influence coefficient of ambient temperature on liquid height sensor; Kv h Expressed as the influence coefficient of vibration intensity on liquid height sensor; Kθ h Expressed as the influence coefficient of the tilt angle on the liquid height sensor; The adjusted work weight must satisfy Wp≥0.1, Wm≥0.1, Wh≥0.1; if the calculated result is lower than the lower limit, the corresponding lower limit value shall be used; The ambient temperature reference value is the rated temperature for normal operation of the Smart Core Tank, determined based on the physical and chemical properties of the contents. The vibration intensity reference value is the inherent vibration intensity of the Smart Core Tank's installation environment, determined based on the smoothness requirements of equipment operation. The tilt angle reference value is the allowable horizontal installation error of the Smart Core Tank, determined based on the influence coefficient of the container structure on liquid level measurement. The edge computing terminal sends collection instructions to the corresponding sensors according to the adjusted work weights. The pressure sensor responds to the instructions to output the bottom pressure data of the barrel, the mass sensor responds to the instructions to output the liquid mass data, and the liquid height sensor responds to the instructions to output the liquid height data.

[0010] According to the above scheme, the edge computing terminal extracts the response characteristic parameters of each sensor during the physical rationality verification process. The response characteristic parameters include the stability of the data acquisition cycle, the signal transmission delay time, and the detection value fluctuation amplitude; Based on the response characteristic parameters, identify sensor abnormalities, including acquisition accuracy deviating from the standard range, response speed exceeding the preset threshold, and anti-interference ability falling below the benchmark level; Based on sensor abnormalities, the edge computing terminal sends parameter adjustment instructions to the corresponding sensors. Parameter adjustment instructions include adjusting sensor sampling frequency, modifying sensor operating mode, updating sensor calibration parameters, switching sensor data transmission channels, and reconfiguring sensor networking methods. After the parameter adjustment is completed, the edge computing terminal controls each sensor to restart the data collection process and simultaneously starts the environmental monitoring sensor to continuously monitor the adjusted working environment to ensure that the working environment of the sensor under the new parameter setting meets the preset conditions; When the results of three consecutive physical rationality verifications do not meet the preset requirements, the backup sensor switching mechanism is triggered; if there is no backup sensor to switch to, a fault alarm message is generated, including the abnormal sensor ID, historical adjustment records and current environmental parameters; The edge computing terminal stores the process information of sensor optimization configuration in the configuration log. The process information includes the response characteristic parameter record before parameter adjustment, the parameter adjustment instruction content, the response status of each sensor to the adjustment instruction, and the adjusted working environment parameters recorded by the environmental monitoring sensor.

[0011] According to the above scheme, a credibility grading model is constructed based on the physical rationality verification results, the parameter adjustment records after the sensor configuration optimization, and the environmental monitoring data. The credibility grading model includes data consistency index, sensor stability index, and environmental interference index. The comprehensive credibility score of the data is calculated by weighted summation. The formula is as follows: C=w1×A+w2×B+w3×E; Where C represents the comprehensive credibility score; w1 represents the weight coefficient of the data consistency index, w2 represents the weight coefficient of the sensor stability index, and w3 represents the weight coefficient of the environmental interference index; A represents the data consistency score, which is determined based on the comparison result of the data deviation rate and the preset threshold; B represents the sensor stability score, which is determined based on the fluctuation amplitude of the sensor response characteristic parameter; E represents the environmental interference score, which is determined based on the degree of deviation of the environmental parameter from the baseline value; For example: Temperature reference value: clearly based on the boiling point / freezing point of the contents or industry standards, such as 20±5°C for chemical storage tanks; Vibration reference value: references equipment installation specifications, such as ISO 10816-3's limits on mechanical vibration levels; Tilt reference value: specifies the engineering tolerance for horizontal container installation, such as ±0.5°; w1 is determined based on the weight of the impact of data deviation on subsequent applications; w2 is determined based on the contribution of the sensor's long-term working stability to system reliability; w3 is determined based on the proportion of the impact of environmental interference on measurement error; and w1+w2+w3=1; According to the value range of the comprehensive credibility score, the data credibility is divided into three levels: when the comprehensive credibility score is in the first preset range, it is determined to be level one credibility; when the comprehensive credibility score is in the second preset range, it is determined to be level two credibility; when the comprehensive credibility score is in the third preset range, it is determined to be level three credibility; The first preset interval is determined based on industry-level high-precision monitoring standards and the maximum allowable error of content measurement; the second preset interval is determined based on industrial-level routine monitoring requirements and the acceptable error range of content application; the third preset interval is determined based on the minimum accuracy requirements of basic monitoring scenarios; Level 1 credibility indicates that the data is highly consistent with the theoretical value, the sensor working state is stable, and the impact of environmental interference is small; level 2 credibility indicates that the data is basically consistent with the theoretical value, there are slight fluctuations in the sensor working state, and the impact of environmental interference is within an acceptable range; level 3 credibility indicates that there is a recognizable deviation between the data and the theoretical value, the sensor working state is generally stable, and the impact of environmental interference needs to be paid special attention.

[0012] According to the above scheme, for the first level of trustworthiness, the original collected values ​​are directly retained and marked as baseline data; for the second level of trustworthiness, the original data are corrected based on the environmental compensation algorithm, and the correction process refers to the temperature, vibration and tilt parameters recorded by the environmental monitoring sensor; for the third level of trustworthiness, additional deviation descriptions and correction suggestions are added, and the applicable scope of the data is marked.

[0013] According to the above scheme, the sensor combination information includes the model identification, deployment position code and working mode parameters of the currently activated pressure sensor, mass sensor and liquid height sensor; the environmental compensation parameters include the temperature compensation coefficient, vibration attenuation coefficient and tilt correction value; the data quality identification includes the credibility level identification, comprehensive credibility score, data collection period and sensor status code. The sensor status code is used to indicate the working stability of each sensor during the data collection process.

[0014] A smart core barrel content status monitoring system based on intelligent sensing, the system includes a data acquisition module, a data preprocessing module, a data verification module, a credibility grading module and a data output module; The data acquisition module includes a pressure sensor module, a mass sensor module, a liquid level sensor module and an environmental monitoring sensor module; the pressure sensor module is used to collect the bottom pressure data and the pressure change rate data; the mass sensor module is used to collect the liquid mass data and the mass change rate data; the liquid level sensor module is used to collect the liquid height data and the height change rate data; The data preprocessing module performs format verification on the raw data transmitted by the data acquisition module and aligns the data collected by different sensors at the same time according to a unified time base; The data verification module includes a cross-verification module, a weight adjustment module, and a configuration optimization module; the cross-verification module verifies the accuracy of the data collected by the data acquisition module through physical association relationships; the weight adjustment module calculates the real-time credibility coefficient of each sensor based on the data collected by the environmental sensing module and dynamically adjusts the working weight of the sensor; The credibility grading module evaluates the comprehensive credibility score based on data verification results, sensor optimization records, and environmental data, divides the data into different credibility levels, and performs differentiated processing on data of different credibility levels; The data output module integrates sensor combination information, environmental compensation parameters and data quality indicators to generate standardized data packets.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention uses a cross-validation mechanism of pressure, mass and liquid level sensors, combined with physical correlation to verify data consistency, solve the problem of single sensor measurement deviation, and improve the credibility of monitoring data; 2. The present invention dynamically adjusts the sensor working weight based on environmental parameters, reduces the impact of environmental interference on measurement, and ensures data stability under complex working conditions; 3. The present invention identifies anomalies through sensor response characteristic parameters and automatically adjusts the configuration, completing sensor optimization without human intervention and improving maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flowchart of a method for monitoring the contents status of a smart core barrel based on intelligent sensing in the present invention; Figure 2 The figure is a structural diagram of a smart core barrel content status monitoring system based on intelligent sensing in the present invention. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0018] Example: Figure 1-Figure 2 As shown, the present invention provides a technical solution, a method for monitoring the status of contents in a smart core barrel based on intelligent sensing, the method comprising: A sensor array is deployed in the iCore barrel; the sensor array includes a barrel bottom pressure sensor, an environmental monitoring sensor, a quality sensor, and a liquid height sensor; Specifically, the pressure sensor collects the bottom pressure data and the bottom pressure change rate data; the mass sensor collects the liquid mass data and the liquid mass change rate data; the liquid height sensor collects the liquid height data and the liquid height change rate data; the environmental monitoring sensor includes a temperature sensor, a vibration sensor and a tilt sensor. The temperature sensor collects the ambient temperature data, the vibration sensor collects the vibration intensity data, and the tilt sensor collects the tilt angle data. For example: barrel bottom pressure data: 22.5kPa; barrel bottom pressure change rate data: 0.25kPa / s; Liquid mass data: 420kg; Liquid mass change rate data: 4kg / s; Liquid height data: 0.84m; Liquid height change rate data: 0.014m / s; Ambient temperature data: 32°C; vibration intensity data: 0.2g; tilt angle data: 1.2°; This is just an example, not a limitation. When the rate of change of liquid height, barrel bottom pressure or liquid mass exceeds the preset trigger threshold, the monitoring data of each sensor is collected and transmitted to the edge computing terminal; Specifically, when it is detected that the liquid height change rate, the barrel bottom pressure change rate or the liquid mass change rate exceeds the preset trigger threshold, the data collection instruction is automatically started, and the collection instruction is sent to the pressure sensor, environmental monitoring sensor, quality sensor and liquid height sensor at the same time; the pressure sensor responds to the instruction, outputs the barrel bottom pressure data and the historical barrel bottom pressure data at the current moment; the quality sensor responds to the instruction, outputs the liquid quality data and the historical liquid quality data at the current moment; the liquid height sensor responds to the instruction, outputs the liquid height data and the historical liquid height data at the current moment; the environmental monitoring sensor responds to the instruction, outputs the ambient temperature data, vibration intensity data and tilt angle data at the current moment; each sensor encapsulates the collected monitoring data according to the data frame format of the preset communication protocol and transmits it to the edge computing terminal; after receiving the data, the edge computing terminal performs data integrity verification and timestamp alignment processing.

[0019] Based on the bottom pressure data, liquid mass data, liquid height data, pre-stored liquid density parameters, and the internal bottom area parameters of the smart core barrel, the accuracy of the bottom pressure data, liquid mass data, and liquid height data is verified through physical correlation. Specifically, based on the liquid height data h and the liquid density ρ, the theoretical pressure value at the bottom of the barrel is obtained using the following formula: P l =ρ×g×h; Among them, P l It is expressed as the theoretical pressure value at the bottom of the barrel; g is the acceleration due to gravity; The bottom pressure data P collected by the pressure sensor s The theoretical pressure value P at the bottom of the barrel l Make a comparison; Based on the liquid height data h, the internal bottom area S of the smart core barrel, and the liquid density ρ, the theoretical mass of the liquid is calculated using the following formula: m l =ρ×S×h; Among them, m l Expressed as the theoretical mass value of liquid; The liquid mass data m collected by the mass sensor s and the theoretical mass of the liquid m l Make a comparison; Based on liquid mass data m s , liquid density ρ and the internal bottom area S of the smart core barrel, calculate the theoretical height of the liquid using the following formula: h l =m s / (ρ×S); Among them, h l Expressed as the theoretical height of liquid; The liquid height data h collected by the liquid height sensors and the theoretical height of the liquid h l Make a comparison.

[0020] For example: the storage density of the Zhixin barrel is 1000kg / m 3 The bottom area of ​​the smart core barrel is 0.5m 2 , rated working pressure range 0-30kPa, maximum flow rate 0.3m 3 / min; Theoretical pressure value at the bottom of the barrel: P l =ρ×g×h=1000×9.8×0.84=8.232kPa; Liquid theoretical mass value: m l =ρ×S×h=1000×0.5×0.84=420kg; Theoretical height of liquid: h l =m s / (ρ×S);=420 / (1000×0.5)=0.84m; Furthermore, the deviation rate of the bottom pressure data is calculated as δP=|P s -P l | / P l ×100%, the deviation rate of liquid mass data δm=|m s -m l | / m l ×100%, the deviation rate of liquid height data δh=|h s -h l | / h l ×100%; preset pressure deviation threshold δP0, mass deviation threshold δm0, and height deviation threshold δh0; independently set for pressure parameters, mass parameters, and height parameters, where the pressure deviation threshold δP0 is determined based on the rated working pressure range of the smart core barrel and the measurement accuracy level of the pressure sensor, the mass deviation threshold δm0 is determined based on the rated mass range of the contents and the range error range of the mass sensor, and the height deviation threshold δh0 is determined based on the internal height dimension of the smart core barrel and the resolution parameter of the liquid height sensor; when δP≤δP0, δm≤δm0, and δh≤δh0, the barrel bottom pressure data, liquid mass data, and liquid height data are determined to be accurate; when any deviation rate exceeds the corresponding threshold, the corresponding data is determined to be inaccurate; For example: Deviation threshold: δP0=0.5% (based on rated pressure 30kPa×0.5%, i.e. 0.15kPa); δm0=0.3% (based on maximum range 500kg×0.3%, i.e. 1.5kg); δh0=0.2% (based on maximum height 1.2m×0.2%, i.e. 0.24cm); Pressure deviation rate δP=|22.5-8.232| / 8.232×100%≈173%; Quality deviation rate δm=|420-420| / 420×100%=0%; Height deviation rate δh=|0.84-0.84| / 0.84×100%=0%; δP (173%) > δP0 (0.5%), which means the pressure data is inaccurate; When the verification results show that the data is inaccurate, the working weight of each sensor is dynamically adjusted according to the environmental parameters, the data is re-collected and the physical correlation verification is performed; when the physical rationality verification results do not meet the preset requirements, the sensor optimization configuration is automatically executed; Specifically, the environmental parameters include ambient temperature data, vibration intensity data, and tilt angle data; the real-time credibility coefficient of each sensor is calculated based on the environmental parameters, and a sensor weight distribution model is established; Based on the credibility coefficient, dynamic weight values ​​are assigned to the pressure sensor, mass sensor and liquid height sensor respectively, among which the sensors that are more affected by the environment are assigned lower weights; The adjusted working weight of the pressure sensor is as follows: Wp=Wp0×(1-Kt p ×Dt-Kv p ×Dv-Kθ p ×Dθ); Where Wp0 represents the initial working weight of the pressure sensor; Kt p It is the influence coefficient of ambient temperature on pressure sensor; Dt is the ambient temperature deviation; Kv p It is expressed as the influence coefficient of vibration intensity on pressure sensor; Dv is expressed as the deviation of vibration intensity; Kθ p It is expressed as the influence coefficient of the tilt angle on the pressure sensor; Dθ is expressed as the deviation of the tilt angle; The work weight after quality sensor adjustment is as follows: Wm=Wm0×(1-Kt m ×Dt-Kv m ×Dv-Kθ m ×Dθ); Where Wm0 represents the initial working weight of the mass sensor; Kt m Expressed as the influence coefficient of ambient temperature on the mass sensor; Kv m Expressed as the influence coefficient of vibration intensity on mass sensor; Kθ m Expressed as the influence coefficient of the tilt angle on the mass sensor; The adjusted working weight of the liquid height sensor is as follows: Wh=Wh0×(1-Kt h ×Dt-Kv h ×Dv-Kθ h ×Dθ); Where Wh0 represents the initial working weight of the liquid height sensor; Kt h Expressed as the influence coefficient of ambient temperature on liquid height sensor; Kv h Expressed as the influence coefficient of vibration intensity on liquid height sensor; Kθ h Expressed as the influence coefficient of the tilt angle on the liquid height sensor; The ambient temperature reference value is the rated temperature for normal operation of the Smart Core Tank, determined based on the physical and chemical properties of the contents. The vibration intensity reference value is the inherent vibration intensity of the Smart Core Tank's installation environment, determined based on the smoothness requirements of equipment operation. The tilt angle reference value is the allowable horizontal installation error of the Smart Core Tank, determined based on the influence coefficient of the container structure on liquid level measurement. For example: the ambient temperature reference value is 25°C, the current temperature is 32°C, Dt=|32-25| / 25=0.28; The vibration intensity baseline value is 0.1g, the current value is 0.2g, Dv=|0.2-0.1| / 0.1=1; The reference value of the tilt angle is 1°, the current value is 1.2°, Dθ=|1.2-1| / 1=0.2; The influence coefficient and weight are adjusted, and the preset initial weights are Wp0=0.4, Wm0=0.3, and Wh0=0.3; Pressure sensor adjusted working weight: Wp=0.4×(1-0.3×0.28-0.4×1-0.2×0.2)=0.4×0.46=0.184; Kt p =0.3, Kv p =0.4, Kθ p =0.2; Quality sensor adjusted workload weights: Wm=0.3×(1-0.1×0.28-0.2×1-0.1×0.2)=0.3×0.75=0.225; Kt m =0.1, Kv m =0.2, Kθ m =0.1; Adjusted working weight of liquid level sensor: Wh=0.3×(1-0.2×0.28-0.3×1-0.5×0.2)=0.3×0.59=0.177; Kt h =0.2, Kvh =0.3, Kθ h =0.5; After normalization: Wp'=0.184 / 0.586≈0.314; Wm'≈0.384; Wh'≈0.302; The edge computing terminal sends collection instructions to the corresponding sensors according to the adjusted work weights. The pressure sensor responds to the instructions to output the bottom pressure data of the barrel, the mass sensor responds to the instructions to output the liquid mass data, and the liquid height sensor responds to the instructions to output the liquid height data.

[0021] According to the above scheme, the edge computing terminal extracts the response characteristic parameters of each sensor during the physical rationality verification process. The response characteristic parameters include the stability of the data acquisition cycle, the signal transmission delay time, and the detection value fluctuation amplitude; Based on the response characteristic parameters, identify sensor abnormalities, including acquisition accuracy deviating from the standard range, response speed exceeding the preset threshold, and anti-interference ability falling below the benchmark level; Based on sensor abnormalities, the edge computing terminal sends parameter adjustment instructions to the corresponding sensors. Parameter adjustment instructions include adjusting sensor sampling frequency, modifying sensor operating mode, updating sensor calibration parameters, switching sensor data transmission channels, and reconfiguring sensor networking methods. After the parameter adjustment is completed, the edge computing terminal controls each sensor to restart the data collection process and simultaneously starts the environmental monitoring sensor to continuously monitor the adjusted working environment to ensure that the working environment of the sensor under the new parameter setting meets the preset conditions; The edge computing terminal stores the process information of sensor optimization configuration in the configuration log. The process information includes the response characteristic parameter record before parameter adjustment, the parameter adjustment instruction content, the response status of each sensor to the adjustment instruction, and the adjusted working environment parameters recorded by the environmental monitoring sensor.

[0022] The data is graded for credibility based on the final verification results, and graded according to the credibility level to generate a data package containing sensor combination information, environmental compensation parameters and data quality identification; Specifically, a credibility grading model is constructed based on the physical rationality verification results, the parameter adjustment records after the sensor configuration is optimized, and the environmental monitoring data. The credibility grading model includes data consistency indicators, sensor stability indicators, and environmental interference indicators. The comprehensive credibility score of the data is calculated through weighted summation. The formula is as follows: C=w1×A+w2×B+w3×E; Where C represents the comprehensive credibility score; w1 represents the weight coefficient of the data consistency index, w2 represents the weight coefficient of the sensor stability index, and w3 represents the weight coefficient of the environmental interference index; A represents the data consistency score, which is determined based on the comparison result of the data deviation rate and the preset threshold; B represents the sensor stability score, which is determined based on the fluctuation amplitude of the sensor response characteristic parameter; E represents the environmental interference score, which is determined based on the degree of deviation of the environmental parameter from the baseline value; w1 is determined based on the weight of the impact of data deviation on subsequent applications; w2 is determined based on the contribution of the sensor's long-term working stability to system reliability; w3 is determined based on the proportion of the impact of environmental interference on measurement error; and w1+w2+w3=1; For example: data consistency score A = 0.8; sensor stability score B = 0.7; environmental interference score E = 0.6; weight coefficients w1 = 0.5, w2 = 0.3, w3 = 0.2, C = 0.5 × 0.8 + 0.3 × 0.7 + 0.2 × 0.6 = 0.73; if it is in the second preset range (0.6-0.8], it is determined to be level 2 trustworthy; Furthermore, based on the value range of the comprehensive credibility score, the data credibility is divided into three levels: when the comprehensive credibility score is in the first preset interval, it is determined to be level one credibility; when the comprehensive credibility score is in the second preset interval, it is determined to be level two credibility; when the comprehensive credibility score is in the third preset interval, it is determined to be level three credibility; the first preset interval is determined based on the industry-level high-precision monitoring standards and the maximum allowable error of the content measurement; the second preset interval is determined based on the industrial-level routine monitoring requirements and the acceptable error range of the content application; the third preset interval is determined based on the minimum accuracy requirements of the basic monitoring scenario; For example: the first preset interval: (0.8, 1.0]; the second preset interval: (0.6-0.8]; the third preset interval: (0.3-0.6]; Level 1 credibility indicates that the data is highly consistent with the theoretical value, the sensor working state is stable, and the impact of environmental interference is small; level 2 credibility indicates that the data is basically consistent with the theoretical value, there are slight fluctuations in the sensor working state, and the impact of environmental interference is within an acceptable range; level 3 credibility indicates that there is a recognizable deviation between the data and the theoretical value, the sensor working state is generally stable, and the impact of environmental interference needs to be paid special attention.

[0023] For level one trustworthiness, the original collected values ​​are directly retained and marked as baseline data; for level two trustworthiness, the original data are corrected based on the environmental compensation algorithm, and the correction process refers to the temperature, vibration and tilt parameters recorded by the environmental monitoring sensors; for level three trustworthiness, additional deviation descriptions and correction suggestions are added, and the applicable scope of the data is marked.

[0024] The temperature compensation formula for pressure data is as follows: P corrected =P s / (1-α(TT j )); Among them, P corrected It represents the pressure data after temperature compensation; α represents the temperature coefficient of the pressure sensor; T represents the current temperature, T j Expressed as temperature reference value; The formula for tilt compensation of altitude data is as follows: h corrected =h s ×cosθ; Among them, h corrected Expressed as the compensation of tilt for height; h s It represents the height measured by the sensor, and θ represents the tilt angle.

[0025] For example: pressure data: after temperature compensation, it is corrected to 8.3kPa (the original 22.5kPa is eliminated); mass and height data retain the original values ​​of 420kg and 0.84m; The sensor combination information includes the model identification, deployment location code and working mode parameters of the currently activated pressure sensor, mass sensor and liquid height sensor; the environmental compensation parameters include the temperature compensation coefficient, vibration attenuation coefficient and tilt correction value; the data quality identification includes the credibility level identification, comprehensive credibility score, data collection period and sensor status code. The sensor status code is used to indicate the working stability of each sensor during the data collection process.

[0026] The present invention provides a technical solution, a smart core barrel content status monitoring system based on intelligent sensing, which includes a data acquisition module, a data preprocessing module, a data verification module, a credibility grading module and a data output module; The data acquisition module includes a pressure sensor module, a mass sensor module, a liquid level sensor module and an environmental monitoring sensor module; the pressure sensor module is used to collect the bottom pressure data and the pressure change rate data; the mass sensor module is used to collect the liquid mass data and the mass change rate data; the liquid level sensor module is used to collect the liquid height data and the height change rate data; The data preprocessing module performs format verification on the raw data transmitted by the data acquisition module and aligns the data collected by different sensors at the same time according to a unified time base; The data verification module includes a cross-verification module, a weight adjustment module, and a configuration optimization module; the cross-verification module verifies the accuracy of the data collected by the data acquisition module through physical association relationships; the weight adjustment module calculates the real-time credibility coefficient of each sensor based on the data collected by the environmental sensing module and dynamically adjusts the working weight of the sensor; The credibility grading module evaluates the comprehensive credibility score based on data verification results, sensor optimization records, and environmental data, divides the data into different credibility levels, and performs differentiated processing on data of different credibility levels; The data output module integrates sensor combination information, environmental compensation parameters and data quality indicators to generate standardized data packets.

[0027] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A method for monitoring the contents status of a smart core barrel based on intelligent sensing, characterized by: The method includes: Deploy a sensor array in the smart core barrel; the sensor array includes a barrel bottom pressure sensor, an environmental monitoring sensor, a quality sensor, and a liquid height sensor; When the rate of change of liquid height, barrel bottom pressure or liquid mass exceeds the preset trigger threshold, the monitoring data of each sensor is collected and transmitted to the edge computing terminal; Based on the bottom pressure data, liquid mass data, liquid height data, pre-stored liquid density parameters, and the internal bottom area parameters of the smart core barrel, the accuracy of the bottom pressure data, liquid mass data, and liquid height data is verified through physical correlation. When the verification results show that the data is inaccurate, the working weight of each sensor is dynamically adjusted according to the environmental parameters, the data is re-collected and the physical correlation verification is performed; when the physical rationality verification results do not meet the preset requirements, the sensor optimization configuration is automatically executed; The data is graded for credibility based on the final verification results, and graded according to the credibility level to generate a data package containing sensor combination information, environmental compensation parameters and data quality identification.

2. The method for monitoring the contents status of a smart core barrel based on intelligent sensing according to claim 1, characterized in that: The pressure sensor collects the bottom pressure data and the bottom pressure change rate data; the mass sensor collects the liquid mass data and the liquid mass change rate data; the liquid height sensor collects the liquid height data and the liquid height change rate data; the environmental monitoring sensor includes a temperature sensor, a vibration sensor and a tilt sensor, the temperature sensor collects the ambient temperature data, the vibration sensor collects the vibration intensity data, and the tilt sensor collects the tilt angle data; When it is detected that the liquid height change rate, the barrel bottom pressure change rate or the liquid mass change rate exceeds the preset trigger threshold, the data collection instruction is automatically started, and the collection instruction is sent to the pressure sensor, the environmental monitoring sensor, the quality sensor and the liquid height sensor at the same time; the pressure sensor responds to the instruction, outputs the barrel bottom pressure data at the current moment and the historical barrel bottom pressure data; the quality sensor responds to the instruction, outputs the liquid mass data at the current moment and the historical liquid mass data; the liquid height sensor responds to the instruction, outputs the liquid height data at the current moment and the historical liquid height data; the environmental monitoring sensor responds to the instruction, outputs the ambient temperature data, vibration intensity data and tilt angle data at the current moment; Each sensor encapsulates the collected monitoring data in the data frame format of the preset communication protocol and transmits it to the edge computing terminal; After receiving the data, the edge computing terminal performs data integrity check and timestamp alignment processing.

3. The method for monitoring the contents status of a smart core barrel based on intelligent sensing according to claim 1 is characterized by: Verifying the accuracy of the barrel bottom pressure data, liquid mass data, and liquid height data through physical association includes: Based on the liquid height data h and liquid density ρ, the theoretical pressure value at the bottom of the barrel is obtained using the following formula: P l =ρ×g×h; Among them, P l It is expressed as the theoretical pressure value at the bottom of the barrel; g is the acceleration due to gravity; The bottom pressure data P collected by the pressure sensor s The theoretical pressure value P at the bottom of the barrel l Make a comparison; Based on the liquid height data h, the internal bottom area S of the smart core barrel, and the liquid density ρ, the theoretical mass of the liquid is calculated using the following formula: m l =ρ×S×h; Among them, m l Expressed as the theoretical mass value of liquid; The liquid mass data m collected by the mass sensor s and the theoretical mass of the liquid m l Make a comparison; Based on liquid mass data m s , liquid density ρ and the internal bottom area S of the smart core barrel, calculate the theoretical height of the liquid using the following formula: h l =m s / (ρ×S); Among them, h l Expressed as the theoretical height of liquid; The liquid height data h collected by the liquid height sensor s and the theoretical height of the liquid h l Make a comparison.

4. The method for monitoring the contents status of a smart core barrel based on intelligent sensing according to claim 3 is characterized by: Calculate the deviation rate of the barrel bottom pressure data δP=|P s -P l | / P l ×100%, the deviation rate of liquid mass data δm=|m s -m l | / m l ×100%, the deviation rate of liquid height data δh=|h s -h l | / h l ×100%; Preset pressure deviation threshold δP0, mass deviation threshold δm0 and height deviation threshold δh0; When δP≤δP0, δm≤δm0 and δh≤δh0, the barrel bottom pressure data, liquid mass data and liquid height data are judged to be accurate; when any deviation rate exceeds the corresponding threshold, the corresponding data is judged to be inaccurate.

5. The method for monitoring the contents status of a smart core barrel based on intelligent sensing according to claim 1 is characterized by: The dynamically adjusting the working weight of each sensor according to the environmental parameters includes: The environmental parameters include ambient temperature data, vibration intensity data and tilt angle data; the real-time credibility coefficient of each sensor is calculated based on the environmental parameters, and a sensor weight distribution model is established; Based on the credibility coefficient, dynamic weight values ​​are assigned to the pressure sensor, the mass sensor, and the liquid height sensor, respectively, wherein sensors that are more affected by the environment are assigned lower weights; The edge computing terminal sends collection instructions to the corresponding sensors according to the adjusted work weights. The pressure sensor responds to the instructions to output the bottom pressure data of the barrel, the mass sensor responds to the instructions to output the liquid mass data, and the liquid height sensor responds to the instructions to output the liquid height data.

6. The method for monitoring the contents status of a smart core barrel based on intelligent sensing according to claim 1, characterized in that: The sensor optimization configuration is: The edge computing terminal extracts the response characteristic parameters of each sensor during the physical rationality verification process, wherein the response characteristic parameters include the stability of the data acquisition cycle, the signal transmission delay time, and the detection value fluctuation amplitude; Based on the response characteristic parameters, the sensor abnormalities are identified, including acquisition accuracy deviating from the standard range, response speed exceeding a preset threshold, and anti-interference capability falling below a benchmark level; Based on sensor abnormalities, the edge computing terminal sends parameter adjustment instructions to the corresponding sensor. The parameter adjustment instructions include adjusting the sensor sampling frequency, modifying the sensor working mode, updating the sensor calibration parameters, switching the sensor data transmission channel, and reconfiguring the sensor networking mode. After the parameter adjustment is completed, the edge computing terminal controls each sensor to restart the data collection process and simultaneously starts the environmental monitoring sensor to continuously monitor the adjusted working environment to ensure that the working environment of the sensor under the new parameter setting meets the preset conditions; The edge computing terminal stores the process information of sensor optimization configuration in the configuration log. The process information includes the response characteristic parameter record before parameter adjustment, the parameter adjustment instruction content, the response status of each sensor to the adjustment instruction, and the adjusted working environment parameters recorded by the environmental monitoring sensor.

7. The method for monitoring the contents status of a smart core barrel based on intelligent sensing according to claim 6, characterized in that: The credibility grading of the data according to the final verification result includes: A credibility grading model is constructed based on the physical rationality verification results, the parameter adjustment records after the sensor optimization configuration, and the environmental monitoring data. The credibility grading model includes the data consistency index, the sensor stability index, and the environmental interference index. The comprehensive credibility score of the data is calculated by weighted summation. The formula is as follows: C=w1×A+w2×B+w3×E; Where C represents the comprehensive credibility score; w1 represents the weight coefficient of the data consistency index, w2 represents the weight coefficient of the sensor stability index, and w3 represents the weight coefficient of the environmental interference index; A represents the data consistency score, which is determined based on the comparison result of the data deviation rate and the preset threshold; B represents the sensor stability score, which is determined based on the fluctuation amplitude of the sensor response characteristic parameter; E represents the environmental interference score, which is determined based on the degree of deviation of the environmental parameter from the baseline value; According to the value range of the comprehensive credibility score, the data credibility is divided into three levels: when the comprehensive credibility score is in the first preset interval, it is judged as level one credibility; when the comprehensive credibility score is in the second preset interval, it is judged as level two credibility; when the comprehensive credibility score is in the third preset interval, it is judged as level three credibility.

8. The method for monitoring the contents status of a smart core barrel based on intelligent sensing according to claim 7, characterized in that: The grading process according to the credibility level includes: For the first level of credibility, the original collected values ​​are directly retained and marked as benchmark data; for the second level of credibility, the original data are corrected based on the environmental compensation algorithm, and the correction process refers to the temperature, vibration and tilt parameters recorded by the environmental monitoring sensor; for the third level of credibility, additional deviation descriptions and correction suggestions are added, and the applicable scope of the data is marked.

9. The method for monitoring the contents status of a smart core barrel based on intelligent sensing according to claim 1, characterized in that: The sensor combination information includes the model identification, deployment position code and working mode parameters of the pressure sensor, mass sensor and liquid height sensor that are currently in the activated state; the environmental compensation parameters include the temperature compensation coefficient, vibration attenuation coefficient and tilt correction value; the data quality identification includes the credibility level identification, comprehensive credibility score, data collection period and sensor status code, and the sensor status code is used to indicate the working stability of each sensor during the data collection process.

10. A smart core bucket content status monitoring system based on intelligent sensing, applied to a smart core bucket content status monitoring method based on intelligent sensing according to any one of claims 1 to 9, characterized in that: The system includes a data acquisition module, a data preprocessing module, a data verification module, a credibility grading module and a data output module; The data acquisition module includes a pressure sensor module, a mass sensor module, a liquid level sensor module and an environmental monitoring sensor module; the pressure sensor module is used to collect the bottom pressure data and the pressure change rate data; the mass sensor module is used to collect the liquid mass data and the mass change rate data; the liquid level sensor module is used to collect the liquid height data and the height change rate data; The data preprocessing module performs format verification on the raw data transmitted by the data acquisition module and aligns the data collected by different sensors during the same period according to a unified time reference; The data verification module includes a cross-verification module, a weight adjustment module, and a configuration optimization module; the cross-verification module verifies the accuracy of the data collected by the data acquisition module through physical association relationships; the weight adjustment module calculates the real-time credibility coefficient of each sensor based on the data collected by the environmental sensing module and dynamically adjusts the working weight of the sensor; The credibility grading module evaluates the comprehensive credibility score based on data verification results, sensor optimization records and environmental data, divides the data into different credibility levels, and performs differentiated processing on data of different credibility levels; The data output module integrates sensor combination information, environmental compensation parameters and data quality identifiers to generate a standardized data packet.

Images