Visual real-time monitoring method and system for digital floating disc of storage tank

Abstract

The invention relates to the technical field of storage tank safety monitoring, in particular to a visual real-time monitoring method and system for a digital floating disc of a storage tank. The method comprises the following steps: carrying out real-time floating disc signal acquisition on a full liquid receiving floating disc to obtain real-time floating disc sensing signal data, and carrying out data filtering preprocessing on the real-time floating disc sensing signal data to obtain floating disc sensing signal data; performing Kalman filtering data fusion on the floating disc sensing signal data to obtain real-time floating disc sensing fusion data; performing floating disc abnormal state detection on the real-time floating disc sensing fusion data to obtain floating disc abnormal detection data; floating disc early warning information integration is carried out according to the floating disc anomaly detection data, so that an abnormal floating disc alarm strategy is obtained; data of the full-liquid-receiving floating disc auxiliary mechanism is obtained, prevention and control strategy analysis is carried out, an abnormal floating disc prevention and control strategy is obtained, and the abnormal floating disc prevention and control strategy is uploaded to a controller to execute a floating disc prevention and control task. The safety of the storage tank can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of storage tank safety monitoring, and in particular to a method and system for visualizing real-time monitoring of a digital floating plate of a storage tank. Background Art

[0002] Internal floating roof tanks are widely used in the petroleum, chemical and other industries to store various liquid oil products. The design purpose of this type of tank is to minimize the emission of volatile organic compounds (VOCs) while ensuring the safety of liquid storage, thereby reducing the impact on the environment. Among them, the full-liquid floating plate, as an important auxiliary equipment for storage tanks, mainly realizes the floating and sinking of the floating plate by fully contacting with the oil in the storage tank. The working principle of the full-liquid floating plate is that as the oil enters and exits, the floating plate floats accordingly, and the bottom surface is always in contact with the oil, thereby eliminating the gas phase space above the oil and reducing the volatilization and emission of VOCs.

[0003] However, during the long-term use of internal floating roof tanks, the sealing of the floating plate may be affected by many factors. For example, the quality of the floating plate material, corrosion, and sudden changes in the tank structure may cause the sealing of the floating plate to be damaged. Once the seal is damaged, the oil in the tank is exposed to the outside air, which is likely to cause VOCs to leak and cause serious pollution to the environment. Therefore, real-time monitoring and management of fully liquid-connected floating plates is particularly important.

[0004] In traditional monitoring methods, regular inspections and manual observations are usually used to monitor the working status of the floating plate. This method is not only inefficient, but also prone to omissions, leading to potential safety hazards. In addition, key information such as the sealing and buoyancy status of the floating plate cannot be fed back in real time, making it impossible to effectively control the risks of the tank during operation. Summary of the invention

[0005] Based on this, it is necessary for the present invention to provide a method and system for visual real-time monitoring of a digital floating plate of a storage tank to solve at least one of the above technical problems.

[0006] To achieve the above purpose, a method for visual real-time monitoring of a digital floating plate of a storage tank is provided, which is applied to a digital floating plate monitoring device. The digital floating plate monitoring device includes a fully liquid-connected floating plate, a monitoring instrument and a controller, wherein the monitoring instrument includes a structure monitoring unit, a radar measurement and control instrument, a VOCs online monitoring instrument and a signal collector; the structure monitoring unit includes a two-dimensional inclination sensor and a vertical acceleration sensor, and the shell of the structure monitoring unit is a flameproof shell; the radar measurement and control instrument is a radar level meter; the signal collector integrates a power supply module, a Zener safety barrier, a photoelectric conversion module, and a switch, and the shell of the signal collector is a flameproof shell; the fully liquid-connected floating plate and the monitoring instrument are electrically connected to the controller; the method for visual real-time monitoring of a digital floating plate of a storage tank includes the following steps: Step S1: collecting real-time floating plate signals of the fully liquid-connected floating plate through a monitoring instrument, thereby obtaining real-time floating plate sensor signal data, and performing data filtering preprocessing on the real-time floating plate sensor signal data, thereby obtaining floating plate sensor signal data; Step S2: amplifying and converting the floating disk sensor signal data through the photoelectric conversion module to obtain digital real-time floating disk sensor data; performing Kalman filter data fusion on the digital real-time floating disk sensor data to obtain real-time floating disk sensor fusion data; Step S3: Visualizing the real-time floating plate sensor fusion data to predict the floating plate state, thereby obtaining a floating plate state visualization chart, and performing floating plate abnormal state detection based on the floating plate state visualization chart, thereby obtaining floating plate abnormality detection data; Step S4: classifying the abnormal level of all the floating plates receiving liquid according to the abnormal detection data of the floating plates, thereby obtaining the abnormal level data of all the floating plates receiving liquid, and integrating the floating plate warning information based on the abnormal level data of all the floating plates receiving liquid, thereby obtaining the abnormal floating plate alarm strategy; Step S5: Obtain the data of the auxiliary mechanism of the full-liquid floating plate, and perform prevention and control strategy analysis on the abnormal floating plate alarm strategy based on the data of the full-liquid floating plate auxiliary mechanism, so as to obtain the abnormal floating plate prevention and control strategy, and upload the abnormal floating plate prevention and control strategy to the controller to execute the floating plate prevention and control task.

[0007] The present invention collects floating plate signal data in real time through monitoring instruments, and can quickly obtain key information such as the floating state and sealing of the floating plate. This real-time monitoring is more efficient than traditional manual inspection and can timely discover potential safety hazards. Data filtering preprocessing can remove noise and interference, improve the accuracy of the signal, and thus ensure the reliability of subsequent analysis. This means that subsequent analysis and decision-making will be based on more accurate data. The photoelectric conversion module amplifies and converts the signal so that the weak floating plate signal can be effectively captured, avoiding the monitoring blind spot caused by weak signal. Data fusion through Kalman filtering can integrate multi-source signals, reduce redundancy and errors, and provide more reliable real-time floating plate sensor fusion data, laying a solid foundation for subsequent prediction and analysis. Visualizing the real-time floating plate sensor fusion data allows operators to intuitively observe the operating status of the floating plate. This intuitive form of expression helps to quickly understand complex data and support quick decision-making. Through the analysis of the floating plate state visualization chart, the abnormal state of the floating plate can be detected in time. This process can identify potential problems at an early stage and prevent problems from deteriorating, thereby protecting the environment and equipment safety. The abnormal status of the floating plate is divided into different levels, so that different degrees of abnormal conditions can be given different attention and treatment, which optimizes the allocation and use of resources and improves the scientific nature of management. The early warning strategy based on the integration of abnormal level data can take measures before the problem expands to prevent environmental pollution and safety accidents. This mechanism significantly improves the safety and environmental protection efficiency of operation. By obtaining the data of the auxiliary mechanism of the fully liquid-connected floating plate, the operating status and possible risks of the floating plate can be comprehensively evaluated, and the monitoring ability of complex systems can be enhanced. The abnormal floating plate prevention and control strategy obtained by analysis is uploaded to the controller, which can realize automatic control and real-time response. This mechanism can quickly respond to various abnormal situations to ensure the safety and environmental protection of the floating plate. Through the implementation of these steps, the fully liquid-connected floating plate monitoring system of the internal floating roof storage tank can realize efficient real-time monitoring, accurate data processing and visualization, scientific abnormality detection and early warning, and automated prevention and control strategy execution. This not only improves the safety of the storage tank and reduces the emission risk of VOCs, but also makes a positive contribution to environmental protection.

[0008] Optionally, step S1 specifically includes: Step S11: collecting real-time floating plate signals of the fully liquid-connected floating plate through a monitoring instrument, thereby obtaining real-time floating plate sensor signal data, wherein the real-time floating plate sensor signal data includes real-time floating plate height signal data, real-time floating plate inclination signal data, real-time floating plate vertical acceleration signal data, and real-time floating plate VOCs concentration signal data; Step S12: performing data cleaning on the real-time floating plate sensor signal data, thereby obtaining the floating plate sensor signal data to be normalized; Step S13: normalizing the floating plate sensor signal data to be normalized, thereby obtaining normalized floating plate sensor signal data; Step S14: performing median filtering on the normalized floating plate sensor signal data to obtain floating plate sensor signal data.

[0009] The present invention collects real-time signals of the fully liquid-connected floating plate through monitoring instruments to ensure that key information such as the height, inclination, vertical acceleration and VOCs concentration of the floating plate can be obtained in time. This real-time monitoring can provide reliable data support for subsequent data analysis and decision-making. Different types of sensor signals (such as height, inclination, acceleration and VOCs concentration) can fully reflect the state of the floating plate, provide rich information, and help to comprehensively evaluate the operation and environmental impact of the floating plate. Through real-time monitoring, possible problems in the operation of the floating plate can be discovered in time, and an early warning mechanism can be provided to help maintenance personnel take measures quickly to avoid accidents. Data cleaning can eliminate invalid or erroneous data, such as outliers caused by sensor failure or external interference, and improve the accuracy and reliability of the data. The cleaning process helps focus on meaningful data, making subsequent analysis and processing more efficient and avoiding the effectiveness of the results affected by noise data. By eliminating irrelevant or erroneous data, the amount of data processing can be reduced, computing resources can be saved, and the efficiency of overall data processing can be improved. Through normalization processing, data of different types and ranges are converted into a unified scale for subsequent comparison and analysis. For example, the dimensions of the floating plate height and VOCs concentration are different, and these differences can be eliminated after normalization. Many machine learning and data mining algorithms are sensitive to data scale. Normalization can improve the convergence speed and accuracy of these algorithms and enhance model performance. A unified data scale helps visualize the data, making the trends and patterns of the data more obvious, which is convenient for analysts to make intuitive judgments and decisions. Median filtering is an effective signal processing technology that can effectively suppress random noise in the data, retain important signal features, and improve data quality. Compared with other filtering techniques, median filtering has more advantages in processing the edges of signals and can maintain the mutation characteristics of signals, which is especially important for dynamically changing floating plate signals. The filtered data is smoother and more reliable, and can provide higher quality basic data for subsequent analysis, decision-making and monitoring, thereby improving the effectiveness of the overall monitoring system.

[0010] Optionally, step S2 specifically includes: Step S21: obtaining an operational amplifier parameter group and an analog-to-digital converter parameter group through a photoelectric conversion module; Step S22: performing sensor signal enhancement on the floating plate sensor signal data according to the operational amplifier parameter group, thereby obtaining floating plate sensor enhanced signal data; Step S23: performing analog signal discrete quantization on the floating plate sensor enhancement signal data, thereby obtaining sensor signal quantization data; Step S24: performing analog-to-digital conversion on the quantized data of the sensing signal according to the analog-to-digital converter parameter group, thereby obtaining digital real-time floating disk sensing data; Step S25: Perform Kalman filter data fusion on the digital real-time floating disk sensor data to obtain real-time floating disk sensor fusion data.

[0011] The operational amplifier parameters and analog-to-digital converter parameters obtained by the photoelectric conversion module of the present invention can achieve the optimal configuration of the system and ensure the accuracy and stability of subsequent signal processing. High-performance operational amplifiers and analog-to-digital converters can improve the signal-to-noise ratio (SNR) of the system and reduce system noise, thereby ensuring effective processing of weak signals. By enhancing the floating disk sensor signal through the operational amplifier, the amplitude of the signal can be effectively increased, making it more obvious in the subsequent processing stage and reducing the errors that may occur during the processing. The enhanced signal is easier to distinguish subtle changes, improves the resolution of the measurement, and ensures that the dynamic response of the floating disk is more sensitive. The analog signal is discretely quantized so that the signal meets the requirements of analog-to-digital conversion, laying the foundation for subsequent digital signal processing. Through quantization, while retaining key information, the amount of data is reduced, making data transmission and storage more efficient. The analog-to-digital converter converts the quantized data into a digital signal, so that the system can obtain the floating disk sensor data in real time and adapt to the rapidly changing environment. The digital signal is more compatible with the computer system and subsequent algorithm processing, which is convenient for subsequent data analysis and processing. Kalman filtering can effectively suppress the noise in the data and improve the accuracy and reliability of the floating disk sensor data. By fusing real-time floating disk sensor data, the system model can be dynamically adjusted to improve the adaptability of the system in dynamic environments and ensure the real-time and accuracy of output data.

[0012] Optionally, step S25 is specifically: Step S251: performing time series division of the sensor data according to the digital real-time floating disk sensor data, thereby obtaining the floating disk sensor data at the time start point and the floating disk sensor data at the time end point; Step S252: Estimating the initial state parameters according to the floating plate sensing data at the time starting point, thereby obtaining the initial state estimation value and the initial error covariance matrix; Step S253: constructing a Kalman filter model according to the initial state estimation value and the initial error covariance matrix, and performing sensor prediction on the floating disk sensor data at the time starting point through the Kalman filter model, thereby obtaining Kalman sensor prediction data; Step S254: Perform sensor data fusion update based on the Kalman sensor prediction data and the floating disk sensor data at the end of time, so as to obtain real-time floating disk sensor fusion data.

[0013] The present invention can clarify the data at each time point by dividing the floating disk sensor data in time series, so that the data processing is more orderly. Real-time floating disk data may be affected by environmental noise. After division, it is easier to identify and eliminate outliers, thereby improving the reliability of subsequent data processing. Obtaining the floating disk sensor data at the start and end of time helps to better understand the data change process and its characteristics in a specific time period. By estimating the floating disk sensor data at the start of time, the initial state of the system can be obtained, which is crucial for subsequent state prediction. The acquisition of the initial error covariance matrix helps to quantify the uncertainty of the initial state and provide an accurate error evaluation basis for the Kalman filter, thereby improving the accuracy of the prediction. Accurate initial state estimation can significantly improve the convergence speed and stability of the entire filtering process, and avoid the accumulation of prediction errors caused by inaccurate initial values. The construction of the Kalman filter model enables the system to process the floating disk sensor data in real time, provide dynamic prediction of future states, and thus improve the response speed. By combining the initial state estimation and the error covariance, the Kalman filter can optimize the estimation of the system state when continuously receiving new measurement data, thereby improving the overall performance of the system. The Kalman filter model can effectively combine new observation data with historical data, comprehensively consider various information sources, and improve the reliability and effectiveness of data. By fusing the Kalman sensor prediction data with the time end floating disk sensor data, it can reduce noise and errors and improve the accuracy of the final floating disk sensor fusion data. Real-time updating of sensor data enables the system to adapt to environmental changes and improve its robustness and flexibility. The real-time floating disk sensor fusion data finally obtained provides a solid foundation for subsequent decision-making and control, and can support intelligent decision-making in various application scenarios.

[0014] Optionally, step S3 specifically includes: Step S31: extracting state parameters according to the real-time floating plate sensor fusion data, thereby obtaining floating plate prediction state parameter data and floating plate initial state parameter data; Step S32: Visualizing the change of the floating plate state parameters according to the floating plate initial state parameter data and the floating plate predicted state parameter data, thereby obtaining a floating plate state parameter visualization chart; Step S33: performing state parameter error estimation on the initial state parameter data of the floating plate and the predicted state parameter data of the floating plate, thereby obtaining the state error data of the floating plate, and performing high-value error statistics on the state error data of the floating plate, thereby obtaining the high-value error state parameter data, wherein the high-value error state parameter data includes high-value error posture parameter data and high-value error VOCs concentration data; Step S34: marking the floating plate state parameter visualization chart with high error state parameters according to the high error state parameter data, thereby obtaining a floating plate state visualization chart; Step S35: Detect the abnormal state of the floating plate according to the visualization chart of the floating plate state, so as to obtain the abnormal state detection data of the floating plate.

[0015] The present invention can extract state parameters in time through data fusion of real-time floating plate sensors, so as to monitor the operating status of the floating plate in real time and ensure that it works normally within a predetermined range. Obtaining the predicted state parameter data of the floating plate helps to foresee possible abnormalities or failures, and then take preventive measures to reduce risks. Visualizing the state parameters of the floating plate so that the data is presented in the form of a chart, which is convenient for analysis and understanding. Users can identify the state changes of the floating plate more quickly. Through the visual chart, managers and operators can observe the dynamic state of the floating plate more intuitively, providing strong data support for subsequent decision-making. Estimating the errors of the initial state parameters and the predicted state parameters helps to identify uncertainties and improve the accuracy and reliability of the data. Through the statistics of high error amounts, potential risk factors such as abnormal posture parameters or VOCs concentrations can be discovered, and timely measures can be taken to avoid environmental pollution or equipment failures. By marking the state parameters of high error amounts, abnormal data can be highlighted in the visual chart to help users quickly identify problems. The marked state parameters provide a basis for subsequent in-depth analysis, making the processing of abnormal situations more efficient. By detecting abnormalities in the floating disc status, potential problems can be discovered and dealt with in a timely manner, accidents can be prevented, and overall safety can be improved. The abnormality detection results can be used to optimize maintenance strategies, ensure efficient operation of the equipment, extend the service life of the floating disc, and reduce maintenance costs.

[0016] Optionally, step S35 is specifically: Step S351: dividing the floating plate state visualization chart into visualization charts, thereby obtaining a floating plate posture visualization chart and a floating plate VOCs concentration chart; Step S352: Acquire the floating plate historical state data, and perform floating plate state benchmark statistics according to the floating plate historical state data, so as to obtain floating plate state benchmark parameter data, wherein the floating plate state benchmark parameter data includes floating plate posture benchmark parameter data and floating plate VOCs benchmark concentration data; Step S353: performing high error state parameter abnormality detection on the floating plate attitude visualization chart according to the floating plate state reference parameter data, thereby obtaining abnormal floating plate attitude parameter data, wherein the abnormal floating plate attitude parameter data includes abnormal floating plate height change data, abnormal floating plate inclination change data, and abnormal floating plate vertical acceleration change data; Step S354: performing a high error state parameter abnormality detection on the floating plate VOCs concentration chart according to the floating plate state reference parameter data, thereby obtaining abnormal floating plate VOCs concentration data; Step S355: Merge the abnormal floating plate posture parameter data and the abnormal floating plate VOCs concentration data to obtain floating plate abnormality detection data.

[0017] The present invention visualizes the state of the floating plate, so that the user can intuitively understand the posture of the floating plate and the distribution of VOCs concentration. This visualization method makes complex data easy to understand and helps to quickly determine the operating status of the floating plate. The regularly generated floating plate posture chart and VOCs concentration chart enable monitoring personnel to track the state changes of the floating plate in real time and discover potential problems in time. By statistically analyzing the historical state data of the floating plate, a normal working benchmark of the floating plate can be established. This provides a reference standard for subsequent abnormal detection, making the monitoring results more reliable. The benchmark statistics of historical data enable the changes in current data to be more clearly compared with the past state, which is convenient for identifying potential risks. The abnormal detection of state parameters with high error amounts on the floating plate posture can timely detect abnormal conditions that occur during the operation of the floating plate, such as abnormal fluctuations in height, inclination or acceleration, to prevent environmental risks caused by equipment failure. By identifying abnormal floating plate posture parameters, corresponding maintenance strategies can be formulated and intervened in advance to reduce the risk of floating plate failure. Abnormal detection of VOCs concentration helps to monitor the emission of environmental pollutants in real time, ensure that it does not exceed the safety threshold, and protect the safety of the surrounding environment and people. Real-time monitoring and anomaly detection provide timely data support, allowing decision makers to respond quickly and take measures to reduce the release of VOCs. Abnormal float attitude parameters are combined with VOCs concentration data to form a comprehensive float anomaly detection data set. This data integration helps to comprehensively analyze the operating status of the float and provide deeper insights. Comprehensive anomaly detection data can provide management with a clear basis for formulating targeted improvement measures and management decisions to improve operational efficiency.

[0018] Optionally, step S4 specifically includes: Step S41: extracting the abnormal posture feature of the floating plate and the abnormal VOCs concentration feature of the floating plate from the abnormal detection data of the floating plate, so as to obtain the abnormal posture parameter data of the floating plate and the abnormal VOCs concentration data of the floating plate; Step S42: estimating the predicted displacement amplitude of the floating plate posture on the abnormal floating plate posture parameter data and the floating plate state reference parameter data, thereby obtaining the abnormal floating plate posture displacement amplitude data; Step S43: performing offset amplitude statistics according to the abnormal floating plate posture offset amplitude data, so as to obtain high abnormal offset amplitude floating plate data and low abnormal offset amplitude floating plate data; Step S44: integrating the VOCs concentration prediction trend of the abnormal floating plate VOCs concentration data to obtain the abnormal floating plate VOCs concentration trend data, and performing floating plate concentration trend pattern recognition based on the abnormal floating plate VOCs concentration trend data to obtain the VOCs concentration rising trend floating plate data and the VOCs concentration falling trend floating plate data; Step S45: performing a floating plate intersection operation on the floating plate data with high abnormal deviation amplitude and the floating plate data with rising trend of VOCs concentration, so as to obtain high-risk abnormal floating plate data; performing a floating plate intersection operation on the floating plate data with low abnormal deviation amplitude and the floating plate data with falling trend of VOCs concentration, so as to obtain low-risk abnormal floating plate data; Step S46: merging the high-risk abnormal floating plate data and the low-risk abnormal floating plate data to obtain abnormal level data of all liquid-connected floating plates; Step S47: integrating the floating plate warning information based on the abnormal level data of all the floating plates receiving liquid, so as to obtain an abnormal floating plate alarm strategy.

[0019] The present invention can accurately identify the abnormal behavior of the floating disk by extracting the abnormal posture characteristics and VOCs concentration characteristics of the floating disk. This lays the foundation for subsequent analysis and improves the availability and reliability of data. By comparing the abnormal floating disk posture parameter data with the benchmark parameter data, the posture deviation amplitude of the floating disk can be accurately predicted. This data helps to evaluate the stability and safety of the floating disk and can provide intuitive risk prompts for operators. The statistical analysis of the deviation amplitude makes the state of the floating disk within the normal range and the abnormal range clearer, and can quickly distinguish high-risk and low-risk floating disks, providing a basis for subsequent risk assessment. Trend analysis of VOCs concentration data can identify potential pollution sources and their changes, and timely warn of possible environmental risks. At the same time, through concentration pattern recognition, corresponding treatment measures can be formulated to reduce environmental risks. Intersection operations are performed on floating disks with high abnormal deviation amplitudes and floating disks with rising VOCs concentration trends, which can accurately identify high-risk abnormal floating disks, thereby helping managers to prioritize these floating disks. At the same time, floating disks with low abnormal deviation amplitudes and decreasing concentration trends can also be effectively identified, thereby avoiding unnecessary waste of resources. By combining high-risk and low-risk float data, a comprehensive assessment of the float abnormality level can be conducted to provide support for further decision-making. This way of integrating data can simplify the analysis process and improve work efficiency. Based on the integration of early warning information based on the level data of abnormal floats, alarms can be issued to managers in a timely manner to provide decision support. This real-time alarm strategy can effectively reduce risks and ensure the safe operation of floats, thereby protecting the safety of the environment and equipment.

[0020] Optionally, step S47 is specifically: Obtain the tank safety mechanism and divide the tank safety mechanism into early warning mechanisms, so as to obtain the tank safety emergency alarm mechanism and the tank safety emergency early warning mechanism; According to the tank safety emergency alarm mechanism, the high-risk abnormal floating plate data is matched with the floating plate emergency alarm mechanism to obtain the floating plate emergency alarm data; According to the tank safety emergency warning mechanism, the low-risk abnormal floating plate data is matched with the floating plate emergency warning mechanism to obtain the floating plate emergency warning data, and the floating plate emergency warning data is transmitted to the controller to execute the floating plate safety warning task; Based on the floating disk emergency alarm data, the floating disk alarm path strategy analysis is performed to obtain the abnormal floating disk alarm strategy.

[0021] The present invention divides the early warning mechanism of the storage tank safety mechanism, which can effectively respond to different abnormal data. For example, for high-risk abnormal data (such as abnormal position of the floating plate, too high liquid level, etc.), once triggered, an alarm is immediately issued to the operator. For low-risk abnormal data (such as slight fluctuations of the floating plate), the monitoring system will analyze and warn in advance to prevent the situation from deteriorating. The floating plate data (such as floating plate height, buoyancy, etc.) is obtained by the real-time monitoring system, and the data is matched with the preset high-risk threshold, which can quickly identify potential dangers, reduce response time, improve emergency processing efficiency, and reduce the possibility of accidents. The low-risk floating plate data is analyzed. If the data exceeds the normal fluctuation range but does not reach the emergency alarm threshold, the emergency warning mechanism is triggered, which can detect potential problems in advance, reduce the probability of accidents, and facilitate managers to take preventive measures to ensure safety. After analysis, low-risk floating plate abnormal data is generated and transmitted to the controller to perform the floating plate safety warning task, which can ensure that managers can obtain information in time, make corresponding adjustments and processing, and improve the safety of the storage tank. According to the acquired floating plate alarm data, its alarm path and strategy are analyzed, and a corresponding response plan is formulated. Systematically sorting out abnormal situations of floating plates and clarifying the handling procedures and responsibilities can improve the standardization and efficiency of emergency response.

[0022] Optionally, step S5 specifically includes: Step S51: acquiring auxiliary mechanism data of the full-liquid-connecting floating plate, and extracting mechanism liquid level adjustment parameters from the auxiliary mechanism data of the full-liquid-connecting floating plate, thereby obtaining auxiliary mechanism liquid level adjustment parameter data; Step S52: acquiring historical tank liquid level data, and performing time series correlation on the historical tank liquid level data and the floating plate historical status data, thereby obtaining liquid level-floating plate status correlation data; Step S53: performing a liquid level adjustment strategy analysis on the high-risk abnormal float data and the auxiliary mechanism liquid level adjustment parameter data according to the liquid level-float state association data, thereby obtaining the auxiliary mechanism liquid level adjustment strategy; Step S54: Integrate the abnormal floating plate alarm strategy and the auxiliary mechanism liquid level adjustment strategy to obtain the abnormal floating plate prevention and control strategy, and upload the abnormal floating plate prevention and control strategy to the controller to execute the floating plate prevention and control task.

[0023] By acquiring the data of the auxiliary mechanism, the present invention can fully understand the current working state of the system, including the actual liquid level of the float, the movement state of the float, etc. This provides basic data for subsequent analysis. Extracting the liquid level adjustment parameters can clarify the adjustment ability of the auxiliary mechanism under different working conditions, thereby improving the accuracy of the liquid level control. The acquisition and analysis of real-time data can realize dynamic monitoring of the float, timely adjust the operation strategy, and reduce liquid level fluctuations. By correlating the historical liquid level data with the time series of the float state data, the relationship between the liquid level change and the float state can be identified. This helps to gain a deeper understanding of the law of liquid level changes. By analyzing historical data, potential abnormal float states can be more effectively identified, and possible problems of the system can be warned in advance. Based on the association between the liquid level and the float state, a scientific basis can be provided for the subsequent formulation of liquid level adjustment strategies, thereby optimizing the adjustment effect. By analyzing the high-risk abnormal float data, potential risks can be quickly identified, so that targeted measures can be taken to ensure safety. Combined with the liquid level-float state correlation data, a more accurate and effective liquid level adjustment strategy can be formulated to reduce the possibility of liquid level fluctuations and improve the stability of the system. On the basis of the liquid level adjustment strategy, it can quickly respond to liquid level changes and improve the system's ability to respond to emergencies. Integrating the abnormal float alarm strategy and the auxiliary mechanism liquid level adjustment strategy can form a systematic prevention and control plan to enhance the system's comprehensive protection capabilities. Upload the prevention and control strategy to the controller to ensure the rapid implementation and execution of the strategy, reduce manual intervention, and improve the automation level of the system. Through effective prevention and control strategies, it can timely warn and handle abnormal situations, ensure the safe operation of the system, and reduce the risk of accidents.

[0024] Optionally, the present specification also provides a digital floating plate visual real-time monitoring system for a storage tank, which is used to execute the digital floating plate visual real-time monitoring method for a storage tank as described above, and the digital floating plate visual real-time monitoring system for a storage tank comprises: The signal preprocessing module is used to collect the real-time floating plate signal of the fully liquid-connected floating plate through the monitoring instrument, so as to obtain the real-time floating plate sensor signal data, and perform data filtering preprocessing on the real-time floating plate sensor signal data, so as to obtain the floating plate sensor signal data; The sensor data fusion module is used to amplify and convert the floating disk sensor signal data through the photoelectric conversion module to obtain digital real-time floating disk sensor data; perform Kalman filter data fusion on the digital real-time floating disk sensor data to obtain real-time floating disk sensor fusion data; The floating plate state visualization module is used to visualize the floating plate state prediction based on the real-time floating plate sensor fusion data, thereby obtaining a floating plate state visualization chart, and to detect the abnormal state of the floating plate based on the floating plate state visualization chart, thereby obtaining floating plate abnormality detection data; The floating plate abnormality level classification module is used to classify the abnormality level of all the floating plates connected to the liquid according to the floating plate abnormality detection data, so as to obtain the abnormality level data of all the floating plates connected to the liquid, and integrate the floating plate warning information based on the abnormality level data of all the floating plates connected to the liquid, so as to obtain the abnormal floating plate alarm strategy; The prevention and control strategy analysis module is used to obtain the data of the auxiliary mechanism of the fully liquid-connected floating plate, and perform prevention and control strategy analysis on the abnormal floating plate alarm strategy based on the data of the auxiliary mechanism of the fully liquid-connected floating plate, so as to obtain the abnormal floating plate prevention and control strategy, and upload the abnormal floating plate prevention and control strategy to the controller to execute the floating plate prevention and control task.

[0025] The digital floating plate visualized real-time monitoring system for storage tanks of the present invention can realize any one of the digital floating plate visualized real-time monitoring methods for storage tanks of the present invention, and is used to combine the operation and signal transmission medium between various modules to complete the digital floating plate visualized real-time monitoring method for storage tanks. The internal modules of the system cooperate with each other, thereby improving the safety of the storage tank. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings: Figure 1 It is a schematic diagram of the steps of the method for visual real-time monitoring of a digital floating plate of a storage tank according to the present invention; Figure 2 Detailed step flow diagram of step S1 in the present invention; Figure 3 Detailed step flow diagram of step S2 in the present invention; The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0027] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0028] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0029] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0030] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for visual real-time monitoring of a digital floating plate of a storage tank, the method comprising the following steps: Step S1: collecting real-time floating plate signals of the fully liquid-connected floating plate through a monitoring instrument, thereby obtaining real-time floating plate sensor signal data, and performing data filtering preprocessing on the real-time floating plate sensor signal data, thereby obtaining floating plate sensor signal data; In this embodiment, the radar level meter, VOCs online monitoring instrument, two-dimensional inclination sensor and vertical acceleration sensor included in the monitoring instrument are used to collect real-time signals of the fully liquid-connected floating plate. The collected signals include real-time floating plate height signal data, real-time floating plate inclination signal data, real-time floating plate vertical acceleration signal data and real-time floating plate VOCs concentration signal data. These signals are collected by signal collectors including Zener safety barriers for data processing. Then, a low-pass filter (such as a Butterworth filter) is used to pre-process the signal to remove noise and high-frequency interference to ensure that the acquired floating plate sensor signal data is more accurate. The threshold can be set and the cutoff frequency of the filter can be adjusted according to the actual working conditions to ensure that the interference signal can still be effectively filtered out under different environments.

[0031] Step S2: amplifying and converting the floating disk sensor signal data through the photoelectric conversion module to obtain digital real-time floating disk sensor data; performing Kalman filter data fusion on the digital real-time floating disk sensor data to obtain real-time floating disk sensor fusion data; In this embodiment, the photoelectric conversion module (such as a photoelectric sensor or a fiber optic sensor) included in the signal collector is used to amplify and convert the floating disk sensing signal data. The input of the photoelectric conversion module is a filtered analog signal, and the signal is amplified to a range suitable for digital processing through an operational amplifier. Subsequently, the amplified signal is converted into a digital signal using an analog-to-digital converter (ADC). In order to improve data accuracy, an ADC with high resolution (such as 16 bits or higher) can be selected, and a Kalman filter algorithm can be applied to perform data fusion after conversion to further eliminate noise and obtain more reliable real-time floating disk sensing fusion data.

[0032] Step S3: Visualizing the real-time floating plate sensor fusion data to predict the floating plate state, thereby obtaining a floating plate state visualization chart, and performing floating plate abnormal state detection based on the floating plate state visualization chart, thereby obtaining floating plate abnormality detection data; In this embodiment, data visualization tools (such as Matplotlib or Tableau) are used to predict and visualize the state of the real-time floating plate sensor fusion data. Based on the fusion data, a dynamic model of the floating plate liquid level is established to predict the floating plate state in the future (such as the liquid level change trend, the floating plate posture change trend, the VOCs concentration change trend, etc.). The generated floating plate state visualization chart may include a liquid level curve chart and a state indicator chart to reflect the working status of the floating plate in real time. At the same time, by comparing the set standard value with the actual value, the abnormal state of the floating plate is detected. Anomaly detection uses a threshold method or a machine learning algorithm, such as a support vector machine (SVM), to generate floating plate anomaly detection data.

[0033] Step S4: classifying the abnormal level of all the floating plates receiving liquid according to the abnormal detection data of the floating plates, thereby obtaining the abnormal level data of all the floating plates receiving liquid, and integrating the floating plate warning information based on the abnormal level data of all the floating plates receiving liquid, thereby obtaining the abnormal floating plate alarm strategy; In this embodiment, based on the abnormal detection data of the floating plate, the abnormal level classification of the fully liquid-connected floating plate is implemented. By setting multiple abnormal levels (such as slight, medium, and severe), the fuzzy logic algorithm is used to evaluate the state of the floating plate and determine its abnormal degree. After the level classification, a floating plate early warning information integration plan is formulated based on the abnormal level data, an abnormal floating plate alarm strategy is generated, and a response mechanism is used to automate the alarm, such as notifying the operator through a mobile phone APP or a system alarm interface, and recording the abnormal state to provide data support for subsequent analysis.

[0034] Step S5: Obtain the data of the auxiliary mechanism of the full-liquid floating plate, and perform prevention and control strategy analysis on the abnormal floating plate alarm strategy based on the data of the full-liquid floating plate auxiliary mechanism, so as to obtain the abnormal floating plate prevention and control strategy, and upload the abnormal floating plate prevention and control strategy to the controller to execute the floating plate prevention and control task.

[0035] In this embodiment, the auxiliary mechanism data of the full-liquid floating plate (such as the operating status of the pump, the position of the valve, etc.) is obtained through the tank management platform, and compared with the abnormal detection data of the floating plate for analysis. The decision tree algorithm is applied to analyze the prevention and control strategy of the abnormal floating plate. For example, if the state of the floating plate is "severely abnormal", the pump is automatically instructed to stop working and the relevant valves are closed at the same time. The formulated abnormal floating plate prevention and control strategy should have redundancy and adaptive capabilities to adapt to different working conditions and abnormal types. Finally, the analysis results are uploaded to the controller to execute the floating plate prevention and control tasks, realize the combination of real-time monitoring and active prevention and control, and ensure the safe and stable operation of the system. The above-mentioned controller is connected to the host computer system through wireless signal transmission. The host computer system can perform real-time visual monitoring of the floating plate's posture, floating plate height, floating plate inclination angle, tank structure status, VOCs leakage, etc., and perform graded alarms and provide alarm disposal measures according to the early warning alarm model, including providing system linkage control, and analyzing and recording the alarm information.

[0036] Optionally, step S1 specifically includes: Step S11: collecting real-time floating plate signals of the fully liquid-connected floating plate through a monitoring instrument, thereby obtaining real-time floating plate sensor signal data, wherein the real-time floating plate sensor signal data includes real-time floating plate height signal data, real-time floating plate inclination signal data, real-time floating plate vertical acceleration signal data, and real-time floating plate VOCs concentration signal data; In this embodiment, the radar level meter, VOCs online monitoring instrument, two-dimensional inclination sensor and vertical acceleration sensor included in the monitoring instrument are used to collect real-time signals of the fully liquid floating plate. Specifically, the radar measurement and control instrument can be a radar level meter, or a 3D radar level scanner, which is a radar level timing, not less than 3 units, and when it is a 3D radar level scanner, the number is 1 unit. The radar measurement and control instrument can measure the real-time height signal of the floating plate to ensure that its accuracy is within ±0.1 mm. At the same time, the inclination signal of the floating plate is collected using a two-inclination sensor with a sensitivity of 0.01°, ensuring that the tilt state of the floating plate can be accurately recorded under any operating state. The vertical acceleration signal is obtained by a three-axis acceleration sensor with a sampling frequency of 100 Hz, so as to capture the dynamic changes of the floating plate in the liquid in real time. In addition, the VOCs online monitoring instrument can be a photoionization detector (PID), and the VOCs concentration signal can be collected by a photoionization detector, which can detect a gas concentration of 0.1ppm, ensuring the real-time and accuracy of the signal.

[0037] Step S12: performing data cleaning on the real-time floating plate sensor signal data, thereby obtaining the floating plate sensor signal data to be normalized; In this embodiment, after obtaining the real-time floating plate sensor signal data, it is necessary to clean the data to remove noise and outliers. First, set the threshold, for example, the reasonable range of the height signal and the inclination signal are 0 to 1000 mm and -45° to +45°, respectively. By writing a data cleaning algorithm, data points outside this range are identified and removed. At the same time, for acceleration and VOCs concentration signals, a standard deviation-based detection method is adopted to remove data greater than 3 times the standard deviation. Ultimately, the output floating plate sensor signal data set to be normalized will only contain valid signals to ensure the accuracy of subsequent processing.

[0038] Step S13: normalizing the floating plate sensor signal data to be normalized, thereby obtaining normalized floating plate sensor signal data; In this embodiment, after data cleaning, the floating plate sensor signal data to be normalized is normalized to ensure that the data is in the same range for subsequent analysis. The min-max normalization method is used to perform a linear transformation on each dimension of signal data and scale it to the range of 0 to 1. Specifically, assuming that the minimum and maximum values ​​of the height signal are H_min and H_max, respectively, the normalization formula is: H ′ = \frac{H−H min}{H max −H min}. Similarly, the same normalization method is used for other signals (inclination, acceleration, VOCs concentration). The processed normalized floating plate sensor signal data will provide a consistent input format for subsequent analysis and model training.

[0039] Step S14: performing median filtering on the normalized floating plate sensor signal data to obtain floating plate sensor signal data.

[0040] In this embodiment, after normalization, median filtering is implemented to eliminate random noise in the signal. The filter window size is set to 5, that is, the current value and the two values ​​before and after are processed each time. For each signal data point, the value in the window is extracted and the median is calculated. For example, if the signal value at a certain moment is [H1′, H2′, H3′, H4′, H5′], the median is H'_{med} =\text{median}(H'_1, H'_2, H'_3, H'_4, H'_5). This step can effectively reduce the impact of noise, output smooth and reliable floating disk sensor signal data, and further improve the accuracy of subsequent analysis, model prediction or monitoring decisions.

[0041] Optionally, step S2 specifically includes: Step S21: obtaining an operational amplifier parameter group and an analog-to-digital converter parameter group through a photoelectric conversion module; In this embodiment, the parameters of the operational amplifier and the analog-to-digital converter are obtained through the photoelectric conversion module. These parameters include the characteristics of the operational amplifier, such as gain, input impedance, output impedance, bandwidth, and noise factor, as well as the resolution, sampling frequency, and input voltage range of the analog-to-digital converter. Devices such as oscilloscopes and multimeters can be used to monitor and record these parameters in real time to ensure that the selected operational amplifier and analog-to-digital converter can meet the requirements of the floating disk sensor. In addition, the sensor characteristic curve diagram is used for data verification to ensure the rationality of the equipment selection.

[0042] Step S22: performing sensor signal enhancement on the floating plate sensor signal data according to the operational amplifier parameter group, thereby obtaining floating plate sensor enhanced signal data; In this embodiment, a gain circuit is designed and constructed based on the previously obtained operational amplifier parameter group to enhance the signal data of the floating disk sensor. The operational amplifier can be configured as a non-inverting amplifier to increase the amplitude of the sensing signal and reduce the influence of noise. For example, an operational amplifier with high input impedance is selected, and the gain is set to 10 to amplify the weak signal output by the sensor to a level suitable for subsequent processing. At the same time, by adjusting the ratio of the feedback resistor and the input resistor, the gain value is accurately controlled to ensure the accuracy and reliability of the signal enhancement.

[0043] Step S23: performing analog signal discrete quantization on the floating plate sensor enhancement signal data, thereby obtaining sensor signal quantization data; In this embodiment, the floating disk sensing signal enhanced by the operational amplifier is subjected to discrete quantization processing of analog signals. The sampling theorem is adopted to select a suitable sampling frequency (for example, at least twice the highest frequency of the signal) for data acquisition. In actual operation, an oscilloscope can be used to obtain the waveform of the enhanced signal and convert it into a discrete digital signal through an ADC (analog-to-digital converter). In addition, to improve the quantization accuracy, a 12-bit or higher resolution analog-to-digital converter can be used to divide the enhanced signal into multiple discrete levels to ensure the integrity and accuracy of the data.

[0044] Step S24: performing analog-to-digital conversion on the quantized data of the sensing signal according to the analog-to-digital converter parameter group, thereby obtaining digital real-time floating disk sensing data; In this embodiment, the quantized sensor signal data is converted from analog to digital to obtain digital real-time floating disk sensor data. A suitable analog-to-digital converter (ADC) can be selected, such as AD9208, which supports high-speed and high-precision conversion and is suitable for real-time applications. The sampling rate and input voltage range of the ADC are configured to ensure that the actual floating disk sensor signal range can be covered. During the digital conversion process, the timing signal is used to control the sampling timing of the ADC to achieve synchronous sampling. Finally, the converted digital data is transmitted to the microcontroller for subsequent processing using the SPI or I2C communication interface.

[0045] Step S25: Perform Kalman filter data fusion on the digital real-time floating disk sensor data to obtain real-time floating disk sensor fusion data.

[0046] In this embodiment, the acquired digital real-time floating disk sensor data is subjected to Kalman filtering to improve the accuracy and stability of the data. It is necessary to establish a Kalman filter model and define parameters such as the state transfer matrix, the observation matrix, the process noise covariance, and the observation noise covariance. By cyclically processing the real-time sensor data, the prediction and update mechanism is used to gradually correct the sensor data and filter out noise and uncertainty. For example, historical data can be used to update the model parameters to make the filter more adaptable to dynamic environments. Finally, through fusion processing, smooth real-time floating disk sensor fusion data is obtained, which significantly improves the measurement accuracy.

[0047] Optionally, step S25 is specifically: Step S251: performing time series division of the sensor data according to the digital real-time floating disk sensor data, thereby obtaining the floating disk sensor data at the time start point and the floating disk sensor data at the time end point; In this embodiment, data is obtained from a digital real-time floating plate sensor, which includes the timestamp, location information and signal variables read by the sensor (such as the floating plate height signal, the floating plate inclination signal, the floating plate vertical acceleration signal and the floating plate VOCs concentration). The data is sorted using the timestamp and divided into several time periods. In each time period, the floating plate sensor data corresponding to the starting time (such as the first timestamp of the data) and the end time (such as the last timestamp of the data) are determined. In this process, a programming language (such as Python) can be used to write scripts to automatically segment the data set through time windows (such as every hour, every day) to ensure the integrity and real-time nature of the data.

[0048] Step S252: Estimating the initial state parameters according to the floating plate sensing data at the time starting point, thereby obtaining the initial state estimation value and the initial error covariance matrix; In this embodiment, the initial state parameters are estimated using the floating plate sensor data obtained at the time starting point. The initial state parameters may be the position, velocity, acceleration, etc. of the floating plate. The initial state estimate may be calculated by statistical analysis of the floating plate historical sensor data stored in the controller using the least square method or other suitable estimation methods. In addition, the construction of the initial error covariance matrix also needs to be set according to the standard deviation and correlation of the historical data. This can be achieved using a linear regression model to ensure the reliability and accuracy of parameter estimation.

[0049] Step S253: constructing a Kalman filter model according to the initial state estimation value and the initial error covariance matrix, and performing sensor prediction on the floating disk sensor data at the time starting point through the Kalman filter model, thereby obtaining Kalman sensor prediction data; In this embodiment, a Kalman filter model is constructed to process the sensor data. The Kalman filter is a recursive filtering algorithm that can update the state based on the difference between the predicted and actual measured values. First, the state transfer equation and the observation equation are defined, which are set according to the motion characteristics of the floating plate. Then, the obtained initial state estimate and error covariance matrix are used as inputs to the Kalman filter model. Next, through an iterative process, the Kalman sensor prediction data is gradually generated based on the fusion of the predicted and measured values. This can be modeled and simulated through tools such as MATLAB or Simulink to verify the effectiveness of the filter model.

[0050] Step S254: Perform sensor data fusion update based on the Kalman sensor prediction data and the floating disk sensor data at the end of time, so as to obtain real-time floating disk sensor fusion data.

[0051] In this embodiment, data fusion update is performed based on the generated Kalman sensor prediction data and the time end floating disk sensor data. The Kalman prediction data is used as prior information, and the time end data is used as the observed value, and the state estimate is updated through weighted averaging or other fusion algorithms (such as extended Kalman filtering). This process can be performed in a real-time data stream to ensure the timeliness and accuracy of the data. To achieve this goal, a real-time data processing platform (such as Apache Kafka) can be used to process and integrate sensor data to ensure the efficiency and real-time performance of data fusion.

[0052] Optionally, step S3 specifically includes: Step S31: extracting state parameters according to the real-time floating plate sensor fusion data, thereby obtaining floating plate prediction state parameter data and floating plate initial state parameter data; In this embodiment, the sensors of the floating plate (such as temperature, pressure, humidity, VOC (volatile organic compound) sensors, etc.) collect data in real time. By fusing the data from multiple sensors, the state of the floating plate is estimated and predicted using a data fusion algorithm such as a Kalman filter or a particle filter. First, the initial state parameters of the floating plate, such as the current temperature, humidity, attitude angle, etc., are extracted based on the real-time sensor data. Then, the future state of the floating plate is predicted based on the historical data and the current state, such as the temperature, attitude, and VOC concentration changes of the floating plate in the next 5 minutes. These parameters are predicted through multiple iterations to obtain the initial state and predicted state data of the floating plate. Assuming that the sensor of the floating plate detects that the current air temperature is 25°C, the humidity is 60%, and the VOC concentration is 300 ppb, the Kalman filter fuses these data and predicts that the temperature may change to 26°C, the humidity may change to 61%, and the VOC concentration may increase to 320 ppb in the next 5 minutes.

[0053] Step S32: Visualizing the change of the floating plate state parameters according to the floating plate initial state parameter data and the floating plate predicted state parameter data, thereby obtaining a floating plate state parameter visualization chart; In this embodiment, graphical tools or visualization software (such as Matplotlib, Tableau, Power BI, etc.) are used to convert the state parameters of the floating plate (including initial and predicted states) into visual charts. For example, the initial temperature, humidity, attitude angle, and VOC concentration of the floating plate are plotted on the timeline to form a curve graph or a scatter plot to intuitively show the trend of the state of the floating plate over time. In addition, color coding or different chart levels are used to mark the predicted data and actual data at different time points, thereby providing real-time monitoring of the state changes of the floating plate. For example, the initial state and predicted state of the floating plate are plotted on the timeline, and the changing trends of temperature, humidity, and VOC concentration are respectively displayed. For example, a blue curve is used to represent the initial temperature and a green curve is used to represent the predicted temperature. The temperature change trend of the floating plate can be seen by comparing the curve trends.

[0054] Step S33: performing state parameter error estimation on the initial state parameter data of the floating plate and the predicted state parameter data of the floating plate, thereby obtaining the state error data of the floating plate, and performing high-value error statistics on the state error data of the floating plate, thereby obtaining the high-value error state parameter data, wherein the high-value error state parameter data includes high-value error posture parameter data and high-value error VOCs concentration data; Step S34: marking the floating plate state parameter visualization chart with high error state parameters according to the high error state parameter data, thereby obtaining a floating plate state visualization chart; In this embodiment, based on the obtained high-error state parameter data, marking is performed on the state visualization chart of the floating plate. For example, data points with large error values ​​in a curve or chart can be highlighted in red. For state parameters with high error values, special symbols (such as asterisks, red dots) or different colors (such as red, orange) can be used to highlight them in the visualization chart to help the observer intuitively identify the moments and parameters when the floating plate state is abnormal. For example, in the temperature change chart of the floating plate, assuming that at a certain point in time, the temperature error is 2°C, which exceeds the predetermined high error threshold, then a red dot is used to mark the position on the chart. At the same time, for the VOC concentration change chart, a red line can also be used to mark the time point when the error exceeds 50 ppb.

[0055] Step S35: Detect the abnormal state of the floating plate according to the visualization chart of the floating plate state, so as to obtain the abnormal state detection data of the floating plate.

[0056] In this embodiment, an abnormal state of the floating plate is detected based on the state parameter data that has been marked with a high amount of error. An anomaly detection algorithm (such as a statistical Z-score method, a machine learning model, etc.) is used to detect the abnormal state of the floating plate. By defining the "normal" state range of the floating plate (for example, temperature fluctuations within ±2°C, VOC concentration fluctuations within ±50 ppb), any data outside these ranges is considered abnormal. This method can be used to systematically identify potential abnormal events of the floating plate. Assuming that the temperature fluctuation of the floating plate is within the range of 25°C±2°C, any temperature outside this range can be considered abnormal. If the temperature exceeds 27°C or is lower than 23°C for a period of time, combined with the judgment of the anomaly detection algorithm, the floating plate can be marked as having an abnormal state, and further inspection or maintenance measures may be triggered.

[0057] Optionally, step S35 is specifically: Step S351: dividing the floating plate state visualization chart into visualization charts, thereby obtaining a floating plate posture visualization chart and a floating plate VOCs concentration chart; In this embodiment, the visualization chart of the floating plate state is divided to obtain the visualization chart of the floating plate posture (including the visualization chart of the floating plate height, the visualization chart of the floating plate inclination, and the visualization chart of the vertical acceleration of the floating plate) and the VOCs concentration chart of the floating plate. In the specific implementation, the real-time data of the floating plate is first input into the data processing system, and a preliminary visualization chart is generated through the data analysis software (such as Matplotlib of Python or ggplot2 of R language). Subsequently, the data is grouped according to time, floating plate position, and state using the time series analysis method to distinguish the floating plate posture and VOCs concentration under different states, and finally generate clear and separate visualization charts.

[0058] Step S352: Acquire the floating plate historical state data, and perform floating plate state benchmark statistics according to the floating plate historical state data, so as to obtain floating plate state benchmark parameter data, wherein the floating plate state benchmark parameter data includes floating plate posture benchmark parameter data and floating plate VOCs benchmark concentration data; In this embodiment, historical status data of the floating plate are extracted from the database of the tank management, which includes the attitude information and VOCs concentration data of the floating plate at different time points. Then, statistical analysis methods (such as mean, standard deviation, etc.) are applied to perform benchmark statistics on the historical data to calculate the state benchmark parameters of the floating plate, including the attitude benchmark parameters of the floating plate (such as average height, inclination) and VOCs concentration benchmark data (such as average concentration value, fluctuation range). For example, if the historical data shows that the average height of the floating plate is 2 meters and the standard deviation is 0.1 meters, then the benchmark parameters will be used for subsequent anomaly detection.

[0059] Step S353: performing high error state parameter abnormality detection on the floating plate attitude visualization chart according to the floating plate state reference parameter data, thereby obtaining abnormal floating plate attitude parameter data, wherein the abnormal floating plate attitude parameter data includes abnormal floating plate height change data, abnormal floating plate inclination change data, and abnormal floating plate vertical acceleration change data; In this embodiment, the benchmark parameter data will be used to perform abnormal detection of state parameters with high error amounts on the floating plate attitude. Statistical methods (such as Z-score or IQR method) are used to analyze the difference between the real-time data of the floating plate and the benchmark parameters. When the real-time data (such as the current height, inclination, acceleration) exceeds the set threshold, the data is marked as abnormal data. Assuming that the set height threshold is ±0.5 meters, when it is detected that the floating plate height change exceeds this range, the abnormal data is recorded and subsequent analysis is performed. Finally, an abnormal floating plate attitude parameter data set is formed, which contains abnormal floating plate height, inclination and vertical acceleration change data.

[0060] Step S354: performing a high error state parameter abnormality detection on the floating plate VOCs concentration chart according to the floating plate state reference parameter data, thereby obtaining abnormal floating plate VOCs concentration data; In this embodiment, the VOCs concentration chart of the floating plate is detected for anomalies. First, a sample is extracted from the real-time VOCs concentration data of the floating plate and compared with the historical VOCs baseline concentration. The current concentration is judged to be outside the normal range by the set statistical method (such as control chart, regression analysis, etc.). If the current concentration exceeds the historical mean plus 2 times the standard deviation (for example, the baseline concentration is 50 ppb, the standard deviation is 10 ppb, and the threshold is 70 ppb), the concentration is recorded as abnormal.

[0061] Step S355: Merge the abnormal floating plate posture parameter data and the abnormal floating plate VOCs concentration data to obtain floating plate abnormality detection data.

[0062] In this embodiment, the abnormal data detected in the previous steps are merged. The abnormal floating plate attitude parameter data (including abnormal values ​​of height, inclination, and vertical acceleration) are summarized with the abnormal VOCs concentration data. When merging data, data processing tools (such as Pandas) can be used to integrate these abnormal data by timestamp and location to form a comprehensive data set containing time, floating plate status, and degree of abnormality. For example, if at a certain moment, the height change of the floating plate is abnormal and the VOCs concentration is also abnormal, all relevant information at that time point is recorded. Finally, the generated floating plate abnormality detection data set will be used for further analysis and decision support.

[0063] Optionally, step S4 specifically includes: Step S41: extracting the abnormal posture feature of the floating plate and the abnormal VOCs concentration feature of the floating plate from the abnormal detection data of the floating plate, so as to obtain the abnormal posture parameter data of the floating plate and the abnormal VOCs concentration data of the floating plate; In this embodiment, the data collected by the floating plate sensor is analyzed. First, the signal processing technology (such as wavelet transform) is used to extract the posture characteristics of the floating plate, including the tilt angle, yaw angle, etc. For the VOCs concentration data, the concentration conditions at different time points when abnormal VOCs concentration conditions occur are extracted, which also includes the predicted concentration changes. Through data cleaning and feature extraction, the posture parameters (such as angle change rate) and VOCs concentration (such as peak concentration) data of the abnormal floating plate are finally generated.

[0064] Step S42: estimating the predicted displacement amplitude of the floating plate posture on the abnormal floating plate posture parameter data and the floating plate state reference parameter data, thereby obtaining the abnormal floating plate posture displacement amplitude data; In this embodiment, after obtaining the abnormal floating plate attitude parameter data, it is necessary to compare it with the historical floating plate state benchmark parameter data, and use a statistical regression model (such as linear regression or support vector regression) to estimate the offset amplitude. By analyzing the mean and standard deviation of the offset data, the attitude change of the floating plate can be quantified and the offset amplitude data can be generated. This data can provide a basis for subsequent analysis and help identify whether there is a significant deviation.

[0065] Step S43: performing offset amplitude statistics according to the abnormal floating plate posture offset amplitude data, so as to obtain high abnormal offset amplitude floating plate data and low abnormal offset amplitude floating plate data; In this embodiment, by performing cluster analysis (such as K-means clustering or DBSCAN) on the offset amplitude data, the attitude offset amplitude of the abnormal floating disk is divided into two categories: high abnormality and low abnormality. The high abnormal offset amplitude floating disk data will be marked as a potential risk signal (such as a floating disk with an offset amplitude exceeding a specific value), while the low abnormal offset amplitude data is used for normal monitoring. The statistical analysis can use data visualization tools (such as Matplotlib or Tableau) to display the results.

[0066] Step S44: integrating the VOCs concentration prediction trend of the abnormal floating plate VOCs concentration data to obtain the abnormal floating plate VOCs concentration trend data, and performing floating plate concentration trend pattern recognition based on the abnormal floating plate VOCs concentration trend data to obtain the VOCs concentration rising trend floating plate data and the VOCs concentration falling trend floating plate data; In this embodiment, a time series analysis method (such as an ARIMA model or a long short-term memory network LSTM) is used to predict the trend of the VOCs concentration data of abnormal floating disks. Trend identification can distinguish between increasing and decreasing concentration trends by calculating the rate of change of VOCs concentration (such as the relative change percentage). Based on the trend analysis results, the floating disk data with increasing and decreasing VOCs concentrations are obtained to provide support for risk assessment.

[0067] Step S45: performing a floating plate intersection operation on the floating plate data with high abnormal deviation amplitude and the floating plate data with rising trend of VOCs concentration, so as to obtain high-risk abnormal floating plate data; performing a floating plate intersection operation on the floating plate data with low abnormal deviation amplitude and the floating plate data with falling trend of VOCs concentration, so as to obtain low-risk abnormal floating plate data; In this embodiment, an intersection operation (such as an intersection operation in set theory) is performed on the floating disk data with high abnormal deviation amplitude and the floating disk data with rising trend of VOCs concentration to generate high-risk abnormal floating disk data. Similarly, an intersection operation is performed on the floating disk data with low abnormal deviation amplitude and the floating disk data with falling trend of VOCs concentration to obtain low-risk abnormal floating disk data. The intersection operation can be implemented using a database query or a set operation in a programming language (such as Python).

[0068] Step S46: merging the high-risk abnormal floating plate data and the low-risk abnormal floating plate data to obtain abnormal level data of all liquid-connected floating plates; In this embodiment, the generated high-risk and low-risk abnormal floating disk data are merged to form the abnormal level data of all liquid-contacted floating disks. The merging process can use the merge function in the data framework (such as Pandas) to ensure the integrity and accuracy of all floating disk data. Finally, a comprehensive floating disk abnormal state data set is obtained, which contains the risk level information of each floating disk.

[0069] Step S47: integrating the floating plate warning information based on the abnormal level data of all the floating plates receiving liquid, so as to obtain an abnormal floating plate alarm strategy.

[0070] In this embodiment, based on the abnormal level data of the fully contacted floating plate, a decision tree or a rule-based algorithm is applied to generate floating plate warning information. The strategy will generate corresponding alarm information according to the level of abnormal floating plate (high risk, low risk) and display it to the operator through a visual interface. The alarm strategy can include automatically triggering an alarm, sending a message notification, or generating an alarm report to ensure timely response to abnormal floating plate conditions.

[0071] Optionally, step S47 is specifically: Obtain the tank safety mechanism and divide the tank safety mechanism into early warning mechanisms, so as to obtain the tank safety emergency alarm mechanism and the tank safety emergency early warning mechanism; In this embodiment, the early warning safety mechanism of the storage tank is extracted from the storage tank management system. Then, these safety mechanisms are divided into early warning mechanisms. For example, conditions such as too low or too high liquid level, abnormal pressure, and excessive temperature are divided into emergency alarms and early warnings. Sensors can be used to monitor the status of the storage tank in real time, and risk assessment models can be established through data analysis tools to evaluate various abnormal conditions, and finally form a storage tank safety emergency alarm mechanism (such as an alarm when the liquid level is lower than the set value) and a storage tank safety emergency early warning mechanism (such as a warning signal when the liquid level is close to the set value).

[0072] According to the tank safety emergency alarm mechanism, the high-risk abnormal floating plate data is matched with the floating plate emergency alarm mechanism to obtain the floating plate emergency alarm data; In this embodiment, these high-risk data are matched according to the defined emergency alarm mechanism. If the real-time data of the high-risk abnormal floating disk data feedback meets the emergency alarm mechanism conditions (for example, the floating disk deflection exceeds 5 cm) or the predicted data drops beyond the emergency alarm mechanism conditions, the floating disk emergency alarm data will be automatically generated and recorded. For example, if an abnormal situation exceeding the set threshold is detected, the alarm program is immediately triggered and the alarm information is sent to the control center via the wireless network.

[0073] According to the tank safety emergency warning mechanism, the low-risk abnormal floating plate data is matched with the floating plate emergency warning mechanism to obtain the floating plate emergency warning data, and the floating plate emergency warning data is transmitted to the controller to execute the floating plate safety warning task; In this embodiment, these data are matched according to the established tank safety emergency warning mechanism. For example, if the position drift of the floating plate is between 1 and 3 cm, the system will generate floating plate emergency warning data. A method combining threshold setting and dynamic adjustment can be used to analyze historical data using machine learning algorithms to assess the risk of the floating plate state in real time, and the identified low-risk warning data is transmitted to the controller through the PLC (programmable logic controller). The controller performs corresponding floating plate safety warning tasks according to the warning information, such as starting a slight vibration warning light.

[0074] Based on the floating disk emergency alarm data, the floating disk alarm path strategy analysis is performed to obtain the abnormal floating disk alarm strategy.

[0075] In this embodiment, the alarm path strategy is analyzed based on the acquired floating disk emergency alarm data. The analysis includes determining which alarm information needs to be processed first, the path of information transmission, and the speed of response. For example, when an emergency alarm occurs on the floating disk, analyze the source of the alarm, the scope of impact, and potential risks, and formulate corresponding response strategies. Specifically, data flow diagrams (DFD) and state transition diagrams (STG) models can be used to analyze information flow and decision-making processes to ensure that information is quickly transmitted from the floating disk sensor to the control center, and then to the on-site staff, ultimately forming a clear alarm processing path. In addition, the abnormal floating disk alarm strategy can be optimized in combination with risk management tools to ensure effective response to emergencies in actual operations.

[0076] Optionally, step S5 specifically includes: Step S51: acquiring auxiliary mechanism data of the full-liquid-connecting floating plate, and extracting mechanism liquid level adjustment parameters from the auxiliary mechanism data of the full-liquid-connecting floating plate, thereby obtaining auxiliary mechanism liquid level adjustment parameter data; In this embodiment, the data of the auxiliary mechanism of the full-liquid floating plate is obtained through the tank management platform, and then the liquid level adjustment parameters related to the valve mechanism are extracted, such as valve opening, flow setting, etc. These parameters will be used to optimize the liquid level control to ensure that the floating plate works within the optimal liquid level range and prevent risks caused by excessively high or low liquid levels.

[0077] Step S52: acquiring historical tank liquid level data, and performing time series correlation on the historical tank liquid level data and the floating plate historical status data, thereby obtaining liquid level-floating plate status correlation data; In this embodiment, when obtaining historical tank level data, the level records for the past period of time are extracted from the database. Using a time series analysis tool, the tank level data is segmented and associated with the historical status data of the floating plate to identify the relationship between the level change and the floating plate status. This can be achieved through time series analysis and machine learning methods (such as decision trees or support vector machines) to analyze the response patterns of the floating plate under different liquid level states. Finally, a liquid level-floating plate status association data set is generated, which will be used for subsequent risk analysis and strategy formulation.

[0078] Step S53: performing a liquid level adjustment strategy analysis on the high-risk abnormal float data and the auxiliary mechanism liquid level adjustment parameter data according to the liquid level-float state association data, thereby obtaining the auxiliary mechanism liquid level adjustment strategy; In this embodiment, data mining technology is used to analyze high-risk abnormal float data based on the liquid level-float state association data. Abnormal situations can be identified by setting thresholds and rule engines. For example, when a high-risk abnormal float state occurs, a rule-based decision model or machine learning model (such as random forest) is used to analyze the liquid level adjustment strategy in combination with the liquid level adjustment parameter data of the auxiliary mechanism and the abnormal float state to obtain an effective liquid level adjustment strategy. For example, if it is identified that a specific float state often causes abnormal liquid level, the valve opening or flow setting is adjusted to perform preventive adjustment.

[0079] Step S54: Integrate the abnormal floating plate alarm strategy and the auxiliary mechanism liquid level adjustment strategy to obtain the abnormal floating plate prevention and control strategy, and upload the abnormal floating plate prevention and control strategy to the controller to execute the floating plate prevention and control task.

[0080] In this embodiment, when integrating the abnormal float alarm strategy and the auxiliary mechanism liquid level adjustment strategy, the high-risk float data obtained by analysis is first compared with the existing alarm mechanism to evaluate the effectiveness and timeliness of the alarm strategy. By formulating a comprehensive prevention and control strategy, for example, when the liquid level reaches a preset threshold, an alarm is triggered and the valve opening is automatically adjusted to keep the liquid level stable. The prevention and control strategy is monitored and executed in real time by the controller, and the status can be uploaded to the cloud through the Internet of Things technology for remote monitoring and management. This integrated solution ensures that timely measures can be taken when an abnormal float state occurs, thereby reducing the risk of accidents and ensuring system safety.

[0081] Optionally, the present specification also provides a digital floating plate visual real-time monitoring system for a storage tank, which is used to execute the digital floating plate visual real-time monitoring method for a storage tank as described above, and the digital floating plate visual real-time monitoring system for a storage tank comprises: The signal preprocessing module is used to collect the real-time floating plate signal of the fully liquid-connected floating plate through the monitoring instrument, so as to obtain the real-time floating plate sensor signal data, and perform data filtering preprocessing on the real-time floating plate sensor signal data, so as to obtain the floating plate sensor signal data; The sensor data fusion module is used to amplify and convert the floating disk sensor signal data through the photoelectric conversion module to obtain digital real-time floating disk sensor data; perform Kalman filter data fusion on the digital real-time floating disk sensor data to obtain real-time floating disk sensor fusion data; The floating plate state visualization module is used to visualize the floating plate state prediction based on the real-time floating plate sensor fusion data, thereby obtaining a floating plate state visualization chart, and to detect the abnormal state of the floating plate based on the floating plate state visualization chart, thereby obtaining floating plate abnormality detection data; The floating plate abnormality level classification module is used to classify the abnormality level of all the floating plates connected to the liquid according to the floating plate abnormality detection data, so as to obtain the abnormality level data of all the floating plates connected to the liquid, and integrate the floating plate warning information based on the abnormality level data of all the floating plates connected to the liquid, so as to obtain the abnormal floating plate alarm strategy; The prevention and control strategy analysis module is used to obtain the data of the auxiliary mechanism of the fully liquid-connected floating plate, and perform prevention and control strategy analysis on the abnormal floating plate alarm strategy based on the data of the auxiliary mechanism of the fully liquid-connected floating plate, so as to obtain the abnormal floating plate prevention and control strategy, and upload the abnormal floating plate prevention and control strategy to the controller to execute the floating plate prevention and control task.

[0082] The digital floating plate visualized real-time monitoring system for storage tanks of the present invention can realize any one of the digital floating plate visualized real-time monitoring methods for storage tanks of the present invention, and is used to combine the operation and signal transmission medium between various modules to complete the digital floating plate visualized real-time monitoring method for storage tanks. The internal modules of the system cooperate with each other, thereby improving the safety of the storage tank.

[0083] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0084] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for visual real-time monitoring of a digital floating plate of a storage tank, characterized in that: Applied to a digital floating plate monitoring device, the digital floating plate monitoring device includes a fully liquid-connected floating plate, a monitoring instrument and a controller, wherein the monitoring instrument includes a structure monitoring unit, a radar measurement and control instrument, a VOCs online monitoring instrument and a signal collector; the structure monitoring unit includes a two-dimensional inclination sensor and a vertical acceleration sensor, and the shell of the structure monitoring unit is a flameproof shell; the radar measurement and control instrument is a radar level meter; the signal collector integrates a power supply module, a Zener safety barrier, a photoelectric conversion module, and a switch, and the shell of the signal collector is a flameproof shell; the fully liquid-connected floating plate and the monitoring instrument are electrically connected to the controller; the visual real-time monitoring method of the digital floating plate of the storage tank includes the following steps: Step S1: collecting real-time floating plate signals of the fully liquid-connected floating plate through a monitoring instrument, thereby obtaining real-time floating plate sensor signal data, and performing data filtering preprocessing on the real-time floating plate sensor signal data, thereby obtaining floating plate sensor signal data; Step S2: amplifying and converting the floating disk sensor signal data through the photoelectric conversion module to obtain digital real-time floating disk sensor data; performing Kalman filter data fusion on the digital real-time floating disk sensor data to obtain real-time floating disk sensor fusion data; Step S3: Visualizing the real-time floating plate sensor fusion data to predict the floating plate state, thereby obtaining a floating plate state visualization chart, and performing floating plate abnormal state detection based on the floating plate state visualization chart, thereby obtaining floating plate abnormality detection data; Step S4: classifying the abnormal level of all the floating plates receiving liquid according to the abnormal detection data of the floating plates, thereby obtaining the abnormal level data of all the floating plates receiving liquid, and integrating the floating plate warning information based on the abnormal level data of all the floating plates receiving liquid, thereby obtaining the abnormal floating plate alarm strategy; Step S5: Obtain the data of the auxiliary mechanism of the full-liquid floating plate, and perform prevention and control strategy analysis on the abnormal floating plate alarm strategy based on the data of the full-liquid floating plate auxiliary mechanism, so as to obtain the abnormal floating plate prevention and control strategy, and upload the abnormal floating plate prevention and control strategy to the controller to execute the floating plate prevention and control task.

2. The method for visual real-time monitoring of a digital floating plate of a storage tank according to claim 1 is characterized in that: Step S1 is specifically as follows: Step S11: collecting real-time floating plate signals of the fully liquid-connected floating plate through a monitoring instrument, thereby obtaining real-time floating plate sensor signal data, wherein the real-time floating plate sensor signal data includes real-time floating plate height signal data, real-time floating plate inclination signal data, real-time floating plate vertical acceleration signal data, and real-time floating plate VOCs concentration signal data; Step S12: performing data cleaning on the real-time floating plate sensor signal data, thereby obtaining the floating plate sensor signal data to be normalized; Step S13: normalizing the floating plate sensor signal data to be normalized, thereby obtaining normalized floating plate sensor signal data; Step S14: performing median filtering on the normalized floating plate sensor signal data to obtain floating plate sensor signal data.

3. The method for visual real-time monitoring of a digital floating plate of a storage tank according to claim 1 is characterized in that: Step S2 is specifically as follows: Step S21: obtaining an operational amplifier parameter group and an analog-to-digital converter parameter group through a photoelectric conversion module; Step S22: performing sensor signal enhancement on the floating plate sensor signal data according to the operational amplifier parameter group, thereby obtaining floating plate sensor enhanced signal data; Step S23: performing analog signal discrete quantization on the floating plate sensor enhancement signal data, thereby obtaining sensor signal quantization data; Step S24: performing analog-to-digital conversion on the quantized data of the sensing signal according to the analog-to-digital converter parameter group, thereby obtaining digital real-time floating disk sensing data; Step S25: Perform Kalman filter data fusion on the digital real-time floating disk sensor data to obtain real-time floating disk sensor fusion data.

4. The method for visual real-time monitoring of a digital floating plate of a storage tank according to claim 3 is characterized in that: Step S25 is specifically as follows: Step S251: performing time series division of the sensor data according to the digital real-time floating disk sensor data, thereby obtaining the floating disk sensor data at the time start point and the floating disk sensor data at the time end point; Step S252: Estimating the initial state parameters according to the floating plate sensing data at the time starting point, thereby obtaining the initial state estimation value and the initial error covariance matrix; Step S253: constructing a Kalman filter model according to the initial state estimation value and the initial error covariance matrix, and performing sensor prediction on the floating disk sensor data at the time starting point through the Kalman filter model, thereby obtaining Kalman sensor prediction data; Step S254: Perform sensor data fusion update based on the Kalman sensor prediction data and the floating disk sensor data at the end of time, so as to obtain real-time floating disk sensor fusion data.

5. The method for visual real-time monitoring of a digital floating plate of a storage tank according to claim 1 is characterized in that: Step S3 is specifically as follows: Step S31: extracting state parameters according to the real-time floating plate sensor fusion data, thereby obtaining floating plate prediction state parameter data and floating plate initial state parameter data; Step S32: Visualizing the change of the floating plate state parameters according to the floating plate initial state parameter data and the floating plate predicted state parameter data, thereby obtaining a floating plate state parameter visualization chart; Step S33: performing state parameter error estimation on the initial state parameter data of the floating plate and the predicted state parameter data of the floating plate, thereby obtaining the state error data of the floating plate, and performing high-value error statistics on the state error data of the floating plate, thereby obtaining the high-value error state parameter data, wherein the high-value error state parameter data includes high-value error posture parameter data and high-value error VOCs concentration data; Step S34: marking the floating plate state parameter visualization chart with high error state parameters according to the high error state parameter data, thereby obtaining a floating plate state visualization chart; Step S35: Detect the abnormal state of the floating plate according to the floating plate state visualization chart, so as to obtain floating plate abnormality detection data.

6. The method for visual real-time monitoring of a digital floating platform of a storage tank according to claim 5 is characterized in that: Step S35 is specifically as follows: Step S351: dividing the floating plate state visualization chart into visualization charts, thereby obtaining a floating plate posture visualization chart and a floating plate VOCs concentration chart; Step S352: Acquire the floating plate historical state data, and perform floating plate state benchmark statistics according to the floating plate historical state data, so as to obtain floating plate state benchmark parameter data, wherein the floating plate state benchmark parameter data includes floating plate posture benchmark parameter data and floating plate VOCs benchmark concentration data; Step S353: performing high error state parameter abnormality detection on the floating plate attitude visualization chart according to the floating plate state reference parameter data, thereby obtaining abnormal floating plate attitude parameter data, wherein the abnormal floating plate attitude parameter data includes abnormal floating plate height change data, abnormal floating plate inclination change data, and abnormal floating plate vertical acceleration change data; Step S354: performing a high error state parameter abnormality detection on the floating plate VOCs concentration chart according to the floating plate state reference parameter data, thereby obtaining abnormal floating plate VOCs concentration data; Step S355: Merge the abnormal floating plate posture parameter data and the abnormal floating plate VOCs concentration data to obtain floating plate abnormality detection data.

7. The method for visual real-time monitoring of a digital floating plate of a storage tank according to claim 1 is characterized in that: Step S4 is specifically as follows: Step S41: extracting the abnormal posture feature of the floating plate and the abnormal VOCs concentration feature of the floating plate from the abnormal detection data of the floating plate, so as to obtain the abnormal posture parameter data of the floating plate and the abnormal VOCs concentration data of the floating plate; Step S42: estimating the predicted displacement amplitude of the floating plate posture on the abnormal floating plate posture parameter data and the floating plate state reference parameter data, thereby obtaining the abnormal floating plate posture displacement amplitude data; Step S43: performing offset amplitude statistics according to the abnormal floating plate posture offset amplitude data, thereby obtaining high abnormal offset amplitude floating plate data and low abnormal offset amplitude floating plate data; Step S44: integrating the VOCs concentration prediction trend of the abnormal floating plate VOCs concentration data to obtain the abnormal floating plate VOCs concentration trend data, and performing floating plate concentration trend pattern recognition based on the abnormal floating plate VOCs concentration trend data to obtain the VOCs concentration rising trend floating plate data and the VOCs concentration falling trend floating plate data; Step S45: performing a floating plate intersection operation on the floating plate data with high abnormal deviation amplitude and the floating plate data with rising trend of VOCs concentration, so as to obtain high-risk abnormal floating plate data; performing a floating plate intersection operation on the floating plate data with low abnormal deviation amplitude and the floating plate data with falling trend of VOCs concentration, so as to obtain low-risk abnormal floating plate data; Step S46: merging the high-risk abnormal floating plate data and the low-risk abnormal floating plate data to obtain abnormal level data of all liquid-connected floating plates; Step S47: integrating the floating plate warning information based on the abnormal level data of all the floating plates receiving liquid, so as to obtain an abnormal floating plate alarm strategy.

8. The method for visual real-time monitoring of a digital floating plate of a storage tank according to claim 7 is characterized in that: Step S47 is specifically as follows: Obtain the tank safety mechanism and divide the tank safety mechanism into early warning mechanisms, so as to obtain the tank safety emergency alarm mechanism and the tank safety emergency early warning mechanism; According to the tank safety emergency alarm mechanism, the high-risk abnormal floating plate data is matched with the floating plate emergency alarm mechanism to obtain the floating plate emergency alarm data; According to the tank safety emergency warning mechanism, the low-risk abnormal floating plate data is matched with the floating plate emergency warning mechanism to obtain the floating plate emergency warning data, and the floating plate emergency warning data is transmitted to the controller to execute the floating plate safety warning task; Based on the floating disk emergency alarm data, the floating disk alarm path strategy analysis is performed to obtain the abnormal floating disk alarm strategy.

9. The method for visual real-time monitoring of a digital floating platform of a storage tank according to claim 1 is characterized in that: Step S5 is specifically as follows: Step S51: acquiring auxiliary mechanism data of the full-liquid-connecting floating plate, and extracting mechanism liquid level adjustment parameters from the auxiliary mechanism data of the full-liquid-connecting floating plate, thereby obtaining auxiliary mechanism liquid level adjustment parameter data; Step S52: acquiring historical tank liquid level data, and performing time series correlation on the historical tank liquid level data and the floating plate historical status data, thereby obtaining liquid level-floating plate status correlation data; Step S53: performing a liquid level adjustment strategy analysis on the high-risk abnormal float data and the auxiliary mechanism liquid level adjustment parameter data according to the liquid level-float state association data, thereby obtaining the auxiliary mechanism liquid level adjustment strategy; Step S54: Integrate the abnormal floating plate alarm strategy and the auxiliary mechanism liquid level adjustment strategy to obtain the abnormal floating plate prevention and control strategy, and upload the abnormal floating plate prevention and control strategy to the controller to execute the floating plate prevention and control task.

10. A digital floating plate visual real-time monitoring system for storage tanks, characterized in that: Used to execute the method for visual real-time monitoring of a digital floating plate for a storage tank as claimed in claim 1, the visual real-time monitoring system for a digital floating plate for a storage tank comprises: The signal preprocessing module is used to collect the real-time floating plate signal of the fully liquid-connected floating plate through the monitoring instrument, so as to obtain the real-time floating plate sensor signal data, and perform data filtering preprocessing on the real-time floating plate sensor signal data, so as to obtain the floating plate sensor signal data; The sensor data fusion module is used to amplify and convert the floating disk sensor signal data through the photoelectric conversion module to obtain digital real-time floating disk sensor data; perform Kalman filter data fusion on the digital real-time floating disk sensor data to obtain real-time floating disk sensor fusion data; The floating plate state visualization module is used to visualize the floating plate state prediction based on the real-time floating plate sensor fusion data, thereby obtaining a floating plate state visualization chart, and to detect the abnormal state of the floating plate based on the floating plate state visualization chart, thereby obtaining floating plate abnormality detection data; The floating plate abnormality level classification module is used to classify the abnormality level of all the floating plates connected to the liquid according to the floating plate abnormality detection data, so as to obtain the abnormality level data of all the floating plates connected to the liquid, and integrate the floating plate warning information based on the abnormality level data of all the floating plates connected to the liquid, so as to obtain the abnormal floating plate alarm strategy; The prevention and control strategy analysis module is used to obtain the data of the auxiliary mechanism of the fully liquid-connected floating plate, and perform prevention and control strategy analysis on the abnormal floating plate alarm strategy based on the data of the auxiliary mechanism of the fully liquid-connected floating plate, so as to obtain the abnormal floating plate prevention and control strategy, and upload the abnormal floating plate prevention and control strategy to the controller to execute the floating plate prevention and control task.

Images