Intelligent leakage monitoring method and system in fuel sampling process

Abstract

The invention relates to the technical field of leakage monitoring, and discloses an intelligent leakage monitoring method and system in a fuel sampling process, and the method comprises the steps: deploying a plurality of collection devices on a fuel sampling device, collecting a plurality of groups of modal monitoring data based on the collection devices, and obtaining a plurality of modal monitoring data sets according to each group of modal monitoring data; analyzing the modal monitoring data set, and calculating a single-modal monitoring factor of the fuel sampling equipment based on an analysis result; performing normalization processing on all the single-mode monitoring factors to obtain a normalized single-mode monitoring factor, and calculating a multi-mode monitoring factor of the fuel sampling equipment; a single-mode monitoring factor threshold value is preset, whether fuel sampling leakage exists in the fuel sampling equipment or not is judged according to the relation between the multi-mode monitoring factor and the multi-mode monitoring factor threshold value, multi-mode monitoring data are effectively integrated, internal correlation among the data is determined, leakage monitoring accuracy and intelligence of the equipment are guaranteed, and the leakage monitoring efficiency is improved. And safe and stable operation of the fuel sampling process is ensured.

Description

Technical Field

[0001] This invention relates to the field of leak monitoring technology, and more specifically, to an intelligent leak monitoring method and system for fuel sampling processes. Background Technology

[0002] Fuel sampling is a common and critical step in energy, chemical, and transportation industries, used to analyze and monitor indicators such as fuel composition, purity, and contaminant content. During sampling, fuel leaks can easily occur due to equipment aging, loose connections, seal failure, or improper operation. Leaks not only cause fuel waste and economic losses, but can also lead to major safety accidents such as environmental pollution, fires, and even explosions, seriously threatening personnel lives and the safety of production facilities.

[0003] Currently, leak monitoring during fuel sampling primarily relies on manual inspections or single-sensor detection. Traditional manual inspection methods suffer from poor timeliness, high false negative rates, and significant susceptibility to subjective factors, making real-time, continuous leak monitoring difficult. While using single sensors (such as pressure sensors, flow meters, or gas concentration sensors) improves automation to some extent, their limited monitoring scope makes them susceptible to environmental interference, equipment fluctuations, or sensor drift, leading to false alarms or false negatives. Especially under complex operating conditions, a single signal cannot comprehensively and accurately reflect the leak status, failing to meet the requirements for high-reliability monitoring. Summary of the Invention

[0004] This invention provides an intelligent leak monitoring method and system for fuel sampling, which effectively integrates multimodal monitoring data, determines the intrinsic correlation between data, ensures the accuracy and intelligence of equipment leak monitoring, and guarantees the safe and stable operation of the fuel sampling process.

[0005] To achieve the above objectives, the present invention provides an intelligent leak monitoring method for a fuel sampling process, comprising:

[0006] Multiple acquisition devices are deployed on the fuel sampling equipment, and multiple sets of modal monitoring data are collected based on the acquisition devices. Multiple modal monitoring data sets are obtained based on each set of modal monitoring data.

[0007] The modal monitoring data set is analyzed, and the single-mode monitoring factor of the fuel sampling device is calculated based on the analysis results;

[0008] All single-mode monitoring factors are normalized to obtain normalized single-mode monitoring factors, and the multi-mode monitoring factors of the fuel sampling device are calculated.

[0009] A single-modal monitoring factor threshold is preset, and the relationship between the multimodal monitoring factor and the multimodal monitoring factor threshold is used to determine whether there is a fuel sampling leak in the fuel sampling device.

[0010] Furthermore, when obtaining multiple modal monitoring data sets based on each set of modal monitoring data, this includes:

[0011] Extract one modal monitoring data point from each set of modal monitoring data as the modal monitoring data to be processed;

[0012] The remaining modal monitoring data are traversed, and modal monitoring data of the same type are extracted. Multiple modal monitoring data sets are obtained based on the modal monitoring data to be processed and the modal monitoring data of the same type.

[0013] Furthermore, when analyzing the modal monitoring data set and calculating the single-modal monitoring factor of the fuel sampling device based on the analysis results, the process includes:

[0014] Calculate the first set value and the second set value of the modal monitoring data set, and determine the representative value of each modal monitoring data based on the first set value and the second set value;

[0015] The single-mode monitoring factor of the fuel sampling device is calculated based on the representative value of the monitoring data.

[0016] Further, when calculating the first set value and the second set value of the modal monitoring data set, and determining the representative value of each modal monitoring data based on the first set value and the second set value, the process includes:

[0017] Calculate the mean value corresponding to the modal monitoring data set, and use it as the first set value;

[0018] The median of the modal monitoring data set is determined and used as the second set value;

[0019] Calculate the absolute value of the first difference between the modal monitoring data and the first set of values, and calculate the absolute value of the second difference between the modal monitoring data and the second set of values;

[0020] The sum of the absolute values ​​of the first and second differences is taken as the representative value of the modal monitoring data.

[0021] Furthermore, when calculating the single-mode monitoring factor of the fuel sampling device based on the representative value of the monitoring data, the following steps are included:

[0022] Each q representative values ​​of the monitoring data are combined to obtain multiple groups of representative values ​​of the monitoring data;

[0023] Determine the standard deviation corresponding to each representative value group of monitoring data as the data group fluctuation factor;

[0024] Curve fitting is performed on the volatility factors of all data sets to obtain the volatility factor curves of the data sets;

[0025] The mean of all slopes corresponding to the fluctuation factor curve of the data set is used as the single-mode monitoring factor of the fuel sampling device.

[0026] Furthermore, when normalizing all single-mode monitoring factors to obtain normalized single-mode monitoring factors, and calculating the multi-mode monitoring factors of the fuel sampling device, the following steps are included:

[0027] Multiple relative difference factors were determined based on all normalized single-modal monitoring factors;

[0028] The multimodal monitoring factor of the fuel sampling device is calculated based on all relative difference factors.

[0029] Furthermore, when determining multiple relative difference factors based on all normalized single-modal monitoring factors, this includes:

[0030] The single-mode monitoring factors are combined with each pair of normalized single-mode monitoring factors to obtain a single-mode monitoring factor sequence;

[0031] Calculate the absolute value of the difference between two normalized single-mode monitoring factors in each single-mode monitoring factor sequence as the sequence difference;

[0032] The maximum normalized single-modal monitoring factor and the minimum normalized single-modal monitoring factor are determined from all normalized single-modal monitoring factors, and the difference between the maximum normalized single-modal monitoring factor and the normalized single-modal monitoring factor is calculated as the extreme difference.

[0033] The ratio of the extreme difference to the difference of each sequence is determined as the relative difference factor.

[0034] Furthermore, when calculating the multimodal monitoring factor of the fuel sampling device based on all relative difference factors, the following is included:

[0035] Calculate the mean of all relative difference factors, and use it as the standard relative difference factor;

[0036] Extract all relative difference factors that are greater than the standard relative difference factor, and count the number of the corresponding first relative difference factors;

[0037] Extract all relative difference factors that are equal to the standard relative difference factor, and count the number of corresponding second relative difference factors;

[0038] Extract all relative difference factors that are smaller than the standard relative difference factor, and count the number of corresponding third relative difference factors;

[0039] The multimodal monitoring factor of the fuel sampling device is calculated based on the number of the first relative difference factor, the number of the second relative difference factor, and the number of the third relative difference factor.

[0040] Further, when determining whether there is a fuel sampling leak in the fuel sampling device based on the relationship between the multimodal monitoring factor and the multimodal monitoring factor threshold, the method includes:

[0041] When the multimodal monitoring factor is less than the multimodal monitoring factor threshold, it is determined that there is no fuel sampling leakage in the fuel sampling device;

[0042] When the multimodal monitoring factor is greater than or equal to the multimodal monitoring factor threshold, it is determined that there is a fuel sampling leak in the fuel sampling device.

[0043] To achieve the above objectives, the present invention also provides an intelligent leak monitoring system for a fuel sampling process, comprising:

[0044] The first module is used to deploy multiple acquisition devices on the fuel sampling equipment, acquire multiple sets of modal monitoring data based on the acquisition devices, and obtain multiple modal monitoring data sets based on each set of modal monitoring data;

[0045] The second module is used to analyze the modal monitoring data set and calculate the single-modal monitoring factor of the fuel sampling device based on the analysis results.

[0046] The third module is used to normalize all single-mode monitoring factors to obtain normalized single-mode monitoring factors, and to calculate the multi-mode monitoring factors of the fuel sampling device.

[0047] The fourth module is used to pre-set the single-modal monitoring factor threshold and determine whether there is a fuel sampling leak in the fuel sampling device based on the relationship between the multimodal monitoring factor and the multimodal monitoring factor threshold.

[0048] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0049] This invention discloses an intelligent leak monitoring method and system for fuel sampling. Multiple acquisition devices are deployed on the fuel sampling equipment to collect multiple sets of modal monitoring data. Multiple modal monitoring data sets are obtained based on each set of data. The modal monitoring data sets are analyzed, and a single-modal monitoring factor for the fuel sampling equipment is calculated based on the analysis results. All single-modal monitoring factors are normalized to obtain normalized single-modal monitoring factors, and a multi-modal monitoring factor for the fuel sampling equipment is calculated. A threshold for the single-modal monitoring factor is preset. Based on the relationship between the multi-modal monitoring factor and the threshold, it is determined whether there is a fuel sampling leak in the fuel sampling equipment. This effectively integrates multi-modal monitoring data, determines the inherent correlation between data, ensures the accuracy and intelligence of leak monitoring, and guarantees the safe and stable operation of the fuel sampling process. Attached Figure Description

[0050] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0051] Figure 1 A flowchart illustrating an intelligent leak monitoring method for a fuel sampling process according to an embodiment of the present invention is shown.

[0052] Figure 2 A schematic diagram of the structure of an intelligent leak monitoring system for a fuel sampling process is shown in an embodiment of the present invention. Detailed Implementation

[0053] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0054] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0055] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0056] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0057] The following is a description of preferred embodiments of the present invention in conjunction with the accompanying drawings.

[0058] like Figure 1 As shown, an embodiment of the present invention discloses an intelligent leak monitoring method for a fuel sampling process, comprising:

[0059] S110: Deploy multiple acquisition devices on the fuel sampling equipment, acquire multiple sets of modal monitoring data based on the acquisition devices, and obtain multiple modal monitoring data sets based on each set of modal monitoring data;

[0060] In this embodiment, the data acquisition devices include pressure data acquisition devices, flow data acquisition devices, temperature data acquisition devices, etc.

[0061] In this embodiment, multiple acquisition time points are set before acquisition, and multiple sets of modal monitoring data are acquired based on the acquisition time points. The preferred number of acquisition time points is 30. Starting from the 2nd second, acquisition is performed once every two seconds to obtain 30 sets of modal monitoring data.

[0062] In this embodiment, the modal monitoring data includes equipment pressure, equipment flow rate, and equipment temperature.

[0063] In some embodiments of this application, when obtaining multiple modal monitoring data sets based on each set of modal monitoring data, the following is included:

[0064] Extract one modal monitoring data point from each set of modal monitoring data as the modal monitoring data to be processed;

[0065] The remaining modal monitoring data are traversed, and modal monitoring data of the same type are extracted. Multiple modal monitoring data sets are obtained based on the modal monitoring data to be processed and the modal monitoring data of the same type.

[0066] In this embodiment, modal monitoring data of the same type are combined. For example, the equipment pressure in each set of modal monitoring data is combined to obtain a modal monitoring data set about equipment pressure. A modal monitoring data set about equipment flow can also be obtained.

[0067] S120: Analyze the modal monitoring data set and calculate the single-mode monitoring factor of the fuel sampling device based on the analysis results;

[0068] In some embodiments of this application, analyzing the modal monitoring dataset and calculating the single-modal monitoring factor of the fuel sampling device based on the analysis results includes:

[0069] Calculate the first set value and the second set value of the modal monitoring data set, and determine the representative value of each modal monitoring data based on the first set value and the second set value;

[0070] The single-mode monitoring factor of the fuel sampling device is calculated based on the representative value of the monitoring data.

[0071] In some embodiments of this application, when calculating a first set value and a second set value of the modal monitoring data set, and determining the representative value of each modal monitoring data based on the first set value and the second set value, the process includes:

[0072] Calculate the mean value corresponding to the modal monitoring data set, and use it as the first set value;

[0073] The median of the modal monitoring data set is determined and used as the second set value;

[0074] Calculate the absolute value of the first difference between the modal monitoring data and the first set of values, and calculate the absolute value of the second difference between the modal monitoring data and the second set of values;

[0075] The sum of the absolute values ​​of the first and second differences is taken as the representative value of the modal monitoring data.

[0076] In this embodiment, the representative value of the monitoring data corresponding to each modal monitoring data can be obtained.

[0077] The beneficial effects of the above technical solution are: by calculating the mean and median of the modal monitoring data set, and further obtaining the representative value of each modal monitoring data, it is possible to more accurately reflect the overall characteristics and fluctuations of the data, providing a reliable basis for subsequent calculation of single-modal monitoring factors, and helping to improve the accuracy of leak monitoring.

[0078] In some embodiments of this application, calculating the single-mode monitoring factor of the fuel sampling device based on the representative value of the monitoring data includes:

[0079] Each q representative values ​​of the monitoring data are combined to obtain multiple groups of representative values ​​of the monitoring data;

[0080] Determine the standard deviation corresponding to each representative value group of monitoring data as the data group fluctuation factor;

[0081] Curve fitting is performed on the volatility factors of all data sets to obtain the volatility factor curves of the data sets;

[0082] The mean of all slopes corresponding to the fluctuation factor curve of the data set is used as the single-mode monitoring factor of the fuel sampling device.

[0083] In this embodiment, q is preferably 4.

[0084] The beneficial effects of the above technical solution are: by grouping representative values ​​of monitoring data and calculating the standard deviation, the fluctuation of the data can be quantified, while curve fitting and slope mean calculation further determine the overall trend of data fluctuation, thereby obtaining a more accurate single-mode monitoring factor, which helps to more accurately reflect the status of fuel sampling equipment and improve the sensitivity and reliability of leak monitoring.

[0085] S130: Normalize all single-mode monitoring factors to obtain normalized single-mode monitoring factors, and calculate the multi-mode monitoring factors of the fuel sampling device;

[0086] In this embodiment, the normalization method is relatively mature and will not be described again here.

[0087] In some embodiments of this application, when normalizing all single-mode monitoring factors to obtain normalized single-mode monitoring factors, and calculating the multi-mode monitoring factors of the fuel sampling device, the following steps are included:

[0088] Multiple relative difference factors were determined based on all normalized single-modal monitoring factors;

[0089] The multimodal monitoring factor of the fuel sampling device is calculated based on all relative difference factors.

[0090] In some embodiments of this application, determining multiple relative difference factors based on all normalized single-modal monitoring factors includes:

[0091] The single-mode monitoring factors are combined with each pair of normalized single-mode monitoring factors to obtain a single-mode monitoring factor sequence;

[0092] Calculate the absolute value of the difference between two normalized single-mode monitoring factors in each single-mode monitoring factor sequence as the sequence difference;

[0093] The maximum normalized single-modal monitoring factor and the minimum normalized single-modal monitoring factor are determined from all normalized single-modal monitoring factors, and the difference between the maximum normalized single-modal monitoring factor and the normalized single-modal monitoring factor is calculated as the extreme difference.

[0094] The ratio of the extreme difference to the difference of each sequence is determined as the relative difference factor.

[0095] In this embodiment, the relative difference factor corresponding to each single-modal monitoring factor sequence can be obtained.

[0096] The beneficial effects of the above technical solution are: by calculating the absolute value of the difference and extreme difference between normalized single-mode monitoring factors, and further obtaining the relative difference factor, it is possible to quantify the degree of relative difference between different single-mode monitoring factors, providing an important basis for subsequent calculation of multi-mode monitoring factors, helping to more comprehensively assess the status of fuel sampling equipment, and improving the accuracy and reliability of leak monitoring.

[0097] In some embodiments of this application, calculating the multimodal monitoring factor of the fuel sampling device based on all relative difference factors includes:

[0098] Calculate the mean of all relative difference factors, and use it as the standard relative difference factor;

[0099] Extract all relative difference factors that are greater than the standard relative difference factor, and count the number of the corresponding first relative difference factors;

[0100] Extract all relative difference factors that are equal to the standard relative difference factor, and count the number of corresponding second relative difference factors;

[0101] Extract all relative difference factors that are smaller than the standard relative difference factor, and count the number of corresponding third relative difference factors;

[0102] The multimodal monitoring factor of the fuel sampling device is calculated based on the number of the first relative difference factor, the number of the second relative difference factor, and the number of the third relative difference factor.

[0103] In this embodiment, the multimodal monitoring factor of the fuel sampling device is calculated according to the following formula:

[0104]

[0105] Where s is the multimodal monitoring factor of the fuel sampling device, m1 is the number of the first relative difference factor, m2 is the number of the second relative difference factor, and m3 is the number of the third relative difference factor.

[0106] The beneficial effects of the above technical solution are as follows: by introducing statistical analysis of relative difference factors and constructing a computational model for multimodal monitoring factors, it can comprehensively reflect the difference distribution characteristics between different single-modal monitoring factors. It not only considers the numerical magnitude of relative difference factors but also reflects the dispersion of data distribution through statistical analysis, thus more comprehensively characterizing the multimodal state features of the fuel sampling equipment. This quantitative method effectively integrates information from multi-source monitoring data, providing more discriminative monitoring indicators for leak detection and helping to improve the robustness and accuracy of leak detection under complex operating conditions.

[0107] S140: A single-modal monitoring factor threshold is preset, and the relationship between the multimodal monitoring factor and the multimodal monitoring factor threshold is used to determine whether there is a fuel sampling leak in the fuel sampling device.

[0108] In some embodiments of this application, determining whether there is a fuel sampling leak in the fuel sampling device based on the relationship between the multimodal monitoring factor and the multimodal monitoring factor threshold includes:

[0109] When the multimodal monitoring factor is less than the multimodal monitoring factor threshold, it is determined that there is no fuel sampling leakage in the fuel sampling device;

[0110] When the multimodal monitoring factor is greater than or equal to the multimodal monitoring factor threshold, it is determined that there is a fuel sampling leak in the fuel sampling device.

[0111] In this embodiment, the multimodal monitoring factor can provide feedback on the sampling process fluctuations of the fuel sampling equipment, thereby determining whether a leak exists.

[0112] In this embodiment, the multimodal monitoring factor threshold is preferably 0.8, but it can be adjusted adaptively according to actual needs.

[0113] The beneficial effects of the above technical solution are: by pre-setting a reasonable multimodal monitoring factor threshold and comparing it with the actually calculated multimodal monitoring factor, it is possible to quickly and accurately determine whether there is a leak in the fuel sampling equipment. This effectively avoids misjudgments and missed detections that may occur with single-modal monitoring, improves the reliability and practicality of leak monitoring, and ensures the stability and reliability of the sampling process.

[0114] To further illustrate the technical concept of this invention, the technical solution of this invention will now be described in conjunction with specific application scenarios.

[0115] Correspondingly, such as Figure 2 As shown, this application also provides an intelligent leak monitoring system for the fuel sampling process, comprising:

[0116] The first module is used to deploy multiple acquisition devices on the fuel sampling equipment, acquire multiple sets of modal monitoring data based on the acquisition devices, and obtain multiple modal monitoring data sets based on each set of modal monitoring data;

[0117] The second module is used to analyze the modal monitoring data set and calculate the single-modal monitoring factor of the fuel sampling device based on the analysis results.

[0118] The third module is used to normalize all single-mode monitoring factors to obtain normalized single-mode monitoring factors, and to calculate the multi-mode monitoring factors of the fuel sampling device.

[0119] The fourth module is used to pre-set the single-modal monitoring factor threshold and determine whether there is a fuel sampling leak in the fuel sampling device based on the relationship between the multimodal monitoring factor and the multimodal monitoring factor threshold.

[0120] In the description of the above embodiments, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0121] Although the invention has been described above with reference to embodiments, various modifications can be made and components can be replaced with equivalents without departing from the scope of the invention. In particular, as long as there is no structural conflict, the features in the embodiments disclosed in this invention can be combined with each other in any way. The fact that not all of these combinations are described in this specification is merely for the sake of brevity and resource conservation.

[0122] It will be understood by those skilled in the art that the above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A smart leak monitoring method for fuel sampling process, characterized in that, include: Multiple acquisition devices are deployed on the fuel sampling equipment, and multiple sets of modal monitoring data are collected based on the acquisition devices. Multiple modal monitoring data sets are obtained based on each set of modal monitoring data. The modal monitoring data set is analyzed, and the single-mode monitoring factor of the fuel sampling device is calculated based on the analysis results; All single-mode monitoring factors are normalized to obtain normalized single-mode monitoring factors, and the multi-mode monitoring factors of the fuel sampling device are calculated. A single-modal monitoring factor threshold is preset, and the relationship between the multimodal monitoring factor and the multimodal monitoring factor threshold is used to determine whether there is a fuel sampling leak in the fuel sampling device.

2. The intelligent leak monitoring method for fuel sampling process according to claim 1, characterized in that, When obtaining multiple modal monitoring data sets based on each set of modal monitoring data, the following are included: Extract one modal monitoring data point from each set of modal monitoring data as the modal monitoring data to be processed; The remaining modal monitoring data are traversed, and modal monitoring data of the same type are extracted. Multiple modal monitoring data sets are obtained based on the modal monitoring data to be processed and the modal monitoring data of the same type.

3. The intelligent leak monitoring method for fuel sampling process according to claim 1, characterized in that, When analyzing the modal monitoring data set and calculating the single-modal monitoring factor of the fuel sampling device based on the analysis results, the following steps are included: Calculate the first set value and the second set value of the modal monitoring data set, and determine the representative value of each modal monitoring data based on the first set value and the second set value; The single-mode monitoring factor of the fuel sampling device is calculated based on the representative value of the monitoring data.

4. The intelligent leak monitoring method for fuel sampling process according to claim 3, characterized in that, When calculating the first set value and the second set value of the modal monitoring data set, and determining the representative value of each modal monitoring data based on the first set value and the second set value, the process includes: Calculate the mean value corresponding to the modal monitoring data set, and use it as the first set value; The median of the modal monitoring data set is determined and used as the second set value; Calculate the absolute value of the first difference between the modal monitoring data and the first set of values, and calculate the absolute value of the second difference between the modal monitoring data and the second set of values; The sum of the absolute values ​​of the first and second differences is taken as the representative value of the modal monitoring data.

5. The intelligent leak monitoring method for fuel sampling process according to claim 3, characterized in that, When calculating the single-mode monitoring factor of the fuel sampling device based on the representative value of the monitoring data, the following steps are included: Each q representative values ​​of the monitoring data are combined to obtain multiple groups of representative values ​​of the monitoring data; Determine the standard deviation corresponding to each representative value group of monitoring data as the data group fluctuation factor; Curve fitting is performed on the volatility factors of all data sets to obtain the volatility factor curves of the data sets; The mean of all slopes corresponding to the fluctuation factor curve of the data set is used as the single-mode monitoring factor of the fuel sampling device.

6. The intelligent leak monitoring method for fuel sampling process according to claim 1, characterized in that, When normalizing all single-mode monitoring factors to obtain normalized single-mode monitoring factors, and calculating the multi-mode monitoring factors of the fuel sampling device, the following steps are included: Multiple relative difference factors were determined based on all normalized single-modal monitoring factors; The multimodal monitoring factor of the fuel sampling device is calculated based on all relative difference factors.

7. The intelligent leak monitoring method for fuel sampling process according to claim 6, characterized in that, When determining multiple relative difference factors based on all normalized single-modal monitoring factors, including: The single-mode monitoring factors are combined with each pair of normalized single-mode monitoring factors to obtain a single-mode monitoring factor sequence; Calculate the absolute value of the difference between two normalized single-mode monitoring factors in each single-mode monitoring factor sequence as the sequence difference; The maximum normalized single-modal monitoring factor and the minimum normalized single-modal monitoring factor are determined from all normalized single-modal monitoring factors, and the difference between the maximum normalized single-modal monitoring factor and the normalized single-modal monitoring factor is calculated as the extreme difference. The ratio of the extreme difference to the difference of each sequence is determined as the relative difference factor.

8. The intelligent leak monitoring method for fuel sampling process according to claim 6, characterized in that, When calculating the multimodal monitoring factor of the fuel sampling device based on all relative difference factors, the following are included: Calculate the mean of all relative difference factors, and use it as the standard relative difference factor; Extract all relative difference factors that are greater than the standard relative difference factor, and count the number of the corresponding first relative difference factors; Extract all relative difference factors that are equal to the standard relative difference factor, and count the number of corresponding second relative difference factors; Extract all relative difference factors that are smaller than the standard relative difference factor, and count the number of corresponding third relative difference factors; The multimodal monitoring factor of the fuel sampling device is calculated based on the number of the first relative difference factor, the number of the second relative difference factor, and the number of the third relative difference factor.

9. The intelligent leak monitoring method for fuel sampling process according to claim 1, characterized in that, When determining whether there is a fuel sampling leak in the fuel sampling device based on the relationship between the multimodal monitoring factor and the multimodal monitoring factor threshold, the following steps are included: When the multimodal monitoring factor is less than the multimodal monitoring factor threshold, it is determined that there is no fuel sampling leakage in the fuel sampling device; When the multimodal monitoring factor is greater than or equal to the multimodal monitoring factor threshold, it is determined that there is a fuel sampling leak in the fuel sampling device.

10. An intelligent leak monitoring system for a fuel sampling process, applied to the intelligent leak monitoring method for a fuel sampling process as described in any one of claims 1-9, characterized in that, include: The first module is used to deploy multiple acquisition devices on the fuel sampling equipment, acquire multiple sets of modal monitoring data based on the acquisition devices, and obtain multiple modal monitoring data sets based on each set of modal monitoring data; The second module is used to analyze the modal monitoring data set and calculate the single-modal monitoring factor of the fuel sampling device based on the analysis results. The third module is used to normalize all single-mode monitoring factors to obtain normalized single-mode monitoring factors, and to calculate the multi-mode monitoring factors of the fuel sampling device. The fourth module is used to pre-set the single-modal monitoring factor threshold and determine whether there is a fuel sampling leak in the fuel sampling device based on the relationship between the multimodal monitoring factor and the multimodal monitoring factor threshold.

Images