A gas station danger early warning method and system based on the Internet of Things

Abstract

The present application relates to the technical field of data processing, and more particularly to a gas station danger early warning method and system based on the Internet of Things. The method comprises: acquiring gas-liquid ratio data of a fuel gun oil vapor recovery pipeline, the gas-liquid ratio data comprising gas-liquid ratio values of a plurality of samples arranged in time sequence; taking any sample as a target sample, determining the mutation degree of the target sample; determining the fault factor of the target sample; determining the adaptive sample quantity of the isolation forest algorithm when detecting the target sample; and based on the adaptive sample quantity, performing anomaly detection on the target sample by using the isolation forest algorithm to realize the gas station danger early warning based on the Internet of Things. The present application realizes adaptive adjustment of the sample quantity by calculating the fault factor, effectively distinguishes normal gradual change from abnormal mutation, reduces the false alarm rate of gas-liquid ratio data anomaly detection, and improves the accuracy and reliability of the gas station danger early warning.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a gas station danger early warning method and system based on Internet of Things. BACKGROUND

[0002] As a key infrastructure of the city, the safe operation of the gas station is of great importance, so it belongs to the key safety supervision unit. In the refueling operation, the oil vapor recovery system is generally equipped with the oil vapor recovery system. The oil vapor recovery system aims to recover the oil gas volatilized in the refueling process, so as to reduce environmental pollution and ensure the safety of operation. A core index for measuring the working state of the oil vapor recovery system is the gas-liquid ratio, that is, the volume ratio of the recovered oil gas to the volume of the gasoline filled.

[0003] In the monitoring of the gas station, the gas-liquid ratio data is usually collected and analyzed by using an anomaly detection algorithm. The Isolation Forest algorithm has become a mainstream technology in the field of anomaly detection due to its high calculation efficiency and the advantage of not needing to label the samples in advance. However, when the standard Isolation Forest algorithm is directly applied to the anomaly detection of the gas-liquid ratio data, there are obvious technical defects. The standard Isolation Forest algorithm usually sets a fixed sample size for all test samples when building a tree. The sample size determines the difficulty of isolating the test sample, and thus affects the calculation of its anomaly score.

[0004] The fixed number of processing methods makes it difficult for the standard Isolation Forest algorithm to effectively distinguish between two different situations that may both show high values in numerical values: one is a dangerous peak signal that jumps from a stable baseline due to faults such as accidental disconnection of the oil gun, instantaneous blockage of the pipeline, etc. The other is a normal high value produced by the smooth transition of flow rate from low to high in a normal refueling process. Since normal high values are also relatively rare in the entire data set, the standard Isolation Forest algorithm will frequently misjudge them as abnormal, resulting in false alarms, which not only reduces the reliability of the danger early warning, but also increases the burden of the operation and maintenance personnel. SUMMARY

[0005] In order to solve the problem that the standard Isolation Forest algorithm has a high false alarm rate in the anomaly detection of the gas-liquid ratio data of the gas station due to the use of a fixed sample size, thereby reducing the reliability of the danger early warning, the present application provides a gas station danger early warning method and system based on Internet of Things.

[0006] In the first aspect, the present application provides a gas station danger early warning method based on Internet of Things, which adopts the following technical scheme:

[0007] A gas station danger early warning method based on Internet of Things, comprising: acquiring gas-liquid ratio data of a fuel gun oil vapor recovery pipeline, the gas-liquid ratio data comprising gas-liquid ratio values of a plurality of samples arranged in time sequence; regarding any sample as a target sample, determining a mutation degree of the target sample according to the gas-liquid ratio values of each sample in a data segment to which the target sample belongs; determining a fault factor of the target sample according to the symmetry characteristics of data segments on both sides of the target sample and the mutation degree; determining an adaptive sample number of an isolation forest algorithm used when detecting the target sample according to the fault factor, wherein the adaptive sample number is negatively correlated with the fault factor; and performing abnormality detection on the target sample by using the isolation forest algorithm based on the adaptive sample number, so as to realize the gas station danger early warning based on Internet of Things.

[0008] The application can effectively identify the abnormal jump characteristics of the gas-liquid ratio data by analyzing the gas-liquid ratio values of each sample in the data segment to which the target sample belongs and constructing an evaluation index of the mutation degree, can effectively distinguish normal gradual change from abnormal mutation by analyzing the symmetry characteristics of the data segments on both sides of the target sample and constructing a comprehensive evaluation model of the fault factor, and can intelligently adjust the parameters of the isolation forest algorithm through the negative correlation between the fault factor and the adaptive sample number, so as to reduce the sample number to improve the detection sensitivity when the fault factor is high, indicating abnormal mutation, increase the sample number to avoid false positives when the fault factor is low, indicating normal gradual change, effectively solve the problem that the standard isolation forest algorithm cannot distinguish between normal high values and dangerous peak signals, and improve the accuracy and reliability of the abnormality detection; and through the adaptive sample number adjustment, different types of gas-liquid ratio data are differentially processed, providing more accurate data support for the gas station danger early warning.

[0009] Further, the gas-liquid ratio values are obtained by analog-digital conversion of the collected original data.

[0010] The application converts the collected analog gas-liquid ratio signal into digital values through analog-digital conversion, realizes digital processing of data, provides a standardized data basis for subsequent intelligent analysis and algorithm processing, ensures the accuracy and consistency of data, and avoids noise interference and signal attenuation problems in the analog signal transmission process.

[0011] Further, the data segment to which the target sample belongs is a data segment composed of the target sample and a preset number of samples before the target sample.

[0012] Further, the mutation degree satisfies:

[0013] ; in the formula, is the mutation degree of the i th sample, is the mutation degree of the i th sample, is the mutation degree of the i th sample, The gas-liquid ratio values ​​for each sample. For the first The mean of all gas-liquid ratio values ​​within the data segment to which each sample belongs. For the first The range of all gas-liquid ratio values ​​within the data segment to which each sample belongs. For the first The data segment to which this sample belongs does not contain the first... The range of the residual gas-liquid ratio values ​​for each sample. For hyperparameters, To normalize the maximum and minimum values, It is the absolute value symbol.

[0014] This invention achieves a comprehensive assessment of mutation severity by constructing a composite function containing a deviation term and a range variation term. The deviation term reflects the degree of deviation of the target sample from the average value of the data segment, while the range variation term reflects the contribution of the target sample to the overall range of the data segment. The introduction of hyperparameters ensures the numerical stability of the calculation and avoids calculation anomalies caused by zero values. Normalization eliminates the influence of differences in magnitude between different data segments, making mutation severity highly comparable. Through the above methods, normal gradual changes and abnormal mutations are effectively distinguished: during normal gradual changes, although the deviation at a single point may be large, its contribution to the overall range is relatively small, while during abnormal mutations, not only is the deviation at a single point large, but its contribution to the range also increases significantly, improving the accuracy and robustness of mutation detection and providing reliable input parameters for subsequent fault factor calculation.

[0015] Furthermore, the data segments on both sides of the target sample are selected with the target sample as the center, and the same preset length data segments are selected on both sides of the target sample.

[0016] Furthermore, the failure factor satisfies:

[0017] In the formula, For the first Fault factors for each sample For the first The degree of mutation in each sample In the first The number of samples within a data segment on either side of a given sample. and The first The sample and the first The gas-liquid ratio values ​​for each sample. To normalize the maximum and minimum values, It is a natural exponential function. It is the absolute value symbol.

[0018] The application constructs a comprehensive evaluation model of the fault factor by normalizing the product of the mutation degree and the symmetry index, can effectively fuse the local mutation characteristics and the global symmetry characteristics, realizes the accurate identification of abnormal events, the symmetry index can effectively measure the symmetry degree of the data on both sides of the target sample, when the data on both sides are highly symmetrical, the difference sum tends to 0, and the index term tends to 1, when the data on both sides are asymmetrical, the difference sum increases, and the index term decreases, which is helpful to distinguish normal gradual change and abnormal mutation, thereby effectively suppressing false alarms in normal working conditions, while maintaining high sensitivity to real faults, through the negative correlation between the fault factor and the adaptive sample number, the accuracy and reliability of the isolation forest algorithm in the dangerous early warning of the gas station are improved.

[0019] Further, the adaptive sample number satisfies:

[0020] ; in the formula, is the adaptive sample number of the isolation forest algorithm when detecting the first sample, is the preset initial sample number in the isolation forest algorithm, is the fault factor of the first sample, is the maximum function, is the natural exponential function, is the rounding operation.

[0021] The application rounds the product of the initial sample number and the fault factor to the nearest integer, and sets a minimum lower limit, to construct a calculation model of the adaptive sample number, ensure the negative correlation between the sample number and the fault factor, and realize intelligent adjustment of the parameters, when the fault factor is high, it means abnormal mutation, the adaptive sample number is correspondingly reduced, the detection sensitivity of the isolation forest algorithm to abnormal samples is improved, and false negatives are avoided, when the fault factor is low, it means normal gradual change, the adaptive sample number is increased, the false positive rate is reduced, and the accuracy of detection is improved, the minimum constraint ensures that the sample number is not too small to affect the statistical reliability of the algorithm, the rounding operation ensures that the sample number is an integer, which meets the implementation requirements of the algorithm, through the above mechanism, the contradiction between detection sensitivity and accuracy is effectively balanced, the applicability and reliability of the isolation forest algorithm in the gas-liquid ratio data analysis of the gas station are improved, and more accurate parameter adaptive ability is provided for the dangerous early warning system.

[0022] Further, the preset initial sample number in the isolation forest algorithm is 256.

[0023] Further, the abnormal judgment threshold in the preset parameters of the isolation forest algorithm is preset to be 0.75, and the number of trees is preset to be 50.

[0024] In the second aspect, the present application provides a gas station danger early warning system based on Internet of Things, which adopts the following technical scheme:

[0025] A gas station danger early warning system based on Internet of Things, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned gas station danger early warning method based on Internet of Things is realized.

[0026] By adopting the above technical scheme, the above-mentioned gas station danger early warning method based on Internet of Things is generated into a computer program and stored in the memory to be loaded and executed by the processor, so that a terminal device is made according to the memory and the processor, and use is facilitated.

[0027] The present application has the following technical effects:

[0028] (1) Break through the limitation of fixed sample number of standard isolated forest algorithm, construct a fault factor by depicting the jump strength of gas-liquid ratio value from the baseline and the symmetry characteristics of the two-side data segments, dynamically adjust the adaptive sample number of isolated forest, when the fault factor is high, the sample number is reduced, so that it is more easily identified as an anomaly by the isolated forest algorithm, when the fault factor is low, the sample number is increased, avoiding misjudgment as an anomaly due to the lack of value, solving the misclassification problem of traditional algorithm for danger peak and normal high value, and reducing the false alarm rate.

[0029] (2) The negative correlation mechanism of adaptive sample number and fault factor makes the isolation difficulty of isolated forest algorithm accurately match the actual danger degree of the sample, for the real fault signal such as instantaneous peak caused by pipeline blockage, the few sample numbers corresponding to high fault factor will amplify its abnormal characteristics, ensuring stable identification, for the high value fluctuation in normal operation such as smooth transition of fueling flow rate increase, the many sample numbers corresponding to low fault factor will weaken its rarity influence, avoiding false labeling, thereby improving the accuracy of anomaly detection, making the danger warning more reliable, and providing key support for timely disposal of real risks in gas stations.

[0030] (3) The calculation of the fault factor combines the mutation degree and the symmetry characteristics, and can adapt to the diversified operation scenes and equipment states of the gas station, compared with the judgment logic of the standard isolated forest algorithm which only depends on the value rarity, the adaptability of the present application to complex working conditions is stronger, when the gas-liquid ratio data is affected by factors such as environmental temperature and oil type, the present application can still maintain stable early warning performance, ensuring reliable application in various scenes. BRIEF DESCRIPTION OF DRAWINGS

[0031] Figure 1 is a method flowchart in a gas station danger early warning method based on Internet of Things according to an embodiment of the present application.

[0032] Figure 2 is a broken line schematic diagram of a gas-liquid ratio danger early warning result in a gas station danger early warning method based on an Internet of Things according to an embodiment of the present application. DETAILED DESCRIPTION

[0033] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0034] The embodiments of the present application disclose a gas station danger early warning method based on an Internet of Things, referring to Figure 1 , comprising steps S01-S05:

[0035] S01: Obtain gas-liquid ratio data of a fuel gun oil gas recovery pipeline, wherein the gas-liquid ratio data comprises gas-liquid ratio values of a plurality of samples arranged in time sequence.

[0036] In the present embodiment, the gas-liquid ratio is collected in real time by a gas-liquid ratio sensor deployed on the fuel gun oil gas recovery pipeline in the gas station. Exemplarily, the collection frequency can be set to 10 times per second to ensure that abnormal fluctuations occurring instantaneously can be captured. The analog signal collected by the sensor is converted into digital gas-liquid ratio values by an analog-digital conversion device.

[0037] S02: Take any sample as a target sample, and determine the mutation degree of the target sample.

[0038] It should be noted that, in order to evaluate the mutation degree of each sample compared with its surrounding time, the performance of the gas-liquid ratio value will be analyzed. In the specific analysis, the more extreme the value performance of the gas-liquid ratio value at each sample in its own data segment, the greater the mutation degree, and the greater the possibility of failure of the fuel gun at the time corresponding to the sample.

[0039] Take any sample as a target sample, and determine the mutation degree of the target sample according to the gas-liquid ratio values of the samples in the data segment to which the target sample belongs.

[0040] The implementer can set the length of the data segment according to the specific implementation, for example, 200. It should be specially noted that, since historical data needs to be analyzed, the first 199 samples collected are used to construct the data segment, and the subsequent steps are not calculated.

[0041] Specifically, the data segment to which the target sample belongs is a data segment composed of the target sample and a preset number of samples before the target sample.

[0042] Specifically, the degree of mutation satisfies:

[0043] ;

[0044] In the formula, For the first The degree of mutation in each sample For the first The gas-liquid ratio values ​​for each sample. For the first The mean of all gas-liquid ratio values ​​within the data segment to which each sample belongs. For the first The range of all gas-liquid ratio values ​​within the data segment to which each sample belongs. For the first The data segment to which this sample belongs does not contain the first... The range of the residual gas-liquid ratio values ​​for each sample. For hyperparameters, To normalize the maximum and minimum values, It is the absolute value symbol.

[0045] Implementers can set hyperparameters according to the specific implementation situation, such as 0.001. The existence of hyperparameters is to prevent... or This can lead to situations where the calculation results become meaningless.

[0046] in, The larger it is, the more likely it is to be the first The more extreme the gas-liquid ratio value of a sample is within its data range, the greater the degree of abrupt change. The more samples there are, the greater the likelihood that the fuel nozzle will malfunction at a given time; conversely, the less samples there are, the less likely the fuel nozzle will malfunction at a given time. The larger it is, the more likely it is to be the first The more extreme the gas-liquid ratio value of a sample is within its corresponding data range, the greater its reliability, indicating a greater degree of abrupt change. The more samples there are, the greater the likelihood that the fuel nozzle will malfunction at a given time; conversely, the less samples there are, the less likely the fuel nozzle will malfunction at a given time.

[0047] S03: Determine the failure factors of the target sample.

[0048] It should be noted that the difference between instantaneous spike signals caused by equipment failure and high values ​​in normal flow rate changes lies in the following: When an instantaneous spike signal caused by equipment failure occurs, the values ​​of the data segments on both sides of the sampling time will show a more obvious symmetrical characteristic, while when a high value occurs in normal flow rate changes, the value changes of the data segments on both sides of the sampling time will show a unidirectional upward or downward characteristic. Therefore, in this step, the analysis of the numerical change characteristics of the gas-liquid ratio data, combined with the degree of change of each sample, yields the fault factor for each sample. The logic behind this is: the more obvious the symmetrical characteristic of the values ​​of the data segments on both sides of a sample, the greater the possibility that the cause of the sample's value protrusion is equipment failure rather than normal flow rate change, the greater the possibility that the refueling nozzle malfunctioned at the corresponding moment, and the larger the fault factor of that sample will be.

[0049] The failure factor of the target sample is determined based on the symmetry of the data segments on both sides of the target sample and the degree of mutation.

[0050] Specifically, the data segments on both sides of the target sample are selected with the target sample as the center, and the same preset length data segments are selected on both sides of the target sample.

[0051] Implementers can set the length of the data segment according to the specific implementation situation, for example, 50.

[0052] Specifically, the failure factor satisfies:

[0053] ;

[0054] In the formula, For the first Fault factors for each sample For the first The degree of mutation in each sample In the first The number of samples within a data segment on either side of a given sample. and The first The sample and the first The gas-liquid ratio values ​​for each sample. To normalize the maximum and minimum values, It is a natural exponential function. It is the absolute value symbol.

[0055] in, The larger the value, the better the performance analysis based on the gas-liquid ratio. The more prominent the value of a sample, the greater the possibility of an anomaly, and the greater the corresponding failure factor; conversely, the less prominent the value, the greater the possibility of an anomaly. The smaller the value, the better. The more pronounced the symmetry in the values ​​of the data segments on both sides of a sample, the better the symmetry. If a sample exhibits a significant numerical abnormality, the greater the likelihood that the cause is equipment malfunction rather than normal flow rate variation, indicating that the sample... The higher the probability of the fuel nozzle malfunctioning at the corresponding time point for each sample, the higher the probability of the fuel nozzle malfunctioning at the corresponding time point. The larger the failure factor of a sample, the greater the failure factor; conversely, the smaller the sample, the greater the failure factor.

[0056] S04: Determine the adaptive number of samples to use for the Isolation Forest algorithm when detecting target samples.

[0057] It should be noted that the logic used in this step to adaptively adjust the number of subsamples for each sample based on the fault factor of each sample is as follows: the larger the fault factor of each sample, the greater the probability that the sample will fail at the corresponding time. Therefore, in order to more accurately detect it as an abnormal sample, a smaller adaptive sample number needs to be set to highlight the abnormality.

[0058] Based on the fault factor, an adaptive number of samples is determined for the Isolation Forest algorithm when detecting target samples, wherein the adaptive number of samples is negatively correlated with the fault factor.

[0059] Specifically, the adaptive sample number satisfies:

[0060] ;

[0061] In the formula, For use in detecting the first The adaptive number of samples for the Isolation Forest algorithm when there are 1 sample. This is the preset initial number of samples in the Isolation Forest algorithm. For the first Fault factors for each sample It is a function with maximum value. It is a natural exponential function. This is for rounding operations.

[0062] Implementers can set the initial number of samples in the Isolation Forest algorithm according to the specific implementation situation, for example, 256.

[0063] S05: Based on the adaptive sample size, the isolated forest algorithm is used to detect anomalies in the target samples in order to realize IoT-based gas station hazard warning.

[0064] Implementers can set the anomaly detection threshold and the number of trees according to the specific implementation situation. For example, the anomaly detection threshold is 0.75 and the number of trees is 50.

[0065] After obtaining the adaptive sample number for detecting each sample and the setting of the preset parameter of the isolation forest algorithm, the gas-liquid ratio data is detected for anomaly by using the isolation forest algorithm, and subsequent operations of the isolation forest algorithm are existing known steps, which are not described here.

[0066] As shown in Figure 2 The vertical axis represents the gas-liquid ratio (A / L Ratio), and the value range is 1.0-4.0, and the horizontal axis is the time stamp (covering the period from 01:00:00 to 01:00:10), Figure 2 Two types of gas-liquid ratio data features are clearly distinguished in the present application: one is the normal high value area, in which the gas-liquid ratio value changes smoothly with time, and there is no instantaneous sharp rise and fall phenomenon, which corresponds to the normal working condition of the flow rate transition from low to high during refueling. Due to the low fault factor, the present application avoids misjudgment as an anomaly by increasing the adaptive sample number of the isolation forest algorithm; the second is the detected dangerous peak, which is manifested as the instantaneous jump of the gas-liquid ratio value at a specific time point. This kind of signal has high mutation degree and obvious symmetry characteristics of the two side data segments, and the fault factor is high. The isolation forest algorithm amplifies its abnormal characteristics by reducing the adaptive sample number, so as to realize accurate identification, reduce the false alarm rate, and improve the reliability of the danger warning.

[0067] The embodiment of the present application also discloses a gas station danger warning system based on Internet of Things, which comprises a processor and a memory, and the memory stores computer program instructions. When the computer program instructions are executed by the processor, the method for warning danger of a gas station based on Internet of Things is realized.

[0068] The above system also comprises a communication bus and a communication interface and other components familiar to those skilled in the art, the settings and functions of which are known in the art, and thus are not described here.

[0069] The above are the preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Therefore, any equivalent changes made on the basis of the structure, shape and principle of the present application should be covered within the protection scope of the present application.

Claims

1. A method for early warning of hazards at gas stations based on the Internet of Things, characterized in that, include: Obtain the gas-liquid ratio data of the fuel nozzle vapor recovery pipeline, wherein the gas-liquid ratio data includes the gas-liquid ratio values ​​of multiple samples arranged in chronological order; Designate any sample as the target sample. Based on the gas-liquid ratio of each sample within the data segment to which the target sample belongs, determine the degree of mutation of the target sample, including: In the formula, For the first The degree of mutation in each sample For the first The gas-liquid ratio of each sample. For the first The mean of all gas-liquid ratio values ​​within the data segment to which each sample belongs. For the first The range of all gas-liquid ratio values ​​within the data segment to which each sample belongs. For the first The data segment to which this sample belongs does not contain the first... The range of the residual gas-liquid ratio values ​​for each sample. For hyperparameters, To normalize the maximum and minimum values, It is the absolute value symbol; Based on the symmetry of the data segments on both sides of the target sample and the degree of mutation, the failure factor of the target sample is determined, including: In the formula, For the first Fault factors for each sample In the first The number of samples within a data segment on either side of a given sample. and The first The sample and the first The gas-liquid ratio values ​​for each sample. It is a natural exponential function; Based on the failure factor, an adaptive number of samples is determined for the Isolation Forest algorithm when detecting target samples, wherein the adaptive number of samples is negatively correlated with the failure factor; Based on the adaptive sample size, the isolated forest algorithm is used to detect anomalies in the target samples, so as to realize the Internet of Things-based gas station hazard warning.

2. The method for early warning of hazards at gas stations based on the Internet of Things according to claim 1, characterized in that, The gas-liquid ratio value is obtained by performing analog-to-digital conversion on the collected raw data.

3. The method for early warning of hazards at gas stations based on the Internet of Things according to claim 1, characterized in that, The data segment to which the target sample belongs is a data segment consisting of the target sample and a predetermined number of samples preceding the target sample.

4. The method for early warning of hazards at gas stations based on the Internet of Things according to claim 1, characterized in that, The data segments on both sides of the target sample are selected with the same preset length on both sides of the target sample as the center.

5. The method for early warning of hazards at gas stations based on the Internet of Things according to claim 1, characterized in that, The adaptive sample size satisfies: ； In the formula, For use in detecting the first The adaptive number of samples for the Isolation Forest algorithm when there are 1 sample. This is the preset initial number of samples in the Isolation Forest algorithm. For the first Fault factors for each sample It is a function with maximum value. It is a natural exponential function. This is for rounding operations.

6. The method for early warning of hazards at gas stations based on the Internet of Things according to claim 5, characterized in that, The initial sample size in the isolated forest algorithm is preset to 256.

7. The method for early warning of hazards at gas stations based on the Internet of Things according to claim 1, characterized in that, The preset parameters of the isolated forest algorithm include an anomaly detection threshold of 0.75 and a preset number of trees of 50.

8. A gas station hazard warning system based on the Internet of Things, characterized in that, include: A processor and a memory, the memory storing computer program instructions, which, when executed by the processor, implement a gas station hazard warning method based on the Internet of Things according to any one of claims 1-7.

Images