Petrochemical logistics storage and transportation safety monitoring method and system based on Internet of Things

Abstract

The present application relates to the field of petrochemical logistics storage and transportation technology, and specifically to a petrochemical logistics storage and transportation safety monitoring method and system based on the Internet of Things, the method comprising: obtaining various monitoring data of various collection locations of the oil transportation pipeline at the current and historical moments; analyzing various monitoring data of the oil pipeline, and constructing a safety threshold range for various monitoring data collected at the target node at the current moment; judging whether the various monitoring data collected at the target node at the current moment is within the corresponding safety threshold range, and monitoring the safety of petrochemical logistics storage and transportation. The present application effectively avoids the occurrence of false detection caused by formulating the detection threshold through the historical data of a single detection point, and can complete the preliminary evaluation of its safety situation in the event of a signal delay.

Description

Technical Field

[0001] The present application relates to the technical field of petrochemical logistics storage and transportation, and specifically to a petrochemical logistics storage and transportation safety monitoring method and system based on the Internet of Things. Background Art

[0002] Petrochemical logistics storage and transportation mainly involves the transportation and storage of oil and related products from the production site to the consumption site. Oil and other products usually have dangerous characteristics such as flammability and explosion. The transportation methods of oil include pipeline transportation, railway transportation, road transportation, etc. The real-time monitoring, data analysis and resource integration capabilities of the Internet of Things technology can effectively solve the real-time monitoring and management of the oil transportation process, so this application intends to use the Internet of Things technology to conduct safety monitoring of the oil storage and transportation process.

[0003] In pipeline transportation, since the pipeline is buried deep underground, when sensors monitor the oil transportation in the pipeline, due to environmental factors such as groundwater and soil, the sensors cannot accurately detect the true state of the pipeline, or after detecting the true state, the interference of factors such as soil affects the stability of data transmission, resulting in inaccurate oil pipeline parameters transmitted to the data analysis module, which in turn causes false alarms in the existing technology of monitoring oil transportation safety by determining the safety threshold through historical data of a single detection point. Summary of the invention

[0004] In order to solve the above technical problems, this application provides a petrochemical logistics storage and transportation safety monitoring method and system based on the Internet of Things. The technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present application provides a petrochemical logistics storage and transportation safety monitoring method based on the Internet of Things, the method comprising the following steps:

[0006] Step 1: Obtain various monitoring data of various collection locations of the oil pipeline at the current and historical moments;

[0007] Step 2: Analyze various monitoring data of the oil pipeline and build a safety threshold range for various monitoring data collected by the target node at the current moment; specifically:

[0008] S1, analyze the overall fluctuation of various monitoring data at the target node and its nearby nodes at all historical moments before the current moment, and determine the estimated parameter values ​​of the target node at the current moment for various monitoring data; use the estimated parameter values ​​of the target node at all acquisition moments for various monitoring data to determine the interference range of various monitoring data at the target node;

[0009] S2, for various monitoring data, align the monitoring data of the target node and its previous node in the target window using the DTW algorithm to obtain multiple corresponding relationships; using the difference in time and number of corresponding data between the two monitoring data in each corresponding relationship, determine the corresponding difference in parameter values ​​of the previous node to the target node in various monitoring data in the target window;

[0010] S3, based on the numerical differences and time intervals between the maximum points and minimum points in all extreme point groups in the target windows of various monitoring data, determine the trust factor of the target windows of various monitoring data; and use the trust factors of all windows and the corresponding differences in the parameter values ​​to determine the difference in the comprehensive time impact of the previous node on the target node in various monitoring data;

[0011] S4, using the influence of the comprehensive time influence difference of the previous node on the target node at various monitoring data on the current moment, determine the estimated normal data of the target node at the current moment of various monitoring data; combined with the interference range of various monitoring data at the target node, construct the safety threshold range corresponding to various monitoring data at the target node at the current moment;

[0012] Step 3: Determine whether the various monitoring data collected by the target node at the current moment are within the corresponding safety threshold range to monitor the safety of petrochemical logistics storage and transportation.

[0013] Preferably, the method for determining the inferred parameter value of the target node in various monitoring data at the current moment is:

[0014] For all the monitoring data of the target node at all historical moments before the current moment, calculate the mean of the monitoring data of the nodes near the target node at any historical moment;

[0015] Calculate the time interval between any historical moment and the current moment, and use the opposite of the time interval as the exponent of an exponential function with a natural constant as the base;

[0016] The product of the mean value of the monitoring data at any historical moment and the exponential function is calculated, and the average value of the product at all historical moments before the current moment is used as the estimated parameter value of the target node in various monitoring data at the current moment.

[0017] Preferably, the calculation methods of the upper limit and the lower limit of the interference range of various monitoring data at the target node are:

[0018] Calculate the difference between the monitored data and the inferred temperature value at the target node at any time;

[0019] The maximum value and the minimum value of the difference at the target node are respectively used as the upper limit and the lower limit of the interference situation range.

[0020] Preferably, the method for determining the corresponding difference of the parameter values ​​of the previous node to the target node in various monitoring data in the target window is:

[0021] For various monitoring data, calculate the number of corresponding relationships between the monitoring data at the target node at each moment in the target window and the monitoring data at the previous node; calculate the number of corresponding relationships between the monitoring data at the previous node at each moment in the target window and the monitoring data at the target node; obtain the reciprocal of the maximum value of the two corresponding numbers;

[0022] Calculate the time interval between the time corresponding to the temperature data at the target node and the time corresponding to the temperature data at the previous node in each corresponding relationship in the target window;

[0023] Calculate the product of the inverse of the corresponding relationship between the target node and its previous node at each moment in the target window and the time interval of the corresponding relationship;

[0024] The average value of the product results of all corresponding relationships in the target window is taken as the corresponding difference of the parameter values ​​of the previous node to the target node in various monitoring data in the target window.

[0025] Preferably, the method for determining the credibility factor of the target window of the various monitoring data is:

[0026] For each extreme point group within the target window of various monitoring data, the ratio of the numerical difference between the maximum point and the minimum point within each extreme point group to the time interval is calculated;

[0027] The accumulated results of the ratios of all extreme point groups in the target windows of various monitoring data are subjected to hyperbolic tangent transformation to obtain the credibility factors of the target windows of various monitoring data.

[0028] Preferably, each extreme value point group consists of a maximum value point and its adjacent minimum value point.

[0029] Preferably, the comprehensive time impact difference of the previous node on the target node in various monitoring data is determined by the cumulative result of the product of the trust factor of all windows in the various monitoring data and the corresponding differences of the parameter values.

[0030] Preferably, the method for determining the estimated normal data of the target node of the various monitoring data at the current moment is:

[0031] Calculate the difference between the comprehensive time impact difference of the current moment and the previous node on the target node in various monitoring data as the impact time of the current moment;

[0032] For various monitoring data, the sum of the monitoring data of the previous node of the target node at the current moment and the comprehensive time impact difference is used as the estimated normal data of the target node of various monitoring data at the current moment.

[0033] Preferably, the method for constructing the safety threshold range of the various monitoring data at the target node at the current moment is:

[0034] The sum of the estimated normal data of the target node of various monitoring data at the current moment and the upper limit of the interference range of various monitoring data at the target node is used as the upper limit of the safety threshold range of various monitoring data at the target node at the current moment;

[0035] The sum of the estimated normal data of the target node of various monitoring data at the current moment and the lower limit of the interference range of various monitoring data at the target node is used as the lower limit of the safety threshold range of various monitoring data at the target node at the current moment.

[0036] In the second aspect, an embodiment of the present application also provides a petrochemical logistics storage and transportation safety monitoring system based on the Internet of Things, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, it implements the steps of any one of the above-mentioned petrochemical logistics storage and transportation safety monitoring methods based on the Internet of Things.

[0037] This application has at least the following beneficial effects:

[0038] At present, safety monitoring is mainly carried out during pipeline transportation of oil, mainly through sensor Internet of Things technology, monitoring various physical and chemical parameters, and analyzing many past data of the detection point through long short-term memory network (LSTM) or self-organizing map neural network (SOM) algorithm to obtain the abnormal threshold of the monitoring point. However, when it comes to interference and delay caused by land, it is inevitable to cause false alarms. This application first analyzes the fluctuation of the target node and nearby nodes at past moments, and constructs their interference in each monitoring dimension. Then, the correlation of the data between the target node and the previous node in the pipeline is analyzed to obtain the influence of the previous node on the detection data of the target node; wherein, the past data is first processed in segments; then the extension relationship of the detection data between the two nodes in the window is analyzed; and then the comprehensive corresponding relationship in the past time series is obtained according to the fluctuation and corresponding relationship of the data in many windows. Finally, the detection threshold of the target node is constructed through the detection data upstream of the target node, combined with the influence relationship of the detection data of the two adjacent nodes and the interference of the land on the data of each dimension. So far, the correction of the detection threshold has been completed, and the oil transportation pipeline is safely detected according to this detection threshold. It can effectively avoid the occurrence of false detection caused by setting detection thresholds through historical data of a single detection point, and at the same time, it can complete the preliminary assessment of its safety situation when the signal is delayed. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 A flow chart of the petrochemical logistics storage and transportation safety monitoring method based on the Internet of Things provided in this application;

[0041] Figure 2 The present application provides a safety threshold range for various monitoring data collected from the target node at the current moment. DETAILED DESCRIPTION

[0042] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of the petrochemical logistics storage and transportation safety monitoring method and system based on the Internet of Things proposed in the present application, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0043] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0044] The specific scheme of the petrochemical logistics storage and transportation safety monitoring method and system based on the Internet of Things provided by the present application is described in detail below with reference to the accompanying drawings.

[0045] An embodiment of the present application provides a petrochemical logistics storage and transportation safety monitoring method and system based on the Internet of Things.

[0046] Specifically, the following petrochemical logistics storage and transportation safety monitoring method based on the Internet of Things is provided, please refer to Figure 1 , the method comprises the following steps:

[0047] Step 1: Obtain various monitoring data of various collection locations of the oil pipeline at the current and historical moments;

[0048] Temperature sensors, pressure sensors, flow sensors, etc. are installed on the oil transportation pipeline to detect the oil transportation process.

[0049] Specifically, a group of sensors is set at a certain interval on the oil transportation pipeline. In this embodiment, the preset interval is 10 meters. The position of a group of sensors set at each certain interval is recorded as a detection node, abbreviated as a node.

[0050] The sensor types include at least temperature sensors, piezoresistive pressure sensors, ultrasonic liquid level sensors and electromagnetic flow meters.

[0051] In this embodiment, the preset collection frequency of the sensor is 2 times / second, and the reference period of collection is the past month.

[0052] Step 2: Analyze various monitoring data of the oil pipeline and build a safety threshold range for various monitoring data collected by the target node at the current moment.

[0053] When transporting oil through pipelines, the continuous flow of oil in the pipeline will cause a certain diffusion effect between the corresponding monitoring data between consecutive nodes. For example, when the oil flows from the upstream node to the next node, the temperatures at the two nodes are relatively similar; the difference is basically caused by pipeline friction and heat dissipation. Since the friction and heat dissipation effects of the pipeline are basically unchanged, the difference between the temperatures monitored at the two nodes will also be relatively stable. Similarly, the monitoring data between it and the downstream node will also have this similarity. Based on this, the estimated data at the target node under normal circumstances can be fitted.

[0054] However, at the corresponding nodes, the impact of soil and groundwater conditions on temperature, pressure and other data is different. Since the pipeline will basically not be constructed near it after it is determined, the interference conditions are basically similar, and the data fluctuations caused by this interference are relatively stable. Therefore, the corresponding monitoring threshold can be constructed by combining the interference conditions of the node on the historical data with the normal data inferred at the node.

[0055] In this application, the process flow chart of constructing the safety threshold range for various monitoring data collected by the target node at the current moment is as shown in the attached figure. Figure 2 As shown, specifically:

[0056] S1, analyze the overall fluctuation of various monitoring data at the target node and its nearby nodes at all historical moments before the current moment, and determine the inferred parameter values ​​of various monitoring data of the target node at the current moment; use the inferred parameter values ​​of various monitoring data of the target node at all collection moments to determine the interference range of various monitoring data at the target node.

[0057] S11, by analyzing the overall fluctuation of the target node and its neighboring nodes under various monitoring data, the estimated parameter value of the target node under various monitoring data at the current moment is determined.

[0058] Since oil has always been transported through pipelines, most of the links from production to transportation are consistent. Among them, the oil passes through the compression station and the heating station, so that the transported oil maintains a certain temperature and pressure in the pipeline. That is, within a small range, the actual data of each node in the pipeline is basically the same; considering that the environmental interference in each place is different, the actual parameter value of the target node at the current moment can be approximated based on the centralized trend of the monitoring data near the target node.

[0059] That is, by analyzing the monitoring data of the nodes near the target node, the estimated parameter value at the current moment is estimated. In this embodiment, temperature data is used as an example. Target Node The estimated temperature at , the calculation expression is:

[0060]

[0061] In the formula, Indicates the current time Target Node The estimated temperature value at Indicates the current time The number of collections at previous historical moments; Represents the target node at the tth historical moment The average temperature value monitored by nearby nodes; Indicates the distance between the tth historical moment and the current moment time interval; Represents an exponential function with the natural constant e as base.

[0062] Among them, in this embodiment, the nodes near the target boundary point are selected as nodes within a preset length from the target node. In this embodiment, the preset length is set to 100 meters, which is specifically set by the implementer.

[0063] It should be understood that It can be used to describe the estimated temperature value at the target node at the corresponding historical moment. The formula is a calculation process of weighted average of the temperature values ​​at all historical moments before the current moment. The weight of the average temperature value at each historical moment is the time interval between the corresponding historical moment and the current time. When the time interval between a historical moment and the current moment is far, the impact of the historical moment on the temperature at the target node at the current moment is smaller. The average temperature value of the nodes near the target node at all historical moments is used to evaluate the estimated temperature value at the target node at the current moment.

[0064] So far, get the current time Target Node The estimated temperature at Similarly, each historical moment can be used as the current moment to be analyzed, so that the estimated parameter values ​​at the target node at each historical moment in the past can be obtained.

[0065] S12, using the estimated parameter values ​​of the target node in various monitoring data at all acquisition moments, determine the interference range of various monitoring data at the target node.

[0066] At a single node, since the land environment and other basic changes do not occur much, the impact of the land and other environments on the monitoring node always fluctuates within a certain range. Therefore, the interference range of the land and other environments on the target monitoring node is determined based on the difference range of its monitoring data relative to the inferred parameter value in the past.

[0067] That is, by analyzing the maximum and minimum values ​​of the difference between the estimated parameter value and the actual monitored temperature value in all historical moments before the current moment of the target node, the interference range of the target node is determined. In this embodiment, temperature data is used as an example to calculate the interference range of the target node. The upper and lower limits of the monitored temperature being disturbed are calculated as follows:

[0068]

[0069]

[0070] In the formula, and Respectively represent the target node The upper and lower limits of the interference of the monitored temperature, that is, the range of the difference between the monitored value and the actual value; Indicates the current time The number of collections at previous historical moments; Indicates time At the target node The temperature value monitored at Indicates time At the target node The estimated temperature value at and They respectively represent the maximum and minimum values ​​of the difference between the monitored temperature and the actual temperature value at many moments.

[0071] Similarly, the scope of interference to which various other monitoring data at the target node are interfered can be obtained.

[0072] S2, for various monitoring data, align the monitoring data of the target node and its previous node in the target window using the DTW algorithm to obtain multiple corresponding relationships; use the differences in time and the number of corresponding data between the two monitoring data in each corresponding relationship to determine the corresponding differences in parameter values ​​of the previous node to the target node in various monitoring data in the target window.

[0073] Since the historical data is huge and not all data at all times are valuable, it is necessary to process the historical data in segments:

[0074] For the target nodes Its previous node (referred to as the reference node ) to monitor the temperature time series data obtained at the location, set the sliding window, the window length is preset to all the data collected in 10 minutes, and the sliding step of the window is all the data collected in 3 minutes. An arbitrarily divided window is used as the target window.

[0075] In the pipeline, oil gradually flows from upstream to downstream. After a certain period of time, the oil at the previous node flows to the next node. At the same time, since oil also flows continuously in liquid form, its physical properties such as temperature, flow rate and pressure will also be transmitted and diffused with the flow. This leads to a certain similarity between the parameter data monitored at the previous node and the parameter data at the next node after a certain period of time. This similarity is relatively stable to a certain extent, that is, the difference between the corresponding parameters of the two nodes and the corresponding relationship in the time interval are relatively stable. Based on this, the corresponding relationship between the data of the target node and its previous node in the target window is constructed. This embodiment takes temperature data as an example for analysis.

[0076] This application is first approved The algorithm aligns the temperature time series data of the two nodes in the target window to obtain the reference node The temperature data at each moment corresponds to the target node The temperature data and the corresponding time. That is, the reference node Temperature data at every moment All correspond to the target node Temperature data at a certain moment The DTW algorithm is a well-known technology and will not be described in detail in this embodiment.

[0077] Since the oil flowing through the previous node needs a certain amount of time to flow to the next node, but the previous segmentation was directly based on the time moment, this results in the initial part of the oil at the target node in any time period not having the corresponding oil from the previous node for matching reference. Similarly, the oil from the previous node cannot flow to the next node in this time period, which results in the two segments of data having little or no reference significance.

[0078] Considering The correspondence within the window obtained by the algorithm is mainly based on its change law. Although it can complete the correspondence at each data point, since the window division is directly divided according to time, it leads to the previous node (reference node ) is not in the next node (target node ), which makes some nodes unable to correspond, but in In the algorithm, it will still be associated, which will cause a one-to-many situation, but this correspondence is unreliable. Based on this, the corresponding credibility of the correspondence between the target node at each moment and its previous node is constructed. In this embodiment, the target node at time t in the target window and its previous node (reference node ) , the calculation expression is:

[0079]

[0080] In the formula, Indicates the time in the target window Target Node With reference node The corresponding credibility of the corresponding relationship between Indicates the time in the target window Reference Node Temperature data At the target node The number of corresponding relationships between the temperature data at Indicates the time in the target window Target Node Temperature data At the reference node The number of corresponding relationships between the temperature data at ; max represents the maximum value function.

[0081] It should be understood that time Target Node With reference node The more corresponding data there are, the more the moment can be used to characterize the data changes in the monitoring data within the window. Target Node With reference node The higher the credibility of the correspondence between them.

[0082] The above analysis shows that oil flows from the previous node, and because of the viscosity of oil, its flow speed is relatively difficult to change, which results in the time required for oil to flow from the previous node to the target node being stable in a short period of time; and because the oil pipeline is not affected by the outside world, the heat dissipation and frictional heat generation of oil in the same section of the pipeline will also remain relatively unchanged, which results in the difference in oil conditions between the previous node and the target node being relatively stable. That is, the correspondence and difference relationship between the parameters of the two nodes will not change over time.

[0083] To describe the general correspondence between two nodes in the window period, it is necessary to consider and analyze the concentration trend of many correspondences. The above analysis results are not applicable to all correspondences, so it is necessary to weight the correspondence in the window by the corresponding credibility of the correspondence on a single data, and thus construct a general correspondence in the window. In this application, the time relationship is taken as an example to weight the time relationship. For the target node The corresponding difference of parameter values ​​at temperature data For example, the calculation expression is:

[0084]

[0085] Where K represents the number of corresponding relations in the target window, Indicates the target window The target node in the corresponding relationship Temperature data The corresponding time and reference node Temperature data the time interval between corresponding moments; Indicates the time in the target window Target Node With reference node The corresponding credibility of the corresponding relationship between them.

[0086] It should be understood that the above analysis analyzes the corresponding relationship between the temperature data of the two nodes in the target window in terms of time and the corresponding data quantity. When the time interval between the corresponding relationships is larger and the corresponding credibility is smaller, it means that the corresponding relationship calculated by the two nodes in the target window is less credible, which can be used to indicate that the corresponding difference in the parameter value of the reference node to the target node in the temperature data within the window period is larger.

[0087] S3, based on the numerical differences and time intervals between the maximum points and minimum points in all extreme point groups in the target windows of various monitoring data, determine the trust factors of the target windows of various monitoring data; and use the trust factors of all windows and the corresponding differences in the parameter values ​​to determine the comprehensive time impact difference of the previous node on the target node in various monitoring data.

[0088] Safety monitoring of oil pipeline transportation is a relatively long process. During this process, it is relatively safe most of the time, and the oil situation in the pipeline has not changed much. The above analysis uses a period of time as an example to analyze the corresponding relationship between the oil situation of two adjacent nodes, but it is based on the synchronous change of the data between the two nodes (the previous node changes, and the next node follows), which leads to the fact that the corresponding relationship obtained from the stable data for most of the time is difficult to clarify this synchronization, making it unreliable. That is, the past time series data is divided into many small windows for analysis, but the temperature data in some windows has basically no fluctuation, resulting in the corresponding relationship obtained through its analysis is not obvious, that is, the corresponding relationship obtained in the window with more and larger fluctuations in the detection data is more reliable than the window with smaller or even no data fluctuations.

[0089] Therefore, it is necessary to analyze the credibility factor of each window. In this embodiment, the credibility factor of temperature data in the target window is For example, the calculation expression is:

[0090]

[0091] In the formula, represents the hyperbolic tangent function; N represents the number of extreme value point groups in the differential data of the temperature data in the target window, where each extreme value point group consists of a maximum value point and its adjacent minimum value point; In the differential data representing the temperature data within the target window, The difference between the maximum and minimum points in the extreme point group; Indicates the target window The time interval corresponding to the maximum point and the minimum point in an extreme point group.

[0092] It should be understood that the difference between the two extreme points To describe the size of the data fluctuation within the window, It is used to represent the weighted mean of the differences between multiple groups of extreme values, describing the severity of the fluctuation of the detected data in the current window. The weight is the time interval corresponding to the maximum and minimum points in the extreme point group.

[0093] At this point, the accuracy of the corresponding relationship between the two nodes in the corresponding period can be described by analyzing the fluctuation amplitude and speed of the oil temperature data at two nodes in the oil pipeline in each window, and the credibility factor of each window can be obtained accordingly.

[0094] Then, the credibility factor can be used to perform a weighted average on the corresponding relationships obtained from many windows in the past time, thereby increasing the credibility weight of the corresponding relationships in the time periods with high corresponding accuracy, that is, large fluctuations, and obtaining the influence relationship of the temperature data between two nodes in the oil pipeline in the entire past time series.

[0095] This application uses the above node (reference node ) for the target node The integrated time effect difference in temperature data For example, the calculation expression is:

[0096]

[0097] In the formula, P represents the number of windows, Indicates Reference nodes in the window For the target node The corresponding difference in parameter values ​​at the temperature data is the time taken for the oil to flow over in the corresponding period; Indicates that the temperature data is The credibility factor of the window.

[0098] It should be understood that the reference node can be calculated For the target node The comprehensive parameters affect the difference , that is, the temperature change of oil flowing from the previous node to the target node can be calculated by the same calculation method.

[0099] So far, through the correlation analysis of numerous data on oil temperature and time between two nodes in the historical time series, the influence relationship of the previous node on the target node in temperature data was obtained.

[0100] S4, using the impact of the previous node on the target node's comprehensive time impact difference on various monitoring data at the current moment, determine the estimated normal data of the target node of various monitoring data at the current moment; combined with the interference range of various monitoring data at the target node, construct the corresponding safety threshold range of various monitoring data at the target node at the current moment.

[0101] Taking temperature data as an example, the above analysis shows the impact of the previous node on the monitoring data of the current node between two adjacent nodes in the oil pipeline.

[0102] That is, in an oil pipeline, the flow of oil is continuous, flowing from one node to the next node. The temperature of the previous node at the current moment is constant at the next node at the next moment, because its initial temperature has been monitored, and its temperature drop and temperature rise in the pipeline can be obtained through past temperature changes, and its flow rate can also be analyzed. Based on this influence relationship, the estimated normal data at the target node can be estimated based on the monitoring data at the corresponding time on the adjacent nodes.

[0103] Based on this, this application analyzes the estimated normal data of various monitoring data at the target node at the current moment, taking the temperature data as the target node Estimated normal temperature at the current time For example, the calculation expression is:

[0104]

[0105] In the formula, Indicates the current time The impact moment, Represents the reference node At the present moment Moments of Impact The monitored temperature value at Represents the reference node For the target node The integrated time effect difference in the temperature data.

[0106] In the above formula, the current time Moments of Impact The way to obtain is: ; In the formula, Indicates the current moment.

[0107] At this point, the estimated normal temperature of the target node at the current moment is obtained. The estimated normal data of the target node at the current moment, such as pressure and flow, can be constructed through the same calculation logic.

[0108] Then, combined with the interference range of various monitoring data at the target node, the safety threshold range of various monitoring data at the target node is constructed:

[0109]

[0110]

[0111] In the formula, and Respectively represent the target node at the current moment The upper and lower safety thresholds of the temperature data; Indicates the target node the estimated normal temperature at the present moment; and Respectively represent the target nodes The upper and lower limits of the interference range where the monitored temperature is disturbed.

[0112] At this point, the upper and lower limits of the corrected temperature safety threshold are obtained.

[0113] Similarly, the safety threshold ranges for pressure, flow, liquid level, etc. can be obtained based on the same logical method.

[0114] Step 3: Determine whether the various monitoring data collected by the target node at the current moment are within the corresponding safety threshold range to monitor the safety of petrochemical logistics storage and transportation.

[0115] When the monitored data is not within the safety threshold range of the corresponding monitoring type, it means that the currently monitored node is at risk of oil leakage or other dangerous situations. At this time, an alarm signal is issued and preset measures are taken.

[0116] Based on the same inventive concept as the above method, an embodiment of the present application also provides a petrochemical logistics storage and transportation safety monitoring system based on the Internet of Things, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above methods for petrochemical logistics storage and transportation safety monitoring methods based on the Internet of Things are implemented.

[0117] The various embodiments in the present application are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0118] It should be noted that, unless otherwise specified and limited, terms such as "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such article or device. In the absence of further restrictions, an element defined by the sentence "including one..." does not exclude the existence of other identical elements in the article or device including the element. In addition, the term "and\or" used herein includes any and all combinations of one or more related listed items.

[0119] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not invented by the present application.

[0120] It should be understood that the present application is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof.

Claims

1. A petrochemical logistics storage and transportation safety monitoring method based on the Internet of Things, characterized in that: The method comprises the following steps: Step 1: Obtain various monitoring data of various collection locations of the oil pipeline at the current and historical moments; Step 2: Analyze various monitoring data of the oil pipeline and build a safety threshold range for various monitoring data collected by the target node at the current moment; specifically: S1, analyze the overall fluctuation of various monitoring data at the target node and its nearby nodes at all historical moments before the current moment, and determine the estimated parameter values ​​of the target node at the current moment for various monitoring data; use the estimated parameter values ​​of the target node at all acquisition moments for various monitoring data to determine the interference range of various monitoring data at the target node; S2, for various monitoring data, align the monitoring data of the target node and its previous node in the target window using the DTW algorithm to obtain multiple corresponding relationships; for various monitoring data, calculate the number of corresponding relationships between the monitoring data at the target node at each moment in the target window and the monitoring data at its previous node; calculate the number of corresponding relationships between the monitoring data at the previous node at each moment in the target window and the monitoring data at its target node; obtain the reciprocal of the maximum value of the two corresponding numbers; calculate the time interval between the moment corresponding to the temperature data at the target node and the moment corresponding to the temperature data at the previous node in each corresponding relationship in the target window; calculate the product result of the reciprocal of the corresponding relationship calculated between the target node and its previous node at each moment in the target window and the time interval of the corresponding relationship; take the average value of the product results of all corresponding relationships in the target window as the corresponding difference of the parameter values ​​of the previous node to the target node in various monitoring data in the target window; S3, for each extreme point group in the target window of various monitoring data, calculate the ratio of the numerical difference between the maximum point and the minimum point in each extreme point group to the time interval; perform a hyperbolic tangent transformation on the cumulative result of the ratio of all extreme point groups in the target window of various monitoring data to obtain the credible factor of the target window of various monitoring data; and use the credible factors of all windows and the corresponding differences of the parameter values ​​to determine the comprehensive time influence difference of the previous node on the target node in various monitoring data; S4, using the influence of the comprehensive time influence difference of the previous node on the target node at various monitoring data on the current moment, determine the estimated normal data of the target node at the current moment of various monitoring data; combined with the interference range of various monitoring data at the target node, construct the safety threshold range corresponding to various monitoring data at the target node at the current moment; Step 3: Determine whether the various monitoring data collected by the target node at the current moment are within the corresponding safety threshold range to monitor the safety of petrochemical logistics storage and transportation.

2. The petrochemical logistics storage and transportation safety monitoring method based on the Internet of Things as claimed in claim 1 is characterized in that: The method for determining the inferred parameter value of the target node in various monitoring data at the current moment is: For all the monitoring data of the target node at all historical moments before the current moment, calculate the mean of the monitoring data of the nodes near the target node at any historical moment; Calculate the time interval between any historical moment and the current moment, and use the opposite of the time interval as the exponent of an exponential function with a natural constant as the base; The product of the mean of the monitoring data at any historical moment and the exponential function is calculated, and the average value of the product at all historical moments before the current moment is used as the estimated parameter value of the target node in various monitoring data at the current moment.

3. The petrochemical logistics storage and transportation safety monitoring method based on the Internet of Things as claimed in claim 1 is characterized in that: The calculation methods of the upper and lower limits of the interference range of various monitoring data at the target node are: Calculate the difference between the monitored data and the inferred temperature value at the target node at any time; The maximum value and the minimum value of the difference at the target node are respectively used as the upper limit and the lower limit of the interference situation range.

4. The petrochemical logistics storage and transportation safety monitoring method based on the Internet of Things as claimed in claim 1 is characterized in that: Each extreme value point group consists of a maximum value point and its adjacent minimum value points.

5. The petrochemical logistics storage and transportation safety monitoring method based on the Internet of Things as claimed in claim 1 is characterized in that: The comprehensive time impact difference of the previous node on the target node in various monitoring data is determined by the cumulative result of the product of the corresponding differences of the credible factors and the parameter values ​​of all windows in the various monitoring data.

6. The petrochemical logistics storage and transportation safety monitoring method based on the Internet of Things as claimed in claim 1 is characterized in that: The method for determining the estimated normal data of the target node of the various monitoring data at the current moment is: Calculate the difference between the comprehensive time impact difference of the current moment and the previous node on the target node in various monitoring data as the impact time of the current moment; For various monitoring data, the sum of the monitoring data of the previous node of the target node at the current moment and the comprehensive time impact difference is used as the estimated normal data of the target node of various monitoring data at the current moment.

7. The petrochemical logistics storage and transportation safety monitoring method based on the Internet of Things as claimed in claim 3 is characterized in that: The method for constructing the safety threshold range of various monitoring data at the target node at the current moment is: The sum of the estimated normal data of the target node of various monitoring data at the current moment and the upper limit of the interference range of various monitoring data at the target node is used as the upper limit of the safety threshold range of various monitoring data at the target node at the current moment; The sum of the estimated normal data of the target node of various monitoring data at the current moment and the lower limit of the interference range of various monitoring data at the target node is used as the lower limit of the safety threshold range of various monitoring data at the target node at the current moment.

8. A petrochemical logistics storage and transportation safety monitoring system based on the Internet of Things, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the petrochemical logistics storage and transportation safety monitoring method based on the Internet of Things as described in any one of claims 1-7 are implemented.

Images