Anomaly detection method for a tank container, electronic device, and storage medium

Abstract

The application provides an abnormality detection method for a tank container, an electronic device and a storage medium, and belongs to the technical field of container supervision. In each detection period, the absolute value of the difference between the sensor data of the sensor node in the current detection period and the sensor data updated by the sensor node in the last detection period is calculated, and the size of the absolute value of the difference and the first preset threshold are compared, so that it can be judged whether the event triggering condition is met. If it is met, the event triggering mechanism is triggered, at this time, the test statistic of the sensor node in the current detection period is calculated, and the tank container can be detected according to the test statistic whether it is in an abnormal state. That is, by setting the event triggering mechanism, the iteration update can be stopped after the event triggering mechanism is triggered, so that the iteration number can be effectively reduced, and the problem of waste of communication resources caused by too many iteration numbers can be solved.

Description

Technical Field

[0001] This application relates to the field of container monitoring technology, and in particular to an anomaly detection method, electronic equipment and storage medium for tank containers. Background Technology

[0002] Container shipping is one of the most important modes of international and domestic trade cargo transportation. With the development of information technology and the Internet of Things (IoT), the market demands more diversified container needs and more sophisticated management. Therefore, end-to-end monitoring of the container shipping process is essential.

[0003] Currently, centralized anomaly monitoring methods for containers require centralized processing of data collected from each node, resulting in higher computational and communication costs compared to distributed anomaly monitoring. While traditional distributed anomaly monitoring methods based on average consistency can reduce computational load and communication volume through information communication between sensor nodes, they suffer from wasted communication resources when the number of iterations exceeds a certain threshold. Summary of the Invention

[0004] The main objective of this application is to propose an anomaly detection method, electronic device, and storage medium for tank containers, aiming to set up an event triggering mechanism that can reduce the number of iterations, thereby solving the problem of a large waste of communication resources under the traditional average consensus algorithm.

[0005] To achieve the above objectives, a first aspect of this application proposes an anomaly detection method for a tank container, wherein the tank container includes multiple sensor nodes arranged in a distributed manner, the multiple sensor nodes being used to collect sensor data corresponding to different locations on the tank container, and adjacent sensor nodes communicating with each other, the detection method comprising:

[0006] In each detection cycle, the sensor node acquires the sensor data updated by the adjacent sensor node in the previous detection cycle, and iteratively updates the sensor data updated by the sensor node in the previous detection cycle and the sensor data updated by the adjacent sensor node in the previous detection cycle to obtain the sensor data corresponding to the sensor node in the current detection cycle.

[0007] Calculate the absolute value of the difference between the sensor data of the sensor node in the current detection cycle and the sensor data updated by the sensor node in the previous detection cycle, and determine whether the absolute value of the difference is less than a first preset threshold.

[0008] When the absolute value of the difference is less than the first preset threshold, the test statistics of the sensor node in the current detection cycle are calculated based on the sensor data of the sensor node in the current detection cycle, the total number of the sensor nodes, and the first preset threshold.

[0009] The test statistics are used to detect whether the tank container is in an abnormal state.

[0010] In one embodiment of this application, detecting whether the tank container is in an abnormal state based on the test statistics includes:

[0011] Determine whether the test statistic is greater than a second preset threshold;

[0012] If the test statistic is greater than the second preset threshold, then the tank container is determined to be in an abnormal state.

[0013] If the test statistics are less than or equal to the second preset threshold, then the tank container is determined to be in a normal state.

[0014] In one embodiment of this application, the method further includes:

[0015] In the first detection cycle, the sensor node normalizes the real-time sensor data collected in history to obtain the sensor data corresponding to the sensor node in the first detection cycle.

[0016] In one embodiment of this application, the sensor node normalizes the historically collected real-time sensor data to obtain the sensor data corresponding to the first detection cycle using the following formula:

[0017]

[0018] In the formula, y i,0 This represents the sensor data corresponding to sensor node i in the first detection cycle, y i This represents the real-time sensor data collected by sensor node i. ∑ represents the average value of sensor data calculated by sensor node i based on historically collected real-time sensor data. i This represents the variance of sensor data calculated by sensor node i based on historically collected real-time sensor data, and m represents the dimension of the data collected by sensor node.

[0019] In one embodiment of this application, the sensor node iteratively updates the sensor data obtained by the sensor node in the previous detection cycle and the sensor data obtained by the adjacent sensor nodes in the previous detection cycle to obtain the sensor data corresponding to the sensor node in the current detection cycle, including:

[0020] Based on the distribution of the multiple sensor nodes in the tank container, determine the weighting matrix between each sensor node;

[0021] According to the weighting matrix, the sensor data updated by the sensor node in the previous detection cycle and the sensor data updated by the adjacent sensor node in the previous detection cycle are weighted to obtain the sensor data corresponding to the sensor node in the current detection cycle.

[0022] In one embodiment of this application, the weighting matrix corresponding to each sensor node is calculated using the following formula:

[0023]

[0024] In the formula, w ij L represents the weight of sensor node i relative to sensor node j. i Let d represent the set of neighboring sensor nodes of sensor node i. g d represents the maximum distance between any two sensor nodes on a tank container. g (i) represents the number of sensor nodes adjacent to sensor node i.

[0025] In one embodiment of this application, the sensor node iteratively updates the sensor data obtained by the sensor node in the previous detection cycle and the sensor data obtained by the adjacent sensor node in the previous detection cycle to obtain the sensor data corresponding to the sensor node in the current detection cycle using the following formula:

[0026]

[0027] In the formula, y i,k+1 y represents the sensor data corresponding to sensor node i in the current detection cycle. i,k y represents the sensor data corresponding to sensor node i in the previous detection cycle. j,k w represents the sensor data of the adjacent sensor node j in the previous detection cycle. ii w represents the weight of sensor node i relative to itself. ij L represents the weight of adjacent sensor node j relative to sensor node i. i This represents the set of neighboring sensor nodes of sensor node i.

[0028] In one embodiment of this application, the calculation of the test statistics of the sensor node in the current detection period based on the sensor data of the sensor node in the current detection period, the total number of sensor nodes, and the first preset threshold is performed by the following formula:

[0029]

[0030] In the formula, J i This represents the test statistics corresponding to sensor node i in the current detection cycle, M represents the total number of sensor nodes, δ represents the first preset threshold, and y represents the test statistics corresponding to sensor node i in the current detection cycle. i,k+1 This represents the sensor data corresponding to sensor node i in the current detection cycle.

[0031] To achieve the above objectives, a second aspect of this application provides an electronic device, the electronic device including a memory and at least one processor, the memory storing a computer program, and the at least one processor executing the computer program to implement the method of the first aspect of this application.

[0032] To achieve the above objectives, a third aspect of the present application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method of the first aspect of the present application.

[0033] In the technical solution provided in this application embodiment, in each detection cycle, after acquiring the sensor data updated by adjacent sensor nodes in the previous detection cycle, the sensor node can update the sensor data corresponding to the current detection cycle based on the sensor data updated by adjacent sensor nodes in the previous detection cycle, and calculate the absolute value of the difference between the sensor data corresponding to the current detection cycle and the sensor data updated by the sensor node in the previous detection cycle. Therefore, if the absolute value of this difference is less than a first preset threshold, it indicates that the event triggering condition is met, and the event triggering mechanism is triggered. At this time, the test statistics corresponding to the sensor node in the current detection cycle are calculated, and the tank container can be detected as being in an abnormal state based on the test statistics. That is, by setting an event triggering mechanism, this application can stop iterative updates after the event triggering mechanism is triggered, thereby effectively reducing the number of iterations and solving the problem of communication resource waste caused by excessive iterations.

[0034] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0035] Figure 1This is a flowchart of an anomaly detection method for tank containers provided in one embodiment of this application.

[0036] Figure 2 This is a schematic diagram of the sensor node distribution of a tank container provided in one embodiment of this application.

[0037] Figure 3 This is an embodiment of the sensor network undirected communication topology diagram of a tank container provided in this application.

[0038] Figure 4 This is a flowchart illustrating the steps of a sensor node in one embodiment of the present application to iteratively update the sensor data obtained by the sensor node in the previous detection cycle and the sensor data obtained by the adjacent sensor nodes in the previous detection cycle to obtain the sensor data corresponding to the sensor node in the current detection cycle.

[0039] Figure 5 This is a flowchart of the steps for detecting whether a tank container is in an abnormal state based on test statistics, provided in one embodiment of this application.

[0040] Figure 6 This is a real-time temperature monitoring graph corresponding to sensor node 1 provided in an embodiment of this application.

[0041] Figure 7 This is a graph showing the test statistics judgment results corresponding to sensor node 1 under normal conditions, provided in an embodiment of this application.

[0042] Figure 8 This is a graph showing the test statistics judgment results for sensor node 1 under abnormal conditions, as provided in the embodiments of this application.

[0043] Figure 9 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0045] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0046] Unless otherwise defined, 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. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0047] Tank containers are mainly used for long-distance transportation of gases, liquids, and hazardous materials. Some liquid cargoes are quite sensitive to temperature; during storage and transportation, product temperature has a significant impact on quality and safety, such as MDI (diphenylmethane diisocyanate) and electrolytes. Therefore, online monitoring of abnormal conditions is necessary.

[0048] Currently, centralized anomaly monitoring methods for containers require centralized processing of data collected from each node, resulting in higher computational and communication costs compared to distributed anomaly monitoring. While traditional distributed anomaly monitoring methods based on average consistency can reduce computational load and communication volume through inter-node communication, they suffer from wasted communication resources when the number of iterations exceeds a certain threshold.

[0049] Based on this, this application proposes an anomaly detection method for tank containers, which aims to set up an event triggering mechanism to reduce the number of iterations, thereby solving the problem of a large waste of communication resources under the traditional average consensus algorithm.

[0050] Reference Figure 1 , Figure 1 This is a flowchart of an anomaly detection method for tank containers provided in an embodiment of this application, including but not limited to steps S110 to S140.

[0051] In step S110, during each detection cycle, the sensor node acquires the sensor data updated by the adjacent sensor node in the previous detection cycle, and iteratively updates the sensor data updated by the sensor node in the previous detection cycle and the sensor data updated by the adjacent sensor node in the previous detection cycle to obtain the sensor data corresponding to the sensor node in the current detection cycle.

[0052] In this embodiment, the tank container includes multiple sensor nodes arranged in a distributed manner. These sensor nodes are used to collect sensor data at different locations on the tank container, including temperature, pressure, humidity, etc. The data to be monitored varies depending on the cargo loaded in the tank container. For example, if the cargo loaded in the tank container is MDI (Multi-Specific Identifier), then the data to be monitored is temperature. Adjacent sensor nodes communicate with each other, enabling the interaction and iterative updating of sensor data between adjacent nodes.

[0053] For example, refer to Figures 2-3 , Figure 2This is a schematic diagram of the sensor node distribution of a tank container provided in one embodiment of this application. Figure 3 This is an embodiment of the sensor network undirected communication topology diagram of a tank container provided in this application. Eight sensor nodes are distributed on the tank container to collect temperature data at different locations. The adjacent nodes of sensor node 1 include sensor nodes 2 and 8; the adjacent nodes of sensor node 2 include sensor nodes 1 and 3; the adjacent nodes of sensor node 3 include sensor nodes 2 and 4; the adjacent nodes of sensor node 4 include sensor nodes 3 and 5; the adjacent nodes of sensor node 5 include sensor nodes 4 and 6; the adjacent nodes of sensor node 6 include sensor nodes 5 and 7; the adjacent nodes of sensor node 7 include sensor nodes 6 and 8; and the adjacent nodes of sensor node 8 include sensor nodes 1 and 7. The adjacent sensor nodes communicate with each other, allowing the current sensor node to iteratively update its sensor data based on the sensor data sent by its neighboring sensor nodes.

[0054] Specifically, in the first detection cycle, the sensor node normalizes the historically acquired real-time sensor data to obtain the sensor data corresponding to the sensor node in the first detection cycle. For example, anomaly detection can be set to occur every 60 seconds, i.e., the detection cycle is set to 60 seconds. If sensor node i can acquire sensor data every 1 second, then in the first detection cycle, sensor node i acquires 60 real-time sensor data. At this time, sensor node i can normalize the 60 historically acquired real-time sensor data to obtain the sensor data corresponding to sensor node i in the first detection cycle. Specifically, the normalization of the historically acquired real-time sensor data by sensor node i can be calculated using the following formula 1:

[0055]

[0056] In Equation 1, y i,0 This represents the sensor data corresponding to sensor node i in the first detection cycle, y i This represents the real-time sensor data collected by sensor node i. This represents the average value of sensor data calculated by sensor node i based on historically collected real-time sensor data. Sensor node i collected N historical data before the first detection cycle. i Real-time sensor data, Σ i This represents the variance of sensor data calculated by sensor node i based on historically collected real-time sensor data. m represents the dimension of the data collected by sensor node i. For example, if sensor node i is used to collect temperature data, then m = 1. If sensor node i is used to collect temperature and pressure data, then m = 2. If sensor node i is used to collect temperature, pressure, and humidity data, then m = 3.

[0057] In this embodiment, sensor node i normalizes the historically collected real-time sensor data to obtain the sensor data y corresponding to the first detection cycle. i,0 Subsequently, in the next detection cycle, sensor node i can acquire the sensor data updated by its neighboring sensor node j in the previous detection cycle. After acquiring the sensor data updated by its neighboring sensor node j in the previous detection cycle, sensor node i and its neighboring sensor node j are iteratively updated to obtain the sensor data corresponding to sensor node i in the current detection cycle.

[0058] Reference Figure 4 , Figure 4 This application provides a flowchart of the steps for a sensor node to iteratively update the sensor data obtained by the sensor node in the previous detection cycle and the sensor data obtained by the adjacent sensor nodes in the previous detection cycle to obtain the sensor data corresponding to the sensor node in the current detection cycle, including but not limited to steps S410 to S420.

[0059] Step S410: Determine the weighting matrix between each sensor node based on the distribution of multiple sensor nodes in the tank container.

[0060] Step S420: Based on the weighting matrix, the sensor data updated by the sensor node in the previous detection period and the sensor data updated by the adjacent sensor nodes in the previous detection period are weighted to obtain the sensor data corresponding to the sensor node in the current detection period.

[0061] In this embodiment, the weighting matrix between multiple sensor nodes can be determined based on their distribution within the tank container. Specifically, the weighting matrix between the sensor nodes can be calculated using the following Equation 2:

[0062]

[0063] In Equation 2, w ij L represents the weight of sensor node i relative to sensor node j. i Let d represent the set of neighboring sensor nodes of sensor node i, and let j represent the sensor node that is distinct from sensor node i. gd represents the maximum distance between any two sensor nodes on a tank container. g (i) represents the number of sensor nodes adjacent to sensor node i.

[0064] As shown in Equation 2, the weights of each adjacent sensor node relative to sensor node i are equal, and are all equal to... The weight w of sensor node i relative to itself ii equal The weights of all sensor nodes that are not adjacent to sensor node i relative to sensor node i are all 0.

[0065] In this embodiment of the application, if the tank container has M sensor nodes, i.e., L = {1,2,3,……M}, then w ij The matrix formed It satisfies I T W = I T WI = I, in, For matrix The spectral radius is given by I, which represents the identity matrix.

[0066] by Figure 3 As shown, there are 8 sensor nodes distributed on the tank container. The maximum distance d between any two sensor nodes on the tank container is... g If the weighting is 4, then the weighting matrix between each sensor node can be obtained as follows:

[0067]

[0068] It can be seen that, for sensor node 1, the weight of sensor node 1 relative to itself... Weight of sensor node 2 relative to sensor node 1 Weight of sensor node 8 relative to sensor node 1 The weights w of other sensor nodes (including sensor node 3, sensor node 4, sensor node 5, sensor node 6, and sensor node 7) relative to sensor node 1. 13 =w 14 =w 15 =w 16 =w 17 =0.

[0069] In this embodiment of the application, after determining the weighting matrix between each sensor node based on the distribution of multiple sensor nodes in the tank container, the sensor data updated by the sensor node in the previous detection cycle and the sensor data updated by the adjacent sensor nodes in the previous detection cycle can be weighted according to the weighting matrix to obtain the sensor data corresponding to the sensor node in the current detection cycle.

[0070] Specifically, the sensor data corresponding to sensor node i in the current detection cycle can be calculated using the following equation 3:

[0071]

[0072] In Equation 3, y i,k+1 y represents the sensor data corresponding to sensor node i in the current detection cycle. i,k y represents the sensor data corresponding to sensor node i in the previous detection cycle. j,k w represents the sensor data of the adjacent sensor node j in the previous detection cycle. ii w represents the weight of sensor node i relative to itself. ij L represents the weight of adjacent sensor node j relative to sensor node i. i Let represent the set of neighboring sensor nodes of sensor node i. d g d represents the maximum distance between any two sensor nodes on a tank container. g (i) represents the number of adjacent sensor nodes that are adjacent to sensor node i.

[0073] by Figure 3 Taking sensor node 1 as an example, sensor node 1 performs normalization processing on the historically collected real-time sensor data to obtain the sensor data y corresponding to the first detection cycle. 1,0 Then, sensor node 1 can acquire sensor data sent by adjacent sensor nodes 2 and 8. After acquiring the sensor data sent by adjacent sensor nodes 2 and 8, sensor node 1 can update the sensor data y obtained by sensor node 1 in the previous detection cycle. 1,0 The sensor data y obtained by sensor node 2 in the previous detection cycle 2,0 Sensor data y obtained by sensor node 8 in the previous detection cycle 8,0 Perform iterative updates to obtain the sensor data y corresponding to sensor node 1 in the current detection cycle. 1,1 , that is, y 1,1 =w 11 *y 1,0 +w 12 *y 2,0 +w18 *y 8,0 =0.6y 1,0 +0.2y 2,0 +0.2y 8,0 In this way, the iteratively updated sensor data for each sensor node in each detection cycle can be calculated.

[0074] Step S120: Calculate the absolute value of the difference between the sensor data corresponding to the sensor node in the current detection cycle and the sensor data updated by the sensor node in the previous detection cycle, and determine whether the absolute value of the difference is less than the first preset threshold.

[0075] In this embodiment, considering that traditional distributed anomaly monitoring methods based on average consistency can reduce computational load and communication volume, but suffer from wasted communication resources when there are too many iterations, this embodiment sets up an event triggering mechanism. Specifically, an event triggering condition is set, and the mechanism is triggered when the condition is met. By setting a first preset threshold, after the sensor node calculates the sensor data corresponding to the current detection cycle, the absolute value of the difference between the sensor data corresponding to the current detection cycle and the sensor data updated in the previous detection cycle can be further calculated. The current detection cycle is then judged to meet the event triggering condition by determining whether the absolute value of the difference is less than the first preset threshold. If the absolute value of the difference is less than the first preset threshold, the current detection cycle is determined to meet the event triggering condition. In this case, the tank container may be abnormal. However, if the absolute value of the difference is greater than or equal to the first preset threshold, the current detection cycle is determined not to meet the event triggering condition, and the tank container is not abnormal.

[0076] Step S130: When the absolute value of the difference is less than the first preset threshold, calculate the test statistics corresponding to the sensor node in the current detection cycle based on the sensor data corresponding to the sensor node in the current detection cycle, the total number of sensor nodes, and the first preset threshold.

[0077] In this embodiment, when the absolute value of the difference between the sensor data of the sensor node in the current detection period and the sensor data updated by the sensor node in the previous detection period is less than a first preset threshold, it is determined that the current detection period meets the event triggering condition. At this point, it is necessary to further calculate the test statistics of the sensor node in the current detection period based on the sensor data of the sensor node in the current detection period, the total number of sensor nodes, and the first preset threshold, so as to determine whether the tank container is in an abnormal state based on the test statistics of the current detection period. Specifically, the test statistics of the sensor node in the current detection period can be calculated using the following formula 4:

[0078]

[0079] In Equation 4, J i This represents the test statistics corresponding to sensor node i in the current detection cycle, M represents the total number of sensor nodes, δ represents the first preset threshold, and y represents the test statistics corresponding to sensor node i in the current detection cycle. i,k+1 This represents the sensor data corresponding to sensor node i in the current detection cycle.

[0080] Step S140: Detect whether the tank container is in an abnormal state based on the test statistics.

[0081] In this embodiment of the application, after calculating the test statistics corresponding to the current detection cycle, it is possible to detect whether the tank container is in an abnormal state based on the test statistics corresponding to the current detection cycle.

[0082] Reference Figure 5 , Figure 5 This is a flowchart of steps for detecting whether a tank container is in an abnormal state based on test statistics, provided in an embodiment of this application, including but not limited to steps S510 to S530.

[0083] Step S510: Determine whether the test statistic is greater than the second preset threshold;

[0084] Step S520: If the test statistic is greater than the second preset threshold, then the tank container is determined to be in an abnormal state.

[0085] Step S530: If the test statistic is less than or equal to the second preset threshold, then the tank container is determined to be in a normal state.

[0086] In this embodiment, after calculating the test statistics corresponding to the current detection cycle, it can be determined whether the test statistics corresponding to the current detection cycle are greater than a second preset threshold to determine whether the tank container is in an abnormal state. Specifically, if the test statistics are greater than the second preset threshold, the tank container is determined to be in an abnormal state; if the test statistics are less than or equal to the second preset threshold, the tank container is determined to be in a normal state.

[0087] by Figure 3 Taking the distribution of sensor nodes in a tank container as an example, the data collected by each sensor node has a dimension of 1, i.e., m = 1. Furthermore, before the first detection cycle, each sensor node has collected 6000 real-time sensor data points for offline training, measuring the variance ∑ of the noise. i =0.2. Eight sensor nodes are distributed on the tank container, i.e., M=8. Let the event trigger condition value δ=0.01, i.e., the first preset threshold is 0.01. The second preset threshold J... th =3.84. Reference Figures 6-8 , Figure 6 This is a real-time temperature monitoring graph corresponding to sensor node 1 provided in an embodiment of this application. Figure 7 This is a graph showing the test statistics judgment results corresponding to sensor node 1 under normal conditions, provided in an embodiment of this application. Figure 8 This is a graph showing the test statistics judgment results for sensor node 1 under abnormal conditions, as provided in this embodiment of the application. Under normal conditions, sensor node 1 collected 500 samples and performed real-time distributed temperature monitoring, as shown below. Figure 6 As shown. (Refer to...) Figure 7 Under normal conditions, the test statistics of sensor node 1 are all less than the second preset threshold, which demonstrates that if the test statistics are less than the second preset threshold J... th This confirms that the tank container is normal. (Refer to...) Figure 8In the system, sensor node 1 collected samples from the first 200 sampling moments under normal conditions. After 200 sampling moments, an operator error caused an anomaly in the tank container refrigeration system, resulting in a 0.5°C increase in the temperature inside the tank container. Under these abnormal conditions, sensor node 1 collected 300 samples. Comparing the test statistics of sensor node 1 with the second preset threshold shows that the anomaly detection method provided in this application can detect the system's abnormal state. Furthermore, without an event triggering mechanism, 100 iterations are required to ensure average consistency across sensor nodes; however, with the event triggering mechanism, simulations show an average iteration count of only 11. This demonstrates that the anomaly detection method provided in this application, by incorporating an event triggering mechanism, reduces the number of iterations, thus addressing the problem of wasted communication resources caused by excessive iterations.

[0088] Please see Figure 9 , Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device includes:

[0089] The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0090] The memory 902 can be implemented in the form of ROM (Read Only Memory), static storage device, dynamic storage device, or RAM (Random Access Memory). The memory 902 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901.

[0091] The input / output interface 903 is used to implement information input and output;

[0092] The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0093] Bus 909 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904);

[0094] The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0095] This application also provides a storage medium, which is a computer-readable storage medium, storing a computer program that, when executed by a processor, implements the above-described method.

[0096] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0097] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0098] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0099] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0100] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0101] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0102] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0103] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0104] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0105] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0106] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0107] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for detecting anomalies in tank containers, characterized in that, The tank container includes multiple sensor nodes arranged in a distributed manner. These sensor nodes are used to collect sensor data corresponding to different locations on the tank container. Adjacent sensor nodes communicate with each other. The detection method includes: In each detection cycle, the sensor node acquires the sensor data updated by the adjacent sensor node in the previous detection cycle, and iteratively updates the sensor data updated by the sensor node in the previous detection cycle and the sensor data updated by the adjacent sensor node in the previous detection cycle to obtain the sensor data corresponding to the sensor node in the current detection cycle. Calculate the absolute value of the difference between the sensor data of the sensor node in the current detection cycle and the sensor data updated by the sensor node in the previous detection cycle, and determine whether the absolute value of the difference is less than a first preset threshold. When the absolute value of the difference is less than the first preset threshold, the iterative update stops. Based on the sensor data of the sensor node in the current detection cycle, the total number of sensor nodes, and the first preset threshold, the test statistics of the sensor node in the current detection cycle are calculated. The test statistics are calculated using the following formula: ； In the formula, Represents sensor nodes The test statistics corresponding to the current testing cycle This represents the total number of sensor nodes. This represents the first preset threshold. Represents sensor nodes Sensor data corresponding to the current detection cycle; Determine whether the test statistic is greater than a second preset threshold; If the test statistic is greater than the second preset threshold, then the tank container is determined to be in an abnormal state. If the test statistics are less than or equal to the second preset threshold, then the tank container is determined to be in a normal state.

2. The method according to claim 1, characterized in that, The method further includes: In the first detection cycle, the sensor node normalizes the real-time sensor data collected in history to obtain the sensor data corresponding to the sensor node in the first detection cycle.

3. The method according to claim 2, characterized in that, The sensor node normalizes the historically collected real-time sensor data to obtain the sensor data corresponding to the first detection cycle using the following formula: ； In the formula, Represents sensor nodes Sensor data corresponding to the first detection cycle Represents sensor nodes Real-time sensor data collected, Represents sensor nodes The average value of sensor data calculated based on historically collected real-time sensor data. Represents sensor nodes The sensor data variance is calculated based on historically collected real-time sensor data, where m represents the sensor node. The dimensionality of the collected data.

4. The method according to claim 1, characterized in that, The sensor node iteratively updates the sensor data obtained by itself in the previous detection cycle and the sensor data obtained by the adjacent sensor nodes in the previous detection cycle to obtain the sensor data corresponding to the sensor node in the current detection cycle, including: Based on the distribution of the multiple sensor nodes in the tank container, determine the weighting matrix between each sensor node; According to the weighting matrix, the sensor data updated by the sensor node in the previous detection cycle and the sensor data updated by the adjacent sensor node in the previous detection cycle are weighted to obtain the sensor data corresponding to the sensor node in the current detection cycle.

5. The method according to claim 4, characterized in that, The weighting matrix corresponding to each sensor node is calculated using the following formula: ； In the formula, Represents sensor nodes relative sensor nodes The weight, Represents sensor nodes The set of adjacent sensor nodes, This represents the maximum distance between any two sensor nodes on a tank container. Indicates the relationship with sensor nodes The number of adjacent sensor nodes.

6. The method according to claim 1, characterized in that, The sensor node iteratively updates the sensor data obtained by itself in the previous detection cycle and the sensor data obtained by the adjacent sensor nodes in the previous detection cycle to obtain the sensor data corresponding to the sensor node in the current detection cycle using the following formula: ； In the formula, Represents sensor nodes Sensor data corresponding to the current detection cycle, Represents sensor nodes Sensor data from the previous detection cycle, Indicates adjacent sensor nodes Sensor data from the previous detection cycle, Represents sensor nodes Relative to its own weight, Indicates adjacent sensor nodes relative sensor nodes The weight, Represents sensor nodes The set of adjacent sensor nodes.

7. An electronic device, characterized in that, The electronic device includes a memory and at least one processor, the memory storing a computer program, and the at least one processor executing the computer program to implement the method according to any one of claims 1 to 6.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

Images