Military equipment monitoring system based on edge computing data processing

Abstract

This invention belongs to the field of military equipment supervision and involves data analysis technology. It addresses the problem that existing military equipment monitoring methods cannot achieve refined hierarchical management and multi-factor fusion analysis of equipment. Specifically, it is a military equipment monitoring system, method, and medium based on edge computing data processing, including a monitoring and analysis center. The monitoring and analysis center is communicatively connected to a monitoring classification module, a parameter monitoring module, a monitoring analysis module, a fusion analysis module, and a storage module. The monitoring classification module is used for hierarchical monitoring of military equipment, the parameter monitoring module is used for monitoring monitoring parameters, the monitoring analysis module is used for monitoring and analyzing the monitoring parameters of the classified military equipment, and the fusion analysis module is used for fusion analysis of military equipment by combining multiple monitoring parameters. This invention can distinguish the risk status of military equipment and thus achieve targeted monitoring, improving the accuracy and efficiency of military equipment status judgment.

Description

Technical Field

[0001] This invention belongs to the field of military equipment monitoring and involves data analysis technology, specifically a military equipment monitoring system based on edge computing data processing. Background Technology

[0002] Military equipment refers to various equipment and materials used for military purposes and is an important component of national defense. In the modern military industry, the complexity and importance of military equipment are constantly increasing, and efficient, accurate and real-time monitoring of it has become the key to ensuring the smooth conduct of military operations and the safe and reliable operation of equipment.

[0003] Existing methods for monitoring military equipment often lack refined hierarchical management of equipment, making it difficult to allocate monitoring resources according to different risk states and importance of equipment, and also making it difficult to accurately assess the status of equipment through integrated analysis of multiple factors.

[0004] To address the aforementioned technical problems, this application proposes a solution. Summary of the Invention

[0005] The purpose of this invention is to provide a military equipment monitoring system, method, and medium based on edge computing data processing, which solves the problem that existing military equipment monitoring methods cannot perform refined hierarchical management and multi-factor fusion analysis of equipment.

[0006] The technical problem to be solved by this invention is: how to provide a military equipment monitoring system, method and medium based on edge computing data processing that can perform refined hierarchical management and multi-factor fusion analysis of military equipment.

[0007] The objective of this invention can be achieved through the following technical solutions:

[0008] A military equipment monitoring system based on edge computing data processing includes a monitoring and analysis center, which is communicatively connected to a monitoring hierarchy module, a parameter monitoring module, a monitoring and analysis module, a fusion analysis module, and a storage module.

[0009] The monitoring and grading module is used to perform graded monitoring of military equipment: marking military equipment as monitoring objects, the risk coefficient FX of the monitoring objects, comparing the risk coefficient FX of the monitoring objects with the preset risk threshold FXmax, and marking the monitoring objects as elastic objects or rigid objects.

[0010] The parameter monitoring module is used to monitor the monitoring parameters: the functional modules of the monitored object are marked as monitoring points n, n=1, 2, ..., i, where i is a positive integer; various sensors are distributed and installed at the monitoring point n to obtain the monitoring parameters m of the monitoring point n in real time, where m=1, 2, ..., j, where j is a positive integer;

[0011] The monitoring and analysis module is used to monitor and analyze the monitoring parameters of the graded military equipment: obtain the standard range [MINm, MAXm] corresponding to the monitoring parameter m, mark the monitoring parameter m that exceeds the corresponding standard range [MINm, MAXm] as parameter abnormality, mark the number of times the monitoring point n has parameter abnormality as abnormal value YCn; analyze the abnormal value YCn of the monitoring point n in rigid objects and elastic objects, and generate alarm signals or fusion analysis signals;

[0012] The fusion analysis module is used to perform fusion analysis on military equipment by combining multiple monitoring parameters: the monitoring parameter m in monitoring point n that has abnormal parameters is marked as abnormal parameters, and the monitoring parameters m in monitoring point n other than abnormal parameters are marked as reference parameters. The reference parameters are analyzed to generate alarm signals or observation signals.

[0013] Furthermore, the process of obtaining the risk coefficient FX includes: obtaining the usage duration SC, usage count CS, and storage quantity SL of the monitored object; the usage duration SC is the difference between the real-time time of the monitored object during use and the service start time; the usage count CS is the number of times the monitored object completes the outbound and inbound operations within the current usage duration SC; the storage quantity SL is the actual storage quantity of the same type of monitored object in the equipment warehouse; and the risk coefficient FX of the monitored object is obtained by numerically calculating the usage duration SC, usage count CS, and storage quantity SL.

[0014] Furthermore, the risk coefficient FX of the monitored object is compared with the preset risk threshold FXmax: if the risk coefficient FX is less than the risk threshold FXmax, the risk status of the monitored object is determined to meet the requirements, and the monitored object is marked as a flexible object; if the risk coefficient FX is greater than or equal to the risk threshold FXmax, the risk status of the monitored object is determined to not meet the requirements, and the monitored object is marked as a rigid object.

[0015] Furthermore, all sensors are connected to the edge computing nodes wirelessly, and the edge computing nodes are equipped with independent processors and memory.

[0016] Furthermore, when the monitored object is a rigid object, if a parameter anomaly occurs at monitoring point n, the corresponding abnormal value YCn is obtained. If the abnormal value YCn of monitoring point n is equal to 0, it is determined that the monitoring point n is experiencing a parameter anomaly for the first time, a fusion analysis signal is generated, and the signal is sent to the fusion analysis module. If the abnormal value YCn of monitoring point n is greater than or equal to 1, it is determined that the monitoring point n is not experiencing a parameter anomaly for the first time, an alarm signal is generated, and the monitored object and monitoring point n are sent to the monitoring analysis center.

[0017] Furthermore, when the monitored object is an elastic object, the abnormal threshold YCmax of monitoring point n is obtained through the storage module. If an abnormality occurs in the parameters of monitoring point n, the abnormal value YCn corresponding to monitoring point n is obtained, and the abnormal value YCn is compared with the abnormal threshold YCmax: if the abnormal value YCn of monitoring point n is less than or equal to the abnormal threshold YCmax, a fusion analysis signal is generated and sent to the fusion analysis module; if the abnormal value YCn of monitoring point n is greater than the abnormal threshold YCmax, an alarm signal is generated and the monitored object and monitoring point n are sent to the monitoring analysis center.

[0018] Furthermore, the standard range [MINm, MAXm] of the monitoring parameter m is calculated with the preset boundary parameter t: the lower boundary XBm is obtained by dividing MINm and the boundary parameter t, and the upper boundary SBm is obtained by multiplying MAXm and the boundary parameter t.

[0019] Furthermore, the period from L1 seconds before the parameter anomaly to the time of the anomaly is marked as the analysis period. A rectangular coordinate system is established with the reference parameter as the Y-axis and time as the X-axis, and a reference parameter-time curve is plotted. The reference parameter-time curve is divided into several analysis points p along the X-axis, and the slope kp between analysis point p and its previous analysis point is calculated. If the reference parameter corresponding to analysis point p is greater than or equal to the upper boundary SBm, and (kp*kp-1) is greater than 0, then it is determined that the monitoring parameter m is continuously increasing and there is a risk of exceeding the standard range [MINm, MAXm]. An alarm signal is generated, and the monitoring object and monitoring point n are sent to the monitoring analysis center. If the reference parameter corresponding to analysis point p is less than the lower boundary XBm, and (kp*kp-1) is greater than 0, then it is determined that the monitoring parameter m is continuously decreasing and there is a risk of exceeding the standard range [MINm, MAXm]. An alarm signal is generated, and the monitoring object and monitoring point n are sent to the monitoring analysis center. Otherwise, an observation signal is generated, and the monitoring object and monitoring point n are sent to the monitoring analysis center.

[0020] A method for monitoring military equipment based on edge computing data processing includes the following steps:

[0021] Step 1: Mark military equipment as monitoring objects, and obtain the usage duration SC, usage count CS, and storage quantity SL of the monitoring objects; calculate the risk coefficient FX by numerically calculating the usage duration SC, usage count CS, and storage quantity SL, and mark the monitoring objects as flexible or rigid objects by judging the risk coefficient FX.

[0022] Step 2: Mark the functional modules of the monitored object as monitoring points n, n=1, 2, ..., i, where i is a positive integer; install various sensors in a distributed manner at monitoring point n to obtain the monitoring parameters m of monitoring point n in real time, where m=1, 2, ..., j, where j is a positive integer;

[0023] Step 3: Obtain the standard range [MINm, MAXm] corresponding to the monitoring parameter m, mark the monitoring parameter m that exceeds the corresponding standard range [MINm, MAXm] as parameter abnormality, and mark the number of times the monitoring point n has parameter abnormality as the abnormal value YCn; analyze the abnormal value YCn of the monitoring point n in rigid and elastic objects, and generate alarm signals or fusion analysis signals;

[0024] Step 4: Mark the monitoring parameter m at monitoring point n that has an abnormal parameter as an abnormal parameter, and mark the monitoring parameter m at monitoring point n that is not an abnormal parameter as a reference parameter; generate alarm signals or observation signals by analyzing the reference parameters.

[0025] Furthermore, the present invention provides a computer storage medium storing a computer program that, when executed by a processor, implements a method for monitoring military equipment based on edge computing data processing.

[0026] Furthermore, the present invention also provides a computer device, including: a processor and a memory; the memory stores a computer program, and the processor executes the computer program stored in the memory to enable the computer device to perform a military equipment monitoring method based on edge computing data processing.

[0027] The present invention has the following beneficial effects:

[0028] 1. By classifying military equipment based on a comprehensive analysis of usage time, frequency, and storage quantity through a monitoring classification module, it is possible to accurately distinguish equipment in different risk states, achieve reasonable allocation of resources and focus on key areas, provide a foundation for targeted monitoring solutions, and improve monitoring efficiency.

[0029] 2. The parameter monitoring module uses distributed sensors to monitor the various functional modules of military equipment in real time, ensuring the comprehensiveness and real-time nature of the monitoring data and enabling the timely detection of potential problems.

[0030] 3. The monitoring and analysis module can make targeted judgments on abnormal situations at monitoring points based on the classification of military equipment, and generate different alarm strategies, which also improves the accuracy of judging the status of military equipment.

[0031] 4. The fusion analysis module combines multiple monitoring parameters for in-depth analysis, further improving the accuracy of equipment status assessment and enabling early detection of risks that may exceed standard ranges. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 This is a system block diagram of Embodiment 1 of the present invention;

[0034] Figure 2 This is a flowchart of the method in Embodiment 2 of the present invention. Detailed Implementation

[0035] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0036] Example 1

[0037] like Figure 1 As shown, the military equipment monitoring system based on edge computing data processing includes a monitoring and analysis center, which is communicatively connected to a monitoring hierarchy module, a parameter monitoring module, a monitoring and analysis module, a fusion analysis module, and a storage module.

[0038] The monitoring and grading module is used for graded monitoring of military equipment: marking military equipment as monitoring objects, and obtaining the usage duration (SC), usage count (CS), and storage quantity (SL) of the monitoring objects; usage duration (SC) is the difference between the real-time time of the monitoring object during use and the service start time; usage count (CS) is the number of times the monitoring object has completed full inbound and outbound operations within the current usage duration (SC); storage quantity (SL) is the actual storage quantity of the same type of monitoring object in the equipment warehouse; and this is achieved through formulas. The risk coefficient FX of the monitored object is obtained by numerically calculating the usage duration SC, usage frequency CS, and storage quantity SL, where k1, k2, and k3 are proportional coefficients, and k1 > k2 > k3 > 1. The risk threshold FXmax of the monitored object is obtained through the storage module. The risk coefficient FX of the monitored object is compared with the preset risk threshold FXmax: if the risk coefficient FX is less than the risk threshold FXmax, the risk status of the monitored object is judged to meet the requirements, and the monitored object is marked as a flexible object; if the risk coefficient FX is greater than or equal to the risk threshold FXmax, the risk status of the monitored object is judged to not meet the requirements, and the monitored object is marked as a rigid object. By classifying the military equipment through a comprehensive analysis of usage duration, frequency, and storage quantity using the monitoring classification module, it is possible to accurately distinguish equipment with different risk statuses, realize the rational allocation of resources and focus on key areas, provide a foundation for targeted monitoring solutions, and improve monitoring efficiency.

[0039] The parameter monitoring module is used to monitor monitoring parameters: Functional modules of the monitored object are marked as monitoring points n, where n = 1, 2, ..., i, and i is a positive integer. For example, functional modules include power systems, weapon systems, and electronic control systems. Power systems include engines and battery packs, weapon systems include gun barrels and loading devices, and electronic control systems include main control computers and circuit boards. Various sensors are distributed and installed at monitoring point n to acquire monitoring parameters m in real time, where m = 1, 2, ..., j, and j is a positive integer. All sensors are connected to edge computing nodes via wireless communication. Edge computing nodes are equipped with independent processors and memory. For example, monitoring parameters for the engine in an armored vehicle typically include cylinder surface temperature, fuel line pressure, and fuel line flow rate. By using distributed sensors, the parameter monitoring module monitors the various functional modules of military equipment in real time, ensuring the comprehensiveness and real-time nature of the monitoring data and enabling timely detection of potential problems.

[0040] The monitoring and analysis module is used to monitor and analyze the monitoring parameters of the graded military equipment: It obtains the standard range [MINm, MAXm] corresponding to the monitoring parameter m through the storage module; during the operation of the monitored object, if the monitoring parameter m of monitoring point n exceeds the corresponding standard range [MINm, MAXm], it is marked as a parameter anomaly, and the number of times parameter anomalies occur at monitoring point n is marked as an anomaly value YCn; the module then analyzes the anomaly value YCn of monitoring point n in the monitored object.

[0041] When the monitored object is a rigid object, if a parameter anomaly occurs at monitoring point n, the corresponding abnormal value YCn is obtained. If the abnormal value YCn of monitoring point n is equal to 0, it is determined that the parameter anomaly of monitoring point n is the first time, a fusion analysis signal is generated and sent to the fusion analysis module; if the abnormal value YCn of monitoring point n is greater than or equal to 1, it is determined that the parameter anomaly of monitoring point n is not the first time, an alarm signal is generated and the monitored object and monitoring point n are sent to the monitoring analysis center.

[0042] When the monitored object is an elastic object, the abnormal threshold YCmax of monitoring point n is obtained through the storage module. If an abnormality occurs in the parameters of monitoring point n, the abnormal value YCn corresponding to monitoring point n is obtained, and the abnormal value YCn is compared with the abnormal threshold YCmax: if the abnormal value YCn of monitoring point n is less than or equal to the abnormal threshold YCmax, a fusion analysis signal is generated and sent to the fusion analysis module; if the abnormal value YCn of monitoring point n is greater than the abnormal threshold YCmax, an alarm signal is generated and the monitored object and monitoring point n are sent to the monitoring analysis center. Through the monitoring analysis module, the abnormal situation of the monitoring point can be judged in a targeted manner according to the classification of military equipment, and different alarm strategies are generated, which also improves the accuracy of judging the status of military equipment.

[0043] The fusion analysis module is used to perform fusion analysis on military equipment by combining multiple monitoring parameters: If the fusion analysis module receives a fusion analysis signal, it performs fusion analysis on the monitoring parameter m of monitoring point n: The standard range [MINm, MAXm] of the monitoring parameter m is calculated with the preset boundary parameter t: MINm is divided by the boundary parameter t to obtain the lower boundary XBm, and MAXm is multiplied by the boundary parameter t to obtain the upper boundary SBm, where the value of t is 0.9;

[0044] Mark the monitoring parameter m at monitoring point n that experiences an anomaly as the anomaly parameter, and mark all other monitoring parameters m at monitoring point n as reference parameters. Mark the period from L1 seconds before the anomaly to the point where the anomaly occurs as the analysis period. Establish a Cartesian coordinate system with the reference parameter as the Y-axis and time as the X-axis, and plot the reference parameter-time curve. Divide the reference parameter-time curve along the X-axis into several analysis points p. The slope between analysis point p and its previous analysis point is Kp = (Yp - Yp-1) / (Xp - ... Xp-1); Analyze all analysis points p: If the reference parameter corresponding to analysis point p is greater than or equal to the upper boundary SBm, and (kp*kp-1) is greater than 0, then it is determined that the monitoring parameter m is continuously increasing and there is a risk of exceeding the standard range [MINm, MAXm]. An alarm signal is generated and the monitoring object and monitoring point n are sent to the monitoring analysis center; If the reference parameter corresponding to analysis point p is less than the lower boundary XBm, and (kp*kp-1) is greater than 0, then it is determined that the monitoring parameter m is continuously decreasing and there is a risk of exceeding the standard range [MINm, MAXm]. An alarm signal is generated and the monitoring object and monitoring point n are sent to the monitoring analysis center; otherwise, an observation signal is generated and the monitoring object and monitoring point n are sent to the monitoring analysis center; The fusion analysis module combines multiple monitoring parameters for in-depth analysis, further improving the accuracy of equipment status judgment and enabling early detection of risks that may exceed the standard range.

[0045] Example 2

[0046] like Figure 2 As shown, a method for monitoring military equipment based on edge computing data processing includes the following steps:

[0047] Step 1: Mark military equipment as monitoring objects, and obtain the usage duration SC, usage count CS, and storage quantity SL of the monitoring objects; calculate the risk coefficient FX by numerically calculating the usage duration SC, usage count CS, and storage quantity SL, and mark the monitoring objects as flexible or rigid objects by judging the risk coefficient FX.

[0048] Step 2: Mark the functional modules of the monitored object as monitoring points n, n=1, 2, ..., i, where i is a positive integer; install various sensors in a distributed manner at monitoring point n to obtain the monitoring parameters m of monitoring point n in real time, where m=1, 2, ..., j, where j is a positive integer;

[0049] Step 3: Obtain the standard range [MINm, MAXm] corresponding to the monitoring parameter m, mark the monitoring parameter m that exceeds the corresponding standard range [MINm, MAXm] as parameter abnormality, and mark the number of times the monitoring point n has parameter abnormality as the abnormal value YCn; analyze the abnormal value YCn of the monitoring point n in rigid and elastic objects, and generate alarm signals or fusion analysis signals;

[0050] Step 4: Mark the monitoring parameter m at monitoring point n that has an abnormal parameter as an abnormal parameter, and mark the monitoring parameter m at monitoring point n that is not an abnormal parameter as a reference parameter; generate alarm signals or observation signals by analyzing the reference parameters.

[0051] The present invention also includes a readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned military equipment monitoring method based on edge computing data processing. Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented using hardware related to the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0052] The terminal of this invention includes a processor and a memory; the memory stores computer programs; the processor is connected to the memory and executes the computer programs stored in the memory, enabling the terminal to execute any military equipment monitoring method based on edge computing data processing. Specifically, the memory includes various media capable of storing program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card, or optical disk.

[0053] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0054] A military equipment monitoring system based on edge computing data processing, during operation, marks military equipment as monitoring objects, obtains the risk coefficient of the monitored objects, and marks the monitored objects as flexible or rigid objects based on the risk coefficient; the functional modules of the monitored objects are marked as monitoring points, and various sensors are distributedly installed at the monitoring points to obtain the monitoring parameters of the monitoring points in real time, obtain the standard range corresponding to the monitoring parameters, mark the monitoring parameters that exceed the corresponding standard range as parameter anomalies, and mark the number of times the monitoring points have parameter anomalies as outliers; the outliers of the monitoring points in rigid and flexible objects are analyzed to generate alarm signals or fusion analysis signals; the monitoring parameters in the monitoring points that have parameter anomalies are marked as anomalous parameters, and the monitoring parameters in the monitoring points other than anomalous parameters are marked as reference parameters. Finally, the reference parameters are analyzed to generate alarm signals or observation signals.

[0055] The above description is merely an example and illustration of the structure of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the structure of the invention or exceed the scope defined in the claims, all of which should fall within the protection scope of the present invention.

[0056] The above formulas are all derived from software simulations using a large amount of data, and are selected to be close to the true values. The coefficients in the formulas are set by those skilled in the art based on the actual situation; for example: formula Multiple sets of sample data are collected by a person skilled in the art, and a corresponding risk coefficient is set for each set of sample data. The set risk coefficient and the collected sample data are substituted into the formula, and any three formulas form a system of three linear equations. The calculated coefficients are filtered and the average value is taken to obtain the values ​​of k1, k2 and k3 as 3.12, 2.05 and 1.65 respectively.

[0057] The size of the coefficient is a specific value obtained by quantifying each parameter to facilitate subsequent comparison. The size of the coefficient depends on the amount of sample data and the risk coefficient initially set by those skilled in the art for each set of sample data. As long as it does not affect the proportional relationship between the parameter and the quantified value, such as the risk coefficient being proportional to the usage time.

[0058] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0059] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A military equipment monitoring system based on edge computing data processing, characterized in that, It includes a monitoring and analysis center, which is communicatively connected to a monitoring hierarchy module, a parameter monitoring module, a monitoring and analysis module, a fusion analysis module, and a storage module; The monitoring and grading module is used to perform graded monitoring of military equipment: marking military equipment as monitoring objects, obtaining the risk coefficient FX of the monitoring objects, comparing the risk coefficient FX of the monitoring objects with the preset risk threshold FXmax, and marking the monitoring objects as elastic objects or rigid objects. The process of obtaining the risk coefficient FX includes: obtaining the usage duration SC, usage count CS, and storage quantity SL of the monitored object; the usage duration SC is the difference between the real-time time of the monitored object during use and the service start time; the usage count CS is the number of times the monitored object has completed full outbound and inbound operations within the current usage duration SC; the storage quantity SL is the actual storage quantity of the same type of monitored object in the equipment warehouse; the risk coefficient FX of the monitored object is obtained by numerically calculating the usage duration SC, usage count CS, and storage quantity SL. The parameter monitoring module is used to monitor the monitoring parameters: the functional modules of the monitored object are marked as monitoring points n, n=1, 2, ..., i, where i is a positive integer; various sensors are distributed and installed at the monitoring point n to obtain the monitoring parameters m of the monitoring point n in real time, where m=1, 2, ..., j, where j is a positive integer; The monitoring and analysis module is used to monitor and analyze the monitoring parameters of the graded military equipment: obtain the standard range [MINm, MAXm] corresponding to the monitoring parameter m, mark the monitoring parameter m that exceeds the corresponding standard range [MINm, MAXm] as parameter abnormality, mark the number of times the monitoring point n has parameter abnormality as abnormal value YCn; analyze the abnormal value YCn of the monitoring point n in rigid objects and elastic objects, and generate alarm signals or fusion analysis signals; The fusion analysis module is used to perform fusion analysis on military equipment by combining multiple monitoring parameters: marking the monitoring parameter m in monitoring point n that has abnormal parameters as abnormal parameters, marking the monitoring parameters m in monitoring point n other than abnormal parameters as reference parameters, and analyzing the reference parameters to generate alarm signals or observation signals; The standard range [MINm, MAXm] of the monitoring parameter m is calculated with the preset boundary parameter t: the lower boundary XBm is obtained by dividing MINm and the boundary parameter t, and the upper boundary SBm is obtained by multiplying MAXm and the boundary parameter t. The period from L1 seconds before the parameter anomaly to the time of the anomaly is marked as the analysis period. A rectangular coordinate system is established with the reference parameter as the Y-axis and time as the X-axis, and a reference parameter-time curve is plotted. The reference parameter-time curve is divided into several analysis points p along the X-axis, and the slope kp between analysis point p and the previous analysis point is calculated. If the reference parameter corresponding to analysis point p is greater than or equal to the upper boundary SBm, and (kp*kp-1) is greater than 0, then it is determined that the monitoring parameter m is continuously increasing and there is a risk of exceeding the standard range [MINm, MAXm]. An alarm signal is generated, and the monitoring object and monitoring point n are sent to the monitoring analysis center. If the reference parameter corresponding to analysis point p is less than the lower boundary XBm, and (kp*kp-1) is greater than 0, then it is determined that the monitoring parameter m is continuously decreasing and there is a risk of exceeding the standard range [MINm, MAXm]. An alarm signal is generated, and the monitoring object and monitoring point n are sent to the monitoring analysis center. Otherwise, an observation signal is generated, and the monitoring object and monitoring point n are sent to the monitoring analysis center.

2. The military equipment monitoring system based on edge computing data processing according to claim 1, characterized in that, The risk coefficient FX of the monitored object is compared with the preset risk threshold FXmax. If the risk coefficient FX is less than the risk threshold FXmax, the risk status of the monitored object is determined to meet the requirements, and the monitored object is marked as an elastic object. If the risk coefficient FX is greater than or equal to the risk threshold FXmax, the risk status of the monitored object is determined to be unsatisfactory, and the monitored object is marked as a rigid object.

3. The military equipment monitoring system based on edge computing data processing according to claim 2, characterized in that, All sensors are connected to the edge computing nodes wirelessly, and the edge computing nodes are equipped with independent processors and memory.

4. A military equipment monitoring system based on edge computing data processing according to claim 3, characterized in that, When the monitored object is a rigid object, if a parameter anomaly occurs at monitoring point n, the corresponding abnormal value YCn is obtained. If the abnormal value YCn of monitoring point n is equal to 0, it is determined that the parameter anomaly of monitoring point n is the first time, a fusion analysis signal is generated and sent to the fusion analysis module; if the abnormal value YCn of monitoring point n is greater than or equal to 1, it is determined that the parameter anomaly of monitoring point n is not the first time, an alarm signal is generated and the monitored object and monitoring point n are sent to the monitoring analysis center.

5. A military equipment monitoring system based on edge computing data processing according to claim 4, characterized in that, When the monitored object is an elastic object, the abnormal threshold YCmax of monitoring point n is obtained through the storage module. If the parameters of monitoring point n are abnormal, the abnormal value YCn corresponding to monitoring point n is obtained, and the abnormal value YCn is compared with the abnormal threshold YCmax: if the abnormal value YCn of monitoring point n is less than or equal to the abnormal threshold YCmax, a fusion analysis signal is generated and the signal is sent to the fusion analysis module; if the abnormal value YCn of monitoring point n is greater than the abnormal threshold YCmax, an alarm signal is generated and the monitored object and monitoring point n are sent to the monitoring analysis center.

6. A method for monitoring military equipment based on edge computing data processing, characterized in that, The military equipment monitoring system based on edge computing data processing, as described in any one of claims 1-5, includes the following steps: Step 1: Mark military equipment as monitoring objects, and obtain the usage duration SC, usage count CS, and storage quantity SL of the monitoring objects; calculate the risk coefficient FX by numerically calculating the usage duration SC, usage count CS, and storage quantity SL, and mark the monitoring objects as flexible or rigid objects by judging the risk coefficient FX. Step 2: Mark the functional modules of the monitored object as monitoring points n, n=1, 2, ..., i, where i is a positive integer; install various sensors in a distributed manner at monitoring point n to obtain the monitoring parameters m of monitoring point n in real time, where m=1, 2, ..., j, where j is a positive integer; Step 3: Obtain the standard range [MINm, MAXm] corresponding to the monitoring parameter m, mark the monitoring parameter m that exceeds the corresponding standard range [MINm, MAXm] as parameter abnormality, and mark the number of times the monitoring point n has parameter abnormality as the abnormal value YCn; analyze the abnormal value YCn of the monitoring point n in rigid and elastic objects, and generate alarm signals or fusion analysis signals; Step 4: Mark the monitoring parameter m at monitoring point n that has an abnormal parameter as an abnormal parameter, and mark the monitoring parameter m at monitoring point n that is not an abnormal parameter as a reference parameter; generate alarm signals or observation signals by analyzing the reference parameters.

7. A computer storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the military equipment monitoring method based on edge computing data processing as described in claim 6.

Images