Distributed intelligent monitoring method and system based on multi-node edge computing device

Abstract

The invention relates to the technical field of distributed intelligent monitoring, and discloses a distributed intelligent monitoring method and system based on a multi-node edge computing device, and the method comprises the following steps: arranging M * N monitoring nodes at a fixed interval on a target monitoring ice surface; when the vertical acceleration collected by any monitoring node exceeds a preset acceleration threshold value, corresponding triggering time is recorded, and the real-time wheel speed of the vehicle is calculated based on the triggering time and the fixed distance; the main fluctuation frequency is obtained based on the vertical acceleration corresponding to the triggering time, the main fluctuation frequency is associated with the real-time wheel speed of the vehicle, the fluctuation wave number is determined firstly, and then the ice layer vertical displacement and the ice layer curvature are determined based on the fluctuation wave number; calculating a correction wave velocity based on the ice layer vertical displacement and the fixed spacing to obtain a damping coefficient; and calculating the maximum bending stress of the corresponding monitoring node in combination with the curvature of the ice layer and the priori material parameters.

Description

Technical Field

[0001] The present invention relates to the field of distributed intelligent monitoring technology, and more specifically, to a distributed intelligent monitoring method and system based on multi-node edge computing devices. Background Art

[0002] In cold regions, ice surfaces are widely used as temporary transportation corridors. Existing ice safety monitoring technologies include embedded temperature sensors, strain gauges, or sonar equipment to monitor ice thickness, temperature distribution, and static stress, triggering warnings when these parameters exceed thresholds. However, existing ice safety monitoring technologies are only suitable for static or low dynamic load scenarios and cannot reflect the dynamic fluctuations of ice during vehicle operation.

[0003] When a vehicle travels on ice, the concentrated loads from the wheels cause the ice to vibrate elastically, generating gravity waves in the water beneath the ice. These waves propagate forward along the ice, keeping pace with the vehicle's direction and speed.

[0004] The core defects of existing ice safety monitoring technology are: Existing ice layer safety monitoring technology does not establish a monitoring model based on the dynamic fluctuation characteristics of the ice layer when the vehicle is driving. It is unable to identify the high-risk state of rapid stress amplification when the vehicle speed approaches the critical wave speed, resulting in safety risks for vehicle driving. Summary of the Invention

[0005] The present invention provides a distributed intelligent monitoring method and system based on multi-node edge computing devices to solve the technical problems raised in the background technology.

[0006] In a first aspect, a distributed intelligent monitoring method based on a multi-node edge computing device is characterized by comprising: Step 1: Arrange M×N monitoring nodes at a fixed spacing on the target monitoring ice surface; when the vertical acceleration collected by any monitoring node exceeds a preset acceleration threshold, record the corresponding trigger time, and calculate the vehicle's real-time wheel speed based on the trigger time and the fixed spacing; Step 2: obtaining a main frequency of the fluctuation based on the vertical acceleration corresponding to the trigger time, and correlating the main frequency of the fluctuation with the real-time wheel speed of the vehicle, first determining the number of fluctuations, and then determining the vertical displacement of the ice layer and the curvature of the ice layer based on the number of fluctuations; Step 3: Calculate the corrected wave velocity based on the vertical displacement of the ice layer and the fixed spacing to obtain a damping coefficient; and calculate the maximum bending stress of the corresponding monitoring node in combination with the ice layer curvature and prior material parameters; Step 4: Each monitoring node exchanges the corrected wave velocity and the maximum bending stress, and uses a distributed alternating direction multiplier method for iterative processing to obtain a global average wave velocity and a global average bending stress of the target monitored ice surface; Step 5: Each monitoring node calculates a critical wave speed based on the global average wave speed and the prior material parameters, compares the global average bending stress with a preset bending stress threshold to generate a safety factor, and generates a speed margin based on the vehicle's real-time wheel speed and the critical wave speed; In step 6, each monitoring node fuses the speed margin, the safety factor, and the damping coefficient according to preset weights to obtain a global average risk, and outputs a target monitoring ice surface management plan based on the global average risk.

[0007] Furthermore, calculating the real-time wheel speed of the vehicle based on the trigger time and the fixed interval includes: The trigger time when the vertical acceleration of the i-th monitoring node is greater than the preset acceleration threshold; Performing differential processing on the triggering time of the monitoring nodes adjacent to the i-th monitoring node to obtain differential time; The fixed interval is divided by the differential time of the trigger time to obtain the real-time wheel speed of the vehicle.

[0008] Furthermore, obtaining the main frequency of the fluctuation based on the vertical acceleration corresponding to the trigger time, and associating the main frequency of the fluctuation with the real-time wheel speed of the vehicle to determine the number of fluctuation waves includes: intercepting the time window of the vertical acceleration of the i-th monitoring node with the trigger time as the center; Performing time-frequency analysis on the vertical acceleration within the time window to obtain the main frequency of the fluctuation; The main frequency of the fluctuation is associated with the real-time wheel speed of the vehicle, and the corresponding fluctuation wave number is output.

[0009] Furthermore, the vertical displacement of the ice layer and the curvature of the ice layer are determined based on the wave number, including: The prior material parameters include: ice density, ice Poisson's ratio, ice elastic modulus, ice bending stiffness at each monitoring node, and ice thickness at each monitoring node; The fluctuation wave number and prior material parameters of each monitoring node are brought into the vibration equation as follows: in, represents the second-order derivative of the vertical displacement of the ice layer corresponding to the i-th monitoring node with respect to the trigger time, represents the density of the ice layer, represents the bending stiffness of the ice layer at the i-th monitoring node, represents the ice thickness of the monitoring node of the i-th monitoring node, represents the fluctuation wave number of the i-th monitoring node, represents the vertical displacement of the ice layer at the i-th monitoring node; the vertical displacement of the ice layer is obtained by solving the vibration equation through numerical integration; The ice layer curvature is obtained by performing a square operation on the fluctuation wave number and the vertical displacement of the ice layer.

[0010] Furthermore, calculating a corrected wave velocity based on the vertical displacement of the ice layer and the fixed spacing to obtain a damping coefficient includes: A trigger time window H is set to extract the vertical displacement of the ice layer and the amplitude of the vertical displacement of the ice layer within the time window H, starting from the trigger time of the monitoring node; Determine the peak value of the vertical displacement of the ice layer at the i-th monitoring node within the time window H, and the peak value of the vertical displacement of the ice layer at the monitoring nodes adjacent to the i-th monitoring node within the time window H, record the arrival time of the peak value of the vertical displacement of the ice layer, and calculate the arrival time difference; use the ratio of the fixed spacing and the arrival time difference as the corrected wave velocity; Determine the peak value of the vertical displacement amplitude of the ice layer at the i-th monitoring node within the time window H , and the peak amplitude of the vertical displacement of the ice layer at the monitoring nodes adjacent to the i-th monitoring node within the time window H , and calculate the damping coefficient of the i-th monitoring node ,as follows: , in, Indicates fixed spacing.

[0011] Furthermore, the maximum bending stress of the corresponding monitoring node is calculated by combining the ice layer curvature and prior material parameters, including: Calculate the maximum bending stress of the i-th monitoring node as follows: in, represents the maximum bending stress of the i-th monitoring node, represents the elastic modulus of the ice layer, represents the ice layer curvature of the i-th monitoring node.

[0012] Furthermore, each monitoring node exchanges the corrected wave velocity and the maximum bending stress, and uses a distributed alternating direction multiplier method for iterative processing to obtain the global average wave velocity and the global average bending stress of the target monitored ice surface, including: Step 41, load the local variables and dual variables of the alternating direction multiplier; among them, the corrected wave velocity and maximum bending stress Local variables that serve as multipliers in alternating directions , initialize the corresponding dual variables All are 0; Step 42, at the kth iteration, k ≥ 0, based on the dual variable of the kth iteration and Update local variables ; Step 43: Get the M×N monitoring nodes Average value are respectively used as the global average values ​​of the k+1th iteration; among them, ; Step 44: Based on the global average value of the k+1th iteration, update the dual variable ; Step 45 , looping steps 42 to 44 repeatedly for a preset number of times, to obtain the global average wave velocity and the global average bending stress of the target monitored ice surface.

[0013] Furthermore, each monitoring node calculates a critical wave speed based on the global average wave speed and the prior material parameters, compares the global average bending stress with a preset bending stress threshold to generate a safety factor, and generates a speed margin based on the vehicle's real-time wheel speed and the critical wave speed, including: The calculation formula of critical wave speed is as follows: , , ,in, represents the critical wave velocity of the i-th monitoring node, represents the critical wave number of the i-th monitoring node, is the Poisson's ratio of the ice layer, represents the gravitational acceleration; where the global average wave velocity is used as the initial value of the critical wave number to iteratively converge Get the critical wave number; The ratio of the global average bending stress to the preset bending stress threshold is used as the safety factor ; The ratio of the vehicle's real-time wheel speed to the critical wave speed is used as the speed margin of the corresponding monitoring node .

[0014] Furthermore, each monitoring node fuses the speed margin, the safety factor, and the damping coefficient according to a preset weight to obtain a global average risk, and outputs a target monitoring ice surface management plan based on the global average risk, including: The speed margin, damping coefficient, and safety factor of each monitoring node are linearly integrated according to the preset weights to obtain the local risk index of each monitoring node; Pick The average value of the local risk indicators of the monitoring nodes is used to obtain the global average risk; When the global average risk is greater than or equal to the preset global risk threshold, the target monitoring ice surface is turned off; otherwise, the target monitoring ice surface is kept on.

[0015] In a second aspect, a distributed intelligent monitoring system based on a multi-node edge computing device is applied to any of the above-mentioned distributed intelligent monitoring methods based on a multi-node edge computing device, including: a data acquisition module configured to arrange M×N monitoring nodes at a fixed spacing on the target monitoring ice surface; record a corresponding trigger time when the vertical acceleration collected by any monitoring node exceeds a preset acceleration threshold, and calculate the vehicle's real-time wheel speed based on the trigger time and the fixed spacing; a data processing module, configured to obtain a main frequency of the fluctuation based on the vertical acceleration corresponding to the trigger time, associate the main frequency of the fluctuation with the real-time wheel speed of the vehicle, first determine the number of fluctuations, and then determine the vertical displacement of the ice layer and the curvature of the ice layer based on the number of fluctuations; A bending stress module is used to calculate the modified wave velocity based on the vertical displacement of the ice layer and the fixed spacing to obtain a damping coefficient; and to calculate the maximum bending stress of the corresponding monitoring node in combination with the ice layer curvature and prior material parameters; An iterative averaging module is used to exchange the corrected wave velocity and the maximum bending stress at each monitoring node, and obtain the global average wave velocity and the global average bending stress of the target monitored ice surface through iterative processing using a distributed alternating direction multiplier method; a risk factor module, wherein each monitoring node calculates a critical wave speed based on the global average wave speed and the prior material parameters, compares the global average bending stress with a preset bending stress threshold to generate a safety factor, and generates a speed margin based on the vehicle's real-time wheel speed and the critical wave speed; The risk assessment module integrates the speed margin, the safety factor, and the damping coefficient at each monitoring node according to a preset weight to obtain a global average risk, and outputs a target monitoring ice surface management plan based on the global average risk.

[0016] The beneficial effect of the present invention is that by coupling the vehicle speed, ice layer wave velocity and bending stress, a full-process dynamic assessment of the ice surface safety status is achieved during the real-time driving of the vehicle, breaking through the technical bottleneck of the existing static monitoring technology that can only reflect the static load status and cannot identify the stress amplification induced by the critical wave velocity, thereby realizing predictive warning and intelligent management of vehicle driving safety, and improving the reliability of temporary ice surface passage in cold areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1It is a flow chart of the distributed intelligent monitoring method based on multi-node edge computing devices of the present invention. DETAILED DESCRIPTION

[0018] The subject matter described herein will now be discussed with reference to exemplary embodiments. It should be understood that these embodiments are discussed solely to enable those skilled in the art to better understand and implement the subject matter described herein, and that the functions and arrangements of the elements discussed may be varied without departing from the scope of this specification. Various examples may omit, substitute, or add various processes or components as needed. In addition, features described with respect to some examples may also be combined in other examples.

[0019] like Figure 1 As shown, the distributed intelligent monitoring method based on multi-node edge computing devices includes: Step 1: Arrange M×N monitoring nodes at a fixed spacing on the target monitoring ice surface; when the vertical acceleration collected by any monitoring node exceeds a preset acceleration threshold, record the corresponding trigger time, and calculate the vehicle's real-time wheel speed based on the trigger time and the fixed spacing; In one embodiment of the present invention, calculating the real-time wheel speed of the vehicle based on the trigger time and the fixed interval includes: The trigger time when the vertical acceleration of the i-th monitoring node is greater than the preset acceleration threshold; Performing differential processing on the triggering time of the monitoring nodes adjacent to the i-th monitoring node to obtain differential time; The fixed interval is divided by the differential time of the trigger time to obtain the real-time wheel speed of the vehicle.

[0020] In detail, step 1 is as follows: In order to quickly and accurately obtain the real-time speed of the vehicle when it enters the ice, the present invention uses a method based on trigger time and fixed interval to estimate the vehicle speed online as follows: Several monitoring nodes are arranged in a fixed-distance array on both sides of the ice road. Each monitoring node is numbered in the direction of vehicle travel. The horizontal distance between adjacent nodes has been calibrated by technicians during installation and stored in the local memory of the monitoring node, which is recorded as , unit is meter.

[0021] Each monitoring node is equipped with a vertical acceleration sensor to capture the instantaneous impact vibration generated when the vehicle load arrives. Under normal conditions, the sensor will continuously collect the vertical acceleration at the monitoring node at a fixed sampling frequency. ,in, Indicates the monitoring nodes, is a time variable in seconds. An acceleration threshold is set by an expert ,When the vehicle wheel passes the monitoring node, the vertical acceleration at the monitoring node will ,shortly surge due to the vehicle load; If the vertical acceleration at this moment satisfy, , then determine the A monitoring node is triggered, and the moment is recorded as the triggering time .

[0022] The vehicles passed through monitoring nodes and Monitoring nodes. When a monitoring node is triggered, the trigger time is recorded. ;No. When a monitoring node is triggered, the trigger time is recorded. .but ; Further, .

[0023] Step 2: obtaining a main frequency of the fluctuation based on the vertical acceleration corresponding to the trigger time, and correlating the main frequency of the fluctuation with the real-time wheel speed of the vehicle, first determining the number of fluctuations, and then determining the vertical displacement of the ice layer and the curvature of the ice layer based on the number of fluctuations; In one embodiment of the present invention, obtaining the main frequency of the fluctuation based on the vertical acceleration corresponding to the trigger time, and correlating the main frequency of the fluctuation with the real-time wheel speed of the vehicle to determine the number of fluctuation waves includes: intercepting the time window of the vertical acceleration of the i-th monitoring node with the trigger time as the center; Performing time-frequency analysis on the vertical acceleration within the time window to obtain the main frequency of the fluctuation; The main frequency of the fluctuation is associated with the real-time wheel speed of the vehicle, and the corresponding fluctuation wave number is output.

[0024] Specifically, when a vehicle travels on ice, the concentrated loads generated by its wheels cause the ice to bend transiently where the wheels press down, generating a flexure-gravity wave in the water beneath the ice layer that couples with the ice. This wave propagates forward along the ice layer, synchronized with the vehicle; that is, as the vehicle moves forward, the phase of the wave advances at the interface between the ice layer and the water layer at the same speed (approximately equal to the vehicle's speed). The main spatiotemporal characteristics of flexure-gravity waves are: Main frequency : represents the basic oscillation frequency of the wave in the time dimension, reflecting the periodic characteristics of the ice sheet vibration; Wave speed : The speed of the wave when propagating in the ice layer and the water below. Under the vehicle load, the wave speed is proportional to the vehicle's real-time wheel speed. approximately equal; Fluctuation wave number : describes the distribution characteristics of the wave in the spatial dimension (i-th monitoring node), , and satisfy the dispersion relation: , is the ice layer vibration frequency.

[0025] Step 21: intercept the acceleration time window centered on the trigger time, as follows: At trigger time Based on the Symmetric time window, that is, retain the The vertical acceleration segment between , recorded as: , Since the load exerted by the vehicle wheels on the ice surface is the strongest at the time of triggering, the vibration response of the ice layer usually lasts for a short period of time after the triggering. The vertical acceleration segment is used to retain the pre-shock and subsequent oscillation information before and after the triggering moment, avoiding confusion between multiple consecutive triggering events.

[0026] Step 22, vertical acceleration segment Perform continuous wavelet transform to calculate the wavelet coefficients; square the wavelet coefficients to get the energy spectrum; at the trigger moment At the point where the maximum value of the energy spectrum is searched, the scale corresponding to the maximum value is searched, and the main frequency of the fluctuation is calculated by using the inverse relationship between the center frequency of the mother wavelet and the scale. ; Step 23: Under the action of the vehicle load, the ice layer and the water below form a coupled thin plate-fluid system, and the propagating bending-gravity waves satisfy the following linear dispersion relation (linear infinite depth approximation): , in, represents the acceleration due to gravity, represents the bending stiffness of the ice layer, represents the density of the ice layer, represents the ice thickness at the i-th monitoring node; But when the vehicle's real-time wheel speed When rolling over ice, the observed fluctuations mainly exhibit the propagation characteristics of "same speed as the vehicle" and have a strong excitation intensity, making the fluctuations approximately satisfy the simplified relationship driven by "moving load": , that is, the ice layer vibration frequency and spatial wave number under load driving Roughly proportional, the proportionality coefficient is approximately the vehicle speed. Based on this approximation, the corresponding formula between wave number, frequency and wheel speed can be directly derived without solving more complex dispersion equations. Then the fluctuation wave number of the i-th monitoring node is , the linear approximation formula is: , this implementation has the following significant beneficial effects: The dynamic coupling between vehicle speed, ice layer fluctuation frequency and wave number is realized, which can accurately identify the high-risk state of a sharp increase in internal stress of the ice layer when the vehicle speed approaches or exceeds the critical wave speed.

[0027] All calculations are completed locally at the edge monitoring node, with a processing delay of hundreds of milliseconds, fully meeting the real-time requirements of vehicle driving monitoring.

[0028] By using linear approximation formulas, the computational complexity brought by directly solving high-order dispersion equations is avoided, and the demand for computing power of embedded edge devices is reduced.

[0029] In detail, step 2 is as follows: In one embodiment of the present invention, determining the vertical displacement of the ice layer and the curvature of the ice layer based on the wave number includes: The prior material parameters include: ice density, ice Poisson's ratio, ice elastic modulus, ice bending stiffness at each monitoring node, and ice thickness at each monitoring node; The fluctuation wave number and prior material parameters of each monitoring node are brought into the vibration equation as follows: ,in, represents the second-order derivative of the vertical displacement of the ice layer corresponding to the i-th monitoring node with respect to the trigger time, represents the density of the ice layer, represents the bending stiffness of the ice layer at the i-th monitoring node, represents the ice thickness of the monitoring node of the i-th monitoring node, represents the fluctuation wave number of the i-th monitoring node, represents the vertical displacement of the ice layer at the i-th monitoring node; the vertical displacement of the ice layer is obtained by solving the vibration equation through numerical integration; The ice layer curvature is obtained by performing a square operation on the fluctuation wave number and the vertical displacement of the ice layer.

[0030] In detail, step 2 also includes: To directly invert the vertical displacement and curvature of the ice layer based on the wave number, it is necessary to introduce the prior material parameters of the ice layer and substitute these parameters and the wave number into the ice layer vibration equation. Finally, the vertical displacement of the ice layer at each monitoring node is obtained through numerical solution, and the ice layer curvature is further calculated as follows: Ice density: refers to the density of the ice itself, measured in kilograms per cubic meter. A typical value is 917 kg / m³.

[0031] Poisson's ratio of ice: refers to the ratio between the transverse strain and the longitudinal strain of the ice material. The typical value is 0.3.

[0032] Ice elastic modulus: refers to the stiffness coefficient of ice material during elastic deformation, measured in Pascals. A typical value is 9 GPa.

[0033] Ice thickness at each monitoring node: refers to the ice thickness at the location of the i-th monitoring node, measured in meters. This is determined by the sonar unit at the monitoring node.

[0034] Bending stiffness of the ice layer at each monitoring node: The bending stiffness of the ice layer at the i-th monitoring node, in Newton-meters, is used as the bending elastic coefficient of the thin plate.

[0035] In the coupled system of the ice surface and the water below, the ice acts as a thin elastic plate whose thickness is much smaller than its length. Its bending dynamics can be approximately described by the Kirchhoff–Love thin plate theory. The free vibration equations for elastic thin plates derived from this theory contain fourth-order spatial and second-order temporal derivatives.

[0036] Based on a simplified vibration model of bending-gravity waves in a thin plate-fluid system, the wave number detected at each monitoring node and the prior material parameters are substituted into the transient vibration equation of the node and numerically solved. The vertical displacement of the ice layer is obtained, and the ice layer curvature is further calculated by multiplying the wave number and displacement. The details are as follows: At the i-th monitoring node, the number of fluctuation waves recorded by the i-th monitoring node is , and combined with the prior material parameters. Then the transient bending vibration of the node can be approximately described by a one-dimensional simplified thin plate vibration differential equation as follows: ,in, represents the vertical displacement of the ice layer corresponding to the i-th monitoring node, Indicates the vertical displacement of the ice layer at the i-th monitoring node to the trigger time The second derivative of , that is, the vertical acceleration; The fourth power of the wave number reflects the influence of higher-order derivatives in the plate bending differential equation on the bending shape. Its physical significance lies in the fact that as the wave number increases, the spatial curvature increases, and the energy distribution of the corresponding vibration mode changes accordingly.

[0037] It should be noted that the vertical displacement of the ice layer at each monitoring node is obtained by numerical solution, and the numerical solution algorithm can be: the fourth-order Runge-Kutta method.

[0038] In thin plate bending mechanics, the local curvature of the ice layer It can be approximately expressed as the second-order spatial derivative of displacement. However, in actual measurement, the continuous displacement curve of the ice layer in the spatial direction is not obtained, but the wave number is obtained. To indirectly characterize the spatial distribution characteristics.

[0039] The second-order spatial derivative is expressed as: , in, Indicates the spatial coordinate along the longitudinal extension direction of the ice surface (in meters), which is consistent with the direction of vehicle travel. It represents the second-order partial derivative of the spatial coordinate x, describing the degree of bending of the vertical displacement of the ice layer in the direction of the spatial coordinate x; Ice curvature and wave number and vertical displacement of the ice sheet There is an approximate relationship: , Step 3: Calculate the corrected wave velocity based on the vertical displacement of the ice layer and the fixed spacing to obtain a damping coefficient; and calculate the maximum bending stress of the corresponding monitoring node in combination with the ice layer curvature and prior material parameters; In one embodiment of the present invention, calculating the modified wave velocity based on the vertical displacement of the ice layer and the fixed spacing to obtain the damping coefficient includes: A trigger time window H is set to extract the vertical displacement of the ice layer and the amplitude of the vertical displacement of the ice layer within the time window H, starting from the trigger time of the monitoring node; Determine the peak value of the vertical displacement of the ice layer at the i-th monitoring node within the time window H, and the peak value of the vertical displacement of the ice layer at the monitoring nodes adjacent to the i-th monitoring node within the time window H, record the arrival time of the peak value of the vertical displacement of the ice layer, and calculate the arrival time difference; use the ratio of the fixed spacing and the arrival time difference as the corrected wave velocity; Determine the peak value of the vertical displacement amplitude of the ice layer at the i-th monitoring node within the time window H , and the peak amplitude of the vertical displacement of the ice layer at the monitoring nodes adjacent to the i-th monitoring node within the time window H , and calculate the damping coefficient of the i-th monitoring node ,as follows: ,in, Indicates fixed spacing.

[0040] In detail, the detection node records the trigger moment At the moment, immediately As the center, define a time period: Get The absolute value (amplitude) of the vertical displacement of the ice layer at each moment in the period, and the maximum value is taken as the peak value of the vertical displacement amplitude. When a vehicle travels over ice, it excites a time-series of flexure-gravity waves. As these waves propagate forward, they undergo two significant physical processes: First, the wave's propagation speed is not strictly equal to the speed corresponding to the time difference between the triggering time and the time recorded at the node at the time the vehicle is triggered, but rather lags slightly behind the vehicle's instantaneous load. Second, as the wave propagates, its amplitude decreases due to viscous dissipation in the ice itself and the water below. Based on these two points, we need to introduce a modified wave velocity and damping coefficient to more accurately characterize the true propagation characteristics of the wave, as follows: When a vehicle tire passes a monitoring node, the node's accelerometer records the transient impact of the vehicle's load on the ice surface, allowing a trigger time to be determined. However, the flexure-gravity wave does not directly reach the adjacent node at the trigger time. Instead, it propagates along a path where coupling, velocity conversion, and energy redistribution occur between the water and the ice. This causes the peak displacement of the wave to arrive at the adjacent node slightly later than the trigger time. Therefore, estimating the wave velocity solely by the difference in trigger times ignores this small but critical time lag. Within a time window H starting at the trigger time, the vertical displacement of the ice layer is extracted for each node's time series. The vertical displacement (amplitude) with the largest absolute value and the corresponding time are found. This time is the moment when the flexure-gravity wave is at its strongest and most easily identifiable after medium dissipation and propagation delay. This is also the moment when the flexure-gravity wave actually reaches the monitoring node and produces its maximum deflection. The arrival time difference represents the actual time it takes for the flexure-gravity wave to complete a propagation between two adjacent monitoring nodes and reach its peak. Therefore, the corrected wave velocity not only compensates for the phase lag effect, but also utilizes the most significant amplitude information of ice layer vibration, so it is more accurate than simply estimating the wave velocity using the trigger time difference.

[0041] Specifically, after the flexure-gravity wave starts from the vehicle loading point, it transfers energy in the ice layer due to elastic deformation, while at the same time it consumes energy in the water layer beneath the ice layer due to viscous resistance. This energy dissipation mechanism in the double-layer medium causes the amplitude of the flexure-gravity wave to gradually weaken with the horizontal propagation distance. Therefore, the flexure-gravity wave decays exponentially along the propagation distance, and the damping coefficient quantifies the logarithmic decay rate of the wave amplitude per unit distance. The peak amplitude detected at each monitoring node is , and the interval distance is No. The peak attenuation measured at each monitoring node is , then the damping coefficient is the one that reduces the bending-gravity wave to The damping coefficient describes the effect of the bending-gravity wave on the Monitoring nodes to The energy consumed by each monitoring node can reflect the comprehensive impact of the viscosity of ice and water, microcrack dissipation, etc. on wave attenuation.

[0042] therefore, , simplified to: .

[0043] In one embodiment of the present invention, the maximum bending stress of the corresponding monitoring node is calculated by combining the ice layer curvature and the prior material parameters, including: Calculate the maximum bending stress of the i-th monitoring node as follows: ,in, represents the maximum bending stress of the i-th monitoring node, represents the elastic modulus of the ice layer, represents the ice layer curvature of the i-th monitoring node.

[0044] Specifically, when a vehicle load acts on an ice layer, it behaves like a thin elastic plate in bending, deforming in the loaded zone. In this bending state, the fibers within the ice layer are subjected to both tension and compression. For example, fibers at the top of the ice layer experience horizontal tension, while those at the bottom experience compression. Fibers at the top and bottom surfaces of the ice layer experience the greatest stress, and therefore the maximum bending stress represents the internal force limit that the weakest fibers within the ice layer can withstand when bending.

[0045] In the classical elastic thin plate bending theory, there is a very intuitive linear relationship between bending stress and curvature. If the ice layer has ice curvature at a certain point According to Hooke's law and thin plate mechanics, the thickness is The curvature of the ice layer When, located The maximum bending stress of the i-th monitoring node is the largest, which can be expressed as: , Step 4: Each monitoring node exchanges the corrected wave velocity and the maximum bending stress, and uses a distributed alternating direction multiplier method for iterative processing to obtain a global average wave velocity and a global average bending stress of the target monitored ice surface; In one embodiment of the present invention, each monitoring node exchanges the corrected wave velocity and the maximum bending stress, and uses a distributed alternating direction multiplier method for iterative processing to obtain a global average wave velocity and a global average bending stress of the target monitored ice surface, including: Step 41, load the local variables and dual variables of the alternating direction multiplier; among them, the corrected wave velocity and maximum bending stress Local variables that serve as multipliers in alternating directions , initialize the corresponding dual variables All are 0; Step 42, at the kth iteration, k ≥ 0, based on the dual variable of the kth iteration Update local variables , as follows: , in, They represent the local variables updated by the i-th monitoring node in the k+1-th iteration, They represent the dual variables of the i-th monitoring node at the k-th iteration, represents the penalty factor of the penalty factor distributed alternating direction multiplier method; Step 43: Get the M×N monitoring nodes Average value are respectively used as the global average values ​​of the k+1th iteration; among them, ; Step 44: Based on the global average value of the k+1th iteration, update the dual variable , as follows: , , in, denote the dual variables of the k+1th iteration respectively; Step 45 , looping steps 42 to 44 repeatedly for a preset number of times, to obtain the global average wave velocity and the global average bending stress of the target monitored ice surface.

[0046] It should be noted that the distributed alternating direction multiplier method is an existing technology and will not be described in detail.

[0047] Step 5: Each monitoring node calculates a critical wave speed based on the global average wave speed and the prior material parameters, compares the global average bending stress with a preset bending stress threshold to generate a safety factor, and generates a speed margin based on the vehicle's real-time wheel speed and the critical wave speed; In one embodiment of the present invention, each monitoring node calculates a critical wave speed based on the global average wave speed and the prior material parameters, compares the global average bending stress with a preset bending stress threshold to generate a safety factor, and generates a speed margin based on the vehicle's real-time wheel speed and the critical wave speed, including: The calculation formula of critical wave speed is as follows: , in, represents the critical wave velocity of the i-th monitoring node, represents the critical wave number of the i-th monitoring node, is the Poisson's ratio of the ice layer, represents the gravitational acceleration; where the global average wave velocity is used as the initial value of the critical wave number to iteratively converge Get the critical wave number; The ratio of the global average bending stress to the preset bending stress threshold is used as the safety factor ; The ratio of the vehicle's real-time wheel speed to the critical wave speed is used as the speed margin of the corresponding monitoring node .

[0048] Specifically, when a vehicle travels across the ice, flexure-gravity waves (BGWs) are generated. When these waves propagate through the ice, if the vehicle's speed is below a certain critical value, gravity dominates the wave's motion. However, once the speed exceeds this critical value, the flexure of the ice (the rigidity of the ice itself as a solid sheet) begins to dominate, causing a sudden shift in the propagation mode of the BGWs. The critical wave speed is the speed at which the flexure-gravity wave pattern in the ice shifts from being dominated by gravity waves to being dominated by the ice's flexure. When the vehicle's actual speed approaches or exceeds the critical wave speed, the bending deformation within the ice sheet is amplified, making the ice more susceptible to cracks.

[0049] The safety factor represents the ratio between the maximum bending stress that the ice layer can withstand and the preset maximum allowable bending stress of the ice layer. The preset maximum allowable bending stress of the ice layer is set by experts. If the safety factor is greater than 1, the risk is high. If the safety factor is less than or equal to 1, the ice layer risk is low.

[0050] The speed margin represents the ratio of the vehicle's real-time wheel speed to the critical wave speed. If the speed margin is greater than 1, the ice risk is high; if the speed margin is less than or equal to 1, the ice risk is low.

[0051] In step 6, each monitoring node fuses the speed margin, the safety factor, and the damping coefficient according to preset weights to obtain a global average risk, and outputs a target monitoring ice surface management plan based on the global average risk.

[0052] In one embodiment of the present invention, each monitoring node fuses the speed margin, the safety factor, and the damping coefficient according to preset weights to obtain a global average risk, and outputs a target monitoring ice surface management plan based on the global average risk, including: The speed margin, damping coefficient, and safety factor of each monitoring node are linearly integrated according to the preset weights to obtain the local risk index of each monitoring node; Pick The average value of the local risk indicators of the monitoring nodes is used to obtain the global average risk; When the global average risk is greater than or equal to the preset global risk threshold, the target monitoring ice surface is turned off; otherwise, the target monitoring ice surface is kept on.

[0053] In detail, the calculation formula of the local risk index of the i-th monitoring node is as follows: ,in, represent the first preset weight, the second preset weight and the third preset weight respectively, The sum of is 1 and all are greater than 0.

[0054] A distributed intelligent monitoring system based on a multi-node edge computing device, applied to any of the above-mentioned distributed intelligent monitoring methods based on a multi-node edge computing device, comprises: a data acquisition module configured to arrange M×N monitoring nodes at a fixed spacing on the target monitoring ice surface; record a corresponding trigger time when the vertical acceleration collected by any monitoring node exceeds a preset acceleration threshold, and calculate the vehicle's real-time wheel speed based on the trigger time and the fixed spacing; a data processing module, configured to obtain a main frequency of the fluctuation based on the vertical acceleration corresponding to the trigger time, associate the main frequency of the fluctuation with the real-time wheel speed of the vehicle, first determine the number of fluctuations, and then determine the vertical displacement of the ice layer and the curvature of the ice layer based on the number of fluctuations; A bending stress module is used to calculate the modified wave velocity based on the vertical displacement of the ice layer and the fixed spacing to obtain a damping coefficient; and to calculate the maximum bending stress of the corresponding monitoring node in combination with the ice layer curvature and prior material parameters; An iterative averaging module is used to exchange the corrected wave velocity and the maximum bending stress at each monitoring node, and obtain the global average wave velocity and the global average bending stress of the target monitored ice surface through iterative processing using a distributed alternating direction multiplier method; a risk factor module, wherein each monitoring node calculates a critical wave speed based on the global average wave speed and the prior material parameters, compares the global average bending stress with a preset bending stress threshold to generate a safety factor, and generates a speed margin based on the vehicle's real-time wheel speed and the critical wave speed; The risk assessment module integrates the speed margin, the safety factor, and the damping coefficient at each monitoring node according to a preset weight to obtain a global average risk, and outputs a target monitoring ice surface management plan based on the global average risk.

[0055] The above describes the embodiments of this embodiment, but this embodiment is not limited to the above specific implementation methods. The above specific implementation methods are merely illustrative and not restrictive. Ordinary technicians in this field can also make many forms based on the inspiration of this embodiment, all of which are protected by this embodiment.

Claims

1. A distributed intelligent monitoring method based on multi-node edge computing devices, characterized in that: include: Step 1: Arrange M×N monitoring nodes at a fixed spacing on the target monitoring ice surface; when the vertical acceleration collected by any monitoring node exceeds a preset acceleration threshold, record the corresponding trigger time, and calculate the vehicle's real-time wheel speed based on the trigger time and the fixed spacing; Step 2: obtaining a main frequency of the fluctuation based on the vertical acceleration corresponding to the trigger time, and correlating the main frequency of the fluctuation with the real-time wheel speed of the vehicle, first determining the number of fluctuations, and then determining the vertical displacement of the ice layer and the curvature of the ice layer based on the number of fluctuations; Step 3, calculating a corrected wave velocity based on the vertical displacement of the ice layer and the fixed spacing to obtain a damping coefficient; Combining the ice layer curvature and prior material parameters, the maximum bending stress of the corresponding monitoring node is calculated; Step 4: Each monitoring node exchanges the corrected wave velocity and the maximum bending stress, and uses a distributed alternating direction multiplier method for iterative processing to obtain a global average wave velocity and a global average bending stress of the target monitored ice surface; Step 5: Each monitoring node calculates a critical wave speed based on the global average wave speed and the prior material parameters, compares the global average bending stress with a preset bending stress threshold to generate a safety factor, and generates a speed margin based on the vehicle's real-time wheel speed and the critical wave speed; In step 6, each monitoring node fuses the speed margin, the safety factor, and the damping coefficient according to preset weights to obtain a global average risk, and outputs a target monitoring ice surface management plan based on the global average risk.

2. The distributed intelligent monitoring method based on multi-node edge computing devices according to claim 1 is characterized in that: Calculating the real-time wheel speed of the vehicle based on the trigger time and the fixed interval includes: The trigger time when the vertical acceleration of the i-th monitoring node is greater than the preset acceleration threshold; Performing differential processing on the triggering time of the monitoring nodes adjacent to the i-th monitoring node to obtain differential time; The fixed interval is divided by the differential time of the trigger time to obtain the real-time wheel speed of the vehicle.

3. The distributed intelligent monitoring method based on multi-node edge computing devices according to claim 2 is characterized in that: The method includes: obtaining a main frequency of the fluctuation based on the vertical acceleration corresponding to the trigger time, correlating the main frequency of the fluctuation with the real-time wheel speed of the vehicle, and determining a number of fluctuation waves, including: Taking the trigger time as the center, intercepting the time window of the vertical acceleration of the i-th monitoring node; Performing time-frequency analysis on the vertical acceleration within the time window to obtain the main frequency of the fluctuation; The main frequency of the fluctuation is associated with the real-time wheel speed of the vehicle, and the corresponding fluctuation wave number is output.

4. The distributed intelligent monitoring method based on multi-node edge computing devices according to claim 3 is characterized in that: Determine the vertical displacement of the ice layer and the curvature of the ice layer based on the wave number, including: The prior material parameters include: ice density, ice Poisson's ratio, ice elastic modulus, ice bending stiffness at each monitoring node, and ice thickness at each monitoring node; The fluctuation wave number and prior material parameters of each monitoring node are brought into the vibration equation as follows: in, represents the second-order derivative of the vertical displacement of the ice layer corresponding to the i-th monitoring node with respect to the trigger time, represents the density of the ice layer, represents the bending stiffness of the ice layer at the i-th monitoring node, represents the ice thickness of the monitoring node of the i-th monitoring node, represents the fluctuation wave number of the i-th monitoring node, represents the vertical displacement of the ice layer at the i-th monitoring node; the vertical displacement of the ice layer is obtained by solving the vibration equation through numerical integration; The ice layer curvature is obtained by performing a square operation on the fluctuation wave number and the vertical displacement of the ice layer.

5. The distributed intelligent monitoring method based on multi-node edge computing devices according to claim 4 is characterized in that: Calculating a corrected wave velocity based on the vertical displacement of the ice layer and the fixed spacing to obtain a damping coefficient includes: A trigger time window H is set to extract the vertical displacement of the ice layer and the amplitude of the vertical displacement of the ice layer within the time window H, starting from the trigger time of the monitoring node; Determine the peak value of the vertical displacement of the ice layer at the i-th monitoring node within the time window H, and the peak value of the vertical displacement of the ice layer at the monitoring nodes adjacent to the i-th monitoring node within the time window H, record the arrival time of the peak value of the vertical displacement of the ice layer, and calculate the arrival time difference; use the ratio of the fixed spacing and the arrival time difference as the corrected wave velocity; Determine the peak value of the vertical displacement amplitude of the ice layer at the i-th monitoring node within the time window H , and the peak amplitude of the vertical displacement of the ice layer at the monitoring node adjacent to the i-th monitoring node within the time window H , and calculate the damping coefficient of the i-th monitoring node ,as follows: ， in, Indicates fixed spacing.

6. The distributed intelligent monitoring method based on multi-node edge computing devices according to claim 5 is characterized in that: Combining the ice layer curvature and prior material parameters, the maximum bending stress of the corresponding monitoring node is calculated, including: Calculate the maximum bending stress of the i-th monitoring node as follows: in, represents the maximum bending stress of the i-th monitoring node, represents the elastic modulus of the ice layer, represents the ice layer curvature of the i-th monitoring node.

7. The distributed intelligent monitoring method based on multi-node edge computing devices according to claim 6 is characterized in that: Each monitoring node exchanges the corrected wave velocity and the maximum bending stress, and uses a distributed alternating direction multiplier method for iterative processing to obtain the global average wave velocity and the global average bending stress of the target monitored ice surface, including: Step 41, load the local variables and dual variables of the alternating direction multiplier; among them, the corrected wave velocity and maximum bending stress Local variables that serve as multipliers in alternating directions , initialize the corresponding dual variables All are 0; Step 42, at the kth iteration, k ≥ 0, based on the dual variable of the kth iteration and Update local variables ; Step 43: Get the M×N monitoring nodes Average value are respectively used as the global average values ​​of the k+1th iteration; among them, ; Step 44: Based on the global average value of the k+1th iteration, update the dual variable ; Step 45 , looping steps 42 to 44 repeatedly for a preset number of times, to obtain the global average wave velocity and the global average bending stress of the target monitored ice surface.

8. The distributed intelligent monitoring method based on multi-node edge computing devices according to claim 7 is characterized in that: Each monitoring node calculates a critical wave speed based on the global average wave speed and the prior material parameters, compares the global average bending stress with a preset bending stress threshold to generate a safety factor, and generates a speed margin based on the vehicle's real-time wheel speed and the critical wave speed, including: The calculation formula of critical wave speed is as follows: ， ， ,in, represents the critical wave velocity of the i-th monitoring node, represents the critical wave number of the i-th monitoring node, is the Poisson's ratio of the ice layer, represents the gravitational acceleration; where the global average wave velocity is used as the initial value of the critical wave number to iteratively converge Get the critical wave number; The ratio of the global average bending stress to the preset bending stress threshold is used as the safety factor ; The ratio of the vehicle's real-time wheel speed to the critical wave speed is used as the speed margin of the corresponding monitoring node .

9. The distributed intelligent monitoring method based on multi-node edge computing devices according to claim 8, characterized in that: Each monitoring node fuses the speed margin, the safety factor, and the damping coefficient according to a preset weight to obtain a global average risk, and outputs a target monitoring ice surface management plan based on the global average risk, including: The speed margin, damping coefficient, and safety factor of each monitoring node are linearly integrated according to the preset weights to obtain the local risk index of each monitoring node; Pick The average value of the local risk indicators of the monitoring nodes is used to obtain the global average risk; When the global average risk is greater than or equal to the preset global risk threshold, the target monitoring ice surface is turned off; otherwise, the target monitoring ice surface is kept on.

10. A distributed intelligent monitoring system based on a multi-node edge computing device, applied to the distributed intelligent monitoring method based on a multi-node edge computing device according to any one of claims 1 to 9, characterized in that: include: a data acquisition module configured to arrange M×N monitoring nodes at a fixed spacing on the target monitoring ice surface; record a corresponding trigger time when the vertical acceleration collected by any monitoring node exceeds a preset acceleration threshold, and calculate the vehicle's real-time wheel speed based on the trigger time and the fixed spacing; a data processing module, configured to obtain a main frequency of the fluctuation based on the vertical acceleration corresponding to the trigger time, associate the main frequency of the fluctuation with the real-time wheel speed of the vehicle, first determine the number of fluctuations, and then determine the vertical displacement of the ice layer and the curvature of the ice layer based on the number of fluctuations; a bending stress module, configured to calculate a modified wave velocity based on the vertical displacement of the ice layer and the fixed spacing to obtain a damping coefficient; Combining the ice layer curvature and prior material parameters, the maximum bending stress of the corresponding monitoring node is calculated; An iterative averaging module is used to exchange the corrected wave velocity and the maximum bending stress at each monitoring node, and obtain the global average wave velocity and the global average bending stress of the target monitored ice surface through iterative processing using a distributed alternating direction multiplier method; a risk factor module, wherein each monitoring node calculates a critical wave speed based on the global average wave speed and the prior material parameters, compares the global average bending stress with a preset bending stress threshold to generate a safety factor, and generates a speed margin based on the vehicle's real-time wheel speed and the critical wave speed; The risk assessment module integrates the speed margin, the safety factor, and the damping coefficient at each monitoring node according to a preset weight to obtain a global average risk, and outputs a target monitoring ice surface management plan based on the global average risk.

Images