A snow state monitoring system based on wireless sensing technology and cloud service

Abstract

The application discloses a kind of based on wireless sensing technology and cloud service's snow state monitoring system, belong to snow disaster monitoring technical field, including node deployment module, for recording node information;Node activation module, assess whether to activate node;Structure identification module, the data collected to snow layer structure is identified and judged by receiving activated node;Node scheduling module, for judging node subsequent working state;Information aggregation module, the information collected by activated node is integrated and labels dangerous area.This based on wireless sensing technology and cloud service's snow state monitoring system, through the monitoring mechanism and energy state perception model of the multi-level structure state of perception snow, combined with snow condition change trend, dynamically regulates node sampling frequency, data back behavior and communication path, effectively prolongs the equipment running cycle and improves the maintainability in harsh environment, can be based on the snow layer state change condition identified to priority allocation monitoring resource.

Description

Technical Field

[0001] This invention belongs to the field of snow disaster monitoring technology, and in particular relates to a snow cover status monitoring system based on wireless sensing technology and cloud services. Background Technology

[0002] With the increasing frequency of extreme weather events, snow cover monitoring is playing an increasingly important role in public safety, traffic management, power facility operation and maintenance, and disaster early warning in mountainous areas. Currently, many regions, especially high-altitude or remote areas, rely on snow sensor networks to monitor snowfall changes in real time and prevent risks such as avalanches, ice storms, road closures, and power outages. Existing snow cover monitoring systems are mainly based on sensors for physical quantities such as snow depth, temperature, and humidity. These sensors typically transmit collected data back to a cloud platform via wireless communication for data visualization and early warning analysis. Meanwhile, the development of cloud services, low-power IoT devices, and edge computing technologies in recent years has also provided technical support for snow condition monitoring, gradually forming a monitoring system of "front-end perception + back-end analysis."

[0003] However, current technologies primarily rely on "point-based measurements," indirectly inferring regional snow cover conditions by measuring variables such as snow depth, temperature, and humidity at a specific location. This lacks the ability to effectively identify the internal structural state of snow cover (e.g., layering, cavities, ice sheets). This prevents the system from determining the presence of potentially unstable structures in the snow, severely limiting its applicability in critical scenarios such as avalanche warning and snow pressure assessment. Secondly, the complexity of snowy environments makes sensor nodes highly susceptible to snow cover or damage, limiting node communication quality. Furthermore, most systems rely on battery power, leading to significant energy consumption issues during long-term operation. Existing systems generally employ periodic sampling and unified reporting mechanisms, failing to intelligently schedule data collection based on node status, remaining battery power, and snow condition changes, resulting in unnecessary data redundancy and energy waste. Thirdly, due to significant differences in snow cover evolution paths across different regions, existing systems lack the ability to assess "task urgency" in data acquisition scheduling, failing to prioritize "potential risk points," thus causing delayed responses to sudden risks. Furthermore, existing systems generally employ simple rules or threshold judgments in sensor data processing, failing to fully utilize structured modeling methods for in-depth analysis and prediction of snow conditions, resulting in the data value not being effectively mined.

[0004] To address these issues, we propose a snow cover status monitoring system based on wireless sensing technology and cloud services. Summary of the Invention

[0005] The purpose of this invention is to solve the problems of lack of snow layer structure identification and inability to intelligently schedule in the existing technology, and to propose a snow cover status monitoring system based on wireless sensing technology and cloud services.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] A snow cover status monitoring system based on wireless sensing technology and cloud services includes:

[0008] The node deployment module is used to record basic node information and calculate risk sensitivity scores for each node. The basic node information includes node location information, node terrain conditions, node energy status, and node slope conditions. The risk sensitivity scores are obtained by weighted calculation of the basic node information.

[0009] The node activation module is used to determine whether a node is to be activated. The node is evaluated by a node activation score, which is calculated by weighting the node's basic information and risk sensitivity score. Nodes that reach the activation threshold are activated. After the node is activated, sound wave sampling and information recording are performed to obtain sound wave reflection data, node temperature and snow depth.

[0010] The structure recognition module is used to model and recognize feature structure vectors and output a structure risk score. The feature structure vectors include sound wave reflection data, node basic information, node temperature and snow depth. The structure risk score is calculated through a structure mapping model, which consists of two layers of linear transformation and activation function.

[0011] The node scheduling module is used to determine whether each node should continue sampling or enter hibernation in the current scheduling cycle. The determination is made by comparing the node scheduling score with the scheduling threshold. The node scheduling score is obtained by weighting the structural risk score, node energy status, node location information and temperature change rate into the scheduling score function. The temperature change rate is calculated from the node temperature.

[0012] The information aggregation module is used to aggregate the input data of all activated nodes to obtain a regional structural risk map. The input data includes the spatial coordinates of the nodes, structural risk scores, and node scheduling status. The regional structural risk map is calculated by a spatial weighted interpolation algorithm and then written into a two-dimensional grid or vector map. A structural risk threshold is set, and when the structural risk score is higher than the structural risk threshold, it is marked as a risk area.

[0013] Preferably, the node energy status includes the node's initial power, the node's remaining power, and the power supply status of the node's solar panels.

[0014] Preferably, a redundancy regularization term is introduced into the activation scoring function to indicate whether there are other nodes that have recently been sampled in the local region, thus avoiding duplicate sampling.

[0015] Preferably, the activation threshold is a dynamic threshold, which is adjusted based on the average environmental fluctuation value of all nodes in the most recent time window. When the average environmental fluctuation value is at its maximum, the activation threshold is at its minimum.

[0016] Preferably, the acoustic wave reflection data includes the acoustic wave reflection signal, the primary reflection delay, the primary reflection echo intensity, the attenuation intensity, the number of multiple reflections, and the effective reflective layer count.

[0017] Preferably, a risk-sensitive regularization term is introduced into the structure mapping model to highlight the potential risk sensitivity of high stratification and near-phase transition temperatures. It is constructed by multiplying the stratification complexity, snow temperature sensitivity, and structural risk score. The stratification complexity is obtained by standardizing the number of multi-echo structures, and the snow temperature sensitivity is obtained by the average temperature of past time windows.

[0018] Preferably, the scheduling threshold is a dynamic threshold, which is adjusted based on the temperature drop within the most recent time window. When the temperature drop is large, the scheduling threshold is small.

[0019] Preferably, when the node scheduling score is greater than the scheduling threshold, the node enters the active state and performs acoustic sampling; when the node scheduling score is less than or equal to the scheduling threshold, the node enters the sleep mode and delays the next sampling.

[0020] Preferably, the information aggregation module is also used to calculate the gradient change rate of the region to help determine whether there is a trend of drastic structural change, which is obtained through central difference calculation.

[0021] In summary, the technical effects and advantages of this invention are as follows: This snow cover condition monitoring system based on wireless sensing technology and cloud services designs a monitoring mechanism capable of sensing the multi-layered structural state of snow cover. This allows the system to no longer rely on indirect parameters such as single-point snow depth, but instead identify key snow layer characteristics including layer thickness, compaction degree, and structural heterogeneity, thereby improving the ability to identify potential structural instability. Secondly, the system incorporates an energy state perception model into the sensor node design, dynamically adjusting the node sampling frequency, data transmission behavior, and communication path based on snow condition trends, effectively extending the equipment's operating cycle and improving maintainability in harsh environments. Furthermore, the system proposed in this invention possesses "risk-driven scheduling capability," enabling priority allocation of monitoring resources based on identified snow layer state changes, ensuring real-time uploading and priority processing of data from high-risk areas. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of the structure in this invention. Detailed Implementation

[0023] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0024] like Figure 1 As shown, a snow cover status monitoring system based on wireless sensing technology and cloud services includes:

[0025] The node deployment module is used to record basic node information and calculate risk sensitivity scores for each node. The basic node information includes node location information, node terrain conditions, node energy status, and node slope conditions. The risk sensitivity scores are obtained by weighted calculation of the basic node information.

[0026] The node activation module is used to determine whether a node is to be activated. The node is evaluated by a node activation score, which is calculated by weighting the node's basic information and risk sensitivity score. Nodes that reach the activation threshold are activated. After the node is activated, sound wave sampling and information recording are performed to obtain sound wave reflection data, node temperature and snow depth.

[0027] The structure recognition module is used to model and recognize feature structure vectors and output a structure risk score. The feature structure vectors include sound wave reflection data, node basic information, node temperature and snow depth. The structure risk score is calculated through a structure mapping model, which consists of two layers of linear transformation and activation function.

[0028] The node scheduling module is used to determine whether each node should continue sampling or enter hibernation in the current scheduling cycle. The determination is made by comparing the node scheduling score with the scheduling threshold. The node scheduling score is obtained by weighting the structural risk score, node energy status, node location information and temperature change rate into the scheduling score function. The temperature change rate is calculated from the node temperature.

[0029] The information aggregation module is used to aggregate the input data of all activated nodes to obtain a regional structural risk map. The input data includes the spatial coordinates of the nodes, structural risk scores, and node scheduling status. The regional structural risk map is calculated by a spatial weighted interpolation algorithm and then written into a two-dimensional grid or vector map. A structural risk threshold is set, and when the structural risk score is higher than the structural risk threshold, it is marked as a risk area.

[0030] The following is a detailed description of the system operation steps in this embodiment:

[0031] Step 1: Node Modeling and Risk Perception Preset

[0032] This step aims to complete the initial deployment of the entire system, establishing reasonable data support for structure identification and dynamic scheduling in subsequent steps. In particular, in this patent, the snow scene has the following typical characteristics:

[0033] The nodes can be deployed in various environments (such as mountains, rooftops, and bridges);

[0034] The power source relies on batteries and possible solar energy, and long-term operation is extremely sensitive to energy consumption.

[0035] The goal is to prioritize the identification and monitoring of areas with high structural risks and high terrain sensitivity.

[0036] Record basic information for each node i and construct a node status table.

[0037]

[0038] x i ,y i The latitude and longitude of the node are obtained from the GPS module;

[0039] h i The elevation of a node can be extracted using GPS or a digital elevation map (DEM).

[0040] T i Node deployment terrain type, discrete variables (e.g., roof = 1, slope = 2, flat land = 3, mountain = 4), obtained through manual annotation or remote sensing image recognition;

[0041] The initial battery level of the node, in Wh, is read in real time by the battery power acquisition module;

[0042] S i : Whether there is solar panel power supply, Boolean variable (1 indicates yes, 0 indicates no);

[0043] V i : Slope angle at node deployment location, in degrees (°), measured by tilt sensor.

[0044] Calculate the risk sensitivity score λ for each node. i This is used to guide the prioritization of subsequent structural monitoring:

[0045]

[0046] λ i : Risk sensitivity score of nodes, normalized to [0,1], the higher the score, the more likely structural instability will occur;

[0047] w1, w2, w3: Manually set weighting coefficients used to control the influence weight of different factors (e.g., w1 = 0.6, w2 = 0.3, w3 = 0.1);

[0048] T i : Terrain type factor (discrete values);

[0049] V i : Slope angle, in degrees;

[0050] SlopeFactor(h i ): A slope-elevation related correction factor used to reflect the higher likelihood of structural anomalies in high-altitude areas, for example:

[0051]

[0052] After the nodes are deployed, their status and risk sensitivity are uploaded to the cloud to form a node configuration dataset.

[0053]

[0054] Step 2: Structure-driven acoustic wave sampling scheduling

[0055] The goal of this step is to dynamically activate sensor nodes deployed in areas with higher snow disaster risk to perform structure-level acoustic sampling operations, while meeting low power consumption constraints. This step is a key scheduling step in realizing the "state-level snow accumulation monitoring system" of this patent, and it follows the node risk sensitivity λ from step one. i and energy status By employing innovative scoring functions and redundancy regularization mechanisms, a sampling decision-making strategy of "structural risk-driven + energy feasibility assessment + spatial coverage optimization" is implemented. Unlike traditional timed or uniform strategies, snow accumulation exhibits high terrain dependence and localized abrupt changes. For example, snow accumulation on steep slopes is more prone to structural stratification and cavities, potentially triggering avalanches; while changes in snow pressure at the base of power towers may indicate snow load risks. Therefore, this step must not only consider whether the sensor "has power," but also answer whether it is worthwhile to activate this node to sample structural information.

[0056] To achieve this goal, we define a node sampling activation scoring function A. i (t), which is the core decision-making element for whether node t enters the acoustic sampling state at time t:

[0057]

[0058] in:

[0059] A i(t): Activation score of node i at time t;

[0060] λ i The risk sensitivity score of a node (generated from step one) reflects the physical importance of the node in structural monitoring.

[0061] E i (t): The node's current remaining power, in Wh, is periodically updated by the hardware power acquisition module;

[0062] The initial power of the node has been set in step one;

[0063] S i : Does it have solar panel support (1 for yes, 0 for no)?

[0064] Redundancy(x i ,y i ,R loc ): Indicates that the node is in the local region R loc The function returns a density penalty term (e.g., the number of nearest neighbors divided by the total number of neighbors) to determine whether there are other recently sampled nodes within a radius of 10 meters.

[0065] Volatility i (t): The node's location is the nearest T. v Estimates of the magnitude of temperature fluctuations or snow surface height changes within minutes (e.g., rate of temperature decrease + snow depth fluctuations) are used to capture potential drastic changes.

[0066] α,β,γ,δ,η: These are manually set adjustable weights. The default recommended values ​​are α=0.4, β=0.25, γ=0.15, δ=0.1, and η=0.1.

[0067] The creativity of this formula is reflected in the following points:

[0068] Structural risk drives λ i Unlike common scheduling strategies based on sensor power levels, this patent incorporates structural sensitivity into the core of sampling decisions, emphasizing "who is worth activating, rather than activating randomly."

[0069] Redundancy: By evaluating the sampling density near a node through local node state broadcasting or cloud scheduling records, duplicate sampling is avoided, thus reducing the overall energy consumption of the system.

[0070] Volatility, a driver of change i (t): Used to identify areas where snow cover changes rapidly (e.g., blizzard front, snow melting area under strong radiation), with strong scene adaptability and dynamic response capability;

[0071] The formula combination is a regular expression rather than a black box network: suitable for embedded deployment, avoiding high computing power requirements, and meeting the edge computing power limitations of snow zone nodes.

[0072] The system automatically sets an activation threshold τ(t) within each scheduling cycle, and only when A... i Nodes where (t)>τ(t) are activated to perform acoustic sampling:

[0073]

[0074] τ(t): The activation threshold of the system at time t;

[0075] τ0: The initial activation threshold of the system (e.g., set to 0.5);

[0076] κ: Adjustment coefficient;

[0077] In the past T v Average Volatility of all nodes within the time window i The (t) value reflects the degree of fluctuation in the current global environment.

[0078] When the system detects a drastic change in the overall environment (such as a sudden drop in temperature or concentrated snow melting), τ(t) automatically decreases, thereby allowing more nodes to enter the sampling state and realizing a rapid response mechanism.

[0079] All satisfying A i Nodes where (t)>τ(t) are activated, and the following specific operations are performed:

[0080] Activate the sound wave transmitter to emit short pulses with a frequency range of 1–3 kHz;

[0081] The snow reflection signal S is collected by a microphone array. i (t), and record the echo characteristics (such as the main reflection delay Δt). i Attenuation intensity A i Number of multiple reflections n i );

[0082] Local temperature, humidity, timestamps, etc. are recorded synchronously for subsequent model interpretation.

[0083] All results are input into the next step of the structural state recognition model.

[0084] Step 3: Snow Layer Structure Identification and Multi-Level Risk Scoring

[0085] This step follows up on the acoustic reflection data S collected by the activated node i in the previous step. i (t), and its associated structural features Δt i (Primary reflection delay time), Ai (reflection intensity), n i (Number of reflections), T i (t)(current temperature), H i (t)(snow depth), etc., constitute the input feature vector x. i By deeply modeling and identifying these structural signals, it is inferred whether there are structural anomalies (such as weak layers, cavities, ice plate interlayers, etc.) inside the snow body in this area, thereby outputting a continuous structural risk score R. i This data will be used by subsequent behavior scheduling and regional early warning modules. Unlike traditional snow monitoring systems that rely solely on characterizing data such as snow depth or temperature, this step involves constructing a "structural state mapping model" to mine the hierarchical change characteristics in the sound wave propagation signal and substantially determine whether the snow body has a potentially unstable structure.

[0086] The input feature vector is defined as follows:

[0087] x i =(Δt) i A i ,n i ,T i (t),H i (t))

[0088] Δt i The primary reflection delay of a sound wave, measured in milliseconds (ms), is obtained through sound wave timing signal detection and reflects the total thickness of the snow layer or the first reflection interface.

[0089] A i : Main reflected echo intensity, in dB, indicates the density of the medium; ice layers typically reflect strongly.

[0090] n i Effective reflective layer count, identified in the echo signal using the zero-crossing / local peak method;

[0091] T i (t): The current temperature measured at the node, in °C;

[0092] H i (t): Current snow depth, obtained through the node's independent snow depth sensor, in cm.

[0093] This step employs a multi-layer acoustic structure fusion model. Its design goal is to extract the implicit physical structure information of multi-layered snow bodies from limited sensor data and output a continuous risk score R. i To adapt to edge computing environments, the model employs a lightweight two-layer neural network with structured physical regularization, as shown below:

[0094] R i=Sigmoid(W2·ReLU(W1·x) i +b1)+b2)

[0095] R i Structural risk score, defined as a continuous variable in the interval [0, 1], with higher values ​​indicating greater structural instability;

[0096] The structure mapping model consists of two layers of linear transformations and activation functions, with the parameter set θ = {W1, b1, W2, b2}.

[0097] The model is trained in the cloud using historical structured label data and then deployed to the edge of each node after model compression.

[0098] Compared to traditional classifiers, this model outputs a continuous risk measure, making it more suitable for building hierarchical response mechanisms.

[0099] To enhance the model's ability to identify "hazardous structural features," especially when the number of echoes n... i Multiple, reflection intensity A i When there are large fluctuations or the temperature is close to the critical melting point (e.g., -1℃ to 0℃), this step designs a snow temperature-driven risk-sensitive regularization term as an enhancement mechanism during the model training phase:

[0100]

[0101] BCE(R i ,y i ): Basic cross-entropy loss function, y i ∈{0,1} indicates whether structural instability has actually occurred in this region at this moment (according to experimental or historical data);

[0102] The second item is the structural layer number × snow temperature sensitivity × risk score modulation item;

[0103] Indicates past T w The average temperature over several minutes, in °C, is the sensitivity of this control risk hot zone identification.

[0104] n i / 3: Standardize the number of multi-echo structures to represent the complexity of snow body layering; the larger the number, the higher the risk.

[0105] λ: Regularization weight coefficient, recommended to be set to 0.15;

[0106] This regularization term highlights the potential risk sensitivity of the "high stratification + near phase transition temperature" scenario, and has a high degree of physical rationality and scenario fit.

[0107] Step 4: Node behavior scheduling driven by structure and energy coordination

[0108] The goal of this step is to build upon the structural risk score R output from step three in the previous step. i and the current remaining power E of the node i (t) executes node behavior scheduling, determining whether each node should continue sampling or enter a dormant state in the current scheduling cycle, so as to maximize the overall system uptime and energy efficiency while ensuring structural risk response capability.

[0109] The input variables for this step include:

[0110] R i The structural risk score from step three, ranging from [0,1], represents the degree of structural instability in the region where node i is located.

[0111] E i (t): The remaining power of the current node, in Wh, is read in real time through the node power acquisition module;

[0112] The node's initial charge;

[0113] x i ,y i The geographical location of the node is used for redundant calculations;

[0114] The rate of change of ambient temperature, ΔT(t), is obtained from a temperature sensor and is expressed in °C.

[0115] Node behavior scheduling is determined by a comprehensive scoring function U. i (t) Control:

[0116]

[0117] Variable description:

[0118] U i (t): The scheduling score of node i at time t, used to determine whether it is activated;

[0119] α: Structural risk weight (recommended α = 0.5);

[0120] β: Energy weight (recommended β = 0.3);

[0121] γ: Weight of redundancy penalty term (recommended γ = 0.2);

[0122] Redundancy(x i ,y i ): Calculate whether there are other sampled nodes in the neighborhood of a node (e.g., radius r = 10m). It can be represented by the normalized density of active nodes per unit area, in the range [0,1].

[0123] The system sets a dynamic scheduling threshold τ(t) to determine the sampling threshold for the current period, defined as follows:

[0124] τ(t)=τ0·(1-∈·ΔT(t))

[0125] Variable description:

[0126] τ(t): Dynamic scheduling threshold;

[0127] τ0: Initial threshold value (e.g., 0.5);

[0128] ∈: Temperature fluctuation adjustment coefficient (e.g., 0.05);

[0129] ΔT(t): represents the temperature drop in the last T minutes (e.g., if it is 3℃, then τ(t) = 0.5·(1-0.05·3) = 0.425), which comes from meteorological data from nodes or the cloud.

[0130] The scheduling policy execution process is as follows:

[0131] The node calculates its U locally. i (t);

[0132] If U i If (t)>τ(t), then the node enters the active state and performs acoustic sampling;

[0133] If U i If (t)≤τ(t), then the node enters sleep mode and delays the next sampling.

[0134] Node behavior state can be stored as A i (t+1)∈{activation, hibernation}, serves as the input for subsequent system evaluation and scheduling.

[0135] Step 5: Cloud aggregation, risk area identification, and remote collaborative response

[0136] The task of this step is to analyze the data (x) uploaded by all active nodes i at time t in the cloud. i ,y i ,R i A i (t+1) is aggregated to construct a structural risk map H(x, y) for the entire monitoring area, which can then be used for visualization, platform analysis, and auxiliary early warning functions. This step does not involve behavioral control; it is only responsible for spatial aggregation and information representation.

[0137] All input data must satisfy A. i (t+1) = 1, meaning only nodes that have been activated and successfully sampled are aggregated:

[0138] x i ,y iThe spatial coordinates of the nodes are derived from the deployed static GPS information;

[0139] R i Structural risk scoring is derived from the model in step three.

[0140] A i (t+1): Node behavior state, derived from the scheduling strategy in step four, with a value of 1 indicating valid sampling;

[0141] All data is uploaded to the cloud platform in real time and written to the database or cache in a structured format (such as JSON / Protobuf).

[0142] To construct a continuous regional structural risk map H(x,y), a spatial weighted interpolation algorithm based on Gaussian kernels is used, defined as follows:

[0143]

[0144] illustrate:

[0145] H(x,y): Structural risk score for grid point (x,y);

[0146] R i : Node structure score from step three;

[0147] d i : The Euclidean distance from node i to (x,y);

[0148] σ: Spatial attenuation coefficient (e.g., σ = 20m);

[0149] The set of active nodes whose distance (x,y) is less than r (e.g., r = 50m);

[0150] The interpolation results are written into a two-dimensional grid or vector map for risk heat map creation.

[0151] Cloud system sets structural risk threshold R crit (e.g., 0.7) is used to determine whether a grid area is a high-risk area, and is marked with red highlighting:

[0152] If H(x,y)>R crit The system will mark this point as high risk in the results;

[0153] Visual charts can be output by overlaying layers, allowing administrators to view them remotely.

[0154] To assist managers in identifying drastic changes in regional conditions, the system also calculates the regional gradient change rate Ψ(x,yi):

[0155]

[0156] illustrate:

[0157] Ψ(x,y): The intensity of risk change in the grid (x,y), used to help determine whether there is a trend of drastic structural change;

[0158] The values ​​are calculated using the central difference method;

[0159] These are not control parameters; they are only used for information analysis and heatmap auxiliary layer drawing.

[0160] The output of this step includes:

[0161] Spatial risk map H(x,y) (used for heat map display and regional analysis);

[0162] Auxiliary layer Ψ(x,y) (for visualizing gradient changes);

[0163] High-risk point list ((x,y) position + H(x,y) value);

[0164] The data is uploaded to the cloud database for platform management and access.

[0165] Final implementation instructions:

[0166] All interpolation and gradient calculations are performed asynchronously by cloud microservices.

[0167] The recommended update cycle for heatmaps is every 5 minutes (configurable);

[0168] Interpolation region density adaptation: use fine mesh in areas with high node density, and appropriately reduce resolution in low-density areas;

[0169] The output results can be displayed through the front-end web platform or the mobile map module, and API access and download are supported.

[0170] The technical solutions described in the embodiments of this application have at least the following technical effects or advantages: This solution designs a monitoring mechanism capable of sensing the multi-layered structural state within snow cover, enabling the system to no longer rely on indirect parameters such as single-point snow depth, but instead identify key snow layer characteristics including layer thickness, compaction degree, and structural heterogeneity, thereby improving the ability to identify potential structural instability. Secondly, the system incorporates an energy state perception model in its sensor node design, dynamically adjusting node sampling frequency, data transmission behavior, and communication paths based on snow condition trends, effectively extending equipment operating cycles and improving maintainability in harsh environments. Furthermore, the system proposed in this invention possesses "risk-driven scheduling capability," enabling priority allocation of monitoring resources based on identified snow layer state changes, ensuring real-time uploading and priority processing of data from high-risk areas. The entire system is built on a widely deployable wireless sensing platform, combined with a cloud-based dynamic analysis engine and intelligent scheduling algorithm, achieving a complete closed loop of "near-ground precise perception—remote dynamic management."

[0171] The working principle is as follows: By setting up a monitoring mechanism to sense the multi-layer structure of the snow cover, key snow layer characteristics, including layer thickness, compaction degree, and structural heterogeneity, are identified. An energy state sensing model is introduced, and combined with the snow condition change trend, the node sampling frequency, data transmission behavior, and communication path are dynamically adjusted.

[0172] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A snow cover status monitoring system based on wireless sensing technology and cloud services, characterized in that, include: The node deployment module is used to record basic information of each node and calculate a risk sensitivity score. The basic information of the node includes node location information, node terrain conditions, node energy status and node slope conditions. The risk sensitivity score is obtained by weighted calculation of the basic information of the node. The node activation module is used to determine whether a node is activated and to evaluate the node by means of a node activation score, which is obtained by weighting the node's basic information and risk sensitivity score. Nodes that reach the activation threshold are activated. After activation, sound wave sampling and information recording are performed to obtain sound wave reflection data, node temperature and snow depth. The structure recognition module is used to model and recognize feature structure vectors and output a structure risk score. The feature structure vector includes acoustic reflection data, node basic information, node temperature and snow depth. The structure risk score is calculated through a structure mapping model, which consists of two layers of linear transformation and activation function. The node scheduling module is used to determine whether each node should continue sampling or enter hibernation in the current scheduling cycle. The determination is made by comparing the node scheduling score with the scheduling threshold. The node scheduling score is obtained by weighting the structural risk score, node energy status, node location information and temperature change rate into the scheduling score function. The temperature change rate is calculated from the node temperature. The information aggregation module is used to aggregate the input data of all active nodes to obtain a regional structural risk map. The input data includes the spatial coordinates of the nodes, structural risk scores, and node scheduling status. The regional structural risk map is calculated by a spatial weighted interpolation algorithm and then written into a two-dimensional grid or vector map. Set a structural risk threshold; when the structural risk score is higher than the structural risk threshold, it is marked as a risk area.

2. The snow cover status monitoring system based on wireless sensing technology and cloud services according to claim 1, characterized in that, The node energy status includes the node's initial power, the node's remaining power, and the power supply status of the node's solar panels.

3. The snow cover status monitoring system based on wireless sensing technology and cloud services according to claim 1, characterized in that, The node activation score incorporates a redundancy regularization term to indicate whether there are other recently sampled nodes within the local area, thus avoiding duplicate sampling.

4. The snow cover status monitoring system based on wireless sensing technology and cloud services according to claim 1, characterized in that, The activation threshold is a dynamic threshold, which is adjusted based on the average environmental fluctuation value of all nodes in the most recent time window. When the average environmental fluctuation value is at its maximum, the activation threshold is at its minimum.

5. The snow cover status monitoring system based on wireless sensing technology and cloud services according to claim 1, characterized in that, The acoustic wave reflection data includes the acoustic wave reflection signal, the main reflection delay, the main reflection echo intensity, the attenuation intensity, the number of multiple reflections, and the effective reflective layer count.

6. The snow cover status monitoring system based on wireless sensing technology and cloud services according to claim 1, characterized in that, The structure mapping model introduces a risk-sensitive regularization term to highlight the potential risk sensitivity of high-level stratification and near-phase transition temperatures. It is constructed by multiplying the stratification complexity, snow temperature sensitivity, and structural risk score. The stratification complexity is obtained by standardizing the number of multi-echo structures, and the snow temperature sensitivity is obtained by the average temperature value of past time windows.

7. The snow cover status monitoring system based on wireless sensing technology and cloud services according to claim 1, characterized in that, The scheduling threshold is a dynamic threshold, which is adjusted based on the temperature drop within the most recent time window. When the temperature drop is large, the scheduling threshold is small.

8. The snow cover status monitoring system based on wireless sensing technology and cloud services according to claim 1, characterized in that, When the node scheduling score is greater than the scheduling threshold, the node enters the active state and performs acoustic sampling; when the node scheduling score is less than or equal to the scheduling threshold, the node enters the sleep mode and delays the next sampling.

9. The snow cover status monitoring system based on wireless sensing technology and cloud services according to claim 1, characterized in that, The information aggregation module is also used to calculate the gradient change rate of the region to help determine whether there is a trend of drastic structural change, which is obtained through central difference calculation.

Images