System and method for predicting external interference risk of electric control cabinet

Abstract

The invention relates to the technical field of electric control cabinet monitoring and management, and discloses an electric control cabinet external interference risk prediction system and method, and the system comprises a disturbance modeling module, a dust migration trend prediction module, a risk map generation module, and a risk identification and output module. A disturbance vector field model is constructed by collecting temperature, air pressure and airflow velocity data outside an electric control cabinet, a particulate matter migration path is simulated, the momentum change rate is calculated, and then a focusing risk map evolving along with time is generated in a space range. The system matches the space contour of the electric control cabinet with the atlas, outputs risk levels and maintenance suggestions, realizes feed-forward modeling and quantitative risk assessment of the dust pollution trend, and improves the operation reliability and the operation and maintenance intelligence level of the electric control system in a complex environment.

Description

Technical Field

[0001] This invention relates to the field of electrical control cabinet monitoring and management technology, and in particular to a system and method for predicting external interference risks of electrical control cabinets. Background Technology

[0002] During the long-term operation of high-temperature equipment in industrial sites, airborne dust particles, influenced by the pressure difference created by heat source disturbances and structural obstructions, often migrate along nonlinear paths, potentially leading to dust aggregation in localized areas. Especially when the dust's movement path coincides with the air inlet or gaps of the electrical control cabinet, even without a significant increase in dust concentration, dangerous accumulation can occur within a short period.

[0003] Most existing technologies focus on analyzing changes in dust concentration inside electrical control cabinets and rely heavily on human disturbances such as cabinet door opening for data collection. These methods cannot capture early dynamic signals of "focusing migration trends" in the air, nor can they provide predictive judgments before dust enters the equipment. Therefore, it is necessary to design a dust focusing trend modeling method driven by external thermal-air disturbances, and to provide early warnings before dust enters the cabinet, thereby improving the protection capabilities and intelligent operation and maintenance level of industrial electrical control equipment. Summary of the Invention

[0004] The first objective of this invention is to provide a system for predicting external interference risks in electrical control cabinets, which has the advantages of being able to complete migration trend assessment and risk focusing judgment before dust enters the equipment, thereby improving the lead time, spatial resolution and decision-making ability of detection response.

[0005] The above-mentioned technical objective of the present invention is achieved through the following technical solution:

[0006] A system for predicting external interference risks in electrical control cabinets, characterized in that it comprises:

[0007] The disturbance modeling module is used to collect ambient temperature distribution, airflow velocity vector and air pressure change data in the area around the electrical control cabinet, and to construct a disturbance vector field model based on the data.

[0008] The dust migration trend prediction module is used to use the disturbance vector field model as a boundary condition, combined with dust particle size and density parameters, to simulate the migration momentum path of particulate matter under the action of the disturbance field, and output the path cluster and its corresponding momentum change rate.

[0009] The risk map generation module is used to calculate the dust accumulation intensity per unit area in the target three-dimensional space based on the path cluster and momentum change rate, construct a dust focusing risk map, and introduce the disturbance persistence parameter in the disturbance vector field model to control the time evolution range of the map.

[0010] The risk identification and output module is used to spatially match the spatial outline of the electrical control cabinet with the high-risk areas in the dust focusing risk map, calculate the potential dust accumulation risk value on the cabinet surface, and output the risk level of the electrical control cabinet and the corresponding maintenance suggestions based on the risk value. The maintenance suggestions are called from a preset maintenance suggestion library, and the suggestion library corresponds one-to-one with different risk levels.

[0011] Further settings:

[0012] The disturbance modeling module includes:

[0013] The heat source detection unit is used to acquire the spatial distribution and thermal radiation parameters of high-temperature equipment, and to estimate the area affected by the heat source based on this.

[0014] The air pressure difference estimation unit is used to collect air pressure data from multiple measuring points in the area surrounding the electrical control cabinet, and calculate the air pressure gradient field based on the difference between the measuring points.

[0015] The airflow velocity acquisition unit is used to collect airflow velocity and direction information at different locations through multi-point miniature wind speed sensors installed around the electrical control cabinet, and generate an airflow velocity vector field.

[0016] The vector field generation unit is used to construct a disturbance vector field model based on the heat source parameters, air pressure gradient field and airflow velocity vector field, which is used to describe the driving characteristics of external air disturbances in the electrical control cabinet.

[0017] By adopting the above technical solution and introducing a heat source detection unit, a pressure difference estimation unit, and an airflow velocity acquisition unit into the disturbance modeling module, multi-dimensional perception of external environmental disturbance factors of the electrical control cabinet is achieved. By measuring the heat source distribution, pressure gradient, and airflow vector distribution respectively, the system can comprehensively capture the disturbance driving elements caused by equipment heating, air buoyancy, and local streamline bending in high-temperature industrial environments.

[0018] In particular, the airflow velocity acquisition unit collects airflow velocity and direction information based on multi-point micro wind speed sensors to construct a spatially continuous airflow velocity vector field, providing a real fluid field basis for subsequent disturbance vector field models.

[0019] This module not only strengthens the physical basis and predictability of the disturbance model, but also improves the accuracy of subsequent dust migration path simulation and the stability of disturbance-driven modeling, effectively enhancing the feedforward capability and controllability of the risk prediction mechanism.

[0020] Further settings:

[0021] The vector field generation unit constructs a perturbation vector field model based on the following steps:

[0022] The pressure gradient field generated by the pressure difference estimation unit, the airflow velocity vector field, and the thermal radiation distribution function output by the heat source detection unit are used as inputs.

[0023] A disturbance driving factor function is constructed to characterize the degree of influence of the disturbance source on local aerodynamics, wherein:

[0024]

[0025] in:

[0026] For the disturbance driving factor function;

[0027] This represents the pressure gradient field.

[0028] This represents the airflow velocity vector field.

[0029] Let be the thermal radiation distribution function;

[0030] α and β are the perturbation composite weighting coefficients, satisfying: α + β = 1;

[0031] Using the disturbance driving factor function as the boundary input, and combining the boundary conditions and continuity constraints within the three-dimensional control region, the disturbance vector field model is solved. Its definition is:

[0032]

[0033] Among them, e -t / τ is the perturbation attenuation factor, used to describe the natural attenuation process of the perturbation vector's effect on particulate matter migration over time t; where T is the perturbation duration time constant, reflecting the duration of the perturbation effect.

[0034] By employing the above technical solution, a disturbance driving factor function is constructed in the vector field generation unit, and weight control terms α and β are introduced to mathematically integrate the pressure gradient with the airflow-heat source coupled disturbance, forming a disturbance driving model with spatial continuity and physical causal logic. This model can dynamically reflect the actual disturbance intensity and direction characteristics based on the measured multi-source field data, achieving adjustable, interpretable, and computable disturbance generation.

[0035] By introducing a perturbation duration time constant τ into the vector field model, a perturbation vector field expression that decays exponentially over time is constructed, enabling time-dependent modeling of the impact of perturbation effects on dust migration. This mechanism avoids misjudgments of historical residues caused by static perturbation models and improves the fitting accuracy of migration trends in future time periods.

[0036] This modeling method, based on a functional expression of physical mechanisms, possesses versatility and adaptability, and can more realistically reflect the environmental response characteristics of particulate matter under complex thermal disturbances, providing a solid computational foundation for subsequent path simulation and risk assessment.

[0037] Further settings:

[0038] The dust migration trend prediction module, based on the perturbation vector field model output by the perturbation modeling module, constructs the dynamic migration trajectory of particulate matter using the Lagrange particle tracking method, specifically including:

[0039] The dust particles are simplified into a mass point model, and their motion path under the drive of the perturbation field is solved by combining the particle size, density, initial spatial position and initial time.

[0040] The path calculation is based on the following ordinary differential equation:

[0041]

[0042] in, For the perturbation vector field model, This indicates the position of the particle at time t;

[0043] Furthermore, the velocity change of each path segment is extracted, and the rate of change of momentum is calculated as follows:

[0044]

[0045] Among them, M i Let be the momentum of the particle on the i-th migration path. ρ is the velocity vector. i This represents the equivalent density of particles along this path.

[0046] The set of momentum change rates and endpoint positions along multiple paths is used as output to describe the migration trend and focusing ability of dust particles under disturbance.

[0047] By adopting the above technical solution, this invention introduces the Lagrange particle tracking algorithm into the dust migration trend prediction module and combines it with the dynamic input of the perturbation vector field model to realize the simulation of dust movement path and momentum evolution analysis at the particle level.

[0048] Based on physical mechanisms, this module directly calculates the spatial migration trajectory and velocity changes of dust under disturbance, thereby forming the particle momentum change rate. This parameter can reflect whether the particles are subject to significant external disturbances, whether there is a tendency to converge, and where deposition hotspots may form.

[0049] In particular, using the Lagrange method to model single-particle paths avoids the problem of Eulerian field methods neglecting path continuity and historical inertia, thus improving the ability to model migration trends under complex unsteady disturbances. Furthermore, the momentum change rate output by this module can not only be used for subsequent risk mapping but also has independent significance as an early warning criterion.

[0050] Therefore, the dust migration trend prediction module has higher physical accuracy and engineering adaptability, significantly improving the foresight and reliability of the pollution prediction system, and providing basic support for the identification of dust focusing trends in complex disturbance environments in industrial scenarios.

[0051] Further configuration: The risk map generation module is used to map the path trajectory and momentum change rate output by the dust migration trend prediction module to the three-dimensional region where the electrical control cabinet is located, generating a dust focusing risk map, specifically including:

[0052] Using the perturbation vector field model, the path data, and the momentum change rate as inputs, a particle passage density distribution function is established within the target space region;

[0053] By introducing a disturbance persistence parameter τ, the traffic density is accumulated over time to construct a time-varying risk map R(x, y, z, t), the expression of which is:

[0054]

[0055] Where φ(x, y, z, t′) is the weighted density of the number of path clusters passing through the spatial point per unit time, and τ is the time constant of the disturbance duration;

[0056] The graph is used to reflect the dust focusing intensity at different spatial locations at different time points, and serves as the basis for subsequent risk assessment and alarm decisions.

[0057] By adopting the above technical solution and introducing the path cluster traffic density and disturbance persistence parameter τ into the risk map generation module, spatiotemporal dynamic modeling of dust aggregation trends is achieved. Compared with the existing technology that relies on a single concentration value at a certain time point to judge pollution risk, this invention is based on Lagrange path simulation results, maps the trajectory information of particles moving in space to a traffic density function, and dynamically accumulates the aggregation trend of particles in each spatial region through time sliding window integration.

[0058] Specifically, this invention introduces the disturbance persistence parameter τ from the disturbance modeling module to perform a weighted integral on the traffic density, forming a focusing intensity map that varies over time. This allows the system to accurately reflect high-risk areas of potential pollution at any given moment and distinguish between short-term disturbances and persistent dust focusing effects. This map construction method with time memory characteristics greatly improves the stability and spatial accuracy of risk identification.

[0059] Further configuration: The risk identification and output module is used to calculate the dust accumulation risk value at the cabinet level based on the spatial relationship between the risk map and the electrical control cabinet, specifically including:

[0060] The spatial shape model of the electrical control cabinet Ω cab Mapping to the three-dimensional spatial coordinate system corresponding to the dust focusing risk map R(x, y, z, t), identify the intersection region Ω between the two. * ;

[0061] In the intersection region Ω * The risk intensity function of the internal map is spatially integrated, and combined with the distribution function κ(x, y, z) of the ventilation aggregation coefficient in the cabinet structure, the total risk value Ψ of the cabinet is calculated, and its expression is:

[0062]

[0063] Where R(x, y, z, t) represents the dust focusing risk intensity in the intersection space, and κ(x, y, z) represents the ventilation accretion weight coefficient of the electrical control cabinet at that point, which is used to quantify the sensitivity of the structure in that area to particle accumulation.

[0064] By adopting the above technical solution, and by introducing a three-dimensional spatial matching mechanism between the spatial outline of the electrical control cabinet and the risk map in the risk identification and output module, a mathematical method that can accurately locate and quantitatively calculate the risk of cabinet contamination is constructed.

[0065] This invention integrates continuous spatial functions in a risk map with the actual physical structure of the electrical control cabinet, achieving a systematic risk assessment from a "surface" rather than a "point" perspective. Specifically, the system identifies the spatial intersection region Ω* between the electrical control cabinet structure and high-risk areas in the map, and performs integral calculations on the dust focusing intensity function R(x, y, z, t) within this region. This effectively captures the potential threat posed to the entire cabinet by continuous dust focusing. Simultaneously, a ventilation structure factor function κ(x, y, z) is introduced to weight the structural adhesion susceptibility of the cabinet surface, making the calculation results closer to the cabinet's actual anti-pollution capability and overcoming the lack of abstraction in existing solutions when dealing with structural differences.

[0066] By constructing the aforementioned integral model, the system can output a quantifiable cabinet contamination risk value Ψ with clear physical meaning, which can be used for subsequent risk level classification, maintenance recommendation formulation, and intelligent scheduling. This method significantly improves the system's adaptability, interpretability, and decision-making accuracy in different industrial scenarios, achieving a crucial transformation from prediction results to a closed-loop engineering response.

[0067] Further configuration: The risk identification and output module classifies the current status of the electrical control cabinet based on the numerical range of the risk value Ψ and outputs corresponding response actions, specifically including:

[0068] If the risk value Ψ≤Ψ1, the system is considered to be in a safe state and will not trigger any intervention.

[0069] If the risk value satisfies Ψ1<Ψ≤Ψ2, it is determined to be a monitorable state, and the system records the trend and periodically refreshes the graph;

[0070] If the risk value satisfies Ψ2<Ψ≤Ψ3, it is determined to be a warning state, the system pushes a risk warning to the maintenance terminal, and suggests on-site inspection;

[0071] If the risk value Ψ > Ψ3, it is determined to be a mandatory maintenance state, and the system generates a task order with a timestamp and location number.

[0072] By adopting the above technical solution and using the risk level classification method based on the range of dust focusing risk value Ψ, the system has the ability to make graded judgments based on quantitative indicators, and can automatically match the corresponding response strategies according to different risk levels, thereby constructing a closed-loop control system that integrates prediction and identification, risk classification and strategy output.

[0073] This invention employs a multi-level risk threshold mechanism, mapping the continuous quantity Ψ to discrete safety level labels, and designs differentiated response actions (such as data refresh, early warning prompts, task order generation, and auxiliary ventilation) for different levels, which greatly improves the automation level, response flexibility, and operation and maintenance efficiency of the system in actual industrial operation scenarios.

[0074] Another object of the present invention is to provide a method for predicting external interference risks of electrical control cabinets, comprising the following steps:

[0075] S1. Collect the ambient temperature, air pressure distribution and airflow velocity vector outside the electrical control cabinet, and construct a heat source-air pressure coupled disturbance vector field model;

[0076] S2. Based on the aforementioned perturbation vector field model, the Lagrange method is used to simulate the migration path of dust particles and calculate the rate of change of momentum along the path.

[0077] S3. Using multiple migration paths and their momentum change rates as input, construct a three-dimensional time-varying dust focusing risk map;

[0078] S4. Spatial matching of the electrical control cabinet's spatial location with the risk map, calculation of the cabinet's focused risk value, and output of maintenance suggestions or response strategies based on the preset risk level.

[0079] In summary, the present invention has the following beneficial effects:

[0080] This invention utilizes a disturbance modeling module to perform multi-source fusion modeling of temperature distribution, airflow velocity, and air pressure changes in the environment surrounding the electrical control cabinet, establishing a disturbance vector field model coupled with heat source and air pressure. This model can reflect the local low-pressure disturbance effect caused by heat source distribution and structural shielding in high-temperature industrial environments, revealing the external driving force for particulate matter focusing and migration from the source, and overcoming the deficiency in existing technologies that neglect the external aerodynamic disturbance mechanism of the cabinet.

[0081] The dust migration trend prediction module uses the perturbation vector field as a boundary condition, combined with particulate matter size and density parameters, to construct a Lagrange path simulation model. This model accurately reconstructs the dynamic trajectory of dust under the influence of the perturbation field and outputs the momentum change rate of each path, thereby identifying dust migration paths with a convergence tendency. This process achieves proactive prediction of particle migration behavior, breaking through the existing passive sensing method that relies on dust concentration measurement, and enabling the identification of dust accumulation areas before pollution forms.

[0082] The risk map generation module of this invention projects multiple migration paths onto a three-dimensional spatial grid region, calculates and accumulates the particle passage density per unit time, and introduces a persistence parameter from a perturbation model to dynamically control the map evolution range, thereby constructing a dust focusing heatmap with temporal continuity. Unlike traditional single-point measurement methods, this map can not only visualize the pollution concentration area at future moments but also reflect the evolution trend of the dust focusing process, achieving a dynamic presentation of risk.

[0083] Based on this map, the risk identification and output module of this invention performs three-dimensional spatial matching between the spatial location of the electrical control cabinet and high-risk areas. Based on the dust risk intensity of the overlapping areas and the ventilation characteristic factors in the cabinet structure, it calculates the dust accumulation risk value at the cabinet level and outputs the cabinet status level and maintenance response suggestions accordingly. This enables precise maintenance and hierarchical control supported by data, and has stronger adaptability and engineering guidance value.

[0084] In summary, this invention constructs a full-chain, closed-loop pollution risk identification system from multiple dimensions, including pollution cause modeling, path evolution prediction, risk trend quantification, and equipment response recommendation. Compared to existing passive analysis methods that primarily focus on changes in dust concentration inside electrical cabinets, this invention completes migration trend assessment and risk focusing judgment before dust enters the equipment, improving the lead time, spatial resolution, and decision-making capability of detection response, and significantly enhancing the stability and operational efficiency of industrial electrical control equipment in complex environments. Attached Figure Description

[0085] Figure 1 This is a schematic diagram of the system architecture of an embodiment. Detailed Implementation

[0086] The present invention will be further described in detail below with reference to the accompanying drawings.

[0087] Example:

[0088] A system for predicting external interference risks in electrical control cabinets, such as Figure 1 As shown, including:

[0089] The disturbance modeling module is used to collect ambient temperature distribution, airflow velocity vector and air pressure change data in the area around the electrical control cabinet, and to construct a disturbance vector field model based on the data.

[0090] The dust migration trend prediction module is used to use the disturbance vector field model as a boundary condition, combined with dust particle size and density parameters, to simulate the migration momentum path of particulate matter under the action of the disturbance field, and output the path cluster and its corresponding momentum change rate.

[0091] The risk map generation module is used to calculate the dust accumulation intensity per unit area in the target three-dimensional space based on the path cluster and momentum change rate, construct a dust focusing risk map, and introduce the disturbance persistence parameter in the disturbance vector field model to control the time evolution range of the map.

[0092] The risk identification and output module is used to spatially match the spatial outline of the electrical control cabinet with the high-risk areas in the dust focusing risk map, calculate the potential dust accumulation risk value on the cabinet surface, and output the risk level of the electrical control cabinet and the corresponding maintenance suggestions based on the risk value; the maintenance suggestions are called from a preset maintenance suggestion library, and the suggestion library corresponds one-to-one with different risk levels.

[0093] The disturbance modeling module, risk map generation module, and risk identification module are deployed in edge computing nodes or industrial servers, and are connected to the monitoring system via industrial Ethernet or fieldbus.

[0094] In a preferred embodiment of the present invention, the dust focusing risk modeling and fault prediction system outside the electrical control cabinet includes a disturbance modeling module, which is used to construct a disturbance vector field model in a local area outside the electrical control cabinet, and to drive the prediction of dust migration path.

[0095] The disturbance modeling module includes the following units:

[0096] The heat source detection unit is used to acquire the location, surface temperature, and radiation influence range of the main heat sources deployed in high-temperature industrial areas, and to generate a spatial distribution function of heat source intensity based on the plant layout. This function is used to reflect the degree of thermal radiation received at different locations in space, and can be obtained using infrared temperature imaging, thermocouple arrays, or industrial temperature spectrum prediction methods.

[0097] The air pressure difference estimation unit collects static or dynamic pressure values ​​at measurement points by arranging multiple miniature air pressure sensors around the electrical control cabinet, and performs spatial interpolation processing on the collected air pressure data to calculate the three-dimensional air pressure gradient field. This pressure gradient reflects the tendency of local low-pressure convergence and is one of the driving forces of dust migration.

[0098] The airflow velocity acquisition unit employs multi-point miniature anemometers (such as hot-wire anemometers or MEMS vortex sensors) to collect airflow velocity magnitude and direction information from different sides, top, and bottom of the control cabinet. The airflow velocity information from each measuring point is then vectorized and normalized to form an airflow velocity vector field.

[0099] The vector field generation unit integrates the heat source distribution function, the pressure gradient field, and the airflow velocity vector field to construct the disturbance driving factor function. Its expression is as follows:

[0100]

[0101] Wherein, α and β are the combined weighting coefficients of the pressure gradient-dominant disturbance and the heat source-airflow coupling disturbance, respectively, satisfying α+β=1, and their values ​​are optimized and adjusted based on experimental experience and site layout.

[0102] Furthermore, to characterize the decay behavior of the disturbance over time, the time constant τ of the disturbance duration is introduced into the disturbance vector function, and a time-decaying disturbance vector field model is constructed as follows:

[0103]

[0104] In the formula, e -t / τ τ is the disturbance attenuation factor, used to describe the natural attenuation process of the influence of disturbance on dust migration over time. τ represents the effective duration of the disturbance field, which is generally in the range of 15-45 seconds, depending on the thermal inertia of the equipment and the ambient air exchange rate.

[0105] The perturbation vector field It can serve as a driving field for subsequent dust migration path simulation, providing boundary constraints for the Lagrange particle tracking model, and enabling prediction of the dynamic migration trajectory of particles after real disturbance.

[0106] The disturbance modeling process in this embodiment has good adaptability in actual deployment. It can collect the required environmental parameters through the deployed industrial sensor network, the model calculation can be completed in the edge computing node, and the disturbance field can be updated periodically to achieve dynamic tracking and prediction.

[0107] In a preferred embodiment of the present invention, the dust migration trend prediction module uses the perturbation vector field model output by the perturbation modeling module to simulate the path of particulate matter using the Lagrange particle tracking algorithm to determine whether there is a significant convergence trend under the perturbation drive.

[0108] Specifically, dust particles are treated as mass point models, with each particle possessing attributes such as initial position, particle size, and density. The system takes time t0 as the starting point, inputs the initial state of the particles, and calls the local velocity values ​​provided by the perturbation vector field model to construct the particle's motion differential equations:

[0109]

[0110] This formula states that the velocity-driving force on a particle at any time t is determined by the perturbation vector value at its current position. The system performs numerical integration on this equation to obtain the particle's continuous path throughout the entire prediction time window.

[0111] While acquiring the path, the system records the speed change values ​​along each path. And based on density ρ i Calculate the rate of change of particle momentum:

[0112]

[0113] Among them, M i Let be the momentum of the particle on the i-th migration path. ρ is the velocity vector. i This represents the equivalent density of particles along this path.

[0114] The migration paths, endpoints, and momentum change rates of multiple particles are summarized and output to form a time-series migration trend dataset, which can be used for subsequent spatial focusing risk map generation or to directly determine the location and time of possible dust accumulation areas.

[0115] The dust migration trend prediction module can be deployed in edge computing units or central control servers. It features low latency and high accuracy, and is suitable for complex, volatile, and unevenly ventilated industrial environments. It can predict the potential migration trend of dust before it actually enters the electrical control cabinet, and assist in adjusting ventilation strategies in advance or issuing maintenance warnings.

[0116] In a preferred embodiment of the present invention, the system includes a risk map generation module, which is used to construct a dust focusing risk map in three-dimensional space based on the path trajectory data output by the dust migration trend prediction module and the disturbance persistence parameters output by the disturbance modeling module.

[0117] First, the system receives the motion paths of multiple dust particles and discretizes their trajectories within a spatial grid. It then counts the number of particles passing through each grid cell per unit time, the path density, or the momentum intensity, thereby constructing a path passage density distribution function.

[0118] Considering the finite persistence of the impact of disturbances on path trends, the system introduces the disturbance persistence time constant τ from the disturbance modeling module. By applying an exponential decay integral to the traffic density at each spatial point, the focusing intensity risk function evolving over time is obtained:

[0119]

[0120] Where R(x, y, z, t) represents the dust focusing risk intensity at spatial point (x, y, z) at time t, φ(x, y, z, t′) is the traffic density at time t, and τ controls the time weight decay rate of the disturbance effect.

[0121] The final generated risk map R(x, y, z, t) is visualized and output in the form of a three-dimensional spatial heat map. The system can use this map to identify the high-risk areas where dust is most likely to accumulate in real time, forming a spatial-level pollution prediction basis.

[0122] The risk map generation module can be deployed on edge servers or industrial data centers, supporting multi-layer overlay and time evolution comparison analysis. It can also serve as a direct input for the downstream module "electrical control cabinet matching and scoring," realizing a continuous link from physical disturbance modeling to spatial risk presentation. It is a key component of the system's prediction closed loop.

[0123] In a preferred embodiment of the present invention, the risk identification and output module is used to calculate the pollution risk value of each target cabinet based on the generated dust focusing risk map and the spatial structure information of the electrical control cabinet, and to provide subsequent response strategies accordingly.

[0124] Specifically, the system first maps the structural model Ωcab of the electrical control cabinet to the same three-dimensional coordinate system as the map R(x, y, z, t), and identifies the spatial overlap region Ω* between it and the high-risk area in the map. This region represents the local spatial range where the dust migration path may eventually converge.

[0125] Subsequently, the system performs integral calculations within this intersection region, using the following risk value integration model:

[0126]

[0127] Wherein, R(x, y, z, t) is the dust focusing risk intensity function, representing the intensity of the particle focusing tendency in a unit space; κ(x, y, z) is the ventilation susceptibility parameter distribution function of the electrical control cabinet structural surface. κ(x, y, z) is preset according to the equipment structure or dynamically generated by training a model from historical dust accumulation data. It is used to reflect the sensitivity of different structural parts to dust accumulation. For example, the κ value is higher in areas such as openings, gaps, and radiators.

[0128] After the calculation is completed, the system outputs a single cabinet risk value Ψ, the magnitude of which reflects the intensity of particulate matter focusing threat faced by the electrical control cabinet under the current disturbance conditions. The system can compare the Ψ value with the preset risk level threshold to determine the cabinet status level (safe, monitorable, early warning or mandatory maintenance) and push corresponding maintenance response suggestions or activate auxiliary protection mechanisms.

[0129] In a preferred embodiment of the present invention, the risk identification and output module determines the level of each electrical control cabinet based on the risk value Ψ calculated in claim 5, and outputs a corresponding response strategy accordingly.

[0130] The system presets three threshold parameters: Ψ1, Ψ2, and Ψ3, whose meanings are as follows:

[0131] Ψ1: The upper limit of the normal value. A value below this indicates that the dust focusing intensity is relatively low and the risk is negligible.

[0132] Ψ2: It is recommended to check the threshold. If it is exceeded, maintenance personnel should be reminded to conduct on-site verification.

[0133] Ψ3: High-risk threshold; exceeding this threshold will force the system to enter the maintenance scheduling process.

[0134] The specific judgment and response logic is as follows:

[0135] Safe status (Ψ≤Ψ1): The system determines that there is currently no focus risk to the cabinet, does not perform any operations, and only archives the risk value and map snapshot in a routine manner.

[0136] Monitorable status (Ψ1<Ψ≤Ψ2): The system records the trend curve under this status, continuously tracks dust migration, and periodically regenerates the graph for updating the judgment.

[0137] Warning status (Ψ2<Ψ≤Ψ3): The system triggers a risk warning and pushes a "medium-level dust focusing warning" through the remote interface. At the same time, a work order to be confirmed is generated, and it is recommended to arrange an on-site inspection within 24 hours.

[0138] Forced maintenance status (Ψ>Ψ3): The system immediately generates an emergency maintenance task order, binds the cabinet number, timestamp and location coordinates, pushes it to the dispatch platform, and links to control the external air supply device to automatically turn on for dust blocking. If connected to the intelligent dispatch system, the cabinet can also be included in the high-priority work order queue.

[0139] In actual deployment, the threshold can be set by fitting historical data, adaptive algorithms or expert experience, or it can be based on a standardized risk level system to form an industry-wide general standard.

[0140] A method for predicting external interference risks in electrical control cabinets includes the following steps:

[0141] S1. Collect the ambient temperature, air pressure distribution and airflow velocity vector outside the electrical control cabinet, and construct a heat source-air pressure coupled disturbance vector field model;

[0142] S2. Based on the aforementioned perturbation vector field model, the Lagrange method is used to simulate the migration path of dust particles and calculate the rate of change of momentum along the path.

[0143] S3. Using multiple migration paths and their momentum change rates as input, construct a three-dimensional time-varying dust focusing risk map;

[0144] S4. Spatial matching of the electrical control cabinet's spatial location with the risk map, calculation of the cabinet's focused risk value, and output of maintenance suggestions or response strategies based on the preset risk level.

[0145] This invention constructs a full-link, closed-loop pollution risk identification system from multiple dimensions, including pollution cause modeling, path evolution prediction, risk trend quantification, and equipment response recommendation. Compared to existing passive analysis methods that primarily focus on changes in dust concentration inside electrical cabinets, this invention completes migration trend assessment and risk focusing judgment before dust enters the equipment, improving the lead time, spatial resolution, and decision-making capability of detection response, and significantly enhancing the stability and operational efficiency of industrial electrical control equipment in complex environments.

[0146] The embodiments described above do not constitute a limitation on the scope of protection of this technical solution. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the above embodiments should be included within the scope of protection of this technical solution.

Claims

1. A system for predicting external interference risks in electrical control cabinets, characterized in that, include: The disturbance modeling module is used to collect ambient temperature distribution, airflow velocity vector and air pressure change data in the area around the electrical control cabinet, and to construct a disturbance vector field model based on the data. The dust migration trend prediction module is used to use the disturbance vector field model as a boundary condition, combined with dust particle size and density parameters, to simulate the migration momentum path of particulate matter under the action of the disturbance field, and output the path cluster and its corresponding momentum change rate. The risk map generation module is used to calculate the dust accumulation intensity per unit area in the target three-dimensional space based on the path cluster and momentum change rate, construct a dust focusing risk map, and introduce the disturbance persistence parameter in the disturbance vector field model to control the time evolution range of the map. The risk identification and output module is used to spatially match the spatial outline of the electrical control cabinet with the high-risk areas in the dust focusing risk map, calculate the potential dust accumulation risk value on the cabinet surface, and output the risk level of the electrical control cabinet and the corresponding maintenance suggestions based on the risk value. The maintenance suggestions are called from a preset maintenance suggestion library, and the suggestion library corresponds one-to-one with different risk levels.

2. The system for predicting external interference risks of electrical control cabinets according to claim 1, characterized in that, The disturbance modeling module includes: The heat source detection unit is used to acquire the spatial distribution and thermal radiation parameters of high-temperature equipment, and to estimate the area affected by the heat source based on this. The air pressure difference estimation unit is used to collect air pressure data from multiple measuring points in the area surrounding the electrical control cabinet, and calculate the air pressure gradient field based on the difference between the measuring points. The airflow velocity acquisition unit is used to collect airflow velocity and direction information at different locations through multi-point miniature wind speed sensors installed around the electrical control cabinet, and generate an airflow velocity vector field. The vector field generation unit is used to construct a disturbance vector field model based on the heat source parameters, air pressure gradient field and airflow velocity vector field, which is used to describe the driving characteristics of external air disturbances in the electrical control cabinet.

3. The system for predicting external interference risks of electrical control cabinets according to claim 2, characterized in that, The vector field generation unit constructs a perturbation vector field model based on the following steps: The pressure gradient field generated by the pressure difference estimation unit, the airflow velocity vector field, and the thermal radiation distribution function output by the heat source detection unit are used as inputs. A disturbance driving factor function is constructed to characterize the degree of influence of the disturbance source on local aerodynamics, wherein: in: For the disturbance driving factor function; This represents the pressure gradient field. This represents the airflow velocity vector field. Let be the thermal radiation distribution function; α and β are the perturbation composite weighting coefficients, satisfying: α + β = 1; Using the disturbance driving factor function as the boundary input, and combining the boundary conditions and continuity constraints within the three-dimensional control region, the disturbance vector field model is solved. Its definition is: Among them, e -t / τ τ is the disturbance attenuation factor, used to describe the natural attenuation process of the disturbance vector's effect on particulate matter migration over time t; where τ is the disturbance duration time constant, reflecting the duration of the disturbance effect.

4. The external interference risk prediction system for electrical control cabinets according to claim 3, characterized in that, The dust migration trend prediction module, based on the perturbation vector field model output by the perturbation modeling module, constructs the dynamic migration trajectory of particulate matter using the Lagrange particle tracking method, specifically including: The dust particles are simplified into a mass point model, and their motion path under the drive of the perturbation field is solved by combining the particle size, density, initial spatial position and initial time. The path calculation is based on the following ordinary differential equation: in, For the perturbation vector field model, This indicates the position of the particle at time t; Furthermore, the velocity change of each path segment is extracted, and the rate of change of momentum is calculated as follows: Among them, M i Let be the momentum of the particle on the i-th migration path. ρ is the velocity vector. i This represents the equivalent density of particles along this path. The set of momentum change rates and endpoint positions along multiple paths is used as output to describe the migration trend and focusing ability of dust particles under disturbance.

5. The system for predicting external interference risks in electrical control cabinets according to claim 4, characterized in that, The risk map generation module is used to map the path trajectory and momentum change rate output by the dust migration trend prediction module to the three-dimensional area where the electrical control cabinet is located, generating a dust focusing risk map, specifically including: Using the perturbation vector field model, the path data, and the momentum change rate as inputs, a particle passage density distribution function is established within the target space region; By introducing a disturbance persistence parameter τ, the traffic density is accumulated over time to construct a time-varying risk map R(x, y, z, t), the expression of which is: Where φ(x, y, z, t′) is the weighted density of the number of path clusters passing through the spatial point per unit time, and τ is the time constant of the disturbance duration; The graph is used to reflect the dust focusing intensity at different spatial locations at different time points, and serves as the basis for subsequent risk assessment and alarm decisions.

6. The external interference risk prediction system for electrical control cabinets according to claim 5, characterized in that, The risk identification and output module is used to calculate the dust accumulation risk value at the cabinet level based on the spatial relationship between the risk map and the electrical control cabinet, specifically including: The spatial shape model of the electrical control cabinet Ω cab Mapping to the three-dimensional spatial coordinate system corresponding to the dust focusing risk map R(x, y, z, t), identify the intersection region Ω between the two. * ; In the intersection region Ω * The risk intensity function of the internal map is spatially integrated, and combined with the distribution function κ(x, y, z) of the ventilation aggregation coefficient in the cabinet structure, the total risk value Ψ of the cabinet is calculated, and its expression is: Ψ=∫ Ω * R(x,y,z,t)·κ(x,y,z)dΩ Where R(x, y, z, t) represents the dust focusing risk intensity in the intersection space, and κ(x, y, z) represents the ventilation accretion weight coefficient of the electrical control cabinet at that point, which is used to quantify the sensitivity of the structure in that area to particle accumulation.

7. A system for predicting external interference risks in electrical control cabinets according to claim 6, characterized in that, The risk identification and output module classifies the current status of the electrical control cabinet based on the numerical range of the risk value Ψ and outputs corresponding response actions, specifically including: If the risk value Ψ≤Ψ1, the system is considered to be in a safe state and will not trigger any intervention. If the risk value satisfies Ψ1<Ψ≤Ψ2, it is determined to be a monitorable state, and the system records the trend and periodically refreshes the graph; If the risk value satisfies Ψ2<Ψ≤Ψ3, it is determined to be a warning state, the system pushes a risk warning to the maintenance terminal, and suggests on-site inspection; If the risk value Ψ > Ψ3, it is determined to be a mandatory maintenance state, and the system generates a task order with a timestamp and location number.

8. A method for predicting external interference risks of electrical control cabinets, applied to the method for predicting external interference risks of electrical control cabinets as described in any one of claims 1-7, characterized in that, Includes the following steps: S1. Collect the ambient temperature, air pressure distribution and airflow velocity vector outside the electrical control cabinet, and construct a heat source-air pressure coupled disturbance vector field model; S2. Based on the aforementioned perturbation vector field model, the Lagrange method is used to simulate the migration path of dust particles and calculate the rate of change of momentum along the path. S3. Using multiple migration paths and their momentum change rates as input, construct a three-dimensional time-varying dust focusing risk map; S4. Spatial matching of the electrical control cabinet's spatial location with the risk map, calculation of the cabinet's focused risk value, and output of maintenance suggestions or response strategies based on the preset risk level.

Images