Underground power distribution room immersion simulation and first-aid repair training method and system based on Internet of Things data acquisition

Abstract

The invention relates to the technical field of power distribution room water immersion simulation, and discloses an underground power distribution room water immersion simulation and first-aid repair training method and system based on Internet of Things data acquisition, and the method comprises the steps: simulating a water level evolution matrix of an underground power distribution room in a water immersion scene through employing a shallow water diffusion wave model; calculating to obtain a water level time sequence of the power distribution equipment and a fault event occurrence probability; and the virtual reality training platform integrates the power distribution room environment, the water level evolution matrix and the fault probability of the power distribution equipment to generate an underground power distribution room first-aid repair training scene. According to the method, a shallow water diffusion wave model fusing terrain gradient, drainage capacity and rainfall trend is constructed, propagation evolution of the water level in the space-time dimension is simulated, then the fault probability of each power distribution device is evaluated, the fault probability, a water level evolution result and a power distribution room environment are integrated with a virtual reality environment, immersive training of a first-aid repair task is realized, and the training efficiency is improved. And the emergency response capability and the maintenance efficiency of first-aid repair personnel to flood situations are obviously improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of substation water immersion simulation, and particularly relates to a substation water immersion simulation and repair training method and system based on Internet of Things data acquisition. BACKGROUND

[0002] With the continuous expansion of urban power grid scale and the extensive development of underground space resources, underground substations, as important urban power infrastructure, are widely deployed in human-intensive areas such as urban transportation hubs, commercial complexes, and underground parking lots. Underground substations not only undertake the task of regional distribution and transmission of electric energy, but also play an important role in power system relay, protection and monitoring. The safe and stable operation of underground substations is directly related to the power supply reliability of the entire urban power grid and the normal production and life order of urban residents. However, since most underground substations are built in low-lying or enclosed environments, and the drainage capacity of the terrain is limited, they are prone to water immersion accidents under extreme weather conditions such as heavy rain, typhoons, and waterlogging.

[0003] Once a water immersion accident occurs, it will not only cause the insulation performance of high-voltage power equipment to deteriorate and short-circuit burnout, but also may trigger a chain of equipment failures, causing widespread power outages and even personal injuries. At the same time, rescue personnel often face many uncertainties in the water immersion site, such as unknown water levels, invisible equipment states, and unknown risk areas, which seriously affect the timeliness and safety of emergency repair.

[0004] Currently, some research has attempted to monitor substations intelligently through Internet of Things and information fusion. For example, CN114710644A discloses a power substation comprehensive monitoring system, which includes a video and access control subsystem for collecting video monitoring information and performing access control management, an environment control subsystem for collecting running environment information, a power monitoring subsystem for monitoring equipment running data, and a network communication system for transmission and dispatch. The system can realize unified collection and management of multiple information of the substation, and has certain practical value in environmental perception and comprehensive supervision.

[0005] However, most existing technologies focus on state monitoring and early warning, lack physical modeling and dynamic evolution analysis of the water immersion process, and have not yet achieved accurate prediction of the degradation of power equipment insulation performance under disaster scenarios. In addition, most current virtual training platforms use regular scripts or static models, which cannot dynamically reflect the risk evolution process of power distribution equipment under complex hydrodynamic environments, and it is also difficult to form a repair decision training system for "real combat".

[0006] Therefore, a kind of underground distribution room flooding simulation and repair training method fusing physical parameter dynamic perception, hydrodynamic evolution modeling is urgently needed, to improve the predictability of equipment state under water disaster scenario, the rationality of repair strategy and the immersion, authenticity of emergency training, and effectively enhance the efficiency of repair. SUMMARY

[0007] Therefore, the present application provides a kind of underground distribution room flooding simulation and repair training method and system based on Internet of Things data acquisition, acquires the key physical parameter data in the process of flooding, constructs the improved shallow water diffusion wave model fusing topographic information and hydrodynamic characteristics, accurately simulates the evolution process of water level with time and space, further combined with the position information of distribution equipment, extracts the water level time series of each distribution equipment, establishes the insulation state degradation model, and calculates the probability of failure of distribution equipment by fault tree, finally injects the water level evolution result and failure probability into virtual reality engine, generates immersive interactive repair training scene, realizes the training scheme of virtual-real fusion.

[0008] To achieve the above object, the underground distribution room flooding simulation and repair training method based on Internet of Things data acquisition provided by the present application comprises the following steps:

[0009] S1: sensors are laid in underground distribution room to perceive physical parameters, and physical parameter perception data of underground distribution room under flooding scenario is obtained;

[0010] S2: combined with physical parameter perception data, improved shallow water diffusion wave model is used to simulate water level evolution matrix of underground distribution room under flooding scenario;

[0011] S3: water level time series of each distribution equipment in underground distribution room is calculated by using water level evolution matrix, time sequence attenuation evolution of insulation state of distribution equipment is carried out, and the probability of failure event of each distribution equipment is generated by using fault tree reasoning method;

[0012] S4: underground distribution room scene, water level evolution matrix and the probability of failure event of each distribution equipment are integrated into virtual reality training platform, and virtual reality training platform generates underground distribution room repair training scene, and user carries out interactive repair training in underground distribution room repair training scene.

[0013] As a further improved method of the present application:

[0014] Optionally, the types of the sensors include tipping-bucket rain gauges, soil conductivity sensors, electromagnetic current meters, liquid level meters and flow meters, comprising:

[0015] A plurality of same type sensors are arranged in a fixed area of an underground power distribution room to obtain a plurality of physical parameter sensing results of the same type sensors in the fixed area, wherein the tipping bucket rain gauge is used to sense rainfall intensity, the soil conductivity sensor is used to sense soil permeability, the electromagnetic current meter and the liquid level meter are used to sense the roughness coefficient of the ground of the power distribution room, and the liquid level meter and the flow meter are used to sense the drainage capacity of the power distribution room.

[0016] Optionally, all the physical parameter sensing results of the same type sensors are fused by using an adaptive weighted fusion method, including:

[0017] The adaptive weighted fusion formula is as follows:

[0018]

[0019] Wherein, the adaptive weighted fusion formula is as follows: indicates the fusion processing result of the ith physical parameter at the rth physical parameter sensing moment, indicates the physical parameter sensing result of the nth sensor for collecting the ith physical parameter at the rth physical parameter sensing moment, R indicates the number of physical parameter sensing moments, n ∈ [1, N], and N indicates the number of the same type sensors arranged in the fixed area, indicates the adaptive weight of the nth sensor for collecting the ith physical parameter at the rth physical parameter sensing moment, and the first to fourth physical parameters are rainfall intensity, soil permeability, roughness coefficient of the ground of the power distribution room, and drainage capacity of the power distribution room in sequence;

[0020] α1, α2, α3 are weight adjustment coefficients for adjusting the weights of different factors, and are set to 0.6, 0.2 and 0.2 in sequence;

[0021] is the physical parameter sensing result is the corresponding data deviation factor for measuring the deviation degree between the physical parameter sensing result and the historical sliding average, and the data deviation factor is in the form of a normalized value;

[0022] is the physical parameter sensing result is the corresponding packet loss rate factor, reflecting the data transmission stability of the nth sensor for collecting the ith physical parameter in the past period of time, the greater the value of the packet loss rate factor, the more serious the packet loss of the nth sensor for collecting the ith physical parameter, and the lower the transmission stability, and the packet loss rate factor is in the form of a value between 0 and 1;

[0023] is the physical parameter sensing result a corresponding sensor health state factor reflecting a current health state of the n th sensor collecting the i th physical parameter, a larger value of the sensor health state factor indicating a worse current health state of the n th sensor collecting the i th physical parameter, the sensor health state factor being in a value form between 0 and 1;

[0024] fusing the results of the different physical parameters at the R physical parameter perception moments as physical parameter perception data.

[0025] Optionally, in combination with the physical parameter perception data, a modified shallow water diffusion wave model is used to simulate a water level evolution matrix of the underground power distribution room in a water immersion scenario, including:

[0026] a three-dimensional laser scanning method is used to obtain a scene point cloud of the underground power distribution room, and a digital elevation model is extracted from the scene point cloud;

[0027] in combination with the physical parameter perception data and the digital elevation model, a modified shallow water diffusion wave model is constructed:

[0028]

[0029]

[0030] wherein, represents a water depth of a g th ground coordinate ((x g ,y g ) in the underground power distribution room at an r th physical parameter perception moment, Δ represents a time difference between adjacent physical parameter perception moments, represents a global water distribution item of the g th ground coordinate (x g ,y g ) at the r th physical parameter perception moment, G represents a number of ground coordinates of the underground power distribution room, z * (x g ,y g ) represents a height at the ground coordinate (x g ,y g ), Ω * (x g ,y g ) represents a set of adjacent ground coordinates in a region with a radius of 1 meter centered at the ground coordinate ((x g ,y g ), represents a water distribution weight based on a height difference, represents a preset maximum height, and the is set to 0.5 meters, represents a water diffusion item of the g th ground coordinate (x g ,y g ) at the r th physical parameter perception moment;

[0031] The water allocation item is the water allocation value of surface precipitation to the ground coordinates in the underground distribution room, which is calculated based on rainfall intensity, soil permeability and unit drainage of the distribution room at unit coordinates. is the unit water discharge of the underground distribution room at the rth physical parameter sensing moment;

[0032] The water diffusion term is the water distribution value of the water depth of the ground coordinate in the underground power distribution room to the adjacent ground coordinate;

[0033] S represents the ground area of ​​the underground distribution room;

[0034] These are the fusion results of rainfall intensity, soil permeability, distribution room ground roughness coefficient, and distribution room drainage capacity in the physical parameter perception data at the rth physical parameter perception moment;

[0035] Represents the set of neighboring ground coordinates Ω * (x g ,y g ) in the water depth of the adjacent ground coordinates The amount of diffusion;

[0036] The water depths at different ground coordinates at different physical parameter sensing moments are taken as the water level evolution matrix. The water level evolution matrix is ​​in the form of a matrix with R rows and G columns. The rth row and gth column in the water level evolution matrix is ​​the gth ground coordinate (x g ,y g ) Water depth at the rth physical parameter sensing moment

[0037] Optionally, the water level evolution matrix is ​​used to calculate a water level time series for each power distribution device in the underground power distribution room, and the insulation state of the power distribution device is subjected to time-series attenuation evolution, including:

[0038] Obtain the two-dimensional ground position coordinates of each distribution device in the underground distribution room, and extract the water depths at the R physical parameter sensing moments corresponding to the two-dimensional ground position coordinates from the water level evolution matrix as the water level time series of the distribution device;

[0039] The water level time series is used to calculate the insulation state of the power distribution equipment after the time series attenuation evolution at different physical parameter sensing moments.

[0040] Optionally, combining the water level time series and the time series decay evolution results of the insulation state, a fault tree reasoning method is used to generate the probability of a fault event occurring in each power distribution device, including:

[0041] The time sequence attenuation evolution results of the water level change rate and the insulation state of the power distribution equipment are acquired as nodes in a fault tree, and a fault Boolean expression of the power distribution equipment is constructed, when the water level change rate is higher than a preset water level threshold and the insulation state is lower than a preset insulation state threshold, the fault Boolean expression of the power distribution equipment outputs 1, indicating that the power distribution equipment is prone to a fault event in a short time, and the time sequence attenuation evolution results of the water level change rate and the insulation state of the power distribution equipment are normalized, weighted and subjected to a logistic regression, to generate a probability of a fault event of the power distribution equipment.

[0042] Optionally, the underground power distribution room scene, the water level evolution matrix, the probability of a fault event of each power distribution equipment and the repair priority are integrated into a virtual reality training platform, and the virtual reality training platform generates an underground power distribution room repair training scene, including:

[0043] Based on the underground power distribution room scene, an underground power distribution room structure model is generated, the underground power distribution room scene including the positions of the power distribution equipment and a scene point cloud of the underground power distribution room acquired by a three-dimensional laser scanning method;

[0044] The water level evolution matrix is converted into a water level change animation by using a VR engine, the water level change animation including a water surface rising animation in the underground power distribution room and a water flow rising sound;

[0045] A fault scene after a fault event of each power distribution equipment is generated, including special effect animations of smoke and electric arc;

[0046] The underground power distribution room structure model, the water level change animation, the probability of a fault event of each power distribution equipment and the fault scene are integrated into a virtual reality training platform, and the virtual reality training platform generates an underground power distribution room repair training scene.

[0047] To solve the above problems, the present application provides an underground power distribution room flooding simulation and repair training system based on Internet of Things data acquisition, to realize any one of the foregoing underground power distribution room flooding simulation and repair training methods based on Internet of Things data acquisition, the underground power distribution room flooding simulation and repair training system based on Internet of Things data acquisition comprising a virtual reality training platform and a data acquisition device:

[0048] The data acquisition device is used to arrange sensors in the underground power distribution room to sense physical parameters, to obtain physical parameter sensing data of the underground power distribution room in a flooding scene, to simulate a water level evolution matrix of the underground power distribution room in the flooding scene by using an improved shallow water diffusion wave model in combination with the physical parameter sensing data, to calculate a water level time sequence of each power distribution equipment in the underground power distribution room by using the water level evolution matrix, to perform time sequence attenuation evolution on the insulation state of the power distribution equipment, and to generate a probability of a fault event of each power distribution equipment by using a fault tree reasoning method;

[0049] The virtual reality training platform is used for obtaining an underground power distribution room scene, a water level evolution matrix and a probability of a fault event of each power distribution device, and generating an underground power distribution room repair training scene.

[0050] To solve the above problems, the present application provides an electronic device, which comprises:

[0051] a memory, which stores at least one instruction;

[0052] a communication interface, which realizes communication of the electronic device; and

[0053] a processor, which executes the instruction stored in the memory to realize the underground power distribution room water immersion simulation and repair training method based on Internet of Things data collection.

[0054] To solve the above problems, the present application further provides a computer readable storage medium, which stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to realize the underground power distribution room water immersion simulation and repair training method based on Internet of Things data collection.

[0055] Compared with the prior art, the present application provides an underground power distribution room water immersion simulation and repair training method and system based on Internet of Things data collection, which has the following beneficial effects:

[0056] Firstly, in view of the problems of different sensing device accuracies and unstable transmission, a dynamic weighted fusion mechanism based on sensor state is adopted, different weights are given to each sensor data for similar physical parameters by comprehensively considering multiple dimensions such as numerical deviation, data transmission efficiency and residual power, and through multi-dimensional quality factor calculation, the data contribution is corrected in real time, the influence of high noise or performance degradation sensors is suppressed, and the reliability and robustness of the overall sensing result are enhanced. This mechanism not only realizes effective fusion of multi-source heterogeneous data, but also improves the balance and accuracy of spatial data distribution, and provides high adaptability and high engineering value sensing support for water level sensing and intelligent monitoring in the complex environment of underground power distribution rooms.

[0057] Meanwhile, the application improves the diffusive wave model, the improved shallow water diffusive wave model faces the risk scenario that the underground power distribution room is prone to water accumulation and equipment immersion under extreme weather conditions such as heavy rain and large flow attack, and proposes a water depth simulation method combining regional overall water quantity control and local water dynamic diffusion mechanism. Unlike the traditional model which highly depends on the distribution of local rainfall and drainage, the model dynamically maps the global time series information such as overall rainfall, soil permeability and drainage capacity to the local spatial unit by constructing a water quantity distribution weight function, effectively solving the problems of high-density data acquisition difficulty and high deployment cost. The diffusion term introduces a nonlinear water potential gradient and elevation difference driving mechanism, and considers the influence of frictional dissipation, so that the model has stronger physical consistency and simulation accuracy in simulating underground structures with complex terrain, steps, slopes or depressions, and significantly improves the spatial restoration ability of the water propagation path and water level change distribution. BRIEF DESCRIPTION OF DRAWINGS

[0058] Figure 1 A flowchart of a water immersion simulation and repair training method for an underground power distribution room based on Internet of Things data acquisition is provided for an embodiment of the application.

[0059] Figure 2 A data acquisition flowchart for an underground power distribution room based on Internet of Things data acquisition is provided for an embodiment of the application.

[0060] The implementation, functional features and advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0061] It should be understood that the specific embodiments described herein are only used to explain the application and not to limit the application.

[0062] The application embodiment provides a water immersion simulation and repair training method for an underground power distribution room based on Internet of Things data acquisition. The execution subject of the water immersion simulation and repair training method for the underground power distribution room based on Internet of Things data acquisition includes but is not limited to at least one of the electronic devices capable of being configured to execute the method provided by the application, such as a server, a terminal and the like. In other words, the water immersion simulation and repair training method for the underground power distribution room based on Internet of Things data acquisition can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0063] REFERENCE Figure 1 Embodiment 1 of the application is:

[0064] A water immersion simulation and repair training method for an underground power distribution room based on Internet of Things data acquisition includes the following steps:

[0065] S1: A sensor is arranged in the underground power distribution room to sense physical parameters and obtain physical parameter sensing data of the underground power distribution room in a water immersion scenario.

[0066] The types of the sensor include a tipping bucket rain gauge, a soil conductivity sensor, an electromagnetic current meter, a liquid level meter, and a flow meter, including:

[0067] A plurality of sensors of the same type are arranged in a fixed area of the underground power distribution room to obtain a plurality of physical parameter sensing results of the sensors of the same type in the fixed area, the tipping bucket rain gauge is used to sense rainfall intensity, the soil conductivity sensor is used to sense soil permeability, the electromagnetic current meter and the liquid level meter are used to sense a roughness coefficient of the ground of the power distribution room, and the liquid level meter and the flow meter are used to sense drainage capacity of the power distribution room.

[0068] Specifically, the tipping bucket rain gauge is arranged in a surface area above the underground power distribution room, the soil conductivity sensor is arranged in a soil layer area 0.2-1 meters below the surface area, the water depth and the water speed of the ground of the underground power distribution room are calculated by using the electromagnetic current meter and the liquid level meter, the Manning coefficient is inversely calculated in combination with the slope of the ground of the power distribution room as the roughness coefficient of the ground of the power distribution room, and the liquid level meter and the flow meter are arranged in a drainage outlet area of the underground power distribution room.

[0069] As an embodiment of the present application, the tipping bucket rain gauge represents a fixed water volume each time the bucket tips, the rainfall intensity is calculated by the number of tipping times per unit time, the flow speed of the drainage outlet area is calculated by using the flow meter, and the drainage capacity of the power distribution room is estimated in combination with the cross-sectional area of the drainage outlet.

[0070] Specifically, each sensor is integrated with a LoRa wireless communication module, accesses a gateway node through a star-shaped networking structure, and uploads to a server through 4G / NB-IoT for adaptive weighted fusion and generation of a water level evolution matrix, a probability of failure of each power distribution device, and a repair priority.

[0071] An adaptive weighted fusion method is used to fuse all physical parameter sensing results of the sensors of the same type, including:

[0072] The adaptive weighted fusion formula is:

[0073]

[0074] wherein, represents a fusion processing result of the ith physical parameter at the rth physical parameter sensing moment, represents a physical parameter sensing result of the nth sensor for collecting the ith physical parameter at the rth physical parameter sensing moment, R represents the number of physical parameter sensing moments, n∈[1, N], and N represents the number of sensors of the same type arranged in the fixed area. represents the adaptive weight of the nth sensor used to collect the i-th physical parameter at the time of sensing the r-th physical parameter. The first to fourth physical parameters are rainfall intensity, soil permeability, distribution room ground roughness coefficient, and distribution room drainage capacity, respectively.

[0075] α1, α2, and α3 are weight adjustment coefficients used to adjust the weights of different factors. α1, α2, and α3 are set to 0.6, 0.2, and 0.2 respectively;

[0076] Perception results for physical parameters The corresponding data deviation factor is used to measure the physical parameter perception results The degree of deviation from the historical sliding mean. The data deviation factor is a normalized numerical value. Specifically, the calculation formula of the data deviation factor is:

[0077]

[0078] in, Representation sequence The mean of Representation sequence The standard deviation of ,∈ represents the micro-control coefficient, and ∈ is set to 0.001;

[0079] Perception results for physical parameters The corresponding packet loss rate factor reflects the data upload stability of the nth sensor collecting the i-th physical parameter over the past period of time. A larger value of the packet loss rate factor indicates more severe packet loss and lower transmission stability for the nth sensor collecting the i-th physical parameter. The packet loss rate factor is a numerical value between 0 and 1. Specifically, the packet loss rate factor is calculated as follows:

[0080]

[0081] in, represents the number of data frames transmitted by the nth sensor collecting the i-th physical parameter from the rLth physical parameter sensing moment to the rth physical parameter sensing moment, represents the number of data frames sent by the nth sensor collecting the ith physical parameter from the rLth physical parameter sensing moment to the rth physical parameter sensing moment, where L represents the preset time period length and is set to 5;

[0082] Perception results for physical parameters A corresponding sensor health state factor reflects the current health state of the nth sensor collecting the ith physical parameter, the greater the value of the sensor health state factor, the worse the current health state of the nth sensor collecting the ith physical parameter, and the sensor health state factor is in the form of a value between 0 and 1; specifically, the calculation formula of the sensor health state factor is:

[0083]

[0084] Wherein, represents the nominal electric quantity of the nth sensor collecting the ith physical parameter, represents the electric quantity of the nth sensor collecting the ith physical parameter at the rth physical parameter sensing moment;

[0085] The fusion results of the different physical parameters at the R physical parameter sensing moments are taken as physical parameter sensing data.

[0086] As Figure 2 shown in a kind of underground power distribution room data acquisition flow chart based on Internet of Things data acquisition, by deploying multiple sensors in underground power distribution room, the perceived data is transmitted to gateway node and uploaded to data server, to realize underground power distribution room data acquisition and monitoring based on Internet of Things data acquisition, simulation operation is carried out using data server, underground power distribution room scene, water level evolution matrix, probability of failure of each power distribution equipment and repair priority are integrated into virtual reality training platform, and virtual reality training platform generates underground power distribution room repair training scene.

[0087] Specifically, in a complex environment with redundant sensing data, different accuracy and large sensor performance difference, by dynamically weighting the same physical parameters of different types of sensors, fully fusing multi-sensor heterogeneous information, and real-time multi-angle evaluation of the state of the sensor, including deviation control angle, transmission efficiency angle and residual electric quantity angle, the weight of the physical parameter sensing data of the sensor in poor state is reduced, the accuracy of the fusion data is improved, the fusion result is ensured not to rely too much on the redundant data of a certain area, the overall spatial information balance is improved, the intelligent sensing quality and practical value of the underground power distribution room environment are greatly improved, and good engineering adaptability and promotion potential are possessed.

[0088] S2: combining physical parameter sensing data, an improved shallow water diffusion wave model is used to simulate the water level evolution matrix of underground power distribution room in the flooding scenario.

[0089] Combining the physical parameter sensing data, an improved shallow water diffusion wave model is used to simulate the water level evolution matrix of underground power distribution room in the flooding scenario, including:

[0090] The scene point cloud of the underground power distribution room is acquired by using a three-dimensional laser scanning method, and a digital elevation model is extracted from the scene point cloud. Specifically, the scene point cloud is three-dimensional coordinate data, and the extraction method of the digital elevation model is:

[0091]

[0092] wherein, {z * (x g ,y g )|g∈[1,G]},(x g ,y g ) represents the gth ground coordinate of the underground power distribution room, G represents the number of ground coordinates of the underground power distribution room, z * (x g ,y g ) represents the height at the ground coordinate (x g ,y g ), Ω((x g ,y g ) represents the ground coordinate set of the scene point cloud in the area with a radius of 1 meter centered at the ground coordinate (x g ,y g ), ((x ′ ,y ′ ,z ′ ) represents the scene point cloud, (x ′ ,y ′ ) represents any ground coordinate in the ground coordinate set Ω(x g ,y g ), represents the lowest scene point cloud height selected from the scene point cloud in the area with a radius of 1 meter centered at the ground coordinate (x g ,y g );

[0093] An improved shallow water diffusion wave model is constructed by combining physical parameter perception data and a digital elevation model:

[0094]

[0095]

[0096] wherein, represents the water depth of the gth ground coordinate ((x g ,y g ) of the underground power distribution room at the rth physical parameter perception moment, Δ represents the time difference between adjacent physical parameter perception moments, represents the gth ground coordinate (x g ,y g) is a global water allocation item at the rth physical parameter sensing moment, G represents the number of ground coordinates of the underground power distribution room, z * (x g ,y g ) represents the height at the ground coordinate (x g ,y g ), Ω * (x g ,y g ) represents a set of adjacent ground coordinates in a region with a radius of 1 meter centered at the ground coordinate ((x g ,y g ), represents a water allocation weight based on the height difference, represents a preset maximum height, set to 0.5 meters, represents a water diffusion item of the gth ground coordinate (x g ,y g ) at the rth physical parameter sensing moment;

[0097] The water allocation item is a water allocation value of ground coordinates in the underground power distribution room by surface precipitation, calculated by rainfall intensity, soil permeability and unit drainage capacity of the power distribution room per unit coordinate, is the unit drainage capacity of the underground power distribution room at the rth physical parameter sensing moment, representing the contribution of rainfall intensity, soil permeability and unit drainage capacity of the power distribution room per unit coordinate to the water depth of the ground coordinate;

[0098] The water diffusion item is a water allocation value of the water depth of the ground coordinate to the adjacent ground coordinates in the underground power distribution room, and is optimized by using the ground roughness coefficient of the power distribution room, representing the contribution of the water depth of the adjacent ground coordinates to the water depth of the ground coordinate;

[0099] S represents the ground area of the underground power distribution room;

[0100] In turn, the fusion results of rainfall intensity, soil permeability, ground roughness coefficient of the power distribution room and drainage capacity of the power distribution room at the rth physical parameter sensing moment in the physical parameter sensing data;

[0101] represents the diffusion amount of the water depth of the adjacent ground coordinates in the set of adjacent ground coordinates Ω * (x g ,y g ) to ;

[0102] Specifically, if is positive, it represents the ground coordinate ((x g ,y g)’s neighboring ground coordinates move to the ground coordinate (x g ,y g ) Diffusion water volume, if If it is a negative value, it means the ground coordinate ((x g ,y g ) diffuses water volume to adjacent ground coordinates at the rth physical parameter sensing moment;

[0103] The water depths at different ground coordinates at different physical parameter sensing moments are taken as the water level evolution matrix. The water level evolution matrix is ​​in the form of a matrix with R rows and G columns. The rth row and gth column in the water level evolution matrix is ​​the gth ground coordinate (x g ,y g ) Water depth at the rth physical parameter sensing moment The horizontal direction in the water level evolution matrix represents the temporal variation of the water depth in the ground coordinate, and the vertical direction represents the spatial variation of the water depth in the ground coordinate.

[0104] Specifically, (x, y) represents the set of neighboring ground coordinates Ω * (x g ,y g ) in the adjacent ground coordinates, z * ((x,y) represents the height at ((x,y), Indicates the water depth of the adjacent ground coordinate (x, y) at the rth physical parameter sensing moment, dis((x, y), (x g ,y g )) represents the adjacent ground coordinates (x,y) and (x g ,y g ), Indicates the initial water depth, set

[0105] As an embodiment of the present invention, by adjusting rainfall intensity, soil permeability, and drainage capacity of the distribution room, the improved shallow water diffusion wave model is used to simulate and generate a water level evolution matrix for different underground distribution room flooding conditions;

[0106] In particular, the improved shallow water diffusion wave model is aimed at the problems of water accumulation and equipment immersion in underground power distribution rooms under extreme weather conditions such as heavy rain, large flow attack, etc. The model combines regional total quantity driving and local water dynamic diffusion mechanism to estimate water depth. In detail, in the actual application scene where only overall time sequence information such as rainfall, soil permeability, drainage capacity, etc. is available and local distribution data are lacking, the water quantity distribution weight is introduced to realize dynamic mapping of global water quantity to local coordinates, solve the problem of strong dependence of traditional diffusion wave model on local rainfall input and high data demand, effectively reduce the layout cost and modeling threshold, and make the water quantity diffusion item enter the nonlinear coupling diffusion mechanism, which conforms to the real water potential driving and friction dissipation law. Compared with the model considering only the water depth difference in the traditional way, the improved model can better reflect the direct control of terrain height on the flow direction and intensity of water, significantly improve the spatial distribution accuracy of water immersion simulation, and is especially suitable for platform structure scenes with local depressions, steps and height differences in underground space.

[0107] S3: Calculate the water level time sequence of each power distribution equipment in the underground power distribution room by using the water level evolution matrix, perform time sequence attenuation evolution on the insulation state of the power distribution equipment, and generate the probability of failure event of each power distribution equipment by using fault tree reasoning.

[0108] Calculate the water level time sequence of each power distribution equipment in the underground power distribution room by using the water level evolution matrix, perform time sequence attenuation evolution on the insulation state of the power distribution equipment, including:

[0109] Obtain the two-dimensional ground position coordinates of each power distribution equipment in the underground power distribution room, and extract the water depth of the R physical parameter sensing time corresponding to the two-dimensional ground position coordinates from the water level evolution matrix as the water level time sequence of the power distribution equipment;

[0110] Calculate the insulation state of the power distribution equipment after time sequence attenuation evolution at different physical parameter sensing time by using the water level time sequence. In particular, the insulation state of the power distribution equipment c after time sequence attenuation evolution at the r+1 physical parameter sensing time is:

[0111]

[0112] Wherein, f r+1 (c) represents the insulation state of the power distribution equipment c at the r+1 physical parameter sensing time, Label((c) represents the device type sensitive coefficient corresponding to the power distribution equipment c, which characterizes the vulnerability of the power distribution equipment to water erosion, is set according to the type of the power distribution equipment, and the range of the device type sensitive coefficient is between 0 and 1. The higher the device type sensitive coefficient, the easier the power distribution equipment is to fail after being eroded by water, represents the water depth of the position of the power distribution equipment c at the r physical parameter sensing time, hec represents the installation height of the power distribution equipment c, represents a water level erosion function, Δ represents a time difference between adjacent physical parameter sensing moments, f0(c) is an initial insulation state of the power distribution equipment c, he represents a preset installation height threshold, and he is set to 0.3 meters.

[0113] In combination with the water level time sequence and the time sequence attenuation evolution result of the insulation state, a fault tree reasoning manner is used to generate a probability of a fault event of each power distribution equipment, including:

[0114] The water level change rate of the power distribution equipment and the time sequence attenuation evolution result of the insulation state are acquired as nodes in the fault tree, and a fault Boolean expression of the power distribution equipment is constructed. When the water level change rate is higher than a preset water level threshold and the insulation state is lower than a preset insulation state threshold, the fault Boolean expression of the power distribution equipment outputs 1, indicating that the power distribution equipment is prone to a fault event in a short time. The water level change rate of the power distribution equipment and the time sequence attenuation evolution result of the insulation state are normalized and weighted and subjected to a logistic regression to generate a probability of a fault event of the power distribution equipment. The logistic regression uses a Sigmoid function. As an embodiment of the present application, if the fault Boolean expression output is not 1, the probability of a fault event is set to 0.

[0115] S4: integrating the underground power distribution room scene, the water level evolution matrix and the probability of a fault event of each power distribution equipment into a virtual reality training platform, and the virtual reality training platform generating an underground power distribution room repair training scene, and a user performing interactive repair training in the underground power distribution room repair training scene.

[0116] The underground power distribution room scene, the water level evolution matrix, the probability of a fault event of each power distribution equipment and the repair priority are integrated into a virtual reality training platform, and the virtual reality training platform generates an underground power distribution room repair training scene, including:

[0117] Based on the underground power distribution room scene, an underground power distribution room structure model is generated, and the underground power distribution room scene includes the positions of the power distribution equipment and a scene point cloud of the underground power distribution room acquired by using a three-dimensional laser scanning manner.

[0118] The water level evolution matrix is converted into a water level change animation by using a VR engine, and the water level change animation includes a water surface rising animation in the underground power distribution room and a water flow rising sound. As an embodiment of the present application, the VR engine is Unity3D.

[0119] A fault scene after a fault event of each power distribution equipment is generated, including special effect animations of smoke and electric arc.

[0120] The underground power distribution room structure model, the water level change animation, the probability of failure event of each power distribution equipment, and the fault scene are integrated into a virtual reality training platform, and the virtual reality training platform generates an underground power distribution room repair training scene. Specifically, the underground power distribution room repair training scene generates a training environment scene based on the underground power distribution room structure model, generates a water level dynamic change scene based on the water level change animation, dynamically adjusts the power distribution equipment that fails based on the probability of failure event of each power distribution equipment, and generates a fault scene.

[0121] Embodiment 2

[0122] The user interaction training module of the underground power distribution room repair training scene includes a virtual patrol task, a fault positioning challenge, a dynamic training score, a power distribution equipment reset and replacement task, the virtual patrol task is that a user simulates a moving route through a VR handle, identifies a power distribution equipment flooded by water in a flooded scene, completes a patrol task, the fault positioning challenge is to quickly label a power distribution equipment that may fail and submit a repair path planning suggestion, the dynamic training score is that a user performs a repair training through a VR device, and scoring feedback is given according to whether a repair path passes through a high-risk area, a repair operation accuracy rate, etc., and the power distribution equipment reset and replacement task is that a user operates a virtual tool to perform switching off, drainage pipe layout, equipment replacement, and other interactive exercises.

[0123] Embodiment 3

[0124] An underground power distribution room flooding simulation and repair training system based on Internet of Things data acquisition is used to implement the underground power distribution room flooding simulation and repair training method based on Internet of Things data acquisition of the foregoing embodiments, and the system includes a virtual reality training platform and a data acquisition device.

[0125] The data acquisition device is used to lay sensors in an underground power distribution room to perform physical parameter sensing, obtain physical parameter sensing data of the underground power distribution room in a flooded scene, use an improved shallow water diffusion wave model to simulate a water level evolution matrix of the underground power distribution room in the flooded scene in combination with the physical parameter sensing data, use the water level evolution matrix to calculate a water level time sequence of each power distribution equipment in the underground power distribution room, perform time sequence attenuation evolution on an insulation state of the power distribution equipment, and use a fault tree reasoning method to generate a probability of failure event of each power distribution equipment.

[0126] The virtual reality training platform is used to obtain an underground power distribution room scene, a water level evolution matrix, and a probability of failure event of each power distribution equipment, and generate an underground power distribution room repair training scene.

[0127] It should be understood that the embodiments are only for illustration, and the scope of the patent application is not limited by the structure.

[0128] It should be noted that the above-mentioned embodiment serial numbers of the present application are only for description, not representing the advantages and disadvantages of the embodiments. Also, the terms "comprising", "containing" or any other variants thereof in this document are intended to cover the non-exclusive inclusion, so that the process, device, article or method including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, device, article or method. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0129] Through the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and necessary general hardware platforms, of course, they can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a plurality of instructions for making a terminal device (which can be a mobile phone, computer, server, or network device, etc.) execute the methods described in various embodiments of the present application.

[0130] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent flow transformation made by using the content of the present application specification and drawings, or directly or indirectly applied to other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for underground power distribution room flooding simulation and emergency repair training based on Internet of Things data collection, characterized in that: The method comprises: S1: Sensors are deployed in the underground power distribution room to sense physical parameters and obtain physical parameter sensing data of the underground power distribution room under flooding scenarios. The types of physical parameters include rainfall intensity, soil permeability, distribution room ground roughness coefficient and distribution room drainage capacity; S2: Combined with physical parameter perception data, an improved shallow water diffusion wave model is used to simulate the water level evolution matrix of the underground distribution room under flooding scenarios. The water level evolution matrix is ​​the water level values ​​at different locations in the underground distribution room that evolve over time. S3: Use the water level evolution matrix to calculate the water level time series of each distribution device in the underground distribution room, perform time-series decay evolution on the insulation state of the distribution equipment, and use fault tree reasoning to generate the probability of a failure event for each distribution device; S4: Integrate the underground distribution room scenario, water level evolution matrix, and the probability of failure events for each distribution equipment into the virtual reality training platform. The virtual reality training platform generates an underground distribution room emergency repair training scenario, and users conduct interactive emergency repair training in the underground distribution room emergency repair training scenario.

2. The underground power distribution room flooding simulation and emergency repair training method based on Internet of Things data collection according to claim 1 is characterized in that: The types of sensors include tipping bucket rain gauges, soil conductivity sensors, electromagnetic flow meters, liquid level meters, and flow meters, including: Multiple sensors of the same type are deployed in a fixed area of ​​the underground distribution room to obtain multiple physical parameter perception results of the same type of sensors in the fixed area. The tipping bucket rain gauge is used to sense rainfall intensity, the soil conductivity sensor is used to sense soil permeability, the electromagnetic flow meter and the liquid level meter are used to sense the ground roughness coefficient of the distribution room, and the liquid level meter and flow meter are used to sense the drainage capacity of the distribution room.

3. The underground power distribution room flooding simulation and emergency repair training method based on Internet of Things data collection according to claim 2 is characterized in that: Adaptive weighted fusion is used to fuse all the physical parameter perception results of sensors of the same type, including: The adaptive weighted fusion formula is: in, represents the fusion processing result of the i-th physical parameter at the r-th physical parameter sensing moment, represents the physical parameter sensing result of the nth sensor used to collect the i-th physical parameter at the r-th physical parameter sensing moment, R represents the number of physical parameter sensing moments, n∈[1,N], N represents the number of sensors of the same type deployed in a fixed area, represents the adaptive weight of the nth sensor used to collect the i-th physical parameter at the time of sensing the r-th physical parameter. The first to fourth physical parameters are rainfall intensity, soil permeability, distribution room ground roughness coefficient, and distribution room drainage capacity, respectively. α1, α2, and α3 are weight adjustment coefficients used to adjust the weights of different factors. α1, α2, and α3 are set to 0.6, 0.2, and 0.2 respectively; Perception results for physical parameters The corresponding data deviation factor is used to measure the physical parameter perception results The degree of deviation from the historical sliding mean, where the data deviation factor is a normalized numerical value; Perception results for physical parameters The corresponding packet loss rate factor reflects the data upload stability of the nth sensor collecting the i-th physical parameter over the past period of time. A larger value of the packet loss rate factor indicates more severe packet loss and lower transmission stability for the nth sensor collecting the i-th physical parameter. The packet loss rate factor is a numerical value between 0 and 1. Perception results for physical parameters The corresponding sensor health factor reflects the current health status of the nth sensor collecting the i-th physical parameter. A larger value of the sensor health factor indicates a worse current health status of the nth sensor collecting the i-th physical parameter. The sensor health factor is a numerical value between 0 and 1. The fusion results of the different physical parameters at the R physical parameter perception moments are used as physical parameter perception data.

4. The underground power distribution room flooding simulation and emergency repair training method based on Internet of Things data collection according to claim 3 is characterized in that: Combined with the physical parameter sensing data, an improved shallow water diffusion wave model is used to simulate the water level evolution matrix of the underground distribution room under flooding scenarios, including: Use 3D laser scanning to obtain the scene point cloud of the underground distribution room, and extract the digital elevation model from the scene point cloud; Combining physical parameter perception data and digital elevation models, an improved shallow water diffusion wave model is constructed: in, Indicates the g-th ground coordinate ((x g ,y g ) is the water depth at the rth physical parameter sensing moment, Δ represents the time difference between adjacent physical parameter sensing moments, Indicates the g-th ground coordinate (x g ,y g ) is the global water allocation item at the rth physical parameter sensing moment, G represents the ground coordinate number of the underground distribution room, z * (x g ,y g ) represents the ground coordinate (x g ,y g ) at the height, Ω * (x g ,y g ) represents the ground coordinate ((x g ,y g ) as the center and a radius of 1 meter in the area of ​​the adjacent ground coordinates, represents the water distribution weight based on height difference, Indicates the preset maximum height, set 0.5 meters, Indicates the g-th ground coordinate (x g ,y g ) is the water diffusion term at the rth physical parameter sensing moment; The water allocation item is the water allocation value of surface precipitation to the ground coordinates in the underground distribution room, which is calculated based on rainfall intensity, soil permeability and unit drainage of the distribution room at unit coordinates. is the unit water discharge of the underground distribution room at the rth physical parameter sensing moment; The water diffusion term is the water distribution value of the water depth of the ground coordinate in the underground power distribution room to the adjacent ground coordinate; S represents the ground area of ​​the underground distribution room; These are the fusion results of rainfall intensity, soil permeability, distribution room ground roughness coefficient, and distribution room drainage capacity in the physical parameter perception data at the rth physical parameter perception moment; Represents the set of neighboring ground coordinates Ω * (x g ,y g ) in the water depth of the adjacent ground coordinates The amount of diffusion; The water depths at different ground coordinates at different physical parameter sensing moments are taken as the water level evolution matrix. The water level evolution matrix is ​​in the form of a matrix with R rows and G columns. The rth row and gth column in the water level evolution matrix is ​​the gth ground coordinate (x g ,y g ) Water depth at the rth physical parameter sensing moment 5. The underground power distribution room flooding simulation and emergency repair training method based on Internet of Things data collection according to claim 4 is characterized in that: The water level evolution matrix is ​​used to calculate the water level time series of each distribution equipment in the underground distribution room, and the insulation state of the distribution equipment is subjected to time-series decay evolution, including: Obtain the two-dimensional ground position coordinates of each distribution device in the underground distribution room, and extract the water depths at the R physical parameter sensing moments corresponding to the two-dimensional ground position coordinates from the water level evolution matrix as the water level time series of the distribution device; The water level time series is used to calculate the insulation state of the power distribution equipment after the time series attenuation evolution at different physical parameter sensing moments.

6. The underground power distribution room flooding simulation and emergency repair training method based on Internet of Things data collection according to claim 5 is characterized in that: Combining the water level time series and the insulation state decay evolution results, the fault tree reasoning method is used to generate the probability of a fault event for each distribution equipment, including: The water level change rate and insulation state time-series attenuation evolution results of the distribution equipment are obtained as nodes in the fault tree, and a fault Boolean expression for the distribution equipment is constructed. When the water level change rate is higher than the preset water level threshold and the insulation state is lower than the preset insulation state threshold, the fault Boolean expression output of the distribution equipment is 1, indicating that the distribution equipment is prone to failure events in a short period of time. The water level change rate and insulation state time-series attenuation evolution results of the distribution equipment are normalized, weighted, and subjected to logistic regression to generate the probability of a failure event occurring in the distribution equipment.

7. The underground power distribution room flooding simulation and emergency repair training method based on Internet of Things data collection according to claim 1, characterized in that: The underground distribution room scenario, water level evolution matrix, probability of failure of each distribution equipment, and emergency repair priority are integrated into the virtual reality training platform. The virtual reality training platform generates an underground distribution room emergency repair training scenario, including: Generate a structural model of the underground distribution room based on the underground distribution room scenario, wherein the underground distribution room scenario includes the location of the distribution equipment and a scene point cloud of the underground distribution room obtained by 3D laser scanning; Using a VR engine to convert the water level evolution matrix into a water level change animation, the water level change animation includes an animation of the water surface rising in the underground power distribution room and the sound of rising water flow; Generate fault scenarios for each power distribution equipment after a fault occurs, including special effects animations of smoke and arcs; The structural model of the underground power distribution room, the water level change animation, the probability of failure of each power distribution equipment, and the failure scenario are integrated into a virtual reality training platform, and the virtual reality training platform generates an emergency repair training scenario for the underground power distribution room.

8. An underground power distribution room flooding simulation and emergency repair training system based on Internet of Things data collection, characterized by: The underground power distribution room flooding simulation and emergency repair training system based on IoT data collection includes a virtual reality training platform and a data collection device: The data acquisition device is used to deploy sensors in the underground distribution room to sense physical parameters, obtain physical parameter sensing data of the underground distribution room under flooding scenarios, combine the physical parameter sensing data, use an improved shallow water diffusion wave model to simulate the water level evolution matrix of the underground distribution room under flooding scenarios, use the water level evolution matrix to calculate the water level time series of each distribution device in the underground distribution room, perform time-series attenuation evolution on the insulation state of the distribution equipment, and use a fault tree reasoning method to generate the probability of a failure event for each distribution device; The virtual reality training platform is used to obtain the underground power distribution room scene, the water level evolution matrix and the probability of a failure event for each power distribution equipment, and generate an underground power distribution room emergency repair training scene; To realize the underground power distribution room flooding simulation and emergency repair training method based on Internet of Things data collection as described in any one of claims 1-7.

Images