Early warning method and device for substation operation risk

Abstract

The application discloses a kind of early warning methods and devices for substation operation risk, it is related to electric power technical field, especially it is related to substation technical field.The method comprises the following steps: obtaining N substation data;According to the target three-dimensional model of substation data, the target three-dimensional model of substation is determined, wherein the target three-dimensional model of substation changes with the change of substation data, and the target three-dimensional model is used to characterize the three-dimensional scene of operating personnel when carrying out construction operation to substation;According to the operation risk information of target three-dimensional model, the early warning information for substation is generated according to the operation risk information of substation.The application solves the technical problems that the risk monitoring effect is poor in the prior art due to the use of a single static data source for substation operation risk monitoring and the information transmission and response in early warning are not timely.

Description

Technical Field

[0001] This application relates to the field of power technology, and more particularly to the field of substation technology. Specifically, it relates to a method and apparatus for early warning of operational risks in substations. Background Technology

[0002] With the development of power systems and the increasing complexity of substation operations, traditional risk monitoring methods face a series of challenges and limitations. Traditional risk monitoring methods mainly rely on limited data and simple risk assessment models, which cannot effectively address the complex scenarios and diverse risk factors in substation operations. Currently, substation operation risk monitoring suffers from the following main problems:

[0003] First, traditional monitoring methods are mostly based on a single data source, such as manual observation or a limited number of sensor data, which cannot comprehensively capture the real situation at the work site. This limitation leads to insufficient accuracy and comprehensiveness of monitoring results, making it difficult to provide timely and effective early warning and handling of potential risks in complex work environments. Second, existing risk assessment models are usually based on static data and simple statistical analysis, ignoring the impact of temporal dynamics and spatial correlations on risks. This results in the inability to accurately predict and identify specific risk events in substation operations, affecting the scientific nature and effectiveness of safety management and decision-making. In addition, traditional technologies suffer from long information transmission and response time delays in risk early warning and decision support. Monitoring systems lack real-time performance and efficiency, failing to respond promptly to changes in risks at the work site, thus affecting the effectiveness of emergency response and accident prevention.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This application provides a method and apparatus for early warning of substation operation risks, which at least solves the technical problems in the prior art where the use of a single static data source for substation operation risk monitoring and the untimely information transmission and response in early warning lead to poor risk monitoring results.

[0006] To achieve the above objectives, according to one aspect of this application, a method for early warning of substation operation risks is provided, comprising: acquiring N substation data points, where N is an integer greater than 1, and the N substation data points include at least the location and behavior information of substation workers, the location and status information of substation equipment, and the location and usage status information of workers' operating tools; determining a target three-dimensional model of the substation based on the substation data, wherein the target three-dimensional model of the substation changes with the changes in the substation data, and the target three-dimensional model is used to represent the three-dimensional scene when workers are performing construction operations at the substation; determining substation operation risk information based on the target three-dimensional model; and generating early warning information for the substation based on the substation operation risk information.

[0007] Optionally, the target 3D model of the substation is determined based on the substation data, including: using a time synchronization strategy, a spatial synchronization strategy, and an information complementarity strategy to fuse data from N substations to obtain work site information. Specifically, the time synchronization strategy is used to align the data from N substations based on the timestamp information of each substation; the spatial synchronization strategy is used to transform the data from N substations to the same spatial coordinate system; and the information complementarity strategy is used to integrate substation data with a preset logical relationship. The target 3D model of the substation is then determined based on the work site information.

[0008] Optionally, determining the target 3D model of the substation based on the work site information includes: acquiring the device poses of multiple data acquisition devices, wherein the data acquisition devices are used to collect substation data, and the multiple data acquisition devices include lidar, cameras, and inertial sensors; fusing the device poses of the multiple data acquisition devices to obtain the target pose; and determining the target 3D model of the substation based on the work site information and the target pose.

[0009] Optionally, the target 3D model of the substation is determined based on the work site information and target pose, including: determining the depth map of the work site of the substation based on the work site information and target pose; determining the 3D point cloud data of the work site based on the depth map and images of the work site acquired by the camera; performing resolution enhancement processing on the 3D point cloud data to obtain the target 3D point cloud data; and determining the target 3D model based on the target 3D point cloud data.

[0010] Optionally, the substation operation risk information is determined based on the target 3D model. The early warning method for substation operation risks also includes: determining a target dataset based on N substation data, target pose, environmental parameters of the work site, and operation data of the operators, wherein the operation data represents the operation behavior of the operators; obtaining association rules, wherein the association features between the preset risk events and the N substation data are used to determine the substation operation risk information based on the target dataset, association rules, and target 3D model.

[0011] Optionally, determining substation operation risk information based on the target dataset, association rules, and target 3D model further includes: determining a first type of risk factor based on the target dataset and target 3D model, wherein the first type of risk factor is used to characterize abnormal behavior factors of substation equipment and abnormal behavior factors of operators when performing operations on the substation; determining a second type of risk factor based on association rules and target 3D model, wherein the second type of risk factor is used to characterize potential risk factors for the occurrence of preset risk events at the work site; and using the first type of risk factor and the second type of risk factor as substation operation risk information.

[0012] Optionally, generating early warning information for the substation based on substation operation risk information includes: obtaining the weights and impact values ​​corresponding to the first type of risk factor and the second type of risk factor, respectively, wherein the weights and impact values ​​change with the changes in substation data, and the impact values ​​are used to characterize the degree of influence of the first type of risk factor or the second type of risk factor on the occurrence of abnormal events in the substation; determining the risk levels corresponding to the first type of risk factor and the second type of risk factor based on the weights and impact values; and generating early warning information for the substation based on the risk levels and preset early warning thresholds.

[0013] According to another aspect of this application, an early warning device for substation operation risks is also provided, comprising: a first acquisition unit for acquiring N substation data, wherein N is an integer greater than 1, and the N substation data includes at least the location and behavior information of substation operators, the location and status information of substation equipment, and the location and usage status information of operators' tools; a first determination unit for determining a target three-dimensional model of the substation based on the substation data, wherein the target three-dimensional model of the substation changes with the changes in the substation data, and the target three-dimensional model is used to represent the three-dimensional scene when operators are carrying out construction work on the substation; a second determination unit for determining substation operation risk information based on the target three-dimensional model; and a first generation unit for generating early warning information for the substation based on the substation operation risk information.

[0014] According to another aspect of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, wherein when the computer program is executed, the device in which the computer-readable storage medium is located performs the above-described early warning method for substation operation risks.

[0015] According to another aspect of this application, an electronic device is also provided, wherein the electronic device includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the above-described early warning method for substation operation risks.

[0016] In this embodiment, a three-dimensional model of the substation operation site is constructed by acquiring data from multiple substations. This three-dimensional model is updated in real time as the substation data changes. Then, the operation risk information of the substation is determined based on the three-dimensional model. Finally, a corresponding risk warning is generated based on the operation risk information. This achieves the purpose of real-time monitoring and timely risk warning of the substation operation site, thereby improving the technical effect of substation risk monitoring. It also solves the technical problems in the prior art where the use of a single static data source for substation operation risk monitoring and the untimely information transmission and response in terms of warnings lead to poor risk monitoring effect. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0018] Figure 1 This is a flowchart of an optional early warning method for substation operation risks according to an embodiment of this application;

[0019] Figure 2 This is a schematic diagram of an optional early warning device for substation operation risks according to an embodiment of this application. Detailed Implementation

[0020] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0021] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0022] It should also be noted that the information and data collected in this application are authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of this data all comply with the relevant laws, regulations, and standards of the relevant regions, and necessary confidentiality measures have been taken. This does not violate public order and good morals, and corresponding access points are provided for users to choose to authorize or refuse. For example, this system has interfaces with relevant users or organizations. Before obtaining relevant information, a request to obtain the information needs to be sent to the aforementioned user or organization through the interface, and the relevant information is obtained only after receiving consent from the aforementioned user or organization.

[0023] According to an embodiment of this application, an embodiment of a method for early warning of risks in substation operations is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0024] It should be noted that an intelligent risk early warning system serves as the executing entity for the early warning method for substation operation risks in this application embodiment. It is understood that the early warning method for substation operation risks provided in this application embodiment can also be executed by other systems or devices, and this application embodiment does not specifically limit this.

[0025] Figure 1 This is a flowchart of an optional early warning method for substation operational risks according to an embodiment of this application, such as... Figure 1 As shown, the method includes the following steps:

[0026] Step S101: Obtain data from N substations.

[0027] In step S101, N is an integer greater than 1, and the N substation data include at least the location and behavior information of the substation operators, the location and status information of the substation equipment, and the location and usage status information of the operators' tools.

[0028] Optionally, the intelligent risk warning system can use BeiDou high-precision positioning sensors, visual sensors, binocular visual sensors, and inertial sensors to collect data from the substation operation site. Users can install various sensors for data collection in appropriate locations and calibrate them according to the substation operation site conditions.

[0029] Optionally, the intelligent risk warning system can use wireless transmission technology to transmit the data collected by the sensors to the data processing center in real time, and establish a data storage system to store and back up the transmitted data.

[0030] Optionally, the intelligent risk early warning system can perform preliminary processing on the collected substation data, including at least noise removal, data completion, and data format conversion. For noise removal, filtering algorithms can be applied to remove noise from the data; for data completion, interpolation methods or predictive models can be used to fill in missing data.

[0031] Step S102: Determine the target three-dimensional model of the substation based on the substation data.

[0032] In step S102, the target 3D model of the substation changes as the substation data changes. The target 3D model is used to represent the 3D scene when the operators are carrying out construction work on the substation.

[0033] Optionally, when the substation data changes, the constructed target 3D model will also change accordingly, and the target 3D model changes in real time as the substation data changes.

[0034] Step S103: Determine the operational risk information of the substation based on the target 3D model.

[0035] Optionally, after constructing the target 3D model, the intelligent risk early warning system monitors the status of the entire substation in real time based on the observed target 3D model, and determines the risk information of the substation by combining the target 3D model and related technologies.

[0036] Step S104: Generate early warning information for the substation based on the substation's operational risk information.

[0037] Optionally, after generating operational risk information for a substation, the intelligent risk early warning system will promptly issue relevant warnings to remind operators or managers to check and maintain the information. The intelligent risk early warning system can display all risk conditions within the substation through a visual interface.

[0038] As can be seen from steps S101 to S104, in this application, firstly, N substation data are obtained, where N is an integer greater than 1. The N substation data include at least the location and behavior information of the substation workers, the location and status information of the substation equipment, and the location and usage status information of the workers' operating tools. Then, a target 3D model of the substation is determined based on the substation data. The target 3D model of the substation changes with the changes in the substation data. The target 3D model is used to represent the 3D scene when the workers are carrying out construction work on the substation. Then, the operation risk information of the substation is determined based on the target 3D model. Finally, early warning information for the substation is generated based on the operation risk information of the substation.

[0039] As can be seen from the above, in this embodiment of the application, a three-dimensional model of the substation operation site is constructed by acquiring data from multiple substations. This three-dimensional model is updated in real time as the substation data changes. Then, the operation risk information of the substation is determined based on the three-dimensional model. Finally, a corresponding risk warning is generated based on the operation risk information. This achieves the purpose of real-time monitoring and timely risk warning of the substation operation site, thereby improving the technical effect of substation risk monitoring. It also solves the technical problems in the prior art where the use of a single static data source for substation operation risk monitoring and the untimely information transmission and response in terms of warnings lead to poor risk monitoring effect.

[0040] In one optional embodiment, the intelligent risk warning system employs a time synchronization strategy, a spatial synchronization strategy, and an information complementarity strategy to fuse data from N substations to obtain work site information. Specifically, the time synchronization strategy is used to align the data from the N substations based on the timestamp information of each substation's data; the spatial synchronization strategy is used to transform the data from the N substations to the same spatial coordinate system; and the information complementarity strategy is used to integrate substation data with preset logical relationships, and then determine the target three-dimensional model of the substation based on the work site information.

[0041] Optionally, the intelligent risk warning system first timestamps the data collected by different sensors, and then converts the data collected by different sensors to the same spatial coordinate system.

[0042] Optionally, the intelligent risk warning system employs Bayesian estimation data fusion algorithms and multi-sensor data fusion models in deep learning (such as convolutional neural networks) to fuse multi-source data.

[0043] As can be seen from the above, data fusion algorithms integrate multi-source data to form comprehensive on-site information, improving the accuracy and efficiency of data fusion. At the same time, the fusion process takes into account time synchronization, spatial alignment, and information complementarity, thus improving the integrity and accuracy of the data.

[0044] In one optional embodiment, the intelligent risk warning system acquires the device poses of multiple data acquisition devices, wherein the data acquisition devices are used to collect substation data, and the multiple data acquisition devices include lidar, cameras and inertial sensors. Then, the device poses of the multiple data acquisition devices are fused to obtain the target pose, and finally, the target three-dimensional model of the substation is determined based on the work site information and the target pose.

[0045] Optionally, the intelligent risk warning system uses SLAM (Simultaneous Localization and Mapping) technology to acquire the poses of multiple data acquisition devices, i.e., the location and attitude information of the data acquisition devices.

[0046] Optionally, the pose of the lidar is obtained in the following way:

[0047] First, obtain the point cloud data P. L As shown in formula (1):

[0048] P L ={(x i y i , z i ) |i=1,2...N (1)

[0049] Among them, (x i y i , z i ) represents the three-dimensional coordinates of each point obtained by the lidar scan.

[0050] Then, the pose T is obtained using the ICP algorithm. L As shown in formula (2):

[0051] T L =ICP(P L (2)

[0052] Among them, T L The SLAM pose of the LiDAR is given, and ICP is the Iterative Closest Point Algorithm used for point cloud registration.

[0053] Alternatively, the pose of the visual acquisition device (such as a camera) is obtained in the following ways:

[0054] First, image data is acquired. Then, the visual device pose T is obtained by processing the image data using the ORB (Oriented Fast and Rotated BRIEF) algorithm and the BA (Bundle Adjustment) algorithm. V As shown in formula (3):

[0055] T V =BA(ORB(images))(3)

[0056] Among them, T V For visual SLAM pose.

[0057] Optionally, the pose T of the inertial sensor I It is obtained in the following way, as shown in formula (4):

[0058] T I =∫adt(4)

[0059] Where a represents the acceleration data and dt represents the time increment.

[0060] Optionally, the pose is predicted and updated by fusing multi-source pose data according to EKF (Extended Kalman Filter), as shown in Equation (5):

[0061] T = EKF(T) L T V T I (5)

[0062] Where T represents the fused pose.

[0063] As can be seen from the above, by acquiring pose information from multiple acquisition devices in real time based on SLAM technology and then fusing the acquired pose information, the effect of timely updates can be achieved. At the same time, based on the accurate pose state of the acquisition devices, a foundation can be provided for the subsequent construction of accurate 3D models.

[0064] In one optional embodiment, the intelligent risk warning system determines the depth map of the substation's work site based on the work site information and the target pose. Then, it determines the three-dimensional point cloud data of the work site based on the depth map and the images of the work site collected by the camera. Next, it performs resolution enhancement processing on the three-dimensional point cloud data to obtain the target's three-dimensional point cloud data. Finally, it determines the target's three-dimensional model based on the target's three-dimensional point cloud data.

[0065] Optionally, the intelligent risk warning system generates a depth map D based on binocular vision. The generation process of the depth map D is shown in formula (6):

[0066] D=DepthEstimation(stereo_images)(6)

[0067] Here, DepthEstimation is the depth estimation algorithm, and stereo_images are stereo images.

[0068] Optionally, the intelligent risk warning system uses AtlasNet (AtlasNet: 3D Shape Generation from Boundaries, a three-dimensional reconstruction neural network) to generate a three-dimensional point cloud P3D. The generation process of the three-dimensional point cloud P3D is shown in formula (7):

[0069] P3D = AtlasNet(D, images)(7)

[0070] Optionally, the intelligent risk warning system uses SRCNN (Super-Resolution Convolutional Neural Network) to perform super-resolution enhancement processing on the 3D point cloud to obtain the target 3D point cloud P3D. enhanced The process is shown in formula (8):

[0071] P3D enhanced =SRCNN(P3D)(8)

[0072] Optionally, when generating depth maps based on binocular vision, it is necessary to accurately collect the device's pose information to ensure the accuracy of the data and model.

[0073] Optionally, when the substation data changes, the changed area ΔI in the substation is obtained through monitoring, and the changed area ΔI can be obtained according to formula (9):

[0074] ΔI=Difference(I t I t-1 (9)

[0075] Among them, I t For the image at the current moment, I t-1 This is the image from the previous time step, and Difference is the image difference algorithm.

[0076] After obtaining ΔI, a changing depth map ΔD will be generated, as shown in formula (10):

[0077] ΔD=DepthEstimation(ΔI)(10)

[0078] The changing depth map ΔD generates changing 3D point cloud data ΔP. 3D As shown in formula (11):

[0079] ΔP 3D =PointCloudGeneration(ΔD)(11)

[0080] PointCloudGeneration is the point cloud generation algorithm.

[0081] As shown in formula (12), the intelligent risk warning system will change the target's three-dimensional point cloud P3D before the change. enhanced and 3D point cloud ΔP generated based on depth map changes 3D The new 3D point cloud data P is obtained by summarizing. 3D new When the 3D point cloud data changes, the target 3D model will also change accordingly.

[0082] P 3D new =P 3D enhanced +ΔP 3D (12)

[0083] As can be seen from the above, a 3D model is constructed by collecting the specific pose information and depth map of the equipment. When the depth map changes, the 3D model also changes, thus enabling the generation of an accurate 3D model in a dynamic environment. In other words, the 3D model can be used to monitor the substation operation site in real time. At the same time, by processing the 3D point cloud data to enhance resolution, the accuracy of the target 3D model is improved.

[0084] In one optional embodiment, the intelligent risk warning system determines a target dataset based on data from N substations, target pose, environmental parameters of the work site, and operational data of the operators, wherein the operational data characterizes the operational behavior of the operators. Then, it obtains association rules, which are used to determine the association features between preset risk events and data from N substations. Finally, it determines substation operation risk information based on the target dataset, association rules, and target 3D model.

[0085] Optionally, the intelligent risk warning system standardizes the target dataset to achieve a mean of 0 and a variance of 1. The processing procedure is shown in formula (13).

[0086]

[0087] Where, x t Let μ be the input data at time t, μ be the mean, and σ be the standard deviation.

[0088] Optionally, the intelligent risk early warning system organizes the feature data of the substation operation site into a transaction set D. Each transaction T∈D contains a set of features I. The system uses the Apriori algorithm in association rule mining to mine frequent itemsets. Frequent itemsets F are found through iteration. This frequent itemset F represents the set of all itemsets I with support greater than or equal to min_support. This set includes all itemsets considered to occur frequently in the dataset, as shown in formula (14):

[0089] F={I|Support(I)≥min_support}(14)

[0090] Support(I) is a metric that measures the frequency of itemset I across all events.

[0091] The association rule R is generated based on the frequent itemset F, as shown in formula (15):

[0092] R={A→B∣Confidence(A→B)≥min_confidence}(15)

[0093] Here, A and B are part of a frequent itemset F, Confidence(A→B) represents the confidence that A leads to B, which is a metric, and min_confidence represents the minimum confidence threshold.

[0094] Optionally, association rules R help discover relationships between different features, such as the association between specific operating modes, environmental conditions, or equipment status and risk events. They also help understand which combinations of features may lead to high risk. For example, if a feature A and a risk or fault B satisfy the judgment in the association rule, i.e., A→B is true, it means that A and B are highly correlated, which means that feature A is likely to lead to the occurrence of a risk event, and can help discover potential risk events.

[0095] As can be seen from the above, association rules can be used to discover potential risk events in substations. Based on these potential risk events, managers or operators can review or maintain the substations in advance to prevent them from occurring. Finally, the operational risk information of the entire substation can be determined by using the obtained target dataset, association rules, and target 3D model.

[0096] In one optional embodiment, the intelligent risk early warning system determines a first type of risk factor based on the target dataset and the target 3D model. The first type of risk factor is used to characterize the abnormal behavior factors of equipment in the substation and the abnormal behavior factors of operators when performing operations at the substation. Then, it determines a second type of risk factor based on association rules and the target 3D model. The second type of risk factor is used to characterize the potential risk factors of preset risk events occurring at the work site. Finally, the first type of risk factor and the second type of risk factor are used as substation operation risk information.

[0097] Optionally, the intelligent risk warning system uses a long short-term memory network (LSTM) to identify the first type of risk factor, and uses the target dataset and the target 3D point cloud data as the input data X of the model, as shown in formula (16):

[0098] X = [P] 3D new x t ′] (16)

[0099] The calculation formulas for LSTM cells are shown in (17)-(21):

[0100] f t =σ(W f x′ t +U f h t-1 +b f (17)

[0101] i t =σ(W i x′ t +U i h t-1 +b i (18)

[0102] o t =σ(W o x t ′+U o h t-1 +b o (19)

[0103] c t =f t ⊙c t-1 +i t ⊙tanh(W c x′ t +U c h t-1 +b c (20)

[0104] h t =o t⊙tanh(c t )(twenty one)

[0105] Among them, f t i t o t These are the forget gate, input gate, and output gate, respectively. t For the unit state, h t To be in a hidden state, W f W i W o W c W y U is the LSTM weight matrix. f U i U o U c Let b be the LSTM hidden state weight matrix. f b i b o b c b y This is the bias vector for the LSTM.

[0106] Optionally, the intelligent risk early warning system trains the LSTM model to obtain the target model using historical substation data, historical risk events, and the correlation between historical substations and historical risk events. The input data X is then fed into the target model for analysis to identify abnormal behaviors of operators and abnormal states of equipment. In the LSTM model, the hidden state h in the last layer... t The behavioral classification result y is output through a fully connected layer and a Softmax function. This classification result y is the first type of risk factor, as shown in formula (22):

[0107] y = softmax(W y h t +b y )(twenty two)

[0108] Among them, W y and b y These are the weight matrix and the bias vector, respectively.

[0109] Optionally, the intelligent risk early warning system can determine the second type of risk factor based on the generated association rules and three-dimensional target model. The second type of risk factor represents the potential risk factors of the substation. Finally, the first type of risk factor and the second type of risk factor together constitute the operational risk information of the substation.

[0110] As can be seen from the above, by obtaining the first and second types of risk factors, the risk information of the entire substation operation can be obtained. Corresponding solutions can be taken for the substation based on the obtained risk information, and a basis can be provided for subsequent risk warning.

[0111] In one optional embodiment, the intelligent risk early warning system obtains the weights and impact values ​​corresponding to the first type of risk factor and the second type of risk factor, respectively. The weights and impact values ​​change with the changes in substation data. The impact value is used to characterize the degree of influence of the first type of risk factor or the second type of risk factor on the occurrence of abnormal events in the substation. Then, the risk level corresponding to the first type of risk factor and the second type of risk factor is determined according to the weights and impact values. Finally, early warning information for the substation is generated according to the risk level and the preset early warning threshold.

[0112] Optionally, the intelligent risk early warning system establishes a risk assessment model to quantify the risk level of each risk factor and define the weight 'a' of each risk factor. i The weights are determined by relevant technical personnel or machine learning models, defining the impact value b of each risk factor. i The impact value is obtained through actual data measurement. The risk level E is determined according to the weight and impact value of the risk factors, and the risk is divided into five levels: extremely high, high, medium, low and acceptable. Different countermeasures are taken according to different risk levels. The formula for risk level E is shown in (23):

[0113]

[0114] Where n is the number of risk factors.

[0115] Optionally, the weight of the risk factor a i and influence value b i It can be dynamically adjusted based on real-time substation data X and historical substation data H, where the weight a i and influence value b i The calculation formulas are shown in formulas (24) and (25) respectively:

[0116] a i (t+1)=m·a i (t)+(1-m)·f(X,H) (24)

[0117] Where m is the adjustment coefficient and f(·) is the prediction function based on the machine learning model.

[0118]

[0119] in, The impact value is based on historical data. The impact value is based on real-time data. The impact value is based on the ratings of personnel in the relevant technical field. The influence value is predicted based on the machine learning model, where α, β, γ, and δ are weighting coefficients, and α+β+γ+δ=1.

[0120] The substation's historical data includes past operation records, equipment and environmental status, sensor data, risk assessment and early warning records. Operation records include historical action records of operators, operation steps, equipment usage, historical abnormal events, fault records, and accident reports. Equipment and environmental status includes historical equipment operation data, maintenance records, fault logs, and environmental parameters such as temperature, humidity, and electromagnetic interference. Sensor data includes historical data collected from various sensors (such as visual sensors, inertial sensors, and lidar) and historical location information, such as location data of operators and equipment collected through BeiDou high-precision positioning technology. Risk assessment and early warning records include historical risk assessment reports and results, including risk level, risk factors, historical early warning records, early warning triggering conditions, and subsequent measures.

[0121] Optionally, the intelligent risk early warning system sets different early warning thresholds based on the risk level. When the risk level exceeds the early warning threshold, an early warning will be issued in a timely manner. The system will formulate early warning strategies, including the type of early warning information, the sending method, and the recipients, to provide real-time reminders to substation managers or operators. It will also use multiple methods to release early warning information, including SMS, email, mobile applications, and other channels, to ensure that substation managers or operators receive early warning information in a timely manner. At the same time, it will also build a visual page to display the risk distribution and early warning information through a graphical interface to assist in decision-making.

[0122] Optionally, the intelligent risk early warning system updates the data at the work site in real time to ensure the continuity of risk monitoring. It also collects feedback from workers and managers, analyzes the effectiveness and accuracy of the early warning, and then continuously optimizes the risk monitoring and early warning system based on the feedback.

[0123] As can be seen from the above, by obtaining the weight and impact value of each risk factor, the risk factor can be quantified, the risk level can be clearly defined, and early warnings can be issued based on the risk level. This helps substation managers or operators quickly identify the location, type, and degree of risk, and continuously monitor the work site, update the risk assessment results and early warning information in real time, collect on-site feedback information, and continuously optimize the risk monitoring algorithm and early warning system to improve the accuracy and reliability of the system.

[0124] According to an embodiment of this application, an embodiment of an early warning device for substation operation risks is also provided. Figure 2 This is a schematic diagram of an optional early warning device for substation operational risks according to an embodiment of this application, such as... Figure 2As shown, the early warning device for substation operation risks includes: a first acquisition unit 201, a first determination unit 202, a second determination unit 203, and a first generation unit 204.

[0125] Optionally, the first acquisition unit 201 is used to acquire N substation data, where N is an integer greater than 1, and the N substation data includes at least the location and behavior information of the substation workers, the location and status information of the substation equipment, and the location and usage status information of the workers' operating tools; the first determination unit 202 is used to determine the target three-dimensional model of the substation based on the substation data, wherein the target three-dimensional model of the substation changes with the changes in the substation data, and the target three-dimensional model is used to represent the three-dimensional scene when the workers are carrying out construction work on the substation; the second determination unit 203 is used to determine the operation risk information of the substation based on the target three-dimensional model; and the first generation unit 204 is used to generate early warning information for the substation based on the operation risk information of the substation.

[0126] Optionally, the first determining unit 202 includes: a first processing subunit and a first determining subunit. The first processing subunit is used to perform data fusion on data from N substations using a time synchronization strategy, a spatial synchronization strategy, and an information complementarity strategy to obtain work site information. Specifically, the time synchronization strategy is used to align the data from the N substations based on the timestamp information of each substation; the spatial synchronization strategy is used to convert the data from the N substations to the same spatial coordinate system; and the information complementarity strategy is used to integrate substation data with a preset logical relationship. The first determining subunit is used to determine the target three-dimensional model of the substation based on the work site information.

[0127] Optionally, the first determining subunit includes: a first acquisition module, a first processing module, and a first determining module. The first acquisition module is used to acquire the device poses of multiple data acquisition devices, wherein the data acquisition devices are used to collect substation data, and the multiple data acquisition devices include lidar, cameras, and inertial sensors; the first processing module is used to fuse the device poses of the multiple data acquisition devices to obtain the target pose; and the first determining module is used to determine the target 3D model of the substation based on the work site information and the target pose.

[0128] Optionally, the first determining module includes: a first determining submodule, a second determining submodule, a first processing submodule, and a third determining submodule. The first determining submodule is used to determine the depth map of the substation's work site based on the work site information and the target pose; the second determining submodule is used to determine the three-dimensional point cloud data of the work site based on the depth map and images of the work site acquired by the camera; the first processing submodule is used to perform resolution enhancement processing on the three-dimensional point cloud data to obtain the target's three-dimensional point cloud data; and the third determining submodule is used to determine the target's three-dimensional model based on the target's three-dimensional point cloud data.

[0129] Optionally, the second determining unit 203 includes: a second determining subunit, a first acquiring subunit, and a third determining subunit. The second determining subunit is used to determine a target dataset based on N substation data, target pose, environmental parameters of the work site, and operator operation data, wherein the operation data characterizes the operator's operational behavior. The first acquiring subunit is used to acquire association rules, which are used to determine the association characteristics between preset risk events and N substation data. The third determining subunit is used to determine substation operation risk information based on the target dataset, association rules, and a target 3D model.

[0130] Optionally, the third determining subunit includes: a second determining module, a third determining module, and a fourth determining module. The second determining module is used to determine a first type of risk factor based on the target dataset and the target 3D model, wherein the first type of risk factor characterizes abnormal equipment behavior factors and abnormal behavior factors of operators when performing operations at the substation. The third determining module is used to determine a second type of risk factor based on association rules and the target 3D model, wherein the second type of risk factor characterizes potential risk factors for the occurrence of preset risk events at the work site. The fourth determining module is used to use the first type of risk factor and the second type of risk factor as substation operation risk information.

[0131] Optionally, the first generation unit 204 includes: a second acquisition subunit, a fourth determination subunit, and a first generation subunit. The second acquisition subunit is used to acquire the weights and impact values ​​corresponding to the first type of risk factor and the second type of risk factor, respectively. The weights and impact values ​​change with the substation data, and the impact values ​​characterize the degree of influence of the first or second type of risk factor on abnormal events occurring at the substation. The fourth determination subunit is used to determine the risk levels corresponding to the first and second type of risk factors based on the weights and impact values. The first generation subunit is used to generate early warning information for the substation based on the risk levels and preset early warning thresholds.

[0132] According to another aspect of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, wherein when the computer program is executed, the device in which the computer-readable storage medium is located performs the above-described early warning method for substation operation risks.

[0133] According to another aspect of this application, an electronic device is also provided, wherein the electronic device includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the above-described early warning method for substation operation risks.

[0134] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0135] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0136] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0137] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0138] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0139] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0140] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A pre-warning method for substation operation risk, characterized in that, The method comprises the following steps: acquiring N substation data, wherein N is an integer greater than 1, and the N substation data at least includes position information and behavior information of a worker of a substation, position information and state information of equipment of the substation, position information and use state information of an operation tool of the worker; determining a target three-dimensional model of the substation according to the substation data, wherein the target three-dimensional model of the substation changes with the change of the substation data, and the target three-dimensional model is used to represent a three-dimensional scene of the worker when performing an operation on the substation; determining operation risk information of the substation according to the target three-dimensional model; generating early warning information for the substation according to the operation risk information of the substation; wherein determining the operation risk information of the substation according to the target three-dimensional model comprises: acquiring an association rule, wherein the association rule is used to determine an association feature between a preset risk event and the N substation data; determining a first type of risk factor according to the N substation data and the target three-dimensional model, wherein the first type of risk factor is used to represent an abnormal behavior factor of the equipment of the substation and an abnormal behavior factor of the worker when performing an operation on the substation; determining a second type of risk factor according to the association rule and the target three-dimensional model, wherein the second type of risk factor is used to represent a potential risk factor of the occurrence of the preset risk event in the operation site; and taking the first type of risk factor and the second type of risk factor as the operation risk information of the substation; wherein generating early warning information for the substation according to the operation risk information of the substation comprises: acquiring a weight and an influence value corresponding to the first type of risk factor and the second type of risk factor respectively, wherein the weight and the influence value change with the change of the substation data, and the influence value is used to represent an influence degree of the first type of risk factor or the second type of risk factor on the occurrence of an abnormal event of the substation; determining a risk level corresponding to the first type of risk factor and the second type of risk factor respectively according to the weight and the influence value; and generating early warning information for the substation according to the risk level and a preset early warning threshold; wherein the formula determining the risk levels corresponding to the first type of risk factor and the second type of risk factor respectively according to the weights and the influence values, i weights a representing each risk factor, i influence values b representing each risk factor, n is the number of risk factors, and E is the risk level; wherein the weights a i and the influence values b i are dynamically adjusted according to real-time substation data X and substation historical data H. By the formula a i (t+1) = m · a i (t) + (1 - m) · f(X, H) determines the weight a i ; The impact value b is determined by the formula i :​ wherein m is an adjustment coefficient, f(·) is a prediction function based on a machine learning model, is an impact value based on historical data, is an impact value based on real-time data, is an impact value based on the score of a related technical personnel, is an impact value based on a machine learning model prediction, and α, β, γ, δ are weight coefficients, with α+β+γ+δ=1.

2. The pre-warning method for substation work risk according to claim 1, characterized in that, determining the target three-dimensional model of the substation according to the substation data comprises: performing data fusion on the N substation data by adopting a time synchronization strategy, a space synchronization strategy and an information complementary strategy to obtain operation site information, wherein the time synchronization strategy is used to time-align the N substation data according to time stamp information of each substation data; the space synchronization strategy is used to convert the N substation data to the same space coordinate system; and the information complementary strategy is used to integrate substation data having a preset logical relationship; determining the target three-dimensional model of the substation according to the operation site information.

3. The pre-warning method for substation work risk according to claim 2, characterized in that, determining the target three-dimensional model of the substation according to the operation site information comprises: Obtaining device poses of a plurality of data acquisition devices, wherein the data acquisition devices are used to acquire the substation data, and the plurality of data acquisition devices include a lidar, a camera, and an inertial sensor; Fusing the device poses of the plurality of data acquisition devices to obtain a target pose; Determining a target three-dimensional model of the substation according to the job site information and the target pose.

4. The pre-warning method for substation work risk according to claim 3, characterized in that, Determining a target three-dimensional model of the substation according to the job site information and the target pose, includes: Determining a depth map of the job site of the substation according to the job site information and the target pose; Determining three-dimensional point cloud data of the job site according to the depth map and an image of the job site acquired by the camera; Performing resolution enhancement processing on the three-dimensional point cloud data to obtain target three-dimensional point cloud data; Determining the target three-dimensional model according to the target three-dimensional point cloud data.

5. The pre-warning method for substation work risk according to claim 3, characterized in that, Determining substation job risk information according to the target three-dimensional model, the early warning method for substation job risk further includes: Determining a target data set according to the N pieces of substation data, the target pose, environmental parameters of the job site, and operation data of the job personnel, wherein the operation data represents operation behaviors of the job personnel; Determining the substation job risk information according to the target data set, the association rule, and the target three-dimensional model.

6. A device for early warning of risks of substation work for realizing the method for early warning of risks of substation work according to any one of claims 1 to 5, characterized by, includes: A first obtaining unit that obtains N pieces of substation data, wherein N is an integer greater than 1, and the N pieces of substation data at least include position information and behavior information of job personnel of a substation, position information and state information of equipment of the substation, and position information and use state information of an operation tool of the job personnel; A first determining unit that determines a target three-dimensional model of the substation according to the substation data, wherein the target three-dimensional model of the substation changes with changes in the substation data, and the target three-dimensional model is used to represent a three-dimensional scene of the job personnel when performing a construction job on the substation; A second determining unit that determines job risk information of the substation according to the target three-dimensional model; A first generating unit that generates early warning information for the substation according to the job risk information of the substation.

7. A computer readable storage medium characterized in that, The computer readable storage medium stores a computer program, wherein when the computer program runs, the device where the computer readable storage medium is located executes the early warning method for substation job risk in any one of claims 1 to 5.

8. An electronic device, comprising: includes one or more processors and a memory, and the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the early warning method for substation job risk in any one of claims 1 to 5.

Images