Power distribution network uninterrupted operation monitoring method, system and equipment based on virtual reality, and medium

Abstract

The invention discloses a virtual reality-based power distribution network uninterrupted operation monitoring method and system, computer equipment and a storage medium, and the method comprises the steps: configuring a virtual reality training scene, and obtaining the real-time motion data of an operator; calculating the overall matching degree between the actual action and the standard action based on the real-time action data; identifying the combined action data of the operator through a pre-constructed deep learning model to obtain continuous combined actions, and predicting corresponding equipment state data based on the continuous combined actions; after detecting that the equipment state is abnormal based on the equipment state data, performing abnormal judgment again based on the obtained adjustment action data of the operator to obtain an abnormal judgment result; and constructing an abnormal action list based on an abnormal judgment result, and performing abnormal reminding after determining a high-frequency abnormal action group according to the abnormal action list. According to the scheme, the action of the operator and the feedback of the equipment state can be matched in real time, and the real-time monitoring of the non-power-cut operation of the operator is realized.

Description

Technical Field

[0001] The present application relates to the field of virtual reality technology, and in particular to a method, system, computer equipment and storage medium for monitoring non-stop operations of distribution networks based on virtual reality. Background Art

[0002] With the continuous development of the power industry and the expansion of the power grid, the technology of non-stop operation of distribution networks has gradually become an important means to ensure the stable supply of electricity. Its application scenarios are wide, covering areas such as power grid maintenance, equipment replacement, and fault repair. Most of the existing operation training methods use on-site drills or simplified simulation systems. In order to conduct training safely, training programs for non-stop operation of distribution networks in a simulated environment based on virtual display technology have begun to appear.

[0003] Although existing technologies use virtual reality technology to simulate working environments to a certain extent, they are mostly limited to single action simulation or equipment status feedback, and lack accurate identification and feedback mechanisms for the complex relationship between operator actions and equipment status. In particular, when operators perform complex continuous actions, they are unable to provide accurate data-based judgments in real time. At the same time, when detecting abnormal operations or equipment abnormalities, there is also a lack of effective prediction and feedback mechanisms, making it impossible to correct the operator's erroneous behavior in a timely manner or predict potential problems with the equipment status.

[0004] The preceding description is intended to provide general background information and does not necessarily constitute prior art. Summary of the invention

[0005] Based on this, the present application provides a distribution network non-stop operation monitoring method, system, computer equipment and storage medium based on virtual reality to solve the potential problems that the existing technology cannot provide accurate data-based judgments in real time, and lacks an effective prediction and feedback mechanism, resulting in the inability to promptly correct the operator's erroneous behavior or predict the equipment status.

[0006] In order to solve the above technical problems, in the first aspect, the present application provides a method for monitoring power distribution network non-stop operation based on virtual reality, comprising:

[0007] Configure virtual reality training scenarios and obtain real-time operator action data;

[0008] Calculating the overall matching degree between the actual action and the standard action based on the real-time action data;

[0009] The operator's combined action data is identified by a pre-built deep learning model to obtain continuous combined actions, and corresponding equipment status data is predicted based on the continuous combined actions;

[0010] After detecting that the equipment state is abnormal based on the equipment state data, re-determine the abnormality based on the acquired adjustment action data of the operator to obtain an abnormality determination result;

[0011] An abnormal action list is constructed based on the abnormal determination result, and an abnormal reminder is issued after a high-frequency abnormal action group is determined according to the abnormal action list.

[0012] Optionally, in some embodiments of the present application, the method for monitoring power distribution network non-stop operation based on virtual reality further includes:

[0013] Collect the real-time dynamic data, the device status data, the device status data prediction value and the abnormal action list, and summarize them into operation data;

[0014] The operation data is encrypted and the encrypted operation data is backed up to a cloud server and a local storage database respectively.

[0015] Optionally, in some embodiments of the present application, configuring a virtual reality training scene and obtaining real-time motion data of an operator includes:

[0016] Configuring the virtual reality training scene, wherein the configuration of the virtual reality training includes a head-mounted display device, a customized virtual operating console, a matching graphics workstation and a simulated joystick;

[0017] Equipped with a virtual reality scene based on a 3D engine, including the modeling of the working environment, operating tools and scenes in the non-stop operation of the distribution network;

[0018] The real-time motion data of the operator is acquired and recorded in real time through the motion step device, wherein the real-time motion data includes the three-dimensional trajectory of each motion and the posture angle data of the operator.

[0019] Optionally, in some embodiments of the present application, the calculating the overall matching degree between the actual action and the standard action based on the real-time action data includes:

[0020] Define standard action trajectories based on standard operating actions for power distribution network without power outages, and construct corresponding standard action sequences;

[0021] Constructing a corresponding actual action sequence based on the real-time action data;

[0022] Based on the actual action sequence and the standard action sequence, calculating the Euclidean distance between the actual action trajectory and the standard action trajectory;

[0023] Determine the minimum cumulative distance between the actual action sequence and the standard action sequence based on the Euclidean distance using a dynamic time warping algorithm;

[0024] The overall matching degree between the actual action and the standard action is determined based on the minimum cumulative distance.

[0025] Optionally, in some embodiments of the present application, the identifying the operator's combined action data by a pre-built deep learning model to obtain a continuous combined action, and predicting corresponding equipment status data based on the continuous combined action includes:

[0026] Identify and match continuous combined actions and distribution network operation equipment status feedback in a virtual reality environment;

[0027] Based on the collected combined action data and the distribution network operation equipment status data, unified collection is performed, and time series alignment processing is performed to generate a corresponding combined data set for each moment;

[0028] Constructing a deep learning model, and using a training set to train the deep learning model to obtain a trained deep learning model;

[0029] Based on the trained deep learning model, the operator's combined action data is identified to obtain the corresponding continuous combined actions;

[0030] Reasoning is performed based on the continuous combined actions through a Bayesian network to calculate the predicted value of the device status data at the corresponding moment and determine the corresponding device status data.

[0031] Optionally, in some embodiments of the present application, after detecting that the equipment state is abnormal based on the equipment state data, re-determining the abnormality based on the acquired adjustment action data of the operator to obtain the abnormality determination result includes:

[0032] Statistics of the operator's adjustment action group and corresponding abnormality judgment data under abnormality reminder;

[0033] Generate an abnormal action list based on the adjustment action group that appears abnormally again, and calculate the abnormal probability according to the proportion of the number of occurrences of the adjustment action group in the total number of adjustments;

[0034] Based on the abnormal probability of the abnormal action, the change rate of the abnormal probability between every two abnormal actions is calculated to generate the abnormal judgment result.

[0035] Optionally, in some embodiments of the present application, constructing an abnormal action list based on the abnormal determination result, and performing an abnormal reminder after determining a high-frequency abnormal action group according to the abnormal action list, includes:

[0036] Based on the abnormal determination result, the abnormal actions corresponding to the change rate greater than the average change rate are determined as a high-frequency abnormal action group;

[0037] Constructing a corresponding abnormal action list based on the high-frequency abnormal action group;

[0038] Based on the virtual reality environment, the corresponding window information is displayed according to the abnormal action list to remind the operator of the abnormality.

[0039] In a second aspect, the present application provides a distribution network non-stop operation monitoring system based on virtual reality, comprising:

[0040] The acquisition module is used to configure the virtual reality training scene and obtain the operator's real-time action data;

[0041] A calculation module, used for calculating the overall matching degree between the actual action and the standard action based on the real-time action data;

[0042] A prediction module, used to identify the operator's combined action data through a pre-built deep learning model, obtain continuous combined actions, and predict corresponding equipment status data based on the continuous combined actions;

[0043] A determination module, configured to, after detecting that the equipment state is abnormal based on the equipment state data, re-determine the abnormality based on the acquired adjustment action data of the operator to obtain an abnormality determination result;

[0044] The reminder module is used to construct an abnormal action list based on the abnormal determination result, and to perform abnormal reminder after determining a high-frequency abnormal action group according to the abnormal action list.

[0045] In a third aspect, the present application provides a computer device including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method for monitoring non-stop operations of distribution networks based on virtual reality as described in the first aspect are implemented.

[0046] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for non-stop operation monitoring of distribution network based on virtual reality as described in the first aspect.

[0047] The present application provides a method, system, computer device and storage medium for monitoring non-stop operation of distribution network based on virtual reality. The method for monitoring non-stop operation of distribution network based on virtual reality includes: configuring a virtual reality training scene and obtaining real-time action data of an operator; calculating the overall matching degree between actual action and standard action based on the real-time action data; identifying the combined action data of the operator through a pre-built deep learning model to obtain continuous combined action, and predicting the corresponding equipment status data based on the continuous combined action; after detecting an abnormal equipment status based on the equipment status data, re-determining the abnormality based on the obtained adjustment action data of the operator to obtain an abnormality determination result; constructing an abnormal action list based on the abnormal determination result, and performing an abnormal reminder after determining a high-frequency abnormal action group according to the abnormal action list. In the virtual reality-based distribution network non-stop operation monitoring solution provided in the present application, the typical work scenes and operating tools in the non-stop operation of the 10kV distribution network can be simulated in the VR simulation virtual reality environment. By calculating the Euclidean distance between the actual action and the standard action, the action deviation of the operator when performing the operation in the virtual reality environment can be accurately evaluated. By constructing an LSTM deep learning model to classify the operator's actions and combining it with the Bayesian network, the operator's actions can be matched with the feedback of the equipment status in real time, thereby realizing real-time monitoring of the operator's non-stop operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] in:

[0050] Figure 1 It is a flow chart of a method for monitoring non-stop operation of a distribution network based on virtual reality provided in an embodiment of the present application;

[0051] Figure 2 It is a structural schematic diagram of a distribution network non-stop operation monitoring system based on virtual reality provided in an embodiment of the present application;

[0052] Figure 3 It is a structural schematic diagram of the computer device provided by this application. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0054] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0055] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present application, and have no specific meanings. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0057] The present application provides a method, system, computer equipment and storage medium for monitoring non-stop operations of a distribution network based on virtual reality.

[0058] Among them, the virtual reality-based distribution network non-stop operation monitoring system provided by the present application can be integrated in a computer device, which can be directly or indirectly connected to a computer device through wired or wireless communication. The computer device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker or a smart watch, etc., but is not limited to this. In addition, the computer device can also be connected to a server, which can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. This application does not limit this.

[0059] The present application discloses a method for monitoring distribution network non-stop operations based on virtual reality, comprising: configuring a virtual reality training scene and obtaining real-time action data of an operator; calculating the overall matching degree between actual actions and standard actions based on the real-time action data; identifying the operator's combined action data through a pre-built deep learning model to obtain continuous combined actions, and predicting corresponding equipment status data based on the continuous combined actions; after detecting an abnormal equipment status based on the equipment status data, re-determining the abnormality based on the obtained operator's adjustment action data to obtain an abnormality determination result; constructing an abnormal action list based on the abnormal determination result, and performing an abnormal reminder after determining a high-frequency abnormal action group based on the abnormal action list.

[0060] See also Figure 1 , Figure 1 A flow chart of a method for monitoring non-stop operation of a distribution network based on virtual reality provided in this application. The specific flow of the method for monitoring non-stop operation of a distribution network based on virtual reality can be as follows:

[0061] S1. Configure the virtual reality training scene and obtain the operator's real-time action data;

[0062] Specifically, for step S1, the main task is to configure a virtual reality training scene, simulate a virtual reality environment through VR (Virtual Reality, virtual reality technology), thereby simulating typical work scenes and operating tools in non-stop operations of a 10kV distribution network, and collect the operator's current real-time action data to form a detailed operation record.

[0063] S2. Calculate the overall matching degree between the actual action and the standard action based on the real-time action data;

[0064] Specifically, for step S2, the Euclidean distance between the operator's actual action and the standard action trajectory is mainly calculated, and the overall matching degree of the sequence is determined in combination with the dynamic time warping algorithm DTW.

[0065] S3. Identify the operator's combined action data through a pre-built deep learning model to obtain continuous combined actions, and predict corresponding equipment status data based on the continuous combined actions;

[0066] Specifically, step S3 includes constructing an LSTM (Long Short-Term Memory) deep learning model, so that the constructed LSTM deep learning model recognizes the operator's continuous combination actions, and predicts the equipment status data according to the continuous combination actions based on the Bayesian network.

[0067] S4. After detecting an abnormal state of the device based on the device state data, re-determine the abnormality based on the acquired operator adjustment action data to obtain an abnormality determination result;

[0068] Specifically, for step S4, whether the state of the equipment is abnormal is determined based on the abnormal equipment state data. After determining that the equipment state is abnormal, the abnormality determination is re-performed based on the operator's adjustment action group to obtain the latest abnormality determination result.

[0069] S5. Construct an abnormal action list based on the abnormal determination results, and determine the high-frequency abnormal action group according to the abnormal action list and then issue an abnormal reminder;

[0070] Specifically, for step S5, based on the latest abnormal determination result obtained in the previous step, an abnormal action list is constructed, and a common abnormal action group is determined by calculating the change rate of the abnormal probability of each abnormal action in the abnormal action list, and finally an abnormal reminder is given to the common abnormal action group.

[0071] It can be seen that the virtual reality-based distribution network non-stop operation monitoring method provided in this embodiment can simulate typical work scenes and operating tools in 10kV distribution network non-stop operation in a virtual reality environment through VR simulation. By calculating the Euclidean distance between the actual action and the standard action, the action deviation of the operator when performing the operation in the virtual reality environment can be accurately evaluated. By constructing an LSTM model to classify the operator's actions and combining it with the Bayesian network, the operator's actions can be matched with the feedback of the equipment status in real time, thereby realizing real-time monitoring of the operator's non-stop operation.

[0072] Optionally, in some embodiments, the method for monitoring power distribution network non-stop operation based on virtual reality may further include:

[0073] S61. Collect real-time dynamic data, equipment status data, equipment status data prediction value and abnormal action list, and summarize them into operation data;

[0074] S62. Encrypt the job data and back up the encrypted job data to the cloud server and the local storage database respectively.

[0075] Specifically, after determining the common abnormal action group for abnormal reminder, this embodiment also provides a method for statistics and encryption of monitoring data, continuously collecting the operator's action data and equipment status data as well as the equipment status data prediction value and abnormal action list, performing statistical summary, using the TLS protocol for data transmission encryption, using AES-256 for symmetrical encryption of the transmitted data, and backing up and storing it in the cloud server and storage hard disk.

[0076] This embodiment uses the TLS protocol to encrypt data transmission, which can effectively prevent the data from being intercepted or tampered with during the transmission process. By performing AES-256 encryption on the collected operator action data, equipment status data, and prediction data, it can ensure that even if the data is illegally obtained during the storage process, the attacker cannot easily decrypt the data, which greatly improves the security of the data. The encrypted data is backed up to the cloud server and storage hard disk to achieve dual backup locally and in the cloud to prevent data loss.

[0077] Optionally, in some embodiments, step S1 “configure a virtual reality training scene and obtain real-time motion data of the operator” may specifically include:

[0078] Configure virtual reality training scenarios. The configuration of virtual reality training includes head-mounted display devices, customized virtual operation consoles, supporting graphics workstations and simulated joysticks;

[0079] Equipped with a virtual reality scene based on a 3D engine, including the modeling of the working environment, operating tools and scenes in the non-stop operation of the distribution network;

[0080] The real-time motion data of the operator is acquired and recorded in real time through the motion step device. The real-time motion data includes the three-dimensional trajectory of each motion and the posture angle data of the operator.

[0081] Specifically, for step S1, first, a dedicated virtual reality training scene is configured, including a head-mounted display device (such as HTC VIVE Pro), a customized virtual operating console, a matching graphics workstation and a simulated operating handle, and a virtual reality scene based on the Unity3D engine is installed, including the modeling of a typical working environment, operating tools and scenes in non-stop operations of a 10kV distribution network; then, a motion capture device in the virtual reality is used to obtain the operator's real-time motion data and record it in real time, including the three-dimensional trajectory of each motion, and collect the operator's posture angle data.

[0082] This embodiment uses VR to simulate a virtual reality environment to simulate typical work scenes and operating tools in non-stop operations of a 10kV distribution network, which can not only reduce the use and wear of actual operating equipment, but also reduce equipment loss during training. The virtual scene can be used multiple times and is easy to update and maintain, saving training costs. Operators can practice complex and dangerous operating procedures in a low-risk environment, enhance safety awareness and operating proficiency, and form detailed operation records by collecting the operator's motion data and posture angles. Operators can deal with high-risk operations in a safe virtual space, effectively avoiding dangers in actual operations. By simulating emergency situations, operators can train how to deal with emergencies, thereby better preventing and responding to risks in real work.

[0083] Optionally, in some embodiments, step S2 of “calculating the overall matching degree between the actual action and the standard action based on the real-time action data” may specifically include:

[0084] Define standard action trajectories based on standard operating actions for power distribution network without power outages, and construct corresponding standard action sequences;

[0085] Build the corresponding actual action sequence based on real-time action data;

[0086] Based on the actual action sequence and the standard action sequence, the Euclidean distance between the actual action and the standard action trajectory is calculated;

[0087] The dynamic time warping algorithm is used to determine the minimum cumulative distance between the actual action sequence and the standard action sequence based on the Euclidean distance;

[0088] The overall match between the actual action and the standard action is determined based on the minimum cumulative distance.

[0089] Specifically, for step S2, the Euclidean distance between the operator's actual action and the standard action trajectory is calculated, and the overall matching degree of the sequence is determined by combining the dynamic time warping algorithm DTW. The specific process is as follows:

[0090] Based on the standard operation action of the distribution network without power outage, the standard action trajectory is defined based on virtual reality, and a standard action sequence is constructed. The sequence data points represent the specific spatial position and posture angle data of the standard action. According to the real-time actions of the operator collected in the virtual reality environment, including spatial position and posture angle data, the actual action sequence is constructed; the Euclidean distance between the actual action of the operator and the standard action trajectory is calculated, which is expressed as:

[0091]

[0092] A=(x i -x′ j ) 2 +(y i -y′ j ) 2 +(Z i -z′ j ) 2 ;

[0093] B=(θ x -θ′ x ) 2 +(θ y -θ′ y ) 2 +(θ z -θ′ z ) 2 ;

[0094] Where d(c i , x j ) represents the actual action x j With standard action c i The Euclidean distance between i ,y i 、z i and x′ j , y′ j , z′ j Represent the spatial coordinates of the standard action and the actual action, θ x ,θ y ,θ z and θ′ x ,θ′ y ,θ′ z Respectively represent the posture angles of standard action and actual action;

[0095] The overall matching degree of the sequence is determined based on the calculation of Euclidean distance combined with the dynamic time warping algorithm DTW (Dynamic Time Warping), and the cumulative distance matrix is ​​defined. The elements of the matrix represent the minimum distance path from the starting point coordinates (1, 1) to the current point (i, j), which is expressed as:

[0096] D(i, j) = d(c i , x j )+min{D(i-1,j),D(i,j-1),D(i-1,j-1)};

[0097] Where D(i, j) represents the minimum cumulative distance from the starting point of the sequence to the current point (i, j), min{D(i-1, j), D(i, j-1), D(i-1, j-1)} represents the minimum cumulative distance to the previous position;

[0098] Based on the minimum cumulative distance, the path is backtracked until it returns to the starting point to determine the optimal time alignment path P between the standard action and the actual action; the minimum cumulative distance is standardized to obtain the matching data; the sum of the average value and the standard deviation of the historical matching data of the actions considered qualified is used as the matching threshold. If the matching data is less than or equal to the matching threshold, it is determined that the deviation of the operator's actual action is large.

[0099] This embodiment can accurately evaluate the operator's action deviation when performing work in a virtual reality environment, including the difference in spatial position and posture angle, by calculating the Euclidean distance between the actual action and the standard action. The calculation of the Euclidean distance quantitatively compares the standard action with the actual action, providing a clear deviation measurement to help the training system identify the operator's specific operation problems. By using the DTW algorithm, the action matching in the time dimension can be dynamically adjusted to avoid erroneous evaluations caused by slight differences in the operator's action rhythm. Through DTW, the system can flexibly adapt to different action speeds and time changes to ensure that even if the operator's action speed is different, the trajectory of its actual action and the standard action can still be accurately matched, providing a more flexible and reasonable matching evaluation. The use of the cumulative distance matrix can Accurately tracking the operator's action execution path and finding the best alignment path through path backtracking helps to identify which steps in the operator's actions deviate most seriously from the standard actions, allowing the system to provide guidance and feedback on specific issues and improve training efficiency. The matching data obtained by standardizing the minimum cumulative distance can enable the system to fairly compare the action performance of different operators. The matching threshold constructed based on the matching average and standard deviation of qualified historical actions can effectively distinguish whether the operator's actions are qualified. By defining standard action trajectories and implementing a strict matching evaluation mechanism, the system helps to promote standardized operating procedures in non-stop operations in distribution networks. Operators can better follow standard action requirements through system feedback to ensure consistency and standardization of the operating process.

[0100] Optionally, in some embodiments, step S3 of “identifying the operator's combined action data through a pre-built deep learning model to obtain continuous combined actions, and predicting corresponding device status data based on the continuous combined actions” may specifically include:

[0101] Identify and match continuous combined actions and distribution network operation equipment status feedback in a virtual reality environment;

[0102] Based on the collected combined action data and distribution network operation equipment status data, unified collection is performed, and time series alignment processing is performed to generate a corresponding combined data set for each moment;

[0103] Build a deep learning model and use the training set to train the deep learning model to obtain a trained deep learning model;

[0104] Based on the trained deep learning model, the operator's combined action data is identified to obtain the corresponding continuous combined actions;

[0105] The Bayesian network is used to perform reasoning based on continuous combined actions, calculate the predicted value of the device status data at the corresponding moment, and determine the corresponding device status data.

[0106] Specifically, for step S3, an LSTM deep learning model is constructed to identify the operator's continuous combined actions, and the equipment status data is predicted based on the continuous combined actions based on the Bayesian network. The specific process is as follows:

[0107] Identify and match the operator's continuous combined actions and distribution network operation equipment status feedback in a virtual reality environment; uniformly collect the operator's action data and the distribution network operation equipment status data in a virtual reality environment, align the time series, and generate a combined data set for each moment, including action data and equipment status data at the same time; build an LSTM deep learning model, including an input layer, an LSTM layer, and an output layer, where the input layer inputs the action sequence at each time point, the LSTM layer classifies the action sequence through multiple time steps, and the output layer outputs the predicted label of each combined action; use the training set to train the model, select the cross entropy loss function to calculate the difference between the category probability predicted by the model and the actual label, and use the Adam optimizer for gradient descent Optimize and update the parameters of the LSTM model. If the loss of the model no longer decreases significantly during the continuous iteration process, stop iterating and output the model parameters to update the model; use the LSTM model to identify the operator's continuous combined actions; use the directed acyclic graph DAG based on the Bayesian network to represent the conditional dependency between random variables, and use the operator's combined action data and equipment state parameters as two subsets of the Bayesian network respectively. Different action data and equipment state data in each subset represent action nodes and equipment state nodes respectively; define the impact of the combined action data at the last moment on the equipment data as the edge of the Bayesian network; determine the operator's combined action data at time t based on the training data, and determine the conditional probability table CPT based on the probability of each value of the equipment state data at the last moment of the combined action;

[0108] According to the actual operation data of the operator, the Bayesian network is used to infer the current conditional probability table and calculate the predicted value of the equipment status data at the corresponding time, which is expressed as:

[0109]

[0110] Where P(S(t+1)) and P(S(t)) represent the device state probabilities at time t+1 and time t, respectively. represents the sum of all device states S(t) at time t, Y co represents the combined actions of the operator identified by the LSTM model, and S(t) represents the equipment status data at time t.

[0111] In this embodiment, the LSTM model is constructed to classify the operator's actions and combined with the Bayesian network. The system can match the operator's actions with the feedback of the equipment status in real time, ensuring that each operator's action can be directly reflected in the distribution network equipment status, helping the operator to understand the impact of his operation and correct errors in time during the operation. The LSTM model recognizes the operator's continuous combined actions, and the system can capture the complex and multi-step operations performed by the operator in the virtual reality environment. The time dependency of different operator actions can be accurately distinguished to ensure that the system can recognize the relationship between each action. The Bayesian network can predict the future state of the equipment by analyzing the conditional dependency between the operator's combined actions and the equipment status. Based on the current value of the equipment status and the operator's actions, the system can infer the state change of the equipment at the future moment. By combining the operator action data and the equipment status data, the system can train the LSTM and Bayesian network models based on a large amount of historical data, thereby gradually optimizing the accuracy of the model. The operator can understand the impact of each of his actions through real-time feedback. Through the action recognition of the LSTM model and the equipment status prediction of the Bayesian network, the operator can clearly know which operations may cause abnormal equipment status.

[0112] Optionally, in some embodiments, step S4 “after detecting that the device state is abnormal based on the device state data, re-determine the abnormality based on the acquired adjustment action data of the operator to obtain the abnormality determination result” may specifically include:

[0113] Statistics of the operator's adjustment action group and corresponding abnormality judgment data under abnormality reminder;

[0114] Generate an abnormal action list based on the adjustment action group that appears abnormally again, and calculate the abnormal probability according to the proportion of the number of occurrences of the adjustment action group in the total number of adjustments;

[0115] Based on the abnormal probability of the abnormal action, the change rate of the abnormal probability between every two abnormal actions is calculated to generate the abnormal judgment result.

[0116] Specifically, for step S4, the abnormal state of the equipment is determined based on the abnormal equipment state data, and the abnormality determination is re-performed based on the operator's adjustment action group. The specific process is as follows:

[0117] Based on the equipment status data, abnormal equipment status data is selected as the abnormal data set. If the predicted equipment status data belongs to the abnormal data set, it is judged that the operator's operation is abnormal. Based on the virtual reality environment, the operator is reminded of abnormal operation, and the LSTM model is used to re-identify the operator's adjustment action group under the abnormal reminder. The equipment status data based on the adjustment action group is predicted based on the Bayesian network to perform repeated abnormal judgment.

[0118] This embodiment classifies abnormal situations in the equipment status data into abnormal data sets. When the system predicts that the equipment status data belongs to the abnormal data set, it immediately determines that there may be problems with the operator's operation. After the system detects an abnormal operation in a virtual reality environment, it can immediately warn the operator through the abnormal operation reminder function. After receiving the reminder, the operator can dynamically adjust his actions, which improves the operator's efficiency in correcting operational errors and helps the operator quickly adapt to complex work scenarios. Based on the operator's adjustment action group, the Bayesian network can predict the new equipment state and perform repeated abnormality judgments. This multi-level abnormality judgment method ensures the high robustness of the system and can continuously track whether the operator's adjustments are effective. If the adjusted operation still causes abnormal equipment status, the system will continue to provide operational feedback until the problem is resolved, helping the operator to continuously optimize his operating behavior through multiple corrections.

[0119] Optionally, in some embodiments, step S5 "building an abnormal action list based on the abnormal determination result, and determining a high-frequency abnormal action group according to the abnormal action list and then performing an abnormal reminder" may specifically include:

[0120] Based on the abnormal determination result, the abnormal actions corresponding to the change rate greater than the average change rate are determined as the high-frequency abnormal action group;

[0121] Build a corresponding abnormal action list based on the high-frequency abnormal action group;

[0122] Based on the virtual reality environment, the corresponding window information is displayed according to the abnormal action list to remind the operator of the abnormality.

[0123] Specifically, for step S5, the abnormal action list is mainly constructed, the change rate of the abnormal probability is calculated to determine the common abnormal action group, and the abnormal reminder is performed. The specific process is as follows:

[0124] Statistics are collected on the operator's adjustment action groups and corresponding abnormal judgment data under abnormal reminders; an abnormal action list is generated based on the adjustment action groups with abnormal judgments that appear again, and the abnormal probability is calculated based on the proportion of the number of occurrences of the adjustment action groups in the total number of adjustments; based on the abnormal probability of the abnormal actions, the change rate of the abnormal probability between every two abnormal actions is calculated, and based on the average change rate, the abnormal actions corresponding to the abnormal actions that are greater than the average change rate are selected as common abnormal action groups; based on the virtual reality environment, abnormal reminders are given according to the window information displayed according to the common abnormal action groups.

[0125] In this embodiment, by counting the operator's adjustment action groups and abnormal judgment data, the system can generate an abnormal action list and calculate the abnormal probability based on the frequency of occurrence of the adjustment action group in the total adjustment, so as to help the system accurately locate the common errors of the operator during the operation process and provide data support for subsequent abnormal reminders, thereby achieving targeted reminders and reducing redundant information. The system can help operators understand their common operating errors in real time in a virtual reality environment by selecting abnormal action groups with a rate of change greater than the average as common abnormal action groups. Since the system can continuously monitor the operator's adjustment action groups and abnormal probability data, the common abnormal action groups of each operator can be dynamically updated. By counting and analyzing common abnormal actions, the system can help operators continuously optimize their operating processes and gradually move closer to standardization.

[0126] The above completes the non-stop operation monitoring process of the distribution network based on virtual reality in the embodiment of the present application.

[0127] As described above, the embodiment of the present application provides a method for monitoring power distribution network non-stop operation based on virtual reality.

[0128] First, configure the virtual reality training scene and obtain the real-time action data of the operator; calculate the overall matching degree between the actual action and the standard action based on the real-time action data; then, identify the operator's combined action data through the pre-built deep learning model to obtain continuous combined actions, and predict the corresponding equipment status data based on the continuous combined actions; then, after detecting the abnormal state of the equipment based on the equipment status data, re-determine the abnormality based on the obtained operator's adjustment action data to obtain the abnormal determination result; finally, build an abnormal action list based on the abnormal determination result, and determine the high-frequency abnormal action group according to the abnormal action list and then make an abnormal reminder. In the virtual reality-based distribution network non-stop operation monitoring scheme provided in this embodiment, the typical working scenes and operating tools in the 10kV distribution network non-stop operation can be simulated in the VR simulation virtual reality environment. By calculating the Euclidean distance between the actual action and the standard action, the action deviation of the operator when performing the operation in the virtual reality environment can be accurately evaluated. By constructing an LSTM deep learning model to classify the operator's actions and combining the Bayesian network, the operator's actions and the feedback of the equipment status can be matched in real time, and the real-time monitoring of the operator's non-stop operation can be realized.

[0129] In order to facilitate the better implementation of the distribution network non-stop operation monitoring method based on virtual reality of the embodiment of the present application, the embodiment of the present application also provides a distribution network non-stop operation monitoring system based on virtual reality. The meanings of the terms are the same as those in the above-mentioned distribution network non-stop operation monitoring method based on virtual reality, and the specific implementation details can refer to the description in the method embodiment.

[0130] See also Figure 2 The embodiment of the present application provides a distribution network non-stop operation monitoring system based on virtual reality. The distribution network non-stop operation monitoring system based on virtual reality may specifically include an acquisition module 201, a calculation module 202, a prediction module 203, a determination module 204 and a reminder module 205, which are as follows:

[0131] The acquisition module 201 is used to configure the virtual reality training scene and obtain the real-time action data of the operator;

[0132] A calculation module 202, for calculating the overall matching degree between the actual action and the standard action based on the real-time action data;

[0133] The prediction module 203 is used to identify the operator's combined action data through a pre-built deep learning model to obtain continuous combined actions, and predict corresponding equipment status data based on the continuous combined actions;

[0134] The determination module 204 is used to re-determine the abnormality based on the acquired adjustment action data of the operator after detecting the abnormality of the equipment state based on the equipment state data, and obtain the abnormality determination result;

[0135] The reminder module 205 is used to construct an abnormal action list based on the abnormal determination result, and to perform abnormal reminder after determining a high-frequency abnormal action group according to the abnormal action list.

[0136] Optionally, in some embodiments, the virtual reality-based distribution network non-stop operation monitoring system may further include:

[0137] The statistics module is used to collect real-time dynamic data, equipment status data, equipment status data prediction values ​​and abnormal action lists, and summarize them into operation data;

[0138] The encrypted backup module is used to encrypt the job data and back up the encrypted job data to the cloud server and the local storage database respectively.

[0139] Optionally, in some embodiments, the acquisition module 201 may specifically include:

[0140] A configuration unit, used for configuring a virtual reality training scene. The configuration of the virtual reality training includes a head-mounted display device, a customized virtual operating console, a matching graphic workstation, and a simulated joystick;

[0141] The carrying unit is used to carry virtual reality scenes based on a three-dimensional engine, including the modeling of the working environment, operating tools and scenes in the non-stop operation of the distribution network;

[0142] The acquisition unit is used to acquire the operator's real-time motion data through the motion step device and record it in real time. The real-time motion data includes the three-dimensional trajectory of each motion and the operator's posture angle data.

[0143] Optionally, in some embodiments, the calculation module 202 may specifically include:

[0144] A standard action sequence unit is used to define a standard action trajectory based on the standard operation action of the distribution network without power outage, and to construct a corresponding standard action sequence;

[0145] An actual action sequence unit, used for constructing a corresponding actual action sequence based on real-time action data;

[0146] A calculation unit, used for calculating the Euclidean distance between the actual action and the standard action trajectory based on the actual action sequence and the standard action sequence;

[0147] A minimum cumulative distance unit is used to determine the minimum cumulative distance between the actual action sequence and the standard action sequence based on the Euclidean distance using the dynamic time warping algorithm;

[0148] The matching degree unit is used to determine the overall matching degree between the actual action and the standard action based on the minimum cumulative distance.

[0149] Optionally, in some embodiments, the prediction module 203 may specifically include:

[0150] A matching unit, used to identify and match continuous combined actions and distribution network operation equipment status feedback in a virtual reality environment;

[0151] An alignment unit is used to uniformly collect the collected combined action data and distribution network operation equipment status data, and perform time series alignment processing to generate a corresponding combined data set for each moment;

[0152] A model building unit, used to build a deep learning model, and use a training set to train the deep learning model to obtain a trained deep learning model;

[0153] A recognition unit, used for recognizing the operator's combined action data based on the trained deep learning model to obtain the corresponding continuous combined action;

[0154] The prediction unit is used to perform reasoning based on continuous combined actions through a Bayesian network, calculate the predicted value of the device status data at the corresponding moment, and determine the corresponding device status data.

[0155] Optionally, in some embodiments, the determination module 204 may specifically include:

[0156] An abnormality statistics unit is used to count the operator's adjustment action groups and corresponding abnormality judgment data under abnormality reminders;

[0157] An adjustment unit, configured to generate an abnormal action list based on the adjustment action group in which the abnormal determination occurs again, and calculate the abnormal probability according to the proportion of the occurrence number of the adjustment action group in the total adjustment number;

[0158] The abnormality determination unit is used to calculate the change rate of the abnormality probability between every two abnormal actions based on the abnormality probability of the abnormal action, and generate an abnormality determination result.

[0159] Optionally, in some embodiments, the reminder module 205 may specifically include:

[0160] A determination unit is used only to determine the abnormal actions corresponding to the change rate greater than the average change rate as a high-frequency abnormal action group based on the abnormal determination result;

[0161] A list building unit, used for building a corresponding abnormal action list based on the high-frequency abnormal action group;

[0162] The abnormality reminder unit is used to display corresponding window information according to the abnormal action list based on the virtual reality environment to remind the operator of the abnormality.

[0163] As described above, this embodiment provides a distribution network non-stop operation monitoring system based on virtual reality, wherein the acquisition module 201 configures a virtual reality training scene and acquires the real-time action data of the operator; the calculation module 202 calculates the overall matching degree between the actual action and the standard action based on the real-time action data; the prediction module 203 identifies the operator's combined action data through a pre-built deep learning model, obtains continuous combined actions, and predicts the corresponding equipment status data based on the continuous combined actions; the judgment module 204 re-performs an abnormality judgment based on the acquired operator's adjustment action data after detecting an abnormal equipment status based on the equipment status data, and obtains an abnormal judgment result; the reminder module 205 constructs an abnormal action list based on the abnormal judgment result, and performs an abnormal reminder after determining the high-frequency abnormal action group according to the abnormal action list. In the virtual reality-based distribution network non-stop operation monitoring solution provided in this embodiment, the typical work scenes and operating tools in the 10kV distribution network non-stop operation can be simulated in the VR simulation virtual reality environment. By calculating the Euclidean distance between the actual action and the standard action, the action deviation of the operator when performing the operation in the virtual reality environment can be accurately evaluated. By constructing an LSTM deep learning model to classify the operator's actions and combining it with the Bayesian network, the operator's actions can be matched with the feedback of the equipment status in real time, thereby realizing real-time monitoring of the operator's non-stop operation.

[0164] In addition, the present application also provides a computer device, such as Figure 3 , which shows a schematic diagram of the structure of the computer device involved in the present application. Specifically, the computer device may include one or more processing core processors 301, one or more computer-readable storage media memories 302, a power supply 303, an input unit 304 and other components. Those skilled in the art can understand that Figure 3 The computer device structure shown in the figure does not constitute a limitation on the computer device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:

[0165] The processor 301 is the control center of the computer device. It uses various interfaces and lines to connect various parts of the entire computer device. By running or executing software programs and / or modules stored in the memory 302 and calling data stored in the memory 302, it executes various functions of the computer device and processes data, thereby monitoring the computer device as a whole. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 301.

[0166] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and data processing by running the software programs and modules stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 302 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0167] The computer device also includes a power supply 303 for supplying power to each component. Preferably, the power supply 303 can be logically connected to the processor 301 through a power management system, so that the power management system can manage charging, discharging, and power consumption. The power supply 303 can also include any components such as one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators. The computer device can also include an input unit 304, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0168] Although not shown, the computer device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 301 in the computer device will load the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 will run the application programs stored in the memory 302, thereby realizing various functions, as follows:

[0169] Configure a virtual reality training scenario and obtain the operator's real-time motion data; calculate the overall matching degree between the actual motion and the standard motion based on the real-time motion data; identify the operator's combined motion data through a pre-built deep learning model to obtain continuous combined motions, and predict the corresponding equipment status data based on the continuous combined motions; after detecting an abnormal equipment status based on the equipment status data, re-determine the abnormality based on the obtained operator's adjusted motion data to obtain an abnormality determination result; construct an abnormal motion list based on the abnormal determination result, and issue an abnormal reminder after determining the high-frequency abnormal motion group based on the abnormal motion list.

[0170] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0171] The embodiment of the present application can simulate typical work scenarios and operating tools in 10kV distribution network non-stop operations in a VR simulation virtual reality environment. By calculating the Euclidean distance between the actual action and the standard action, the action deviation of the operator when performing the operation in the virtual reality environment can be accurately evaluated. By constructing an LSTM deep learning model to classify the operator's actions and combining it with the Bayesian network, the operator's actions can be matched with the feedback of the equipment status in real time, thereby realizing real-time monitoring of the operator's non-stop operations.

[0172] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0173] To this end, the present application provides a storage medium in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any one of the methods for monitoring power distribution network non-stop operation based on virtual reality provided in the present application. For example, the instructions can execute the following steps:

[0174] Configure a virtual reality training scenario and obtain the operator's real-time motion data; calculate the overall matching degree between the actual motion and the standard motion based on the real-time motion data; identify the operator's combined motion data through a pre-built deep learning model to obtain continuous combined motions, and predict the corresponding equipment status data based on the continuous combined motions; after detecting an abnormal equipment status based on the equipment status data, re-determine the abnormality based on the obtained operator's adjusted motion data to obtain an abnormality determination result; construct an abnormal motion list based on the abnormal determination result, and issue an abnormal reminder after determining the high-frequency abnormal motion group based on the abnormal motion list.

[0175] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0176] The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0177] Since the instructions stored in the storage medium can execute the steps in any one of the virtual reality-based distribution network non-stop operation monitoring methods provided in the present application, the beneficial effects that can be achieved by any one of the virtual reality-based distribution network non-stop operation monitoring methods provided in the present application can be achieved. For details, please see the previous embodiments and will not be repeated here.

[0178] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above-mentioned various optional implementations.

[0179] The above is a detailed introduction to the distribution network non-stop operation monitoring method, system, computer equipment and storage medium based on virtual reality provided by the present application. This article uses specific examples to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for monitoring non-stop operation of distribution network based on virtual reality, characterized in that: include: Configure virtual reality training scenarios and obtain real-time operator action data; Calculating the overall matching degree between the actual action and the standard action based on the real-time action data; The operator's combined action data is identified by a pre-built deep learning model to obtain continuous combined actions, and corresponding equipment status data is predicted based on the continuous combined actions; After detecting that the equipment state is abnormal based on the equipment state data, re-determine the abnormality based on the acquired adjustment action data of the operator to obtain an abnormality determination result; An abnormal action list is constructed based on the abnormal determination result, and an abnormal reminder is issued after a high-frequency abnormal action group is determined according to the abnormal action list.

2. The method for monitoring power distribution network non-stop operation based on virtual reality according to claim 1 is characterized in that: The method further comprises: Collect the real-time dynamic data, the device status data, the device status data prediction value and the abnormal action list, and summarize them into operation data; The operation data is encrypted and the encrypted operation data is backed up to a cloud server and a local storage database respectively.

3. The method for monitoring power distribution network non-stop operation based on virtual reality according to claim 1 is characterized in that: The configuring of the virtual reality training scene and obtaining the real-time motion data of the operator includes: Configuring the virtual reality training scene, wherein the configuration of the virtual reality training includes a head-mounted display device, a customized virtual operating console, a matching graphics workstation and a simulated joystick; Equipped with a virtual reality scene based on a 3D engine, including the modeling of the working environment, operating tools and scenes in the non-stop operation of the distribution network; The real-time motion data of the operator is acquired and recorded in real time through the motion step device, wherein the real-time motion data includes the three-dimensional trajectory of each motion and the posture angle data of the operator.

4. The method for monitoring power distribution network non-stop operation based on virtual reality according to claim 1 is characterized in that: The calculating the overall matching degree between the actual action and the standard action based on the real-time action data includes: Define standard action trajectories based on standard operating actions for power distribution network without power outages, and construct corresponding standard action sequences; Constructing a corresponding actual action sequence based on the real-time action data; Based on the actual action sequence and the standard action sequence, calculating the Euclidean distance between the actual action trajectory and the standard action trajectory; Determine the minimum cumulative distance between the actual action sequence and the standard action sequence based on the Euclidean distance using a dynamic time warping algorithm; The overall matching degree between the actual action and the standard action is determined based on the minimum cumulative distance.

5. The method for monitoring power distribution network non-stop operation based on virtual reality according to claim 1 is characterized in that: The method of identifying the operator's combined action data by a pre-built deep learning model to obtain continuous combined actions, and predicting corresponding equipment status data based on the continuous combined actions, includes: Identify and match continuous combined actions and distribution network operation equipment status feedback in a virtual reality environment; Based on the collected combined action data and the distribution network operation equipment status data, unified collection is performed, and time series alignment processing is performed to generate a corresponding combined data set for each moment; Constructing a deep learning model, and using a training set to train the deep learning model to obtain a trained deep learning model; Based on the trained deep learning model, the operator's combined action data is identified to obtain the corresponding continuous combined actions; Reasoning is performed based on the continuous combined actions through a Bayesian network to calculate the predicted value of the device status data at the corresponding moment and determine the corresponding device status data.

6. The method for monitoring power distribution network non-stop operation based on virtual reality according to claim 1 is characterized in that: After the abnormality of the equipment state is detected based on the equipment state data, re-determining the abnormality based on the acquired adjustment action data of the operator to obtain the abnormality determination result includes: Statistics of the operator's adjustment action group and corresponding abnormality judgment data under abnormality reminder; Generate an abnormal action list based on the adjustment action group that appears abnormally again, and calculate the abnormal probability according to the proportion of the number of occurrences of the adjustment action group in the total number of adjustments; Based on the abnormal probability of the abnormal action, the change rate of the abnormal probability between every two abnormal actions is calculated to generate the abnormal judgment result.

7. The method for monitoring power distribution network non-stop operation based on virtual reality according to claim 1 is characterized in that: The step of constructing an abnormal action list based on the abnormal determination result, and performing an abnormal reminder after determining a high-frequency abnormal action group according to the abnormal action list, includes: Based on the abnormal determination result, the abnormal actions corresponding to the change rate greater than the average change rate are determined as a high-frequency abnormal action group; Constructing a corresponding abnormal action list based on the high-frequency abnormal action group; Based on the virtual reality environment, the corresponding window information is displayed according to the abnormal action list to remind the operator of the abnormality.

8. A distribution network non-stop operation monitoring system based on virtual reality, characterized in that: include: The acquisition module is used to configure the virtual reality training scene and obtain the operator's real-time action data; A calculation module, used for calculating the overall matching degree between the actual action and the standard action based on the real-time action data; A prediction module, used to identify the operator's combined action data through a pre-built deep learning model, obtain continuous combined actions, and predict corresponding equipment status data based on the continuous combined actions; A determination module, configured to, after detecting that the equipment state is abnormal based on the equipment state data, re-determine the abnormality based on the acquired adjustment action data of the operator to obtain an abnormality determination result; The reminder module is used to construct an abnormal action list based on the abnormal determination result, and to perform abnormal reminder after determining a high-frequency abnormal action group according to the abnormal action list.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method for monitoring power distribution network non-stop operations based on virtual reality as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for monitoring power distribution network non-stop operation based on virtual reality as claimed in any one of claims 1 to 7 are implemented.

Images