A digital twin visualization data processing system for smart parks

Abstract

The present invention discloses a digital twin visualization data processing system for a smart park, which relates to the technical field of equipment data processing. A digital twin model of power equipment operation is generated from power equipment related data, abnormalities are identified for the operation data of the power equipment, and a fault prediction instruction is issued to the outside when the number of abnormal values ​​exceeds expectations; the digital twin model of power equipment operation is used to predict the faults of the power equipment, and a first-level alarm instruction is issued to the outside after automatically generating a fault log; a warning value is generated from the receiving status data of the first-level alarm instruction, and the faulty equipment is screened out from a number of devices according to the warning value, and a maintenance path is planned for the faulty equipment in the park, and the environmental condition data and operation status data of the faulty equipment are visualized. By issuing alarm instructions at multiple levels, the resolution rate of the operation faults of the power equipment is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment data processing, and specifically to a smart park digital twin visualization data processing system. Background Art

[0002] Smart industrial parks are an important part of the smart cities advocated by the country. They use the Internet of Things, network communications and information technology to sense, analyze, integrate and intelligently respond to key information in the park. From the perspective of equipment, smart industrial parks are a comprehensive ecosystem that integrates advanced sensors, intelligent control systems, automated production lines and big data analysis platforms. These devices not only realize the automation and intelligence of production processes, but also optimize energy use and predict maintenance needs through real-time data monitoring and analysis, ensuring the efficiency, safety and environmental protection of park operations, and jointly promote the development of parks in a more intelligent and sustainable direction.

[0003] In the Chinese invention patent with application publication number CN109598308A, a data processing platform and method for automatically judging equipment failure is provided, including: collecting and analyzing the long-term operation data of the same type of equipment under similar conditions to establish a sample database; collecting data of on-site equipment and comparing it with the sample database, and when parameters that meet the fault judgment criteria of the sample database appear, calling up the on-site monitoring pictures of the corresponding equipment; diagnosing and identifying the status information of the equipment through image recognition technology, comprehensively judging the possibility of equipment failure, and performing early warning or alarm processing according to different levels. Effectively make scientific and accurate predictions on whether the equipment will fail, and perform early warning and alarm processing on equipment information with a high probability of failure.

[0004] Combined with the above application and the contents of the prior art:

[0005] When many devices in the industrial park, especially power equipment, are in operation, in order to ensure the normal operation of the industrial park, it is necessary to monitor the operating status of each device in real time. At the same time, in order to improve the monitoring effect of the equipment, the various operating data of the equipment are usually displayed visually, so as to facilitate the prediction of the operating trend of equipment, such as power equipment, and timely discover possible operating abnormalities.

[0006] In the existing park equipment data processing methods, when processing equipment-related data, they usually focus on data trend analysis and abnormal data detection, which helps to schedule various equipment in the production process and reduce the operating load of the equipment. However, it is limited by the production status in the industrial park. For example, the concentration of particulate matter in the industrial park is high and the humidity is high. Especially when the equipment has entered a high-load operating state, the risk of equipment operating failure will gradually increase. When processing existing equipment data, there is a lack of equipment fault analysis. When the equipment is in an abnormal state during operation, it is difficult to process quickly, and the processing efficiency of abnormal behavior is low.

[0007] To this end, the present invention provides a smart park digital twin visualization data processing system. Summary of the invention

[0008] In view of the deficiencies of the prior art, the present invention provides a digital twin visualization data processing system for a smart park. By generating a digital twin model of power equipment operation from the relevant data of the power equipment, the operation data of the power equipment is identified for abnormalities, and a fault prediction instruction is issued to the outside when the number of abnormal values ​​exceeds expectations; the digital twin model of power equipment operation is used to predict the faults of the power equipment, and a first-level alarm instruction is issued to the outside after automatically generating a fault log; a warning value is generated from the receiving status data of the first-level alarm instruction, and the faulty equipment is screened out from a number of devices based on the warning value, and a maintenance path is planned for the faulty equipment in the park, and the environmental condition data and operation status data of the faulty equipment are visualized. By issuing alarm instructions at multiple levels, the resolution rate of the operation faults of the power equipment is improved. Thereby, the technical problems recorded in the background technology are solved.

[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0010] A method for processing visualized data of a digital twin of a smart park, comprising: after collecting operating condition data of power equipment, generating an abnormality of the operating environment condition from the operating environment status data, and issuing a data collection instruction to the outside when the abnormality exceeds an abnormal threshold;

[0011] Generate a digital twin model of power equipment operation from relevant data of power equipment, identify anomalies in the operation data of power equipment, and issue fault prediction instructions to the outside when the number of abnormal values ​​exceeds expectations;

[0012] Use the digital twin model of power equipment to predict power equipment failures, and generate risk values ​​from the predicted data. If the risk value does not exceed the risk threshold, a fault log is automatically generated and a first-level alarm instruction is issued to the outside.

[0013] The warning value is generated by the receiving status data of the first-level alarm command. The faulty equipment is screened out from a number of devices based on the warning value, and the maintenance path is planned for the faulty equipment in the park. The environmental condition data and operating status data of the faulty equipment are visualized.

[0014] Furthermore, a sensor network is set up in the operating area of ​​the power equipment, and the sensor network collects and monitors environmental condition data in the operating area, including at least particulate matter concentration, humidity and power equipment operating load, and summarizes and generates a set of operating environment status data of the power equipment.

[0015] Further, after receiving the data collection instruction, relevant data of each power equipment in the industrial park is collected;

[0016] The machine learning algorithm is trained with the power equipment data to generate a digital twin model of the power equipment operation, which is updated with real-time data.

[0017] Furthermore, after monitoring and collecting the operating data of the power equipment within a preset detection period, an operating data set of the power equipment is summarized and generated; the operating data in the operating data set of the power equipment is used as input, and abnormal data recognition is performed by a trained abnormal data recognition model.

[0018] Further, after receiving the fault prediction instruction, the operation data and environmental data of the power equipment are used as input, and the power equipment operation digital twin model is used to predict the fault of the power equipment;

[0019] If the power equipment will have an operational failure, data dimension reduction and feature extraction will be performed on the operating data and environmental data to identify the influencing factors and their degree of influence on the power equipment operational failure, and monitor and collect real-time data values ​​of the influencing factors.

[0020] Furthermore, the corresponding impact degree is taken as the impact value. Under dimensionless conditions, the risk value is constructed based on the relationship between the real-time data value and the qualified threshold value and the impact value. , as follows:

[0021] Where: It is Factors affecting time Real-time data value, It is The influence value of each influencing factor, For the The qualified threshold of each influencing factor; is the total number of influencing factors, is the monitoring interval; weight coefficient, ， , .

[0022] Furthermore, if the number of first-level alarm instructions received during the preset fault maintenance cycle exceeds expectations, the time node at which the first-level alarm instruction is received is used as the alarm node, and the proportion of each risk value exceeding the risk threshold is used as the risk ratio;

[0023] The warning value is generated according to the distribution status and risk ratio of the alarm nodes; if the warning value exceeds the warning threshold, the corresponding power equipment will be regarded as a faulty equipment and a secondary alarm command will be issued to the outside.

[0024] Furthermore, after receiving the second-level alarm instruction, the faulty equipment is marked on the electronic map, and the risk value of the power equipment and the abnormality of the environment when the first-level alarm instruction is issued are recorded, thereby generating the priority of the maintenance of the faulty equipment;

[0025] According to the changes in equipment operating status and environmental condition data, the maintenance priority of faulty equipment is adjusted in real time.

[0026] Furthermore, after obtaining the location information, maintenance priority, and estimated maintenance time of each faulty device, the time window constraint is set according to the device operation time, and the pre-trained ant colony algorithm is used to solve the optimal maintenance path for the faulty device;

[0027] The optimal maintenance path obtained is marked on the electronic map and used as the maintenance sequence to visualize the environmental condition data and operating status data of the faulty equipment.

[0028] A smart park digital twin visualization data processing system, comprising:

[0029] The abnormal condition analysis unit collects the operating condition data of the power equipment, generates the abnormality of the operating environment condition from the operating environment status data, and sends a data collection instruction to the outside when the abnormality exceeds the abnormal threshold;

[0030] The model generation unit generates a digital twin model of the power equipment operation from the relevant data of the power equipment, identifies anomalies in the operation data of the power equipment, and issues a fault prediction instruction to the outside when the number of abnormal values ​​exceeds expectations;

[0031] The equipment fault prediction unit uses the digital twin model of power equipment operation to predict the faults of power equipment, and generates a risk value from the predicted data. If the risk value does not exceed the risk threshold, a fault log is automatically generated and a first-level alarm instruction is issued to the outside.

[0032] The maintenance unit generates an alert value from the receiving status data of the first-level alarm command, selects the faulty equipment from a number of devices based on the alert value, plans maintenance paths for the faulty equipment in the park, and visualizes the environmental condition data and operating status data of the faulty equipment.

[0033] The present invention provides a smart park digital twin visualization data processing system, which has the following beneficial effects:

[0034] 1. Judge whether there is any abnormality in the current operating conditions of the power equipment based on the degree of abnormality. If there is an abnormality and the abnormal state continues, monitor and adjust the abnormal operating conditions in real time to ensure the safety of the power equipment.

[0035] 2. Based on the digital twin model of power equipment operation, the real-time status of the power equipment can be monitored and observed, and early warning can be achieved when the operating conditions of the power equipment are abnormal.

[0036] 3. Based on the number and degree of abnormal values, the abnormality of the operation of the power equipment can be judged to verify whether there is any abnormality in the power equipment. If the power equipment may have abnormal operation, it can be processed.

[0037] 4. Through principal component analysis and feature extraction, the main factors that increase the risk of power equipment failure are determined, and the main influencing factors are adjusted and controlled in a targeted manner to reduce the possibility of actual operational failures. The main influencing factors are visualized to display the operational risks that power equipment may face.

[0038] 5. If the power equipment has entered a fault state, based on the determination of the main influencing factors, by generating a fault log, the maintenance can be more targeted and the operating status of the power equipment can be improved.

[0039] 6. The current fault degree of the power equipment can be further evaluated based on the warning value. By treating the power equipment with operating faults as faulty equipment, multi-level alarm for the operating status of the power equipment can be implemented. When the power equipment operates abnormally or fails, alarm instructions are issued at multiple levels to improve the resolution rate of operating faults of the power equipment.

[0040] 7. Generate the maintenance priority of faulty equipment based on risk value and abnormality, and obtain the maintenance path of power equipment in real time. If there are many faulty equipment in the industrial park, the overall maintenance efficiency can be improved based on the visualization of various data. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a flow chart of the visualization data processing method of the digital twin of a smart park of the present invention;

[0042] Figure 2 This is a schematic diagram of the structure of the digital twin visualization data processing system for the smart park of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] See also Figure 1 The present invention provides a method for processing visualization data of a digital twin of a smart park, comprising:

[0045] Step 1: After collecting the operating condition data of the power equipment, the abnormality of the operating environment condition is generated from the operating environment status data, and when the abnormality exceeds the abnormal threshold, a data collection instruction is issued to the outside;

[0046] The step 1 includes the following contents:

[0047] Step 101: construct an electronic map covering the industrial park, and mark the power equipment in the park on the electronic map;

[0048] A sensor network is set up in the operating area of ​​the power equipment, such as an air humidity sensor, a temperature sensor, and an air quality sensor, etc. The sensor network collects and monitors environmental condition data in the operating area, such as measuring the concentration of particulate matter in the air, temperature and humidity data, etc., and obtains the operating data and load data of the power equipment, and aggregates the above data to generate a set of operating environment status data of the power equipment;

[0049] Step 102: Generate the abnormality of the operating environment condition from the relevant data in the operating environment status data set, wherein the particle concentration ,humidity and operating load Perform linear normalization and map the corresponding data values ​​to the interval According to the following formula:

[0050] in, , , Monitor nodes separately particle concentration, humidity and operating load on the , and are qualified reference values ​​for particulate matter concentration, humidity and operating load, respectively. , and are the standard deviations of particle concentration, humidity and operating load, respectively; , , is the weight coefficient, which can be obtained by referring to the hierarchical analysis method. ， , , the weight coefficient can be obtained by referring to the hierarchical analysis method, , is the number of monitoring nodes;

[0051] Pre-set abnormal thresholds based on historical data and management expectations for power equipment operation;

[0052] If the abnormality exceeds the abnormality threshold, it means that the current operating state and operating environment may have a greater impact and interference on the operation of the power equipment, which greatly increases the risk of operating failures of the power equipment during operation. It is necessary to monitor and collect various operating data of the power equipment in real time. At this time, a data collection instruction is issued to the outside;

[0053] When using, combine the contents in steps 101 and 102:

[0054] When power equipment or other types of equipment are in continuous operation, the environmental conditions and real-time operating status of the power equipment are monitored and the degree of abnormality is established. Based on the degree of abnormality, it is judged whether there is any abnormality in the current operating conditions of the power equipment. If there is an abnormality and the abnormal state continues, the equipment in the industrial park, especially the power equipment, will have a greater risk of failure and hidden dangers. If such abnormal operating conditions are monitored and adjusted in real time, the safety of the power equipment can be guaranteed.

[0055] In the existing park equipment data processing methods, when processing equipment-related data, they usually focus on data trend analysis and abnormal data detection, which helps to schedule various equipment in the production process and reduce the operating load of the equipment. However, it is limited by the production status in the industrial park. For example, the concentration of particulate matter in the industrial park is high and the humidity is high. Especially when the equipment has entered a high-load operating state, the risk of equipment operating failure will gradually increase. When processing existing equipment data, there is a lack of equipment fault analysis. When the equipment is in an abnormal state during operation, it is difficult to process quickly, and the processing efficiency of abnormal behavior is low.

[0056] Step 2: Generate a digital twin model of power equipment operation from the relevant data of the power equipment, identify anomalies in the operation data of the power equipment, and issue a fault prediction instruction to the outside when the number of abnormal values ​​exceeds expectations;

[0057] The step 2 includes the following contents

[0058] Step 201: after receiving the data collection instruction, collect the specification data, structure data, performance data and operation data of each power equipment in the industrial park, and summarize and generate a data set related to the power equipment;

[0059] The machine learning algorithm is trained with the power equipment data in the power equipment related data set to generate a digital twin model of the power equipment operation, and the digital twin model is updated with real-time data;

[0060] When in use, a digital twin model of power equipment operation is constructed based on the collection and acquisition of various data. The real-time status of the power equipment can be monitored and observed based on the digital twin model of power equipment operation, and early warning can be achieved when the operating conditions of the power equipment are abnormal;

[0061] Step 202: After monitoring and collecting the operating data of the power equipment such as temperature, current, voltage, etc. within a preset detection period, aggregating and generating a set of operating data of the power equipment;

[0062] The convolutional neural network is trained with the labeled sample data to obtain a trained abnormal data recognition model;

[0063] Taking the operation data in the power equipment operation data set as input, the trained abnormal data recognition model performs abnormal data recognition. If the number of abnormal values ​​in the operation data exceeds the expected number, it indicates that the operation status of the power equipment may be abnormal. At this time, a fault prediction instruction is issued to the outside.

[0064] When using, combine the contents in steps 201 and 202:

[0065] By identifying anomalies in the operating data of the power equipment and obtaining corresponding abnormal values, the abnormality of the power equipment operation can be judged based on the number and degree of abnormal values, and it can be verified whether the power equipment has abnormalities. If the power equipment may have operating abnormalities, it can be processed.

[0066] Step 3: Use the digital twin model of power equipment to predict faults of power equipment, and generate a risk value based on the predicted data. If the risk value does not exceed the risk threshold, a fault log is automatically generated and a first-level alarm instruction is issued to the outside.

[0067] The step three includes the following contents:

[0068] Step 301: After receiving the fault prediction instruction, the operation data and environmental data of the power equipment are used as input, and the power equipment operation digital twin model is used to predict the fault of the power equipment. If the power equipment will have an operation fault, a feature extraction instruction is issued to the outside;

[0069] Step 302: After receiving the feature extraction instruction, based on the historical data, the operating data and environmental data are subjected to data dimension reduction and feature extraction by using the PCA principal component analysis method to identify the influencing factors and their degree of influence on the operating failure of the power equipment;

[0070] Monitor and collect real-time data values ​​of influencing factors, and visualize the influencing factors based on the changing trends of the real-time data values ​​of the influencing factors;

[0071] When in use, when there may be operational failures in power equipment, taking into account the need to deal with abnormal failures, principal component analysis and feature extraction are performed to determine the main factors that increase the risk of power equipment failure. After determining the main influencing factors, targeted adjustments and controls are performed on the main influencing factors to reduce the possibility of actual operational failures. At the same time, data visualization of the main influencing factors can also display the operational risks that the power equipment may face.

[0072] Step 303: After real-time monitoring of the real-time data values ​​of various influencing factors of the power equipment, determine the corresponding qualified threshold for each influencing factor, take the corresponding impact degree as the impact value, and construct the risk value based on the relationship between the real-time data value and the qualified threshold and the impact value. , as follows:

[0073] Where: It is Factors affecting time Real-time data value, It is The influence value of each influencing factor, For the The qualified threshold of each influencing factor; is the total number of influencing factors, is the monitoring interval; weight coefficient, ， , ;

[0074] Pre-set risk thresholds based on historical data and expectations for the operation status management of power equipment;

[0075] If the risk value If the risk threshold is not exceeded, it means that the power equipment is in an unsafe state under the influence of the current environmental conditions and operating load. At this time, the abnormal time of the power equipment, various operating parameter values, environmental data and equipment status, etc. are recorded, and a fault log is automatically generated, and a first-level alarm instruction is issued to the outside;

[0076] When using, combine the contents in steps 301 to 303:

[0077] When multiple operating parameters of the power equipment have abnormalities, the risk value is constructed according to the degree of abnormality , analyze and judge the safety of power equipment operation based on the risk value. If it is judged that the power equipment has entered a fault state, on the basis of determining the main influencing factors, by generating a fault log, the maintenance can be more targeted and the operating status of the power equipment can be improved.

[0078] Step 4: Generate an alert value from the received status data of the first-level alarm command, select the faulty equipment from a number of equipment based on the alert value, plan a maintenance path for the faulty equipment in the park, and visualize the environmental condition data and operating status data of the faulty equipment;

[0079] The step 4 includes the following contents:

[0080] Step 401: If the number of first-level alarm instructions received during the preset fault maintenance cycle exceeds the expected number, the time node of receiving the first-level alarm instruction is used as the alarm node, and the risk value of each time is used as the alarm node. The proportion exceeding the risk threshold was taken as the risk ratio;

[0081] Under dimensionless conditions, the warning value is generated according to the distribution status and risk ratio of the alarm nodes. , as follows:

[0082] Where: is the monitoring interval; is the risk threshold, The value can be 2.718, is the time attenuation coefficient, ranging from 0 to 1. is the distance attenuation coefficient, ranging from 0.01 to 0.1; For the time No. Alarm nodes, For the and The time interval between alarm nodes, is the number of alarm nodes, For the The risk ratio at each alarm node;

[0083] Pre-set warning thresholds based on historical data and expected management of the operating status of power equipment;

[0084] If the warning value exceeds the warning threshold, it means that the current operation failure of the power equipment may be further deepened and there is a risk of stopping operation. At this time, the corresponding power equipment is regarded as a faulty device and a secondary alarm instruction is issued to the outside;

[0085] When in use, a warning value is constructed based on the first-level alarm instruction for the power equipment. The current fault degree of the power equipment can be further evaluated based on the warning value. By treating the power equipment with operating faults as faulty equipment, multi-level alarms for the operating status of the power equipment can be achieved. Therefore, when the power equipment operates abnormally or fails, alarm instructions can be issued at multiple levels and levels, which can improve the resolution rate of operating faults of the power equipment.

[0086] Step 402: After receiving the second-level alarm instruction, mark the faulty equipment on the electronic map, and record the risk value of the power equipment when issuing the first-level alarm instruction and the abnormality of the environment. Under dimensionless conditions, the risk value and abnormality Generate the maintenance priority of the faulty equipment as follows:

[0087] Weight coefficient: , ,and ; can refer to the analytical method to obtain;

[0088] According to the changes in equipment operating status and environmental condition data, the maintenance priority of faulty equipment can be adjusted in real time;

[0089] Step 403: After obtaining the location information, maintenance priority, and estimated maintenance time of each faulty device, a time window constraint is set according to the device operation time, and a pre-trained ant colony algorithm is used to solve the optimal maintenance path for the faulty device;

[0090] The optimal maintenance path is marked on the electronic map and used as the maintenance sequence to visualize the environmental condition data and operating status data of the faulty equipment.

[0091] When used, combine the contents in steps 401 to 403:

[0092] When it is determined that maintenance is required for faulty power equipment, the fault type and the main factors causing the fault have been determined, and the priority of faulty equipment maintenance is generated based on the risk value and abnormality, and the maintenance path of the power equipment is obtained in real time. If there are many faulty equipment in the industrial park, the overall maintenance efficiency can be improved based on the visualization of various data.

[0093] The Analytic Hierarchy Process (AHP) is a decision-making method that decomposes decision-related elements into levels such as goals, criteria, and plans, and conducts qualitative and quantitative analysis on this basis. It is particularly suitable for dealing with target systems with hierarchical and staggered evaluation indicators, and when the target value is difficult to describe quantitatively, the AHP is an effective decision-making tool.

[0094] The core of the hierarchical analysis method is to decompose the decision problem into multiple levels to form a hierarchical structure, which usually includes the target level, the criterion level, the sub-criterion level and the solution level. By solving the eigenvector of the judgment matrix, the priority weight of each element of each level to an element of the previous level is obtained, and the final weight of each alternative solution to the total goal is recursively merged by the weighted sum method, so as to find the optimal solution.

[0095] See also Figure 2 The present invention provides a smart park digital twin visualization data processing system, comprising:

[0096] The abnormal condition analysis unit collects the operating condition data of the power equipment, generates the abnormality of the operating environment condition from the operating environment status data, and sends a data collection instruction to the outside when the abnormality exceeds the abnormal threshold;

[0097] The model generation unit generates a digital twin model of the power equipment operation from the relevant data of the power equipment, identifies anomalies in the operation data of the power equipment, and issues a fault prediction instruction to the outside when the number of abnormal values ​​exceeds expectations;

[0098] The equipment fault prediction unit uses the digital twin model of power equipment operation to predict the faults of power equipment, and generates a risk value from the predicted data. If the risk value does not exceed the risk threshold, a fault log is automatically generated and a first-level alarm instruction is issued to the outside.

[0099] The maintenance unit generates an alert value from the receiving status data of the first-level alarm command, selects the faulty equipment from a number of devices based on the alert value, plans maintenance paths for the faulty equipment in the park, and visualizes the environmental condition data and operating status data of the faulty equipment.

[0100] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0101] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0102] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0103] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0104] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A digital twin visualization data processing system for a smart park, characterized by: include, The abnormal condition analysis unit collects the operating condition data of the power equipment and generates the abnormal degree of the operating environment condition from the operating environment status data. , when the abnormality exceeds the abnormal threshold, it sends a data collection instruction to the outside; among them, the particle concentration ,humidity and operating load Perform linear normalization and map the corresponding data values ​​to the interval The abnormality is generated according to the following formula : in, , , Monitor nodes separately particle concentration, humidity and operating load on the , and are qualified reference values ​​for particulate matter concentration, humidity and operating load, respectively. , and are the standard deviations of particle concentration, humidity and operating load, respectively; , , is the weight coefficient, ， , , , is the number of monitoring nodes; The model generation unit generates a digital twin model of the power equipment operation from the relevant data of the power equipment, identifies anomalies in the operation data of the power equipment, and issues a fault prediction instruction to the outside when the number of abnormal values ​​exceeds expectations; The equipment failure prediction unit uses the digital twin model of power equipment operation to predict the failure of power equipment and generates risk values ​​from the prediction data If the risk value exceeds the risk threshold, a fault log will be automatically generated and a first-level alarm command will be issued to the outside; Among them, the corresponding qualified threshold is determined for each influencing factor, and the corresponding influence degree of the influencing factor is used as the influence value. Under dimensionless conditions, the risk value is constructed based on the relationship between the real-time data value and the qualified threshold and the influence value. , as follows: Where: It is Factors affecting time Real-time data value, It is The influence value of each influencing factor, For the The qualified threshold of each influencing factor; is the total number of influencing factors, is the monitoring interval; weight coefficient, ， , ; The maintenance unit generates an alert value from the received status data of the first-level alarm command, selects the faulty equipment from a number of devices based on the alert value, plans maintenance paths for the faulty equipment in the park, and visualizes the environmental condition data and operating status data of the faulty equipment. If the number of first-level alarm instructions received during the preset fault maintenance cycle exceeds the expected number, the time node when the first-level alarm instruction is received will be used as the alarm node, and the risk value will be used as the alarm node. The proportion exceeding the risk threshold is used as the risk ratio; the warning value is generated based on the distribution status of the alarm node and the risk ratio. , as follows: Where: is the monitoring interval; is the risk threshold, The value is 2.718, is the time attenuation coefficient, ranging from 0 to 1. is the distance attenuation coefficient, ranging from 0.01 to 0.1; For the time No. Alarm nodes, For the and The time interval between alarm nodes, is the number of alarm nodes, For the The risk ratio at each alarm node; If the number of first-level alarm instructions received during the preset fault maintenance cycle exceeds the expected number, the time node of receiving the first-level alarm instruction will be used as the alarm node, and the proportion of each risk value exceeding the risk threshold will be used as the risk ratio; Generate warning values ​​based on the distribution status and risk ratio of alarm nodes; if the warning value exceeds the warning threshold, the corresponding power equipment will be regarded as a faulty equipment and a secondary alarm command will be issued to the outside; After receiving the second-level alarm command, mark the faulty equipment on the electronic map and record the risk value of the power equipment and the abnormality of the environment when issuing the first-level alarm command. , and then generate the maintenance priority of the faulty equipment; According to the changes in the equipment operating status and environmental conditions data, the priority of maintenance of faulty equipment is adjusted in real time, among which the risk value and abnormality Generate the maintenance priority of the faulty equipment as follows: Weight coefficient: , ,and .

2. According to claim 1, a smart park digital twin visualization data processing system is characterized by: A sensor network is set up in the operating area of ​​the power equipment, and the sensor network collects and monitors environmental condition data in the operating area, including at least particulate matter concentration, humidity and power equipment operating load, and summarizes and generates a set of operating environment status data of the power equipment.

3. According to claim 2, a smart park digital twin visualization data processing system is characterized by: After receiving the data collection instruction, the relevant data of each power equipment in the industrial park are collected; the machine learning algorithm is trained with the power equipment data to generate a digital twin model of the power equipment operation, and it is updated with real-time data.

4. According to claim 3, a smart park digital twin visualization data processing system is characterized by: After monitoring and collecting the operating data of the power equipment within a preset detection period, the operating data set of the power equipment is summarized and generated; the operating data in the operating data set of the power equipment is used as input, and abnormal data is identified by the trained abnormal data identification model.

5. According to claim 4, a smart park digital twin visualization data processing system is characterized by: After receiving the fault prediction instruction, the power equipment operation data and environmental data are used as input, and the power equipment operation digital twin model is used to predict the fault of the power equipment; If the power equipment will have an operational failure, data dimension reduction and feature extraction will be performed on the operating data and environmental data to identify the influencing factors and their degree of influence on the power equipment operational failure, and monitor and collect real-time data values ​​of the influencing factors.

6. The smart park digital twin visualization data processing system according to claim 5 is characterized by: After obtaining the location information, maintenance priority, and estimated maintenance time of each faulty device, the time window constraint is set according to the device operation time, and the pre-trained ant colony algorithm is used to solve the optimal maintenance path for the faulty device; The optimal maintenance path obtained is marked on the electronic map and used as the maintenance sequence to visualize the environmental condition data and operating status data of the faulty equipment.

Images