Multi-dimensional intelligent adjusting system and method applied to power equipment

Abstract

The invention discloses a multi-dimensional intelligent adjustment system and method applied to power equipment, and relates to the technical field of power equipment inspection, and the method comprises the steps: generating an equipment performance value of the power equipment through obtained performance data, and predicting the operation state of the power equipment if the correlation between an environment risk value and the equipment performance value exceeds the expectation; the health state of the power equipment is evaluated according to the prediction data, and if the power equipment is in an unhealthy state, a multi-level alarm instruction is sent to the outside according to the unhealthy degree; planning and acquiring a routing inspection path for the power equipment in the industrial park so as to perform routing inspection on each abnormal equipment, and verifying the abnormity of the power equipment according to the acquired routing inspection data; and after the trained parameter control model is used for automatically controlling the abnormal equipment, a maintenance scheme is output for the abnormal equipment. When the abnormal equipment is maintained according to the inspection path obtained through planning, the abnormal equipment which is poor in health degree and frequently abnormal is maintained preferentially.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment inspection, and in particular to a multi-dimensional intelligent regulation system and method applied to power equipment. Background Art

[0002] Power equipment inspection is an indispensable part of power system maintenance. It involves regular and systematic inspection, monitoring and maintenance of power plants, substations, transmission lines and various types of power equipment. It aims to timely discover and eliminate potential fault hazards through appearance inspection, performance testing, operation status monitoring and surrounding environment assessment, ensure the safe and stable operation of power equipment, thereby optimizing equipment management, reducing maintenance costs, and improving the overall quality and reliability of power supply.

[0003] In the Chinese invention patent with application publication number CN118472838A, a method, system and inspection execution terminal for power equipment inspection based on drones are disclosed. The power inspection server obtains power inspection information, determines the target power equipment according to the power inspection information, and starts the drone parameter definition module of the inspection execution terminal; the inspection execution terminal controls the power inspection drone to perform the inspection operation based on the power inspection information and the target power equipment; the power inspection drone sends the inspection process information to the inspection execution terminal, so that the inspection execution terminal feeds back the inspection process information to the power inspection server. The present invention realizes an automatic inspection process, can perform inspections according to pre-set inspection information, meet the inspection process requirements, and can also adjust the inspection process in real time to ensure the stable operation of the power network and power equipment.

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

[0005] When the power equipment in the industrial park is in operation, in order to ensure that the production process in the industrial park can be carried out normally, it is necessary to monitor the operating status of the power equipment in real time to ensure that the industrial park does not enter a power outage state. In order to further ensure that there is no power outage in the industrial park, it is usually necessary to conduct regular inspections of the power equipment.

[0006] In the existing inspection method of power equipment, regular inspections are usually carried out on all power equipment in the industrial park. This inspection method has a wide coverage, but in fact, when the industrial park is in production, a large amount of polluting gas will be discharged to the outside, and the power equipment may be in a salt spray environment. If the power equipment is in this scenario for a long time, some of its components may be due to corrosion or similar reasons, resulting in a significant decline in performance. Therefore, in this scenario, if a comprehensive inspection mechanism is still carried out on the power equipment, when time is limited, it may lead to low inspection efficiency, and may also cause some abnormal power equipment to be neglected, and fail to effectively ensure the operation of the power equipment.

[0007] To this end, the present invention provides a multi-dimensional intelligent regulation system and method applied to power equipment. Summary of the invention

[0008] 1. Technical issues to be resolved

[0009] In view of the deficiencies of the prior art, the present invention provides a multi-dimensional intelligent regulation system and method for power equipment, which predicts the operating status of the power equipment; evaluates the health status of the power equipment based on the predicted data, and if the power equipment is in an unhealthy state, issues a multi-level alarm instruction to the outside according to the degree of unhealthiness; plans and obtains the inspection path for the power equipment in the industrial park, thereby inspecting each abnormal equipment, and verifies the abnormality of the power equipment based on the obtained inspection data; uses the trained parameter control model to automatically control the abnormal equipment, and outputs a maintenance plan for the abnormal equipment. When maintaining the abnormal equipment according to the inspection path obtained by the plan, priority maintenance is given to abnormal equipment with poor health and frequent abnormalities, thereby solving the technical problems recorded in the background technology.

[0010] (II) Technical solution

[0011] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0012] The multi-dimensional intelligent adjustment method applied to power equipment includes: monitoring air quality data in the industrial park, generating environmental risk values ​​from the air quality data, and issuing fault monitoring instructions to the outside if the environmental risk value exceeds expectations;

[0013] Monitor the operating performance of power equipment in real time, generate equipment performance values ​​of power equipment from the acquired performance data, and if the correlation between the environmental risk value and the equipment performance value exceeds expectations, predict the operating status of the power equipment and obtain corresponding prediction data;

[0014] Evaluate the health status of power equipment based on prediction data. If the power equipment is in an unhealthy state, issue multi-level alarm instructions to the outside according to the degree of unhealthiness.

[0015] Plan and obtain inspection routes for power equipment in the industrial park, inspect each abnormal device, and verify power equipment anomalies based on the inspection data obtained;

[0016] After using the trained parameter control model to automatically control the abnormal equipment, the power equipment maintenance knowledge graph outputs a maintenance plan for the abnormal equipment.

[0017] Furthermore, the sensor network collects air quality data in the industrial park and aggregates them into an air quality data set. The air quality data is used as input and the trained environmental risk identification model is used to identify the environmental risks faced by power equipment. If there is an environmental risk, an environmental risk value is generated from the air quality data set.

[0018] Furthermore, after receiving the fault monitoring instruction, performance monitoring is performed on each power equipment in the industrial park, and the performance data of the equipment is collected in real time. The acquired equipment performance data is aggregated to generate a performance data set, and the equipment performance value of the power equipment is generated from the performance data set.

[0019] Further, a correlation analysis is performed between the environmental risk value and the equipment performance value and a corresponding correlation coefficient is obtained. If the correlation coefficient exceeds a preset correlation threshold;

[0020] The trained operating status prediction model is used to predict the operating parameters of the power equipment, obtain the corresponding prediction data, and summarize and generate a set of operating status prediction data for the power equipment.

[0021] Furthermore, the predicted number of the power equipment operation status is used as input, and the trained equipment operation status recognition model is used to perform a health assessment on the operation status of the power equipment to obtain a corresponding health score;

[0022] If the health score of the power equipment is lower than the health threshold, the corresponding power equipment will be treated as an abnormal device and a first-level alarm instruction will be issued to the outside.

[0023] Furthermore, if the number of first-level alarm instructions received continuously within a preset observation period exceeds expectations, a warning value is constructed based on the difference between the device health score and the health threshold, and the distribution status of the time nodes at which the first-level alarm instructions are received: if the warning value exceeds the warning threshold, a second-level alarm instruction is issued to the outside.

[0024] Further, after receiving the second-level alarm instruction, the abnormal power equipment is marked on the electronic map;

[0025] Based on the location information and health score of abnormal equipment, the pre-trained path planning algorithm plans and obtains the inspection path within the industrial park; the inspection path is marked on the electronic map, and the inspection route is adjusted dynamically according to the update of abnormal equipment.

[0026] Furthermore, the inspection equipment conducts inspections in the industrial park according to the generated inspection path, collects appearance images, thermal imaging data and operation data of abnormal equipment in real time, and summarizes the collected data as inspection data to generate an equipment inspection data set; the collected inspection data is used as input, and the trained anomaly recognition model is used to perform anomaly recognition on the inspection data; if the abnormal equipment still has an abnormality, the corresponding abnormal features are extracted, and an abnormal reminder instruction is issued to the outside.

[0027] Furthermore, after receiving the abnormal reminder instruction, the abnormal equipment is automatically controlled using the trained parameter control model with the operation data of the abnormal equipment as input; the power equipment maintenance is used as the target word, and the power equipment maintenance knowledge graph is pre-set;

[0028] Before performing maintenance on abnormal equipment, an equipment operation report is generated, which at least includes a maintenance plan, a health status index and predicted operation data for the abnormal equipment.

[0029] The multi-dimensional intelligent regulation system applied to power equipment includes an environmental risk analysis unit, which monitors air quality data in the industrial park and generates environmental risk values ​​from the air quality data. If the environmental risk value exceeds expectations, a fault monitoring instruction is issued to the outside.

[0030] The equipment performance analysis unit monitors the operating performance of the power equipment in real time, generates the equipment performance value of the power equipment from the acquired performance data, and predicts the operating status of the power equipment and obtains the corresponding prediction data if the correlation between the environmental risk value and the equipment performance value exceeds expectations;

[0031] The alarm unit evaluates the health status of the power equipment based on the prediction data. If the power equipment is in an unhealthy state, it issues a multi-level alarm command to the outside according to the degree of unhealthiness;

[0032] The inspection unit plans and obtains the inspection route of the power equipment in the industrial park, inspects each abnormal equipment, and verifies the abnormality of the power equipment based on the inspection data obtained;

[0033] The emergency handling unit uses the trained parameter control model to automatically control the abnormal equipment, and then the power equipment maintenance knowledge graph outputs a maintenance plan for the abnormal equipment.

[0034] (III) Beneficial effects

[0035] The present invention provides a multi-dimensional intelligent regulation system and method for electric power equipment, which has the following beneficial effects:

[0036] 1. Predict and determine the impact of air quality on power equipment, and comprehensively evaluate the impact of air quality on power equipment. When the air quality in the industrial park area is abnormal, the current production status can be adjusted to protect the power equipment.

[0037] 2. By generating equipment performance values ​​from equipment operation performance data, the current performance status of the power equipment is judged to confirm whether there are any abnormalities in the power equipment. If there are any abnormalities, they can be handled in a timely manner to ensure that the power equipment in the industrial park can operate normally.

[0038] 3. Determine the impact of air quality on the operating performance of power equipment, which will make adjustments and treatments of air pollution in industrial parks more targeted and more accurate in predicting the operating status of power equipment.

[0039] 4. Evaluate the health of power equipment based on the health score, screen out abnormal equipment in a timely manner, and when the operating performance and operating status of abnormal equipment further deteriorate, timely processing and maintenance are carried out to achieve the continuation of normal production status in the industrial park.

[0040] 5. Based on the warning value, the health of power equipment in the industrial area can be evaluated holistically to verify the changes in the health of power equipment under the overall influence of polluted air in the industrial park. When the impact exceeds expectations, timely inspections and processing can be carried out to ensure the reliability of power equipment as a whole.

[0041] 6. When performing maintenance on abnormal equipment according to the inspection route obtained through planning, priority maintenance is given to abnormal equipment with poor health and frequent abnormalities to improve maintenance efficiency; the abnormality of abnormal equipment can be verified through inspection data to avoid misjudgment and improve the reliability of fault prediction and fault inspection; feature engineering and feature extraction are performed based on the received inspection data to clarify the type and content of faults in power equipment, so as to achieve targeted processing of abnormal equipment.

[0042] 7. Through the parameter control model, various parameters of abnormal equipment are automatically controlled. When it is confirmed that the power equipment has an abnormality, emergency processing can be implemented to avoid the deterioration of the power equipment and affect the production process in the industrial park. The power equipment maintenance knowledge map outputs maintenance plans for abnormal equipment, gives targeted maintenance plans and performs targeted maintenance, and implements targeted maintenance after patrol inspections of the power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a schematic flow chart of the multi-dimensional intelligent adjustment method for power equipment of the present invention;

[0044] Figure 2 The figure is a schematic diagram of the structure of the multi-dimensional intelligent regulation system for power equipment according to the present invention. DETAILED DESCRIPTION

[0045] 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.

[0046] See also Figure 1 The present invention provides a multi-dimensional intelligent adjustment method for electric power equipment, comprising:

[0047] Step 1: Monitor the air quality data in the industrial park and generate an environmental risk value from the air quality data. If the environmental risk value exceeds the expectation, issue a fault monitoring instruction to the outside.

[0048] The step 1 includes the following contents:

[0049] Step 101: deploy an environmental sensor network in the industrial park, including a gas detection sensor, a humidity sensor, a temperature sensor, a salt spray sensor, etc.: the sensor network collects air quality data in the industrial park, including acidic gas, alkaline gas and salt spray concentration, etc., and aggregates the collected air quality data to generate an air quality data set;

[0050] Step 102: train a deep learning algorithm with labeled sample data to obtain a trained environmental risk identification model; use the collected air quality data as input and use the trained environmental risk identification model to identify environmental risks faced by power equipment, such as corrosion of power equipment by polluted air. If there is an environmental risk, generate an environmental risk value from the air quality data set after linear normalization of the data, as follows:

[0051]

[0052] Where: W i is the weight coefficient of the ith air quality index, and its value falls within [0,1], S i is the abnormal degree of the ith air quality index, D i is the density of the time node when the i-th air quality index produces anomalies;

[0053] If the environmental risk value exceeds the preset risk threshold, it means that the current air quality in the industrial park, such as pollutants in the air, will cause a certain degree of corrosion to the power equipment, affecting its operating performance and increasing the risk of failure. There is an environmental risk. At this time, a fault monitoring instruction is issued to the outside.

[0054] When using, combine the contents in steps 101 and 102:

[0055] Due to the limitations of production tasks and production status, when there are more air pollutants in the park, the air quality in the industrial park is monitored in real time. The trained environmental risk identification model is used to predict and judge the impact of air quality on power equipment. By constructing an environmental risk value, a comprehensive assessment is made of the impact of air quality on power equipment based on the impact on each power equipment. When the air quality in the industrial park area is abnormal, the current production status can be adjusted or the power equipment can be protected.

[0056] In the existing inspection method of power equipment, regular inspections are usually carried out on all power equipment in the industrial park. This inspection method has a wide coverage, but in fact, when the industrial park is in production, a large amount of polluting gas will be discharged to the outside, and the power equipment may be in a salt spray environment. If the power equipment is in this scenario for a long time, some of its components may be due to corrosion or similar reasons, resulting in a significant decline in performance. Therefore, in this scenario, if a comprehensive inspection mechanism is still carried out on the power equipment, when time is limited, it may lead to low inspection efficiency, and may also cause some abnormal power equipment to be neglected, and fail to effectively ensure the operation of the power equipment.

[0057] Step 2: monitor the operating performance of the power equipment in real time, generate the equipment performance value of the power equipment from the acquired performance data, and if the correlation between the environmental risk value and the equipment performance value exceeds expectations, predict the operating status of the power equipment and obtain corresponding prediction data;

[0058] The step 2 includes the following contents:

[0059] Step 201: After receiving the fault monitoring instruction, the performance of each power equipment is monitored in the industrial park, for example, a sensor network such as a temperature sensor, a vibration sensor and a gas detection sensor is arranged at the transformer, switch cabinet, cable joint, bus connection point, etc.; the sensor network collects the performance data of the equipment in real time, such as the operating temperature, voltage and current, power factor and response speed, etc.; the acquired equipment performance data is aggregated to generate a performance data set;

[0060] Step 202: Under dimensionless conditions, the equipment performance value of the power equipment is generated from the performance data in the performance data set in the following manner:

[0061]

[0062] Where: α and β are weight coefficients, both of which fall within [0,1], P i is the i-th performance parameter, μ i is the mean value of the i-th performance parameter, σ i is the corresponding standard deviation, k is the adjustment parameter; n is the number of performance parameters, w i is the weight of the i-th performance parameter, is the spectrum energy of the ith performance parameter, is the square of the spectrum amplitude of the i-th performance parameter at frequency f, representing the spectrum energy density;

[0063] When in use, when the current air quality in the air park is abnormal, the equipment performance value is generated by the equipment operation performance data, and the current performance status of the power equipment is judged based on the equipment performance value to confirm whether there is any abnormality in the power equipment. If there is any abnormality, it can be handled in a timely manner to ensure that the power equipment in the industrial park can operate normally.

[0064] Step 203: perform correlation analysis between the environmental risk value and the equipment performance value and obtain the corresponding correlation coefficient. If the correlation coefficient exceeds a preset correlation threshold, train a convolutional neural network with the labeled sample data to obtain a trained power equipment operation status prediction model.

[0065] Use the trained operation status prediction model to predict various operation parameters of the power equipment, obtain corresponding prediction data, such as electrical performance parameters, mechanical state parameters and reliability parameters, and aggregate the obtained prediction data to generate an operation status prediction data set for the power equipment;

[0066] When using, combine the contents in steps 201 to 203:

[0067] By analyzing the correlation between air quality and power equipment performance in industrial parks, we can determine the impact of air quality on the operating performance of power equipment, so that we can be more targeted when adjusting and treating air pollution in industrial parks; on this basis, we can predict the operating status of power equipment with higher accuracy.

[0068] Step 3: Evaluate the health status of the power equipment based on the predicted data. If the power equipment is in an unhealthy state, issue a multi-level alarm command to the outside according to the degree of unhealthiness.

[0069] The step three includes the following contents:

[0070] Step 301: train a machine learning algorithm with the labeled sample data to obtain a trained equipment health status recognition model; use the predicted number of the power equipment operation status as input, use the trained equipment operation status recognition model to perform a health assessment on the operation status of the power equipment, obtain a corresponding health score, and quantify the health status of the equipment with the health score;

[0071] The health threshold is pre-set based on historical data and management expectations for the health status of power equipment. If the health score of the power equipment is lower than the health threshold, it means that the current operating status of the power equipment is abnormal. At this time, the corresponding power equipment is regarded as an abnormal device and a first-level alarm instruction is issued to the outside.

[0072] When in use, the health of the power equipment is identified based on the acquisition of various prediction data, and the health of the power equipment is evaluated according to the health score. Abnormal equipment is screened out in time, and when the operating performance and operating status of the abnormal equipment further deteriorate, timely processing and maintenance are carried out to achieve the continuation of normal production status in the industrial park.

[0073] Step 302: If the number of first-level alarm instructions received continuously within the preset observation period exceeds the expectation, according to the difference between the equipment health score and the health threshold, and the distribution state of the time nodes of receiving the first-level alarm instructions, under dimensionless conditions, the warning value is constructed in the following manner:

[0074]

[0075] Where: H(t) is the equipment health score at time t, H t is the health score threshold, T is the length of the observation period, N is the number of times the first-level alarm command is received, ΔN is the corresponding deviation value, A(t) is the function of receiving the alarm command at time t, indicating whether the alarm command is received, λ(t) is the time decay function, k1, k2 and k3 are weight coefficients, and their values ​​all fall into [0,1];

[0076] Based on historical data and management expectations of the health status of power equipment, the warning threshold is pre-set; if the warning value exceeds the warning threshold, it means that the current abnormality of the power equipment is high and needs to be handled in time. At this time, a secondary alarm instruction is issued to the outside;

[0077] When using, combine the contents in steps 301 and 302:

[0078] On the basis of abnormal equipment that has been screened out, warning values ​​are constructed through the unhealthy degree and frequency of power equipment. Based on the warning values, a holistic assessment of the health of power equipment in industrial areas can be made, and changes in the health of power equipment under the overall influence of polluted air in industrial parks can be verified. When the degree of impact exceeds expectations, timely inspections and processing can be carried out to ensure the reliability of power equipment as a whole.

[0079] Step 4: Plan and obtain inspection routes for power equipment in the industrial park, inspect each abnormal device, and verify the abnormality of the power equipment based on the inspection data obtained;

[0080] The step 4 includes the following contents:

[0081] Step 401: after receiving the second-level alarm instruction, construct an electronic map covering the industrial park and mark the abnormal power equipment on the electronic map;

[0082] Based on the location information and health score of abnormal equipment, the pre-trained path planning algorithm plans and obtains the inspection path within the industrial park; the inspection path is marked on the electronic map, and the inspection route is adjusted dynamically according to the update of abnormal equipment;

[0083] When in use, when there are many abnormal devices in the industrial park, when maintaining the abnormal devices according to the inspection path obtained by planning, the abnormal devices with poor health and frequent abnormalities are given priority maintenance to improve the maintenance efficiency;

[0084] Step 402: Inspection equipment equipped with high-definition cameras, infrared sensors, laser rangefinders and other equipment conducts inspections in the industrial park according to the generated inspection path, and collects appearance images, thermal imaging data and operation data of abnormal equipment in real time; the above collected data is used as inspection data, and is summarized to generate a set of equipment inspection data;

[0085] Step 403: train a convolutional neural network with the labeled sample data to obtain a trained anomaly recognition model; use the collected inspection data as input, use the trained anomaly recognition model to perform anomaly recognition on the inspection data, and obtain the abnormal conditions of the abnormal equipment, such as abnormal equipment appearance, abnormal temperature, and corrosion marks; if the abnormal equipment still has an abnormality, extract the corresponding abnormal features, and issue an abnormal reminder instruction to the outside;

[0086] When used, combine the contents in steps 401 to 403:

[0087] When patrolling various abnormal equipment in industrial parks with patrol robots or drones, the abnormality of the abnormal equipment can be verified through the patrol data to avoid misjudgment and improve the reliability of fault prediction and fault inspection. Feature engineering and feature extraction are performed based on the received patrol data to clarify the type and content of faults in the power equipment, so as to achieve targeted processing of abnormal equipment.

[0088] Step 5: After the trained parameter control model is used to automatically control the abnormal equipment, the power equipment maintenance knowledge graph outputs a maintenance plan for the abnormal equipment;

[0089] The step five includes the following contents:

[0090] Step 501: pre-set qualified ranges for various control parameters of abnormal equipment; train the machine learning algorithm with the labeled sample data to obtain the trained parameter control model; after receiving the abnormal reminder instruction, use the operating data of the abnormal equipment as input and use the trained parameter control model to automatically control the abnormal equipment, such as adjusting voltage, closing / opening the switch, etc., to ensure rapid response in emergency situations;

[0091] When in use, when there is an abnormality in the power equipment, the various parameters of the abnormal equipment are automatically controlled through the parameter control model. When the abnormality of the power equipment is confirmed, emergency treatment can be implemented to prevent the abnormality of the power equipment from further deteriorating and affecting the production process in the industrial park;

[0092] Step 502: Taking power equipment maintenance as the target word, after deep retrieval and entity relationship building, pre-set the power equipment maintenance knowledge graph; according to the correspondence between abnormal features and maintenance plans, the power equipment maintenance knowledge graph outputs a maintenance plan for the abnormal equipment;

[0093] Generate an equipment operation report before performing maintenance on abnormal equipment, including at least the maintenance plan, health status index and predicted operation data of the abnormal equipment;

[0094] When using, combine the contents in steps 501 and 502:

[0095] After determining the abnormal characteristics of the abnormal equipment, the power equipment maintenance knowledge graph outputs a maintenance plan for the abnormal equipment on the basis of automatic control of the power equipment. When the power equipment in the industrial park becomes abnormal, a targeted maintenance plan can be given and targeted maintenance can be carried out. After patrolling the power equipment, targeted maintenance can be achieved.

[0096] The construction method of the power equipment maintenance knowledge graph can refer to the following:

[0097] First, it is necessary to clarify the construction goals of the power equipment maintenance knowledge graph, including but not limited to improving fault diagnosis efficiency, optimizing maintenance plans, and promoting knowledge sharing. Clarifying the goals will help guide subsequent construction work.

[0098] Data source determination: Collect various types of data related to power equipment maintenance, including equipment operation logs, maintenance records, fault reports, expert experience, technical manuals, etc. Data diversity: Ensure the diversity of data types, including text, images, videos, etc., so as to more comprehensively reflect the actual situation of power equipment maintenance.

[0099] Data cleaning: remove duplicate, erroneous, and incomplete data to ensure data accuracy and consistency. Data labeling: label the collected data, including entity recognition, relationship extraction, etc., to provide a basis for subsequent knowledge graph construction.

[0100] Entity recognition: Use natural language processing (NLP) technology to identify entities such as power equipment, fault types, and maintenance measures from text data. Relationship extraction: Further extract the relationship between entities, such as "a certain equipment - a fault - a certain type of fault" and "a certain fault - corresponding to a certain maintenance measure".

[0101] Knowledge graph construction: The extracted entities and relationships are represented in a graphical way to form a knowledge graph for power equipment maintenance. Coding and standardization: Encoding and standardizing entities and relationships to ensure the semantic consistency and scalability of the knowledge graph. Data storage: Store the constructed knowledge graph in a database or graph database for fast retrieval and query. Query optimization: Design efficient query algorithms and interfaces to facilitate users to quickly obtain relevant knowledge and information according to their needs.

[0102] See also Figure 2 The present invention provides a multi-dimensional intelligent regulation system for electric power equipment, comprising:

[0103] The environmental risk analysis unit monitors the air quality data in the industrial park and generates an environmental risk value from the air quality data. If the environmental risk value exceeds the expectation, a fault monitoring instruction is issued to the outside.

[0104] The equipment performance analysis unit monitors the operating performance of the power equipment in real time, generates the equipment performance value of the power equipment from the acquired performance data, and predicts the operating status of the power equipment and obtains the corresponding prediction data if the correlation between the environmental risk value and the equipment performance value exceeds expectations;

[0105] The alarm unit evaluates the health status of the power equipment based on the prediction data. If the power equipment is in an unhealthy state, it issues a multi-level alarm command to the outside according to the degree of unhealthiness;

[0106] The inspection unit plans and obtains the inspection route of the power equipment in the industrial park, inspects each abnormal equipment, and verifies the abnormality of the power equipment based on the inspection data obtained;

[0107] The emergency handling unit uses the trained parameter control model to automatically control the abnormal equipment, and then the power equipment maintenance knowledge graph outputs a maintenance plan for the abnormal equipment.

[0108] 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.

[0109] 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.

[0110] 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 for some logical functions. 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.

[0111] 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.

[0112] 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 multi-dimensional intelligent adjustment method for power equipment, characterized in that: include, Monitor air quality data in the industrial park and generate environmental risk values ​​from the air quality data. If the environmental risk value exceeds expectations, a fault monitoring instruction is issued to the outside. Monitor the operating performance of power equipment in real time, generate equipment performance values ​​of power equipment from the acquired performance data, and if the correlation between the environmental risk value and the equipment performance value exceeds expectations, predict the operating status of the power equipment and obtain corresponding prediction data; Evaluate the health status of power equipment based on prediction data. If the power equipment is in an unhealthy state, issue multi-level alarm instructions to the outside according to the degree of unhealthiness. Plan and obtain inspection routes for power equipment in the industrial park, inspect each abnormal device, and verify power equipment anomalies based on the inspection data obtained; After using the trained parameter control model to automatically control the abnormal equipment, the power equipment maintenance knowledge graph outputs a maintenance plan for the abnormal equipment.

2. The multi-dimensional intelligent adjustment method for power equipment according to claim 1 is characterized in that: The sensor network collects air quality data in the industrial park and aggregates them to generate an air quality data set; Taking air quality data as input, the trained environmental risk identification model is used to identify the environmental risks faced by power equipment. If there is an environmental risk, the environmental risk value is generated by the air quality data set.

3. The multi-dimensional intelligent adjustment method applied to power equipment according to claim 2 is characterized in that: After receiving the fault monitoring instruction, the performance of each power equipment is monitored in the industrial park, and the performance data of the equipment is collected in real time. The acquired equipment performance data is summarized to generate a performance data set, and the equipment performance value of the power equipment is generated from the performance data set.

4. The multi-dimensional intelligent adjustment method for electric power equipment according to claim 3 is characterized in that: Perform correlation analysis between environmental risk values ​​and equipment performance values ​​and obtain the corresponding correlation coefficient. If the correlation coefficient exceeds the preset correlation threshold; The trained operating status prediction model is used to predict the various operating parameters of the power equipment, obtain the corresponding prediction data, and summarize and generate a set of operating status prediction data for the power equipment.

5. The multi-dimensional intelligent adjustment method for electric power equipment according to claim 4 is characterized in that: Taking the predicted number of the power equipment operating status as input, the trained equipment operating status recognition model is used to conduct health assessment on the operating status of the power equipment and obtain the corresponding health score; If the health score of the power equipment is lower than the health threshold, the corresponding power equipment will be treated as an abnormal device and a first-level alarm instruction will be issued to the outside.

6. The multi-dimensional intelligent adjustment method for electric power equipment according to claim 5 is characterized in that: If the number of consecutive first-level alarm instructions received within the preset observation period exceeds the expected number, the warning value is constructed based on the difference between the device health score and the health threshold, and the distribution status of the time nodes when the first-level alarm instructions are received: If the warning value exceeds the warning threshold, a secondary alarm command will be issued to the outside.

7. The multi-dimensional intelligent adjustment method for electric power equipment according to claim 6 is characterized in that: After receiving the second-level alarm command, the abnormal power equipment is marked on the electronic map; Based on the location information and health score of abnormal equipment, the pre-trained path planning algorithm plans and obtains the inspection path within the industrial park; The inspection route is marked on the electronic map and dynamically adjusted based on the update of abnormal equipment.

8. The multi-dimensional intelligent adjustment method for electric power equipment according to claim 7 is characterized in that: The inspection equipment conducts inspections in the industrial park according to the generated inspection paths, collects appearance images, thermal imaging data and operation data of abnormal equipment in real time, and summarizes the collected data as inspection data to generate equipment inspection data sets; The collected inspection data is used as input, and the trained anomaly recognition model is used to identify anomalies in the inspection data. If the abnormal equipment still has an abnormality, the corresponding abnormal features are extracted and an abnormal reminder instruction is issued to the outside.

9. The multi-dimensional intelligent adjustment method applied to power equipment according to claim 8, characterized in that: After receiving the abnormal reminder instruction, the abnormal equipment is automatically controlled using the trained parameter control model with the operation data of the abnormal equipment as input; Taking power equipment maintenance as the target word, a knowledge graph of power equipment maintenance is pre-set; Before performing maintenance on abnormal equipment, an equipment operation report is generated, which at least includes a maintenance plan, a health status index and predicted operation data for the abnormal equipment.

10. A multi-dimensional intelligent regulation system applied to power equipment, characterized in that: include, The environmental risk analysis unit monitors the air quality data in the industrial park and generates an environmental risk value from the air quality data. If the environmental risk value exceeds the expectation, a fault monitoring instruction is issued to the outside. The equipment performance analysis unit monitors the operating performance of the power equipment in real time, generates the equipment performance value of the power equipment from the acquired performance data, and predicts the operating status of the power equipment and obtains the corresponding prediction data if the correlation between the environmental risk value and the equipment performance value exceeds expectations; The alarm unit evaluates the health status of the power equipment based on the prediction data. If the power equipment is in an unhealthy state, it issues a multi-level alarm command to the outside according to the degree of unhealthiness; The inspection unit plans and obtains the inspection route of the power equipment in the industrial park, inspects each abnormal equipment, and verifies the abnormality of the power equipment based on the inspection data obtained; The emergency handling unit uses the trained parameter control model to automatically control the abnormal equipment, and then the power equipment maintenance knowledge graph outputs a maintenance plan for the abnormal equipment.

Images