Handheld intelligent inspection instrument and method integrating partial discharge detection and infrared imaging

By integrating local detection and infrared imaging technology, combining composite index index and coordination mechanism, appropriate analysis methods are selected, the problem of insufficient processor capabilities of handheld intelligent patrol instruments is solved, and more efficient fault detection and maintenance strategies are achieved, improving The safe operation and maintenance efficiency of power equipment.

CN118708944BActive Publication Date: 2024-11-05CHENGDU YIDIAN CLOUD BUSINESS ENG SERVICE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411181719.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-11-05
Estimated Expiration
2044-08-27

AI Technical Summary

Technical Problem

While the handheld intelligent patrol instrument is improved in portability, the internal processor is difficult to meet the needs of large-scale computing and analysis, resulting in limited accuracy and efficiency in power equipment failure detection.

Method used

Through integrated local detection and infrared imaging technology, the composite index index is used to generate and select appropriate algorithms (simple threshold or weighted comprehensive scoring algorithm), combined with local and cloud collaboration mechanisms for analysis, select the most appropriate analysis method, and use fuzzy reasoning and Time series models perform fault prediction and maintenance strategy execution.

Benefits of technology

Improve the accuracy and adaptability of fault prediction, optimize resource utilization, ensure the most appropriate analysis method in different situations, save time and computing resources, improve the accuracy of fault detection, reduce unnecessary maintenance, reduce maintenance costs, and advance Identify potential failures, arrange maintenance plans reasonably, and improve maintenance efficiency and effectiveness.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118708944B_ABST
    Figure CN118708944B_ABST
Patent Text Reader

Abstract

The present invention discloses a handheld intelligent inspection instrument and method integrating partial discharge detection and infrared imaging, and specifically relates to the technical field of power equipment inspection, and comprises the following steps: generating a composite index by collecting the environment and operation information of the target power equipment; selecting a simple threshold algorithm or a weighted comprehensive scoring algorithm based on the composite index to perform local or cloud collaborative analysis; for local analysis, using fuzzy reasoning to judge the maintenance type; for cloud analysis, using a time series model to predict the operation risk and execute corresponding security policies; the present invention can select a suitable algorithm based on the composite index to improve the prediction accuracy and adaptability, judge the local-cloud collaborative mechanism mode, ensure the most suitable analysis mode is adopted in different situations, and can optimize the maintenance resource allocation, reduce unnecessary maintenance, reduce maintenance costs, reasonably arrange maintenance plans, improve maintenance efficiency and effects, and reduce equipment downtime.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment inspection, and more specifically to a handheld intelligent inspection instrument and method integrating partial discharge detection and infrared imaging. Background Art

[0002] The handheld intelligent inspection instrument with integrated partial discharge detection and infrared imaging is a portable device used for comprehensive inspection of power equipment. It combines partial discharge detection and infrared imaging technology to detect electrical and thermal faults of power equipment in real time. Partial discharge detection can identify electrical insulation defects inside the equipment, such as partial discharge phenomena in cables, transformers and switchgear, while infrared imaging can detect temperature anomalies on the surface of the equipment, such as overheating or hot spots, which are early signs of power equipment failure.

[0003] This handheld intelligent inspection device is portable and intelligent, which makes it convenient for power operation and maintenance personnel to conduct inspections on site quickly and efficiently. However, different electrical equipment has different inspection accuracy, and different amounts of data need to be collected and analyzed. While the portability of handheld intelligent inspection equipment is improved, its own computing power is also sacrificed to a certain extent. Its internal processor often cannot meet the needs of large-scale computing and analysis. Therefore, a handheld intelligent inspection instrument and method integrating partial discharge detection and infrared imaging are proposed herein. Summary of the invention

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] The handheld intelligent inspection method integrating partial discharge detection and infrared imaging includes the following steps:

[0006] Collect environmental information and operation information of target power equipment, and then conduct preliminary analysis together to generate a composite indicator index;

[0007] Based on the composite index, a simple threshold algorithm or a weighted comprehensive scoring algorithm is selected to judge the collected operation information in a local-cloud collaborative mechanism manner, and whether to use local analysis or cloud analysis is determined;

[0008] When the local analysis method is selected, fuzzy reasoning is used to determine the type of maintenance;

[0009] When cloud-based analysis is used, the operating risk level of the target power equipment is predicted, and corresponding security strategies are implemented based on the predicted results.

[0010] In a preferred embodiment, the logic for obtaining the composite index is as follows:

[0011] Extract environmental feature data corresponding to multiple preset environmental features from the collected environmental information, and obtain a first operating feature data group from the collected operating information. The first operating feature data group generally refers to a feature that is simple and quick to obtain, does not require too complicated computing power costs, and has a certain degree of correlation that affects the safe operation of the equipment, such as ambient temperature, equipment operating time, equipment failure frequency, and the number of partial discharges that occur per unit time of the equipment. The first operating feature data group contains operating feature data corresponding to multiple preset equipment-type operating features, and then performs the following calculations: ; HJi is the environmental characteristic data numbered i, HBi is the standard environmental data corresponding to the environmental characteristic numbered i, YXi is the operating characteristic data numbered i, yi is the preset proportional coefficient corresponding to a type of operating characteristic numbered i, hi is the preset proportional coefficient corresponding to the environmental characteristic data i, k1 and k2 are both preset proportional coefficients, and the sum of the two is one, N is the total number of environmental characteristic data, M is the total amount of operating characteristic data in the first operating characteristic data group, and C is the composite indicator index.

[0012] In a preferred embodiment, selecting a simple threshold algorithm or a weighted comprehensive scoring algorithm based on the composite indicator index means: a reference threshold corresponding to the composite indicator index is preset, and the composite indicator index is compared with the preset reference threshold. If the composite indicator index is greater than or equal to the preset reference threshold, the weighted comprehensive scoring algorithm is selected; if the composite indicator index is less than the preset reference threshold, the simple threshold algorithm is selected.

[0013] In a preferred embodiment, the simple threshold algorithm refers to:

[0014] A second operating characteristic data group is obtained from the operating information collected from the target power equipment. The second operating characteristic data group includes operating characteristic data corresponding to multiple preset Class II operating characteristics of the equipment. Each operating characteristic data corresponding to the Class II operating characteristic is provided with an operating threshold interval. The operating threshold interval is divided into multiple sub-intervals. Each sub-interval level corresponds to a unique level value in the fault level 0-U, U is the total number of sub-interval levels, and the operating characteristic data corresponding to each Class II operating characteristic obtains its corresponding fault level, and then all fault levels are summed to obtain a comprehensive fault degree value.

[0015] In a preferred embodiment, the weighted comprehensive scoring algorithm refers to:

[0016] A second operating characteristic data group is obtained from the operating information collected from the target power equipment. The second operating characteristic data group includes operating characteristic data corresponding to multiple preset Class II operating characteristics of the equipment. The operating characteristic data corresponding to each Class II operating characteristic is provided with an operating standard value. The absolute value of the difference between the operating characteristic data of each Class II operating characteristic and the operating standard value is calculated. A weight coefficient is assigned to each Class II operating characteristic. The obtained absolute value is multiplied by the corresponding weight coefficient, and then the sum is calculated to obtain a comprehensive fault degree value.

[0017] In a preferred embodiment, determining whether to use local analysis or cloud analysis refers to:

[0018] Obtain the comprehensive fault severity value obtained using a simple threshold algorithm or a weighted comprehensive scoring algorithm, and compare it with the preset collaborative threshold. If the comprehensive fault severity value is greater than or equal to the preset collaborative threshold, cloud analysis is used; if the comprehensive fault severity value is less than the preset collaborative threshold, local analysis is used.

[0019] In a preferred embodiment, the logic of fuzzy reasoning is:

[0020] Obtain partial discharge detection information and infrared imaging information, perform partial discharge detection feature extraction and infrared imaging feature extraction respectively, obtain multiple partial discharge detection feature data and infrared imaging feature data, use the multiple partial discharge detection feature data and infrared imaging feature data as input variables, use the type of maintenance as the output variable, perform fuzzy processing on the input variables, convert the values ​​of the input variables into fuzzy sets, perform fuzzy processing on the output variables, convert the output variables into fuzzy sets, formulate fuzzy rules, describe the maintenance requirements under different data type combinations, infer the fuzzified input variables through fuzzy rules, and determine the type of maintenance required for the target power equipment.

[0021] In a preferred embodiment, predicting the operating risk level of the target power equipment refers to:

[0022] The operation risk level of the target power equipment is predicted and analyzed through the time series model. The time series model adopts the ARIMAX model. The specific steps of predicting the operation risk level of the target power equipment through the time series model are as follows:

[0023] Step 1: Obtain prediction data;

[0024] Step 2: Establish ARIMAX model;

[0025] Step 3: Use the maximum likelihood estimation method to estimate the ARIMAX model parameters;

[0026] Step 4: Verify the effect of the fitting model and check the goodness of fit of the model through residual analysis;

[0027] Step 5: Use the fitted model to predict the future operational risk level.

[0028] In a preferred embodiment, the exogenous variables in the ARIMAX model include the partial discharge detection deviation index and the infrared imaging deviation index, and the ARIMAX model formula is: ; is the error term at time point t, is a constant term, is the operational risk level at time point t-1, is the operational risk level at time point t, is the partial discharge detection deviation index at time point t, is the coefficient of the partial discharge detection deviation index, is the infrared imaging deviation index at time point t, is the coefficient of the infrared imaging deviation index, is the first-order autoregressive parameter, is the first-order moving average parameter;

[0029] The logic for obtaining the partial discharge detection deviation index is as follows: characteristic data related to partial discharge detection are collected from the actual operation of the target power equipment and the standard operation of the power equipment, and then standardized, and finally the partial discharge detection deviation index D of the actual operation of the target power equipment and the standard operation of the power equipment is calculated using the Euclidean distance;

[0030] The infrared imaging deviation index is used to measure the fluctuation of the number of hot spots in the infrared imaging map. The infrared imaging deviation index is the standard deviation of the number of hot spots.

[0031] In a preferred embodiment, a handheld intelligent inspection instrument integrating partial discharge detection and infrared imaging includes a preliminary analysis module, a judgment module, a local analysis module, a cloud analysis module, and a safety maintenance module;

[0032] The preliminary analysis module is used to collect environmental information and operation information of the target power equipment, and then conduct preliminary analysis together to generate a composite indicator index;

[0033] The judgment module is used to select a simple threshold algorithm or a weighted comprehensive scoring algorithm based on the composite index to judge the collected operation information in a local-cloud collaborative mechanism manner, and to judge whether to use a local analysis or a cloud analysis method;

[0034] The local analysis module is used to determine the type of maintenance by fuzzy reasoning when the local analysis method is selected;

[0035] The cloud analysis module is used to predict the operating risk level of the target power equipment when the cloud analysis method is selected;

[0036] The security maintenance module is used to execute corresponding maintenance strategies according to the maintenance type determined by the local analysis module, and to execute corresponding security strategies according to the operating risk level of the target power equipment predicted by the cloud analysis module.

[0037] Technical effects and advantages of the present invention:

[0038] The present invention generates a composite indicator index by collecting and analyzing environmental information and operating information, thereby providing a more comprehensive and accurate basis for fault prediction. The present invention selects a suitable algorithm based on the composite indicator index: a simple threshold algorithm or a weighted comprehensive scoring algorithm, thereby improving the accuracy and adaptability of the prediction. The collected operating information is judged by a local-cloud collaborative mechanism, and the choice of local analysis or cloud analysis is determined to ensure that the most appropriate analysis method is used in different situations to optimize resource utilization.

[0039] In the present invention, for simple faults, local analysis is used for quick judgment, saving time and computing resources; for complex faults, cloud analysis is used for in-depth prediction to improve the accuracy of fault detection. When the local analysis method is selected, the fuzzy reasoning system is used to determine the maintenance type, provide clear maintenance suggestions, and ensure timely and effective maintenance. When the cloud analysis method is selected, the ARIMAX model is used to predict the degree of operation risk, and the corresponding safety strategy is executed based on the prediction results to ensure the safe operation of the equipment. It can also optimize the allocation of maintenance resources, reduce unnecessary maintenance, reduce maintenance costs, identify potential faults in advance, reasonably arrange maintenance plans, improve maintenance efficiency and effects, and reduce equipment downtime. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0041] Figure 1 This is a schematic diagram of the handheld intelligent inspection method integrating partial discharge detection and infrared imaging in the present invention.

[0042] Figure 2 The schematic diagram of the handheld intelligent inspection instrument integrating partial discharge detection and infrared imaging in the present invention;

[0043] Figure 3 It is a schematic diagram of the preliminary analysis module in the present invention. DETAILED DESCRIPTION

[0044] 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.

[0045] Reference Figure 1 - Figure 3 The following embodiments are obtained:

[0046] Embodiment 1: A handheld intelligent inspection method integrating partial discharge detection and infrared imaging comprises the following steps:

[0047] Step 1: Collect environmental information and operation information of the target power equipment, and then conduct preliminary analysis together to generate a composite indicator index;

[0048] Step 2: Based on the composite index, a simple threshold algorithm or a weighted comprehensive scoring algorithm is selected to judge the collected operation information by a local-cloud collaborative mechanism, and whether to use local analysis or cloud analysis;

[0049] Step 3: When the local analysis method is selected, the fuzzy reasoning method is used to determine the type of maintenance;

[0050] Step 4: When using cloud analysis, predict the operating risk level of the target power equipment and implement corresponding security strategies based on the predicted results.

[0051] The logic for obtaining the composite index is as follows:

[0052] Extract environmental feature data corresponding to multiple preset environmental features from the collected environmental information, and obtain a first operating feature data group from the collected operating information. The first operating feature data group generally refers to a feature that is simple and quick to obtain, does not require too complicated computing power costs, and has a certain degree of correlation that affects the safe operation of the equipment, such as ambient temperature, equipment operating time, equipment failure frequency, and the number of partial discharges that occur per unit time of the equipment. The first operating feature data group contains operating feature data corresponding to multiple preset equipment-type operating features, and then performs the following calculations: ; HJi is the environmental characteristic data numbered i, HBi is the standard environmental data corresponding to the environmental characteristic numbered i, YXi is the operating characteristic data numbered i, yi is the preset proportional coefficient corresponding to a type of operating characteristic numbered i, hi is the preset proportional coefficient corresponding to the environmental characteristic data i, k1 and k2 are both preset proportional coefficients, and the sum of the two is one, N is the total number of environmental characteristic data, M is the total amount of operating characteristic data in the first operating characteristic data group, and C is the composite indicator index.

[0053] The handheld intelligent inspection equipment that can perform partial discharge detection and infrared imaging is indeed portable and intelligent. The built-in data sensor of the equipment can perform local processing when the problem is small, so that the early signals of the fault can be quickly identified and displayed, so that the inspection personnel can take timely measures. This local processing not only improves the detection efficiency, but also saves bandwidth and storage resources. When the detected problem has a large impact or is complex, the device can upload the data to the cloud platform through the wireless communication function for further processing and analysis. The cloud platform has powerful computing power and can perform in-depth analysis of large amounts of data. Inspection personnel can not only handle simple faults on site in a timely manner, but also rely on the powerful analysis capabilities of the cloud to conduct in-depth diagnosis of complex problems to ensure the safe operation of power equipment.

[0054] Composite index C can dynamically reflect the various states and environmental conditions of equipment operation. For example, when the ambient temperature is high, the equipment operation time is long, or the historical fault frequency is high, the use of a more complex weighted comprehensive scoring algorithm can improve the accuracy of fault detection. By introducing multiple key parameters such as ambient temperature, equipment operation time, equipment failure frequency, and the number of partial discharges that occur per unit time, composite index C can more comprehensively evaluate the health status of the equipment. In this way, choosing the right algorithm (simple threshold or weighted comprehensive scoring) can more accurately predict faults and avoid false positives or false negatives. When the conditions are simple (such as low temperature, short operation time, and low historical fault frequency), using a simple threshold algorithm can save computing resources and processing time, while also having sufficient credibility. When the conditions are complex, using a weighted comprehensive scoring algorithm can ensure the accuracy of the detection results.

[0055] Selecting a simple threshold algorithm or a weighted comprehensive scoring algorithm based on a composite indicator index means: a reference threshold corresponding to the composite indicator index is preset, and the composite indicator index is compared with the preset reference threshold. If the composite indicator index is greater than or equal to the preset reference threshold, the weighted comprehensive scoring algorithm is selected; if the composite indicator index is less than the preset reference threshold, the simple threshold algorithm is selected.

[0056] The simple threshold algorithm refers to: obtaining a second operating characteristic data group from the operating information collected from the target power equipment, the second operating characteristic data group contains operating characteristic data corresponding to multiple preset Class II operating characteristics of the equipment, and each operating characteristic data corresponding to the Class II operating characteristic is corresponding to an operating threshold interval, and the operating threshold interval is divided into multiple sub-intervals, each sub-interval level corresponds to a unique level value in the fault level 0-U, U is the total number of sub-interval levels, and the operating characteristic data corresponding to each Class II operating characteristic obtains its corresponding fault level, and then all fault levels are summed up to obtain the comprehensive fault degree value.

[0057] The weighted comprehensive scoring algorithm refers to: obtaining a second operating characteristic data group from the operating information collected from the target power equipment, the second operating characteristic data group contains operating characteristic data corresponding to multiple preset Class II operating characteristics of the equipment, and each operating characteristic data corresponding to the Class II operating characteristic is provided with an operating standard value. The absolute value of the difference between the operating characteristic data of each Class II operating characteristic and the operating standard value is calculated, and a weight coefficient is assigned to each Class II operating characteristic. The absolute value obtained is multiplied by the corresponding weight coefficient, and then the sum is calculated to obtain the comprehensive fault degree value.

[0058] The simple threshold algorithm is suitable for scenarios that require a quick response. Its simplicity and easy-to-understand nature make it an ideal choice for on-site rapid fault detection. In actual use, if the use environment becomes more complex, the weighted comprehensive scoring algorithm is used. The weighted comprehensive scoring algorithm is suitable for fault assessment scenarios that require more refinement and higher accuracy. By introducing weight coefficients, it can flexibly reflect the importance of different features and has strong adaptability. The selection of a specific algorithm needs to be determined based on the actual application scenario. The weighted comprehensive scoring algorithm can more flexibly reflect the importance of each feature by assigning different weights to different features, and takes into account the difference between the feature and the standard value, so it can more carefully evaluate the degree of fault. The weight coefficient can be adjusted according to the actual situation to improve the flexibility and adaptability of the model. The weights are assigned based on expert experience or historical data, which will not be elaborated here.

[0059] The method of judging whether to use local analysis or cloud analysis refers to:

[0060] Obtain the comprehensive fault degree value obtained using a simple threshold algorithm or a weighted comprehensive scoring algorithm, and compare it with the preset collaborative threshold. If the comprehensive fault degree value is greater than or equal to the preset collaborative threshold, cloud analysis is used; if the comprehensive fault degree value is less than the preset collaborative threshold, local analysis is used. This judgment method is conducive to efficient use of computing resources: local analysis is suitable for faults with small computing volume, fast response, and resource saving; cloud analysis is used to handle complex faults and provide more accurate analysis results; reduce latency: simple fault detection is processed locally, reducing data transmission time and latency, and responding in a timely manner; flexible response to faults:

[0061] For simple faults, local analysis is sufficient to avoid over-reliance on cloud resources; for complex faults, cloud analysis provides more comprehensive and in-depth diagnosis to ensure accuracy; Adaptive analysis strategy:

[0062] By dynamically adjusting the analysis method, the most appropriate analysis strategy can be automatically selected according to the degree of fault, thereby improving overall diagnostic efficiency; reducing operating costs: local analysis reduces the cost of data transmission and cloud computing, and is suitable for daily monitoring; cloud analysis is used only when necessary to save cloud resources and costs; improving equipment life: through timely and accurate fault detection and processing, equipment downtime is reduced and equipment service life is extended.

[0063] The logic of fuzzy reasoning is: obtain partial discharge detection information and infrared imaging information, perform partial discharge detection feature extraction and infrared imaging feature extraction respectively, obtain multiple partial discharge detection feature data and infrared imaging feature data, use the multiple partial discharge detection feature data and infrared imaging feature data as input variables, use the type of maintenance as the output variable, fuzzify the input variables, convert the values ​​of the input variables into fuzzy sets, fuzzify the output variables, convert the output variables into fuzzy sets, formulate fuzzy rules, describe the maintenance requirements under different data type combinations, and reason the fuzzified input variables through fuzzy rules to determine the type of maintenance required for the target power equipment.

[0064] Partial discharge detection is to evaluate the insulation condition of equipment by monitoring the partial discharge activity in power equipment. Examples of partial discharge detection characteristics are as follows: Partial discharge amplitude, definition: the discharge amount of a single partial discharge, usually measured in picocoulombs. The higher the amplitude, the stronger the discharge activity and the greater the risk of insulation damage. Number of discharges: the number of partial discharges that occur per unit time. The more discharges, the higher the degree of degradation of the insulation material. Discharge pulse interval: the time interval between two consecutive discharge pulses. The pulse interval can reflect the regularity and intensity of the discharge activity. Cumulative energy: the total energy of all discharge events within a certain period of time. A large cumulative energy indicates that the discharge activity is frequent and intense, and the insulation condition is poor.

[0065] Infrared imaging evaluates the operating status of equipment by detecting the heat distribution on the surface of the equipment. Examples of infrared imaging features are as follows: Maximum temperature: the highest temperature detected in the infrared imaging image. If the maximum temperature is higher than the normal value, it may indicate that the equipment is overheated or has hot spots; Minimum temperature: the lowest temperature detected in the infrared imaging image. The lowest temperature can be used for comparative analysis to detect temperature anomalies; Average temperature: the average temperature of the detection area in the infrared imaging image. If the average temperature is high, it may indicate that the overall temperature of the equipment is abnormal. Temperature gradient: the rate of temperature change in the detection area. A large temperature gradient may indicate local overheating or uneven heat dissipation. Number of hot spots: the number of hot spots in the infrared imaging image whose temperature is significantly higher than the background. A large number of hot spots indicates that the equipment has multiple overheating spots and a high potential failure risk. Hot spot area: the total area of ​​the hot spots. A large hot spot area indicates that the equipment has a wide heating area and may have more serious failures.

[0066] An example is given as follows: in the present invention, the partial discharge amplitude and the number of discharges in the partial discharge detection feature, the number of hot spots and the total area of ​​hot spots in the infrared imaging feature can be selected as input variables, and the type of maintenance can be used as the output variable, the partial discharge amplitude: low, medium, high; the number of discharges: low, medium, high; the number of hot spots: a few, medium, many; the total area of ​​hot spots: small, medium, large; the maintenance type: no maintenance required, preventive maintenance, emergency maintenance, and an example is given as follows: if the partial discharge amplitude is high, the number of discharges is high, the number of hot spots is many, and the total area of ​​hot spots is large, then the maintenance type is emergency maintenance; if the partial discharge amplitude is medium, the number of discharges is medium, the number of hot spots is medium, and the total area of ​​hot spots is medium, then the maintenance type is preventive maintenance. The purpose of preventive maintenance is to regularly inspect and maintain the equipment before it fails, so as to reduce the incidence of equipment failures, extend the life of the equipment, and ensure the reliable operation of the equipment. Preventive maintenance prevents and discovers potential problems through regular inspection, testing, cleaning, lubrication, replacement of wearing parts and other measures, thereby avoiding sudden failures and downtime losses. Emergency maintenance refers to maintenance and repair measures taken immediately when a serious equipment failure or potential major failure risk occurs. It is usually carried out when the equipment can no longer operate safely, or there are significant safety hazards or performance problems. Emergency maintenance aims to quickly restore the normal operation of the equipment to avoid more serious damage or safety accidents. Emergency maintenance requires an immediate response and has the highest priority. It usually requires the normal operation of the equipment to be suspended immediately for repair. The maintenance work needs to be completed in the shortest time possible to restore the normal operation of the equipment as soon as possible.

[0067] Predicting the operating risk level of the target power equipment refers to: predicting and analyzing the operating risk level of the target power equipment through a time series model. The time series model uses an ARIMAX model. The specific steps for predicting the operating risk level of the target power equipment through a time series model are as follows:

[0068] Step 1: Obtain prediction data;

[0069] Step 2: Establish ARIMAX model;

[0070] Step 3: Use the maximum likelihood estimation method to estimate the ARIMAX model parameters;

[0071] Step 4: Verify the effect of the fitting model and check the goodness of fit of the model through residual analysis;

[0072] Step 5: Use the fitted model to predict the future operational risk level.

[0073] The exogenous variables in the ARIMAX model include the partial discharge detection deviation index and the infrared imaging deviation index. The ARIMAX model formula is: ; is the error term at time point t, is a constant term, is the operational risk level at time point t-1, is the operational risk level at time point t, is the partial discharge detection deviation index at time point t, is the coefficient of the partial discharge detection deviation index, is the infrared imaging deviation index at time point t, is the coefficient of the infrared imaging deviation index, is the first-order autoregressive parameter, is the first-order moving average parameter; It is calculated by the maximum likelihood estimation method.

[0074] The logic for obtaining the partial discharge detection deviation index is as follows: collect the characteristic data related to partial discharge detection from the actual operation of the target power equipment and the standard operation of the power equipment, and then perform standardization processing. Finally, the Euclidean distance is used to calculate the partial discharge detection deviation index D under the actual operation of the target power equipment and the standard operation of the power equipment. The specific calculation formula is: ; N is the total number of characteristic data related to partial discharge detection, i is the number of the characteristic related to partial discharge detection, P1i is the data with characteristic number i detected under the actual operation of the target power equipment, and P2i is the standard value of the data with characteristic number i detected under the standard operation of the power equipment; the infrared imaging deviation index is used to measure the fluctuation of the number of hot spots in the infrared imaging map, and collects the number of hot spots in the infrared imaging map of the target power equipment at multiple time points. The infrared imaging deviation index is the standard deviation of the number of hot spots.

[0075] By predicting the degree of operational risk of power equipment, potential faults and risks can be identified in advance, and downtime and safety accidents caused by sudden faults can be avoided. Through real-time monitoring and prediction, it can ensure that the equipment operates in the best condition, avoid reduced efficiency due to faults, and ensure the stability and continuity of power supply. It provides accurate risk prediction data to support operation and maintenance personnel and management to make scientific decisions and optimize equipment management and operation strategies. Partial discharge is an early signal of insulation failure of power equipment. By monitoring and analyzing partial discharge, insulation problems can be discovered early to prevent further deterioration of the equipment. The partial discharge detection deviation index reflects the difference between the actual operating status of the equipment and the standard operating status, and can accurately diagnose the health status of the insulation material. The changing trend of partial discharge activity can be used as a key indicator to predict failures and help evaluate the operating risks of equipment. Based on the data of partial discharge detection deviation index, more accurate safety strategies can be formulated to prevent equipment damage caused by insulation failures. Infrared imaging technology can detect the temperature distribution on the surface of the equipment and identify hot spots and overheating areas. The infrared imaging deviation index can measure the fluctuations of these hot spots. Changes in the number and distribution of hot spots can reflect the heat dissipation problems and local overheating of the equipment, helping to identify potential failures. The temperature deviation index can reflect the changes in the load conditions and operating environment of the equipment, evaluate the load pressure and operating status of the equipment, and by monitoring and analyzing temperature fluctuations, timely measures can be taken to prevent equipment failures and safety accidents caused by overheating.

[0076] Embodiment 2: A handheld intelligent inspection instrument integrating partial discharge detection and infrared imaging, comprising a preliminary analysis module, a judgment module, a local analysis module, a cloud analysis module, and a safety maintenance module;

[0077] The preliminary analysis module is used to collect environmental information and operation information of the target power equipment, and then conduct preliminary analysis together to generate a composite indicator index; specifically, the preliminary analysis module includes an environmental information collection unit, a partial discharge detection unit, an infrared imaging unit, an equipment operation information collection unit, and a preliminary analysis unit. The partial discharge detection unit is used to perform partial discharge detection on the target power equipment, the infrared imaging unit is used to perform infrared imaging on the target power equipment, and the environmental information collection unit is used to collect information on the operating environment of the target power equipment, including but not limited to environmental data such as temperature and humidity;

[0078] The judgment module is used to select a simple threshold algorithm or a weighted comprehensive scoring algorithm based on the composite index to judge the collected operation information in a local-cloud collaborative mechanism manner, and to judge whether to use a local analysis or a cloud analysis method;

[0079] The local analysis module is used to determine the type of maintenance by fuzzy reasoning when the local analysis method is selected;

[0080] The cloud analysis module is used to predict the operating risk level of the target power equipment when the cloud analysis method is selected;

[0081] The security maintenance module is used to execute corresponding maintenance strategies according to the maintenance type determined by the local analysis module, and to execute corresponding security strategies according to the operating risk level of the target power equipment predicted by the cloud analysis module. Both security strategies and maintenance strategies are pre-set and will not be elaborated here.

[0082] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0083] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0084] 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.

[0085] 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.

[0086] 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 handheld intelligent inspection method integrating partial discharge detection and infrared imaging, characterized in that: The following steps are involved: Step 1: Collect environmental information and operation information of the target power equipment, and then conduct preliminary analysis together to generate a composite indicator index; Step 2: Based on the composite index, a simple threshold algorithm or a weighted comprehensive scoring algorithm is selected to judge the collected operation information by a local-cloud collaborative mechanism, and whether to use local analysis or cloud analysis; Step 3: When the local analysis method is selected, the fuzzy reasoning method is used to determine the type of maintenance; Step 4: When cloud analysis is used, the operating risk level of the target power equipment is predicted, and corresponding security strategies are implemented based on the predicted results; The logic for obtaining the composite index is as follows: Extract environmental feature data corresponding to multiple preset environmental features from the collected environmental information, and obtain a first operation feature data group from the collected operation information, wherein the first operation feature data group includes operation feature data corresponding to multiple preset equipment-type operation features, and then perform the following calculations: ; HJi is the environmental characteristic data numbered i, HBi is the standard environmental data corresponding to the environmental characteristic numbered i, YXi is the operation characteristic data numbered i, yi is the preset proportional coefficient corresponding to a type of operation characteristic numbered i, hi is the preset proportional coefficient corresponding to the environmental characteristic data i, k1 and k2 are both preset proportional coefficients, and the sum of the two is one, N is the total number of environmental characteristic data, M is the total amount of operation characteristic data in the first operation characteristic data group, and C is the composite index index; Selecting a simple threshold algorithm or a weighted comprehensive scoring algorithm based on a composite index means: presetting a reference threshold corresponding to the composite index, comparing the composite index with the preset reference threshold, and selecting the weighted comprehensive scoring algorithm if the composite index is greater than or equal to the preset reference threshold; and selecting the simple threshold algorithm if the composite index is less than the preset reference threshold; The simple threshold algorithm refers to: A second operation characteristic data group is obtained from the operation information collected from the target power equipment. The second operation characteristic data group includes operation characteristic data corresponding to a plurality of preset second-class operation characteristics of the equipment. Each operation characteristic data corresponding to the second-class operation characteristic is provided with an operation threshold interval. The operation threshold interval is divided into a plurality of sub-intervals. Each sub-interval level corresponds to a unique level value in the fault level 0-U. U is the total number of sub-interval levels. Each operation characteristic data corresponding to the second-class operation characteristic obtains its corresponding fault level. Then, all fault levels are summed to obtain a comprehensive fault degree value. The weighted comprehensive scoring algorithm refers to: A second operation characteristic data group is obtained from the operation information collected from the target power equipment, wherein the second operation characteristic data group includes operation characteristic data corresponding to a plurality of preset second-class operation characteristics of the equipment, and each operation characteristic data corresponding to the second-class operation characteristic is provided with an operation standard value, and the absolute value of the difference between the operation characteristic data of each second-class operation characteristic and the operation standard value is calculated, and a weight coefficient is assigned to each of the second-class operation characteristics, and the obtained absolute value is multiplied by the corresponding weight coefficient, and then summed up to obtain a comprehensive fault degree value; The method of judging whether to use local analysis or cloud analysis refers to: Obtain the comprehensive fault degree value obtained by using a simple threshold algorithm or a weighted comprehensive scoring algorithm, and compare it with the preset collaborative threshold. If the comprehensive fault degree value is greater than or equal to the preset collaborative threshold, use the cloud analysis method; if the comprehensive fault degree value is less than the preset collaborative threshold, use the local analysis method; The logic of fuzzy reasoning is: Obtain partial discharge detection information and infrared imaging information, perform partial discharge detection feature extraction and infrared imaging feature extraction respectively, obtain multiple partial discharge detection feature data and infrared imaging feature data, use the multiple partial discharge detection feature data and infrared imaging feature data as input variables, use the type of maintenance as the output variable, perform fuzzy processing on the input variables, convert the values ​​of the input variables into fuzzy sets, perform fuzzy processing on the output variables, convert the output variables into fuzzy sets, formulate fuzzy rules, describe maintenance requirements under different data type combinations, and infer the fuzzified input variables through fuzzy rules to determine the type of maintenance required for the target power equipment; Predicting the operational risk level of target power equipment refers to: The operation risk level of the target power equipment is predicted and analyzed through the time series model. The time series model adopts the ARIMAX model. The specific steps of predicting the operation risk level of the target power equipment through the time series model are as follows: Step 1: Obtain prediction data; Step 2: Establish ARIMAX model; Step 3: Use the maximum likelihood estimation method to estimate the ARIMAX model parameters; Step 4: Verify the effect of the fitting model and check the goodness of fit of the model through residual analysis; Step 5: Use the fitted model to predict the future operational risk level; The exogenous variables in the ARIMAX model include the partial discharge detection deviation index and the infrared imaging deviation index. The ARIMAX model formula is: ; is the error term at time point t, is a constant term, is the operational risk level at time point t-1, is the operational risk level at time point t, is the partial discharge detection deviation index at time point t, is the coefficient of the partial discharge detection deviation index, is the infrared imaging deviation index at time point t, is the coefficient of the infrared imaging deviation index, is the first-order autoregressive parameter, is the first-order moving average parameter; The logic for obtaining the partial discharge detection deviation index is as follows: characteristic data related to partial discharge detection are collected from the actual operation of the target power equipment and the standard operation of the power equipment, and then standardized, and finally the partial discharge detection deviation index D of the actual operation of the target power equipment and the standard operation of the power equipment is calculated using the Euclidean distance; The infrared imaging deviation index is used to measure the fluctuation of the number of hot spots in the infrared imaging map. The infrared imaging deviation index is the standard deviation of the number of hot spots.

2. A handheld intelligent inspection instrument integrating partial discharge detection and infrared imaging, based on the handheld intelligent inspection method integrating partial discharge detection and infrared imaging according to claim 1, characterized in that: It includes preliminary analysis module, judgment module, local analysis module, cloud analysis module and security maintenance module; The preliminary analysis module is used to collect environmental information and operation information of the target power equipment, and then conduct preliminary analysis together to generate a composite indicator index; The judgment module is used to select a simple threshold algorithm or a weighted comprehensive scoring algorithm based on the composite index to judge the collected operation information in a local-cloud collaborative mechanism manner, and to judge whether to use a local analysis or a cloud analysis method; The local analysis module is used to determine the type of maintenance by fuzzy reasoning when the local analysis method is selected; The cloud analysis module is used to predict the operating risk level of the target power equipment when the cloud analysis method is selected; The security maintenance module is used to execute corresponding maintenance strategies according to the maintenance type determined by the local analysis module, and to execute corresponding security strategies according to the operating risk level of the target power equipment predicted by the cloud analysis module.