Power grid monitoring system and method based on portable infrared detection equipment

Abstract

The invention provides a power grid monitoring system and method based on portable infrared detection equipment, and relates to the technical field of equipment monitoring, and the system comprises an infrared detection module which generates a real-time temperature report based on the portable infrared detection equipment; the determination module is used for determining historical equipment report data and historical equipment abnormal data of each piece of real-time to-be-detected equipment; the analysis module is used for determining equipment exception type data and equipment type feature vectors of each exception type of each real-time to-be-detected equipment; the construction module is used for constructing an abnormality diagnosis model of each real-time to-be-detected device; and the diagnosis module is used for calculating the predicted accurate value of each real-time to-be-detected device, determining real-time abnormal data and giving a real-time alarm to realize real-time monitoring of the power grid. The intelligent real-time monitoring of the power grid can be realized, the equipment abnormity type can be quickly and accurately identified, the diagnosis accuracy and reliability are improved, the dynamic optimization and self-adaption of the abnormity diagnosis model are realized, the operation and maintenance efficiency of the power grid is improved, and the safe and stable operation of the power grid is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment monitoring, and specifically to a power grid monitoring system and method based on a portable infrared detection device. Background Art

[0002] Traditional power grid monitoring mainly relies on manual inspections and fixed monitoring devices. Manual inspections are inefficient, labor-intensive, and it is difficult to detect equipment abnormalities in real time. Although fixed monitoring devices can provide certain real-time data, they lack flexibility and it is difficult to cover all key equipment and complex environments. With the expansion of the power grid scale and the increase in equipment complexity, traditional monitoring methods can no longer meet the high requirements of modern power grids for safety and reliability. In recent years, with the development of infrared detection technology, portable infrared detection devices have gradually been applied to power grid monitoring, but there is still a lack of systematic data processing and abnormal diagnosis capabilities.

[0003] Therefore, the present invention provides a power grid monitoring system and method based on a portable infrared detection device. Summary of the Invention

[0004] The present invention addresses the problems existing in the prior art and provides a power grid monitoring system and method based on a portable infrared detection device.

[0005] To achieve the above object, the technical solutions adopted by the present invention are as follows: On the one hand, the present invention provides a power grid monitoring system based on a portable infrared detection device, mainly including the following modules: Infrared detection module: Based on the portable infrared detection device, it real-time collects the real-time temperature data of the real-time equipment set to be detected in the power grid and generates a real-time temperature report; Determination module: Obtains the historical temperature report and historical abnormal data of the power grid, and determines the historical equipment report data and historical equipment abnormal data of each real-time equipment to be detected in the real-time equipment set to be detected; Analysis module: Based on the historical equipment report data and historical equipment abnormal data of each real-time equipment to be detected, determines the equipment abnormal type data of each abnormal type of each real-time equipment to be detected, and determines the equipment type feature vector of each abnormal type of each real-time equipment to be detected; Construction module: Based on the historical equipment report data, historical equipment abnormal data, and equipment type feature vectors of all abnormal types of each real-time equipment to be detected, constructs an abnormal diagnosis model for each real-time equipment to be detected; Diagnosis module: Based on the real-time temperature report and the abnormal diagnosis models of all real-time equipment to be detected, calculates the prediction accuracy value of each real-time equipment to be detected and determines the real-time abnormal data, and issues a real-time alarm based on the real-time abnormal data to achieve real-time monitoring of the power grid.

[0006] The power grid monitoring system based on a portable infrared detection device provided by the present invention, the infrared detection module, includes the following units: Real-time device set to be detected unit: Obtain the real-time monitoring requirements of the power grid at the current monitoring time point, and determine the real-time device set to be detected based on the real-time monitoring requirements. The real-time device set to be detected includes multiple real-time devices to be detected; Detection point unit: Based on the device structure of each real-time device to be detected in the real-time device set to be detected, determine multiple detection points for each real-time device to be detected; Real-time temperature sub-data unit: The operation and maintenance personnel carry a portable infrared detection device to collect the real-time temperature sub-data of all detection points of each real-time device to be detected in the real-time device set to be detected. The portable infrared detection device is integrated based on multiple processes and is at least composed of a lens, components, an infrared detector, and a printed circuit board; Real-time temperature data unit: Based on the real-time temperature sub-data of all real-time devices to be detected in the real-time device set to be detected, determine the real-time temperature data of the power grid.

[0007] The power grid monitoring system based on a portable infrared detection device provided by the present invention, the infrared detection module, further includes the following units: Real-time temperature sub-report unit: The portable infrared detection device generates a real-time temperature sub-report for each real-time device to be detected based on the template library and the real-time temperature sub-data of each real-time device to be detected collected in real time. The template library includes multiple preset professional report templates. The real-time temperature sub-report at least includes the real-time device to be detected label, the thermal imaging diagram of the real-time device to be detected, and the current monitoring time point; Real-time temperature report unit: Based on the real-time temperature sub-reports of all real-time devices to be detected in the real-time device set to be detected, determine the real-time temperature report of the power grid.

[0008] The power grid monitoring system based on a portable infrared detection device provided by the present invention, the determination module, includes the following units: Historical temperature report unit: Obtain the historical temperature reports of multiple historical monitoring time points before the current monitoring time point. The historical temperature report includes the historical temperature sub-reports of each historical detection device in the historical detection device set at the historical monitoring time point. The historical temperature sub-report at least includes the historical detection device label, the thermal imaging diagram of the historical detection device, and the historical monitoring time point; Historical Abnormal Data Unit: Obtain historical abnormal data of multiple historical monitoring time points before the current monitoring time point. The historical abnormal data includes historical abnormal sub-data of each historical detection device in the historical detection device set at the historical monitoring time point. The historical abnormal sub-data includes a historical detection device label, a historical monitoring time point, multiple historical abnormal regions, the abnormal type of each historical abnormal region, the area of the historical abnormal region, and the historical abnormal level.

[0009] According to the power grid monitoring system based on a portable infrared detection device provided by the present invention, the determination module further includes the following units: Historical Device Report Data Unit: Based on the real-time detection device label in the real-time temperature sub-report of each real-time device to be detected in the real-time temperature report, extract the historical temperature sub-reports corresponding to the historical detection device labels that are the same as the real-time detection device label in the historical temperature reports of all historical monitoring time points, and obtain the historical device report data of each real-time device to be detected in the real-time device to be detected set; Historical Device Abnormal Data Unit: Based on the real-time detection device label in the real-time temperature sub-report of each real-time device to be detected in the real-time temperature report, extract the historical abnormal sub-data corresponding to the historical detection device labels that are the same as the real-time detection device label in the historical abnormal data of all historical monitoring time points, and obtain the historical device abnormal data of each real-time device to be detected in the real-time device to be detected set.

[0010] According to the power grid monitoring system based on a portable infrared detection device provided by the present invention, the analysis module includes the following units: Historical Imaging Map Vector Unit: Extract features from the historical detection device thermal imaging map of each historical temperature sub-report in the historical device report data of each real-time device to be detected, and determine the historical imaging map vector of each historical temperature sub-report; Historical Abnormal Vector Unit: Extract features from each historical abnormal region of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected, and determine the historical abnormal vector of each historical abnormal region of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected in combination with the abnormal type and abnormal level of each historical abnormal region; Historical Sub-Thermal Imaging Map Unit: Based on each historical abnormal region of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected, map and intercept the historical detection device thermal imaging map in the historical temperature sub-report corresponding to the historical device report data of each real-time device to be detected, and determine the historical sub-thermal imaging map of each historical abnormal region of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected; Historical sub-imaging map vector unit: Extract features from the historical sub-thermal imaging maps of each historical abnormal area of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected, and determine the historical sub-imaging map vectors of the historical sub-thermal imaging maps of each historical abnormal area of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected; Device abnormal type data unit: Based on the abnormal types of all historical abnormal areas of all historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected, extract the historical abnormal vectors and historical sub-imaging map vectors of each historical abnormal area of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected, and determine the device abnormal type data of each abnormal type of each real-time device to be detected. The device abnormal type data includes the historical abnormal vectors and historical sub-imaging map vectors of multiple historical abnormal areas of multiple historical abnormal sub-data.

[0011] According to the power grid monitoring system based on a portable infrared detection device provided by the present invention, the analysis module includes the following units: Correlation covariance matrix unit: Based on the device abnormal type data of each abnormal type of each real-time device to be detected, and the historical imaging map vectors of all historical temperature sub-reports in the historical device report data of each real-time device to be detected, calculate the correlation covariance matrix of each abnormal type of each real-time device to be detected; Time region feature vector unit: Based on the historical device abnormal data of each real-time device to be detected, the device abnormal type data of each abnormal type of each real-time device to be detected, and the historical imaging map vectors of all historical temperature sub-reports in the historical device report data of each real-time device to be detected, calculate the first weight and region feature vector of each historical abnormal sub-data of each abnormal type of each real-time device to be detected, and calculate the time region feature vector of each abnormal type of each real-time device to be detected; Projection matrix unit: Perform singular value decomposition on the correlation covariance matrix of each abnormal type of each real-time device to be detected, extract the first specified number of principal component directions of the left singular vector matrix after singular value decomposition, and determine the projection matrix of each abnormal type of each real-time device to be detected; First feature vector unit: Vectorize the projection matrix of each abnormal type of each real-time device to be detected to determine the first feature vector of each abnormal type of each real-time device to be detected; Device type feature vector unit: Based on the time region feature vector and the first feature vector of each abnormal type of each real-time device to be detected, determine the device type feature vector of each abnormal type of each real-time device to be detected.

[0012] According to the power grid monitoring system based on a portable infrared detection device provided by the present invention, the construction module includes the following units: Device anomaly diagnosis model unit: taking the historical device report data of each real-time device to be detected as the input of the device anomaly diagnosis model of each real-time device to be detected, and taking the historical device anomaly data of each real-time device to be detected as the output of the device anomaly diagnosis model of each real-time device to be detected; Construction unit: constructing the device anomaly diagnosis model of each real-time device to be detected based on the device type feature vectors of all anomaly types of each real-time device to be detected.

[0013] According to the power grid monitoring system based on a portable infrared detection device provided by the present invention, the diagnosis module includes the following units: Real-time anomaly sub-data unit: inputting the real-time temperature sub-report of each real-time device to be detected in the real-time temperature report into the device anomaly diagnosis model of the corresponding real-time device to be detected, and determining the real-time anomaly sub-data of each real-time device to be detected based on the output result of the anomaly diagnosis model. The real-time anomaly sub-data includes the real-time device to be detected label, the current monitoring time point, multiple real-time anomaly regions, the first anomaly type of each real-time anomaly region, the size of the real-time anomaly region, and the real-time anomaly level; Real-time sub-thermal imaging map unit: mapping and intercepting the real-time device thermal imaging map in the real-time temperature sub-report of each real-time device to be detected based on each real-time anomaly region in the real-time anomaly sub-data of each real-time device to be detected, and determining the real-time sub-thermal imaging map of each real-time anomaly region in the real-time anomaly sub-data of each real-time device to be detected; Real-time sub-imaging map vector unit: extracting features from the real-time sub-thermal imaging map of each real-time anomaly region in the real-time anomaly sub-data of each real-time device to be detected, and determining the real-time sub-imaging map vector of each real-time anomaly region in the real-time anomaly sub-data of each real-time device to be detected; Sub-imaging map vector consistency value unit: calculating the consistency value between the real-time sub-imaging map vector of each real-time anomaly region in the real-time anomaly sub-data of each real-time device to be detected and the sub-imaging map vector of the device anomaly type data of each anomaly type of each real-time device to be detected based on all device anomaly type data, real-time anomaly sub-data, and the real-time sub-imaging map vectors of all real-time anomaly regions in the real-time anomaly sub-data of each real-time device to be detected; Second abnormal type unit: From the real-time sub-imaging map vectors of each real-time abnormal area in the real-time abnormal sub-data of each real-time device to be detected, and the consistent values of the sub-imaging map vectors of the device abnormal type data of each abnormal type of each real-time device to be detected, select the abnormal type corresponding to the maximum sub-imaging map vector consistent value as the second abnormal type of each real-time abnormal area in the real-time abnormal sub-data of each real-time device to be detected; Prediction accuracy value unit: Compare the first abnormal type and the second abnormal type of each real-time abnormal area in the real-time abnormal sub-data of each real-time device to be detected, and calculate the prediction accuracy value of each real-time device to be detected based on the comparison results of all real-time abnormal areas in the real-time abnormal sub-data of each real-time device to be detected; Optimization unit: Optimize the device abnormal diagnosis model of each real-time device to be detected with a prediction accuracy value lower than the preset threshold based on the real-time abnormal sub-data; Alarm unit: Determine the real-time abnormal data based on the real-time abnormal sub-data of all real-time devices to be detected with a prediction accuracy value higher than the preset threshold, and issue a real-time alarm based on the real-time abnormal sub-data of all real-time devices to be detected in the real-time abnormal data.

[0014] On the other hand, the present invention provides a power grid monitoring system based on a portable infrared detection device, which mainly includes the following steps: Step 1: Real-time collect the real-time temperature data of the set of real-time devices to be detected of the power grid based on the portable infrared detection device, and generate a real-time temperature report; Step 2: Obtain the historical temperature report and historical abnormal data of the power grid, and determine the historical device report data and historical device abnormal data of each real-time device to be detected in the set of real-time devices to be detected; Step 3: Based on the historical device report data and historical device abnormal data of each real-time device to be detected, determine the device abnormal type data of each abnormal type of each real-time device to be detected, and determine the device type feature vector of each abnormal type of each real-time device to be detected; Step 4: Based on the historical device report data, historical device abnormal data and device type feature vectors of all abnormal types of each real-time device to be detected, construct an abnormal diagnosis model for each real-time device to be detected; Step 4: Based on the real-time temperature report and the abnormal diagnosis models of all real-time devices to be detected, determine the real-time abnormal data, and issue a real-time alarm based on the real-time abnormal data to realize the real-time monitoring of the power grid.

[0015] Compared with the prior art, the present invention has the following beneficial effects: By using a portable infrared detection device to collect real-time temperature data of the power grid in real time, generating a real-time temperature report, determining the device anomaly type data and device type feature vectors of each anomaly type for each real-time device to be detected based on the obtained historical temperature reports and historical anomaly data, constructing an anomaly diagnosis model for each real-time device to be detected, and determining real-time anomaly data and issuing a real-time alarm based on the real-time temperature report and the anomaly diagnosis models of all real-time devices to be detected, real-time monitoring of the power grid is achieved. It can realize intelligent real-time monitoring of the power grid, quickly detect device anomalies, accurately identify the types of device anomalies, reduce misjudgments and missed judgments, improve the accuracy and reliability of diagnosis, realize dynamic optimization and self-adaptation of the anomaly diagnosis model, ensure that maintenance personnel can respond in a timely manner, reduce fault losses, improve the efficiency of power grid operation and maintenance, and ensure the safe and stable operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 FIG. is a schematic structural diagram of a power grid monitoring system based on a portable infrared detection device provided by an embodiment of the present invention.

[0017] Figure 2 FIG. is a schematic flow diagram of a power grid monitoring method based on a portable infrared detection device provided by an embodiment of the present invention.

[0018] Figure 3 FIG. is a Die Attach (DA) process flow of a portable infrared detection device provided by an embodiment of the present invention.

[0019] Figure 4 FIG. is a Wire Bonding process flow of a portable infrared detection device provided by an embodiment of the present invention.

[0020] Figure 5 FIG. is a Lens Holder Attach (LHA) process flow of a portable infrared detection device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] It should be noted that the methods used in the present invention are all conventional methods unless otherwise specified; the raw materials and devices used are all conventional commercially available products unless otherwise specified, and their sources are not specifically limited.

[0022] Example 1: An embodiment of the present invention provides a power grid monitoring system based on a portable infrared detection device, as Figure 1 shown, mainly including the following steps: Infrared detection module: Based on a portable infrared detection device, collect real-time temperature data of the set of real-time devices to be detected in the power grid in real time, and generate a real-time temperature report; Determination module: Obtain the historical temperature reports and historical abnormal data of the power grid, and determine the historical device report data and historical device abnormal data of each real-time device to be detected in the real-time device set to be detected; Analysis module: Based on the historical device report data and historical device abnormal data of each real-time device to be detected, determine the device abnormal type data of each abnormal type of each real-time device to be detected, and determine the device type feature vector of each abnormal type of each real-time device to be detected; Construction module: Based on the historical device report data, historical device abnormal data and device type feature vectors of all abnormal types of each real-time device to be detected, construct the abnormal diagnosis model of each real-time device to be detected; Diagnosis module: Based on the real-time temperature report and the abnormal diagnosis models of all real-time devices to be detected, calculate the prediction accuracy value of each real-time device to be detected and determine the real-time abnormal data, and issue a real-time alarm based on the real-time abnormal data to achieve real-time monitoring of the power grid.

[0023] In this embodiment, the infrared detection module is the data acquisition core of the system, and it collects the temperature data of power grid devices in real time based on portable infrared detection devices. These devices can non-contact measure the surface temperature of the devices and generate real-time temperature reports.

[0024] In this embodiment, the function of the determination module is to extract information related to the current device to be detected from historical data. By obtaining historical temperature reports and historical abnormal data, the system can determine the historical device report data and historical device abnormal data of each real-time device to be detected.

[0025] In this embodiment, the analysis module is the core part of the system and is responsible for extracting key features from historical data. Specifically, the analysis module determines the device abnormal type data of each abnormal type based on the historical device report data and historical device abnormal data of each real-time device to be detected, and generates a device type feature vector.

[0026] In this embodiment, the construction module constructs the abnormal diagnosis model of each real-time device to be detected based on the historical device report data, historical device abnormal data and device type feature vectors. These models can predict whether a device is abnormal and the type of abnormality according to real-time data by learning the abnormal patterns in historical data. Through the optimization of the feature vectors, the models can more accurately identify abnormalities and reduce false positives and false negatives.

[0027] In this embodiment, the diagnosis module is the output part of the system, which is responsible for calculating the predicted accurate value of each device to be detected in real time according to the real-time temperature report and the abnormal diagnosis model, and determining the real-time abnormal data. The system issues a real-time alarm based on the real-time abnormal data to notify the operation and maintenance personnel to respond in a timely manner. In addition, the diagnosis module also has a dynamic optimization function, which can adjust the diagnosis model according to real-time data to ensure the long-term stable operation of the system.

[0028] Beneficial effects of the above technical solution: Real-time temperature data of the power grid is collected by a portable infrared detection device in real time to generate a real-time temperature report. According to the obtained historical temperature report and historical abnormal data, the device abnormal type data and device type feature vector of each abnormal type of each device to be detected in real time are determined, and an abnormal diagnosis model for each device to be detected in real time is constructed. According to the real-time temperature report and the abnormal diagnosis models of all devices to be detected in real time, real-time abnormal data is determined and a real-time alarm is issued to realize the real-time monitoring of the power grid. It can realize the intelligent real-time monitoring of the power grid, quickly discover device abnormalities, accurately identify the types of device abnormalities, reduce misjudgment and missed judgment, improve the accuracy and reliability of diagnosis, realize the dynamic optimization and self-adaptation of the abnormal diagnosis model, ensure that the operation and maintenance personnel can respond in a timely manner, reduce fault losses, improve the operation and maintenance efficiency of the power grid, and ensure the safe and stable operation of the power grid.

[0029] Embodiment 2: The embodiment of the present invention provides a power grid monitoring system based on a portable infrared detection device. The infrared detection module includes the following units: Real-time device to be detected set unit: Obtain the real-time monitoring requirements of the power grid at the current monitoring time point, and determine the set of real-time devices to be detected based on the real-time monitoring requirements. The set of real-time devices to be detected includes multiple real-time devices to be detected; Detection point unit: Based on the device structure of each real-time device to be detected in the set of real-time devices to be detected, determine multiple detection points for each real-time device to be detected; Real-time temperature sub-data unit: The operation and maintenance personnel carry a portable infrared detection device to collect the real-time temperature sub-data of all detection points of each real-time device to be detected in the set of real-time devices to be detected. The portable infrared detection device is integrated based on multiple processes and is at least composed of a lens, components, an infrared detector, and a printed circuit board; Real-time temperature data unit: Based on the real-time temperature sub-data of all real-time devices to be detected in the set of real-time devices to be detected, determine the real-time temperature data of the power grid.

[0030] In this embodiment, the real-time monitoring requirements of the power grid at the current monitoring time point can be automatically generated according to the operating state of the power grid (such as load peak, equipment maintenance plan). For example, during the high-temperature period in summer, the main transformer and heavy-load lines are automatically included in the key detection set. When a new device is put into operation, the detection frequency of it is temporarily increased.

[0031] In this embodiment, 3D models of typical power grid equipment (such as windings, bushings, and cooling systems of transformers) are pre-stored, and key detection points (such as electrical connection points and heat dissipation channels) are automatically identified. For irregular equipment (such as GIS combined electrical appliances), the hot spot grid method is adopted to divide the equipment surface into detection grids of 5 cm × 5 cm; for easily heated parts (such as breaker contacts), high-density detection points are set (spacing ≤ 3 cm).

[0032] In this embodiment, the portable thermal imaging intelligent temperature measurement device mainly consists of four parts: Lens (lens), Holder (parts), Sensor (infrared detector), and PCBA (printed circuit board). Among them, the Sensor is the most core component. Since the resolution of traditional infrared detectors is 1280P and 640P, due to their large area array and high power consumption, it is difficult to meet the miniaturization requirements; while there have been significant technological breakthroughs in the low-power design of miniaturized infrared detectors such as 384P and 256P (power consumption reduced to less than 100 mW). The project team plans to use a 384P miniaturized infrared detector as the core component, and the remaining Lens (lens), Holder (parts), and PCBA (printed circuit board) use existing mature components from manufacturers for the overall hardware structure design.

[0033] In this embodiment, the portable infrared detection device is based on multiple process integrations, including the Lens + Holder combination process: This process mainly involves Les and Holder, and the main work is to pre-twist the two together to facilitate the subsequent LHA process. According to experience, it is appropriate to design the torque control between 30 kgfcm (torque unit) and 120 kgfcm. If the torque is too high, it will affect the implementation of the subsequent focusing station, and if it is too low, it may cause defocusing after focusing and before dispensing.

[0034] In this embodiment, the portable infrared detection device is based on multiple process integrations, and also includes the Die Attach (DA) process: In this process, glue is applied to the middle of the PCBA board, and the Sensor is accurately glued to the PCBA according to the optical positioning points to achieve a fixing effect. The key to this process is to select the glue technically. The glue selected for this project has characteristics such as high strength and strong temperature adaptability, as Figure 3 shown.

[0035] In this embodiment, the portable infrared detection device is based on multiple process integrations, and also includes the Wire Bonding process: In this process, electrical conduction between the Sensor and the PCBA board is achieved (the first solder joint and the second solder joint in the following figure). The project uses gold wire as the medium, and the diameter of the gold wire used is between 20 and 25 um. The process indicators include temperature, pressure, time, etc., asFigure 4 as shown

[0036] In this embodiment, the portable infrared detection device is based on multiple processes integration, and also includes the Lens Holder Attach (LHA) process flow: After the above three processes, the Lens has been locked to the Holder, and the Sensor has been electrically connected to the PCBA. In this process flow, the above two products are adhesively coupled. As Figure 5 shown, on the lens bonding machine, the principle is to rely on the positioning marks on the PCBA board and the Holder, and the CCD cameras in three directions to complete the coincidence correction of the optical centers of the Sensor and the Lens. The accuracy of this step of the thermal imaging module can reach within 25um.

[0037] In this embodiment, the portable infrared detection device is based on multiple processes integration, and also includes: the subsequent production process flow: the subsequent production process needs to be transferred to a thousand-class dust-free workshop, and there are two key steps: focusing and final inspection of the image. Compared with the visible light module, the focusing link of the thermal imaging module is very different because the imaging principle of the thermal imaging module is infrared light, and it requires the step difference of the target object's heat to act as the target object, that is, a black body is needed. The solution is to use the black body + metal four-bar target scheme, that is, in front of the high-temperature / low-temperature black body, a normal-temperature metal sheet is blocked, and multiple groups of four-bar target patterns are left on the metal sheet. Then, the focusing distance is set according to the lens focal length, and the automatic focusing function is realized in cooperation with the AF program customized for the thermal imaging.

[0038] The beneficial effects of the above technical solution: Based on the portable infrared detection device to collect the real-time temperature data of the real-time equipment set to be detected in the power grid in real time, it can provide data support for generating a real-time temperature report, realize on-demand monitoring to avoid monitoring blindness, and improve the monitoring efficiency.

[0039] Embodiment 3: The embodiment of the present invention provides a power grid monitoring system based on a portable infrared detection device, and the infrared detection module further includes the following units: Real-time temperature sub-report unit: The portable infrared detection device generates a real-time temperature sub-report for each real-time equipment to be detected based on the template library and the real-time temperature sub-data collected in real time. The template library includes multiple preset professional report templates, and the real-time temperature sub-report at least includes the real-time equipment to be detected label, the thermal imaging map of the real-time equipment to be detected, and the current monitoring time point; Real-time temperature report unit: Based on the real-time temperature sub-reports of all real-time equipment to be detected in the real-time equipment set to be detected, determine the real-time temperature report of the power grid.

[0040] In this embodiment, the template library presets a variety of professional report templates, and each template includes: a fixed-format area (such as a report header and an equipment information column); a dynamically generated area (such as a thermal imaging diagram and a temperature statistics table); template dynamic update: new templates can be pushed through the cloud; support for users to customize template fields (such as adding enterprise logos and specific analysis items).

[0041] In this embodiment, the thermal imaging diagram of the device to be detected in real time can use pseudo-color coding (such as blue-green-yellow-red indicating increasing temperature).

[0042] The beneficial effects of the above technical solution: generating a real-time temperature report can provide high-quality data support for determining real-time abnormal data, and improve the monitoring efficiency and detection accuracy.

[0043] Embodiment 4: The embodiment of the present invention provides a power grid monitoring system based on a portable infrared detection device. The determination module includes the following units: Historical temperature report unit: Obtain historical temperature reports at multiple historical monitoring time points before the current monitoring time point. The historical temperature report includes historical temperature sub-reports of each historical detection device in the historical detection device set at the historical monitoring time point. The historical temperature sub-report includes at least a historical detection device label, a historical thermal imaging diagram of the historical detection device, and a historical monitoring time point; Historical abnormal data unit: Obtain historical abnormal data at multiple historical monitoring time points before the current monitoring time point. The historical abnormal data includes historical abnormal sub-data of each historical detection device in the historical detection device set at the historical monitoring time point. The historical abnormal sub-data includes a historical detection device label, a historical monitoring time point, multiple historical abnormal areas, the abnormal type of each historical abnormal area, the area of the historical abnormal area, and the historical abnormal level.

[0044] In this embodiment, temperature reports of power grid equipment at multiple historical monitoring time points are obtained. It includes: Historical detection device label: used to uniquely identify each device; Historical thermal imaging diagram of the historical detection device: an image generated by thermal imaging technology, intuitively showing the temperature distribution on the surface of the device. The thermal imaging diagram can clearly show the hot spot area of the device, helping the operation and maintenance personnel quickly locate the overheated part, which is difficult to achieve by traditional temperature measurement methods; Historical monitoring time point: records the specific time of data collection.

[0045] In this embodiment, abnormal data of power grid equipment at multiple historical monitoring time points is obtained. These data record the abnormal situations that occurred during the past operation of the equipment and are important bases for diagnosing and preventing faults. The historical abnormal data includes the following key information: Historical detection device label: It is the same as the device label in the historical temperature report unit and is used to identify a specific device; Historical monitoring time point: Records the specific time when the abnormality occurred; Multiple historical abnormal areas: Clearly indicate the specific locations where abnormalities occurred on the device. In complex devices, different areas may have abnormalities for different reasons; Abnormality type for each historical abnormal area: Classify the abnormalities, such as overheating, short circuit, insulation aging, etc.; Historical abnormality level: Grade the severity of the abnormalities, such as minor, medium, and severe. The abnormality level helps operation and maintenance personnel quickly evaluate the urgency of the fault, prioritize the handling of severe abnormalities, and reasonably arrange maintenance resources.

[0046] Beneficial effects of the above technical solution: Obtaining the historical temperature report and historical abnormal data of the power grid can provide data support for determining historical device report data and historical device abnormal data, improve the comprehensiveness and reliability of monitoring, reduce operation and maintenance costs, and ensure the stable operation of the power grid.

[0047] Embodiment 5: The embodiment of the present invention provides a power grid monitoring system based on a portable infrared detection device. The determination module further includes the following units: Historical device report data unit: Based on the real-time detection device label of each real-time device to be detected in the real-time temperature report, extract the historical temperature sub-reports corresponding to the historical detection device labels that are the same as the real-time detection device label in the historical temperature reports at all historical monitoring time points, and obtain the historical device report data of each real-time device to be detected in the real-time device to be detected set; Historical device abnormal data unit: Based on the real-time detection device label of each real-time device to be detected in the real-time temperature report, extract the historical abnormal sub-data corresponding to the historical detection device labels that are the same as the real-time detection device label in the historical abnormal data at all historical monitoring time points, and obtain the historical device abnormal data of each real-time device to be detected in the real-time device to be detected set.

[0048] In this embodiment, the core function of the historical device report data unit is to extract the historical temperature data related to the currently real-time device to be detected. This process is based on the device tags in the real-time temperature report and is achieved through the following steps: First, the system extracts the tag information of each device to be detected from the real-time temperature report. The system traverses the historical temperature reports at all historical monitoring time points to find the historical detection device tags that match the tags of the real-time devices to be detected. Once a match is found, the system extracts the corresponding historical temperature sub-report. Through the above matching and extraction processes, the system finally determines the historical device report data for each real-time device to be detected.

[0049] In this embodiment, the function of the historical device anomaly data unit is to extract the historical anomaly data related to the currently real-time device to be detected. This process is also based on the device tags in the real-time temperature report and is achieved through the following steps: The system extracts the tag information of each device to be detected from the real-time temperature report as the key basis for data retrieval. The system traverses the historical anomaly data at all historical monitoring time points to find the historical detection device tags that match the tags of the real-time devices to be detected. Once a match is found, the system extracts the corresponding historical anomaly sub-data. Through the above matching and extraction processes, the system finally determines the historical device anomaly data for each real-time device to be detected. These data include detailed information such as the anomaly type, anomaly area, and anomaly level that occurred during the past operation of the device.

[0050] Beneficial effects of the above technical solution: Determining the historical device report data and historical device anomaly data for each real-time device to be detected in the set of real-time devices to be detected can achieve personalized extraction, improve the pertinence and accuracy of detection, and enhance the detection accuracy.

[0051] Embodiment 6: The embodiment of the present invention provides a power grid monitoring system based on a portable infrared detection device, and an analysis module, including the following units: Historical imaging map vector unit: Extract features from the historical detection device thermal imaging maps of each historical temperature sub-report in the historical device report data of each real-time device to be detected, and determine the historical imaging map vector of each historical temperature sub-report; Historical anomaly vector unit: Extract features from each historical anomaly area of each historical anomaly sub-data in the historical device anomaly data of each real-time device to be detected, and combine the anomaly type and anomaly level of each historical anomaly area to determine the historical anomaly vector of each historical anomaly area of each historical anomaly sub-data in the historical device anomaly data of each real-time device to be detected; Historical sub-thermal imaging map unit: Based on each historical abnormal area of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected, map and intercept the historical detection device thermal imaging map in the historical temperature sub-report corresponding to the historical device report data of each real-time device to be detected, and determine the historical sub-thermal imaging map of each historical abnormal area of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected; Historical sub-imaging map vector unit: Extract features from the historical sub-thermal imaging map of each historical abnormal area of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected, and determine the historical sub-imaging map vector of the historical sub-thermal imaging map of each historical abnormal area of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected; Device abnormal type data unit: Based on the abnormal types of all historical abnormal areas of all historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected, extract the historical abnormal vectors and historical sub-imaging map vectors of each historical abnormal area of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected, and determine the device abnormal type data of each abnormal type of each real-time device to be detected. The device abnormal type data includes the historical abnormal vectors and historical sub-imaging map vectors of multiple historical abnormal areas of multiple historical abnormal sub-data.

[0052] In this embodiment, the main function of the historical imaging map vector unit is to extract features from the historical detection device thermal imaging map in the historical device report data of each real-time device to be detected. The specific steps are as follows: The system analyzes the historical detection device thermal imaging map in each obtained historical temperature sub-report and extracts key features. Convert the extracted features into vector form.

[0053] In this embodiment, the main function of the historical abnormal vector unit is to extract features from the historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected. The specific steps are as follows: The system obtains each historical abnormal sub-data, including information such as the abnormal area, abnormal type, and abnormal level. Combine the abnormal type and abnormal level to extract features from each historical abnormal area. For example, for overheating abnormalities, the features may include the temperature range and area of the abnormal area; for insulation aging abnormalities, the features may include the texture changes in the abnormal area. Convert the extracted features into vector form. These vectors not only contain information about the type and level of the abnormality but also further refine the detailed information of the abnormality through feature extraction.

[0054] In this embodiment, the main function of the historical sub-thermal imaging map unit is to extract sub-thermal imaging maps related to the abnormal area from the historical thermal imaging maps according to the historical abnormal area. The specific steps are as follows: The system locates the corresponding area in the historical thermal imaging map according to the abnormal area information in the historical abnormal sub-data. Map and intercept the area corresponding to the abnormal area in the thermal imaging map to generate historical sub-thermal imaging maps. These sub-thermal imaging maps focus on the abnormal area and can more clearly show the temperature distribution of the abnormal area. Through the mapping and intercepting operations, the system generates historical sub-thermal imaging maps for each historical abnormal area.

[0055] In this embodiment, the main function of the historical sub-imaging map vector unit is to extract features from the historical sub-thermal imaging maps to generate historical sub-imaging map vectors. The specific steps are as follows: The system obtains each historical sub-thermal imaging map, which has been generated by the historical sub-thermal imaging map unit and focuses on the abnormal area. Analyze the sub-thermal imaging maps to extract key features. Since these maps focus on the abnormal area, feature extraction can more accurately reflect the abnormal situation. Convert the extracted features into vector form. These vectorized data further refine the feature information of the abnormal area.

[0056] In this embodiment, the main function of the device abnormal type data unit is to integrate the historical abnormal vectors and historical sub-imaging map vectors to determine the device abnormal type data for each abnormal type of each real-time device to be detected. The specific steps are as follows: The system integrates the historical abnormal vectors and historical sub-imaging map vectors of all historical abnormal sub-data according to the abnormal type. Generate device abnormal type data for each abnormal type. These data include historical abnormal vectors and historical sub-imaging map vectors of multiple historical abnormal areas of multiple historical abnormal sub-data.

[0057] In this embodiment, the historical imaging map vector may include the global average temperature, global temperature variance, global maximum temperature, global temperature gradient distribution, and global temperature peak value of the historical detection device thermal imaging map corresponding to the historical temperature sub-report in the historical device report data.

[0058] In this embodiment, the historical abnormal vector may include the abnormal type, abnormal level, historical abnormal area area complexity, etc. of the historical abnormal area of the historical abnormal sub-data in the corresponding historical device abnormal data.

[0059] In this embodiment, the historical sub-imaging map vector may include the local average temperature, local temperature variance, local maximum temperature, local temperature gradient distribution, and local temperature peak value of the historical abnormal area of the historical abnormal sub-data in the corresponding historical device abnormal data.

[0060] Beneficial effects of the above technical solution: Based on the historical device report data and historical device anomaly data of each real-time device to be detected, the device anomaly type data of each anomaly type of each real-time device to be detected can be determined, enabling refined sign extraction to improve monitoring accuracy and achieving multi-dimensional data fusion to enhance the comprehensiveness of monitoring.

[0061] Example 7: The embodiment of the present invention provides a power grid monitoring system based on a portable infrared detection device, and an analysis module, including the following units: Correlation covariance matrix unit: Based on the device anomaly type data of each anomaly type of each real-time device to be detected, and the historical imaging map vectors of all historical temperature sub-reports in the historical device report data of each real-time device to be detected, calculate the correlation covariance matrix of each anomaly type of each real-time device to be detected; Time region feature vector unit: Based on the historical device anomaly data of each real-time device to be detected, the device anomaly type data of each anomaly type of each real-time device to be detected, and the historical imaging map vectors of all historical temperature sub-reports in the historical device report data of each real-time device to be detected, calculate the first weight and region feature vector of each historical anomaly sub-data of each anomaly type of each real-time device to be detected, and calculate the time region feature vector of each anomaly type of each real-time device to be detected; Projection matrix unit: Perform singular value decomposition on the correlation covariance matrix of each anomaly type of each real-time device to be detected, extract the first specified number of principal component directions of the left singular vector matrix after singular value decomposition, and determine the projection matrix of each anomaly type of each real-time device to be detected; First feature vector unit: Vectorize the projection matrix of each anomaly type of each real-time device to be detected to determine the first feature vector of each anomaly type of each real-time device to be detected; Device type feature vector unit: Based on the time region feature vector and the first feature vector of each anomaly type of each real-time device to be detected, determine the device type feature vector of each anomaly type of each real-time device to be detected.

[0062] In this embodiment, the correlation covariance matrix unit: Based on the device anomaly type data of each anomaly type of each real-time device to be detected, and the historical imaging map vectors of all historical temperature sub-reports in the historical device report data of each real-time device to be detected, calculate the correlation covariance matrix of each anomaly type of each real-time device to be detected. The calculation formula of the correlation covariance matrix can be: ; ; Where represents the correlation covariance matrix of the j-th abnormal type of the i-th real-time device to be detected, and ijN2 represents the number of historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected, represents the number of historical abnormal regions in the t-th historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected, represents the historical sub-image vector of the historical sub-thermal imaging map of the k-th historical abnormal region in the t-th historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected, represents the historical image vector of the historical detection device thermal imaging map of the historical temperature sub-report in the historical device report data corresponding to the t-th historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected, represents the average historical sub-image vector of the historical sub-thermal imaging maps of all historical abnormal regions in the t-th historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected, represents the average historical image vector of the historical detection device thermal imaging maps of all historical temperature sub-reports in the historical device report data corresponding to the t-th historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected, represents the historical sub-image vector of the historical sub-thermal imaging map of the k-th historical abnormal region in the t-th historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected, and the average historical sub-image vector of the historical sub-thermal imaging maps of all historical abnormal regions in the t-th historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected, based on the first indicator function of the j-th abnormal type, represents the j-th abnormal type, represents the abnormal type of the k-th historical abnormal region in the t-th historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected.

[0063] In this embodiment, represents the number of all historical abnormal regions in all historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected.

[0064] In this embodiment, the correlation covariance matrix The association between the historical sub - imaging map vectors of all historical abnormal regions of all historical abnormal sub - data of the device abnormal type data of the j - th abnormal type of the i - th real - time device to be detected, and the historical imaging map vectors of all historical temperature sub - reports in the historical device report data corresponding to all historical abnormal sub - data of the j - th abnormal type of the i - th real - time device to be detected.

[0065] In this embodiment, The matrix dimension of is determined according to the vector dimension of the historical sub - imaging map vector and the vector dimension of the historical imaging map vector For example, if the vector dimension of the historical sub - imaging map vector is D1, and the vector dimension of the historical imaging map vector is D2, then The matrix dimension of is D1×D2.

[0066] In this embodiment, represents the transposed vector of the difference between the historical imaging map vector and the draw - level historical imaging map vector

[0067] In this embodiment, the time - region feature vector unit: Based on the historical device abnormal data of each real - time device to be detected, the device abnormal type data of each abnormal type of each real - time device to be detected, and the historical imaging map vectors of all historical temperature sub - reports in the historical device report data of each real - time device to be detected, calculate the first weight and region feature vector of each historical abnormal sub - data of each abnormal type of each real - time device to be detected, and calculate the time - region feature vector of each abnormal type of each real - time device to be detected. The calculation formula of the time - region feature vector can be: ; ; ; ; ; ; Among them, represents the deviation value of the historical sub - imaging map vector of the k - th historical abnormal region of the t - th historical abnormal sub - data in the device abnormal type data of the j - th abnormal type of the i - th real - time device to be detected based on the historical imaging map vector of the historical detection device thermal imaging map corresponding to the t - th historical abnormal sub - data, ​The first weight of the t-th historical abnormal sub-data of the device abnormal type data of the j-th abnormal type of the i-th device to be detected in real time Indicates the abnormal type of the b-th historical abnormal area of the a-th historical abnormal sub-data in the historical device abnormal data of the i-th device to be detected in real time Indicates the number of historical abnormal areas of the a-th historical abnormal sub-data in the historical device abnormal data of the i-th device to be detected in real time Indicates the time decay factor Indicates the current monitoring time point Indicates the historical monitoring time point of the a-th historical abnormal sub-data in the historical device abnormal data of the i-th device to be detected in real time; The second weight of the k-th historical abnormal area of the t-th historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th device to be detected in real time Indicates the historical abnormal area area of the k-th historical abnormal area of the t-th historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th device to be detected in real time Indicates the area of the historical detection device thermal imaging map of the historical temperature sub-report in the historical device report data corresponding to the t-th historical abnormal sub-data of the device abnormal type data of the j-th abnormal type of the i-th device to be detected in real time Indicates the area feature vector of all historical abnormal areas of the t-th historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th device to be detected in real time The second weight of the k-th historical abnormal area of the t-th historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th device to be detected in real time, based on the second indicator function of the j-th abnormal type Indicates the historical abnormal vector of the k-th historical abnormal area of the t-th historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th device to be detected in real time Indicates the time area feature vector of all historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th device to be detected in real time

[0068] In this embodiment Measure the historical sub-imaging map vector And the historical imaging map vector The distance between The larger it is, the greater the difference between the historical sub-thermal imaging map of the k-th historical abnormal area of the t-th historical abnormal sub-data of the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected and the historical imaging map vector of the historical temperature sub-report in the historical device report data corresponding to the t-th historical abnormal sub-data of the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected, indicating a higher degree of abnormality in this historical abnormal area.

[0069] In this embodiment, represents the historical abnormal vector , the historical sub-imaging map vector and the deviation value of the concatenated vector.

[0070] In this embodiment, represents the regional feature vector and the historical imaging map vector of the concatenated vector.

[0071] In this embodiment, the main function of the projection matrix unit is to extract key features through singular value decomposition and generate a projection matrix. The specific steps are as follows: perform singular value decomposition on the correlation covariance matrix of each abnormal type of each real-time device to be detected. Singular value decomposition is a commonly used dimensionality reduction technique that can decompose a matrix into singular values, left singular vectors, and right singular vectors. Extract the specified number of principal component directions from the left singular vector matrix after singular value decomposition. The principal component directions reflect the main change trends of the data, can effectively reduce the dimension and extract key features. Combine the extracted principal component directions into a projection matrix. The projection matrix is used to project the original data into a low-dimensional space.

[0072] In this embodiment, the main function of the first feature vector unit is to vectorize the projection matrix to generate the first feature vector. The specific steps are as follows: perform a matrix vectorization operation on the projection matrix of each abnormal type of each real-time device to be detected. Matrix vectorization is the process of expanding a matrix into a one-dimensional vector. Through matrix vectorization, the first feature vector of each abnormal type is generated. The first feature vector is a compact representation of the projection matrix and can further simplify the data.

[0073] In this embodiment, the main function of the device type feature vector unit is to integrate the time region feature vector and the first feature vector to generate the device type feature vector. The specific steps are as follows: The system combines the time region feature vector and the first feature vector of each abnormal type. Through concatenation and integration, the device type feature vector of each abnormal type is generated. The device type feature vector is the final feature vector that comprehensively considers time, region, and principal component features.

[0074] Beneficial effects of the above technical solution: By determining the device type feature vectors of each abnormal type for each real-time device to be detected, accurate abnormal correlation analysis and multi-dimensional feature integration can be achieved, improving the comprehensiveness and accuracy of monitoring and enhancing the monitoring accuracy.

[0075] Example 8: The embodiment of the present invention provides a power grid monitoring system based on a portable infrared detection device. The construction module includes the following units: Device abnormal diagnosis model unit: Using the historical device report data of each real-time device to be detected as the input of the device abnormal diagnosis model of each real-time device to be detected, and using the historical device abnormal data of each real-time device to be detected as the output of the device abnormal diagnosis model of each real-time device to be detected; Construction unit: Based on the device type feature vectors of all abnormal types of each real-time device to be detected, construct the device abnormal diagnosis model of each real-time device to be detected.

[0076] In this embodiment, the historical device abnormal data of each real-time device to be detected is used as the output of the device abnormal diagnosis model. The historical device abnormal data records the abnormal situations that occurred during the past operation of the device, including detailed information such as abnormal types, abnormal areas, and abnormal levels. These data are the targets for model learning and are used to train the model to identify abnormal patterns.

[0077] In this embodiment, by clarifying the input and output data, a clear data basis is provided for the construction of the device abnormal diagnosis model. The input data provides the background information of the device operation, while the output data provides the label information of the abnormality, enabling the model to learn the mapping relationship between the device operation state and the abnormality.

[0078] In this embodiment, the main function of the construction unit is to construct the device abnormal diagnosis model of each real-time device to be detected based on the device type feature vectors. The specific steps are as follows: The system constructs the device abnormal diagnosis model according to the device type feature vectors of each abnormal type of each real-time device to be detected. The construction process of the model is to learn the mapping relationship between the input feature vectors and the output abnormal data, enabling the model to predict whether the device has an abnormality and the type of the abnormality based on the input device operation data.

[0079] Beneficial effects of the above technical solution: Based on the historical device report data, historical device abnormal data, and device type feature vectors of all abnormal types of each real-time device to be detected, constructing the abnormal diagnosis model of each real-time device to be detected can improve the accuracy and generalization ability of the abnormal diagnosis model and enhance the recognition ability of different abnormal types.

[0080] Example 9: The embodiment of the present invention provides a power grid monitoring system based on a portable infrared detection device, and a construction module, including the following units: Real-time abnormal sub-data unit: Input the real-time temperature sub-report of each real-time device to be detected in the real-time temperature report into the device abnormal diagnosis model of the corresponding real-time device to be detected, and determine the real-time abnormal sub-data of each real-time device to be detected based on the output result of the abnormal diagnosis model. The real-time abnormal sub-data includes the real-time device to be detected label, the current monitoring time point, multiple real-time abnormal regions, the first abnormal type of each real-time abnormal region, the size of the real-time abnormal region, and the real-time abnormal level; Real-time sub-thermal imaging map unit: Based on each real-time abnormal region in the real-time abnormal sub-data of each real-time device to be detected, map and intercept the real-time device thermal imaging map in the real-time temperature sub-report of each real-time device to be detected in the real-time temperature report, and determine the real-time sub-thermal imaging map of each real-time abnormal region in the real-time abnormal sub-data of each real-time device to be detected; Real-time sub-imaging map vector unit: Extract features from the real-time sub-thermal imaging map of each real-time abnormal region in the real-time abnormal sub-data of each real-time device to be detected, and determine the real-time sub-imaging map vector of each real-time abnormal region in the real-time abnormal sub-data of each real-time device to be detected; Sub-imaging map vector consistency value unit: Based on all device abnormal type data, real-time abnormal sub-data of each real-time device to be detected, and the real-time sub-imaging map vectors of all real-time abnormal regions in the real-time abnormal sub-data, calculate the real-time sub-imaging map vector of each real-time abnormal region in the real-time abnormal sub-data of each real-time device to be detected, and the sub-imaging map vector consistency value with the device abnormal type data of each abnormal type of each real-time device to be detected; Second abnormal type unit: Select the abnormal type corresponding to the maximum sub-imaging map vector consistency value from the real-time sub-imaging map vectors of each real-time abnormal region in the real-time abnormal sub-data of each real-time device to be detected and the sub-imaging map vector consistency values with the device abnormal type data of each abnormal type of each real-time device to be detected as the second abnormal type of each real-time abnormal region in the real-time abnormal sub-data of each real-time device to be detected; Prediction accuracy value unit: Compare the first abnormal type and the second abnormal type of each real-time abnormal region in the real-time abnormal sub-data of each real-time device to be detected, and calculate the prediction accuracy value of each real-time device to be detected based on the comparison results of all real-time abnormal regions in the real-time abnormal sub-data of each real-time device to be detected; Optimization unit: Optimize the device abnormal diagnosis model of each real-time device to be detected with a prediction accuracy value lower than the preset threshold based on the real-time abnormal sub-data; Alarm unit: Determine real-time abnormal data based on the real-time abnormal sub-data of all real-time devices to be detected with predicted accurate values higher than the preset threshold, and issue real-time alarms based on the real-time abnormal sub-data of all real-time devices to be detected in the real-time abnormal data.

[0081] In this embodiment, the core function of the real-time abnormal sub-data unit is to input the data in the real-time temperature report into the device abnormal diagnosis model and output real-time abnormal sub-data. The specific steps are as follows: Input the real-time temperature sub-report of each real-time device to be detected in the real-time temperature report into the corresponding device abnormal diagnosis model. Based on the output result of the device abnormal diagnosis model, determine the real-time abnormal sub-data of each real-time device to be detected. The real-time abnormal sub-data includes the following detailed information: Real-time device to be detected label: Used to uniquely identify the device; Current monitoring time point: Records the specific time of data collection; Multiple real-time abnormal areas: Identifies the specific locations where abnormalities occur on the device; The first abnormal type of each real-time abnormal area; Real-time abnormal area size: The range size of the abnormal area; Real-time abnormal level: Grades the severity of the abnormality.

[0082] In this embodiment, the main function of the real-time sub-thermal imaging map unit is to extract the corresponding sub-thermal imaging map from the real-time thermal imaging map according to the real-time abnormal area. The specific steps are as follows: Based on the real-time abnormal area information in the real-time abnormal sub-data, locate the corresponding area in the real-time thermal imaging map. Map and intercept the real-time thermal imaging map to extract the sub-thermal imaging map corresponding to the abnormal area. These sub-thermal imaging maps focus on the abnormal area and can more clearly show the temperature distribution of the abnormal area. Through mapping and intercepting operations, generate the real-time sub-thermal imaging map of each real-time abnormal area.

[0083] In this embodiment, the main function of the real-time sub-imaging map vector unit is to extract features from the real-time sub-thermal imaging map and generate real-time sub-imaging map vectors. The specific steps are as follows: Receive the real-time sub-thermal imaging map of each real-time abnormal area. Analyze the real-time sub-thermal imaging map and extract key features. Convert the extracted features into vector form.

[0084] In this embodiment, the sub-imaging map vector consistency value unit: Based on all device abnormal type data, real-time abnormal sub-data of each real-time device to be detected, and the real-time sub-imaging map vectors of all real-time abnormal areas in the real-time abnormal sub-data, calculate the real-time sub-imaging map vector of each real-time abnormal area in the real-time abnormal sub-data of each real-time device to be detected, and the sub-imaging map vector consistency value of the sub-imaging map vector of each abnormal type of each real-time device to be detected. The calculation formula of the sub-imaging map vector consistency value can be expressed as: ; ; ; ; wherein, represents the consistency value of the real-time sub-image map vector of the p-th real-time abnormal area in the real-time abnormal sub-data of the i-th real-time device to be detected and the sub-image map vector of the historical sub-image map vectors of all historical abnormal areas in the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected; represents the real-time sub-image map vector of the p-th real-time abnormal area in the real-time abnormal sub-data of the i-th real-time device to be detected; represents the historical sub-image map vector of the historical sub-thermal image of the k-th historical abnormal area of the t-th historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected, based on the third indication function of the j-th abnormal type; represents the historical sub-image map vector of the historical sub-thermal image of the k-th historical abnormal area of the t-th historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected, based on the fourth indication function of the j-th abnormal type; represents the similarity value of the real-time sub-image map vector of the p-th real-time abnormal area in the real-time abnormal sub-data of the i-th real-time device to be detected and the historical sub-image map vector of the k-th historical abnormal area of the t-th historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected; represents the probability of occurrence of the j-th abnormal type in all device abnormal type data of the i-th real-time device to be detected.

[0085] In this embodiment, represents the number of historical abnormal areas in all historical abnormal sub-data of the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected, where the abnormal type is equal to the j-th abnormal type.

[0086] In this embodiment, represents the number of all historical abnormal areas in all historical abnormal sub-data of the device abnormal type data of all abnormal types of the i-th real-time device to be detected.

[0087] In this embodiment, represents the similarity value of the real-time sub-image map vector of the p-th real-time abnormal area in the real-time abnormal sub-data of the i-th real-time device to be detected and the historical sub-image map vector of all historical abnormal areas in the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected.

[0088] In this embodiment, It represents the average similarity value between the real-time sub-image vector of the p-th real-time abnormal area in the real-time abnormal sub-data of the i-th real-time device to be detected and the historical sub-image vectors of all historical abnormal areas in all historical abnormal sub-data of the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected.

[0089] In this embodiment, the prediction accuracy value unit: calculates the prediction accuracy value of each real-time device to be detected based on the comparison results of all real-time abnormal areas in the real-time abnormal sub-data of each real-time device to be detected. The calculation formula of the prediction accuracy value can be: ; ; ; ; Among them, represents the prediction accuracy value of the i-th real-time device to be detected, represents the first abnormal type of the p-th real-time abnormal area in the real-time abnormal sub-data of the i-th real-time device to be detected, represents the second abnormal type of the p-th real-time abnormal area in the real-time abnormal sub-data of the i-th real-time device to be detected, The comparison result of the p-th real-time abnormal area in the real-time abnormal sub-data of the i-th real-time device to be detected, iN4 represents the number of real-time abnormal areas in the real-time abnormal sub-data of the i-th real-time device to be detected, represents the probability that the g-th abnormal level of the j-th abnormal type occurs in all device abnormal type data of the i-th real-time device to be detected, represents the historical abnormal level of the k-th historical abnormal area of the t-th historical abnormal sub-data in the device abnormal type data of the j-th abnormal type of the i-th real-time device to be detected, represents the g-th abnormal level of the j-th abnormal type, The real-time abnormal level of the p-th real-time abnormal area in the real-time abnormal sub-data of the i-th real-time device to be detected, jN5 represents the number of abnormal levels of the j-th abnormal type, represents the abnormal level indication function of the p-th real-time abnormal area in the real-time abnormal sub-data of the i-th real-time device to be detected.

[0090] In this embodiment, the main function of the optimization unit is to dynamically optimize the device anomaly diagnosis model based on the predicted accurate value. The specific steps are as follows: Identify devices with predicted accurate values lower than the preset threshold. Based on the real-time anomaly sub-data, optimize the anomaly diagnosis models of these devices. The optimization process may include adjusting model parameters, updating model structures, or retraining models. Optimization result feedback: Reapply the optimized model to real-time monitoring to ensure that the model is always in the best state.

[0091] In this embodiment, the main function of the alarm unit is to issue real-time alarms based on real-time anomaly data with high accurate values. The specific steps are as follows: High-accurate value screening: Screen devices with predicted accurate values higher than the preset threshold. Based on the real-time anomaly sub-data of these devices, determine the real-time anomaly data. Issue real-time alarms according to the real-time anomaly data to notify the operation and maintenance personnel to respond in a timely manner.

[0092] Beneficial effects of the above technical solution: Calculate the predicted accurate value of each real-time device to be detected and determine the real-time anomaly data based on the real-time temperature report and the anomaly diagnosis models of all real-time devices to be detected. Issue real-time alarms based on the real-time anomaly data to achieve real-time monitoring of the power grid. It can achieve accurate identification of real-time anomalies, improve the real-time performance and accuracy of power grid monitoring, double-verify the anomaly types to reduce misjudgment and enhance the diagnostic reliability, improve the adaptive ability of monitoring, reduce fault losses, and ensure the stable operation of the power grid.

[0093] Embodiment 10: The embodiment of the present invention provides a power grid monitoring method based on a portable infrared detection device, as Figure 2 shown, mainly including the following steps: Step 1: Based on the portable infrared detection device, collect the real-time temperature data of the set of real-time devices to be detected in the power grid in real time and generate a real-time temperature report; Step 2: Obtain the historical temperature report and historical anomaly data of the power grid, and determine the historical device report data and historical device anomaly data of each real-time device to be detected in the set of real-time devices to be detected; Step 3: Based on the historical device report data and historical device anomaly data of each real-time device to be detected, determine the device anomaly type data of each anomaly type of each real-time device to be detected, and determine the device type feature vector of each anomaly type of each real-time device to be detected; Step 4: Based on the historical device report data, historical device anomaly data of each real-time device to be detected, and the device type feature vectors of all anomaly types, construct the anomaly diagnosis model of each real-time device to be detected; Step 4: Based on the real-time temperature report and the anomaly diagnosis models of all real-time devices to be detected, determine the real-time anomaly data, issue real-time alarms based on the real-time anomaly data, and achieve real-time monitoring of the power grid.

[0094] Beneficial effects of the above technical solution: By using a portable infrared detection device to collect real-time temperature data of the power grid in real time, generating a real-time temperature report, determining the device anomaly type data and device type feature vectors of each anomaly type for each real-time device to be detected based on the obtained historical temperature reports and historical anomaly data, constructing an anomaly diagnosis model for each real-time device to be detected, and determining real-time anomaly data and issuing a real-time alarm based on the real-time temperature report and the anomaly diagnosis models of all real-time devices to be detected, real-time monitoring of the power grid is achieved. It can realize intelligent real-time monitoring of the power grid, quickly detect device anomalies, accurately identify the types of device anomalies, reduce misjudgments and missed judgments, improve the accuracy and reliability of diagnosis, realize dynamic optimization and self-adaptation of the anomaly diagnosis model, ensure that maintenance personnel can respond in a timely manner, reduce fault losses, improve the efficiency of power grid operation and maintenance, and ensure the safe and stable operation of the power grid.

[0095] Finally, it should be noted that the above content is only used to illustrate the technical solution of the present invention, rather than limiting the protection scope of the present invention. Any simple modification or equivalent replacement made by those of ordinary skill in the art to the technical solution of the present invention shall not depart from the essence and scope of the technical solution of the present invention.

Claims

1. A power grid monitoring system based on a portable infrared detection device, characterized in that: It includes the following modules: Infrared detection module: Based on the portable infrared detection device, it collects the real-time temperature data of the real-time device set to be detected in the power grid in real time and generates a real-time temperature report; Determination module: Obtains the historical temperature report and historical abnormal data of the power grid, and determines the historical device report data and historical device abnormal data of each real-time device to be detected in the real-time device set to be detected; Analysis module: Based on the historical device report data and historical device abnormal data of each real-time device to be detected, determines the device abnormal type data of each abnormal type of each real-time device to be detected, and determines the device type feature vector of each abnormal type of each real-time device to be detected; Construction module: Based on the historical device report data, historical device abnormal data of each real-time device to be detected, and the device type feature vectors of all abnormal types, constructs an abnormal diagnosis model for each real-time device to be detected; Diagnosis module: Based on the real-time temperature report and the abnormal diagnosis models of all real-time devices to be detected, calculates the predicted accurate value of each real-time device to be detected and determines the real-time abnormal data, and issues a real-time alarm based on the real-time abnormal data to achieve real-time monitoring of the power grid.

2. The power grid monitoring system based on the portable infrared detection device according to claim 1, characterized in that: The infrared detection module includes the following units: Real-time device set unit to be detected: Obtains the real-time monitoring requirements of the power grid at the current monitoring time point, and determines the real-time device set to be detected based on the real-time monitoring requirements. The real-time device set to be detected includes multiple real-time devices to be detected; Detection point unit: Based on the device structure of each real-time device to be detected in the real-time device set to be detected, determines multiple detection points for each real-time device to be detected; Real-time temperature sub-data unit: The operation and maintenance personnel carry the portable infrared detection device to collect the real-time temperature sub-data of all detection points of each real-time device to be detected in the real-time device set to be detected. The portable infrared detection device is integrated based on multiple processes and is at least composed of a lens, components, an infrared detector, and a printed circuit board; Real-time temperature data unit: Based on the real-time temperature sub-data of all real-time devices to be detected in the real-time device set to be detected, determines the real-time temperature data of the power grid.

3. The power grid monitoring system based on the portable infrared detection device according to claim 2, wherein: The infrared detection module also includes the following units: Real-time temperature sub-report unit: The portable infrared detection device generates a real-time temperature sub-report for each real-time device to be detected based on the template library and the real-time temperature sub-data of each real-time device to be detected collected in real time. The template library includes multiple preset professional report templates. The real-time temperature sub-report at least includes the real-time device to be detected label, the thermal imaging diagram of the real-time device to be detected, and the current monitoring time point; Real-time temperature report unit: Based on the real-time temperature sub-reports of all real-time devices to be detected in the real-time device set to be detected, determines the real-time temperature report of the power grid.

4. The power grid monitoring system based on the portable infrared detection device according to claim 1, characterized in that: The determination module includes the following units: Historical Temperature Report Unit: Obtain historical temperature reports for multiple historical monitoring time points before the current monitoring time point. The historical temperature report includes historical temperature sub-reports for each historical detection device in the historical detection device set at the historical monitoring time point. The historical temperature sub-report includes at least the historical detection device label, the historical thermal imaging map of the historical detection device, and the historical monitoring time point. Historical Abnormal Data Unit: Obtain historical abnormal data for multiple historical monitoring time points before the current monitoring time point. The historical abnormal data includes historical abnormal sub-data for each historical detection device in the historical detection device set at the historical monitoring time point. The historical abnormal sub-data includes the historical detection device label, the historical monitoring time point, multiple historical abnormal regions, the abnormal type of each historical abnormal region, the area of the historical abnormal region, and the historical abnormal level.

5. The power grid monitoring system based on a portable infrared detection device according to claim 4, characterized in that: The determination module further includes the following units: Historical Device Report Data Unit: Based on the real-time detection device label in the real-time temperature sub-report of each real-time device to be detected in the real-time temperature report, extract the historical temperature sub-reports corresponding to the historical detection device labels that are the same as the real-time detection device label in the historical temperature reports for all historical monitoring time points, and obtain the historical device report data for each real-time device to be detected in the real-time device to be detected set. Historical Device Abnormal Data Unit: Based on the real-time detection device label in the real-time temperature sub-report of each real-time device to be detected in the real-time temperature report, extract the historical abnormal sub-data corresponding to the historical detection device labels that are the same as the real-time detection device label in the historical abnormal data for all historical monitoring time points, and obtain the historical device abnormal data for each real-time device to be detected in the real-time device to be detected set.

6. The power grid monitoring system based on the portable infrared detection device according to claim 5, characterized in that: Analysis Module, including the following units: Historical Imaging Map Vector Unit: Extract features from the historical thermal imaging map of each historical temperature sub-report in the historical device report data of each real-time device to be detected, and determine the historical imaging map vector of each historical temperature sub-report. Historical Abnormal Vector Unit: Extract features from each historical abnormal region of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected, and combine the abnormal type and abnormal level of each historical abnormal region to determine the historical abnormal vector of each historical abnormal region of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected. Historical Sub-Thermal Imaging Map Unit: Based on each historical abnormal region of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected, map and intercept the historical thermal imaging map in the historical temperature sub-report corresponding to the historical device report data of each real-time device to be detected, and determine the historical sub-thermal imaging map of each historical abnormal region of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected. Historical Sub-imaging Map Vector Unit: Extract features from the historical sub-thermal imaging maps of each historical abnormal area of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected, and determine the historical sub-imaging map vectors of the historical sub-thermal imaging maps of each historical abnormal area of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected; Device Abnormal Type Data Unit: Based on the abnormal types of all historical abnormal areas of all historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected, extract the historical abnormal vectors and historical sub-imaging map vectors of each historical abnormal area of each historical abnormal sub-data in the historical device abnormal data of each real-time device to be detected, and determine the device abnormal type data of each abnormal type of each real-time device to be detected. The device abnormal type data includes the historical abnormal vectors and historical sub-imaging map vectors of multiple historical abnormal areas of multiple historical abnormal sub-data.

7. The power grid monitoring system based on the portable infrared detection device according to claim 6, wherein: Analysis Module, including the following units: Correlation Covariance Matrix Unit: Calculate the correlation covariance matrix of each abnormal type of each real-time device to be detected based on the device abnormal type data of each abnormal type of each real-time device to be detected and the historical imaging map vectors of all historical temperature sub-reports in the historical device report data of each real-time device to be detected; Time Region Feature Vector Unit: Calculate the first weight and region feature vector of each historical abnormal sub-data of each abnormal type of each real-time device to be detected, and calculate the time region feature vector of each abnormal type of each real-time device to be detected based on the historical device abnormal data of each real-time device to be detected, the device abnormal type data of each abnormal type of each real-time device to be detected, and the historical imaging map vectors of all historical temperature sub-reports in the historical device report data of each real-time device to be detected; Projection Matrix Unit: Perform singular value decomposition on the correlation covariance matrix of each abnormal type of each real-time device to be detected, and extract the specified number of principal component directions of the left singular vector matrix after singular value decomposition to determine the projection matrix of each abnormal type of each real-time device to be detected; First Feature Vector Unit: Vectorize the projection matrix of each abnormal type of each real-time device to be detected to determine the first feature vector of each abnormal type of each real-time device to be detected; Device Type Feature Vector Unit: Determine the device type feature vector of each abnormal type of each real-time device to be detected based on the time region feature vector and the first feature vector of each abnormal type of each real-time device to be detected.

8. The power grid monitoring system based on the portable infrared detection device according to claim 1, characterized in that: Construction Module, including the following units: Device Abnormal Diagnosis Model Unit: Use the historical device report data of each real-time device to be detected as the input of the device abnormal diagnosis model of each real-time device to be detected, and use the historical device abnormal data of each real-time device to be detected as the output of the device abnormal diagnosis model of each real-time device to be detected; Construction Unit: Construct the device abnormal diagnosis model of each real-time device to be detected based on the device type feature vectors of all abnormal types of each real-time device to be detected.

9. The power grid monitoring system based on a portable infrared detection device according to claim 3, wherein: Diagnostic module, including the following units: Real-time abnormal sub-data unit: Input the real-time temperature sub-report of each real-time device to be detected in the real-time temperature report into the device abnormal diagnosis model of the corresponding real-time device to be detected, and determine the real-time abnormal sub-data of each real-time device to be detected based on the output result of the abnormal diagnosis model. The real-time abnormal sub-data includes the real-time device to be detected label, the current monitoring time point, multiple real-time abnormal regions, the first abnormal type of each real-time abnormal region, the size of the real-time abnormal region, and the real-time abnormal level; Real-time sub-thermal imaging map unit: Based on each real-time abnormal region in the real-time abnormal sub-data of each real-time device to be detected, map and intercept the real-time device thermal imaging map in the real-time temperature sub-report of each real-time device to be detected in the real-time temperature report, and determine the real-time sub-thermal imaging map of each real-time abnormal region in the real-time abnormal sub-data of each real-time device to be detected; Real-time sub-imaging map vector unit: Extract features from the real-time sub-thermal imaging map of each real-time abnormal region in the real-time abnormal sub-data of each real-time device to be detected, and determine the real-time sub-imaging map vector of each real-time abnormal region in the real-time abnormal sub-data of each real-time device to be detected; Sub-imaging map vector consistency value unit: Based on all device abnormal type data, real-time abnormal sub-data of each real-time device to be detected, and the real-time sub-imaging map vectors of all real-time abnormal regions in the real-time abnormal sub-data, calculate the real-time sub-imaging map vector of each real-time abnormal region in the real-time abnormal sub-data of each real-time device to be detected, and the sub-imaging map vector consistency value with the device abnormal type data of each abnormal type of each real-time device to be detected; Second abnormal type unit: Select the abnormal type corresponding to the maximum sub-imaging map vector consistency value from the real-time sub-imaging map vectors of each real-time abnormal region in the real-time abnormal sub-data of each real-time device to be detected and the sub-imaging map vector consistency values with the device abnormal type data of each abnormal type of each real-time device to be detected as the second abnormal type of each real-time abnormal region in the real-time abnormal sub-data of each real-time device to be detected; Prediction accuracy value unit: Compare the first abnormal type and the second abnormal type of each real-time abnormal region in the real-time abnormal sub-data of each real-time device to be detected, and calculate the prediction accuracy value of each real-time device to be detected based on the comparison results of all real-time abnormal regions in the real-time abnormal sub-data of each real-time device to be detected; Optimization unit: Optimize the device abnormal diagnosis model of each real-time device to be detected with a prediction accuracy value lower than the preset threshold based on the real-time abnormal sub-data; Alarm unit: Determine the real-time abnormal data based on the real-time abnormal sub-data of all real-time devices to be detected with a prediction accuracy value higher than the preset threshold, and issue a real-time alarm based on the real-time abnormal sub-data of all real-time devices to be detected in the real-time abnormal data.

10. A power grid monitoring method based on a portable infrared detection device, characterized in that: It includes the following steps: Step 1: Based on the portable infrared detection device, collect the real-time temperature data of the real-time device set to be detected in the power grid in real time, and generate a real-time temperature report; Step 2: Obtain the historical temperature report and historical abnormal data of the power grid, and determine the historical device report data and historical device abnormal data of each real-time device to be detected in the real-time device set to be detected; Step 3: Based on the historical device report data and historical device abnormal data of each real-time device to be detected, determine the device abnormal type data of each abnormal type of each real-time device to be detected, and determine the device type feature vector of each abnormal type of each real-time device to be detected; Step 4: Based on the historical device report data, historical device abnormal data of each real-time device to be detected, and the device type feature vectors of all abnormal types, construct an abnormal diagnosis model for each real-time device to be detected; Step 4: Based on the real-time temperature report and the abnormal diagnosis models of all real-time devices to be detected, determine the real-time abnormal data, and send a real-time alarm based on the real-time abnormal data to realize the real-time monitoring of the power grid.

Images