A risk identification method and system for power equipment

Abstract

The present invention relates to the field of power risk management, and discloses a risk identification method and system for power equipment. By adopting the method of group remote sensing monitoring, thermal data of a photovoltaic power equipment group is collected at a preset periodic frequency, and then the temperature change of each photovoltaic power equipment can be monitored. The risk of the equipment is judged through the abnormal temperature change of the photovoltaic power equipment. Compared with the traditional monitoring scheme with multiple sets of sensors, it is more suitable for large-scale equipment groups. The method of group remote sensing monitoring effectively reduces the data sources, reduces the data communication pressure of the Internet of Things devices, and can avoid the occurrence of risk misjudgment caused by the failure of the Internet of Things sensing network devices.

Description

Technical Field

[0001] The present invention relates to the field of power risk management, and specifically to a method and system for risk identification of power equipment. Background Art

[0002] With the increasing emphasis on environmental protection, the application scale of clean energy is also gradually increasing. Different from traditional power production methods, the power collection of clean energy has characteristics such as dispersion and multiple nodes. Especially for wind power and photovoltaic power, the power equipment settings often have the characteristics of large scale and many devices.

[0003] For the equipment risk monitoring of photovoltaic power equipment, usually a sensor group is used to monitor the corresponding reference data, and then the operating state of the photovoltaic power equipment is judged according to the change of the reference data. The method of using independent sensors for individual monitoring has high monitoring accuracy and is applicable to the distributed solutions with small areas and multiple regions existing in the process of photovoltaic power promotion (such as distributed settings on the roofs of rural and urban areas, etc.). However, with the increase in the scale of clean energy, large-scale cluster-type photovoltaic power stations are rapidly expanding in wide-area places such as the northwest and the sea. When facing a large area of photovoltaic power equipment groups, such a monitoring method will cause a large amount of sensing data to be generated by the sensors of a large number of photovoltaic power equipment in the Internet of Things network, resulting in the pressure of data backhaul. Moreover, the sensor data of many independent corresponding photovoltaic power equipment all need to be processed and evaluated one by one, leading to an increase in computing power requirements. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for risk identification of power equipment to solve the problems raised in the above background art.

[0005] To achieve the above purpose, the present invention provides the following technical solutions:

[0006] A method for risk identification of power equipment includes:

[0007] Updating and obtaining sensing data for the monitoring area at preset data acquisition cycle intervals, and the sensing data at each acquisition cycle node includes multiple groups of multi-type sensing data stacked in alignment;

[0008] Based on the image data of the sensing data, locating and matching the data coordinates and distribution coordinates of several photovoltaic objects, and obtaining inclination state data corresponding one-to-one to the distribution coordinates, where the inclination state data is used to characterize the spatial orientation of the photovoltaic panel;

[0009] Processing the thermal sensing data of several photovoltaic objects to obtain the rising coefficient and steady-state extreme value of the temperature change state of each photovoltaic object, and both the rising coefficient and the steady-state extreme value are associated with the current illumination condition and the inclination state data;

[0010] Arrange the rising coefficient and steady-state extreme value of the array based on the continuous sequence of inclination state data to establish an evaluation sequence, and respectively perform fitting evaluation of smooth curves on the rising coefficient and steady-state extreme value in the evaluation sequence. If the error fluctuation value beyond the smooth curve is exceeded, risk marking is performed on the photovoltaic object;

[0011] Perform risk bias evaluation on the risk-marked photovoltaic object. If the rising coefficient or steady-state extreme value is higher than the smooth curve fitting value, the risk level is marked as high risk, otherwise the risk level is marked as to be evaluated, and visual output is performed on the risk object based on the risk level.

[0012] As a further solution of the present invention: The step of updating and acquiring sensing data for the monitoring area at preset data acquisition cycle intervals specifically includes:

[0013] Execute the dynamic monitoring step, initialize the inclination states of several photovoltaic objects so that the photovoltaic objects face away from the light direction, and after initialization, evenly take multiple evaluation nodes between the backlight direction and the maximum light direction, and control the photovoltaic objects to stay at multiple evaluation nodes at intervals in turn, and record the corresponding sensing data;

[0014] Execute the static monitoring step. After the photovoltaic object enters the normal operation posture, monitor the photovoltaic object at preset data acquisition cycle intervals to obtain sensing data, and the data acquisition cycle interval is not shared with the interval in the dynamic monitoring.

[0015] As a further solution of the present invention: It further includes a dirt evaluation step, which specifically includes:

[0016] Obtain the power feeding data of several photovoltaic objects per unit time, and perform spatial arrangement on the several power feeding data based on the distribution coordinates of the photovoltaic objects;

[0017] Calculate the unit light intensity of several photovoltaic objects according to the inclination attitude data of the photovoltaic objects and the current ambient light intensity, and evaluate the ideal power feeding intensity of the photovoltaic objects through a preset photovoltaic power feeding light model;

[0018] Calculate the difference between the ideal power feeding intensity and the power feeding data, obtain the power feeding offset value of the corresponding photovoltaic object, and perform spatial surface fitting on the several power feeding offset values based on the spatial arrangement of the power feeding data to obtain a power feeding offset distribution image;

[0019] Perform deviation level area division on the power feeding offset distribution image through a preset spatial height ladder. The higher the deviation level area with a larger power feeding offset value, the higher the corresponding dirt level.

[0020] As a further solution of the present invention: It further includes a low-temperature auxiliary verification step, which specifically includes:

[0021] Evaluate the smoothness of the feed offset distribution image, mark the convex nodes, and obtain the photovoltaic objects corresponding to the distribution coordinates of the convex nodes. If the corresponding marked risk level is to be evaluated, re-mark them and mark the corresponding risk level as high risk.

[0022] As a further aspect of the present invention: it further includes a collaborative optimization management step, specifically including:

[0023] Obtain the feed data of several photovoltaic objects per unit time, and perform feed curve fitting on the several feed data according to the continuous sequence of inclination state data. The feed curve is used to characterize the correlation between the unit light intensity, the steady-state extreme temperature, and the feed capacity of the photovoltaic object;

[0024] Determine the peak value of the feed curve. If there is a unique feed peak in the feed curve, it indicates that the unit light intensity and the steady-state extreme value are both not greater than the optimal efficiency state, and set the inclination state data of the photovoltaic object corresponding to the feed peak as the current optimal attitude solution;

[0025] If there are non-unique feed peaks in the feed curve, and one side of the feed peak is in an ascending or descending state, and the other side is in a balanced state, it indicates that the unit light of the photovoltaic unit corresponding to the balanced state exceeds the optimal efficiency state, and its corresponding temperature data is not greater than the optimal efficiency state. Set the inclination state data of the multiple photovoltaic objects corresponding to the balanced state as the current optimal attitude solution;

[0026] If there are non-unique feed peaks in the feed curve, and the two sides of the feed peak are in opposite ascending or descending states respectively, it indicates that the unit light intensity and the steady-state extreme value of the photovoltaic unit corresponding to the balanced state both exceed the optimal efficiency state in the current environment. Set the inclination state data of the photovoltaic object corresponding to the balanced state as the current optimal attitude solution.

[0027] The embodiment of the present invention aims to provide a risk identification system for power equipment, including:

[0028] A data update module for updating and obtaining sensing data of the monitoring area at intervals of a preset data acquisition cycle. The sensing data at each acquisition cycle node includes multiple groups of multi-type sensing data stacked in alignment;

[0029] An object matching module for positioning and matching the data coordinates and distribution coordinates of several photovoltaic objects based on the image data of the sensing data, and obtaining the inclination state data corresponding one by one to the distribution coordinates. The inclination state data is used to characterize the spatial orientation of the photovoltaic panel;

[0030] A feature evaluation module for processing the thermal sensing data of several photovoltaic objects to obtain the rising coefficient and steady-state extreme value of the temperature change state of each photovoltaic object, where both the rising coefficient and the steady-state extreme value are associated with the current illumination condition and the inclination state data;

[0031] A risk marking module for arranging the rising coefficients and steady-state extreme values in an array based on a continuous sequence of inclination state data to establish an evaluation sequence, and respectively performing fitting evaluation of a smooth curve on the rising coefficients and steady-state extreme values in the evaluation sequence. If the error fluctuation value of the smooth curve is exceeded, risk marking is performed on the photovoltaic object;

[0032] A risk assessment module for performing a risk bias evaluation on the risk-marked photovoltaic object. If the rising coefficient or the steady-state extreme value is higher than the smooth curve fitting value, the risk level is marked as high risk; otherwise, the risk level is marked as to be evaluated, and a visual output of the risk object is performed based on the risk level.

[0033] As a further solution of the present invention: The data update module includes:

[0034] A dynamic update unit for performing a dynamic monitoring step, initializing the inclination state of several photovoltaic objects so that the photovoltaic objects face away from the illumination direction, and evenly taking multiple evaluation nodes between the backlighting direction and the maximum illumination direction after initialization, and controlling the photovoltaic objects to stay at multiple evaluation nodes at intervals in turn, and recording the corresponding sensing data;

[0035] A static update unit for performing a static monitoring step. After the photovoltaic object enters the normal operation attitude, the photovoltaic object is monitored at preset data acquisition period intervals to obtain sensing data, and the data acquisition period intervals are not shared with the intervals during dynamic monitoring.

[0036] As a still further solution of the present invention: It further includes a dirt evaluation module, specifically including:

[0037] A power feed feedback unit for obtaining the power feed data of several photovoltaic objects per unit time, and spatially arranging the several power feed data based on the distribution coordinates of the photovoltaic objects;

[0038] An ideal evaluation unit for calculating the unit illumination intensity of several photovoltaic objects according to the inclination attitude data of the photovoltaic objects and the current ambient illumination intensity, and evaluating the ideal power feed intensity of the photovoltaic objects through a preset photovoltaic power feed illumination model;

[0039] A deviation evaluation unit for calculating the difference between the ideal power feed intensity and the power feed data, obtaining the power feed offset value of the corresponding photovoltaic object, and performing a spatial surface fitting on several power feed offset values based on the spatial arrangement of the power feed data to obtain a power feed offset distribution image;

[0040] A dirt rating unit, configured to divide the deviation level regions of the feed offset distribution image through a preset spatial height ladder. The higher the dirt level of the deviation level region with a larger feed offset value.

[0041] As a further aspect of the present invention: It further includes a low-temperature auxiliary verification module;

[0042] The low-temperature auxiliary verification module is configured to evaluate the smoothness of the feed offset distribution image, mark the protruding nodes and obtain the photovoltaic objects corresponding to the distribution coordinates of the protruding nodes. If the corresponding marked risk level is to be evaluated, re-mark it and mark the corresponding risk level as high risk.

[0043] As a further aspect of the present invention: It further includes a collaborative optimization module, specifically including:

[0044] A feed fitting unit, configured to obtain the feed data of several photovoltaic objects per unit time, and perform feed curve fitting on the several feed data according to the continuous sequence of the inclination state data. The feed curve is used to characterize the correlation between the unit light intensity, the steady-state extreme temperature and the feed capacity of the photovoltaic object;

[0045] A peak determination unit, configured to perform peak determination on the feed curve. If there is a unique feed peak in the feed curve, it indicates that the unit light intensity and the steady-state extreme value are both not greater than the optimal efficiency state, and set the inclination state data of the photovoltaic object corresponding to the feed peak as the current optimal attitude solution;

[0046] An equilibrium state determination unit, configured to if there are non-unique feed peaks in the feed curve, and one side of the feed peak is in an ascending or descending state and the other side is in an equilibrium state, it indicates that the unit light intensity of the photovoltaic unit corresponding to the equilibrium state exceeds the optimal efficiency state, and its corresponding temperature data is not greater than the optimal efficiency state. Set the inclination state data of the multiple photovoltaic objects corresponding to the equilibrium state as the current optimal attitude solution;

[0047] A multi-peak state determination unit, configured to if there are non-unique feed peaks in the feed curve, and the two sides of the feed peak are respectively in opposite ascending or descending states, it indicates that the unit light intensity and the steady-state extreme value of the photovoltaic unit corresponding to the equilibrium state both exceed the optimal efficiency state in the current environment. Set the inclination state data of the photovoltaic object corresponding to the equilibrium state as the current optimal attitude solution.

[0048] Compared with the prior art, the beneficial effects of the present invention are as follows: By adopting the method of group remote sensing monitoring, thermal data of the photovoltaic power equipment group is collected at a preset periodic frequency, and then the temperature change of each photovoltaic power equipment can be monitored. The risk of the equipment is judged based on the abnormal temperature change of the photovoltaic power equipment. Compared with the traditional monitoring scheme with multiple sets of sensors, it is more suitable for large-scale equipment groups. The method of group remote sensing monitoring effectively reduces the data sources, reduces the data communication pressure of the Internet of Things devices, and can avoid the misjudgment of risks caused by the failure of the Internet of Things sensing network devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a flowchart of a risk identification method for a power equipment.

[0050] Figure 2 It is a flowchart of the soiling rating evaluation step in a risk identification method for a power equipment.

[0051] Figure 3 It is a block diagram of the composition of a risk identification system for a power equipment.

[0052] Figure 4 It is a block diagram of the composition of the soiling evaluation module in a risk identification system for a power equipment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0054] The following describes in detail the specific implementation manners of the present invention with reference to specific embodiments.

[0055] As Figure 1 described, a risk identification method for a power equipment provided by an embodiment of the present invention includes the following steps:

[0056] S10. Update and obtain sensing data of the monitoring area at preset data acquisition period intervals. The sensing data at each acquisition cycle node includes multiple sets of multi-type sensing data stacked in alignment;

[0057] S20. Locate and match the data coordinates and distribution coordinates of several photovoltaic objects based on the image data of the sensing data, and obtain the inclination state data corresponding one-to-one to the distribution coordinates. The inclination state data is used to represent the spatial orientation of the photovoltaic panel;

[0058] S30. Process the thermal sensing data of several photovoltaic objects to obtain the rising coefficient and steady-state extreme value of the temperature change state of each photovoltaic object. Both the rising coefficient and the steady-state extreme value are associated with the current illumination condition and the tilt state data.

[0059] S40. Arrange the rising coefficient and the steady-state extreme value based on the continuous sequence of the tilt state data to establish an evaluation sequence. Conduct a fitting evaluation of the smooth curve for the rising coefficient and the steady-state extreme value in the evaluation sequence respectively. If it exceeds the error fluctuation value of the smooth curve, mark the photovoltaic object as risky.

[0060] S50. Conduct a risk bias evaluation for the photovoltaic object marked as risky. If the rising coefficient or the steady-state extreme value is higher than the smooth curve fitting value, mark the risk level as high risk; otherwise, mark the risk level as to be evaluated. Based on the risk level, visually output the risk object.

[0061] In this embodiment, a risk identification method for power equipment is presented. By adopting the method of group remote sensing monitoring, thermal data of a photovoltaic power equipment group is collected at a preset periodic frequency, so as to monitor the temperature change of each photovoltaic power equipment, and judge the equipment risk through the abnormal temperature change of the photovoltaic power equipment. Compared with the traditional monitoring scheme with multiple sets of sensors, it is more applicable to a large-scale equipment group. The method of group remote sensing monitoring effectively reduces the data sources and the data communication pressure of IoT devices, and can avoid the risk misjudgment caused by the failure of IoT sensing network devices. In the prior art, for the equipment risk monitoring of photovoltaic power equipment, sensor groups are usually used to monitor the corresponding reference data, and then the operation state of the photovoltaic power equipment is judged according to the change of the reference data. Such a management method has high monitoring accuracy. However, when facing a large area of photovoltaic power equipment groups, such a monitoring method will cause a large amount of sensing data to be generated by the sensors of a large number of photovoltaic power equipment in the IoT network, resulting in the pressure of data backhaul. Moreover, the sensor data of a large number of independent corresponding photovoltaic power equipment need to be processed and evaluated one by one, resulting in an increase in computing power requirements. Therefore, when facing a large number of photovoltaic power equipment, such a monitoring method has many limitations. The solution adopted in this embodiment is to monitor data through the method of group remote sensing. For example, an unmanned aerial vehicle device flies at a rated time interval and conducts infrared remote sensing monitoring to obtain the temperature remote sensing data of several photovoltaic power equipment in an area. And in the remote sensing data, each photovoltaic power equipment corresponds to a point. Therefore, on this basis, when the orientation postures (angles with direct sunlight) of the photovoltaic power equipment at different points are the same, during the process of moving towards the sun and after a certain time after the orientation is stable, the temperature rise rate and the limit temperature should be consistent within a small allowable error. Therefore, if in the remote sensing data of multiple photovoltaic power equipment with continuously changing postures, the heat data corresponding to the coordinates of a certain photovoltaic power equipment is significantly different from other objects, it indicates that there is a certain risk for this photovoltaic power equipment (the damage of the photovoltaic panel may cause an increase in the heat generation during the operation of the photovoltaic panel, an accelerated temperature rise rate, abnormal high temperature or low temperature failure). Therefore, it is marked for distinction, so as to facilitate the maintenance personnel to process it in a timely manner in the subsequent output. Through such a management method, the high demand for communication by a large number of data sources and the high computing power demand for data processing are avoided, and it is more applicable to the management of large-scale photovoltaic power equipment.

[0062] As another preferred embodiment of the present invention, the step of updating and obtaining the sensing data of the monitoring area at preset data collection period intervals specifically includes:

[0063] Execute the dynamic monitoring step, initialize the tilt states of several photovoltaic objects so that the photovoltaic objects face away from the light direction, and after initialization, evenly take multiple evaluation nodes between the direction away from the light and the direction of maximum light, and control the photovoltaic objects to stay at the multiple evaluation nodes at intervals in turn, and record the corresponding sensing data;

[0064] Execute the static monitoring step. After the photovoltaic object enters the normal operation posture, monitor the photovoltaic object at intervals of a preset data acquisition period to obtain sensing data, and the data acquisition period interval is not shared with that in the dynamic monitoring.

[0065] In this embodiment, the acquisition steps of the sensing data are specifically described. Since the data used for risk judgment mainly includes two parts, one is the dynamic temperature rise rate and the other is the accumulated heat temperature in the stable state, two sets of monitoring step schemes are adopted here. For the dynamic monitoring step, it is necessary to cooperate with the adjustment process of the power photovoltaic equipment to achieve a continuous record. For example, when the sun comes out and reaches a predetermined angle and the photovoltaic panel starts to work, control the photovoltaic panel to rotate step by step from an initialized state facing away from the light, and maintain a certain time at each step to ensure that the heat generation of the equipment reaches equilibrium, and then the temperature rise rate of the equipment can be monitored and used to screen risk equipment. For the static monitoring step, data acquisition can be efficiently obtained by simply setting the data acquisition period for interval acquisition.

[0066] As Figure 2 shown, as another preferred embodiment of the present invention, it further includes a dirt evaluation step, which specifically includes:

[0067] S51, obtain the power feeding data of several photovoltaic objects per unit time, and perform spatial arrangement on the several power feeding data based on the distribution coordinates of the photovoltaic objects;

[0068] S52, calculate the unit light intensity of several photovoltaic objects according to the tilt attitude data of the photovoltaic objects and the current ambient light intensity, and evaluate the ideal power feeding intensity of the photovoltaic objects through a preset photovoltaic power feeding light model;

[0069] S53, calculate the difference between the ideal power feeding intensity and the power feeding data, obtain the power feeding offset value of the corresponding photovoltaic object, and perform spatial surface fitting on the several power feeding offset values based on the spatial arrangement of the power feeding data to obtain a power feeding offset distribution image;

[0070] S54, perform deviation level area division on the power feeding offset distribution image through a preset spatial height ladder. The higher the deviation level area with a larger power feeding offset value, the higher the corresponding dirt level.

[0071] In this embodiment, steps for evaluating the dirt coverage on the surface of the photovoltaic panel are added. Specifically, the implementation principle is as follows: when the surface of the photovoltaic power equipment is free of dirt, the light intensity received by its surface will be equally sensed to generate electricity. However, when dirt appears on the surface, if the light intensity remains the same, the generated electricity will definitely decrease to a certain extent. Therefore, it can be judged based on the deviation between the actual power generation efficiency and the ideal power generation efficiency of the photovoltaic power equipment. Moreover, since within the same area, the dirt distribution should be continuous and show a transitional relationship with adjacent equipment, the dirt level can be distinguished by dividing the height of the deviation image into regions. In addition, the dirt evaluation can also be indirectly achieved by evaluating the light reflection efficiency on the surface of the photovoltaic panel.

[0072] As another preferred embodiment of the present invention, it further includes a low-temperature assisted verification step, specifically including:

[0073] Evaluate the smoothness of the feed deviation distribution image, mark the protruding nodes, and obtain the photovoltaic objects corresponding to the distribution coordinates of the protruding nodes. If the corresponding marked risk level is to be evaluated, re-mark them and mark the corresponding risk level as high risk.

[0074] In this embodiment, based on the dirt judgment step in the previous embodiment, further, for adjacent photovoltaic power equipment in the same area, their surface pollution states affected by the environment should be similar. Therefore, when an abnormal peak appears in the deviation distribution image, it indicates that the photovoltaic power equipment at the corresponding point may be affected by something other than dirt. Therefore, overlapping judgment can be performed based on the to-be-evaluated risk marks in the content of the previous embodiment. If the two overlap, it means that there is a problem with this equipment and there is a risk that requires timely maintenance management. Therefore, the risk level is re-marked as high risk.

[0075] As another preferred embodiment of the present invention, it further includes a collaborative optimization management step, specifically including:

[0076] Obtain the feed data of several photovoltaic objects per unit time, and perform feed curve fitting on the several feed data according to the continuous sequence of tilt angle state data. The feed curve is used to characterize the correlation between the unit light intensity, steady-state extreme temperature, and feed capacity received by the photovoltaic object.

[0077] Perform peak determination on the feed curve. If the feed curve has a unique feed peak, it indicates that both the unit light intensity and the steady-state extreme value are not greater than the optimal efficiency state, and set the tilt angle state data of the photovoltaic object corresponding to the feed peak as the current optimal attitude solution.

[0078] If the feeding curve has non-unique feeding peaks, and one side of the feeding peak is in an ascending or descending state while the other side is in a balanced state, it indicates that the unit light of the photovoltaic unit corresponding to the balanced state exceeds the optimal efficiency state, and the corresponding temperature data is not greater than the optimal efficiency state. The inclination state data of multiple photovoltaic objects corresponding to the balanced state can all be set as the current optimal attitude solution;

[0079] If the feeding curve has non-unique feeding peaks, and the two sides of the feeding peak are respectively in opposite ascending or descending states, it indicates that both the unit light intensity and the steady-state extreme value of the photovoltaic unit corresponding to the balanced state exceed the optimal efficiency state under the current environment. The inclination state data of the photovoltaic object corresponding to the balanced state is set as the current optimal attitude solution.

[0080] In this embodiment, during the initial execution, it is necessary to set a photovoltaic power device to face the sun to obtain the maximum irradiation per unit area, and then judge the critical point of the maximum feeding light threshold (increasing light intensity will increase the power generation efficiency, but increasing temperature will inhibit the power generation efficiency, so the light intensity is not the higher the better), and then control the unit light intensity (i.e., the angle with the direct sunlight direction) and temperature of the photovoltaic power device, so that the photovoltaic power device is in an optimal power generation state.

[0081] As Figure 3 shown, the present invention also provides a risk identification system for a power device, which includes:

[0082] A data update module 100, configured to update and obtain sensing data for the monitoring area at preset data acquisition cycle intervals. The sensing data at each acquisition cycle node includes multiple groups of multi-type sensing data stacked in alignment;

[0083] An object matching module 200, configured to locate and match the data coordinates and distribution coordinates of several photovoltaic objects based on the image data of the sensing data, and obtain inclination state data corresponding one-to-one to the distribution coordinates. The inclination state data is used to characterize the spatial orientation of the photovoltaic panel;

[0084] A feature evaluation module 300, configured to process the thermal sensing data of several photovoltaic objects, and obtain the rising coefficient and steady-state extreme value of the temperature change state of each photovoltaic object. The rising coefficient and the steady-state extreme value are both associated with the current light condition and the inclination state data;

[0085] A risk marking module 400, configured to arrange the rising coefficient and the steady-state extreme value of the array based on the continuous sequence of the inclination state data to establish an evaluation sequence, and respectively perform fitting evaluation of a smooth curve on the rising coefficient and the steady-state extreme value in the evaluation sequence. If it exceeds the error fluctuation value of the smooth curve, the photovoltaic object is marked with a risk;

[0086] A risk assessment module 500 is used to evaluate the risk bias of the photovoltaic objects marked with risks. If the rising coefficient or the steady-state extreme value is higher than the smooth curve fitting value, the risk level is marked as high risk; otherwise, the risk level is marked as to be evaluated. Based on the risk level, a visual output of the risk objects is performed.

[0087] As another preferred embodiment of the present invention, the data update module includes:

[0088] A dynamic update unit is used to execute the dynamic monitoring step, initialize the inclination states of several photovoltaic objects, make the photovoltaic objects face away from the light direction, and evenly take multiple evaluation nodes between the direction facing away from the light and the maximum light direction after initialization, and control the photovoltaic objects to stay at the multiple evaluation nodes at intervals in turn, and record the corresponding sensing data;

[0089] A static update unit is used to execute the static monitoring step. After the photovoltaic objects enter the normal operation posture, the photovoltaic objects are monitored at intervals of a preset data acquisition period to obtain sensing data, and the data acquisition period interval is not shared with the interval during dynamic monitoring.

[0090] As Figure 4 shown, as another preferred embodiment of the present invention, it further includes a dirt evaluation module 600, which specifically includes:

[0091] A power feeding feedback unit 610 is used to obtain the power feeding data of several photovoltaic objects per unit time, and spatially arrange the several power feeding data based on the distribution coordinates of the photovoltaic objects;

[0092] An ideal evaluation unit 620 is used to calculate the unit light intensity of several photovoltaic objects according to the inclination attitude data of the photovoltaic objects and the current environmental light intensity, and evaluate the ideal power feeding intensity of the photovoltaic objects through a preset photovoltaic power feeding light model;

[0093] A deviation evaluation unit 630 is used to calculate the difference between the ideal power feeding intensity and the power feeding data, obtain the power feeding offset value of the corresponding photovoltaic object, and perform a spatial surface fitting on the several power feeding offset values based on the spatial arrangement of the power feeding data to obtain a power feeding offset distribution image;

[0094] A dirt rating unit 640 is used to divide the deviation level area of the power feeding offset distribution image through a preset spatial height ladder. The higher the deviation level area with a larger power feeding offset value, the higher the corresponding dirt level.

[0095] As another preferred embodiment of the present invention, it further includes a low-temperature auxiliary verification module;

[0096] The low-temperature assisted verification module is used to evaluate the smoothness of the feed offset distribution image, mark the protruding nodes, and obtain the photovoltaic objects corresponding to the distribution coordinates of the protruding nodes. If the corresponding marked risk level is to be evaluated, re-mark them and mark the corresponding risk level as high risk.

[0097] As another preferred embodiment of the present invention, it further includes a collaborative optimization module, specifically including:

[0098] The feed fitting unit is used to obtain the feed data of several photovoltaic objects per unit time, and perform feed curve fitting on the several feed data according to the continuous sequence of the inclination state data. The feed curve is used to characterize the correlation between the unit light intensity, the steady-state extreme temperature and the feed capacity of the photovoltaic object;

[0099] The peak determination unit is used to determine the peak of the feed curve. If there is a unique feed peak in the feed curve, it indicates that the unit light intensity and the steady-state extreme value are not greater than the optimal efficiency state, and set the inclination state data of the photovoltaic object corresponding to the feed peak as the current optimal attitude solution;

[0100] The equilibrium state determination unit is used to, if there are non-unique feed peaks in the feed curve, and one side of the feed peak is in an ascending or descending state, and the other side is in an equilibrium state, it indicates that the unit light of the photovoltaic unit corresponding to the equilibrium state exceeds the optimal efficiency state, and the corresponding temperature data is not greater than the optimal efficiency state. Set the inclination state data of the multiple photovoltaic objects corresponding to the equilibrium state as the current optimal attitude solution;

[0101] The multi-peak state determination unit is used to, if there are non-unique feed peaks in the feed curve, and the two sides of the feed peak are in opposite ascending or descending states respectively, it indicates that the unit light intensity and the steady-state extreme value of the photovoltaic unit corresponding to the equilibrium state both exceed the optimal efficiency state in the current environment, and set the inclination state data of the photovoltaic object corresponding to the equilibrium state as the current optimal attitude solution.

[0102] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0103] After considering the specification and the disclosure of the embodiments, those skilled in the art will readily conceive of other embodiments of the present disclosure. The present application is intended to cover any variations, uses, or adaptations of the present disclosure, which follow the general principles of the present disclosure and include well-known knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the claims.

[0104] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A method for identifying risks of power equipment, characterized in that: Include: The sensor data of the monitoring area is updated and acquired at preset data acquisition cycle intervals, and the sensor data of each acquisition cycle node includes multiple groups of multi-type sensor data that are aligned and stacked; Positioning and matching the data coordinates and distribution coordinates of several photovoltaic objects based on the image data of the sensor data, and obtaining the inclination state data corresponding to the distribution coordinates one by one, wherein the inclination state data is used to characterize the spatial orientation of the photovoltaic panel; Processing the thermal sensor data of several photovoltaic objects to obtain the rising coefficient and steady-state extreme value of the temperature change state of each photovoltaic object, wherein the rising coefficient and steady-state extreme value are both associated with the current lighting conditions and the tilt state data; Arranging the rising coefficients and steady-state extreme values ​​of the array based on the continuous sequence of the tilt state data to establish an evaluation sequence, and performing smooth curve fitting evaluation on the rising coefficients and steady-state extreme values ​​in the evaluation sequence, and marking the photovoltaic object for risk if the error fluctuation value of the smooth curve is exceeded; Perform risk bias evaluation on the photovoltaic object with risk mark, if the rising coefficient or the steady-state extreme value is higher than the smooth curve fitting value, the risk level is marked as high risk, otherwise the risk level is marked as to be evaluated, and the risk object is visualized and output based on the risk level; It also includes collaborative optimization management steps, including: Acquire power feeding data per unit time of several photovoltaic objects, and perform power feeding curve fitting on the several power feeding data according to the continuous sequence of the tilt state data, wherein the power feeding curve is used to characterize the correlation between the unit light intensity, the steady-state extreme temperature and the power feeding capacity of the photovoltaic object; A peak value is determined for the feeding curve. If the feeding curve has a unique feeding peak value, it indicates that both the unit light intensity and the steady-state extreme value are not greater than the optimal efficiency state. The inclination state data of the photovoltaic object corresponding to the feeding peak value is set as the current optimal posture solution. If the feed curve has a non-unique feed peak, and one side of the feed peak is in an ascending or descending state, and the other side is in a balanced state, then the unit illumination of the photovoltaic unit corresponding to the balanced state exceeds the optimal efficiency state, and the corresponding temperature data is not greater than the optimal efficiency state, and the inclination state data of multiple photovoltaic objects corresponding to the balanced state can be set as the current optimal posture solution; If the feeding curve has a non-unique feeding peak, and the two sides of the feeding peak are in opposite rising or falling states, then the unit light intensity and steady-state extreme value of the photovoltaic unit corresponding to the equilibrium state exceed the optimal efficiency state under the current environment, and the inclination state data of the photovoltaic object corresponding to the equilibrium state is set as the current optimal posture solution.

2. A method for identifying risks of electric power equipment according to claim 1, characterized in that: The step of updating and acquiring the sensor data of the monitoring area at a preset data collection period interval specifically includes: Execute the dynamic monitoring step, initialize the tilt states of several photovoltaic objects, so that the photovoltaic objects face away from the illumination direction, and evenly select multiple evaluation nodes between the back illumination direction and the maximum illumination direction after initialization, and control the photovoltaic objects to stay at multiple evaluation nodes in sequence and record corresponding sensor data; The static monitoring step is performed. When the photovoltaic object enters a normal operating posture, the photovoltaic object is monitored at a preset data collection cycle interval to obtain sensor data. The data collection cycle interval is not shared with the dynamic monitoring interval.

3. A method for identifying risks of electric power equipment according to claim 2, characterized in that: It also includes a soiling assessment step, which includes: Acquire power feeding data per unit time of a plurality of photovoltaic objects, and spatially arrange the plurality of power feeding data based on distribution coordinates of the photovoltaic objects; Calculating the unit illumination intensity of several photovoltaic objects according to the inclination attitude data of the photovoltaic objects and the current ambient illumination intensity, and evaluating the ideal power feeding intensity of the photovoltaic objects through a preset photovoltaic power feeding illumination model; Calculating the difference between the ideal feeding intensity and the feeding data, obtaining a feeding offset value of the corresponding photovoltaic object, and performing spatial surface fitting on several feeding offset values ​​based on the spatial arrangement of the feeding data to obtain a feeding offset distribution image; The feed offset distribution image is divided into deviation level areas by using preset spatial height steps, and the deviation level area with a larger feed offset value has a higher corresponding dirt level.

4. A method for identifying risks of electric power equipment according to claim 3, characterized in that: It also includes low temperature auxiliary verification steps, including: The smoothness of the feed offset distribution image is evaluated, the protruding nodes are marked and the photovoltaic objects corresponding to the distribution coordinates of the protruding nodes are obtained. If the corresponding marked risk level is to be evaluated, the alignment is re-marked and the corresponding risk level is marked as high risk.

5. A risk identification system for power equipment, characterized in that: Include: A data updating module is used to update and acquire sensor data of the monitoring area at preset data collection period intervals, and the sensor data of each collection period node includes multiple groups of aligned and stacked sensor data of multiple types; An object matching module is used to locate and match the data coordinates and distribution coordinates of several photovoltaic objects based on the image data of the sensor data, and to obtain the inclination state data corresponding to the distribution coordinates one by one, wherein the inclination state data is used to characterize the spatial orientation of the photovoltaic panel; A feature evaluation module is used to process the thermal sensor data of several photovoltaic objects to obtain the rising coefficient and the steady-state extreme value of the temperature change state of each photovoltaic object, wherein the rising coefficient and the steady-state extreme value are both associated with the current lighting conditions and the tilt state data; A risk marking module, used for arranging the rising coefficients and steady-state extreme values ​​of the array based on the continuous sequence of the tilt state data to establish an evaluation sequence, and performing smooth curve fitting evaluation on the rising coefficients and steady-state extreme values ​​in the evaluation sequence respectively, and if the error fluctuation value of the smooth curve is exceeded, the photovoltaic object is marked as risk; A risk assessment module is used to evaluate the risk bias of the photovoltaic object marked with risk. If the rising coefficient or the steady-state extreme value is higher than the smooth curve fitting value, the risk level is marked as high risk, otherwise the risk level is marked as to be evaluated, and the risk object is visualized and output based on the risk level; It also includes collaborative optimization modules, including: A power feeding fitting unit is used to obtain power feeding data per unit time of several photovoltaic objects, and to perform power feeding curve fitting on the several power feeding data according to a continuous sequence of tilt state data, wherein the power feeding curve is used to characterize the correlation between the unit light intensity, the steady-state extreme temperature and the power feeding capacity of the photovoltaic object; A peak determination unit is used to perform peak determination on the feeding curve. If the feeding curve has a unique feeding peak, it indicates that both the unit light intensity and the steady-state extreme value are not greater than the optimal efficiency state, and the inclination state data of the photovoltaic object corresponding to the feeding peak is set as the current optimal posture solution; A balance state determination unit, for if there is a non-unique feed peak value in the feed curve, and one side of the feed peak value is in an ascending or descending state, and the other side is in a balance state, then the unit illumination of the photovoltaic unit corresponding to the balance state exceeds the optimal efficiency state, and the corresponding temperature data is not greater than the optimal efficiency state, and the inclination state data of multiple photovoltaic objects corresponding to the balance state can all be set as the current optimal posture solution; A multi-peak state determination unit is used for, if there is a non-unique feeding peak value in the feeding curve, and the two sides of the feeding peak value are in opposite rising or falling states, then the unit light intensity and the steady-state extreme value of the photovoltaic unit corresponding to the equilibrium state are both beyond the optimal efficiency state under the current environment, and the inclination state data of the photovoltaic object corresponding to the equilibrium state is set as the current optimal posture solution.

6. A risk identification system for electric power equipment according to claim 5, characterized in that: The data updating module comprises: A dynamic update unit is used to execute the dynamic monitoring step, initialize the tilt states of several photovoltaic objects so that the photovoltaic objects face away from the illumination direction, and evenly select multiple evaluation nodes between the back illumination direction and the maximum illumination direction after initialization, and control the photovoltaic objects to stay at multiple evaluation nodes in sequence and record corresponding sensor data; The static updating unit is used to execute the static monitoring step. When the photovoltaic object enters the normal operation posture, the photovoltaic object is monitored at a preset data collection cycle interval to obtain sensor data. The data collection cycle interval is not shared with the dynamic monitoring interval.

7. A risk identification system for electric power equipment according to claim 6, characterized in that: Also included is the Soil Assessment Module, which includes: A power feeding feedback unit, used to obtain power feeding data of a plurality of photovoltaic objects per unit time, and spatially arrange the plurality of power feeding data based on the distribution coordinates of the photovoltaic objects; An ideal evaluation unit, used to calculate the unit illumination intensity of several photovoltaic objects according to the inclination attitude data of the photovoltaic objects and the current ambient illumination intensity, and evaluate the ideal power feeding intensity of the photovoltaic objects through a preset photovoltaic power feeding illumination model; a deviation evaluation unit, configured to calculate the difference between the ideal power feeding intensity and the power feeding data, obtain a power feeding offset value of the corresponding photovoltaic object, and perform spatial surface fitting on several power feeding offset values ​​based on the spatial arrangement of the power feeding data to obtain a power feeding offset distribution image; The dirt rating unit is used to divide the feed offset distribution image into deviation level areas according to preset spatial height steps, and the deviation level area with a larger feed offset value has a higher corresponding dirt level.

8. A risk identification system for electric power equipment according to claim 7, characterized in that: It also includes a cryogenic auxiliary verification module; The low-temperature auxiliary verification module is used to evaluate the smoothness of the feed offset distribution image, mark the protruding nodes and obtain the photovoltaic objects corresponding to the distribution coordinates of the protruding nodes. If the corresponding marked risk level is to be evaluated, the alignment is re-marked and the corresponding risk level is marked as high risk.

Images