Photovoltaic power station fault positioning system based on artificial intelligence

Abstract

The invention relates to the technical field of power station fault positioning, in particular to a photovoltaic power station fault positioning system based on artificial intelligence, which comprises a fault positioning management platform, an operation information unit, a fault judgment unit, a management and control division unit, an induction expression unit, a progressive sorting unit and a management display unit. According to the invention, analysis is carried out from the perspective of the operation process, so that the operation state condition of the system equipment of each level of the photovoltaic power station can be visually known, and the fault equipment can be accurately positioned, operated and maintained. Two points of fault risk degree and historical induction of the fault equipment are subjected to combined analysis in an information feedback mode, so that reasonable operation and maintenance personnel arrangement is performed according to the operation and maintenance types, and the operation and maintenance management efficiency of each operation and maintenance type is improved; and further performing operation and maintenance sorting analysis on the fault equipment in each operation and maintenance type in a progressive manner, so as to improve the operation and maintenance efficiency and rationality of each fault equipment in each operation and maintenance type.

Description

Technical Field

[0001] The present invention relates to the technical field of power station fault location, and in particular to a photovoltaic power station fault location system based on artificial intelligence. Background Art

[0002] Photovoltaic power stations use the photovoltaic effect of photovoltaic cells to directly convert solar radiation into electrical energy. They generally include transformers, inverters, photovoltaic arrays, and related auxiliary facilities. As high-quality terrain photovoltaic development resources become increasingly scarce, large-scale photovoltaic development using complex mountainous or hilly terrain has become the main way to increase photovoltaic power. Large-scale photovoltaic power stations are located in remote areas with complex terrain and large terrain changes. Photovoltaic power stations generally occupy a large area, have a large amount of equipment, and have many hidden fault points, which puts high demands and challenges on operation and maintenance.

[0003] However, in the prior art, it is impossible to accurately monitor the status of the system equipment at each level of the photovoltaic power station, and thus it is impossible to timely and accurately locate and display the faulty equipment, which in turn affects the operation and maintenance effect of the faulty equipment. It is also impossible to reasonably classify the operation and maintenance types and match the operation and maintenance personnel according to the fault control requirements of the faulty equipment, which is not conducive to the reasonable operation and maintenance management of the faulty equipment, and it is impossible to reasonably sort the operation and maintenance management of each faulty equipment in each operation and maintenance type, thereby reducing the rationality and efficiency of the operation and maintenance of the faulty equipment.

[0004] In view of the above technical defects, a solution is now proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a photovoltaic power station fault positioning system based on artificial intelligence to solve the technical defects mentioned above. The present invention analyzes from the perspective of the operation process so as to intuitively understand the operating status of system equipment at each level of the photovoltaic power station, which is helpful to accurately locate and operate the faulty equipment, and conducts a combined analysis of the fault risk level and historical induction of the faulty equipment through information feedback to understand the fault control needs of each faulty equipment, so as to carry out reasonable and targeted operation and maintenance management according to the fault control needs, and at the same time, reasonably arranges operation and maintenance personnel according to the operation and maintenance type to improve the operation and maintenance management efficiency of each operation and maintenance type, and further analyzes the operation and maintenance sorting of the faulty equipment in each operation and maintenance type in a progressive manner to improve the operation and maintenance efficiency and rationality of each faulty equipment in each operation and maintenance type, and at the same time intuitively locates and displays the faulty equipment in a visual manner to improve the fault management effect of the faulty equipment.

[0006] The object of the present invention can be achieved by the following technical solutions: A photovoltaic power station fault location system based on artificial intelligence, including a fault location management platform, an operation information unit, a fault identification unit, a control division unit, an induced performance unit, a progressive sorting unit and a management display unit;

[0007] The operation information unit is used to collect operation-related data of system equipment at each level of the photovoltaic power station and send the operation-related data to the fault determination unit;

[0008] After receiving the operation-related data, the fault identification unit immediately performs operation fault safety supervision analysis on the operation-related data, performs identification processing on the obtained fault assessment index, and obtains the fault signal and the faulty device;

[0009] The control division unit is used to respond to the fault signal, collect the fault data and historical operating condition data of each faulty device, send the historical operating condition data to the induced performance unit, and perform fault control demand type classification analysis on the historical operating condition data, compare and analyze the obtained fault control demand coefficient Qg, and obtain the operation and maintenance type YX;

[0010] After receiving the historical operating condition data, the induced performance unit immediately performs historical fault induced impact analysis on the historical operating condition data to obtain an induced activity factor coefficient;

[0011] The progressive sorting unit is used to respond to the operation and maintenance type YX, collect the parts matching information of each faulty equipment within each operation and maintenance type, and perform operation and maintenance sorting matching management analysis on the parts matching information, and send the sorted fault control demand coefficient corresponding to the faulty equipment to the management display unit, and send the sorted operation and maintenance delay index corresponding to the faulty equipment to the management display unit.

[0012] Preferably, the operation failure safety supervision and analysis process of the fault identification unit is as follows:

[0013] A monitoring cycle is set and set as a time threshold, and operation-related data of each level of system equipment of the photovoltaic power station within the time threshold are obtained. The operation-related data include actual operating voltage and actual energy consumption per unit time. The operation-related data are judged and processed. If the value corresponding to the operation-related data exceeds the preset threshold or the value corresponding to the operation-related data deviates from the preset range, a risk signal is generated, and the number corresponding to the risk signal is obtained. The number corresponding to the risk signal is set as a fault assessment index, and the fault assessment index is judged and processed to obtain a fault signal, and the level system equipment corresponding to the fault signal is set as a faulty device.

[0014] Preferably, the fault control requirement type classification and analysis process of the control classification unit is as follows:

[0015] Fault data of each faulty device within the time threshold is obtained, the fault data including the operation efficiency deviation value and the mutation risk index. At the same time, the induced activity factor coefficient corresponding to each faulty device is retrieved, and the faulty device is set to g, where g is a natural number greater than zero. The operation efficiency deviation value, the mutation risk index and the induced activity factor coefficient are set to YPg, TFg and YHg respectively. The fault control demand coefficient Qg of each faulty device is obtained according to the formula. The fault control demand coefficient Qg is compared and analyzed with the preset fault control demand coefficient range entered and stored internally to obtain Class I operation and maintenance equipment, Class II operation and maintenance equipment and Class III operation and maintenance equipment. Class I operation and maintenance equipment, Class II operation and maintenance equipment and Class III operation and maintenance equipment are set as operation and maintenance type YX, where YX=1, 2, 3.

[0016] Preferably, the operation efficiency deviation value represents the product of the portion of the actual working efficiency of each faulty equipment that is lower than the set working efficiency and the current energy consumption value after data normalization processing; the mutation risk index represents the growth number of the value corresponding to the operation-related data exceeding the preset threshold or the value corresponding to the operation-related data deviating from the preset range within a set time after each faulty equipment generates a risk signal.

[0017] Preferably, the historical fault induced impact analysis process of the induced performance unit is as follows:

[0018] Obtain the historical operating data of each faulty device within the time threshold. The historical operating data includes the operation and maintenance evaluation index and the historical operation efficiency index. The operation and maintenance evaluation index and the historical operation efficiency index are labeled as YW and LX respectively. According to the formula The historical mutation risk coefficient is obtained, where f1 and f2 are the preset weight factor coefficients of the operation and maintenance evaluation index and the historical operation efficiency index respectively, f3 is the preset fault tolerance factor coefficient, f1, f2 and f3 are all greater than zero, and YF represents the historical mutation risk coefficient. The historical mutation risk coefficient YF is compared and analyzed with the preset historical mutation risk coefficient interval stored internally, and the corresponding parameter of the historical mutation risk coefficient YF belonging to the corresponding preset historical mutation risk coefficient interval is set as the induced activity factor coefficient.

[0019] Preferably, the operation and maintenance evaluation index represents the product of the operation and maintenance coefficient of each faulty equipment and the usage index after data normalization processing, the operation and maintenance coefficient represents the sum of the total duration corresponding to the number of historical maintenance delays and the equipment input time, and the usage index represents the time between the end time of the most recent maintenance and the current time; the historical operation efficiency index represents the average of the mutation risk index corresponding to the historically generated risk signals of each faulty equipment.

[0020] Preferably, the operation and maintenance sorting matching management analysis process of the progressive sorting unit is as follows:

[0021] Obtain the fault part code of each faulty device in each operation and maintenance type within the time threshold, and at the same time obtain the existing part code of each existing part in the parts inventory, set each existing part code in the parts inventory as the existing part code, and match the fault part code with the existing part code for analysis:

[0022] If the faulty part code belongs to an existing part code, a feedback instruction is generated. When the feedback instruction is generated, the fault control demand coefficients of each faulty device in each operation and maintenance type are sorted in descending order;

[0023] If the faulty part code does not belong to the existing part codes, a retrieval instruction is generated.

[0024] Preferably, when the progressive sorting unit generates a call instruction:

[0025] The parts matching information of each faulty equipment in each operation and maintenance type within the time threshold is obtained. The parts matching information includes the historical parts procurement times and the historical parts procurement duration. Then, the average of the historical parts procurement duration is obtained based on the historical parts procurement times and the single historical parts procurement duration. The average is set as the operation and maintenance delay index, and the operation and maintenance delay index is sorted in ascending order.

[0026] The beneficial effects of the present invention are as follows:

[0027] (1) The present invention analyzes from the perspective of the operation process to determine whether the operation-related data of each level of system equipment during the operation process is abnormal, so as to intuitively understand the operation status of each level of system equipment in the photovoltaic power station, which is helpful to accurately locate and operate the faulty equipment. In addition, the present invention conducts a combined analysis of the fault risk level and historical induction of the faulty equipment through information feedback to understand the fault control requirements of each faulty equipment, so as to perform reasonable and targeted operation and maintenance management according to the fault control requirements, and at the same time, reasonably arranges the operation and maintenance personnel according to the operation and maintenance type to improve the operation and maintenance management efficiency of each operation and maintenance type;

[0028] (2) The present invention further analyzes the operation and maintenance ranking of faulty equipment in each operation and maintenance type in a progressive manner, that is, performs operation and maintenance ranking and matching management analysis on parts matching information, so as to reasonably and targetedly perform operation and maintenance ranking management on each faulty equipment in each operation and maintenance type, so as to improve the operation and maintenance efficiency and rationality of each faulty equipment in each operation and maintenance type, and at the same time intuitively locate and display the faulty equipment in a visual manner, so as to improve the fault management effect of the faulty equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The present invention will be further described below in conjunction with the accompanying drawings;

[0030] Figure 1 It is a flowchart of the system of the present invention;

[0031] Figure 2 It is a local analysis reference diagram of the second embodiment of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] Embodiment 1:

[0034] See also Figure 1 to Figure 2 As shown, the present invention is a photovoltaic power station fault location system based on artificial intelligence, including a fault location management platform, an operation information unit, a fault determination unit, a control division unit, an induced performance unit, a progressive sorting unit and a management display unit, the fault location management platform is connected to the operation information unit in a one-way communication, the operation information unit is connected to the fault determination unit in a one-way communication, the fault determination unit is connected to the control division unit and the management display unit in a one-way communication, the control division unit is connected to the induced performance unit in a two-way communication, the control division unit is connected to the progressive sorting unit and the management display unit in a one-way communication, and the progressive sorting unit is connected to the management display unit in a one-way communication;

[0035] When the fault location management platform generates an operation management instruction, it sends the operation management instruction to the operation information unit. The operation information unit responds to the operation management instruction and collects the operation-related data of the system equipment at each level of the photovoltaic power station, and sends the operation-related data to the fault identification unit. After receiving the operation-related data, the fault identification unit immediately performs operation fault safety supervision and analysis on the operation-related data to determine whether the operation-related data of the system equipment at each level is abnormal during operation, so as to intuitively understand the operation status of the system equipment at each level of the photovoltaic power station, which is helpful to accurately locate and operate the faulty equipment. The specific operation fault safety supervision and analysis process is as follows:

[0036] Set a monitoring cycle and set it as a time threshold, obtain the operation-related data of each level of system equipment in the photovoltaic power station within the time threshold, the operation-related data includes the actual operation voltage, the actual energy consumption per unit time, etc., and perform judgment processing on the operation-related data. If the value corresponding to the operation-related data exceeds the preset threshold or the value corresponding to the operation-related data deviates from the preset range, a risk signal is generated, the number of risk signals corresponding to the risk signals is obtained, and the number of risk signals corresponding to the risk signals is set as the fault assessment index, and the fault assessment index is judged:

[0037] If the fault evaluation index is equal to zero, no signal is generated;

[0038] If the fault assessment index is not equal to zero, a fault signal is generated, and the hierarchical system equipment corresponding to the fault signal is set as a faulty equipment, and the fault signal is sent to the management display unit. After receiving the fault signal, the management display unit immediately marks the faulty equipment in red, so as to intuitively understand the operating status of the hierarchical system equipment of the photovoltaic power station, which is helpful to accurately locate and operate the faulty equipment, so as to improve the operation and maintenance efficiency of the faulty equipment;

[0039] In the embodiment of the present invention, the system devices at each level include but are not limited to: photovoltaic energy storage devices, inverters; the faulty devices may be one or more. It can be understood that when the fault assessment index in the system devices at each level is not equal to zero, the corresponding device is a faulty device.

[0040] Embodiment 2:

[0041] When a fault signal is generated, the control division unit is used to respond to the fault signal, collect the fault data and historical working condition data of each faulty device, send the historical working condition data to the induced performance unit, and perform fault control demand type division analysis on the historical working condition data, so as to sort and divide the faulty equipment according to the degree of fault control demand, so as to perform reasonable and targeted operation and maintenance management according to the fault control demand situation, so as to improve the operation and maintenance efficiency of the faulty equipment. The specific fault control demand type division analysis process is as follows:

[0042] Obtain the fault data of each faulty device within the time threshold, including the operational efficiency deviation value and the mutation risk index. At the same time, retrieve the induced activity factor coefficient corresponding to each faulty device, set the faulty device to g, where g is a natural number greater than zero, set the operational efficiency deviation value, mutation risk index and induced activity factor coefficient to YPg, TFg and YHg respectively. According to the formula The fault control demand coefficient of each faulty equipment is obtained, where a1, a2 and a3 are respectively the preset proportional factor coefficients of the operational efficiency deviation value, the mutation risk index and the induced activity factor coefficient. The proportional factor coefficient is used to correct the deviation of various parameters in the formula calculation process, so as to make the calculation result more accurate. a4 is the preset correction factor coefficient. a1, a2, a3 and a4 are all greater than zero. Qg is the fault control demand coefficient of each faulty equipment. The fault control demand coefficient Qg is compared and analyzed with the preset fault control demand coefficient range stored in its internal entry:

[0043] If the fault control demand coefficient Qg is greater than the maximum value in the preset fault control demand coefficient range, it is determined to be a Class I operation and maintenance equipment;

[0044] If the fault control demand coefficient Qg falls within the preset fault control demand coefficient range, it is determined to be a Class II operation and maintenance equipment;

[0045] If the fault control demand coefficient Qg is less than the minimum value in the preset fault control demand coefficient range, it is determined to be a Class III operation and maintenance device, wherein the fault control demands corresponding to the Class I operation and maintenance device, the Class II operation and maintenance device, and the Class III operation and maintenance device are successively reduced, and the Class I operation and maintenance device, the Class II operation and maintenance device, and the Class III operation and maintenance device are set to the operation and maintenance type YX, YX=1, 2, 3, that is, when the operation and maintenance type YX=1, it indicates a Class I operation and maintenance device, when the operation and maintenance type YX=2, it indicates a Class II operation and maintenance device, and when the operation and maintenance type YX=3, it indicates a Class III operation and maintenance device, and the operation and maintenance type YX is sent to the management display unit. After receiving the operation and maintenance type YX, the management display unit immediately classifies the faulty device according to the classification situation, so as to perform reasonable and targeted operation and maintenance personnel matching management according to the fault control demand situation, that is, to perform reasonable operation and maintenance personnel arrangement according to the operation and maintenance type, so as to improve the operation and maintenance management efficiency of each operation and maintenance type;

[0046] In the embodiment of the present invention, the operational efficiency deviation value represents the product value obtained by multiplying the portion of the actual working efficiency of each faulty device that is lower than the set working efficiency by the current energy consumption value after data normalization. It should be noted that the analysis is performed from the two points of working efficiency and energy consumption to understand the impact of the current faulty device failure;

[0047] In the embodiment of the present invention, the mutation risk index indicates the growth number of the value corresponding to the operation-related data exceeding the preset threshold or the value corresponding to the operation-related data deviating from the preset range within a set period of time after each faulty device generates a risk signal. It should be noted that the analysis is performed from the perspective of the impact brought by the fault to understand the risk degree of the fault impact change of each faulty device;

[0048] After receiving the historical operating condition data, the induced performance unit immediately performs historical fault induced impact analysis on the historical operating condition data to understand the risk of sudden changes in each faulty device when a fault occurs, so as to provide data support for the operation and maintenance of the faulty device. The specific historical fault induced impact analysis process is as follows:

[0049] Obtain the historical operating data of each faulty device within the time threshold. The historical operating data includes the operation and maintenance evaluation index and the historical operation efficiency index. The operation and maintenance evaluation index and the historical operation efficiency index are labeled as YW and LX respectively. According to the formula The historical mutation risk coefficient is obtained, wherein f1 and f2 are respectively the preset weight factor coefficients of the operation and maintenance evaluation index and the historical operation efficiency index, f3 is the preset fault tolerance factor coefficient, f1, f2 and f3 are all greater than zero, YF represents the historical mutation risk coefficient, the historical mutation risk coefficient YF is compared and analyzed with the preset historical mutation risk coefficient interval stored internally, and the corresponding parameter of the historical mutation risk coefficient YF belonging to the corresponding preset historical mutation risk coefficient interval is set as the induced activity factor coefficient, for example: the historical mutation risk coefficient YF belongs to the first preset historical mutation risk coefficient interval, then the induced activity factor coefficient is c1, the historical mutation risk coefficient YF belongs to the second preset historical mutation risk coefficient interval, then the induced activity factor coefficient is c2, the historical mutation risk coefficient YF belongs to the third preset historical mutation risk coefficient interval, then the induced activity factor coefficient is c3, c1, c2 and c3 are all set parameters, c1, c2 and c3 are all greater than zero;

[0050] In the embodiment of the present invention, the operation and maintenance evaluation index represents the product value obtained by multiplying the operation and maintenance coefficient of each faulty device by the used index after data normalization processing, the operation and maintenance coefficient represents the sum of the total duration corresponding to the number of historical maintenance delays and the equipment input time, and the used index represents the time between the last maintenance end time and the current time. It should be noted that the analysis is performed from three perspectives: maintenance delay time, input time, and maintenance effect, so as to understand the potential interference degree of each faulty device and avoid inducing other faults;

[0051] In the embodiment of the present invention, the historical operation efficiency index represents the average of the mutation risk index corresponding to the historically generated risk signal of each faulty device. It should be noted that the analysis is performed from the perspective of the average of the historical mutation risk index of the faulty device to understand the risk situation of each faulty device that is prone to mutation when a fault occurs.

[0052] Embodiment three:

[0053] The progressive sorting unit is used to respond to the operation and maintenance type YX, collect the parts matching information of each faulty device in each operation and maintenance type, and perform operation and maintenance sorting matching management and analysis on the parts matching information, so as to reasonably and targetedly manage the operation and maintenance sequence of each faulty device in each operation and maintenance type, so as to improve the operation and maintenance efficiency and rationality of each faulty device in each operation and maintenance type. The specific operation and maintenance sorting matching management and analysis process is as follows:

[0054] Obtain the fault part code of each faulty device in each operation and maintenance type within the time threshold, and at the same time obtain the existing part code of each existing part in the parts inventory, set each existing part code in the parts inventory as the existing part code, and match the fault part code with the existing part code for analysis:

[0055] If the faulty part code belongs to an existing part code, a feedback instruction is generated. When the feedback instruction is generated, the fault control demand coefficients of each faulty device in each operation and maintenance type are sorted in descending order, and the faulty device corresponding to the sorted fault control demand coefficient is sent to the management display unit. After receiving the faulty device corresponding to the sorted fault control demand coefficient, the management display unit sequentially displays and locates the faulty device according to the sorted fault control demand coefficient, so as to perform maintenance management according to the sorting of the faulty device, so as to improve the operation and maintenance efficiency and rationality of each faulty device in each operation and maintenance type, that is, sequential operation and maintenance is performed according to the operation and maintenance type and the order of the faulty device;

[0056] If the faulty part code does not belong to the existing part code, a retrieval instruction is generated. When the retrieval instruction is generated, the part matching information of each faulty device in each operation and maintenance type within the time threshold is obtained. The part matching information includes the number of historical part purchases and the historical part purchase duration. Then, the average of the historical part purchase duration is obtained based on the number of historical part purchases and the single historical part purchase duration, and it is set as the operation and maintenance delay index. The operation and maintenance delay index is sorted in ascending order, and the sorted operation and maintenance delay index corresponding to the faulty device is sent to the management display unit. After receiving the sorted operation and maintenance delay index corresponding to the faulty device, the management display unit displays and locates the faulty device in sequence according to the sorted operation and maintenance delay index, so as to perform maintenance management according to the sorting of the faulty equipment.

[0057] In the embodiment of the present invention, if the operation and maintenance delay indexes are the same, the operation and maintenance management is performed in the order of the fault control demand coefficient;

[0058] In summary, the present invention analyzes from the perspective of the operation process to determine whether the operation-related data of each level of system equipment during the operation process is abnormal, so as to intuitively understand the operation status of each level of system equipment in the photovoltaic power station, which is helpful to accurately locate and operate the faulty equipment, and conducts a combined analysis of the fault risk level and historical induction of the faulty equipment in the form of information feedback to understand the fault control requirements of each faulty equipment, so as to perform reasonable and targeted operation and maintenance management according to the fault control requirements, and at the same time, reasonably arranges operation and maintenance personnel according to the operation and maintenance type to improve the operation and maintenance management efficiency of each operation and maintenance type, and further analyzes the operation and maintenance sorting of the faulty equipment in each operation and maintenance type in a progressive manner, that is, performs operation and maintenance sorting matching management analysis on the parts matching information, so as to reasonably and targetedly perform operation and maintenance sorting management on each faulty equipment in each operation and maintenance type, so as to improve the operation and maintenance efficiency and rationality of each faulty equipment in each operation and maintenance type, and at the same time intuitively locates and displays the faulty equipment in a visual manner to improve the fault management effect of the faulty equipment;

[0059] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0060] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula that is close to the actual value. The coefficients in the formula are set by technical personnel in this field according to actual conditions. The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited to this. Any technical personnel familiar with the technical field within the technical scope disclosed by the present invention, according to the technical solution and the inventive concept of the present invention, make equivalent replacement or change, which should be covered within the protection scope of the present invention.

Claims

1. Photovoltaic power station fault location system based on artificial intelligence, characterized by: It includes a fault location management platform, an operation information unit, a fault identification unit, a control division unit, an induced performance unit, a progressive sorting unit, and a management display unit; The operation information unit is used to collect operation-related data of system equipment at each level of the photovoltaic power station and send the operation-related data to the fault determination unit; After receiving the operation-related data, the fault identification unit immediately performs operation fault safety supervision analysis on the operation-related data, performs identification processing on the obtained fault assessment index, and obtains the fault signal and the faulty device; The control division unit is used to respond to the fault signal, collect the fault data and historical operating condition data of each faulty device, send the historical operating condition data to the induced performance unit, and perform fault control demand type classification analysis on the historical operating condition data, compare and analyze the obtained fault control demand coefficient Qg, and obtain the operation and maintenance type YX; After receiving the historical operating condition data, the induced performance unit immediately performs historical fault induced impact analysis on the historical operating condition data to obtain an induced activity factor coefficient; The progressive sorting unit is used to respond to the operation and maintenance type YX, collect the parts matching information of each faulty equipment within each operation and maintenance type, and perform operation and maintenance sorting matching management analysis on the parts matching information, and send the sorted fault control demand coefficient corresponding to the faulty equipment to the management display unit, and send the sorted operation and maintenance delay index corresponding to the faulty equipment to the management display unit.

2. The photovoltaic power station fault location system based on artificial intelligence according to claim 1 is characterized in that: The operation fault safety supervision and analysis process of the fault identification unit is as follows: A monitoring cycle is set and set as a time threshold, and operation-related data of each level of system equipment of the photovoltaic power station within the time threshold are obtained. The operation-related data include actual operating voltage and actual energy consumption per unit time. The operation-related data are judged and processed. If the value corresponding to the operation-related data exceeds the preset threshold or the value corresponding to the operation-related data deviates from the preset range, a risk signal is generated, and the number corresponding to the risk signal is obtained. The number corresponding to the risk signal is set as a fault assessment index, and the fault assessment index is judged and processed to obtain a fault signal, and the level system equipment corresponding to the fault signal is set as a faulty device.

3. The photovoltaic power station fault location system based on artificial intelligence according to claim 1 is characterized in that: The fault control requirement type classification and analysis process of the control classification unit is as follows: Fault data of each faulty device within the time threshold is obtained, the fault data including the operation efficiency deviation value and the mutation risk index. At the same time, the induced activity factor coefficient corresponding to each faulty device is retrieved, and the faulty device is set to g, where g is a natural number greater than zero. The operation efficiency deviation value, the mutation risk index and the induced activity factor coefficient are set to YPg, TFg and YHg respectively. The fault control demand coefficient Qg of each faulty device is obtained according to the formula. The fault control demand coefficient Qg is compared and analyzed with the preset fault control demand coefficient range entered and stored internally to obtain Class I operation and maintenance equipment, Class II operation and maintenance equipment and Class III operation and maintenance equipment. Class I operation and maintenance equipment, Class II operation and maintenance equipment and Class III operation and maintenance equipment are set as operation and maintenance type YX, where YX=1, 2, 3.

4. The photovoltaic power station fault location system based on artificial intelligence according to claim 3 is characterized in that: The operational efficiency deviation value indicates the product of the portion of the actual operational efficiency of each faulty device that is lower than the set operational efficiency and the current energy consumption value after data normalization processing; the mutation risk index indicates the growth rate of the value corresponding to the operational related data exceeding the preset threshold or the value corresponding to the operational related data deviating from the preset range within a set period of time after each faulty device generates a risk signal.

5. The photovoltaic power station fault location system based on artificial intelligence according to claim 1 is characterized in that: The historical fault induced impact analysis process of the induced performance unit is as follows: Obtain the historical operating data of each faulty device within the time threshold. The historical operating data includes the operation and maintenance evaluation index and the historical operation efficiency index. The operation and maintenance evaluation index and the historical operation efficiency index are labeled as YW and LX respectively. According to the formula The historical mutation risk coefficient is obtained, where f1 and f2 are the preset weight factor coefficients of the operation and maintenance evaluation index and the historical operation efficiency index respectively, f3 is the preset fault tolerance factor coefficient, f1, f2 and f3 are all greater than zero, and YF represents the historical mutation risk coefficient. The historical mutation risk coefficient YF is compared and analyzed with the preset historical mutation risk coefficient interval stored internally, and the corresponding parameter of the historical mutation risk coefficient YF belonging to the corresponding preset historical mutation risk coefficient interval is set as the induced activity factor coefficient.

6. The photovoltaic power station fault location system based on artificial intelligence according to claim 5 is characterized in that: The operation and maintenance evaluation index represents the product of the operation and maintenance coefficient of each faulty equipment and the usage index after data normalization processing. The operation and maintenance coefficient represents the sum of the total duration corresponding to the number of historical maintenance delays and the equipment input duration. The usage index represents the duration between the last maintenance end time and the current time. The historical operation efficiency index represents the average of the mutation risk index corresponding to the historical risk signal generated by each faulty equipment.

7. The photovoltaic power station fault location system based on artificial intelligence according to claim 1, characterized in that: The operation and maintenance sorting matching management and analysis process of the progressive sorting unit is as follows: Obtain the fault part code of each faulty device in each operation and maintenance type within the time threshold, and at the same time obtain the existing part code of each existing part in the parts inventory, set each existing part code in the parts inventory as the existing part code, and match the fault part code with the existing part code for analysis: If the faulty part code belongs to an existing part code, a feedback instruction is generated. When the feedback instruction is generated, the fault control demand coefficients of each faulty device in each operation and maintenance type are sorted in descending order; If the faulty part code does not belong to the existing part codes, a retrieval instruction is generated.

8. The photovoltaic power station fault location system based on artificial intelligence according to claim 7 is characterized in that: When the progressive sorting unit generates a call instruction: The parts matching information of each faulty equipment in each operation and maintenance type within the time threshold is obtained. The parts matching information includes the historical parts procurement times and the historical parts procurement duration. Then, the average of the historical parts procurement duration is obtained based on the historical parts procurement times and the single historical parts procurement duration. The average is set as the operation and maintenance delay index, and the operation and maintenance delay index is sorted in ascending order.

Images