A method and device for regulating an inverter of a photovoltaic power generation system

Abstract

The embodiment of the present application provides a kind of photovoltaic power generation system's inverter's regulation and control method and device, above-mentioned regulation and control method includes: obtaining the operation data of photovoltaic power generation system's inverter;The operation data is preprocessed, and operation parameter is obtained;According to the operation parameter, the operating state of the inverter is determined;According to the operating state, the control instruction of the inverter is determined;According to the control instruction, the inverter is regulated and controlled.The embodiment of the present application can respond quickly and effectively handle to abnormal situation, reduce the adverse effects caused by parameter fluctuation.

Description

TECHNICAL FIELD

[0001] The embodiment of the application relates to the technical field of photovoltaic power generation, in particular to a control method and device of an inverter of a photovoltaic power generation system. BACKGROUND

[0002] In a photovoltaic power generation system, the inverter is a core energy conversion device connecting a photovoltaic array (converting solar energy into direct-current power) and a power grid / load (requiring alternating-current power), and the performance of the inverter directly determines the power generation efficiency, operation safety and reliability of the system. The state judgment of the existing inverter of the photovoltaic power generation system depends on a fixed threshold, and the accuracy is insufficient without dynamic evaluation of multiple factors; and the abnormal state processing mechanism is lacking, and it is difficult to respond in time when the parameters fluctuate. SUMMARY

[0003] The technical problem to be solved by the embodiment of the application is to provide a control method and device of an inverter of a photovoltaic power generation system, which can quickly respond to abnormal conditions and effectively handle them, and reduce the adverse effects caused by parameter fluctuations.

[0004] To solve the above technical problems, the technical scheme of the embodiment of the application is as follows:

[0005] A control method of an inverter of a photovoltaic power generation system, comprising:

[0006] obtaining operation data of the inverter of the photovoltaic power generation system;

[0007] preprocessing the operation data to obtain operation parameters;

[0008] determining an operation state of the inverter according to the operation parameters;

[0009] determining a control instruction of the inverter according to the operation state;

[0010] controlling the inverter according to the control instruction.

[0011] Optionally, preprocessing the operation data to obtain operation parameters comprises:

[0012] determining an operation parameter according to XN = ( XY - XI ) / ( XA - XI ) of the operation data;

[0013] wherein, XN is the operation parameter, XY is the operation data, XI is a minimum value of a data frame in a set time period of the operation data, XA is a maximum value of the data frame in the set time period of the operation data.

[0014] Optionally, the operation state of the inverter is determined according to the operation parameters, including:

[0015] According to the operation parameters, a first probability of normal operation, a second probability of overload operation, a third probability of overheating operation, a fourth probability of aging state and a fifth probability of fault state of the inverter are determined.

[0016] According to the first probability, the second probability, the third probability, the fourth probability and the fifth probability, the operation state of the inverter is determined.

[0017] Optionally, the first probability of normal operation of the inverter is determined according to the operation parameters, including:

[0018] According to , the first probability is determined.

[0019] Wherein, P 1 is the first probability, K 1 is the first sensitivity coefficient, XN i is an operation parameter, i=1, 2, 3, …, 11, w i is a weight coefficient of the operation parameter, XM i is a normal reference value of the operation parameter, A is a first score threshold.

[0020] Optionally, the second probability of overload operation of the inverter is determined according to the operation parameters, including:

[0021] According to , the second probability is determined.

[0022] Wherein, P 2 is the second probability, K 2 is the second sensitivity coefficient, w 4 is a weight coefficient of the alternating current, XN 4 is an operation parameter of the alternating current, XG 4 is an overload reference value of the alternating current, w 1 is a weight coefficient of the direct current voltage, XN 1 is an operation parameter of the direct current voltage, XG 1 is an overload reference value of the direct current voltage, w 2 is a weight coefficient of the direct current, XN 2 is an operation parameter of the direct current, XG 2 is an overload reference value of the direct current, B is a second score threshold.

[0023] Optionally, the third probability of overheat of the inverter is determined according to the operation parameter, comprising:

[0024] According to , the third probability is determined;

[0025] wherein, P 3 is the third probability, K 3 is the third sensitivity coefficient, w 9 is a weight coefficient of the insulated gate bipolar transistor temperature, XN 9 is an operation parameter of the insulated gate bipolar transistor temperature, XR 9 is an overheat reference value of the insulated gate bipolar transistor temperature, w 8 is a weight coefficient of the fan rotating speed, XN 8 is an operation parameter of the fan rotating speed, XR 8 is an overheat reference value of the fan rotating speed, C is a third score threshold.

[0026] Optionally, the fourth probability of aging state of the inverter is determined according to the operation parameter, comprising:

[0027] According to , the fourth probability is determined;

[0028] wherein, P 4 is the fourth probability, K 4 is the fourth sensitivity coefficient, w 10 is a weight coefficient of the capacitor impedance, XN 10 is an operation parameter of the capacitor impedance, XL 10 is an aging reference value of the capacitor impedance, w 9 is a weight coefficient of the insulated gate bipolar transistor temperature, XN 9 is an operation parameter of the insulated gate bipolar transistor temperature, XR 9 is an aging reference value of the insulated gate bipolar transistor temperature, D is a fourth score threshold.

[0029] Optionally, the fifth probability of fault state of the inverter is determined according to the operation parameter, comprising:

[0030] According to , the fifth probability is determined;

[0031] wherein, P 5 is the fifth probability, K 5 is the fifth sensitivity coefficient, w i is a weight coefficient of the operation parameter, XN i is an operation parameter,XZ i The fault baseline value for the operating parameters, L This is an abnormal superposition coefficient. P 2 represents the second probability. P 3 is the third probability. E This is the fifth scoring threshold.

[0032] Optionally, the operating state of the inverter is determined based on the first probability, the second probability, the third probability, the fourth probability, and the fifth probability, including:

[0033] like P 5≧ P 6. Determine that the inverter is in a fault state;

[0034] in, P 5 is the fifth probability. P 6 is the fault determination threshold;

[0035] like P 5< P 6, and P 3≧ P 7. Determine that the inverter is in an overheated state.

[0036] in, P 3 is the third probability. P 7 is the overheating threshold;

[0037] like P 5< P 6, P 3< P 7, and P 2≧ P 8. Determine that the inverter is in an overload state;

[0038] in, P 2 represents the second probability. P 8 represents the overload threshold.

[0039] like P 5< P 6, P 3< P 7, P 2< P 8, and P 4≧ P 9. Determine that the inverter is in an aging state.

[0040] in, P 4 is the fourth probability. P 9 is the aging assessment threshold;

[0041] like P5< P 6, P 3< P 7, P 2< P 8, P 4< P 9, and P 1≧ P 10 The inverter is determined to be in normal operating condition.

[0042] in, P 1 represents the first probability. P 10 This is the normal threshold.

[0043] like P 5< P 6, P 3< P 7, P 2< P 8, P 4< P 9, and P 1< P 10 The inverter's operating state is determined to be abnormal.

[0044] Embodiments of the present invention also provide a control device for an inverter in a photovoltaic power generation system, comprising:

[0045] The acquisition module is used to acquire the operating data of the inverter in the photovoltaic power generation system;

[0046] The processing module is used to preprocess the operating data to obtain operating parameters; determine the operating state of the inverter based on the operating parameters; determine the control command of the inverter based on the operating state; and control the inverter according to the control command.

[0047] The above-described solutions of the embodiments of the present invention have at least the following beneficial effects:

[0048] The above-described solution in this invention no longer relies on a single fixed threshold. Instead, it obtains multi-dimensional operating parameters by acquiring inverter operating data and preprocessing it. It comprehensively and dynamically evaluates the inverter's operating status based on multiple factors, which can more comprehensively and accurately reflect the actual operating conditions of the inverter and avoid misjudgment or omission due to the limitations of fixed thresholds.

[0049] A complete mechanism has been established, from determining the operating status to generating control commands and then executing the control. When the inverter experiences parameter fluctuations or abnormal states, corresponding control commands can be generated and executed in a timely manner based on the actual operating status, enabling rapid response and effective handling of abnormal situations and reducing the adverse effects caused by parameter fluctuations.

[0050] Through dynamic and accurate regulation, the inverter can always work in an optimal state, which is beneficial to improve the power generation efficiency of the photovoltaic power generation system, while ensuring the safety and reliability of the system operation, and prolonging the service life of the inverter and the entire photovoltaic power generation system.

[0051] Since the dynamic evaluation mode of multiple factors is adopted, the method can better adapt to the operation requirements of the photovoltaic power generation system under complex and variable working conditions, and ensure that the inverter can stably and efficiently operate under various environmental conditions. BRIEF DESCRIPTION OF DRAWINGS

[0052] Figure 1 is a flowchart of the regulation method of the inverter of the photovoltaic power generation system provided by the embodiment of the present application.

[0053] Figure 2 is a module schematic diagram of the regulation device of the inverter of the photovoltaic power generation system provided by the embodiment of the present application. DETAILED DESCRIPTION

[0054] Exemplary embodiments of the present application will be described herein below with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present application can be more thoroughly understood and the scope of the present application can be accurately conveyed to those skilled in the art.

[0055] As shown in Figure 1 , the embodiment of the present application provides a regulation method of an inverter of a photovoltaic power generation system, comprising:

[0056] Step 11, obtaining operation data of the inverter of the photovoltaic power generation system;

[0057] Step 12, preprocessing the operation data to obtain operation parameters;

[0058] Step 13, determining the operation state of the inverter according to the operation parameters;

[0059] Step 14, determining the regulation instruction of the inverter according to the operation state;

[0060] Step 15, regulating the inverter according to the regulation instruction.

[0061] In this example, instead of relying on a single fixed threshold, multiple-dimensional operation parameters are obtained by obtaining and preprocessing the operation data of the inverter, and the operation state of the inverter is dynamically evaluated by comprehensively considering multiple factors, which can more comprehensively and accurately reflect the actual working condition of the inverter, and avoid misjudgment or omission caused by the limitations of the fixed threshold.

[0062] A complete mechanism from running state determination to control instruction generation to execution control is established, when parameter fluctuation or abnormal state of the inverter occurs, corresponding control instructions can be generated and executed in time according to the actual running state, the fast response and effective processing of abnormal conditions are realized, and the adverse effects caused by parameter fluctuation are reduced.

[0063] Through dynamic and accurate control, the inverter can always work in an optimal state, which is beneficial to improve the power generation efficiency of the photovoltaic power generation system, and at the same time, the safety and reliability of system operation are ensured, and the service life of the inverter and the whole photovoltaic power generation system is prolonged.

[0064] Since the dynamic evaluation method of multiple factors is adopted, the method can better adapt to the operation requirements of the photovoltaic power generation system under complex and variable working conditions, and ensure that the inverter can stably and efficiently operate under various environmental conditions.

[0065] In an optional embodiment of the present application, in step 11, the running data includes: DC side data, AC side data, environmental data, equipment state data and capacitor health parameters;

[0066] The DC side data includes: DC voltage and DC current;

[0067] The AC side data includes: AC voltage, AC current and harmonic distortion rate;

[0068] The environmental data includes: temperature, humidity and light intensity;

[0069] The equipment state data includes: fan speed and insulated gate bipolar transistor temperature;

[0070] The capacitor health parameters include: capacitor impedance.

[0071] Specifically, the running data of the inverter can be acquired by multiple types of sensors, wherein the DC voltage can be acquired by a DC voltage sensor, the DC current can be acquired by a DC current sensor, the AC voltage can be acquired by an AC voltage sensor, the AC current can be acquired by an AC current sensor, the harmonic distortion rate can be acquired by an AC voltage / current sensor, the temperature and humidity can be acquired by a temperature and humidity sensor, the light intensity can be acquired by a light sensor, the fan speed can be acquired by a fan self-contained speed feedback signal, the insulated gate bipolar transistor temperature can be acquired by a thermistor, and the capacitor impedance can be acquired by a capacitor impedance detection module.

[0072] In this example, the operation data is subdivided into five categories: direct current side, alternating current side, environment, device state, and capacitor health, and specific indicators of each subcategory are specified, achieving multi-dimensional and full-scenario coverage of the inverter operation state.

[0073] Different types of operation data reflect the operation status of the inverter from different perspectives. For example, direct current side data reflects the power characteristics of the photovoltaic array input, alternating current side data reflects the power quality of the inverter output to the grid / load, environment data is related to the influence of external working conditions on the device, device state data directly shows the operation of internal key components, and capacitor health parameters are related to the performance of the core components of the inverter. By analyzing these data, the actual operation status of the inverter can be more accurately evaluated, and misjudgments caused by one-sided data can be avoided.

[0074] In an optional embodiment of the present application, in step 12, the operation data is preprocessed to obtain operation parameters, including:

[0075] In step 121, the operation parameters are determined according to XN =( XY - XI ) / ( XA - XI ).

[0076] Wherein, XN is the operation parameter, XY is the operation data, XI is the minimum value of the data frame within the set time period of the operation data, XA is the maximum value of the data frame within the set time period of the operation data.

[0077] In this example, different operation data characteristics can be adapted, as the reference value is taken from the fluctuation range of the data itself within the set period, which can accurately map various data to a unified dimension, avoid deviations caused by fixed ranges, and further improve the accuracy of the operation parameters, providing more accurate data support for subsequent state judgment and control instruction generation.

[0078] In an optional embodiment of the present application, in step 13, the operation state of the inverter is determined according to the operation parameters, including:

[0079] In step 131, the first probability of normal operation, the second probability of overload operation, the third probability of overheating operation, the fourth probability of aging state, and the fifth probability of fault state of the inverter are determined according to the operation parameters.

[0080] In step 132, the operation state of the inverter is determined according to the first probability, the second probability, the third probability, the fourth probability, and the fifth probability.

[0081] In this example, the operating state of the inverter is determined by probability analysis. The operating state is fully covered and is subdivided into five categories: normal, overload, overheating, aging and failure, taking into account both normal and abnormal conditions, avoiding the limitations of single state division in traditional judgment, and more completely capturing the operating state of the inverter. The judgment is more scientific, the probability of each state is calculated, the subjective or fixed threshold judgment is replaced by quantitative data, the human error is reduced, and the state evaluation is more objective and accurate. Provide clear basis for regulation and control, determine the final state according to the multiple probability results, and match the regulation and control strategy.

[0082] In an optional embodiment of the application, in step 131, a first probability that the inverter is operating normally is determined according to the operating parameters, comprising:

[0083] In step 1311, the first probability is determined according to

[0084] wherein, P 1 is the first probability, K 1 is the first sensitivity coefficient, XN i is the operating parameter, i=1, 2, 3,..., 11, w i is the weight coefficient of the operating parameter, XM i is the normal reference value of the operating parameter, A is the first score threshold;

[0085] In step 131, a second probability that the inverter is operating overload is determined according to the operating parameters, comprising:

[0086] In step 1312, the second probability is determined according to

[0087]

[0088] wherein, P 2 is the second probability, K 2 is the second sensitivity coefficient, w 4 is the weight coefficient of the alternating current, XN 4 is the operating parameter of the alternating current, XG 4 is the overload reference value of the alternating current, w 1 is the weight coefficient of the direct current, XN 1 is the operating parameter of the direct current, XG 1 is the overload reference value of the direct current, w 2 is the weight coefficient of the direct current, XN 2 is the operating parameter of the direct current, XG 2 is the overload reference value of the direct current, B is the second score threshold;​​

[0089] In step 131, a third probability of overheat of the inverter is determined according to the operation parameters, comprising:

[0090] In step 1313, the third probability is determined according to

[0091] wherein, P 3 is the third probability, K 3 is the third sensitivity coefficient, w 9 is a weight coefficient of the insulated gate bipolar transistor temperature, XN 9 is an operation parameter of the insulated gate bipolar transistor temperature, XR 9 is an overheat reference value of the insulated gate bipolar transistor temperature, w 8 is a weight coefficient of the fan rotating speed, XN 8 is an operation parameter of the fan rotating speed, XR 8 is an overheat reference value of the fan rotating speed, C is a third score threshold value;

[0092] In step 131, a fourth probability of aging state of the inverter is determined according to the operation parameters, comprising:

[0093] In step 1314, the fourth probability is determined according to

[0094] wherein, P 4 is the fourth probability, K 4 is the fourth sensitivity coefficient, w 10 is a weight coefficient of the capacitor impedance, XN 10 is an operation parameter of the capacitor impedance, XL 10 is an aging reference value of the capacitor impedance, w 9 is a weight coefficient of the insulated gate bipolar transistor temperature, XN 9 is an operation parameter of the insulated gate bipolar transistor temperature, XR 9 is an aging reference value of the insulated gate bipolar transistor temperature, D is a fourth score threshold value;

[0095] In step 131, a fifth probability of fault state of the inverter is determined according to the operation parameters, comprising:

[0096] In step 1315, the fifth probability is determined according to

[0097] wherein, P 5 is the fifth probability, K 5 is the fifth sensitivity coefficient, w ​​​i a weight coefficient of an operating parameter, XN i an operating parameter, XZ i a fault reference value of an operating parameter, L an abnormal superposition coefficient, P 2 is a second probability, P 3 is a third probability, E a fifth score threshold.

[0098] Specifically, XN 1 is a direct current voltage, XN 2 is a direct current, XN 3 is an alternating current voltage, XN 4 is an alternating current, XN 5 is a temperature, XN 6 is humidity, XN 7 is an illumination intensity, XN 8 is a fan speed, XN 9 is an insulated gate bipolar transistor temperature, XN 10 a capacitor impedance, XN 11 a harmonic distortion rate.

[0099] In this example, each state calculation focuses on core influencing parameters: for example, the normal state covers all 11 operating parameters, and the overall working condition is comprehensively considered; overload focuses on direct current voltage, current and alternating current, and directly attacks the key causes of overload; overheating locks the insulated gate bipolar transistor temperature and fan speed, accurately associates the core elements of heat dissipation and heating; aging focuses on capacitor impedance and insulated gate bipolar transistor temperature, which is consistent with the characteristics of component aging; and fault not only combines multiple parameters, but also superimposes the probabilities of overload and overheating, which is suitable for the actual situation that faults are often caused by abnormal superposition.

[0100] The introduction of sensitivity coefficients, parameter weights and exclusive reference values can differentiate the influence of different parameters on each state, avoid the deviation caused by one-size-fits-all parameters, and make the probability calculation more consistent with the operation rules of the inverter.

[0101] Provide accurate data support for state judgment, each probability calculation is based on clear parameters and formulas, the output quantitative results are objective and controllable, which greatly reduces the subjective judgment error, so that the subsequent steps can more accurately identify the real working condition of the inverter according to multiple probabilities to determine the final operating state.

[0102] In an optional embodiment of the present application, in step 132, the operating state of the inverter is determined according to the first probability, the second probability, the third probability, the fourth probability and the fifth probability, which comprises:

[0103] Step 1321, if P 5≧ P 6, it is determined that the operating state of the inverter is a fault state;

[0104] wherein, P 5 is a fifth probability, P 6 is a fault determination threshold value;

[0105] Step 1322, if P 5< P 6, and P 3≧ P 7, it is determined that the operating state of the inverter is an overheating state;

[0106] wherein, P 3 is a third probability, P 7 is an overheating determination threshold value;

[0107] Step 1323, if P 5< P 6, P 3< P 7, and P 2≧ P 8, it is determined that the operating state of the inverter is an overload state;

[0108] wherein, P 2 is a second probability, P 8 is an overload determination threshold value;

[0109] Step 1324, if P 5< P 6, P 3< P 7, P 2< P 8, and P 4≧ P 9, it is determined that the operating state of the inverter is an aging state;

[0110] wherein, P 4 is a fourth probability, P 9 is an aging determination threshold value;

[0111] Step 1325, if P 5< P 6, P 3< P 7, P 2< P 8, P 4< P 9, and P 1≧ P 10 , it is determined that the operating state of the inverter is a normal state;

[0112] wherein, P 1 is a first probability, P 10 is a normal determination threshold value;

[0113] Step 1326, if P 5 P 6, P 3 P 7, P 2 P 8, P 4 P 9, and P 1 P 10 determines that the operating state of the inverter is an abnormal state.

[0114] In this example, the determination is in the order of fault, overheating, overload, aging, normal, the high-risk state such as fault is processed preferentially, and then other abnormal and normal conditions are sequentially investigated, which meets the operation requirements of photovoltaic power generation system of first ensuring safety and then ensuring stability, and avoids delay in handling high-risk problems due to misjudgment of low-priority state.

[0115] The determination criteria are clear and explicit, each step is based on comparison of corresponding probability and exclusive threshold value, there is no subjective and fuzzy determination space, and through multi-condition progressive screening, the error of single condition determination is greatly reduced, so that the operating state recognition is more accurate.

[0116] The covered scenarios are comprehensive, in addition to the five types of core states, an abnormal state is added to cope with special working conditions when all probabilities do not meet the standard, and to avoid blank areas in state determination; at the same time, the hierarchical logic makes the boundaries of various states clear, which not only facilitates the system to quickly locate the current working condition, but also provides clear guidance for subsequent matching of differentiated regulation strategies, further improving the pertinence and effectiveness of inverter regulation.

[0117] In an optional embodiment of the present application, in step 14, the regulation instruction of the inverter is determined according to the operating state, comprising:

[0118] Step 141, if the operating state is a fault state, the regulation instruction of the inverter is determined to be disconnected from the grid and to stop power output;

[0119] Step 142, if the operating state is an overheating state, the regulation instruction of the inverter is determined to be reduced in gradient to reduce the output power of the inverter, and the speed of the cooling fan is increased to the rated maximum value;

[0120] Step 143, if the operating state is an overload state, the regulation instruction of the inverter is determined to limit the input power on the DC side;

[0121] Step 144, if the running state is an aging state, determining the control instruction of the inverter as controlling the insulated gate bipolar transistor temperature below the set working temperature;

[0122] Step 145, if the running state is a normal state, determining the control instruction of the inverter as not performing control;

[0123] Step 146, if the running state is an abnormal state, determining the control instruction of the inverter as raising the sampling frequency of the running data to a set frequency, and re-determining the running state.

[0124] In this example, the exclusive control instruction is matched for different running states, realizing accurate correspondence between state and instruction. The risk prevention and control is accurate and efficient: in the fault state, the power grid connection is cut off and the power output is stopped, which can block the fault diffusion in the first time and avoid damaging the equipment or affecting the safety of the power grid; in the overheating state, the power is reduced by gradient and the fan is operated at full speed, which can quickly relieve the heating problem and prevent the components from failing due to high temperature; in the overload state, the input power of the direct current side is limited, which directly reduces the load pressure from the source and avoids the long-term overload of the inverter to shorten the service life.

[0125] Both running efficiency and equipment protection are considered: in the aging state, the insulated gate bipolar transistor temperature control is focused on, which ensures the stable operation of the core components while avoiding excessive control affecting the power generation efficiency; in the normal state, no control is performed, which reduces unnecessary operation loss, maintains the optimal power generation state of the inverter, and meets the efficient operation demand of the system.

[0126] The abnormality treatment closed loop is perfect: in the abnormal state, the sampling frequency is raised and the state is re-determined, which can accurately capture the working condition changes through more intensive data collection, avoid control without clear corresponding state, avoid improper control due to state misjudgment, further strengthen the stability and reliability of the inverter operation, and provide strong support for the continuous and efficient power generation of the entire photovoltaic power generation system.

[0127] In an optional embodiment of the application, in step 15, the inverter is controlled according to the control instruction, including:

[0128] Step 151, if the running state is a fault state, cutting off the connection between the inverter and the power grid and stopping the power output;

[0129] Step 152, if the running state is an overheating state, limiting the input power of the direct current side;

[0130] Step 153, if the running state is an overload state, controlling the insulated gate bipolar transistor temperature below the set working temperature;

[0131] Step 154, if the running state is an aging state, not performing control;

[0132] Step 155, if the operating state is a normal state,

[0133] Step 156, if the operating state is an abnormal state, the sampling frequency of the operating data is increased to a set frequency, and the operating state is re-judged.

[0134] In this example, according to the regulation instruction landing specific regulation operation, the instruction-execution closed loop is formed to ensure the safe and stable operation of the inverter. The fault is handled decisively and completely: directly cutting off the grid connection and stopping the power output in the fault state, which can immediately block the influence of the fault on the inverter itself and the grid, maximally reduce the risk of equipment damage and the safety hazard of the grid, and avoid the expansion of the fault.

[0135] Abnormal state response is targeted: in the abnormal state, the sampling frequency is increased and the state is re-judged, the working condition details are accurately captured through high-frequency data acquisition, which provides a basis for subsequent accurate adjustment of regulation strategy, effectively solves the regulation problem in the state of ambiguity, and prevents new problems caused by improper handling.

[0136] Example 1

[0137] Taking a 10kW string inverter (rated DC voltage 800V, rated AC current 15A, insulated gate bipolar transistor rated operating temperature 125℃) as an object, example 1 provides a regulation method for an inverter of a photovoltaic power generation system, which comprises:

[0138] Step 21, basic parameter setting:

[0139] In the normal state, the DC voltage reference value corresponds to 600V (0.5 after normalization), the AC current overload reference value is 18A (0.8 after normalization), the insulated gate bipolar transistor overheating reference value is 100℃ (0.7 after normalization), and the capacitor impedance aging reference value is 5Ω (0.6 after normalization); the sensitivity coefficients are: K 1=0.9 (normal probability), K 2=1.1 (overload probability), K 3=1.2 (overheating probability), K 4=1.0 (aging probability), K 5=1.3 (fault probability); in the weight coefficient, the DC voltage is 0.1, the AC current is 0.25, the fan speed is 0.15, the insulated gate bipolar transistor temperature is 0.3, and the capacitor impedance is 0.2; the determination threshold is set as: fault 25%, overheating 35%, overload 40%, aging 50%, normal 85%; the abnormal superposition coefficient L =0.8, the sampling frequency is set to 5Hz (normal 1Hz) in the abnormal state;

[0140] Step 22, scene 1: fault state regulation example:

[0141] Step 221, Data Acquisition:

[0142] At a certain moment, sensor data collected showed: DC voltage 950V (18.75% over the rated value), DC current 12A; AC voltage 380V, AC current 0A (no output), harmonic distortion rate 8% (5% over the national standard); ambient temperature 32℃, humidity 60%, light intensity 800W / ㎡; fan speed 0rpm (stopped), insulated gate bipolar transistor temperature 130℃ (4℃ over the rated value); capacitor impedance 12Ω (140% over the aging reference value).

[0143] Step 222, Data Preprocessing:

[0144] Set a 10-minute data frame (600 frames), calculate the minimum and maximum values ​​and normalize them: DC voltage minimum 500V, maximum 1000V, normalized value is (950-500) / (1000-500)=0.9; similarly, other parameters are obtained: DC current 0.6, AC voltage 0.9, AC current 0, ambient temperature 0.5, humidity 0.6, light intensity 0.8, fan speed 0, insulated gate bipolar transistor temperature 0.9, capacitor impedance 0.8, harmonic distortion rate 0.8;

[0145] Step 223, State determination:

[0146] Calculate the following probabilities: probability of failure P 5 = 35%, normal probability 5%, overload probability 10%, overheating probability 60%, aging probability 70%; because P 5 = 35% ≥ Fault threshold 25%, is judged as a fault state;

[0147] Step 224, Generate instructions:

[0148] Based on the fault status, a control command is generated to disconnect the inverter from the grid and stop power output;

[0149] Step 225, Implementation of Control Measures:

[0150] Execute the network disconnection operation: First, send a trip signal to the grid-side contactor, and receive feedback that the trip is in place after 200ms; then disconnect the DC-side circuit breaker, and confirm that the DC voltage drops from 950V to 5V within 3 sampling cycles (10ms / time), and the power output stops; trigger the red fault light to stay on and the buzzer alarm, send the fault code and parameter snapshot to the monitoring center, lock the inverter status to prevent startup, and record the fault time as 2024-07-10 14:30:00;

[0151] Step 23, Scenario 2: Example of overheating control:

[0152] Step 231, Data Acquisition:

[0153] Midsummer running data: DC voltage 750V, current 13A; AC voltage 380V, current 14A, harmonic distortion rate 3%; ambient temperature 38℃, humidity 50%, light intensity 1000W / ㎡; fan speed 2000rpm (rated maximum 3000rpm), insulated gate bipolar transistor temperature 98℃; capacitor impedance 4.5Ω;

[0154] Step 232, data preprocessing:

[0155] 5-minute data frame processing: insulated gate bipolar transistor temperature minimum value 60℃, maximum value 120℃, normalized value (98-60) / (120-60)=0.63; fan speed normalization 0.67, other parameters: DC voltage 0.5, current 0.8, AC voltage 0.9, current 0.7, ambient temperature 0.7, humidity 0.5, light intensity 1.0, capacitor impedance 0.5, harmonic distortion rate 0.3;

[0156] Step 233, state determination:

[0157] Overheating probability calculation: P 3=42% (based on the weighted calculation of insulated gate bipolar transistor temperature and fan speed deviation from the reference value), fault probability 8%, overload probability 30%, aging probability 35%, normal probability 80%; since fault probability <25% and overheating probability 42%≥35%, it is determined as an overheating state;

[0158] Step 234, generating instructions:

[0159] Generate control instructions to reduce inverter output power by gradient and increase cooling fan speed to the rated maximum value;

[0160] Step 235, control execution:

[0161] Fan control: send 100% PWM signal, confirm speed to 3000rpm (normalized 1.0) after 3 seconds; power regulation: current output power is about 9.1kW, first gradient target 7.7kW (85%), complete adjustment by reducing insulated gate bipolar transistor switching frequency (10kHz-9.5kHz) within 500ms; temperature monitoring shows that the insulated gate bipolar transistor temperature drops to 92℃ (normalized 0.58) after 15 seconds, which is lower than 90% of the overheating reference value; after 30 minutes, the ambient temperature decreases, and the power is restored to 8.5kW by 5% gradient, maintaining the insulated gate bipolar transistor temperature at 87℃;

[0162] Step 24, scene 3: abnormal state control instance:

[0163] Step 241, data acquisition:

[0164] Rainy day data (greater fluctuations): DC voltage 550V (fluctuation ± 50V for 1 minute), current 8A; AC voltage 370V, current 10A, harmonic distortion rate 4%; ambient temperature 28℃, humidity 75%, light intensity 300W / ㎡ (fluctuation ± 100W / ㎡); fan speed 1500rpm, insulated gate bipolar transistor temperature 65℃; capacitor impedance 4.8Ω;

[0165] Step 242, data preprocessing:

[0166] 3-minute data frame processing: DC voltage normalization 0.3 (fluctuation ± 0.1), light intensity 0.3 (fluctuation ± 0.1), other parameters: DC current 0.4, AC voltage 0.85, current 0.5, ambient temperature 0.4, humidity 0.8, fan speed 0.5, insulated gate bipolar transistor temperature 0.3, capacitor impedance 0.55, harmonic distortion rate 0.4;

[0167] Step 243, state determination:

[0168] Normal probability 80% (< 85%), fault probability 5%, overheat probability 15%, overload probability 25%, aging probability 40%, none of which reaches the corresponding threshold, and it is determined as an abnormal state;

[0169] Step 244, generate instructions:

[0170] Generate control instructions to increase the running data sampling frequency to 5Hz and re-determine the running state;

[0171] Step 245, control execution:

[0172] Sampling frequency switching: change the AD sampling period from 1000ms to 200ms, verify that the switching is successful; high-frequency collection for 1 minute (300 frames), after sliding average filtering, the parameter fluctuation is reduced (DC voltage 0.32±0.03, light intensity 0.31±0.02); secondary determination shows that the normal probability is 88% (≥85%), restore the normal sampling frequency, maintain running according to the normal state, and send an abnormal release message;

[0173] Step 25, in the overload state, the AC current normalized value 0.85 (15.3A) causes the overload probability to be 45%, and the control measure is to limit the DC input power to 8kW, and after 10 minutes the current is reduced to 13.5A to restore normal; the aging state causes the aging probability to be 55% due to the capacitor impedance 5.25Ω (normalized 0.65), and by controlling the insulated gate bipolar transistor temperature below 80℃, the device is maintained stable operation; in the normal state, all parameters are within the reference range, and the normal operation mode is maintained, and there is no state switching for 24 hours.

[0174] The present application realizes the double guarantee of comprehensive collection + reliable processing. The running data is subdivided into five categories: DC side (voltage, current), AC side (voltage, current, harmonic distortion rate), environment (temperature and humidity, illumination), equipment state (fan speed, insulated gate bipolar transistor temperature), and capacitor health (capacitor impedance), which are matched with multiple types of professional collection equipment (such as DC / AC sensors, thermistors, etc.), to realize multi-dimensional and full-scene coverage of the inverter running state, avoiding misjudgment caused by one-sided data; through normalization processing, the dimensional difference and numerical deviation are eliminated, and multiple types of data can be analyzed in a unified dimension, providing a high-quality data basis for subsequent evaluation.

[0175] At the state evaluation level, a scientific system of probability quantization + layered judgment is constructed. Special probability calculation methods are designed for normal, overload, overheating, aging, and fault states, focusing on core influencing parameters of each state (such as fault superimposed overload / overheating probability, aging related capacitor impedance and insulated gate bipolar transistor temperature), and introducing sensitivity coefficients, parameter weights, and special reference values, to replace fixed thresholds and subjective judgments with quantitative data, greatly improving the objectivity of evaluation; layered judgment is performed according to the priority of fault-overheat-overload-aging-normal-anomaly, high-risk states are prioritized for disposal, and an abnormal state is added to fill in the blank, making state recognition more accurate and comprehensive, and avoiding misjudgment of low-priority states delaying high-risk problem disposal.

[0176] At the regulation and execution level, precise instructions and closed-loop landing are achieved for efficient response. Special regulation instructions are matched for different states (such as fault cutting off the power grid, overheating gradient reducing power, and abnormal increasing sampling frequency), to realize precise correspondence between state and instruction, ensuring risk prevention (such as fault blocking diffusion and overload limiting input power), and also considering efficiency (normal state without regulation to reduce loss); specific operations are landed to form a closed loop of instruction-execution, even if some steps are different from the previous instructions, the core still focuses on resolving working condition problems, ensuring the effectiveness of regulation instructions, while high-frequency sampling in abnormal state is re-judged to improve the abnormal disposal process and prevent improper regulation.

[0177] At the scene adaptation level, it has the outstanding advantages of dynamic adaptation + long-term stability. The entire method does not rely on a single fixed threshold, and through comprehensive multi-factor dynamic evaluation (such as data preprocessing and probability calculation), it can accurately adapt to complex working conditions such as different illumination, temperature, and load, ensuring stable operation of the inverter in various environments; at the same time, dynamic and accurate regulation can keep the inverter in an optimal state, not only improving the power generation efficiency of the photovoltaic power generation system, but also reducing equipment loss and prolonging the service life of the inverter and the entire system, providing comprehensive technical support for the long-term safe and efficient operation of the photovoltaic power generation system.

[0178] For example, Figure 2As shown, the embodiment of the present application also provides a regulating device 20 of an inverter of a photovoltaic power generation system, comprising:

[0179] an acquisition module 21, configured to acquire operation data of an inverter of a photovoltaic power generation system;

[0180] a processing module 22, configured to pre-process the operation data to obtain operation parameters, determine an operation state of the inverter according to the operation parameters, determine a regulating instruction of the inverter according to the operation state, and regulate the inverter according to the regulating instruction.

[0181] Optionally, the pre-processing of the operation data to obtain operation parameters comprises:

[0182] according to XN =( XY - XI ) / ( XA - XI )to determine operation parameters.

[0183] wherein, XN is the operation parameter, XY is the operation data, XI is a minimum value of a data frame in a set time period of the operation data, XA is a maximum value of a data frame in a set time period of the operation data.

[0184] Optionally, the determination of the operation state of the inverter according to the operation parameters comprises:

[0185] determining a first probability of normal operation, a second probability of overload operation, a third probability of overheating operation, a fourth probability of aging state and a fifth probability of fault state of the inverter according to the operation parameters.

[0186] determining the operation state of the inverter according to the first probability, the second probability, the third probability, the fourth probability and the fifth probability.

[0187] Optionally, the determination of the first probability of normal operation of the inverter according to the operation parameters comprises:

[0188] determining the first probability according to .

[0189] wherein, P 1 is the first probability, K 1 is a first sensitivity coefficient, XN i is the operation parameter, i=1, 2, 3, …, 11, w i is a weight coefficient of the operation parameter, XM iis a normal reference value of the operating parameter, A is a first score threshold.

[0190] Optionally, the second probability of the inverter operating overload is determined according to the operating parameter, comprising:

[0191] the second probability is determined according to

[0192] wherein, P 2 is the second probability, K 2 is a second sensitivity coefficient, w 4 is a weight coefficient of the alternating current, XN 4 is an operating parameter of the alternating current, XG 4 is an overload reference value of the alternating current, w 1 is a weight coefficient of the direct current voltage, XN 1 is an operating parameter of the direct current voltage, XG 1 is an overload reference value of the direct current voltage, w 2 is a weight coefficient of the direct current, XN 2 is an operating parameter of the direct current, XG 2 is an overload reference value of the direct current, B is a second score threshold.

[0193] Optionally, the third probability of the inverter operating overheating is determined according to the operating parameter, comprising:

[0194] the third probability is determined according to

[0195] wherein, P 3 is the third probability, K 3 is a third sensitivity coefficient, w 9 is a weight coefficient of the insulated gate bipolar transistor temperature, XN 9 is an operating parameter of the insulated gate bipolar transistor temperature, XR 9 is an overheating reference value of the insulated gate bipolar transistor temperature, w 8 is a weight coefficient of the fan rotating speed, XN 8 is an operating parameter of the fan rotating speed, XR 8 is an overheating reference value of the fan rotating speed, C is a third score threshold.

[0196] Optionally, the fourth probability of the inverter aging state is determined according to the operating parameter, comprising:

[0197] the fourth probability is determined according to

[0198] wherein, P 4 is the fourth probability, K ​​​4 is a fourth sensitivity coefficient, w 10 is a weight coefficient of the capacitive impedance, XN 10 is an operating parameter of the capacitive impedance, XL 10 is an aging reference value of the capacitive impedance, w 9 is a weight coefficient of the insulated gate bipolar transistor temperature, XN 9 is an operating parameter of the insulated gate bipolar transistor temperature, XR 9 is an aging reference value of the insulated gate bipolar transistor temperature, D is a fourth score threshold.

[0199] Optionally, according to the operating parameter, a fifth probability of the inverter fault state is determined, comprising:

[0200] the fifth probability is determined according to

[0201] wherein, P 5 is the fifth probability, K 5 is a fifth sensitivity coefficient, w i is a weight coefficient of the operating parameter, XN i is an operating parameter, XZ i is a fault reference value of the operating parameter, L is an abnormal superposition coefficient, P 2 is the second probability, P 3 is the third probability, E is a fifth score threshold.

[0202] Optionally, according to the first probability, the second probability, the third probability, the fourth probability and the fifth probability, a running state of the inverter is determined, comprising:

[0203] if P 5≧ P 6, it is determined that the running state of the inverter is a fault state;

[0204] wherein, P 5 is the fifth probability, P 6 is a fault determination threshold;

[0205] if P 5< P 6, and P 3≧ P 7, it is determined that the running state of the inverter is an overheating state;

[0206] wherein, P 3 is the third probability, P ​7 is an overheating determination threshold value;

[0207] If P 5 P 6, P 3 P 7, and P 2 P 8, it is determined that the operation state of the inverter is an overload state.

[0208] wherein, P 2 is a second probability, P 8 is an overload determination threshold value;

[0209] If P 5 P 6, P 3 P 7, P 2 P 8, and P 4 P 9, it is determined that the operation state of the inverter is an aging state.

[0210] wherein, P 4 is a fourth probability, P 9 is an aging determination threshold value;

[0211] If P 5 P 6, P 3 P 7, P 2 P 8, P 4 P 9, and P 1 P 10 , it is determined that the operation state of the inverter is a normal state.

[0212] wherein, P 1 is a first probability, P 10 is a normal determination threshold value;

[0213] If P 5 P 6, P 3 P 7, P 2 P 8, P 4 P 9, and P 1 P 10 , it is determined that the operation state of the inverter is an abnormal state.

[0214] It should be noted that the apparatus corresponds to the method described above, and all implementation manners in the method embodiments are applicable to this embodiment, and the same technical effects can also be achieved.

[0215] Embodiments of the present application also provide a computing device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, so that the one or more processors implement the method described above. All implementation manners in the method embodiments described above are applicable to this embodiment, and the same technical effects can also be achieved.

[0216] Embodiments of the present application also provide a computing device readable storage medium, storing instructions, when the instructions are run on the computing device, so that the computing device executes the method described above. All implementation manners in the method embodiments described above are applicable to this embodiment, and the same technical effects can also be achieved.

[0217] Those skilled in the art can understand that the units and algorithm steps of the examples described in combination with the embodiments disclosed in the present application can be realized by electronic hardware or a combination of software and electronic hardware of the computing device. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0218] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0219] In the embodiments provided by the present application, it should be understood that the disclosed apparatus and method can be implemented by other ways. For example, the apparatus embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0220] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. may be located in one place, or may be distributed on multiple network units. Part or all of the units may be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0221] In addition, each functional unit in various embodiments of the application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0222] If the functions are realized in the form of software functional units and sold or used as independent products, they can be stored in a storage medium readable by a computing device. Based on this understanding, the technical solutions of the application or the part of the technical solutions that essentially contribute to the prior art can be embodied in the form of software products. The computing device software product is stored in a storage medium and includes a plurality of instructions for causing a computing device (which can be a personal computing device, a server, or a network device, etc.) to execute all or part of the steps of the method described in various embodiments of the application. The aforementioned storage medium includes various storage media that can store program codes, such as U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc.

[0223] In addition, it should be noted that in the device and method of the application, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombination should be considered as equivalent solutions of the application. And the steps of executing the above series of processes can naturally be executed in time sequence according to the order of description, but it is not necessary to be executed in time sequence, and some steps can be executed in parallel or independently of each other. It can be understood by those skilled in the art that all or any steps or components of the method and device of the application can be realized in any computing device (including processor, storage medium, etc.) or network of computing devices in hardware, firmware, software or their combination, which can be realized by those skilled in the art by using basic programming skills after reading the description of the application.

[0224] Therefore, the object of the present application can also be achieved by running a program or a set of programs on any computing device. The computing device can be a commonly known general purpose device. Therefore, the object of the present application can also be achieved by merely providing a program product containing program code for implementing the method or device. That is, such a program product also constitutes the present application, and a storage medium storing such a program product also constitutes the present application. Obviously, the storage medium can be any commonly known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present application, obviously, the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions of the present application. Furthermore, the steps of performing the above series of processes can naturally be executed in time sequence according to the order of description, but do not necessarily have to be executed in time sequence. Some steps can be executed in parallel or independently of each other.

[0225] The above is the preferred embodiment of the present application. It should be pointed out that for those skilled in the art, several improvements and refinements can be made without departing from the principles of the present application, and these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A method of regulating an inverter of a photovoltaic power generation system, characterized by, The method comprises: acquiring operation data of an inverter of a photovoltaic power generation system; preprocessing the operation data to obtain operation parameters; determining an operation state of the inverter according to the operation parameters; determining a control instruction of the inverter according to the operation state; controlling the inverter according to the control instruction; wherein preprocessing the operation data to obtain operation parameters comprises: According to XN = ( XY - XI ) / ( XA - XI ), determine the operating parameters; wherein XN is an operating parameter, XY is an operating data, XI is a minimum value of a data frame within a set time period of the operating data, XA is a maximum value of a data frame within a set time period of the operating data; wherein determining the operation state of the inverter according to the operation parameters comprises: determining a first probability of normal operation, a second probability of overload operation, a third probability of overheating operation, a fourth probability of an aging state, and a fifth probability of a fault state of the inverter according to the operation parameters; determining the operation state of the inverter according to the first probability, the second probability, the third probability, the fourth probability, and the fifth probability; wherein determining the operation state of the inverter according to the first probability, the second probability, the third probability, the fourth probability, and the fifth probability comprises: If P 5 P 6, determine that the operating state of the inverter is a fault state; wherein, P 5 is a fifth probability, P 6 is a failure determination threshold; If P 5 P 6, and P 3 ≥ P 7, determine that the operating state of the inverter is an overheat state. wherein, P 3 is a third probability, P 7 is a superheat determination threshold value; If P 5 P 6, P 3 P 7, and P 2 P 8, determine that the operating state of the inverter is an overload state. wherein, P 2 is a second probability, P 8 is an overload decision threshold; If P 5 P 6, P 3 P 7, P 2 P 8, and P 4 ≥ P 9, the operating state of the inverter is determined to be an aging state. wherein, P 4 is a fourth probability, P 9 is an aging determination threshold value; If P 5 P 6, P 3 P 7, P 2 P 8, P 4 P 9, and P 1 P 10 , determine that the operating state of the inverter is a normal state. wherein, P 1 is a first probability, P 10 is a normal decision threshold; If P 5 P 6, P 3 P 7, P 2 P 8, P 4 P 9, and P 1 P 10 determines that the operating state of the inverter is an abnormal state. wherein the operation data comprises DC side data, AC side data, environmental data, device state data, and a capacitor health parameter; the DC side data comprises DC voltage and DC current; the AC side data comprises AC voltage, AC current, and harmonic distortion rate; the environmental data comprises temperature, humidity, and light intensity; the device state data comprises fan speed and insulated gate bipolar transistor temperature; the capacitor health parameter comprises capacitor impedance.

2. The method of claim 1, wherein the method further comprises: determining the first probability of normal operation of the inverter according to the operation parameters comprises: According to , a first probability is determined; wherein, P 1 is a first probability, K 1 is a first sensitivity coefficient, XN i is an operating parameter, i = 1, 2, 3,..., 11, w i is a weight coefficient of the operating parameter, XM i is a normal reference value of the operating parameter, A is a first score threshold.

3. The method of claim 1, wherein the method further comprises: determining the second probability of overload operation of the inverter according to the operation parameters comprises: According to , a second probability is determined; wherein, P 2 is a second probability, K 2 is a second sensitivity coefficient, w 4 is a weight coefficient for the alternating current, XN 4 is an operating parameter for the alternating current, XG 4 is an overload reference value for the alternating current, w 1 is a weight coefficient for the direct voltage, XN 1 is an operating parameter for the direct voltage, XG 1 is an overload reference value for the direct voltage, w 2 is a weight coefficient for the direct current, XN 2 is an operating parameter for the direct current, XG 2 is an overload reference value for the direct current, B is a second score threshold.

4. The method of claim 1, wherein the method further comprises: determining the third probability of overheating operation of the inverter according to the operation parameters comprises: According to , a third probability is determined; wherein, P 3 is a third probability, K 3 is a third sensitivity coefficient, w 9 is a weight coefficient of the insulated gate bipolar transistor temperature, XN 9 is an operating parameter of the insulated gate bipolar transistor temperature, XR 9 is an overheat reference value of the insulated gate bipolar transistor temperature, w 8 is a weight coefficient of the fan rotation speed, XN 8 is an operating parameter of the fan rotation speed, XR 8 is an overheat reference value of the fan rotation speed, C is a third score threshold value.

5. The method of claim 1, wherein the method further comprises: determining the fourth probability of an aging state of the inverter according to the operation parameters comprises: According to , a fourth probability is determined; wherein, P 4 is a fourth probability, K 4 is a fourth sensitivity coefficient, w 10 is a weight coefficient of the capacitance impedance, XN 10 is an operating parameter of the capacitance impedance, XL 10 is an aging reference value of the capacitance impedance, w 9 is a weight coefficient of the insulated gate bipolar transistor temperature, XN 9 is an operating parameter of the insulated gate bipolar transistor temperature, XR 9 is an aging reference value of the insulated gate bipolar transistor temperature, D is a fourth score threshold.

6. The method of claim 1, wherein the method further comprises: determining the fifth probability of a fault state of the inverter according to the operation parameters comprises: According to , a fifth probability is determined; wherein P 5 is a fifth probability, K 5 is a fifth sensitivity coefficient, w i is a weight coefficient of an operating parameter, XN i is an operating parameter, XZ i is a failure reference value of an operating parameter, L is an anomaly superposition coefficient, P 2 is a second probability, P 3 is a third probability, E is a fifth score threshold.

7. A control device of an inverter of a photovoltaic power generation system, characterized by comprising: The method comprises: an acquisition module configured to acquire operation data of an inverter of a photovoltaic power generation system; a processing module configured to preprocess the operation data to obtain operation parameters; determining an operation state of the inverter according to the operation parameters; determining a control instruction of the inverter according to the operation state; controlling the inverter according to the control instruction; wherein preprocessing the operation data to obtain operation parameters comprises: According to XN = ( XY - XI ) / ( XA - XI ), determine the operating parameters; wherein XN is an operating parameter, XY is an operating data, XI is a minimum value of a data frame within a set time period of the operating data, XA is a maximum value of a data frame within a set time period of the operating data; wherein determining the operation state of the inverter according to the operation parameters comprises: determining a first probability of normal operation, a second probability of overload operation, a third probability of overheating operation, a fourth probability of an aging state, and a fifth probability of a fault state of the inverter according to the operation parameters; determining the operation state of the inverter according to the first probability, the second probability, the third probability, the fourth probability, and the fifth probability; wherein determining the operation state of the inverter according to the first probability, the second probability, the third probability, the fourth probability, and the fifth probability comprises: If P 5 P 6, determine that the operating state of the inverter is a fault state; wherein, P 5 is a fifth probability, P 6 is a failure determination threshold; If P 5 P 6, and P 3 P 7, determining that the operating state of the inverter is an overheat state. wherein, P 3 is a third probability, P 7 is a superheat determination threshold value; If P 5 P 6, P 3 P 7, and P 2 P 8, determine that the operating state of the inverter is an overload state. wherein, P 2 is a second probability, P 8 is an overload decision threshold; If P 5 P 6, P 3 P 7, P 2 P 8, and P 4 ≥ P 9, the operating state of the inverter is determined to be an aging state. wherein, P 4 is a fourth probability, P 9 is an aging determination threshold value; If P 5 P 6, P 3 P 7, P 2 P 8, P 4 P 9, and P 1 P 10 determines that the operating state of the inverter is a normal state. wherein, P 1 is a first probability, P 10 is a normal decision threshold; If P 5 P 6, P 3 P 7, P 2 P 8, P 4 P 9, and P 1 P 10 determining that the operating state of the inverter is an abnormal state; The operation data comprises DC side data, AC side data, environment data, device state data and capacitor health parameters; The DC side data comprises DC voltage and DC current; The AC side data comprises AC voltage, AC current and harmonic distortion rate; The environment data comprises temperature, humidity and illumination intensity; The device state data comprises fan rotating speed and insulated gate bipolar transistor temperature; The capacitor health parameters comprise capacitor impedance.

Images