Cloud platform-based photovoltaic power station fault intelligent diagnosis method

Abstract

The application discloses a photovoltaic power station fault intelligent diagnosis method based on a cloud platform and relates to the technical field of photovoltaic power stations.The application solves the problems of lacking a unified "fault-feature curve" mapping system and the big difference in the judgment of the same data by different operation and maintenance personnel.Through comparison between the power generation variation feature curve and the preset fault curve, the application quantifies the overlapping proportion, covers multiple fault scenes, avoids missed judgment, and unifies the judgment standard, thereby replacing subjective experience; the application associates the three types of core parameters of current, voltage and power, extracts the standard trend section, calculates the cross proportion average of the curve interval and the suspected signal, locks the signal with the highest correlation, excludes non-component interference, and improves the diagnosis reliability; the process outputs clear and landable results, does not need to understand complex algorithms, and reduces the operation and maintenance threshold; the application relies on cloud platform data for rapid diagnosis, shortens the response time, and is suitable for efficient operation and maintenance of large-scale power stations.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of photovoltaic power stations, in particular to a photovoltaic power station fault intelligent diagnosis method based on a cloud platform. BACKGROUND

[0002] With the large-scale development of the global photovoltaic industry, photovoltaic power stations have the characteristics of expanded installed capacity, dispersed distribution, and a sharp increase in the number of components, which puts higher requirements on the real-time, accuracy, and operation and maintenance efficiency of fault diagnosis.

[0003] However, the current fault diagnosis technology of photovoltaic power stations still has significant limitations and is difficult to adapt to the fine management needs of large-scale power stations: there are obvious shortcomings in the suspected fault signal generation and screening link: first, the fault determination standard relies on manual experience, lacks a unified "fault-feature curve" mapping system, different operation and maintenance personnel have large differences in judging the same data, and it is difficult to cover component hidden cracks, PID effects, and other hidden fault scenarios, which is prone to fault omission; second, when multiple suspected signals coexist, there is a lack of quantitative correlation evaluation methods, and only relying on subjective selection of " seemingly relevant" signals often misjudges non-component fault signals such as power grid voltage fluctuations and temporary sensor drift as core faults, leading to deviation of subsequent operation and maintenance direction.

[0004] In addition, the traditional diagnosis takes "manual on-site inspection" as the core, which requires operation and maintenance personnel to check components, inverters and other equipment one by one, which not only has a long response time (days) and high operation and maintenance cost in large-scale power stations, but also is difficult to quickly locate hidden faults in dispersed power stations, and cannot meet the needs of "real-time monitoring and efficient diagnosis" under cloud platform management.

[0005] In summary, the deficiencies of the prior art in abnormality recognition accuracy, fault scenario coverage, signal screening reliability, and operation and maintenance efficiency have become a key bottleneck restricting the stable operation and cost control of photovoltaic power stations, and an intelligent diagnosis method that combines the data advantages of the cloud platform and realizes "environmental interference stripping-standardized signal generation-multi-parameter quantitative screening" is urgently needed. SUMMARY

[0006] In view of the deficiencies of the prior art, the present application provides a photovoltaic power station fault intelligent diagnosis method based on a cloud platform, which solves the problem of lack of a unified "fault-feature curve" mapping system, large differences in judging the same data by different operation and maintenance personnel, and difficulty in covering component hidden cracks, PID effects, and other hidden fault scenarios, which is prone to fault omission.

[0007] To achieve the above purpose, the present application realizes the following technical scheme: a photovoltaic power station fault intelligent diagnosis method based on a cloud platform, comprising the following steps:

[0008] Step 1: Confirm the current solar irradiance and its associated power generation characteristics. Based on historical data, determine if there are any abnormal power generation issues with the photovoltaic modules at this moment. The specific method is as follows:

[0009] The light intensity associated with the current moment is denoted as GQ, and the power generation characteristic associated with the current moment is denoted as FD. The single-point intensity DQ is confirmed by using: FD ÷ GQ = DQ.

[0010] Using the current time as the base time, a set of tracing cycles is confirmed. The tracing cycle is a preset cycle. The light intensity that is the same as the light intensity GQ within the tracing cycle is recorded as the undetermined light intensity, and the power generation data associated with the undetermined light intensity is recorded as the undetermined power generation value. Based on the confirmed undetermined light intensity and undetermined power generation value, the following formula is used: undetermined power generation value ÷ undetermined light intensity = undetermined feature, and several undetermined features are confirmed.

[0011] From the identified undetermined features, the standard interval is determined: from the minimum value Dd of the undetermined features. min Begin by identifying the variable range, whose range value is Y1, which is a preset value, and then determining its maximum value Dd from several undetermined features. max , making the variable range from [Dd min Dd min +Y1]to [Dd max -Y1, Dd max Perform range changes and record the total number of undetermined features included in each different variable range. From the recorded total number of undetermined features, select the maximum value and record the variable range associated with the maximum value as the standard range.

[0012] If there is only one standard range, it is called a standard interval;

[0013] If there are multiple standard ranges, select the standard range whose initial value is the minimum value state and record the selected standard range as the standard interval.

[0014] Identify whether the current single-point intensity DQ is below the standard range. If not, proceed with the subsequent monitoring process normally. If so, directly generate an abnormal power generation signal for display.

[0015] Step 2: For cases of abnormal power generation in photovoltaic modules, confirm the monitoring period and record the power generation associated with the monitoring period to confirm the change characteristics between adjacent time points. Then, generate corresponding characteristic curves based on the change characteristics and compare the generated characteristic curves with preset fault curves for verification. According to the verification process, confirm suspected signals. The specific method is as follows:

[0016] For the confirmed power generation abnormal signal, a group of monitoring periods is confirmed, the power generation of the photovoltaic module in the monitoring period is confirmed, and the confirmed power generation data at different times is sorted according to the chronological relationship, and the power generation change characteristics between adjacent time points are confirmed, the change characteristics are the difference between the power generation at the next time point and the power generation at the previous time point in the adjacent time point, and the feature curve of the power generation change characteristics in the monitoring period is generated according to the chronological relationship;

[0017] The confirmed feature curve is compared and verified with the preset fault curve: the feature curve and the fault curve are placed in the same two-dimensional coordinate system, and the feature curve is controlled to move forward and backward, in the moving process, the overlapping part of the feature curve and the preset fault curve is identified, and the related proportion of the overlapping part segment on the feature curve is recorded, the related proportion = the total length of the overlapping part segment ÷ the total length of the feature curve, from the moving process, the maximum value associated with several related proportions is confirmed, the confirmed maximum value is recorded as the calibrated feature of the current feature curve, if the calibrated feature ≥ Y2, the fault signal associated with the preset fault curve is recorded as the suspected signal, Y2 is a preset value, if the calibrated feature < Y2, no calibration is performed;

[0018] The feature curve and the preset fault curve are compared in turn, according to the comparison process, the suspected signal associated with the feature curve is confirmed, and the confirmed suspected signal is displayed;

[0019] Step three, identify the number of suspected signals, if there is only one group, directly display, if there are multiple groups, extract the change characteristics of other data characteristics in the monitoring period, confirm the suspected signal with the highest correlation degree of the photovoltaic module from the change characteristics, and display;

[0020] Preferably, in step three, the specific way of confirming the suspected signal with the highest correlation degree is:

[0021] The current photovoltaic module associated current, voltage and power data in the monitoring period are recorded, and the current change curve, voltage change curve and power change curve associated with the corresponding monitoring period are confirmed according to the chronological relationship;

[0022] Confirming the standard trend segment existing in the interior from the confirmed different change curves: from the change curve, confirming the change characteristics between adjacent time points, and confirming the interval value between the change characteristics of adjacent time periods, and confirming the characteristics to which the corresponding change curve belongs, confirming the characteristic threshold value preset by the belonging characteristics, if the interval value is less than or equal to the characteristic threshold value, the curve segment associated with the adjacent time periods is marked as the same type of characteristic segment, and the same type of characteristic segment associated with the adjacent time periods in the change curve is confirmed in turn, and the longest length value of the same type of characteristic segment is selected as the standard trend segment of the change curve, and the standard trend segment is recorded, the change characteristics associated with the standard trend segment are confirmed, and the maximum value and the minimum value are confirmed as the curve interval associated with the current change curve, if the interval value is greater than the characteristic threshold value, no marking is performed;

[0023] And the curve intervals associated with the corresponding change curves of other belonging characteristics are confirmed in turn;

[0024] The curve intervals confirmed by the belonging characteristics are compared and verified with the numerical interval preset by the suspected signal, the intersection range is confirmed, and the range proportion value of the intersection range in the numerical interval is recorded, and the three range proportion values associated with the three curve intervals are confirmed, and the three range proportion values are processed by mean value, and the suspected characteristics associated with the current suspected signal are confirmed;

[0025] Based on different suspected characteristics associated with different suspected signals, the maximum value is selected, the suspected signal associated with the maximum value is recorded as the suspected signal with the highest correlation degree, and is displayed.

[0026] The application provides a photovoltaic power station fault intelligent diagnosis method based on a cloud platform. Compared with the prior art, the application has the following beneficial effects:

[0027] The application calculates single-point intensity by "power generation / light intensity", removes light fluctuation interference, constructs a standard interval combined with historical similar light intensity data, accurately judges real power generation abnormalities of components, and reduces environmental factor misjudgment;

[0028] The power generation change characteristic curve is compared with the preset fault curve, the overlap proportion is quantified, multiple fault scenarios are covered, misjudgment is avoided, the determination standard is unified, and subjective experience is replaced;

[0029] The three types of core parameters of current, voltage and power are associated, the standard trend segment is extracted, the intersection proportion mean value of the curve interval and the suspected signal is calculated, the signal with the highest correlation degree is locked, non-component interference is excluded, and the diagnosis reliability is improved;

[0030] The process outputs clear and implementable results, does not require complex algorithm understanding, reduces the operation and maintenance threshold, relies on cloud platform data for rapid diagnosis, shortens the response time, and adapts to large-scale power station efficient operation and maintenance. Attached Figure Description

[0031] Figure 1 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0032] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] Please see Figure 1 This application provides a cloud-based intelligent fault diagnosis method for photovoltaic power plants, including the following steps:

[0034] Step 1: Confirm the current light intensity and associated power generation characteristics, and based on historical data characteristics, confirm whether there are any abnormal power generation situations in the photovoltaic modules at the current moment. Specifically, there is a corresponding power generation under the corresponding light intensity. This type of data can be directly collected, and the power generation data analysis process is carried out based on the collected data. From the historical processing process, identify whether there are any numerical anomalies in the power generation data, and display the signals based on the specific identification results for designated personnel to view.

[0035] The specific method for determining whether there is an abnormal power generation in the photovoltaic modules at the current moment is as follows:

[0036] The light intensity associated with the current moment is denoted as GQ, and the power generation characteristic associated with the current moment is denoted as FD. The single-point intensity DQ is confirmed by using: FD ÷ GQ = DQ.

[0037] Using the current time as the base time, a set of traceability cycles is confirmed. The traceability cycle is a preset cycle, which is determined in advance by the operator based on experience. The current time is set as 0 time, and the traceability cycle is the past 1 hour. Then the corresponding traceability cycle is 23h-0h. The light intensity with the same light intensity GQ within the traceability cycle is recorded as the undetermined light intensity, and the power generation data associated with the undetermined light intensity is recorded as the undetermined power generation value. Based on the confirmed undetermined light intensity and undetermined power generation value, the following formula is used: undetermined power generation value ÷ undetermined light intensity = undetermined feature, and several undetermined features are confirmed.

[0038] From the identified undetermined features, the standard interval is determined: from the minimum value Dd of the undetermined features. minFirst, confirm the variable range, the variable range of which has a range value Y1, Y1 is a preset value, the specific value of which is determined by the operator according to experience, and the maximum value Dd is determined from several to-be-determined characteristics max , make the variable range change in the range of [Dd min , Dd min +Y1] to [Dd max -Y1, Dd max ], and record the total number of to-be-determined characteristics included in each different variable range. From the recorded total number of to-be-determined characteristics, select the maximum value, and record the variable range associated with the maximum value as the standard range. If there is only one set of standard range, it is recorded as the standard interval. If there are multiple sets of standard range, select the standard range with the initial value of the minimum value state as the standard interval. For example: different standard ranges have different initial values. There are corresponding minimum values between multiple initial values. The corresponding standard range associated with the minimum value is the corresponding standard interval.

[0039] Identify whether the single-point intensity DQ confirmed at the current time is lower than the standard interval. If not, it means that the photovoltaic module is generating electricity normally at the current time, and the subsequent monitoring process can be normally executed. If yes, it means that the photovoltaic module is generating electricity abnormally at the current time, and an electricity generation abnormality signal is directly generated for display.

[0040] Step two: For the case where the photovoltaic module has electricity generation abnormality, confirm the monitoring period, record the change characteristics between adjacent time points associated with the electricity generation amount, and then generate the corresponding characteristic curve based on the change characteristics. Compare and verify the generated characteristic curve with the preset fault curve. According to the verification process, confirm the suspected signal. Specifically, when the specific abnormal reason is not clear, the closest change stage is evaluated according to the change characteristics between the curve values in the corresponding comparison process, so as to confirm the suspected signal.

[0041] Among them, the specific way to confirm the suspected signal is:

[0042] For the confirmed power generation abnormal signal, a group of monitoring periods is confirmed, the power generation of the photovoltaic module in the monitoring period is confirmed, and the confirmed power generation data at different times is sorted according to the time sequence, the power generation change characteristics between adjacent time points are confirmed, the change characteristics are the difference between the power generation at the next time point and the power generation at the previous time point, and the feature curve of the power generation change characteristics in the monitoring period is generated according to the time sequence. The horizontal coordinate axis of the curve is the time line, the vertical coordinate axis is the change characteristic, the time line is the time period, the time period in the front is sorted in front, the time period in the back is sorted in back, and so on. According to the change relationship between time and power generation change characteristics, the corresponding feature curve can be generated.

[0043] The confirmed feature curve is compared and verified with the preset fault curve: the feature curve and the fault curve are placed in the same two-dimensional coordinate system, and the feature curve is controlled to move forward and backward. In the moving process, the overlapping part of the feature curve and the preset fault curve is identified, and the related proportion of the overlapping part segment in the feature curve is recorded. The related proportion = the total length of the overlapping part segment ÷ the total length of the feature curve. From the moving process, the maximum value associated with several related proportions is confirmed. The confirmed maximum value is recorded as the calibrated feature of the current feature curve. If the calibrated feature is greater than or equal to Y2, the fault signal associated with the preset fault curve is recorded as a suspected signal. Otherwise, no calibration is performed. Y2 is a preset value, which is determined by the operator in advance according to experience. The preset fault curve is generated based on the change characteristic curve under different fault states, which is determined by the operator in advance according to specific operation experience.

[0044] The feature curve and the preset fault curve are compared in turn. According to the comparison process, the suspected signal associated with the feature curve is confirmed, and the confirmed suspected signal is displayed.

[0045] Specifically, in the actual comparison process, the feature curve and the preset fault curve are compared one by one. The corresponding feature curve and fault curve are placed in the same two-dimensional coordinate system, and the corresponding feature curve is moved to confirm the overlapping part between the feature curve and the fault curve. According to the specific proportion of the confirmed overlapping part, the specific confirmation of the calibrated feature is performed, and the suspected signal is confirmed according to the specific process. Based on the corresponding confirmation process, the specific accuracy of the corresponding suspected signal confirmation process can be effectively guaranteed, and the overall judgment effect of the suspected signal can be effectively improved.

[0046] Step three, identify the number of suspected signals. If there is only one group, it is directly displayed. If there are multiple groups, extract the change characteristics of other data characteristics in the monitoring period, confirm the suspected signal with the highest correlation degree of the photovoltaic module from the change characteristics, and display it.

[0047] The specific way of confirming the suspected signal with the highest degree of association is:

[0048] The current current, voltage and power data associated with the photovoltaic module within the monitoring period are recorded, and the current change curve, voltage change curve and power change curve associated with the monitoring period are confirmed according to the chronological relationship;

[0049] From the confirmed different change curves, the standard trend segment existing in the internal is confirmed: from the change curve, the change characteristics between adjacent time points are confirmed, the confirmation method of the power generation change characteristics is consistent, which is also according to the difference between the specific data of the next time point and the data of the previous time point, and the difference value of the change characteristics between adjacent time periods is confirmed, and the difference value is the interval value between the adjacent time periods, and the characteristic (current, voltage or power data) of the corresponding change curve is confirmed, the characteristic threshold of the corresponding characteristic is confirmed, and the characteristic thresholds of different characteristics are different. If the interval value is less than or equal to the characteristic threshold, the curve segment associated with the adjacent time period is marked as the same characteristic segment, otherwise, no marking is performed. The same characteristic segments associated with adjacent time periods in the change curve are confirmed in turn, and the longest one is selected as the standard trend segment of the change curve, and the standard trend segment is recorded. The change characteristics associated with the standard trend segment are confirmed, and the maximum value and the minimum value are confirmed as the curve interval associated with the current change curve;

[0050] And the curve intervals associated with the change curves of other characteristics are confirmed in turn;

[0051] The curve intervals confirmed by the characteristics are compared and verified with the numerical interval preset by the suspected signal, the intersection range is confirmed, and the range proportion value of the intersection range in the numerical interval is recorded. Then the three range proportion values associated with the three curve intervals are confirmed, and the three range proportion values are processed by mean value, and the suspected characteristics associated with the current suspected signal are confirmed;

[0052] Based on different suspected characteristics associated with different suspected signals, the maximum value is selected, the suspected signal associated with the maximum value is recorded as the suspected signal with the highest degree of association, and is displayed for external personnel to view. The suspected signal confirmed at the current time is the specific signal with the highest degree of association, which is most likely to be the specific fault condition;

[0053] Specifically, the specific value change process of the corresponding curve is confirmed by confirming the value change characteristics associated with the corresponding signal one by one, then the specific process with the most stable trend is selected from the corresponding change process, and the specific display of the signal is performed from the selected process, so as to achieve the optimal signal confirmation processing effect and ensure the specific accuracy in the evaluation process.

[0054] Part of the data in the above formula is dimensionless numerical calculation, and the contents not described in detail in the specification all belong to the prior art known to those skilled in the art.

[0055] The above examples are only used to illustrate the technical method of the present application and are not limited. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical method of the present application.

Claims

1. A cloud-based intelligent fault diagnosis method for photovoltaic power plants, characterized in that, Includes the following steps: Step 1: Confirm the current solar irradiance and its associated power generation characteristics. Based on historical data, determine if there are any abnormal power generation issues with the photovoltaic modules at this moment. The specific method is as follows: The light intensity associated with the current moment is denoted as GQ, and the power generation characteristic associated with the current moment is denoted as FD. The single-point intensity DQ is confirmed by using: FD ÷ GQ = DQ. Using the current time as the base time, a set of tracing cycles is confirmed. The tracing cycle is a preset cycle. The light intensity that is the same as the light intensity GQ within the tracing cycle is recorded as the undetermined light intensity, and the power generation data associated with the undetermined light intensity is recorded as the undetermined power generation value. Based on the confirmed undetermined light intensity and undetermined power generation value, the following formula is used: undetermined power generation value ÷ undetermined light intensity = undetermined feature, and several undetermined features are confirmed. From the identified undetermined features, a standard interval is determined: from the minimum value of the undetermined features... Begin by identifying the variable range, whose range value is Y1, which is a preset value, and then determining its maximum value from several undetermined features. , making the variable range from [ , +Y1] towards [ -Y1, The range is varied, and the total number of undetermined features included in each different variable range is recorded. From the recorded total number of undetermined features, the maximum value is selected, and the variable range associated with the maximum value is recorded as the standard range. If there is only one set of standard ranges, it is recorded as the standard interval. Step 2: In the case of abnormal power generation of photovoltaic modules, confirm the monitoring period and record the power generation associated with the monitoring period to confirm the change characteristics between adjacent time points. Then, generate the corresponding characteristic curve based on the change characteristics and compare and verify the generated characteristic curve with the preset fault curve. According to the verification process, confirm the suspected signal. Step 3: Identify the number of suspected signals. If only one group exists, display it directly. If multiple groups exist, extract the change characteristics of other data features within the monitoring period, identify the suspected signal with the highest correlation to the photovoltaic module from the change characteristics, and display it.

2. The intelligent fault diagnosis method for photovoltaic power plants based on a cloud platform according to claim 1, characterized in that, If there are multiple standard ranges, select the standard range whose initial value is the minimum value state and record the selected standard range as the standard interval. Identify whether the current single-point intensity DQ is below the standard range. If not, proceed with the subsequent monitoring process normally. If so, directly generate an abnormal power generation signal for display.

3. The intelligent fault diagnosis method for photovoltaic power plants based on a cloud platform according to claim 1, characterized in that, In step two, the specific method for confirming the suspected signal is as follows: For the confirmed abnormal power generation signals, a set of monitoring cycles is identified, and the power generation generated by the photovoltaic modules within the monitoring cycle is confirmed. According to the time sequence, the power generation data at different times is sorted, and the power generation change characteristics between adjacent times are confirmed simultaneously. The change characteristics are the difference between the power generation at the later time and the power generation at the previous time within adjacent times. Based on the time sequence, a characteristic curve belonging to the power generation change characteristics within this monitoring cycle is generated. The confirmed characteristic curve is compared and verified with the preset fault curve: the characteristic curve and the fault curve are placed in the same two-dimensional coordinate system, and the characteristic curve is controlled to move back and forth. During the movement process, the overlapping part of the characteristic curve and the preset fault curve is identified, and the relevant proportion of the overlapping part is located on the characteristic curve. The relevant proportion = the bus length of the overlapping part ÷ the bus length of the characteristic curve. From the movement process, the maximum value associated with several relevant proportions is confirmed. The confirmed maximum value is recorded as the calibration feature of the current characteristic curve. If the calibration feature ≥ Y2, the fault signal associated with the preset fault curve is recorded as a suspected signal, and Y2 is the preset value. The characteristic curve is compared with the preset fault curve in turn. Based on the comparison process, the suspected signals associated with the characteristic curve are identified and the identified suspected signals are displayed.

4. The intelligent fault diagnosis method for photovoltaic power plants based on a cloud platform according to claim 3, characterized in that, If the calibration feature is less than Y2, no calibration is performed.

5. The intelligent fault diagnosis method for photovoltaic power plants based on a cloud platform according to claim 1, characterized in that, In step three, the specific method for confirming the suspected signal with the highest correlation is as follows: Record the current, voltage, and power data associated with the photovoltaic modules during the monitoring period, and confirm the current change curve, voltage change curve, and power change curve associated with the corresponding monitoring period according to the time sequence. Identify the standard trend segments within the identified different change curves, identify the change characteristics associated with the standard trend segments, and identify the maximum and minimum values ​​from them as the curve interval associated with the current change curve. And then confirm the curve intervals associated with the change curves of other corresponding features in turn; The curve interval confirmed by the feature is compared and verified with the preset numerical interval of the suspected signal to confirm the intersection range and record the proportion of the intersection range in the numerical interval. Then, the proportion of the three ranges associated with the three curve intervals is confirmed, and the three confirmed proportions of the three ranges are averaged to confirm the suspected feature associated with the current suspected signal. Based on the different suspected features associated with different suspected signals, the maximum value is selected, and the suspected signal associated with the maximum value is recorded as the suspected signal with the highest degree of association and displayed.

6. The intelligent fault diagnosis method for photovoltaic power plants based on a cloud platform according to claim 5, characterized in that, The process of confirming the standard trend segment includes: confirming the change characteristics between adjacent time points from within the change curve, and confirming the difference between the change characteristics of adjacent time periods. This difference is the interval value between the change characteristics of adjacent time periods. Confirming the characteristic to which the corresponding change curve belongs, and confirming the preset feature threshold of the characteristic to which it belongs. If the interval value is less than or equal to the feature threshold, the curve segments associated with adjacent time periods are marked as the same type of feature segments. The same type of feature segments associated with adjacent time periods within the change curve are confirmed in sequence, and the group of the same type of feature segments with the longest length value is selected as the standard trend segment of this change curve and recorded.

7. The intelligent fault diagnosis method for photovoltaic power plants based on a cloud platform according to claim 6, characterized in that, If the interval value is greater than the feature threshold, no labeling is performed.

Images