Photovoltaic string fault diagnosis method, device and equipment based on multi-feature fusion

Abstract

This invention relates to the field of photovoltaic power generation technology, and discloses a method, apparatus, and equipment for photovoltaic string fault diagnosis based on multi-feature fusion. The method includes: calculating theoretical operating current data, theoretical operating voltage data, and theoretical power data of the photovoltaic string based on environmental irradiance data and module surface temperature data; calculating current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration based on measured current data, measured voltage data, measured power data, and theoretical operating current data, theoretical operating voltage data, and theoretical power data of the photovoltaic string; fusing the current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration to obtain a comprehensive score; and performing fault diagnosis on the photovoltaic string based on the comprehensive score to obtain a diagnosis result.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic power generation technology, and specifically to a method, apparatus and equipment for diagnosing photovoltaic string faults based on multi-feature fusion. Background Technology

[0002] As the core unit of power generation, photovoltaic (PV) strings are exposed to harsh outdoor environments for extended periods, making them susceptible to faults such as hot spots, partial shading, poor cable connections, module aging and degradation, and inverter malfunctions. These faults not only cause a 5%-15% loss in the annual power generation of the power plant, but can also lead to DC arcing, module burnout, and even fires in severe cases. Currently, most PV string fault diagnosis technologies rely on manual inspections and single-dimensional current and voltage threshold judgments. Manual inspections are inefficient and time-consuming, requiring 7-15 days for a single inspection of a large power plant, and posing blind spots and safety hazards in complex terrain. Single-dimensional threshold judgments do not consider the dynamic effects of environmental irradiance and temperature, resulting in frequent false alarms and missed alarms, and can only locate faults at the combiner box or inverter level, failing to accurately identify the fault. Therefore, the detection methods in these technologies are no longer suitable for the large-scale, unattended development trend of PV power plants and cannot meet the core requirements of intelligent operation and maintenance for real-time fault detection and precise handling. Summary of the Invention

[0003] This invention provides a photovoltaic string fault diagnosis method, device, and equipment based on multi-feature fusion to solve the problems of low efficiency and long cycle of manual inspection in related technologies, the failure of single-dimensional threshold judgment to consider the dynamic influence of environmental irradiance and temperature, frequent false alarms and missed alarms, and the inability to accurately identify faults by only locating the combiner box or inverter level.

[0004] In a first aspect, the present invention provides a photovoltaic string fault diagnosis method based on multi-feature fusion. The method includes: acquiring measured current data, measured voltage data, measured power data, ambient irradiance data, and temperature data of the photovoltaic string surface; calculating theoretical operating current data, theoretical operating voltage data, and theoretical power data of the photovoltaic string based on the ambient irradiance data and temperature data; calculating multiple fault diagnosis features based on the measured current data, measured voltage data, measured power data, and theoretical operating current data, theoretical operating voltage data, and theoretical power data, including current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration; fusing the current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration to obtain a comprehensive score; and performing fault diagnosis on the photovoltaic string based on the comprehensive score to obtain a diagnosis result.

[0005] This invention provides a photovoltaic string fault diagnosis method based on multi-feature fusion. It simultaneously collects measured electrical data of the photovoltaic string, ambient irradiance, and module surface temperature data. Based on environmental conditions, it calculates theoretical operating current, voltage, and power baseline data, breaking the limitations of fixed thresholds and effectively offsetting the interference of environmental factors on power generation parameters, fundamentally reducing the probability of false alarms and missed alarms in fault diagnosis. Simultaneously, it constructs multi-dimensional fault features including current deviation, voltage deviation, power deviation, current fluctuation amplitude, and abnormal duration. Through multi-feature fusion scoring, it achieves comprehensive fault judgment, comprehensively adapting to various fault identifications such as hot spots, partial shading, poor cable contact, module aging and degradation, and inverter anomalies, overcoming the limitations of single-parameter diagnosis. The entire intelligent diagnosis process is based on automated data calculation, eliminating the need for extensive manual on-site inspections. This avoids blind spots and safety risks during inspections, accurately locates faulty strings, reduces power generation losses, and proactively prevents DC arcing, module burnout, and even fire accidents, fully adapting to the development trend of intelligent photovoltaic operation and maintenance.

[0006] In one optional implementation, the step of calculating multiple fault diagnosis features based on measured current data, measured voltage data, measured power data, and theoretical operating current data, theoretical operating voltage data, and theoretical power data includes: calculating current deviation data between measured current data and theoretical operating current data, voltage deviation data between measured voltage data and theoretical operating voltage data, and power deviation data between measured power data and theoretical power data; calculating the current fluctuation amplitude based on the measured current data; and determining the abnormal duration based on the current deviation data, voltage deviation data, power deviation data, and a preset threshold range.

[0007] The method provided in this optional implementation, by calculating the deviation data corresponding to current, voltage, and power respectively, characterizes the degree of deviation between the actual operating conditions of the photovoltaic string and the theoretical normal operating conditions from multiple dimensions, overcoming the shortcomings of the strong one-sidedness and inaccurate identification of single parameter judgment; by calculating the current fluctuation amplitude based solely on measured current data, it can specifically capture the disordered current fluctuation characteristics caused by poor cable contact, arc disturbance, etc., making up for the shortcoming that steady-state parameters cannot identify transient anomalies; at the same time, by determining the duration of anomalies based on the deviations of current, voltage, and power combined with preset threshold ranges, it can effectively distinguish between short-term environmental interference and real continuous faults, filter invalid abnormal signals, and avoid false alarms and missed alarms. By decomposing and separately obtaining the three types of differentiated fault characteristics, a comprehensive characterization of steady-state deviation, transient fluctuations, and fault duration is achieved, making the fault diagnosis basis more comprehensive and the judgment logic more rigorous.

[0008] In one optional implementation, the step of fusing current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration to obtain a comprehensive score includes: fusing current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration based on a pre-built weighted fusion model to obtain a comprehensive score. The weighted fusion model is as follows:

[0009] in, This indicates the overall score; , , , , Represents the weight parameters. Indicates current deviation. Indicates voltage deviation. Indicates power deviation. Indicates the amplitude of current fluctuation. Indicates the duration of the anomaly.

[0010] The method provided in this optional implementation adopts a pre-built weighted fusion model to obtain a comprehensive score by weighted summation of five types of features: current deviation, voltage deviation, power deviation, current fluctuation amplitude, and abnormal duration. Compared with the one-sidedness of single-dimensional threshold judgment in related technologies, it can comprehensively integrate multi-dimensional fault information such as steady-state parameter deviation, transient current fluctuation, and fault duration, accurately adapting to the characteristic patterns of different faults such as hot spots, partial shading, and poor cable contact, thereby reducing the probability of false alarms and missed alarms from the root. At the same time, the adjustable weight parameters can flexibly adapt to the diagnostic needs of different power plant operating conditions and fault types, improving the versatility and pertinence of the method; quantifying multi-dimensional features into a unified comprehensive score facilitates automated classification and precise handling of fault severity, further improving the accuracy of photovoltaic string fault diagnosis.

[0011] In one optional implementation, the step of calculating the theoretical operating current data, theoretical operating voltage data, and theoretical power data of the photovoltaic string based on ambient irradiance data and temperature data includes: calculating battery temperature data based on ambient irradiance data and temperature data; calculating theoretical operating current data based on battery temperature data and ambient irradiance data; calculating theoretical operating voltage data based on battery temperature data and ambient irradiance data; and calculating theoretical power data based on theoretical operating voltage data and theoretical operating current data.

[0012] The method provided in this optional implementation first calculates the actual operating temperature of the battery based on ambient irradiance and module surface temperature, accurately reflecting the true internal heating state of the battery cells and avoiding the reference deviation caused by directly using the module surface temperature. Then, it calculates the theoretical operating current and voltage based on the battery temperature and irradiance respectively, fully matching the physical characteristics of current and voltage changes with irradiance and temperature, eliminating the interference of dynamic environmental changes on the theoretical reference. Finally, it derives the theoretical power from the theoretical current and voltage, ensuring the consistency and accuracy of the theoretical power reference. This approach makes the theoretical reference more closely match the actual normal power generation state of the string, providing a precise comparative basis for subsequent fault feature extraction, fundamentally reducing diagnostic errors caused by environmental factors, and significantly improving the accuracy and environmental adaptability of fault diagnosis.

[0013] In one optional implementation, the step of diagnosing faults in the photovoltaic string based on a comprehensive score to obtain a diagnosis result includes: acquiring pre-constructed fault level assessment information; and diagnosing faults in the photovoltaic string based on the comprehensive score and the fault level assessment information to obtain a diagnosis result.

[0014] The method provided in this optional implementation introduces pre-built fault level assessment information and matches the comprehensive score obtained by fusing multiple features with standardized level rules. This upgrades fault diagnosis from "presence / absence judgment" to "quantitative grading," effectively overcoming the shortcomings of related technologies, such as vague fault grading, reliance on human experience, and weak targeted handling. The pre-fixed level assessment information unifies the criteria for judging the severity of faults, avoiding biases caused by subjective human judgment, and making the diagnostic results more objective and standardized. Combined with the quantitative characteristics of the comprehensive score, it can accurately distinguish between different levels of faults, such as minor, moderate, and severe, providing clear guidance on handling priorities for operation and maintenance personnel. This avoids excessive intervention in minor faults while enabling timely response to severe faults, preventing safety accidents and power generation losses.

[0015] Secondly, the present invention provides a photovoltaic string fault diagnosis device based on multi-feature fusion. The device includes: an acquisition module for acquiring measured current data, measured voltage data, measured power data, ambient irradiance data, and temperature data of the photovoltaic string surface; a first calculation module for calculating theoretical operating current data, theoretical operating voltage data, and theoretical power data of the photovoltaic string based on the ambient irradiance data and temperature data; a second calculation module for calculating multiple fault diagnosis features based on the measured current data, measured voltage data, measured power data, and theoretical operating current data, theoretical operating voltage data, and theoretical power data, including current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration; a fusion module for fusing the current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration to obtain a comprehensive score; and a diagnosis module for performing fault diagnosis on the photovoltaic string based on the comprehensive score to obtain a diagnosis result.

[0016] In one optional implementation, the second calculation module includes: a first calculation submodule, used to calculate current deviation data between measured current data and theoretical operating current data, voltage deviation data between measured voltage data and theoretical operating voltage data, and power deviation data between measured power data and theoretical power data; a second calculation submodule, used to calculate the current fluctuation amplitude based on the measured current data; and a determination submodule, used to determine the duration of the abnormality based on the current deviation data, voltage deviation data, power deviation data, and a preset threshold range.

[0017] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the photovoltaic string fault diagnosis method based on multi-feature fusion described in the first aspect or any corresponding embodiment thereof.

[0018] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the photovoltaic string fault diagnosis method based on multi-feature fusion described in the first aspect or any corresponding embodiment thereof.

[0019] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the photovoltaic string fault diagnosis method based on multi-feature fusion described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0020] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first process of a photovoltaic string fault diagnosis method based on multi-feature fusion according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the second process of the photovoltaic string fault diagnosis method based on multi-feature fusion according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the third process of the photovoltaic string fault diagnosis method based on multi-feature fusion according to an embodiment of the present invention; Figure 5 This is a structural block diagram of a photovoltaic string fault diagnosis device based on multi-feature fusion according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, 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.

[0023] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0024] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0025] As an optional application scenario of this invention, the specific application environment architecture or specific hardware architecture on which the photovoltaic string fault diagnosis method based on multi-feature fusion depends is described here. For example... Figure 1 As shown, the architecture system may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0026] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.

[0027] In related technologies, photovoltaic (PV) string fault diagnosis mostly relies on manual inspection and single-dimensional current and voltage threshold judgment. Manual inspection is inefficient and time-consuming, requiring 7-15 days for a single inspection of a large power plant. Furthermore, blind spots and safety hazards exist in power plants with complex terrain. Single-dimensional threshold judgment does not consider the dynamic effects of environmental irradiance and temperature, leading to frequent false alarms and missed alarms. Moreover, it can only locate faults at the combiner box or inverter level, failing to accurately identify the fault. Therefore, the detection methods in these technologies are no longer suitable for the large-scale, unattended development trend of PV power plants and cannot meet the core requirements of intelligent operation and maintenance for real-time fault detection and precise handling.

[0028] In view of this, this application provides a photovoltaic string fault diagnosis method based on multi-feature fusion, which can be applied to a single server to realize fault diagnosis of photovoltaic strings. The method provided in this application simultaneously collects measured electrical data of photovoltaic strings, ambient irradiance, and component surface temperature data. Based on environmental conditions, it calculates theoretical operating current, voltage, and power benchmark data, breaking the limitations of fixed thresholds and effectively offsetting the interference of environmental factors on power generation parameters, fundamentally reducing the probability of false alarms and missed alarms in fault diagnosis. At the same time, it constructs multi-dimensional fault features such as current deviation, voltage deviation, power deviation, current fluctuation amplitude, and abnormal duration. Through multi-feature fusion scoring, it achieves comprehensive fault judgment, which can fully adapt to the identification of various faults such as hot spots, partial shading, poor cable contact, component aging and degradation, and inverter abnormalities, breaking through the limitations of single-parameter diagnosis. The entire process is based on automated data calculation to complete intelligent diagnosis, without relying on a large amount of manual on-site inspection. This avoids blind spots and safety risks in inspections, accurately locates faulty strings, reduces power generation loss, and prevents DC arcing, component burnout, and even fire accidents in advance, fully adapting to the development trend of intelligent operation and maintenance of photovoltaics.

[0029] According to an embodiment of the present invention, a method for diagnosing photovoltaic string faults based on multi-feature fusion is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] This embodiment provides a photovoltaic string fault diagnosis method based on multi-feature fusion, which can be used in the aforementioned server. Figure 2 This is a flowchart of a photovoltaic string fault diagnosis method based on multi-feature fusion according to an embodiment of the present invention, as shown below. Figure 2 As shown, the process includes the following steps: Step S201: Obtain the measured current data, measured voltage data, measured power data, ambient irradiance data, and temperature data of the photovoltaic string surface.

[0031] For example, the photovoltaic string is a photovoltaic module that requires fault diagnosis. In this embodiment, the measured current and voltage data of the string are synchronously collected by the string inverter, the intelligent acquisition module of the combiner box, or the string current / voltage sensor. The measured power data can be calculated in real time by current and voltage, or directly obtained from the inverter or monitoring system. The sampling frequency is fixed at 5~15 minutes / time. The ambient irradiance data is collected by a total radiation meter installed on the same plane of the module in an unshaded area; the module surface temperature data is collected by a temperature sensor attached to the module backsheet or glass surface, and is sampled synchronously with the electrical data at the same time point to ensure time series alignment.

[0032] Step S202: Calculate the theoretical operating current, theoretical operating voltage, and theoretical power data of the photovoltaic string based on the environmental irradiance data and temperature data.

[0033] For example, in the embodiments of this application, the actual operating temperature of the battery is first obtained by taking the ambient irradiance data and the component surface temperature data as input, and then the theoretical operating current and voltage are calculated by combining the component electrical parameters. Finally, the theoretical power data is obtained by multiplying the two.

[0034] Step S203: Based on the measured current data, measured voltage data, measured power data, and theoretical operating current data, theoretical operating voltage data, and theoretical power data, multiple fault diagnosis features are calculated. These multiple fault diagnosis features include current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration.

[0035] For example, in this embodiment of the application, the relative deviations between the measured and theoretical current, voltage, and power are calculated to obtain current deviation, voltage deviation, and power deviation data; the fluctuation degree of the measured current is statistically analyzed according to a fixed time window to obtain the current fluctuation amplitude; and the abnormal duration is accumulated according to whether the three types of deviations continuously exceed the preset threshold.

[0036] Step S204: The current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration are fused to obtain a comprehensive score.

[0037] For example, in the embodiments of this application, the current deviation, voltage deviation, power deviation, current fluctuation amplitude and abnormal duration are weighted according to preset weight parameters and then summed to obtain a quantitative comprehensive score.

[0038] Step S205: Perform fault diagnosis on the photovoltaic string based on the comprehensive score to obtain the diagnosis result.

[0039] For example, in this embodiment of the application, the correspondence between a predefined comprehensive score range and a fault level is first obtained, then the calculated comprehensive score is compared with each level range, and finally a diagnostic result including fault status, severity level and handling suggestions is output.

[0040] The photovoltaic string fault diagnosis method based on multi-feature fusion provided in this embodiment simultaneously collects measured electrical data of the photovoltaic string, ambient irradiance, and module surface temperature data. Based on environmental conditions, it calculates theoretical operating current, voltage, and power baseline data, breaking the limitations of fixed thresholds and effectively offsetting the interference of environmental factors on power generation parameters, fundamentally reducing the probability of false alarms and missed alarms in fault diagnosis. Simultaneously, it constructs multi-dimensional fault features including current deviation, voltage deviation, power deviation, current fluctuation amplitude, and abnormal duration. Through multi-feature fusion scoring, it achieves comprehensive fault judgment, comprehensively adapting to various fault identifications such as hot spots, partial shading, poor cable contact, module aging and degradation, and inverter anomalies, overcoming the limitations of single-parameter diagnosis. The entire intelligent diagnosis is completed based on automated data calculation, eliminating the need for extensive manual on-site inspections. This avoids blind spots and safety risks during inspections, accurately locates faulty strings, reduces power generation losses, and proactively prevents DC arcing, module burnout, and even fire accidents, fully adapting to the development trend of intelligent photovoltaic operation and maintenance.

[0041] This embodiment provides a photovoltaic string fault diagnosis method based on multi-feature fusion, which can be used in the aforementioned server. Figure 3 This is a flowchart of a photovoltaic string fault diagnosis method based on multi-feature fusion according to an embodiment of the present invention, as shown below. Figure 3 As shown, the process includes the following steps: Step S301: Obtain the measured current data, measured voltage data, measured power data, ambient irradiance data, and module surface temperature data of the photovoltaic string. For details, please refer to [link to relevant documentation]. Figure 2 Step S201 of the illustrated embodiment will not be described again here.

[0042] Step S302: Obtain the measured current data, measured voltage data, measured power data, ambient irradiance data, and temperature data of the photovoltaic string surface.

[0043] Specifically, step S302 includes: Step S3021: Calculate battery temperature data based on ambient irradiance data and temperature data.

[0044] For example, in this embodiment of the application, the battery temperature data can be calculated using the following formula:

[0045] in, Indicates battery temperature. Indicates the temperature of the component surface. Indicates ambient irradiance; This indicates the temperature rise coefficient at the component's nominal operating temperature (NOCT), typically 20-30℃. Indicates the standard test condition irradiance (1000 W / m²). 2 ).

[0046] Step S3022: Calculate the theoretical operating current data based on battery temperature data and ambient irradiance data.

[0047] For example, the theoretical operating current data may include, but is not limited to, the theoretical maximum power point operating current. In this embodiment, the theoretical maximum power point operating current data can be calculated using the following formula:

[0048] in, This represents the theoretical maximum power point operating current. Indicates the nominal maximum power point current. Indicates the temperature coefficient of current. This indicates the standard test temperature (25℃). The meanings of the other variables will not be elaborated here.

[0049] Step S3023: Calculate the theoretical operating voltage data based on battery temperature data and ambient irradiance data.

[0050] For example, the theoretical operating voltage data may include, but is not limited to, the theoretical maximum power point operating voltage. In this embodiment, the voltage is mainly affected by temperature and exhibits a logarithmic variation with irradiance. The theoretical maximum power point operating voltage can be calculated using the following formula:

[0051] in, This represents the theoretical maximum power point operating voltage. This indicates the nominal maximum power point voltage. This represents the voltage temperature coefficient (negative value). This represents the irradiance correction constant (0.05~0.1).

[0052] Step S3024: Calculate the theoretical power data based on the theoretical operating voltage data and the theoretical operating current data.

[0053] For example, the theoretical power data can be calculated based on conventional power calculation formulas, and will not be described in detail in the embodiments of this application.

[0054] Step S303: Based on measured current data, measured voltage data, measured power data, and theoretical operating current data, theoretical operating voltage data, and theoretical power data, multiple fault diagnosis features are calculated. These features include current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration. For details, please refer to [link to relevant documentation]. Figure 2Step S203 of the illustrated embodiment will not be described again here.

[0055] Step S304: The current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration are fused to obtain a comprehensive score.

[0056] Specifically, step S304 includes: Step S3041: Based on the pre-built weighted fusion model, the current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration are fused to obtain a comprehensive score. The weighted fusion model is as follows:

[0057] in, This indicates the overall score; , , , , Represents the weight parameters. Indicates current deviation. Indicates voltage deviation. Indicates power deviation. Indicates the amplitude of current fluctuation. Indicates the duration of the anomaly.

[0058] Exemplary, in the embodiments of this application, , , , , The preset weights are determined by training with historical data based on the sensitivity of each feature to different fault types.

[0059] Step S305: Perform fault diagnosis on the photovoltaic strings based on the comprehensive score to obtain the diagnosis results. For details, please refer to [link to relevant documentation]. Figure 2 Step S205 of the illustrated embodiment will not be described again here.

[0060] This embodiment provides a photovoltaic string fault diagnosis method based on multi-feature fusion, which can be used in the aforementioned server. Figure 4 This is a flowchart of a photovoltaic string fault diagnosis method based on multi-feature fusion according to an embodiment of the present invention, as shown below. Figure 4 As shown, the process includes the following steps: Step S401: Obtain the measured current data, measured voltage data, measured power data, ambient irradiance data, and module surface temperature data of the photovoltaic string. For details, please refer to [link to relevant documentation]. Figure 3 Step S301 of the illustrated embodiment will not be described again here.

[0061] Step S402: Based on environmental irradiance data and temperature data, the theoretical operating current data, theoretical operating voltage data, and theoretical power data of the photovoltaic string are calculated. For details, please refer to [link to relevant documentation]. Figure 3 Step S302 of the illustrated embodiment will not be described again here.

[0062] Step S403: Based on the measured current data, measured voltage data, measured power data, and theoretical operating current data, theoretical operating voltage data, and theoretical power data, multiple fault diagnosis features are calculated. These multiple fault diagnosis features include current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration.

[0063] Specifically, step S403 includes: Step S4031: Calculate the current deviation data between the measured current data and the theoretical operating current data, the voltage deviation data between the measured voltage data and the theoretical operating voltage data, and the power deviation data between the measured power data and the theoretical power data.

[0064] For example, in this embodiment of the application, the relative deviation between the actual current and the reference current is calculated based on the theoretical operating current to obtain the current relative deviation characteristic, which reflects the degree to which the actual current deviates from the normal operating condition; the relative deviation between the actual voltage and the reference voltage is calculated based on the theoretical operating voltage to obtain the voltage deviation characteristic, which reflects the degree to which the actual voltage deviates from the normal operating condition; the actual power is obtained by multiplying the actual current and the actual voltage, and the reference power is obtained by multiplying the theoretical operating current and the theoretical operating voltage, and then the relative deviation between the two is calculated to obtain the power relative deviation characteristic, so as to comprehensively reflect the degree of deviation of the string power generation efficiency.

[0065] Step S4032: Calculate the current fluctuation amplitude based on the measured current data.

[0066] For example, in the embodiments of this application, the current fluctuation amplitude is the standard deviation or range of the current sequence collected within a unit time window (such as 1 hour), which is used to characterize the current instability caused by electric arc, poor contact, etc.

[0067] Step S4033: Determine the duration of the abnormality based on the current deviation data, voltage deviation data, power deviation data, and a preset threshold range.

[0068] For example, in the embodiments of this application, when the relative deviation of the current Voltage offset Or relative power deviation When any one of the features continuously exceeds the preset threshold range, the cumulative timing begins; the data sampling period is used as the minimum step size for accumulation until the corresponding feature recovers to within the threshold range and the timing stops; if multiple features are abnormal at the same time, the duration of the feature that first triggered the abnormality is taken, or the maximum value of the duration of each feature is taken as the input of the fusion feature.

[0069] Step S404 involves fusing the current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration to obtain a comprehensive score. For details, please refer to [link to relevant documentation]. Figure 3 Step S304 of the illustrated embodiment will not be described again here.

[0070] Step S405 is the step of performing fault diagnosis on the photovoltaic string based on the comprehensive score to obtain the diagnosis result.

[0071] Specifically, step S405 includes: Step S4051: Obtain pre-built fault level assessment information.

[0072] For example, in this embodiment of the application, the fault level assessment information can be as shown in Table 1 below: Table 1. Fault Level Assessment Information Table

[0073] The embodiments of this application do not limit the specific content of the fault assessment level information, which can be determined by those skilled in the art according to actual needs.

[0074] Step S4052: Based on the comprehensive score and fault level assessment information, perform fault diagnosis on the photovoltaic string to obtain the diagnosis result.

[0075] For example, this is achieved through preset fault level rules: first, a correspondence between comprehensive scoring intervals and fault levels and handling suggestions is pre-constructed based on operation and maintenance needs; then, the calculated comprehensive score is matched with each level interval one by one to determine the fault level of the current photovoltaic string; finally, a diagnostic result including fault status, severity, and corresponding handling guidelines is output. In this embodiment, the fault levels are divided into three levels: I, II, and III. The corresponding handling suggestions are as follows: Level I generates an observation work order and includes it in the key inspection list for the next day; Level II pushes an alarm to the operation and maintenance personnel and suggests arranging a shutdown for cleaning or tightening inspection; Level III issues an emergency alarm and suggests immediately disconnecting the string DC switch remotely or on-site and arranging emergency repairs.

[0076] This embodiment also provides a photovoltaic string fault diagnosis device based on multi-feature fusion. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0077] This embodiment provides a photovoltaic string fault diagnosis device based on multi-feature fusion, such as... Figure 5 As shown, it includes: The acquisition module 501 is used to acquire the measured current data, measured voltage data, measured power data, ambient irradiance data, and temperature data of the photovoltaic string surface. The first calculation module 502 is used to calculate the theoretical operating current data, theoretical operating voltage data, and theoretical power data of the photovoltaic string based on the environmental irradiance data and temperature data. The second calculation module 503 is used to calculate multiple fault diagnosis features based on measured current data, measured voltage data, measured power data, and theoretical operating current data, theoretical operating voltage data, and theoretical power data. The multiple fault diagnosis features include current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration. The fusion module 504 is used to fuse current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration to obtain a comprehensive score. The diagnostic module 505 is used to perform fault diagnosis on the photovoltaic string based on the comprehensive score and obtain the diagnostic results.

[0078] In some alternative implementations, the second computing module 503 includes: The first calculation submodule is used to calculate the current deviation data between measured current data and theoretical operating current data, the voltage deviation data between measured voltage data and theoretical operating voltage data, and the power deviation data between measured power data and theoretical power data. The second calculation submodule is used to calculate the current fluctuation amplitude based on the measured current data. The determination submodule is used to determine the duration of the anomaly based on current deviation data, voltage deviation data, power deviation data, and a preset threshold range.

[0079] In some alternative implementations, the fusion module 504 includes: The fusion submodule is used to fuse current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration based on a pre-built weighted fusion model to obtain a comprehensive score. The weighted fusion model is as follows:

[0080] in, This indicates the overall score; , , , , Represents the weight parameters. Indicates current deviation. Indicates voltage deviation. Indicates power deviation. Indicates the amplitude of current fluctuation. Indicates the duration of the anomaly.

[0081] In some alternative implementations, the first computing module 502 includes: The third calculation submodule is used to calculate battery temperature data based on environmental irradiance data and temperature data. The fourth calculation submodule is used to calculate the theoretical operating current data based on battery temperature data and ambient irradiance data; The fifth calculation submodule is used to calculate the theoretical operating voltage data based on battery temperature data and ambient irradiance data; The sixth calculation submodule is used to calculate the theoretical power data based on the theoretical operating voltage data and the theoretical operating current data.

[0082] In some alternative implementations, the diagnostic module 505 includes: The acquisition submodule is used to acquire pre-built fault level assessment information; The diagnostic submodule is used to perform fault diagnosis on photovoltaic strings based on comprehensive scoring and fault level assessment information, and obtain diagnostic results.

[0083] The photovoltaic string fault diagnosis device based on multi-feature fusion provided in this embodiment of the invention can execute the photovoltaic string fault diagnosis method based on multi-feature fusion provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0084] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0085] The following is a detailed reference. Figure 6This diagram illustrates a suitable structural design for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 601, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 602 or a program loaded from memory 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of the electronic device. The processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0086] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0087] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a memory 608, or installed from a ROM 602. When the computer program is executed by the processor 601, it performs the functions defined in the photovoltaic string fault diagnosis method based on multi-feature fusion according to embodiments of the present invention.

[0088] Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0089] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the photovoltaic string fault diagnosis method based on multi-feature fusion shown in the above embodiments is implemented.

[0090] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0091] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A photovoltaic string fault diagnosis method based on multi-feature fusion, characterized in that, The method includes: Acquire measured current data, measured voltage data, measured power data, ambient irradiance data, and temperature data of the photovoltaic string surface; The theoretical operating current, theoretical operating voltage, and theoretical power data of the photovoltaic string are calculated based on the environmental irradiance data and temperature data. Based on the measured current data, measured voltage data, measured power data, and theoretical operating current data, theoretical operating voltage data, and theoretical power data, multiple fault diagnosis features are calculated. These multiple fault diagnosis features include current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration. The current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration are fused to obtain a comprehensive score; Based on the comprehensive score, fault diagnosis is performed on the photovoltaic string to obtain the diagnosis results.

2. The method according to claim 1, characterized in that, The steps for calculating multiple fault diagnosis features based on the measured current data, measured voltage data, measured power data, and theoretical operating current data, theoretical operating voltage data, and theoretical power data include: Calculate the current deviation data between measured current data and theoretical operating current data, the voltage deviation data between measured voltage data and theoretical operating voltage data, and the power deviation data between measured power data and theoretical power data; The current fluctuation amplitude is calculated based on the measured current data. The duration of the anomaly is determined based on the current deviation data, the voltage deviation data, the power deviation data, and a preset threshold range.

3. The method according to claim 1 or 2, characterized in that, The step of fusing the current deviation data, the voltage deviation data, the power deviation data, the current fluctuation amplitude, and the abnormal duration to obtain a comprehensive score includes: The current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration are fused based on a pre-built weighted fusion model to obtain a comprehensive score. The weighted fusion model is as follows: in, This indicates the overall score; , , , , Represents the weight parameters. Indicates current deviation. Indicates voltage deviation. Indicates power deviation. Indicates the amplitude of current fluctuation. Indicates the duration of the anomaly.

4. The method according to claim 1 or 2, characterized in that, The steps for calculating the theoretical operating current, theoretical operating voltage, and theoretical power data of the photovoltaic string based on the environmental irradiance data and temperature data include: Battery temperature data is calculated based on the environmental irradiance data and temperature data. The theoretical operating current data is calculated based on the battery temperature data and the ambient irradiance data. The theoretical operating voltage data is calculated based on the battery temperature data and the ambient irradiance data. The theoretical power data is calculated based on the theoretical operating voltage data and the theoretical operating current data.

5. The method according to claim 1, characterized in that, The steps for fault diagnosis of photovoltaic strings based on the comprehensive score to obtain the diagnosis results include: Obtain pre-built fault level assessment information; Based on the comprehensive score and fault level assessment information, fault diagnosis is performed on the photovoltaic string to obtain the diagnosis results.

6. A photovoltaic string fault diagnosis device based on multi-feature fusion, characterized in that, The device includes: The acquisition module is used to acquire measured current data, measured voltage data, measured power data, ambient irradiance data, and temperature data of the photovoltaic string surface. The first calculation module is used to calculate the theoretical operating current data, theoretical operating voltage data, and theoretical power data of the photovoltaic string based on the environmental irradiance data and temperature data. The second calculation module is used to calculate multiple fault diagnosis features based on the measured current data, measured voltage data, measured power data, theoretical operating current data, theoretical operating voltage data, and theoretical power data. The multiple fault diagnosis features include current deviation data, voltage deviation data, power deviation data, current fluctuation amplitude, and abnormal duration. The fusion module is used to fuse the current deviation data, the voltage deviation data, the power deviation data, the current fluctuation amplitude, and the abnormal duration to obtain a comprehensive score; The diagnostic module is used to perform fault diagnosis on the photovoltaic string based on the comprehensive score and obtain the diagnostic results.

7. The apparatus according to claim 6, characterized in that, The second calculation module includes: The first calculation submodule is used to calculate the current deviation data between measured current data and theoretical operating current data, the voltage deviation data between measured voltage data and theoretical operating voltage data, and the power deviation data between measured power data and theoretical power data. The second calculation submodule is used to calculate the current fluctuation amplitude based on the measured current data. The determination submodule is used to determine the duration of the abnormality based on the current deviation data, the voltage deviation data, the power deviation data, and a preset threshold range.

8. An electronic device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the photovoltaic string fault diagnosis method based on multi-feature fusion as described in any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the photovoltaic string fault diagnosis method based on multi-feature fusion as described in any one of claims 1 to 5.

10. A computer program product, characterized in that, It includes computer instructions for causing a computer to execute the photovoltaic string fault diagnosis method based on multi-feature fusion as described in any one of claims 1 to 5.

Images