Intelligent operation and maintenance management system and method for photovoltaic power station

Abstract

The invention discloses an intelligent operation and maintenance management system and method for a photovoltaic power station, relates to the technical field of photovoltaic power station monitoring, and aims to solve the problem that it is difficult to judge that a fault is dominated by the environment and equipment itself in the prior art. The system comprises a data acquisition module, an environment and fault association database, an environment and fault association analysis module and a digital twin modeling module. The data acquisition module is used for acquiring equipment operation data and environment data in the photovoltaic power station; an environment and fault association rule base is arranged in the environment and fault association database, the environment and fault association database is further used for storing the equipment operation data and the environment data, and the environment and fault association rule base comprises mapping data between the environment of the photovoltaic power station and the fault type of the equipment; and the environment and fault association analysis module is used for calling data in the environment and fault association database. The method has the advantage of improving the management efficiency.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic power plant monitoring technology, and more specifically, to an intelligent operation and maintenance management system and method for photovoltaic power plants. Background Technology

[0002] As the global energy structure shifts towards cleaner energy, photovoltaic power generation has become an important part of the global energy system due to its advantages such as renewable resources and low carbon emissions. To maximize the use of solar resources and reduce land costs, a large number of photovoltaic power plants are being deployed in areas with abundant sunshine but harsh ecological environments, such as deserts.

[0003] However, wind and sand in desert areas can cause dust to clog the combiner box, dust to accumulate on the surface of the photovoltaic panel, extreme high temperatures can cause abnormal photovoltaic panel temperatures, and low sunshine duration and high humidity can lead to a decrease in power generation and inverter errors, etc. These environmental factors do not act in isolation, but together affect the state of the equipment.

[0004] However, in traditional operation and maintenance (O&M), it is difficult for O&M personnel to determine whether a fault is caused by environmental factors, the equipment itself, or a combination of both. For example, when power generation decreases, it is difficult to quickly distinguish whether it is due to dust accumulation or the degradation of the photovoltaic panels' performance, often delaying maintenance. Therefore, we propose an intelligent O&M management system and method for photovoltaic power plants. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent operation and maintenance management system and method for photovoltaic power plants, which aims to solve the problem that existing technologies have difficulty in determining whether a fault is caused by the environment or by the equipment itself.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an intelligent operation and maintenance management system for photovoltaic power plants, the system comprising a data acquisition module, an environment and fault correlation database, an environment and fault correlation analysis module, and a digital twin modeling module; The data acquisition module is used to acquire equipment operation data and environmental data within the photovoltaic power station; The environment and fault association database contains an environment and fault association rule base, and is also used to store the equipment operation data and environmental data. The environment and fault association rule base contains mapping data between the environment of the photovoltaic power station and the fault types of the equipment. The environment and fault correlation analysis module is used to retrieve data from the environment and fault correlation database and calculate the probability of fault causes of equipment in the photovoltaic power station. The digital twin modeling module is used to construct a 3D digital twin model of a photovoltaic power station and achieves visualization mapping through a built-in environmental impact layer and fault association layer.

[0007] Preferably, the data acquisition module includes an equipment operation data acquisition unit and an environmental data acquisition unit. The equipment operation data acquisition unit is used to acquire equipment operation data in the photovoltaic power station to determine the fault type of the equipment, including power generation reduction, inverter error, abnormal photovoltaic panel temperature, and dust blockage in the combiner box. The environmental data acquisition unit includes multiple environmental sensors for collecting environmental data of the photovoltaic power station.

[0008] Preferably, the equipment operating data includes photovoltaic panel power generation, inverter voltage, current, and combiner box temperature, and the environmental data includes wind and sand intensity, dust accumulation thickness, sunshine duration, ambient temperature, and ambient humidity.

[0009] Preferably, the mapping data between the environment and equipment failure types of photovoltaic power plants specifically includes: For the fault types of power generation decline: the associated environmental data are wind and sand intensity, dust accumulation thickness, and sunshine duration. Among them, the threshold for wind and sand intensity is >8m / s and lasts for >2h, with a weighting coefficient of 0.4; the threshold for dust accumulation thickness is >2mm, with a weighting coefficient of 0.5; and the threshold for sunshine duration is <4h / day, with a weighting coefficient of 0.1. The corresponding basic equipment fault probability is 0.2-0.5. For the fault types reported by the inverter: the associated environmental data are ambient humidity and ambient temperature. The threshold for ambient humidity is >90%RH and lasts for >72 hours, with a weighting coefficient of 0.6. The threshold for ambient temperature is >40℃ and lasts for >4 hours, with a weighting coefficient of 0.4. The corresponding basic equipment fault probability is 0.3-0.5. For the fault type of abnormal photovoltaic panel temperature, the associated environmental data are sunshine duration and ambient temperature. The sunshine duration threshold is >10h / day with a weighting coefficient of 0.3, and the ambient temperature threshold is >35℃ with a weighting coefficient of 0.7. The corresponding basic equipment fault probability is 0.25-0.4. For the dust blockage fault type of the junction box, the associated environmental data are wind and sand intensity and dust accumulation thickness. The wind and sand intensity threshold is >12m / s and lasts for >1h, with a weighting coefficient of 0.7. The dust accumulation thickness threshold is >3mm, with a weighting coefficient of 0.3. The corresponding basic equipment fault probability is 0.15-0.3.

[0010] Preferably, when the environment and fault correlation analysis module calculates the probability of fault causes for equipment in the photovoltaic power station, it uses the environmental data exceedance contribution method to calculate the probability of environmental impact, thereby determining the fault cause.

[0011] Preferably, the environment and fault correlation analysis module dynamically optimizes the weight coefficients in the environment and fault correlation rule base based on the actual fault causes reported on-site.

[0012] Preferably, the environmental sensors include multiple wind and sand intensity sensors, dust accumulation thickness sensors, sunshine duration sensors, ambient temperature sensors, and ambient humidity sensors.

[0013] Preferably, the environmental impact layer is used to overlay environmental data onto the 3D digital twin model in the form of a color gradient, and the fault association layer is used to connect the faulty equipment with the associated environmental sensors through lines of the same color, visually presenting the relationship between the fault and the environment.

[0014] This invention also provides a method for intelligent operation and maintenance management of photovoltaic power plants, the method comprising the following steps: S1. Construct a 3D digital twin model of the photovoltaic power station using the digital twin modeling module, and then acquire equipment operation data and environmental data within the photovoltaic power station through the data acquisition module. S2. Store equipment operation data and environmental data through an environment and fault association database, and store mapping data between the environment of the photovoltaic power station and the fault types of the equipment through an environment and fault association rule base. S3. Using the environmental data exceedance contribution method in the environmental and fault correlation analysis module, the probability of environmental impact is calculated based on the data in the environmental and fault correlation database to determine the cause of the fault. S4. Finally, the relationship between the fault and the environment is visualized through the digital twin modeling module.

[0015] Preferably, S4 above also includes scheduling on-site personnel of the photovoltaic power station based on the visualized relationship between faults and the environment, so as to realize the operation and maintenance management of the photovoltaic power station.

[0016] Compared with the prior art, the beneficial effects of the present invention are: 1. The data acquisition module in this invention comprehensively acquires equipment operation data and environmental data, providing complete data support for fault analysis. By using environmental data and mapping data stored in the environment and fault association database, the probability of environmental impact is determined, clearly identifying whether the fault is dominated by environmental factors, the equipment itself, or both. This solves the problem of difficulty in locating the cause of photovoltaic equipment faults in desert environments.

[0017] 2. The environment and fault correlation analysis module in this invention defines deviation values ​​based on actual fault causes. By correcting the weight coefficients under the corresponding fault type and performing normalization processing, it updates the environment and fault correlation rule library, reducing the deviation between the environmental impact probability calculation results and the actual situation. This ensures that the weight coefficients in the environment and fault correlation rule library always match the actual situation on site, avoiding fault analysis errors caused by fixed weights, and making fault cause determination more accurate. Attached Figure Description

[0018] Figure 1This is a schematic diagram of the system structure of the present invention; Figure 2 This is a schematic diagram illustrating the principle of the present invention; Figure 3 This is a schematic diagram of the method flow in this invention. Detailed Implementation

[0019] Example 1 This embodiment focuses on the operation and maintenance management of a photovoltaic power station located in a desert.

[0020] This embodiment provides an intelligent operation and maintenance management system for photovoltaic power plants. The system includes a data acquisition module, an environment and fault correlation database, an environment and fault correlation analysis module, and a digital twin modeling module.

[0021] In this embodiment, the data acquisition module includes a device operation data acquisition unit and an environmental data acquisition unit; The equipment operation data acquisition unit is used to acquire equipment operation data in the photovoltaic power station to determine the fault type of the equipment, including reduced power generation, inverter error, abnormal photovoltaic panel temperature, and dust blockage in the combiner box. Its equipment operation data includes photovoltaic panel power generation, inverter voltage, current, and combiner box temperature. The environmental data acquisition unit includes multiple environmental sensors, including multiple wind and sand intensity sensors, dust accumulation thickness sensors, sunshine duration sensors, ambient temperature sensors, and ambient humidity sensors, which are used to collect environmental data of the photovoltaic power station, including wind and sand intensity, dust accumulation thickness, sunshine duration, ambient temperature, and ambient humidity.

[0022] In this embodiment, the environment and fault association database is used to store the equipment operation data and environmental data in the photovoltaic power station acquired by the data acquisition module. In addition, it also stores the mapping data between the environment and the fault types of the photovoltaic power station through the environment and fault association rule base. Specifically, the mapping data between the environment and equipment failure types of photovoltaic power plants includes: For the fault types of power generation decline: the associated environmental data are wind and sand intensity, dust accumulation thickness, and sunshine duration. Among them, the threshold for wind and sand intensity is >8m / s and lasts for >2h, with a weighting coefficient of 0.4; the threshold for dust accumulation thickness is >2mm, with a weighting coefficient of 0.5; and the threshold for sunshine duration is <4h / day, with a weighting coefficient of 0.1. The corresponding basic equipment fault probability is 0.2-0.5. For the fault types reported by the inverter: the associated environmental data are ambient humidity and ambient temperature. The threshold for ambient humidity is >90%RH and lasts for >72 hours, with a weighting coefficient of 0.6. The threshold for ambient temperature is >40℃ and lasts for >4 hours, with a weighting coefficient of 0.4. The corresponding basic equipment fault probability is 0.3-0.5. For the fault type of abnormal photovoltaic panel temperature, the associated environmental data are sunshine duration and ambient temperature. The sunshine duration threshold is >10h / day with a weighting coefficient of 0.3, and the ambient temperature threshold is >35℃ with a weighting coefficient of 0.7. The corresponding basic equipment fault probability is 0.25-0.4. For the dust blockage fault type of the junction box, the associated environmental data are wind and sand intensity and dust accumulation thickness. The wind and sand intensity threshold is >12m / s and lasts for >1h, with a weighting coefficient of 0.7. The dust accumulation thickness threshold is >3mm, with a weighting coefficient of 0.3. The corresponding basic equipment fault probability is 0.15-0.3.

[0023] In this embodiment, the environment and fault correlation analysis module retrieves data from the environment and fault correlation database to calculate the probability of fault causes for equipment in the photovoltaic power station. This process uses the environmental data exceedance contribution method to calculate the probability of environmental impact, thereby determining the cause of the fault. In this embodiment, the specific method for determining the contribution of environmental data exceeding the standard is as follows: Based on the fault type, retrieve the corresponding threshold, weight coefficient, basic equipment fault probability, and environmental data acquired by the data acquisition module from the mapping data. Then calculate the contribution of exceeding the standard for individual environmental data: Define the collected environmental data as values (Environmental data associated with the fault type, such as real-time collected values ​​of wind and sand intensity and real-time collected values ​​of dust accumulation thickness), threshold is The duration threshold is (For example, for fault types involving decreased power generation lasting >2 hours), the real-time duration is... (The actual duration of environmental data associated with the fault type is obtained from environmental data collected by the environmental data acquisition unit), with a weighting coefficient of [missing value]. ; If the environmental data requires a specific duration (e.g., a sandstorm intensity threshold >8 m / s and a duration >2 hours for a fault type indicating reduced power generation), and , ,but ;in, The number of times the data value exceeds the limit. For duration exceeding the limit by a multiple, This is a correction factor (with a value range of 0.3-0.5); If the environmental data does not require a duration (such as dust thickness in a fault type indicating a decrease in power generation, where duration is not required), and ,but ,in, This is a correction factor (with a value range of 0.5-0.8); If the environmental data does not meet the above-mentioned conditions for exceeding the standard (e.g.) or ),but ; Then through the formula Calculate the total environmental impact probability, where, =1 to , (The number of environmental data associated with this fault type) Functions are used to limit The maximum value is 1; according to The calculation results determine the cause of the fault: like ( This represents the basic failure probability of the equipment. If the fault determination threshold (range 1-1.5) is set, the fault is determined to be caused primarily by environmental factors, and the output will be... Environmental data exceeding standards; like If the fault is determined to be caused by the equipment itself, the output will be... ; like This indicates a combined effect of environmental and equipment factors, resulting in an output... , and the proportion of their influence ( (The result is rounded to the nearest integer).

[0024] In this embodiment, the digital twin modeling module is used to construct a 3D digital twin model of a photovoltaic power station, and to achieve visualization mapping through the built-in environmental impact layer and fault association layer; The environmental impact layer is used to overlay environmental data onto the 3D digital twin model in the form of a color gradient, and the fault association layer is used to connect the faulty equipment with the associated environmental sensors through lines of the same color, visually presenting the relationship between the fault and the environment.

[0025] This embodiment also provides a method for intelligent operation and maintenance management of photovoltaic power plants, which includes the following steps: S1. Construct a 3D digital twin model of the photovoltaic power station using the digital twin modeling module, and then acquire equipment operation data and environmental data within the photovoltaic power station through the data acquisition module. S3. Using the environmental data exceedance contribution method in the environmental and fault correlation analysis module, the probability of environmental impact is calculated based on the data in the environmental and fault correlation database to determine the cause of the fault. S4. Finally, the relationship between faults and the environment is visualized through the digital twin modeling module, and the on-site staff of the photovoltaic power station are dispatched based on the visualized relationship between faults and the environment to realize the operation and maintenance management of the photovoltaic power station.

[0026] In this embodiment, an intelligent operation and maintenance management system is constructed, which includes a data acquisition module, an environment and fault correlation database, an environment and fault correlation analysis module, and a digital twin modeling module, thereby achieving precision and visualization of operation and maintenance of desert photovoltaic power stations.

[0027] Among them, the data acquisition module comprehensively acquires equipment operation data and environmental data, providing complete data support for fault analysis. The mapping data stored in the environment and fault association database, combined with the environmental data exceedance contribution method, accurately calculates the probability of environmental impact, clearly determines whether the fault is dominated by environmental factors, the equipment itself, or both, and solves the problem of difficulty in locating the cause of photovoltaic equipment faults in desert environments. The 3D model constructed by the digital twin modeling module achieves visual mapping through the environmental impact layer and the fault association layer, allowing on-site staff to intuitively grasp the relationship between faults and the environment, thereby efficiently dispatching personnel to carry out operation and maintenance, and effectively improving the intelligence level and management efficiency of operation and maintenance of desert photovoltaic power stations.

[0028] Example 2 This embodiment is basically the same as Embodiment 1, except that in this embodiment, the environment and fault correlation analysis module dynamically optimizes the weight coefficients in the environment and fault correlation rule base based on the actual fault causes reported on-site. The specific dynamic optimization process used in this embodiment is as follows: Let the percentage of actual environmental impact recorded by on-site staff be 1. (If wind and sand combined with dust accumulation lead to a decrease in power generation, the environmental impact accounts for 92% of the total.) =0.92), let the environmental impact probability calculated by the environment and fault correlation analysis module be . ; Then adopt Define the deviation value; like If the percentage is greater than 8%, then all weight coefficients for this fault type are calculated. Make corrections and adopt Make corrections, among which... This is a correction factor, ranging from 0.5 to 0.7, and the corrected value applies to all... Normalization is performed to ensure that the sum of the corrected weight coefficients for this fault type is 1, and the optimized weight coefficients are updated in real time to the environment and fault association rule base. like If the value is ≤8%, then the original weighting coefficient remains unchanged. constant.

[0029] Based on Example 1, this embodiment further improves the accuracy of determining the causes of photovoltaic power plant failures and the sustainability of the system by adding dynamic optimization based on on-site feedback to the environment and fault correlation analysis module.

[0030] In this embodiment, the environment and fault correlation analysis module compares the actual fault cause entered by the on-site staff with the calculated environmental impact probability and defines a deviation value. If the deviation value exceeds 8%, the weight coefficient under the corresponding fault type is corrected and normalized before being updated to the environment and fault correlation rule library. If the deviation value is ≤8%, the original weight coefficient remains unchanged, effectively reducing the deviation between the calculation results and the actual operation and maintenance situation. This ensures that the weight coefficient in the environment and fault correlation rule library always matches the actual situation on site, avoiding fault analysis errors caused by fixed weights and making the fault cause determination more accurate.

[0031] The embodiments disclosed in this invention are preferred embodiments, but are not limited thereto. Those skilled in the art can easily understand the spirit of this invention based on the above embodiments and make different extensions and variations, but as long as they do not depart from the spirit of this invention, they are all within the protection scope of this invention.

Claims

1. An intelligent operation and maintenance management system for a photovoltaic power station, characterized in that, The system comprises a data acquisition module, an environment and fault association database, an environment and fault association analysis module, and a digital twin modeling module. The data acquisition module is configured to acquire equipment operation data and environmental data in the photovoltaic power station. The environment and fault association database comprises an environment and fault association rule base, and is configured to store the equipment operation data and the environmental data. The environment and fault association analysis module is configured to retrieve data from the environment and fault association database and calculate the probability of the fault cause of the equipment in the photovoltaic power station. The digital twin modeling module is configured to construct a 3D digital twin model of the photovoltaic power station and realize visual mapping through an embedded environment impact layer and a fault association layer. 2.The intelligent operation and maintenance management system of a photovoltaic power station according to claim 1, characterized in that, The data acquisition module comprises an equipment operation data acquisition unit and an environmental data acquisition unit. 3.The intelligent operation and maintenance management system of a photovoltaic power station according to claim 2, characterized in that, The equipment operation data acquisition unit is configured to acquire equipment operation data in the photovoltaic power station to determine the fault types of the equipment, including power generation reduction, inverter error, photovoltaic panel temperature anomaly, and junction box sand dust blockage. 4.The intelligent operation and maintenance management system of a photovoltaic power station according to claim 3, characterized in that, The environmental data acquisition unit comprises a plurality of environmental sensors configured to acquire environmental data of the photovoltaic power station. The equipment operation data includes photovoltaic panel power generation, inverter voltage, current, and junction box temperature. The environmental data includes wind sand intensity, dust thickness, sunshine duration, environmental temperature, and environmental humidity. The mapping data between the environment and the fault types of the equipment in the photovoltaic power station comprises: For the fault type of power generation reduction, the associated environmental data includes wind sand intensity, dust thickness, and sunshine duration, wherein the wind sand intensity threshold is > 8 m / s and lasts > 2 h, the weight coefficient is 0.4, the dust thickness threshold is > 2 mm, the weight coefficient is 0.5, the sunshine duration threshold is < 4 h / day, the weight coefficient is 0.1, and the corresponding equipment basic fault probability is 0.2-0.5; 5.The intelligent operation and maintenance management system of a photovoltaic power station of claim 1, characterized in that, For the fault type of inverter error, the associated environmental data includes environmental humidity and environmental temperature, wherein the environmental humidity threshold is > 90% RH and lasts > 72 h, the weight coefficient is 0.6, the environmental temperature threshold is > 40℃ and lasts > 4 h, the weight coefficient is 0.4, and the corresponding equipment basic fault probability is 0.3-0.5; For the fault type of photovoltaic panel temperature anomaly, the associated environmental data includes sunshine duration and environmental temperature, wherein the sunshine duration threshold is > 10 h / day, the weight coefficient is 0.3, the environmental temperature threshold is > 35℃, the weight coefficient is 0.7, and the corresponding equipment basic fault probability is 0.25-0.4; For the fault type of junction box sand dust blockage, the associated environmental data includes wind sand intensity and dust thickness, wherein the wind sand intensity threshold is > 12 m / s and lasts > 1 h, the weight coefficient is 0.7, the dust thickness threshold is > 3 mm, the weight coefficient is 0.3, and the corresponding equipment basic fault probability is 0.15-0.

3. When calculating the probability of the fault cause of the equipment in the photovoltaic power station, the environment and fault association analysis module uses the environmental data exceeding standard contribution method to calculate the environmental impact probability, thereby determining the fault cause. 6.The intelligent operation and maintenance management system of a photovoltaic power station of claim 4, characterized in that, The environment and fault correlation analysis module dynamically optimizes each weight coefficient in the environment and fault correlation rule base based on actual fault causes of on-site feedback. 7.The intelligent operation and maintenance management system of a photovoltaic power station according to claim 3, characterized in that, The environment sensor includes multiple wind and sand intensity sensors, dust thickness sensors, sunshine duration sensors, environment temperature sensors, and environment humidity sensors. 8.The intelligent operation and maintenance management system of a photovoltaic power station of claim 1, characterized in that, The environment impact layer is used to superimpose environment data in the form of a color gradient on the 3D digital twin model, and the fault correlation layer is used to connect fault devices and associated environment sensors through isochromatic lines to visually present the correlation between faults and the environment.

9. An intelligent operation and maintenance management method for a photovoltaic power station, the method being applicable to the photovoltaic power station intelligent operation and maintenance management system according to any one of claims 1-8, characterized in that, The method comprises the following steps: S1, a 3D digital twin model of the photovoltaic power station is constructed using a digital twin modeling module, and device operation data and environment data in the photovoltaic power station are obtained through a data acquisition module; S2, the device operation data and the environment data are stored through an environment and fault correlation database, and mapping data between the environment and fault types of the photovoltaic power station are stored through an environment and fault correlation rule base; S3, the environment and fault correlation analysis module uses the environment data exceeding standard contribution degree method to calculate the environment impact probability using the data in the environment and fault correlation database, thereby determining the fault cause; S4, finally, the digital twin modeling module visually presents the correlation between faults and the environment. 10.The intelligent operation and maintenance management method of a photovoltaic power station according to claim 9, characterized in that, In the above S4, the on-site staff of the photovoltaic power station are dispatched according to the visually presented correlation between faults and the environment, thereby realizing operation and maintenance management of the photovoltaic power station.

Images