A management method and system for shared operation and maintenance of distributed photovoltaic power stations

Abstract

The embodiments of this specification provide a management method and system for shared operation and maintenance of a distributed photovoltaic power station. The method includes: obtaining daily monitoring data, the daily monitoring data including first monitoring data and / or second monitoring data obtained from a user terminal; determining a first abnormality indicator based on the daily monitoring data; obtaining corresponding target monitoring data based on the first abnormality indicator; determining a second abnormality indicator based on the target monitoring data; determining a manual detection priority based on the second abnormality indicator; determining a detection management instruction based on the manual detection priority; and sending the detection management instruction to the user terminal.

Description

Technical Field

[0001] The present invention relates to the field of monitoring technology, and in particular to a management method and system for shared operation and maintenance of distributed photovoltaic power stations. Background Art

[0002] In the operation of the distributed photovoltaic power station management system, it is necessary to supervise and inspect the operation of each photovoltaic power station, and conduct a series of error correction and re-inspection based on the inspection results to ensure the normal and reasonable operation of the photovoltaic power station and ensure the safety of the photovoltaic power station. In the process of supervising and inspecting the operation of distributed photovoltaic power stations, there are many locations involved, the inspection items are complicated, and the inspection schemes are different due to the different conditions of the equipment in each photovoltaic power station. The existing inspection schemes are mainly divided into regular inspections and "passive operation and maintenance" methods: (1) "Passive operation and maintenance" method The operation and maintenance management of distributed photovoltaic power stations in my country is mostly "passive operation and maintenance", that is, after a fault occurs, the operation and maintenance personnel are arranged to go to the site to solve the fault, and there is no systematic and scientific arrangement. (2) Regular inspection method The regular inspection method is adopted, based on experience and knowledge, to carry out preventive maintenance or regular inspection of equipment that has not failed. This method can reduce the fault time, but the purposeless high-frequency regular maintenance consumes a lot of manpower and material resources, resulting in a certain degree of resource waste.

[0003] Therefore, it is hoped to provide a management method and system for shared operation and maintenance of distributed photovoltaic power stations, which can help optimize maintenance plans, reduce downtime and maintenance costs, and improve the reliability and operating efficiency of photovoltaic stations by accurately identifying equipment that may be abnormal and performing timely and accurate maintenance. Summary of the invention

[0004] This manual provides a management method and system for shared operation and maintenance of distributed photovoltaic power stations, which accurately identify equipment that may be abnormal and perform timely and accurate maintenance, helping to optimize maintenance plans, reduce downtime and maintenance costs, and improve the reliability and operating efficiency of photovoltaic stations.

[0005] One of the embodiments of the present specification provides a method for shared operation and maintenance management of a distributed photovoltaic power station, the method comprising: obtaining daily monitoring data, the daily monitoring data comprising first monitoring data and / or second monitoring data obtained from a user terminal; determining a first abnormal indicator based on the daily monitoring data; obtaining corresponding target monitoring data based on the first abnormal indicator; determining a second abnormal indicator based on the target monitoring data; determining a manual detection priority based on the second abnormal indicator; determining a detection management instruction based on the manual detection priority; and sending the detection management instruction to the user terminal.

[0006] One of the embodiments of the present specification provides a management system for shared operation and maintenance of a distributed photovoltaic power station, the system comprising: a first acquisition module, used to acquire daily monitoring data, the daily monitoring data including first monitoring data and / or second monitoring data acquired from a user terminal; a first indicator determination module, used to determine a first abnormal indicator based on the daily monitoring data; a second acquisition module, used to acquire corresponding target monitoring data based on the first abnormal indicator; a second indicator determination module, used to determine a second abnormal indicator based on the target monitoring data; a priority determination module, used to determine a manual detection priority based on the second abnormal indicator; an instruction determination module, used to determine a detection management instruction based on the manual detection priority; and an instruction sending module, used to send the detection management instruction to the user terminal.

[0007] One of the embodiments of the present specification provides a management device for shared operation and maintenance of a distributed photovoltaic power station, the device comprising a processor and a memory; the memory is used to store instructions, and when the instructions are executed by the processor, the device causes the device to implement a management method for shared operation and maintenance of a distributed photovoltaic power station as described in any of the above items.

[0008] One of the embodiments of this specification provides a computer-readable storage medium, characterized in that the storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer runs the management method for shared operation and maintenance of distributed photovoltaic power stations described in any one of the above. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0010] Figure 1 It is a schematic diagram of an application scenario of a management system for shared operation and maintenance of a distributed photovoltaic power station according to some embodiments of this specification;

[0011] Figure 2 It is a module schematic diagram of a management system for shared operation and maintenance of a distributed photovoltaic power station according to some embodiments of this specification;

[0012] Figure 3 is an exemplary flow chart of a management method for shared operation and maintenance of a distributed photovoltaic power station according to some embodiments of this specification; DETAILED DESCRIPTION

[0013] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0014] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0015] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0017] Figure 1 It is a schematic diagram of an application scenario of a management system for shared operation and maintenance of a distributed photovoltaic power station according to some embodiments of this specification.

[0018] In some embodiments, a scenario 100 involved in a management system for shared operation and maintenance of a distributed photovoltaic power station may include a processor 110 , a distributed photovoltaic power station component 120 , a storage device 130 , a network 140 , and a user terminal 150 .

[0019] In some embodiments, the processor 110 may be used to process information and / or data related to the scene 100, for example, to determine monitoring indicators and review indicators of the monitoring process based on monitoring data. In some embodiments, the processor 110 may be local or remote. For example, the processor 110 may access information and / or data stored in the storage device 130 or the user terminal 150 via the network 140. For another example, the processor 110 may be directly connected to the storage device 130 or the user terminal 150 to access the stored information and / or data.

[0020] In some embodiments, the processor 110 may process information and / or data related to the scene 100 to perform one or more functions described in the present application. For example, the processor 110 may process the daily monitoring data based on the first model to determine the first abnormal indicator.

[0021] The distributed photovoltaic power station component 120 may refer to all devices of all photovoltaic power stations included. There may be at least one distributed photovoltaic power station component 120. The distributed photovoltaic power station component 120 may include multiple devices, for example, the distributed photovoltaic power station component 120 includes photovoltaic components, inverters, battery packs, grid connection devices, sensor devices, etc.

[0022] The storage device 130 may be used to store data and / or instructions related to the management of the shared operation and maintenance of the distributed photovoltaic power station. In some embodiments, the storage device 130 may store data obtained / retrieved from the user terminal 150. In some embodiments, the storage device 130 may store data and / or instructions that the processor 110 uses to execute or use to complete the exemplary methods described in this application. In some embodiments, the storage device 130 may be implemented on a cloud platform.

[0023] In some embodiments, the storage device 130 may be connected to the network 140 to communicate with one or more components of the scene 100 (e.g., the processor 110, the distributed photovoltaic power station component 120, and the user terminal 150). One or more components of the scene 100 may access data or instructions stored in the storage device 130 via the network 140. In some embodiments, the storage device 130 may be directly connected to or communicate with one or more components of the scene 100 (e.g., the processor 110, the distributed photovoltaic power station component 120, and the user terminal 150). In some embodiments, the storage device 130 may be part of the processor 110. In some embodiments, the storage device 130 may be a separate memory.

[0024] The network 140 can facilitate the exchange of information and / or data. In some embodiments, one or more components of the scene 100 (e.g., the processor 110, the distributed photovoltaic power station component 120, the user terminal 150) can send information and / or data to other components of the scene 100 via the network 140. For example, the processor 110 can obtain daily monitoring data from the user terminal 150 via the network 140. In some embodiments, the network 140 can be a wired network or a wireless network, etc. or any combination thereof. As an example only, the network 140 may include a cable network. In some embodiments, the scene 100 may include one or more network access points. For example, a base station and / or a wireless access point, one or more components of the scene 100 can be connected to the network 140 to exchange data and / or information.

[0025] The user terminal 150 may be a user-directed device or other entity. In some embodiments, the user may be a management executor, maintenance staff, on-site inspection personnel, etc. of the shared operation and maintenance of a distributed photovoltaic power station. In some embodiments, the user terminal 150 may include a mobile phone, a tablet computer, a laptop computer, etc. or any combination thereof. The user refers to the user / controller of the user terminal. In some embodiments, the user may upload the second monitoring data through the user terminal 150. In some embodiments, the user may obtain information through the user terminal 150, for example, obtaining data and / or instructions related to monitoring or review management stored in the storage device 130.

[0026] Figure 2 It is a module diagram of a management system for shared operation and maintenance of a distributed photovoltaic power station according to some embodiments of this specification.

[0027] like Figure 2 As shown, the management system 200 for shared operation and maintenance of distributed photovoltaic power stations may include a first acquisition module 210, a first indicator determination module 220, a second acquisition module 230, a second indicator determination module 240, a priority determination module 250, an instruction determination module 260 and an instruction sending module 270.

[0028] The first acquisition module 210 may be used to acquire daily monitoring data, where the daily monitoring data includes first monitoring data and / or second monitoring data acquired from a user terminal.

[0029] The first indicator determination module 220 may be configured to determine a first abnormal indicator based on daily monitoring data.

[0030] In some embodiments, the first indicator determination module 220 further includes: an information acquisition module, which is used to acquire field information based on a preset information acquisition template; an extraction module, which is used to extract classification information of any information category from the field information; a production module, which is used to determine the field condition generation template corresponding to the information category from a preset field condition generation template library; a condition production module, which is used to generate field conditions based on the field condition generation template and the classification information; a first history acquisition module, which is used to acquire the first historical abnormal record generated in the history of other fields that meet each field condition from a preset information sharing platform; a second history acquisition module, which is used to acquire the second historical abnormal record generated in the field history locally; an abnormal indicator determination module, which counts the first abnormal indicator based on the first historical abnormal record and the second historical abnormal record.

[0031] The second acquisition module 230 may be configured to acquire corresponding target monitoring data based on the first abnormality indicator.

[0032] The second indicator determination module 240 may be configured to determine a second abnormal indicator based on the target monitoring data.

[0033] In some embodiments, the first abnormal indicator includes a monitoring indicator, and the first indicator determination module 220 further includes: a first processing module, used to process daily monitoring data through a first model to determine the number of abnormalities monitored by at least one item, wherein the at least one item includes at least one of photovoltaic components, inverters, grid connection systems, and line failures; a first determination module, used to determine the monitoring indicator based on the number of abnormalities monitored by at least one item.

[0034] In some embodiments, the second abnormal indicator includes a review indicator, and the second indicator determination module 240 further includes: a second processing module, used to process the target monitoring data through a second model, and determine the number of abnormalities of at least one item reviewed, wherein the at least one item includes at least one of photovoltaic components, inverters, grid connection systems, and line failures; a second determination module, used to determine the review indicator based on the number of abnormalities reviewed of at least one item.

[0035] The priority determination module 250 may be configured to determine a manual detection priority based on the second abnormality indicator.

[0036] The instruction determination module 260 may be configured to determine a detection management instruction based on a manual detection priority.

[0037] The instruction sending module 270 may be used to send the detection management instruction to the user terminal.

[0038] It should be understood that the above modules are only simple examples of the relevant modules mainly involved in this specification, and do not represent the display of all relevant contents of this application. There are also some modules and units that are not shown in this module diagram, and they are not illustrated one by one here. Moreover, the above modules and units are not completely independent, and may also be cross-involved.

[0039] Figure 3 is an exemplary flow chart of a management method for shared operation and maintenance of a distributed photovoltaic power station according to some embodiments of this specification. Process 300 may be executed by a processor. Figure 3 As shown, process 300 may include the following steps:

[0040] Step 310, obtaining daily monitoring data.

[0041] Daily monitoring data may refer to routine monitoring data related to each photovoltaic site. Since it is not necessary to monitor each device at the site in real time during daily operations, by only acquiring daily monitoring data, resources and costs can be saved, data processing and analysis can be simplified, etc. Daily monitoring data can be acquired through devices, manual uploads, sensors around the devices, etc. Daily monitoring data includes first monitoring data and / or second monitoring data acquired from a user terminal.

[0042] The first monitoring data may refer to important monitoring data related to the first part of the equipment collected during the daily monitoring process. The first part of the equipment may refer to equipment with high abnormal hidden dangers. High abnormal hidden dangers may refer to large workload, long continuous working time, high equipment service life, major accidents, etc. In some embodiments, the processor may use at least one device of at least two devices of the same model as the first part of the equipment. For example, the number of photovoltaic modules with device model 01 is 2, and photovoltaic modules with a long service life can be used as the first part of the equipment. The first monitoring data may include important performance indicators. Important performance indicators may refer to key indicators and performance parameters of photovoltaic sites. Key indicators may include total power generation, total power generation efficiency, total energy utilization, basic equipment information, equipment operation status, whether to alarm, etc. The equipment includes photovoltaic modules, inverters, battery packs, grid connection equipment, sensor equipment, etc. The equipment operation status corresponding to the photovoltaic module includes light intensity, output voltage, output current, operating temperature, etc. The equipment operation status corresponding to the inverter includes input voltage, input current, output voltage, output current, operating temperature, etc. In some embodiments, the first monitoring data can be obtained through the connection device. By focusing on monitoring only some equipment with higher abnormal risks, we can save resources and costs, simplify data processing and analysis, and achieve extensive and accurate monitoring.

[0043] In some embodiments, the processor may obtain the first monitoring data by connecting to the first part of the equipment.

[0044] The second monitoring data may refer to data manually collected during daily monitoring.

[0045] Operation records may refer to records related to operations recorded by inspectors. In some embodiments, operation records may include inspector information, relevant operation information, recording frequency, etc. Relevant operations may include periodic tasks such as inspections and maintenance, and emergency tasks. Inspector information may refer to information related to inspectors related to obtaining the second monitoring data. In some embodiments, personnel information may include at least one of personnel grade and division of labor, and quality information. In some embodiments, quality information may include at least one of the inspector's moral quality, business ability, judgment ability, and reaction speed.

[0046] In some embodiments, the processor may obtain the second monitoring data by manually checking the shift schedule and manually recording.

[0047] The daily monitoring data may also include a first acquisition frequency, a first monitoring time, etc. The first acquisition frequency may refer to the frequency of daily monitoring data acquisition. For example, the first acquisition frequency may be in seconds. The first monitoring time may refer to the time related to the monitoring process. In some embodiments, the first monitoring time may include the duration and start time of the monitoring. For example, the monitoring time may be from 6 am to 8 am every day.

[0048] Step 320: Determine a first abnormal indicator based on daily monitoring data.

[0049] The first abnormality indicator may refer to an indicator that is initially judged to be abnormal. The first abnormality indicator may include a first abnormal device, a corresponding first abnormality type, a first abnormality probability, and a first abnormality time. In some embodiments, the processor may determine the first abnormality indicator through a first abnormality model based on daily monitoring data. The first abnormality model may be a machine learning model. The input of the first abnormality model is the first monitoring data and the second monitoring data, and the output is the first abnormality indicator. The first abnormality model may be obtained through historical data training.

[0050] The first abnormal probability may refer to the abnormal probability of each device corresponding to the daily monitoring data. In some embodiments, the first abnormal device may refer to the device corresponding to the first abnormal probability being higher than the first abnormal threshold. The first abnormal threshold may be set manually. The first abnormal device may be determined by the first abnormal probability and the first abnormal threshold. The first abnormal device may refer to some of the devices in the first part of the devices. The first abnormal time may refer to the time point or time period when the first abnormal device may be abnormal. For example, based on the current time and the abnormal probability, it is judged that the time of the abnormal event in which the current device may be abnormal is 10 days later. For another example, the first abnormal time may refer to the current time point.

[0051] Through some embodiments of the present specification, by adding the quality information of the inspector to the second monitoring data, the integrity of the inspector and the credibility of the corresponding second monitoring data can be evaluated, further to ensure the accuracy of the first abnormal indicator.

[0052] In some embodiments, the first abnormal probability can be represented by a probability distribution. In some embodiments, the processor can obtain field information based on a preset information acquisition template; extract classification information of any information category from the field information; determine a field condition generation template corresponding to the information category from a preset field condition generation template library; generate field conditions based on the field condition generation template and classification information; obtain first historical abnormal records generated in the history of other fields that meet each field condition from a preset information sharing platform; obtain second historical abnormal records generated in the history of the field from a local location; and count the first abnormal frequency based on the first historical abnormal record and the second historical abnormal record.

[0053] In some embodiments, the working principle and beneficial effects of the above technical solution are:

[0054] The first abnormal probability of a site can be determined based on the second historical abnormal records generated in the site's own history and the first historical abnormal records generated in other sites' history. This improves the comprehensiveness of abnormal probability distribution acquisition and avoids the problem of one-sided abnormal probability distribution caused by some sites that have just been put into use and have not generated too many second historical abnormal records.

[0055] Through some embodiments of this specification, the second historical abnormal record can be obtained from a preset information sharing platform, and the preset information sharing platform is specifically a platform for sharing historical abnormal records between different sites. However, due to the differences in equipment models, equipment maintenance records, and equipment work tasks in different sites, the probability of generating abnormalities will also be different. Therefore, based on the site information, the site conditions are generated, and other sites must meet each site condition, which improves the applicability of obtaining the second historical abnormal record; the site information includes: the equipment model, equipment maintenance records, and equipment work tasks in the site; the site conditions include: the equipment model, equipment maintenance records, and equipment work tasks, for example: the equipment model should be xxx, the equipment maintenance frequency should be xx, the equipment's last maintenance time is xx, and the equipment's daily work task volume should be xx, etc. When generating production conditions, according to the information category, the corresponding preset site condition generation template is determined, and the template is generated based on the site condition generation template; for example: the information category is the equipment model, the corresponding classification information is "101", and the corresponding preset site condition generation template is "the model of the x device in other generation sites should be 101".

[0056] In some embodiments, the first abnormality indicator may also include a monitoring indicator. The monitoring indicator includes the number of abnormalities found in the daily monitoring data. In some embodiments, the daily monitoring data is processed by a first model to determine the number of abnormalities monitored by at least one project, wherein the first model is a machine learning model, and the at least one project includes at least one of photovoltaic components, inverters, grid connection systems, and line faults. Based on the number of abnormalities monitored by at least one project, the monitoring indicator is determined. In some embodiments, the number of abnormalities may be the sum of the number of abnormalities in photovoltaic components, inverters, grid connection systems, and line faults.

[0057] Step 330: Acquire corresponding target monitoring data based on the first abnormal indicator.

[0058] The target monitoring data may refer to monitoring data related to the device that is the same as or similar to the first abnormal device. The device that is the same as or similar to the first abnormal device may refer to the device that is the same model or has the same function as the first abnormal device in the same photovoltaic site. For example, the daily monitoring data only includes the monitoring data of the photovoltaic module of model 1, and the second abnormal device may include all photovoltaic modules of model 1. The device that is the same as or similar to the first abnormal device includes the first abnormal device. Since the daily monitoring data cannot include real-time monitoring data of each part of the site, the part that may have abnormalities is determined through partial data, and the abnormal device and similar devices are monitored in a targeted manner, which narrows the monitoring scope, improves the monitoring efficiency, and helps to accurately and timely detect abnormalities. Since the daily monitoring data can only determine the first abnormal device that may have abnormalities, and cannot determine the abnormal situation of the device that is the same as or similar to the first abnormal device, it is necessary to further obtain more detailed monitoring data of the device that is the same as or similar to the first abnormal device, which can narrow the abnormal scope in a direction and further improve the certainty of the occurrence of abnormalities. Acquiring the corresponding target monitoring data based on the first abnormal indicator can ensure that all abnormal situations are taken into account, without the need to acquire and analyze the data of all devices one by one, which can save resources and costs, simplify data processing and analysis, and achieve extensiveness and accuracy of monitoring.

[0059] The target monitoring data may include a second acquisition frequency, a second monitoring time, etc. The second acquisition frequency may be higher than the first acquisition frequency, and the second monitoring time may be higher than the first monitoring time. By setting the second acquisition frequency higher than the first acquisition frequency, and setting the second monitoring time higher than the first monitoring time, it is to prevent the erroneous judgment of abnormalities caused by other accidents during data transmission or acquisition, and to improve the accuracy of abnormality judgment.

[0060] Step 340: Determine a second abnormal indicator based on the target monitoring data.

[0061] The second abnormality indicator may refer to an indicator that is ultimately judged to be abnormal. The second abnormality indicator may include a second abnormal device, a second abnormal probability, and a second abnormal time. The second abnormal device may refer to a device whose second abnormal probability is higher than a second abnormal threshold. The second abnormal threshold is higher than the first abnormal threshold. The first abnormal threshold can be used to determine a large range of abnormalities, and by setting the second abnormal threshold to be higher than the first abnormal threshold, the probability of determining an abnormality can be increased, and the range of possible abnormalities can be determined in a targeted manner, thereby improving monitoring efficiency.

[0062] In some embodiments, the second abnormality indicator may further include a review indicator. In some embodiments, the processor may determine a review indicator based on the second abnormality indicator, wherein the review indicator includes the number of abnormalities found during the review process. The review process may refer to the process of obtaining target detection data. The review may be completed before the second abnormal time. The details of the second abnormal time may refer to the details of the first abnormal time.

[0063] In some embodiments, the target monitoring data is processed by a second model to determine the number of abnormalities in the review of at least one item, wherein the second model is a machine learning model, and the at least one item includes at least one of a photovoltaic module, an inverter, a grid connection system, and a line fault. Based on the number of fields reviewed for at least one item, a review index is determined. The number of reviewed abnormalities is used as a review index. In some embodiments, the number of abnormalities found in the review can be the sum of the number of abnormalities found in the review of photovoltaic modules, inverters, grid connection systems, and line faults.

[0064] In some embodiments, the processor can determine the accuracy of the second abnormal index based on the monitoring index and the review index. For example, if the number of abnormalities corresponding to the photovoltaic component is high in the monitoring index, and the number of abnormalities corresponding to the inverter is high in the review index, the accuracy of the corresponding second abnormal index is low. In some embodiments, the processor can compare the similarity of the monitoring index and the review index. When the similarity is higher than the similarity threshold, it means that the second abnormal index is more accurate. The similarity threshold can be set manually. The monitoring index and the review index can be represented by a vector. For example, (1, 2, 3, 4) can represent the number of abnormalities of the photovoltaic component, the inverter, the grid connection system, and the line fault respectively. The similarity of the monitoring index and the review index can be represented by the distance between the vectors, and the smaller the distance, the greater the similarity. By determining the accuracy of the second abnormal index, the abnormal range can be further accurately determined, saving resources and costs. In some embodiments of this specification, by obtaining the monitoring index and the review index, the second abnormal index is determined, and the rationalization, automation and efficiency management level of the monitoring process and the review process are improved.

[0065] In some embodiments, the first abnormal indicator or the second abnormal indicator may further include an indicator attribute. The indicator attribute may include the severity of the abnormality of the second abnormal device. The indicator attribute may include a serious fault or a common fault. Common faults may include faults such as shadow blocking, fan damage, circuit breaker tripping, communication interruption, etc. Serious faults mainly include faults that may cause serious economic losses or casualties to the photovoltaic power station. For example, a serious fault may include a fire or the like.

[0066] In some embodiments, the processor may determine the indicator attribute through a classification model based on daily monitoring data. The classification model may be a machine learning model, for example, the classification model may be a convolutional neural network. The input of the classification model may include daily monitoring data, and the output may be anomalies that may occur and corresponding indicator attributes. For example, the output may include: anomalies occur in device 1 of model 1 and the corresponding indicator attribute of the anomaly is a common fault, anomalies occur in device 2 of model 1 and the corresponding indicator attribute of the anomaly is a serious fault. In some embodiments, the parameters of the classification model may be obtained through training. In some embodiments, the classification model may be obtained through multiple labeled training samples. For example, multiple labeled training samples may be input into an initial classification model, a loss function may be constructed through the prediction results of the labels and the initial classification model, and the parameters of the initial classification model may be updated based on the iteration of the loss function. When the loss function of the initial classification model meets the preset conditions, the model training is completed, wherein the preset conditions may be that the loss function converges, the number of iterations reaches a threshold, etc.

[0067] In some embodiments, the classification model may include an input layer, a convolutional layer 1, a pooling layer 1, a convolutional layer 2, a pooling layer 2, and a fully connected layer. The input of the input layer may include daily monitoring data, and the output may include a time feature matrix. The time feature matrix may refer to a matrix composed of daily monitoring data and corresponding time. Exemplarily, the time feature matrix may be represented by formula (1).

[0068]

[0069] Among them, X is the time feature matrix, s represents the number of important performance indicators in daily monitoring data, and t represents the selected time point or time length.

[0070] Through some embodiments of the present specification, the abnormal indicator attributes determined by the classification model based on the time feature matrix can better capture the impact of temporal trends, periodicity and dynamic changes on the indicator attributes, which helps to improve the representation ability and prediction accuracy of the model.

[0071] The input of convolution layer 1 is the time feature matrix, the output of convolution layer 1 is the input of pooling layer 1, the output of pooling layer 1 is the input of convolution layer 2, and further, the output of convolution layer 2 is input into pooling layer 2, and the output of pooling layer 2 is used as the input of the fully connected layer. The function of the fully connected layer is to perform nonlinear combination of the extracted features to obtain the output index attributes.

[0072] In some embodiments, the training samples may include historical daily monitoring data, and the labels may be historical indicator attributes corresponding to the historical daily monitoring data. In some embodiments, the training samples may be acquired based on historical data, and the labels of the training data may be determined by annotating anomalies based on professional knowledge in this field. In some embodiments, the training process includes forward propagation and back propagation. Forward propagation passes the input data to the output layer of the network to generate a prediction result; back propagation may be an Adam algorithm, which uses the difference between the prediction result and the true label to reversely calculate the gradient and update the model parameters to make the model better fit the training data and improve the accuracy of the prediction.

[0073] In some embodiments of this specification, since the Adam algorithm involves bias correction, the bias correction can effectively update the step size, making the parameter update more stable and ensuring the convergence of the training.

[0074] In some embodiments of the present specification, by using a convolutional neural network in determining abnormal indicator attributes, the accuracy and reliability of fault or abnormality judgment can be improved.

[0075] Step 350: Determine the manual detection priority based on the second abnormality indicator.

[0076] The manual detection priority may refer to the order in which manual detection is performed. In some embodiments, the processor may determine the order in which manual detection is performed based on the manual detection priority.

[0077] In some embodiments, the manual inspection priority can be determined by a machine learning model based on the second abnormal device and its basic device information, the second abnormal probability, and the corresponding second abnormal time. The time for manual inspection needs to encounter the second abnormal event. Devices with a higher second abnormal probability can be inspected first. Devices with indicator attributes of severe failure have a higher priority.

[0078] Step 360: Determine the inspection management instruction based on the manual inspection priority.

[0079] The detection management instruction may refer to an instruction related to on-site maintenance. In some embodiments, the detection management instruction may include an instruction to initiate a manual inspection. The detection management instruction may include a command to determine an on-site inspection personnel. The on-site inspection personnel may refer to a person assigned to conduct on-site inspections and possible repairs. The on-site inspection personnel may include internal staff of the power station and social sharing personnel.

[0080] Step 370: Send the detection management instruction to the user terminal.

[0081] The processor can send the detection management instructions to the user terminal, and the on-site inspection personnel can perform manual inspection or on-site maintenance according to the prompts.

[0082] In some embodiments, when the processor determines that the indicator attribute of the current abnormality is a serious fault, the real-time location information of all personnel in the personnel database (including all internal employees of the power station and social sharing personnel) is obtained according to the task location (the equipment where the abnormality may occur), and the first personnel whose distance from the task location is less than the distance threshold is determined based on the real-time location information of the task location and each personnel, wherein the number of the first personnel may be at least one. Further, the processor generates a monitoring management instruction, and simultaneously sends a detection management instruction to the user terminal of at least one first person, and at least one first person responds to the detection management instruction through the user terminal, and the first person who responds first can be used as the target on-site detection personnel for manual detection or on-site maintenance. The distance threshold can be set manually. Through some embodiments of this specification, when the processor determines that the indicator attribute of the current abnormality is a serious fault, the task is dispatched based on time as the only criterion, and safety is an important premise and guarantee.

[0083] In some embodiments, when the processor determines that the indicator attribute of the current abnormality is a common fault, the real-time location information of all personnel in the personnel database is obtained according to the task location, and based on the task location and the real-time location information of each personnel, a second person whose loss value is less than the loss threshold is determined, wherein the number of the second person can be at least one, further, the processor generates a monitoring management instruction, and simultaneously sends a detection management instruction to a user terminal of at least one second person, at least one second person responds to the detection management instruction through the user terminal, and the first second person to respond can be used as a target on-site detection personnel for manual detection or on-site maintenance. The loss threshold can be determined manually.

[0084] The loss value may refer to the economic loss of each second person for manual inspection or on-site maintenance. For internal employees of the power station, the loss value may be the economic loss of the power station that may be caused by the time it takes for each internal employee to reach the abnormal equipment. For social sharing personnel, the loss value includes the economic loss of the power station that may be caused by the time it takes for the social sharing personnel to reach the abnormal equipment, as well as the additional remuneration given by the power station to the social sharing personnel. The time it takes for each second person to reach the abnormal equipment can be determined based on the distance between the task location and its location. For example, it takes 10 minutes for internal employee A to reach the location of device A at the task location, and the economic loss of the power station caused by 10 minutes is 150 yuan. It takes 8 minutes for shared personnel B to reach the location of device A at the task location, and the economic loss of the power station caused by 8 minutes is 120, but the additional remuneration requires 50 yuan. Therefore, the loss value of internal employee A completing the manual inspection or on-site maintenance is 150 yuan, and the loss value of shared personnel B completing the manual inspection or on-site maintenance is 170 yuan.

[0085] Through some embodiments of this specification, based on different indicator attributes, different standard dispatching methods are adopted to maximize the benefits of the power station while ensuring the stability and safety of the power station.

[0086] In some embodiments, the target on-site inspection personnel eliminate defects and provide feedback on the on-site situation. In some embodiments, the feedback content is automatically matched with the power plant operation data, and new historical data is generated to achieve real-time update of classification model parameters, ensuring the reliability and real-time performance of the model accuracy.

[0087] In some embodiments, the detection management instruction may further include a detection time point. On-site detection personnel may be earlier than the second abnormal time. By setting the detection time point to be earlier than the second abnormal time, the staff may detect the second abnormal device before the second time point where the abnormality may occur with the second abnormal device, thereby minimizing the economic losses caused by the abnormality.

[0088] In some embodiments, the detection management instruction is determined based on the updated monitoring frequency and the manual detection priority. For the determination process of the detection management instruction, please refer to the process of detecting the management instruction.

[0089] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other beneficial effects that may be obtained. For example, in some embodiments, when the abnormal indicator attribute is judged to be a serious fault based on daily monitoring data, in line with the principle of reducing economic losses, steps 330-350 may not be performed, and the dispatch may be performed directly.

[0090] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0091] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0092] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some embodiments currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0093] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0094] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0095] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0096] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A management method for shared operation and maintenance of distributed photovoltaic power stations, characterized in that: The method comprises: Acquire daily monitoring data, where the daily monitoring data includes first monitoring data and / or second monitoring data acquired from a user terminal, where the first monitoring data refers to important monitoring data related to the first part of equipment collected during daily monitoring, where the first part of equipment refers to equipment with high abnormal potential risks; Determine a first abnormality indicator based on the daily monitoring data, where the first abnormality indicator refers to an indicator preliminarily determined to be abnormal, and the first abnormality indicator includes a first abnormal device, a corresponding first abnormality type, a first abnormality probability, and a first abnormality time; Acquire corresponding target monitoring data based on the first abnormal indicator, where the target monitoring data refers to monitoring data related to equipment with the same model and / or function as the first abnormal equipment; Determine a second abnormality indicator based on the target monitoring data, where the second abnormality indicator refers to an indicator that is finally determined to be abnormal, and the second abnormality indicator includes a second abnormal device, a second abnormal probability, and a second abnormal time; Determining a manual detection priority based on the second abnormality indicator; Determining a detection management instruction based on the manual detection priority; The detection management instruction is sent to the user terminal.

2. The method according to claim 1, characterized in that The first abnormality indicator includes a first abnormality frequency, and determining the first abnormality indicator based on the daily monitoring data includes: Acquire on-site information based on preset information acquisition templates; Extracting classification information of any information category from the on-site information; Determine a site condition generation template corresponding to the information category from a preset site condition generation template library; Generate a template based on the site conditions, and generate site conditions according to the classification information; Acquire the first historical abnormal record generated in the history of other sites that meet each of the site conditions from a preset information sharing platform; locally obtain a second historical abnormality record generated in the field history; The first abnormality frequency is counted based on the first historical abnormality record and the second historical abnormality record.

3. The method according to claim 1, characterized in that The first abnormal indicator includes a monitoring indicator, and determining the first abnormal indicator based on the daily monitoring data includes: Processing the daily monitoring data through a first model to determine an abnormal number of at least one monitoring item, wherein the at least one item includes at least one of a photovoltaic module, an inverter, a grid connection system, and a line fault; The monitoring indicator is determined based on the abnormal number of the at least one item monitoring.

4. The method according to claim 1, characterized in that: The second abnormality indicator includes a review indicator, and determining the second abnormality indicator based on the target monitoring data includes: Processing the target monitoring data through a second model to determine the number of abnormalities of at least one item review, wherein the at least one item includes at least one of a photovoltaic module, an inverter, a grid connection system, and a line fault; A review indicator is determined based on the number of abnormalities in the review of the at least one item.

5. A management system for shared operation and maintenance of distributed photovoltaic power stations, characterized in that: The system comprises: A first acquisition module is used to acquire daily monitoring data, wherein the daily monitoring data includes first monitoring data and / or second monitoring data acquired from a user terminal, wherein the first monitoring data refers to important monitoring data related to the first part of equipment collected during daily monitoring, and the first part of equipment refers to equipment with high abnormal potential risks; A first indicator determination module, configured to determine a first abnormal indicator based on the daily monitoring data, wherein the first abnormal indicator refers to an indicator initially determined to be abnormal, and the first abnormal indicator includes a first abnormal device, a corresponding first abnormal type, a first abnormal probability, and a first abnormal time; A second acquisition module, configured to acquire corresponding target monitoring data based on the first abnormal indicator, wherein the target monitoring data refers to monitoring data related to a device having the same model and / or function as the first abnormal device; A second indicator determination module, configured to determine a second abnormal indicator based on the target monitoring data, wherein the second abnormal indicator refers to an indicator ultimately determined to be abnormal, and the second abnormal indicator includes a second abnormal device, a second abnormal probability, and a second abnormal time; A priority determination module, used to determine the manual detection priority based on the second abnormality indicator; An instruction determination module, used to determine a detection management instruction based on the manual detection priority; An instruction sending module is used to send the detection management instruction to the user terminal.

6. The system according to claim 5, characterized in that The first abnormality indicator includes a first abnormality frequency, and the first indicator determination module further includes: An information acquisition module is used to acquire on-site information based on a preset information acquisition template; An extraction module, used for extracting classified information of any information category from the on-site information; A production module, used to determine a field condition generation template corresponding to the information category from a preset field condition generation template library; A condition production module, used to generate a template based on the field conditions and to generate field conditions according to the classification information; A first history acquisition module, used to acquire first historical abnormal records generated in the history of other sites that meet each of the site conditions from a preset information sharing platform; A second history acquisition module, used for locally acquiring a second historical abnormality record generated in the field history; The abnormality indicator determination module counts the first abnormality frequency based on the first historical abnormality record and the second historical abnormality record.

7. The system according to claim 5, characterized in that The first abnormal indicator includes a monitoring indicator, and the first indicator determination module further includes: A first processing module, configured to process the daily monitoring data by using a first model to determine an abnormal number of at least one monitoring item, wherein the at least one item includes at least one of a photovoltaic module, an inverter, a grid connection system, and a line fault; The first determination module is used to determine the monitoring indicator based on the abnormal number of the at least one project monitoring.

8. The system according to claim 5, characterized in that The second abnormal indicator includes a review indicator, and the second indicator determination module further includes: A second processing module, configured to process the target monitoring data through a second model to determine the number of abnormalities for review of at least one item, wherein the at least one item includes at least one of a photovoltaic module, an inverter, a grid connection system, and a line fault; The second determination module is used to determine the review index based on the number of abnormalities in the review of the at least one item.

9. A management device for shared operation and maintenance of a distributed photovoltaic power station, the device comprising a processor and a memory; the memory is used to store instructions, characterized in that: When the instruction is executed by the processor, the device implements the management method for shared operation and maintenance of a distributed photovoltaic power station as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer runs the management method for shared operation and maintenance of distributed photovoltaic power stations as described in any one of claims 1 to 4.

Images