A photovoltaic power station transformer state monitoring and failure warning system and method

Abstract

The present invention discloses a photovoltaic power station transformer state monitoring and failure warning system and method, belonging to the technical field of transformer monitoring, including obtaining the real-time operation data of the transformer at the current moment and the real-time perception data collected by the sensor, using a preset decision model to calculate the real-time decision data at the next moment, not only can it be judged whether the transformer has an operation fault according to the real-time data, but also the transformer fault can be predicted according to the decision data at the next moment; at the same time, the transformer fault can be further judged based on the aging condition of the transformer, thereby improving the accuracy of the transformer fault warning and reducing the missed judgment rate of the transformer fault warning.

Description

Technical Field

[0001] The present invention relates to the technical field of transformers, and more particularly to a photovoltaic power station transformer state monitoring and failure early warning system and method. Background Art

[0002] With the rapid development of my country's economy, the scale of the power system grid structure is expanding rapidly. More and more people are demanding more and more power from the grid, and the requirements for power quality are also increasing. How to ensure the stable, safe and reliable operation of power grid equipment is the most important thing for power employees. However, due to the increasing demand for electricity, especially during the peak summer period, the power system is often at full load or even overload. In the daily operation of power equipment, due to the influence of itself and the outside world, certain faults occasionally occur. Once a fault occurs, it will cause irreparable losses to the operation of the power grid.

[0003] The daily responsibilities of power grid equipment monitoring are to control the safe operation of the power grid, monitor and predict the health status of the equipment, and thus stabilize the overall power grid. Power transformers are key monitoring equipment in substations. In the massive amount of monitoring information, accurate identification of transformer operation status is limited by many factors, such as: the transformer equipment status perception model is not yet complete, and it is still mainly based on the status detection analysis results, supplemented by expert experience for judgment. There are many subjective factors, which can easily lead to misjudgment and misjudgment of transformer operation status and early warning.

[0004] Therefore, it is an urgent problem for technical personnel in this field to provide a system and method for monitoring the status and early warning of failure of photovoltaic power station transformers by combining multi-source data and improving the accuracy of transformer operation status monitoring and early warning of failure. Summary of the invention

[0005] In view of this, the present invention provides a photovoltaic power station transformer status monitoring and failure warning system and method, which can combine transformer operation data and perception data to perform photovoltaic power station transformer status monitoring and failure warning, thereby improving the accuracy of transformer operation status monitoring and failure warning.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] On the one hand, the present invention discloses a photovoltaic power station transformer state monitoring and failure warning system, including: a data acquisition module, a control module, a fault judgment module, a fault prediction module, and a warning module;

[0008] The data acquisition module acquires the real-time operation data of the transformer at the current moment and the real-time perception data collected by the sensor, and outputs them to the fault judgment module and the control module;

[0009] The control module outputs decision data for the next moment according to the real-time operation data and the real-time perception data;

[0010] The fault judgment module judges the state of the transformer at the current moment according to the real-time operation data and the real-time sensing data, and if the state is a fault, sends it to the early warning module for fault early warning; if the state is normal, sends it to the fault prediction module;

[0011] The fault prediction module predicts whether the state of the transformer at the next moment is a fault according to the decision data at the next moment, the real-time operation data and the real-time perception data. If the state at the next moment is a fault, it is sent to the early warning module for fault early warning; if the state at the next moment is normal, the control module controls the transformer according to the decision data at the next moment;

[0012] The early warning module issues an early warning according to the judgment results of the fault judgment module and the fault prediction module.

[0013] Preferably, it also includes a decision data adjustment module, which is connected to the fault prediction module and is used to adjust the decision data at the next moment according to the control rules and send it to the fault prediction module for prediction when the fault prediction module predicts that the state at the next moment is a fault based on the decision data at the next moment.

[0014] Preferably, the control module includes a decision data generating unit, a main control unit, a decision data judging unit, and a decision data determining unit;

[0015] The decision data generating unit is used to input the real-time operation data and the real-time perception data into the trained decision model and output the decision data at the next moment;

[0016] The decision data judgment unit is used to judge the decision data at the next moment sent by the fault prediction module and compare it with the decision data at the next moment output by the decision data generation unit. If they are consistent, the decision data at the next moment sent by the fault prediction module is sent to the main control unit; if they are inconsistent, the decision data at the next moment sent by the fault prediction module is sent to the decision data determination unit;

[0017] The decision data determination unit is used to determine whether the decision data at the next moment sent by the fault prediction module meets the decision requirements. If yes, the decision data at the next moment sent by the fault prediction module is input into the main control unit; if no, a signal is sent to the early warning module;

[0018] The main control unit is used to receive a signal sent by the decision data judgment unit and / or the decision data determination unit to control the transformer.

[0019] Preferably, the data acquisition module is also used to obtain the service life and maintenance records of the transformer.

[0020] Preferably, it further comprises an aging assessment module, wherein the aging assessment module comprises a preliminary assessment unit and a correction unit;

[0021] The preliminary evaluation unit is used to evaluate the aging degree of the transformer according to the service life of the transformer and the maintenance record, and determine the preliminary evaluation result of the transformer aging;

[0022] The correction unit is used to correct the preliminary transformer aging assessment result by using the real-time operation data and the real-time perception data to determine the transformer aging result.

[0023] Preferably, the fault judgment module is also used to judge that the state of the transformer at the current moment is normal based on the real-time operation data and the real-time perception data, and further judge the state of the transformer in combination with the transformer aging result. If the state is a fault, it is sent to the early warning module for fault warning; if the state is normal, it is sent to the fault prediction module.

[0024] Preferably, the fault prediction module is also used to predict that the state of the transformer at the next moment is a fault based on the decision data at the next moment, the real-time operation data and the real-time perception data, and further judge the state of the transformer in combination with the transformer aging result; if the state is a fault, it is sent to the early warning module for fault warning; if the state is normal, the decision data at the next moment is sent to the control module, and the control module controls the transformer according to the decision data at the next moment.

[0025] On the other hand, the present invention discloses a method for monitoring the status and early warning of failure of a photovoltaic power station transformer, comprising the following steps:

[0026] Acquire the real-time operation data of the transformer at the current moment, and the real-time perception data collected by the sensor, and output the decision data at the next moment according to the real-time operation data and the real-time perception data;

[0027] Determine the state of the transformer at the current moment according to the real-time operation data and the real-time sensing data, and if the state is a fault, perform a fault warning; if the state is normal, perform a fault prediction;

[0028] According to the decision data at the next moment, the real-time operation data and the real-time perception data, it is predicted whether the state of the transformer at the next moment is a fault. If the state at the next moment is a fault, a fault warning is performed; if the state at the next moment is normal, the transformer is controlled according to the decision data at the next moment.

[0029] Preferably, when it is predicted that the state of the transformer at the next moment is a fault based on the decision data at the next moment, the real-time operation data and the real-time perception data, the decision data at the next moment is adjusted according to the control rules, and the fault prediction is performed again.

[0030] Preferably, the method further comprises:

[0031] Obtaining the service life and maintenance records of the transformer;

[0032] According to the service life of the transformer and the maintenance record, the aging degree of the transformer is evaluated to determine the preliminary evaluation result of the transformer aging;

[0033] Using the real-time operation data and the real-time sensing data, the preliminary transformer aging assessment result is corrected to determine the transformer aging result;

[0034] If the state of the transformer is normal at the current moment according to the real-time operation data and the real-time sensing data, the state of the transformer is further determined in combination with the transformer aging result. If the state is a fault, a fault warning is performed; if the state is normal, a fault prediction is performed;

[0035] When it is predicted that the state of the transformer at the next moment is a fault according to the decision data at the next moment, the real-time operation data and the real-time perception data, the state of the transformer is further judged in combination with the transformer aging result. If the state is a fault, a fault warning is sent; if the state is normal, the transformer is controlled according to the decision data at the next moment.

[0036] It can be seen from the above technical solution that, compared with the prior art, the present invention discloses a photovoltaic power station transformer status monitoring and failure warning system and method, which obtains the real-time operation data of the transformer at the current moment and the real-time perception data collected by the sensor, and uses a preset decision model to calculate the real-time decision data at the next moment. It can not only judge whether the transformer has an operation fault based on the real-time data, but also predict the transformer fault based on the decision data at the next moment; at the same time, it can further judge the transformer fault based on the aging condition of the transformer, thereby improving the accuracy of the transformer fault warning and reducing the missed judgment rate of the transformer fault warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0038] Figure 1 It is a structural schematic diagram of the present invention;

[0039] Figure 2 It is a structural schematic diagram of the control module of the present invention;

[0040] Figure 3 is an aging assessment module of the present invention;

[0041] Figure 4 Flow chart of the early warning method of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] like Figure 1 As shown, the embodiment of the present invention discloses a photovoltaic power station transformer state monitoring and failure warning system, including: a data acquisition module, a control module, a fault judgment module, a fault prediction module, and a warning module;

[0044] The data acquisition module obtains the real-time operation data of the transformer at the current moment, as well as the real-time perception data collected by the sensor, and outputs them to the fault judgment module and the control module; the operation data of the transformer mainly monitors the electrical performance detection data of the transformer (voltage, current, power, etc.) and the transformer identification, and the perception data mainly includes temperature, sound, oil level, oil temperature and oil pressure, etc.

[0045] The control module outputs the decision data for the next moment based on the real-time operation data and real-time perception data;

[0046] The fault judgment module judges the current state of the transformer based on the real-time operation data and real-time perception data. If the state is a fault, it is sent to the early warning module for fault warning; if the state is normal, it is sent to the fault prediction module;

[0047] The fault prediction module predicts whether the state of the transformer at the next moment is a fault based on the decision data, real-time operation data and real-time perception data at the next moment. If the state at the next moment is a fault, it is sent to the early warning module for fault warning; if the state at the next moment is normal, the decision data at the next moment is sent to the control module, and the control module controls the transformer according to the decision data at the next moment.

[0048] The fault prediction module first predicts the operation data and perception data of the next moment based on the decision data, real-time operation data and perception data. Based on the operation data and perception data of the next moment, the transformer fault diagnosis model is used to perform fault diagnosis on the operation data and perception data of the next moment to determine the state of the transformer at the next moment.

[0049] The early warning module issues an early warning based on the judgment results of the fault judgment module and the fault prediction module. The early warning module determines the level of the fault based on the preset value and issues a graded early warning.

[0050] Preferably, it also includes a decision data adjustment module, which is connected to the fault prediction module. When the fault prediction module predicts that the state at the next moment is a fault based on the decision data at the next moment, the decision data at the next moment is adjusted according to the control rules and sent to the fault prediction module for prediction.

[0051] like Figure 2 As shown, the control module includes a decision data generating unit, a main control unit, a decision data judging unit, and a decision data determining unit;

[0052] A decision data generation unit, used to input the real-time operation data and the real-time perception data into the trained decision model and output the decision data at the next moment;

[0053] The decision data judgment unit is used to judge and compare the decision data at the next moment sent by the fault prediction module with the decision data at the next moment output by the decision data generation unit. If the decision data at the next moment sent by the fault prediction module is consistent with the decision data at the next moment output by the decision data generation unit, the decision data at the next moment sent by the fault prediction module is sent to the main control unit; if the decision data at the next moment sent by the fault prediction module is inconsistent with the decision data at the next moment output by the decision data generation unit, the decision data at the next moment sent by the fault prediction module is sent to the decision data determination unit;

[0054] The decision data determination unit is used to determine whether the decision data at the next moment sent by the fault prediction module meets the decision requirements. If yes, the decision data at the next moment sent by the fault prediction module is input into the main control unit; if not, a signal is sent to the early warning module.

[0055] The main control unit is used to receive the signal sent by the decision data judgment unit and / or the decision data determination unit to control the transformer.

[0056] Preferably, the data acquisition module is also used to obtain the service life and maintenance records of the transformer.

[0057] like Figure 3 As shown, the system further includes an aging assessment module, which includes a preliminary assessment unit and a correction unit;

[0058] The preliminary assessment unit is used to assess the aging degree of the transformer according to the service life and maintenance records of the transformer, and determine the preliminary assessment result of the transformer aging;

[0059] The correction unit is used to correct the preliminary evaluation results of transformer aging by using real-time operation data and real-time perception data to determine the transformer aging results.

[0060] Preferably, the fault judgment module is also used to judge whether the state of the transformer at the current moment is normal based on the real-time operation data and the real-time perception data, and then further judge the state of the transformer in combination with the transformer aging result. If the state is a fault, it is sent to the early warning module for fault warning; if the state is normal, it is sent to the fault prediction module.

[0061] Preferably, the fault prediction module is also used to predict that the state of the transformer at the next moment is a fault based on the decision data at the next moment, the real-time operation data and the real-time perception data. Then, the state of the transformer is further judged in combination with the transformer aging result. If the state is a fault, it is sent to the early warning module for a fault warning; if the state is normal, the decision data at the next moment is sent to the control module, and the control module controls the transformer according to the decision data at the next moment.

[0062] On the other hand, the present invention also discloses a method for monitoring the status and early warning of failure of a photovoltaic power station transformer. Figure 4 As shown, the following steps are included:

[0063] Obtain the real-time operation data of the transformer at the current moment, as well as the real-time perception data collected by the sensor, and output the decision data for the next moment based on the real-time operation data and real-time perception data;

[0064] The current state of the transformer is determined based on real-time operation data and real-time perception data. If the state is faulty, a fault warning is issued; if the state is normal, a fault prediction is performed;

[0065] Based on the decision data, real-time operation data and real-time perception data at the next moment, it is predicted whether the state of the transformer at the next moment is a fault. If the state at the next moment is a fault, a fault warning is issued; if the state at the next moment is normal, the transformer is controlled according to the decision data at the next moment.

[0066] Preferably, when the state of the transformer at the next moment is predicted to be a fault based on the decision data at the next moment, the real-time operation data and the real-time perception data, the decision data at the next moment is adjusted according to the control rules, and the fault prediction is performed again.

[0067] Preferably, the method further comprises:

[0068] Obtain the transformer's service life and maintenance records;

[0069] According to the service life and maintenance records of the transformer, the aging degree of the transformer is evaluated and the preliminary evaluation results of the transformer aging are determined;

[0070] Use real-time operation data and real-time perception data to correct the preliminary assessment results of transformer aging and determine the transformer aging results;

[0071] According to the real-time operation data and real-time perception data, the transformer status is judged to be normal at the current moment, and the transformer status is further judged in combination with the transformer aging results. If the status is faulty, a fault warning is performed; if the status is normal, a fault prediction is performed;

[0072] When the state of the transformer at the next moment is predicted to be a fault based on the decision data at the next moment, the real-time operation data and the real-time perception data, the state of the transformer is further judged in combination with the transformer aging result. If the state is a fault, a fault warning is sent; if the state is normal, the transformer is controlled based on the decision data at the next moment.

[0073] Furthermore, when it is judged that the transformer state at the next moment is not faulty according to the adjusted decision data at the next moment, the decision data at the next moment is compared with the decision data at the next moment output after adjustment. If the decision data at the next moment after adjustment is consistent with the decision data at the next moment output for the first time, the transformer operation is controlled according to the decision data at the next moment output for the first time; if they are inconsistent, it is judged whether the decision data at the next moment after adjustment meets the decision requirements. If they meet the requirements, the transformer operation is controlled according to the decision data at the next moment after adjustment; if they do not meet the requirements, an early warning is issued.

[0074] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0075] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A photovoltaic power station transformer status monitoring and failure warning system, It is characterized in that include: Data acquisition module, control module, fault judgment module, fault prediction module, early warning module; The data acquisition module acquires the real-time operation data of the transformer at the current moment and the real-time perception data collected by the sensor, and outputs them to the fault judgment module and the control module; The control module outputs decision data for the next moment according to the real-time operation data and the real-time perception data; The fault judgment module judges the state of the transformer at the current moment according to the real-time operation data and the real-time sensing data, and if the state is a fault, sends it to the early warning module for fault warning; If the state is normal, it is sent to the fault prediction module; The fault prediction module predicts whether the state of the transformer at the next moment is a fault based on the decision data at the next moment, the real-time operation data and the real-time perception data, and if the state at the next moment is a fault, sends it to the early warning module for fault early warning; If the state at the next moment is normal, the control module controls the transformer according to the decision data at the next moment; The early warning module issues an early warning according to the judgment results of the fault judgment module and the fault prediction module; It also includes a decision data adjustment module, which is connected to the fault prediction module and is used to adjust the decision data at the next moment according to the control rule and send it to the fault prediction module for prediction when the fault prediction module predicts that the state at the next moment is a fault according to the decision data at the next moment; The control module includes a decision data generating unit, a main control unit, a decision data judging unit, and a decision data determining unit; The decision data generating unit is used to input the real-time operation data and the real-time perception data into the trained decision model and output the decision data at the next moment; The decision data judging unit is used to judge the decision data at the next moment sent by the fault prediction module and compare it with the decision data at the next moment output by the decision data generating unit. If they are consistent, the decision data at the next moment sent by the fault prediction module is sent to the main control unit; if they are inconsistent, the decision data at the next moment sent by the fault prediction module is sent to the decision data determining unit; The decision data determination unit is used to determine whether the decision data at the next moment sent by the fault prediction module meets the decision requirements. If yes, the decision data at the next moment sent by the fault prediction module is input into the main control unit; if no, a signal is sent to the early warning module; The main control unit is used to receive a signal sent by the decision data judgment unit and / or the decision data determination unit to control the transformer.

2. A photovoltaic power station transformer status monitoring and failure warning system according to claim 1, It is characterized in that The data acquisition module is also used to obtain the service life and maintenance records of the transformer.

3. A photovoltaic power station transformer status monitoring and failure warning system according to claim 2, It is characterized in that Also included is an aging assessment module, the aging assessment module including a preliminary assessment unit and a correction unit; The preliminary evaluation unit is used to evaluate the aging degree of the transformer according to the service life of the transformer and the maintenance record, and determine the preliminary evaluation result of the transformer aging; The correction unit is used to correct the preliminary transformer aging assessment result by using the real-time operation data and the real-time perception data to determine the transformer aging result.

4. A photovoltaic power station transformer status monitoring and failure warning system according to claim 3, It is characterized in that The fault judgment module is also used to judge that the state of the transformer at the current moment is normal according to the real-time operation data and the real-time sensing data, and further judge the state of the transformer in combination with the transformer aging result. If the state is a fault, it is sent to the early warning module for fault warning; If the state is normal, it is sent to the fault prediction module.

5. A photovoltaic power station transformer status monitoring and failure warning system according to claim 3, It is characterized in that The fault prediction module is also used to predict that the state of the transformer at the next moment is a fault according to the decision data at the next moment, the real-time operation data and the real-time perception data, and further judge the state of the transformer in combination with the transformer aging result. If the state is a fault, it is sent to the early warning module for fault early warning; If the state is normal, the decision data of the next moment is sent to the control module, and the control module controls the transformer according to the decision data of the next moment.

6. A photovoltaic power station transformer state monitoring and failure warning method for realizing a photovoltaic power station transformer state monitoring and failure warning system as claimed in any one of claims 1 to 5, It is characterized in that The following steps are involved: Acquire the real-time operation data of the transformer at the current moment, and the real-time perception data collected by the sensor, and output the decision data at the next moment according to the real-time operation data and the real-time perception data; Determine the state of the transformer at the current moment according to the real-time operation data and the real-time sensing data, and if the state is a fault, issue a fault warning; If the state is normal, a fault prediction is performed; Predicting whether the state of the transformer at the next moment is a fault according to the decision data at the next moment, the real-time operation data and the real-time perception data, and issuing a fault warning if the state at the next moment is a fault; If the state at the next moment is normal, the transformer is controlled according to the decision data at the next moment.

7. A photovoltaic power station transformer state monitoring and failure warning method according to claim 6, It is characterized in that When it is predicted that the state of the transformer at the next moment is a fault according to the decision data at the next moment, the real-time operation data and the real-time perception data, the decision data at the next moment is adjusted according to the control rule, and the fault prediction is performed again.

8. A photovoltaic power station transformer state monitoring and failure warning method according to claim 6, It is characterized in that The method further comprises: Obtaining the service life and maintenance records of the transformer; According to the service life of the transformer and the maintenance record, the aging degree of the transformer is evaluated to determine the preliminary evaluation result of the transformer aging; Using the real-time operation data and the real-time sensing data, the preliminary transformer aging assessment result is corrected to determine the transformer aging result; If the state of the transformer is normal at the current moment according to the real-time operation data and the real-time sensing data, the state of the transformer is further determined in combination with the transformer aging result. If the state is a fault, a fault warning is performed; if the state is normal, a fault prediction is performed; When it is predicted that the state of the transformer at the next moment is a fault according to the decision data at the next moment, the real-time operation data and the real-time perception data, the state of the transformer is further judged in combination with the transformer aging result. If the state is a fault, a fault warning is sent; if the state is normal, the transformer is controlled according to the decision data at the next moment.

Images