Power fault diagnosis method and device based on artificial intelligence, and storage medium

Abstract

The embodiment of the invention relates to the technical field of electrical engineering, and discloses a power fault diagnosis method and device based on artificial intelligence, and a storage medium, and the method comprises the steps: obtaining the state data of a first transformer and a second transformer in a first preset time period according to a power fault diagnosis instruction, and obtaining a first state data set; inputting the first state data set into a fault diagnosis model to obtain a first linkage index; under the condition that the first linkage index is smaller than a preset value, performing power transformation control processing on the first transformer, and obtaining state data of the first transformer and the second transformer in a second preset time period to obtain a second state data set; inputting the second state data set into the fault diagnosis model to obtain a second linkage index; and finally, performing power fault diagnosis according to the first linkage index and the second linkage index. According to the invention, accurate fault positioning is realized through the synergistic effect of two times of state data acquisition and active intervention, and the efficiency and accuracy of power fault detection are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical engineering, and particularly relates to a power fault diagnosis method, device and storage medium based on artificial intelligence. Background Art

[0002] In a modern power system, as a key power transmission and distribution link, the stable operation of the step-down power supply network is crucial for ensuring the reliability and continuity of power supply. The step-down power supply network usually includes multiple transformers and various load devices.

[0003] Most traditional power fault diagnosis methods rely on manual experience and simple electrical parameter monitoring. When facing a complex step-down power supply network, manual inspection is not only inefficient but also difficult to comprehensively and timely detect potential fault hazards. Summary of the Invention

[0004] The main objective of the present invention is to provide a power fault diagnosis method, device and storage medium based on artificial intelligence, aiming to solve the technical problem of low efficiency of manual inspection in the prior art.

[0005] To achieve the above objective, in a first aspect, an embodiment of the present application provides a power fault diagnosis method based on artificial intelligence, which is applied to a step-down power supply network. The step-down power supply network includes a first transformer, a second transformer and load devices. The method includes:

[0006] Obtain a power fault diagnosis instruction;

[0007] According to the power fault diagnosis instruction, obtain the state data of the first transformer and the second transformer within a first preset time period to obtain a first state data set;

[0008] Input the first state data set into a fault diagnosis model to obtain a first linkage index, where the first linkage index represents the influence degree of the first transformer on the second transformer;

[0009] In the case where the absolute value of the first linkage index is less than a preset value, perform substation control processing on the first transformer, and obtain the state data of the first transformer and the second transformer within a second preset time period to obtain a second state data set, where the duration corresponding to the second preset time period is greater than the duration corresponding to the first preset time period;

[0010] Input the second state data set into the fault diagnosis model to obtain a second linkage index, where the second linkage index represents the influence degree of the first transformer on the second transformer after substation processing;

[0011] Perform power fault diagnosis according to the first linkage index and the second linkage index.

[0012] In a possible implementation, the power conversion control process for the first transformer includes:

[0013] Adjust the output voltage of the first transformer and control the cooling system of the first transformer to regulate the flow rate of the cooling medium to maintain the operating temperature of the first transformer unchanged.

[0014] In a possible implementation, adjusting the output voltage of the first transformer and controlling the cooling system of the first transformer includes:

[0015] Adjust the output voltage of the first transformer at a preset frequency such that the voltage fluctuation of the first transformer is greater than the voltage fluctuation in the initial state;

[0016] Obtain the historical temperature change of the first transformer under the condition of the output voltage fluctuation;

[0017] Control the cooling system of the first transformer according to the historical temperature change to regulate the flow rate of the cooling medium.

[0018] In a possible implementation, controlling the cooling system of the first transformer according to the historical temperature change includes:

[0019] When the historical temperature change indicates that the temperature of the first transformer rises, increase the flow rate of the cooling medium according to the temperature rise rate to regulate the flow rate of the cooling medium.

[0020] In a possible implementation, obtaining the state data of the first transformer and the second transformer within a first preset time period according to the power failure diagnosis instruction to obtain a first state data set includes:

[0021] Obtain the output voltage and / or current data of the first transformer within a first preset time period to obtain a first state main data set, where the first state main data set characterizes the fluctuation change of the output voltage and / or current of the first transformer within the first preset time period;

[0022] Obtain the temperature data of the second transformer within a first preset time period to obtain a first state secondary data set, where the first state secondary data set characterizes the temperature fluctuation change of the second transformer within the first preset time period.

[0023] In a possible implementation, inputting the first state data set into a fault diagnosis model to obtain a first linkage index includes:

[0024] Determine the fluctuation coefficients of the voltage and / or current of the first transformer in each time window according to the first state main data set to obtain a first main fluctuation coefficient set;

[0025] Determine the fluctuation coefficient of the temperature of the second transformer in each time window according to the first-state secondary data set to obtain the first fluctuation coefficient set;

[0026] Input the first main fluctuation coefficient set and the first fluctuation coefficient set into the linkage coefficient calculation sub-model in the fault diagnosis model to obtain the first linkage index, where the linkage coefficient calculation sub-model satisfies the following expression:

[0027]

[0028] where K1 is the first linkage index; ΔVt is the voltage / current fluctuation coefficient of the first transformer in time window t, that is, the first main fluctuation coefficient set; ΔTt+τ is the temperature fluctuation coefficient of the second transformer in time window t+τ, that is, the first fluctuation coefficient set; τ is a preset delay time parameter used to characterize the lag effect of the fluctuation of the first transformer on the second transformer, and T is the total number of time windows within the first preset time period.

[0029] In a possible implementation manner, the method further includes:

[0030] Obtain the ambient temperature of the variable voltage power supply network in real time;

[0031] In the case where the ambient temperature of the variable voltage power supply network is greater than or equal to the temperature threshold, correct the preset delay time parameter τ according to the electrical distance between the first transformer and the second transformer.

[0032] In a possible implementation manner, the performing power fault diagnosis according to the first linkage index and the second linkage index includes:

[0033] Determine that the second linkage index is greater than the first linkage index, and determine that there is a power fault in the first transformer;

[0034] Determine that the second linkage index is less than or equal to the first linkage index, and determine that there is a power fault in the second transformer.

[0035] In a second aspect, an embodiment of the present application further provides a fault diagnosis device, including:

[0036] A first acquisition module, configured to acquire a power fault diagnosis instruction;

[0037] A second acquisition module, configured to acquire the state data of the first transformer and the second transformer within the first preset time period to obtain a first state data set; and acquire the state data of the first transformer and the second transformer within the second preset time period to obtain a second state data set;

[0038] An input calculation module for inputting the first state data set into a fault diagnosis model to obtain a first linkage index; and inputting the second state data set into the fault diagnosis model to obtain a second linkage index;

[0039] A fault diagnosis module for performing power fault diagnosis based on the first linkage index and the second linkage index.

[0040] In a third aspect, an embodiment of the present application also provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, it runs the steps of the method described in the first aspect.

[0041] Different from the prior art, a power fault diagnosis method based on artificial intelligence provided by an embodiment of the present application first obtains the state data of a first transformer and a second transformer within a first preset time period according to a power fault diagnosis instruction to obtain a first state data set; then inputs the first state data set into a fault diagnosis model to obtain a first linkage index; when the first linkage index is less than a preset value, performs substation control processing on the first transformer, and obtains the state data of the first transformer and the second transformer within a second preset time period to obtain a second state data set; then inputs the second state data set into the fault diagnosis model to obtain a second linkage index; and finally performs power fault diagnosis based on the first linkage index and the second linkage index. That is, the present application realizes accurate fault location through the synergistic effect of two state data acquisitions and active interventions, greatly improving the efficiency and accuracy of power fault detection. Description of the Drawings

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on the structures shown in these drawings.

[0043] Figure 1 It is a schematic application diagram of a power fault diagnosis method based on artificial intelligence in some embodiments of the present application;

[0044] Figure 2 It is a schematic flow diagram of a power fault diagnosis method based on artificial intelligence in some embodiments of the present application;

[0045] Figure 3 It is a schematic flow diagram of step S200 of a power fault diagnosis method based on artificial intelligence in some embodiments of the present application;

[0046] Figure 4 It is a schematic flow diagram of step S300 of a power fault diagnosis method based on artificial intelligence in some embodiments of the present application;

[0047] Figure 5 This is a schematic diagram of the hardware structure of the fault diagnosis device in some embodiments of the present application.

[0048] The implementation, functional features, and advantages of the present invention will be further described in conjunction with the embodiments and with reference to the accompanying drawings. Specific embodiments

[0049] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the scope of protection of the present invention.

[0050] It should be noted that all directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly.

[0051] In addition, the descriptions involving "first", "second", etc. in the present invention are only for descriptive purposes, and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, "and / or" throughout the text includes three scenarios. Taking A and / or B as an example, it includes the technical solution of A, the technical solution of B, and the technical solution that both A and B are satisfied at the same time. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the fact that those of ordinary skill in the art can implement it. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0052] In modern power systems, the step - down power supply network, as a key link for power transmission and distribution, its stable operation is crucial for ensuring the reliability and continuity of power supply. The step - down power supply network usually includes multiple transformers and various load devices.

[0053] Traditional power fault diagnosis methods mostly rely on manual experience and simple electrical parameter monitoring. When facing a complex step - down power supply network, manual inspection is not only inefficient but also difficult to comprehensively and timely detect potential fault hazards.

[0054] As Figure 1 shown, the step - down power supply network in the present application includes a first transformer 100, a second transformer 200, and multiple load devices 300.

[0055] Among them, the first transformer 100 is responsible for converting the low-voltage power of the power station into high-voltage power to reduce the loss of power transmission, and the second transformer 200 is responsible for converting the high-voltage power into low-voltage power for the load device 300 to use.

[0056] It can be understood that since the first transformer 100 and the second transformer 200 are connected to the same power supply network, there is an interaction between the first transformer 100 and the second transformer 200. For example, when the output voltage or output current of the first transformer 100 changes, the second transformer 200 will also have a relative fluctuation. However, under normal circumstances, the second transformer 200 can cope with this change and output a relatively stable voltage or current for the load device 300 to use. In the case of an abnormal power supply network, the voltage or current output by the second transformer 200 is unstable and cannot meet the usage requirements of the load device 300. At this time, it is necessary to diagnose the power failure of the transformer power supply network to quickly locate the fault point, so as to provide a basis for maintenance for the staff and improve the maintenance efficiency of power failures.

[0057] In view of the above problems, the present application proposes an artificial intelligence-based power failure diagnosis method, as Figures 1 - 4 shown. The following takes the power failure diagnosis system executing the artificial intelligence-based power failure diagnosis method as an example for illustration. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from here. Please refer to the appendix Figure 2 . The method includes the following steps S100-step S600:

[0058] Step S100, obtain a power failure diagnosis instruction;

[0059] In the embodiment of the present application, the power failure diagnosis instruction can be automatically triggered by the system. For example, when the load device 300 receives abnormal voltage or the output voltage of the second transformer 200 is abnormal, the power failure diagnosis instruction is automatically triggered.

[0060] In other embodiments, the power failure diagnosis instruction can also be manually triggered by the management personnel. For example, when the power grid status is abnormal, the staff manually triggers a power failure diagnosis request to quickly locate the fault point.

[0061] Step S200, obtain the status data of the first transformer and the second transformer within a first preset time period according to the power failure diagnosis instruction to obtain a first status data set;

[0062] The status data of the first transformer and the second transformer may refer to electrical parameter data such as output voltage, current, or output power, or may refer to temperature parameter data such as operating temperature and heat dissipation efficiency.

[0063] It should be noted that since the electrical adjustment range of the transformer is generally fixed; that is to say, when the voltage or current of the first transformer fluctuates greatly, the output voltage of the second transformer may be abnormal even without a fault. Therefore, there are certain limitations in using the method of detecting whether the output voltage is normal to determine the normality of the second transformer.

[0064] Based on this, in the embodiments of the present application, the electrical parameters of the first transformer and the temperature parameters of the second transformer are used to evaluate the influence degree between the two, that is, by constructing a mapping relationship of "electrical excitation - thermal response" to achieve power fault diagnosis.

[0065] Therefore, in one embodiment, the step S200: obtaining the status data of the first transformer and the second transformer within a first preset time period according to the power fault diagnosis instruction to obtain a first status data set, includes:

[0066] S210. Obtaining the output voltage and / or current data of the first transformer within a first preset time period to obtain a first status main data set, where the first status main data set characterizes the fluctuation change of the output voltage and / or current of the first transformer within the first preset time period;

[0067] S220. Obtaining the temperature data of the second transformer within a first preset time period to obtain a first status secondary data set, where the first status secondary data set characterizes the temperature fluctuation change of the second transformer within the first preset time period.

[0068] Specifically, after the system receives the power fault diagnosis instruction, it obtains the output voltage and / or current data of the first transformer within a first preset time period to obtain a first status main data set. For example, it obtains the output voltage data of the first transformer within 2 minutes after receiving the power fault diagnosis instruction, so as to form a data set characterizing the fluctuation change of the output voltage of the first transformer within the first preset time period. This first status main data set can be represented by a time series curve graph.

[0069] Then, it obtains the temperature data of the second transformer within a first preset time period to obtain a first status secondary data set. For example, it can also obtain the temperature data of the second transformer within 2 minutes after receiving the power fault diagnosis instruction, so as to form a data set characterizing the temperature fluctuation change of the second transformer within the first preset time period. This first status secondary data set can also be represented by a time series curve graph.

[0070] In the embodiments of the present application, the electrical data (voltage and / or current) of the first transformer and the temperature data of the second transformer are used to provide accurate data support for subsequent calculation of the linkage index. Compared with the prior art where the linkage index is calculated solely based on electrical data, the above-mentioned limitations can be eliminated, thereby improving the efficiency and accuracy of power fault diagnosis.

[0071] Step S300: Input the first state data set into the fault diagnosis model to obtain a first linkage index, where the first linkage index represents the influence degree of the first transformer on the second transformer;

[0072] In one embodiment, step S300: Inputting the first state data set into the fault diagnosis model to obtain a first linkage index includes:

[0073] S310: Determine the fluctuation coefficients of the voltage and / or current of the first transformer in each time window according to the first main state data set to obtain a first main fluctuation coefficient set;

[0074] S320: Determine the fluctuation coefficients of the temperature of the second transformer in each time window according to the first secondary state data set to obtain a first secondary fluctuation coefficient set;

[0075] S330: Input the first main fluctuation coefficient set and the first secondary fluctuation coefficient set into the linkage coefficient calculation sub-model in the fault diagnosis model to obtain a first linkage index, where the linkage coefficient calculation sub-model satisfies the following expression:

[0076]

[0077] where, K1 is the first linkage index; ΔV t is the voltage / current fluctuation coefficient of the first transformer at time window t, that is, the first main fluctuation coefficient set; ΔT t+τ is the temperature fluctuation coefficient of the second transformer at time window t + τ, that is, the first secondary fluctuation coefficient set; τ is a preset delay time parameter used to represent the lag effect of the fluctuation of the first transformer on the second transformer, and T is the total number of time windows within the first preset time period.

[0078] Specifically, in the embodiments of the present application, first, the fluctuation coefficients of the voltage and / or current of the first transformer in each time window are determined according to the first main state data set to obtain a first main fluctuation coefficient set. For example, the first preset time period can be divided into 5 time windows, and the fluctuation coefficients of the first transformer in the above 5 time windows are determined according to the first main state data set (the fluctuation coefficients can be equivalently obtained using the change rate of the front and back data), thereby obtaining a first main fluctuation coefficient set containing 5 fluctuation coefficients. It can be understood that the first main fluctuation coefficient set is the fluctuation coefficients of the voltage and / or current of the first transformer in different time windows.

[0079] Then, according to the first - state secondary data set, the fluctuation coefficient of the temperature of the second transformer in each time window is determined to obtain the first fluctuation coefficient set. For example, the first preset time period can also be divided into 5 time windows, and the fluctuation coefficient of the second transformer in the above 5 time windows is determined according to the first - state secondary data set, so as to obtain the first fluctuation coefficient set containing 5 fluctuation coefficients. It can be understood that the first fluctuation coefficient set is the fluctuation coefficient of the temperature of the second transformer in different time windows.

[0080] Finally, the first main fluctuation coefficient set and the first fluctuation coefficient set are input into the linkage coefficient calculation sub - model in the fault diagnosis model to obtain the first linkage index.

[0081] It should be noted that the linkage coefficient calculation sub - model of the embodiment of the present application quantifies the conduction intensity of the fluctuation of the first transformer on the temperature change of the second transformer by calculating the normalized covariance of dynamic time alignment, which can make full use of the data in different time windows and improve the accuracy of the calculation of the linkage index. And considering the delay of the temperature response of the second transformer, the accuracy of the temperature data is improved, and further the accuracy of the calculation of the linkage index is improved. Among them, the preset delay time parameter τ can be 2S or 3S, etc.

[0082] Specifically, when K1 = 1, it indicates that the fluctuation of the electrical parameters of the first transformer and the temperature change of the second transformer are completely positively correlated, and the conduction intensity is the largest. When K1 = 0, it indicates that the fluctuation of the electrical parameters of the first transformer and the temperature change of the second transformer have no significant correlation, and the fluctuation conduction can be ignored. When K1 = - 1, it indicates that the fluctuation of the electrical parameters of the first transformer and the temperature change of the second transformer are completely negatively correlated.

[0083] Exemplarily, when the absolute value of K1 is greater than or equal to 0.7, it indicates that the fluctuation of the electrical parameters of the first transformer and the temperature change of the second transformer are strongly correlated. When the absolute value of K1 is less than 0.3, it indicates that the fluctuation of the electrical parameters of the first transformer and the temperature change of the second transformer are weakly correlated.

[0084] Based on the above - mentioned embodiment, if it is detected that the ambient temperature is high, in a high - temperature environment and under the influence of the self - heating of the second transformer, the accuracy of the temperature detection of the second transformer may be affected by the ambient temperature, that is, the accuracy of the temperature data of the second transformer is low. Therefore, in order to improve the accuracy of the calculation of the first linkage index, in one embodiment, the preset delay time parameter τ can be corrected according to the electrical distance between the first transformer and the second transformer, so as to prevent the accuracy of multiple parameters from being affected and resulting in inaccurate calculation results. That is to say, in the embodiment of the present application, when the accuracy of the temperature data is affected, the accuracy of other data (such as the delay time parameter τ) is ensured as much as possible to improve the accuracy of the calculation result.

[0085] Specifically, when the actual electrical distance between the first transformer and the second transformer is less than the reference value, the preset delay time parameter τ is appropriately reduced. When the actual electrical distance between the first transformer and the second transformer is greater than the reference value, the preset delay time parameter τ is appropriately increased.

[0086] Step S400: When the absolute value of the first linkage index is less than the preset value, perform power conversion control processing on the first transformer, and obtain the state data of the first transformer and the second transformer within a second preset time period to obtain a second state data set, where the duration corresponding to the second preset time period is greater than the duration corresponding to the first preset time period;

[0087] It can be understood that both the first transformer and the second transformer are operating normally. When the voltage or current of the first transformer fluctuates abnormally, in order to ensure the stability of the output voltage or current, the second transformer will inevitably increase its internal loss, so the heat generation of the second transformer will increase; at this time, it can be understood that there is a relatively high correlation strength between the first transformer and the second transformer, that is, the influence degree of the first transformer on the second transformer is relatively large. When the absolute value of the first linkage index is small, such as less than the preset value, it means that the influence degree of the first transformer on the second transformer is small, that is, the two are weakly correlated. In this case, it may be that the first transformer fails, or it may be that the second transformer fails.

[0088] For example, there may be the following situations: (1) The first transformer fails: If a fault occurs inside the first transformer (such as inter-turn short circuit), its electrical parameter fluctuations may be abnormal, but since the fault may not directly affect the temperature of the second transformer (for example, in the early stage of the fault or the heat conduction path is blocked), the linkage index is relatively low. (2) The second transformer fails: A fault in the second transformer itself (such as a cooling system failure) may cause abnormal temperature, but this temperature change has nothing to do with the electrical parameter fluctuations of the first transformer, so the linkage index will also be relatively low.

[0089] In this way, when the absolute value of the first linkage index is less than the preset value, the embodiment of the present application further adopts an active interference scheme, such as performing power conversion control processing on the first transformer, and then obtaining the state data of the first transformer and the second transformer within a second preset time period to obtain a second state data set. And the duration corresponding to the second preset time period is greater than that of the first preset time period. It shows that after active interference, the system will collect data for a longer time to capture possible delayed responses or cumulative effects, so as to further improve the accuracy of the data.

[0090] In one embodiment, the power conversion control process for the first transformer includes: adjusting the output voltage of the first transformer and controlling the cooling system of the first transformer to regulate the flow rate of the cooling medium so as to keep the operating temperature of the first transformer unchanged.

[0091] Specifically, to adjust the output voltage of the first transformer and control the cooling system of the first transformer, the output voltage of the first transformer can be adjusted at a preset frequency first so that the voltage fluctuation of the first transformer is greater than the voltage fluctuation in the initial state; then the historical temperature change of the first transformer under the condition of the output voltage fluctuation is obtained; finally, the cooling system of the first transformer is controlled according to the historical temperature change to regulate the flow rate of the cooling medium. For example, after the power conversion control of the first transformer, when the output voltage fluctuation range is within a certain range, the historical temperature change under this voltage fluctuation range is queried. When the historical temperature change indicates that the temperature of the first transformer rises, the flow rate of the cooling medium is adjusted according to the temperature rise rate, that is, the flow rate of the cooling medium is increased to regulate the flow rate of the cooling medium. More specifically, if the temperature rise rate is faster, the flow rate of the cooling medium is adjusted faster, so as to ensure that the operating temperature of the first transformer remains unchanged when the voltage fluctuates. In this way, the temperature of the second transformer can be avoided from being affected by the temperature of the first transformer, and only the influence degree between the temperature of the second transformer being affected by the electrical parameters of the first transformer is evaluated.

[0092] In this way, in the embodiment of the present application, by isolating the temperature influence, the temperature change of the second transformer more directly reflects the change of the electrical parameters of the first transformer, so that it is easier to identify faults.

[0093] In other embodiments, a pseudo-random binary sequence (PRBS) can also be used to modulate the output voltage of the first transformer to generate a step disturbance signal of ±5% of the rated value; then the flow rate of the cooling medium is adjusted in real time through a PID controller to ensure that the winding temperature of the first transformer is stable within the range of ±0.5°C of the preset reference value, so as to keep the operating temperature of the first transformer basically unchanged when the voltage fluctuates.

[0094] Step S500: Input the second state data set into the fault diagnosis model to obtain a second linkage index, where the second linkage index represents the influence degree of the first transformer on the second transformer after the power conversion process;

[0095] Specifically, after the active interference control is performed on the first transformer and the second state data set is obtained, the second state data set can also be input into the fault diagnosis model to obtain the second linkage index. The calculation process of the second linkage index is similar to that of the first linkage index, which will not be elaborated here.

[0096] Step S600: Perform power fault diagnosis according to the first linkage index and the second linkage index.

[0097] After calculating the first linkage index and the second linkage index, power fault diagnosis can be further performed based on the first linkage index and the second linkage index. If the second linkage index is greater than the first linkage index, it indicates that after active interference, the influence of the first transformer on the second transformer is enhanced. This may be because there is a fault in the first transformer (such as inter-turn short circuit). After adjusting its output voltage, the fault characteristics become more obvious, resulting in an enhanced correlation between the temperature change of the second transformer and the electrical fluctuation of the first transformer. At this time, it is determined that there is a power fault in the first transformer. If the second linkage index is less than or equal to the first linkage index, it indicates that after active interference, the influence of the first transformer on the second transformer is not enhanced, or even weakened. This may be because there is a fault in the second transformer itself (such as a cooling system failure), and its temperature change is mainly caused by its own fault and has nothing to do with the electrical fluctuation of the first transformer. It is determined that there is a power fault in the second transformer.

[0098] Based on this, a power fault diagnosis method based on artificial intelligence provided by an embodiment of the present application first obtains the state data of the first transformer and the second transformer within a first preset time period according to a power fault diagnosis instruction to obtain a first state data set; then inputs the first state data set into a fault diagnosis model to obtain a first linkage index; in the case where the first linkage index is less than a preset value, performs a power conversion control process on the first transformer, and obtains the state data of the first transformer and the second transformer within a second preset time period to obtain a second state data set; then inputs the second state data set into the fault diagnosis model to obtain a second linkage index; and finally performs power fault diagnosis according to the first linkage index and the second linkage index. That is, the present application realizes accurate fault location through the synergistic effect of two state data acquisitions and active interventions, greatly improving the efficiency and accuracy of power fault detection.

[0099] Please refer to the appendix Figure 5 , Figure 5 which is a schematic hardware structure diagram of a fault diagnosis device provided by some embodiments of the present application. An embodiment of the present application also provides a fault diagnosis device, which includes: a first acquisition module 1000 for acquiring a power fault diagnosis instruction; a second acquisition module 2000 for acquiring the state data of the first transformer and the second transformer within a first preset time period to obtain a first state data set; and acquiring the state data of the first transformer and the second transformer within a second preset time period to obtain a second state data set; an input calculation module 3000 for inputting the first state data set into a fault diagnosis model to obtain a first linkage index; and inputting the second state data set into the fault diagnosis model to obtain a second linkage index; a fault diagnosis module 4000 for performing power fault diagnosis according to the first linkage index and the second linkage index.

[0100] An embodiment of the present application also provides a power failure diagnosis system, which includes a memory 400 and a processor 500. Among them, the memory 400 is used to store program codes, and the processor 500 is used to call the program codes to execute the method described above.

[0101] Among them, the processor 500 is used to provide computing and control capabilities to control the power failure diagnosis system to perform corresponding tasks. For example, the processor 500 controls the power failure diagnosis system to execute the power failure diagnosis method based on artificial intelligence in any of the above method embodiments. The method includes: obtaining a power failure diagnosis instruction; obtaining state data of the first transformer and the second transformer within a first preset time period according to the power failure diagnosis instruction to obtain a first state data set; inputting the first state data set into a fault diagnosis model to obtain a first linkage index, where the first linkage index represents the influence degree of the first transformer on the second transformer; in the case where the first linkage index is less than a preset value, performing substation control processing on the first transformer, and obtaining state data of the first transformer and the second transformer within a second preset time period to obtain a second state data set, where the duration corresponding to the second preset time period is greater than the duration corresponding to the first preset time period; inputting the second state data set into the fault diagnosis model to obtain a second linkage index, where the second linkage index represents the influence degree of the first transformer on the second transformer after the substation processing; and performing power failure diagnosis according to the first linkage index and the second linkage index.

[0102] The processor 500 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a hardware chip, or any combination thereof; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The above PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0103] The memory 400, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the artificial intelligence-based power fault diagnosis method in the embodiments of the present application. By running the non-transitory software programs, instructions, and modules stored in the memory 400, the processor 500 can implement the artificial intelligence-based power fault diagnosis method in any of the above method embodiments.

[0104] Specifically, the memory 400 may include a volatile memory (VM), such as a random access memory (RAM); the memory 400 may also include a non-volatile memory (NVM), such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD), or other non-transitory solid-state storage devices; the memory 400 may further include a combination of the above types of memories.

[0105] In summary, the power fault diagnosis system of the present application adopts the technical solution of any one of the above embodiments of the artificial intelligence-based power fault diagnosis method. Therefore, it at least has the beneficial effects brought by the technical solutions of the above embodiments, which will not be elaborated here one by one.

[0106] The embodiments of the present application also provide a computer-readable storage medium, such as a memory including program code, and the above program code can be executed by a processor to complete the artificial intelligence-based power fault diagnosis method in the above embodiments. For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CDROM), a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0107] The embodiments of the present application also provide a computer program product, which includes one or more pieces of program code, and the program code is stored in a computer-readable storage medium. The processor of the power fault diagnosis system reads the program code from the computer-readable storage medium, and the processor executes the program code to complete the steps of the artificial intelligence-based power fault diagnosis method provided in the above embodiments.

[0108] Those of ordinary skill in the art can understand that all or part of the steps to implement the above embodiments can be completed by hardware, or can be completed by hardware related to program code. The program can be stored in a computer-readable storage medium, and the storage medium mentioned above can be a read-only memory, a magnetic disk, an optical disk, etc.

[0109] It should be noted that the device embodiments described above are only illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0110] Through the description of the above embodiments, those of ordinary skill in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware. Those of ordinary skill in the art can understand that all or part of the processes in the above embodiments of the method can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above embodiments of the methods. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0111] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structural transformation made by using the description and drawings of the present invention under the inventive concept of the present invention, or direct / indirect application in other related technical fields, is included in the patent protection scope of the present invention.

Claims

1. A power fault diagnosis method based on artificial intelligence, characterized in that: Applied to a transformer power supply network, the transformer power supply network includes a first transformer, a second transformer and a load device, and the method includes: Get power fault diagnosis instructions; Acquire the state data of the first transformer and the second transformer within a first preset time period according to the power fault diagnosis instruction to obtain a first state data set; Inputting the first state data set into a fault diagnosis model to obtain a first linkage index, where the first linkage index represents the degree of influence of the first transformer on the second transformer; When the absolute value of the first linkage index is less than a preset value, the first transformer is subjected to power transformation control processing, and the state data of the first transformer and the second transformer in a second preset time period are obtained to obtain a second state data set, wherein the duration corresponding to the second preset time period is greater than the duration corresponding to the first preset time period; Inputting the second state data set into a fault diagnosis model to obtain a second linkage index, wherein the second linkage index represents the degree of influence of the first transformer on the second transformer after the power transformation process; Power fault diagnosis is performed according to the first linkage index and the second linkage index.

2. The power fault diagnosis method based on artificial intelligence according to claim 1, characterized in that: The performing power transformation control processing on the first transformer includes: The output voltage of the first transformer is adjusted, and the cooling system of the first transformer is controlled to adjust the flow rate of the cooling medium to maintain the operating temperature of the first transformer unchanged.

3. The power fault diagnosis method based on artificial intelligence as claimed in claim 2, characterized in that: The step of adjusting the output voltage of the first transformer and controlling the cooling system of the first transformer includes: adjusting the output voltage of the first transformer at a preset frequency so that the output voltage fluctuation of the first transformer is greater than the voltage fluctuation in an initial state; Obtaining historical temperature changes of the first transformer under the condition of output voltage fluctuations; The cooling system of the first transformer is controlled according to the historical temperature change to adjust the flow rate of the cooling medium.

4. The power fault diagnosis method based on artificial intelligence as claimed in claim 3 is characterized in that: The step of controlling the cooling system of the first transformer according to the historical temperature change comprises: When the historical temperature change indicates that the temperature of the first transformer increases, the flow rate of the cooling medium is increased according to the temperature rise rate to adjust the flow rate of the cooling medium.

5. The power fault diagnosis method based on artificial intelligence according to claim 1, characterized in that: The step of acquiring the status data of the first transformer and the second transformer within a first preset time period according to the power fault diagnosis instruction to obtain a first status data set includes: Acquire output voltage and / or current data of the first transformer in a first preset time period to obtain a first state main data set, wherein the first state main data set represents fluctuations and changes in output voltage and / or current of the first transformer in the first preset time period; The temperature data of the second transformer in a first preset time period is acquired to obtain a first state sub-data set, wherein the first state sub-data set represents the temperature fluctuation change of the second transformer in the first preset time period.

6. The power fault diagnosis method based on artificial intelligence according to claim 5, characterized in that: The step of inputting the first state data set into a fault diagnosis model to obtain a first linkage index includes: Determine the fluctuation coefficient of the voltage and / or current of the first transformer in each time window according to the first state main data set to obtain a first main fluctuation coefficient set; Determine the fluctuation coefficient of the temperature of the second transformer in each time window according to the first state secondary data set to obtain a first fluctuation coefficient set; The first main fluctuation coefficient set and the first fluctuation coefficient set are input into the linkage coefficient calculation submodel in the fault diagnosis model to obtain a first linkage index, wherein the linkage coefficient calculation submodel satisfies the following expression: Where K1 is the first linkage index; ΔV t is the voltage / current fluctuation coefficient of the first transformer in the time window t, i.e., the first main fluctuation coefficient set; ΔT t+T is the temperature fluctuation coefficient of the second transformer in the time window t+T, that is, the first fluctuation coefficient set; τ is a preset delay time parameter, which is used to characterize the lag effect of the first transformer fluctuation on the second transformer, and T is the total number of time windows in the first preset time period.

7. The power fault diagnosis method based on artificial intelligence according to claim 6, characterized in that: The method further comprises: Obtain the ambient temperature of the transformer power supply network in real time; When the ambient temperature of the transformer power supply network is greater than or equal to a temperature threshold, the preset delay time parameter τ is corrected according to the electrical distance between the first transformer and the second transformer.

8. The power fault diagnosis method based on artificial intelligence according to claim 1, characterized in that: The performing power fault diagnosis according to the first linkage index and the second linkage index includes: Determining that the second linkage index is greater than the first linkage index, and determining that a power fault exists in the first transformer; It is determined that the second linkage index is less than or equal to the first linkage index, and it is determined that a power fault exists in the second transformer.

9. A fault diagnosis device, characterized in that: include: A first acquisition module, used for acquiring a power fault diagnosis instruction; A second acquisition module is used to acquire the status data of the first transformer and the second transformer within a first preset time period to obtain a first status data set; and acquire the status data of the first transformer and the second transformer within a second preset time period to obtain a second status data set; An input calculation module, used for inputting the first state data set into the fault diagnosis model to obtain a first linkage index; and inputting the second state data set into the fault diagnosis model to obtain a second linkage index; The fault diagnosis module is used to perform power fault diagnosis according to the first linkage index and the second linkage index.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are executed.

Images