Direct current transmission system voltage measurement anomaly detection method and device, computer equipment, storage medium and program product

Abstract

The application relates to a direct current power transmission system voltage measurement anomaly detection method and device, computer equipment, a storage medium and a program product. The method comprises the following steps: acquiring a first operation parameter of a to-be-detected converter and a second operation parameter of a target converter, the target converter being a converter on the same pole and on the same side as the to-be-detected converter; inputting the first operation parameter and the second operation parameter into a preselected trained compensation model of the to-be-detected converter to obtain a compensation voltage output by the compensation model of the to-be-detected converter; obtaining a theoretical voltage according to the first operation parameter and a direct current voltage function, and obtaining a predicted voltage of the to-be-detected converter according to the compensation voltage and the theoretical voltage; and obtaining a detection result of the to-be-detected converter according to the predicted voltage and a measured voltage of the to-be-detected converter measured by a voltage sensor. The method can improve the voltage measurement anomaly detection precision.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of high-voltage direct current transmission, and particularly relates to a DC transmission system voltage measurement anomaly detection method and device, computer equipment, a storage medium and a program product. BACKGROUND

[0002] High-voltage direct current transmission has been applied more and more widely due to its low line cost, small transmission loss and flexible regulation in long-distance transmission scenarios. The operating voltage of a long-distance direct current transmission system is generally ±500 kV or ±800 kV, and the control system cannot be directly connected to high voltage. The primary direct current voltage must be collected and converted by a measurement device before it can be used as an input signal of the control system. Voltage measurement anomalies can cause great disturbance to the normal operation of the direct current transmission system, and in severe cases, the protection action of the direct current transmission system can cause emergency shutdown.

[0003] In the traditional technology, the voltage measurement anomaly of the direct current output system is detected by comparison method, data analysis method or theoretical calculation method, but all of them have the problem of low detection accuracy. SUMMARY

[0004] Therefore, it is necessary to provide a DC transmission system voltage measurement anomaly detection method, device, computer equipment, storage medium and program product capable of improving the voltage measurement anomaly detection accuracy in view of the above technical problems.

[0005] In a first aspect, the present application provides a DC transmission system voltage measurement anomaly detection method, which comprises: obtaining a first operating parameter of a to-be-detected converter and a second operating parameter of a target converter, the target converter being a converter on the same pole and on the same side as the to-be-detected converter; inputting the first operating parameter and the second operating parameter into a preselected trained compensation model of the to-be-detected converter to obtain a compensation voltage output by the compensation model of the to-be-detected converter; obtaining a theoretical voltage according to the first operating parameter and a direct current voltage function, and obtaining a predicted voltage of the to-be-detected converter according to the compensation voltage and the theoretical voltage; and obtaining a detection result of the to-be-detected converter according to the predicted voltage and a measured voltage of the to-be-detected converter measured by a voltage sensor.

[0006] In one of the embodiments, the method further comprises: obtaining a first sample operating parameter of the to-be-detected converter, a sample measured voltage of the to-be-detected converter and a second sample operating parameter of the target converter; obtaining a label voltage according to the first sample operating parameter and the sample measured voltage; inputting the first sample operating parameter and the second sample operating parameter into a to-be-trained model to obtain a sample compensation voltage output by the to-be-trained model; and training the to-be-trained model based on the label voltage and the sample compensation voltage to obtain the compensation model of the to-be-detected converter.

[0007] In one of the embodiments, the direct voltage function comprises a first direct voltage function and a second direct voltage function, the control angle of the converter in the first direct voltage function is the converter conduction control angle; the control angle of the converter in the second direct voltage function is the converter extinction control angle; the theoretical voltage is obtained according to the first operating parameter and the direct voltage function, comprising: when the to-be-tested converter is a rectifier-side converter, the theoretical voltage is obtained according to the first operating parameter and the first direct voltage function; when the to-be-tested converter is an inverter-side converter, the theoretical voltage is obtained according to the first operating parameter and the second direct voltage function.

[0008] In one of the embodiments, the first operating parameter comprises an AC side voltage of a converter transformer in the DC power transmission system, a tap switch gear position of the converter transformer, an AC side winding voltage of the converter transformer, a control angle of the to-be-tested converter, and a DC current of the to-be-tested converter.

[0009] In one of the embodiments, the detection result of the to-be-tested converter is obtained according to the predicted voltage and a measured voltage measured by a voltage sensor on the to-be-tested converter, comprising: the difference between the predicted voltage and the measured voltage is obtained to obtain a difference value; when the difference value is greater than or equal to an error threshold value, the detection result comprises that the to-be-tested converter is abnormal.

[0010] In one of the embodiments, the compensation model of the to-be-tested converter is obtained by training the to-be-trained model based on the label voltage and the sample compensation voltage, comprising: a loss value is obtained according to the mean square error of the label voltage and the sample compensation voltage; the parameters of the to-be-trained model are updated according to the loss value to obtain the compensation model of the to-be-tested converter.

[0011] In a second aspect, the application further provides a DC power transmission system voltage measurement abnormality detection device, the device comprising:

[0012] The acquisition module is configured to acquire a first operating parameter of a to-be-tested converter and a second operating parameter of a target converter, the target converter being a converter of the same polarity and the same side as the to-be-tested converter;

[0013] The first determination module is configured to input the first operating parameter and the second operating parameter into a pre-selected trained compensation model of the to-be-tested converter to obtain a compensation voltage output by the compensation model of the to-be-tested converter;

[0014] The second determination module is configured to obtain a theoretical voltage according to the first operating parameter and a direct voltage function, and obtain a predicted voltage of the to-be-tested converter according to the compensation voltage and the theoretical voltage;

[0015] The third determination module is configured to obtain a detection result of the to-be-tested converter according to the predicted voltage and a measured voltage measured by a voltage sensor on the to-be-tested converter.

[0016] In one of the embodiments, the device further comprises a training module configured to obtain a first sample operating parameter of the to-be-tested converter, a sample measured voltage of the to-be-tested converter, and a second sample operating parameter of the target converter; obtain a label voltage according to the first sample operating parameter and the sample measured voltage; input the first sample operating parameter and the second sample operating parameter into the to-be-trained model to obtain a sample compensation voltage output by the to-be-trained model; and train the to-be-trained model based on the label voltage and the sample compensation voltage to obtain the compensation model of the to-be-tested converter.

[0017] In one of the embodiments, the DC voltage function comprises a first DC voltage function and a second DC voltage function, the control angle of the converter in the first DC voltage function is the turn-on control angle of the converter, and the control angle of the converter in the second DC voltage function is the extinction control angle of the converter; and the second determining module is specifically configured to obtain the theoretical voltage according to the first operating parameter and the first DC voltage function when the to-be-tested converter is a converter on the rectifier side, and obtain the theoretical voltage according to the first operating parameter and the second DC voltage function when the to-be-tested converter is a converter on the inverter side.

[0018] In one of the embodiments, the first operating parameter comprises an AC side voltage of a converter transformer in the DC power transmission system, a tap switch gear position of the converter transformer, an AC side winding voltage of the converter transformer, a control angle of the to-be-tested converter, and a DC current of the to-be-tested converter.

[0019] In one of the embodiments, the third determining module is specifically configured to obtain a difference value by subtracting the predicted voltage from the measured voltage; and when the difference value is greater than or equal to an error threshold value, the detection result comprises that the to-be-tested converter is abnormal.

[0020] In one of the embodiments, the training module is specifically configured to obtain a loss value according to a mean square error of the label voltage and the sample compensation voltage; and update parameters of the to-be-trained model according to the loss value to obtain the compensation model of the to-be-tested converter.

[0021] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method in any one of the first aspect when executing the computer program.

[0022] In a fourth aspect, the present application further provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the steps of the method in any one of the first aspect.

[0023] In a fifth aspect, the present application further provides a computer program product comprising a computer program, wherein the computer program is executed by a processor to implement the steps of the method in any one of the first aspect.

[0024] The DC power transmission system voltage measurement anomaly detection method, device, computer device, storage medium and program product, by obtaining the first operation parameter of the to-be-detected converter, obtaining the second operation parameter of the target converter, the target converter being a converter on the same pole and on the same side as the to-be-detected converter, then inputting the first operation parameter and the second operation parameter into the preselected trained compensation model of the to-be-detected converter, obtaining the compensation voltage output by the compensation model of the to-be-detected converter, then obtaining the theoretical voltage according to the first operation parameter and the DC voltage function, and obtaining the predicted voltage of the to-be-detected converter according to the compensation voltage and the theoretical voltage, and then obtaining the detection result of the to-be-detected converter according to the predicted voltage and the measured voltage of the to-be-detected converter measured by the voltage sensor, so as to realize the predicted voltage obtained by combining the trained compensation model and the DC voltage function. Compared with the way of obtaining the predicted voltage by only using the neural network model or directly using the DC voltage function, the accuracy of the predicted voltage can be improved, and then the accuracy of the detection result obtained according to the predicted voltage and the measured voltage can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other related drawings can be obtained by those skilled in the art without creative labor.

[0026] Figure 1 An application environment diagram of the DC power transmission system voltage measurement anomaly detection method in an embodiment;

[0027] Figure 2 A flowchart of the DC power transmission system voltage measurement anomaly detection method in an embodiment;

[0028] Figure 3 A structure diagram of the DC power transmission system in an embodiment;

[0029] Figure 4 A structure diagram of the MLP-c model in an embodiment;

[0030] Figure 5 A schematic diagram of the DC power transmission system voltage measurement anomaly detection principle in an embodiment;

[0031] Figure 6 A flowchart of the training method of the compensation model in an embodiment;

[0032] Figure 7 A comparison result diagram of the present application and the prior art in an embodiment;

[0033] Figure 8 Fig. 1 is a structural block diagram of a DC power transmission system voltage measurement abnormality detection device according to an embodiment;

[0034] Figure 9 Fig. 2 is an internal structural diagram of a computer device according to an embodiment. DETAILED DESCRIPTION

[0035] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not intended to limit the present application.

[0036] High-voltage direct current (HVDC) transmission is increasingly widely used in long-distance power transmission scenarios due to its low line cost, small transmission loss, and flexible regulation. The operating voltage of a long-distance HVDC transmission system is generally ±500 kV or ±800 kV. The control system cannot be directly connected to high voltage, and the primary DC voltage must be collected and converted by a measurement device before it can be used as an input signal for the control system. Voltage measurement abnormalities can cause significant disturbances to the normal operation of the HVDC transmission system, and in severe cases, the HVDC transmission system protection action can cause an emergency shutdown.

[0037] In traditional techniques, the HVDC transmission system voltage measurement abnormality is detected by a comparison method, a data analysis method, or a theoretical calculation method. The comparison method detects the HVDC voltage measurement by observing the differences in key operating parameters of adjacent converters in the HVDC transmission system. For example, simulation analysis is performed on the conditions in which measurement abnormalities occur on the rectifier station side and the inverter station side, respectively, and the operating parameter changes of each converter under different measurement abnormal conditions are given. The fault point is identified by observing the parameter differences in the adjacent converters. This method can only qualitatively determine which side the fault point is located on, and cannot give the specific measurement deviation. Moreover, since the comparison is between the operating parameters of two adjacent converters, this method is not suitable for monopolar single-converter HVDC transmission systems.

[0038] The numerical analysis method detects voltage abnormalities by calculating the numerical relationship between the DC voltage measurement value and the AC / DC side power of the converter. For example, the numerical relationship between the HVDC bus voltage, the tie bus voltage, and the grounding electrode bus voltage of the same pole in a converter station is combined with the AC / DC power deviation to locate the abnormal point. This numerical analysis method has different deviations under different operating conditions. When identifying voltage measurement abnormalities, the threshold must be set to be greater than the maximum deviation that occurs during normal operation, otherwise the normal voltage fluctuations will be frequently misidentified as abnormal during system operation, resulting in low detection accuracy.

[0039] Theoretical calculation method is based on the circuit principle of DC power transmission system to detect DC voltage measurement abnormality. The DC current of the converter, the transformer gear, the conduction control angle and other operating parameters are substituted into the formula to calculate the theoretical voltage. The deviation between the theoretical voltage and the actual measured voltage is compared, and the converter with a deviation greater than the set threshold is determined to have measurement abnormality. In actual operation, the voltage, current, control angle and other parameters can be measured in real time by measuring devices or control systems, but the values of short-circuit reactance and commutation reactance of the converter transformer will change due to factors such as temperature and grid frequency, and cannot be directly measured. The DC voltage calculated only by the measured operating parameters cannot be accurate enough in some operating conditions, so the theoretical calculation method also has the problem of low detection accuracy

[0040] The DC power transmission system voltage measurement abnormality detection method provided by the embodiments of the present application can be applied in the application environment as shown in Figure 1 The terminal 102 communicates with the server 104 through the network. The data storage system can store the data required to be processed by the server 104. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle device, a projection device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 can be a standalone physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0041] In an exemplary embodiment, as shown in Figure 2 A DC power transmission system voltage measurement abnormality detection method is provided. The method is applied to the terminal 102 or the server 104 in the computer device Figure 1 , and includes the following steps 201 to 204. Wherein:

[0042] Step 201, obtaining the first operating parameter of the to-be-tested converter, and obtaining the second operating parameter of the target converter, the target converter being the converter on the same pole and the same side as the to-be-tested converter.

[0043] The DC power transmission system is as shown in Figure 3As shown, the converter in the direct current power transmission system adopts a double twelve-pulse connection mode. Specifically, the direct current power transmission system includes a converter module at a rectifier side and a converter module at an inverter side, the converter module at the rectifier side includes a first converter H1, a second converter H2, a third converter H3 and a fourth converter H4, and the converter module at the inverter side includes a fifth converter H5, a sixth converter H6, a seventh converter H7 and an eighth converter H8.

[0044] The first converter H1, the second converter H2, the third converter H3 and the fourth converter H4 realize the function of converting alternating current into direct current at the rectifier side, and the fifth converter H5, the sixth converter H6, the seventh converter H7 and the eighth converter H8 realize the function of converting direct current into alternating current at the inverter side. A loop formed by the first converter H1, the second converter H2, the fifth converter H5 and the sixth converter H6 is a direct current pole, and a loop formed by the third converter H3, the fourth converter H4, the seventh converter H7 and the eighth converter H8 is another direct current pole. In order to measure the direct current voltage of each converter while reducing the number of devices, voltage sensors are arranged at both ends of the converters, and are distributed as shown in the position marked by the middle circle in the figure, wherein UdH Figure 3 , UdM j , UdN j , and UdN j respectively represent the voltage measurement of each voltage sensor, wherein j∈1, 2, 3, 4.

[0045] The first converter H1 and the second converter H2 are two converters of the same pole and the same side, the third converter H3 and the fourth converter H4 are two converters of the same pole and the same side, the fifth converter H5 and the sixth converter H6 are two converters of the same pole and the same side, and the seventh converter H7 and the eighth converter H8 are two converters of the same pole and the same side. Taking the first converter H1 as an example to explain the relationship between the converters: the first converter H1 and the third converter H3 are two converters of the same side and different poles, the first converter H1 and the fifth converter H5 are two converters of the same pole and different sides, and the first converter H1 and the seventh converter H7 are two converters of different poles and different sides.

[0046] The to-be-measured converter can be a converter at the rectifier side of the direct current power transmission system or a converter at the inverter side of the direct current power transmission system. The target converter is a converter of the same pole and the same side as the to-be-measured converter, for example, when the to-be-measured converter is the first converter H1, the target converter is the second converter H2; when the to-be-measured converter is the second converter H2, the target converter is the first converter H1.

[0047] The first operating parameter can be the operating parameters of the converter under test at the current moment. These parameters include the AC side voltage of the converter transformer in the DC transmission system, the tap changer position of the converter transformer, the AC side winding voltage of the converter transformer, the control angle of the converter under test, and the DC current of the converter under test. Similarly, the second operating parameter can be the operating parameters of the target converter at the current moment. These parameters also include the AC side voltage of the converter transformer in the DC transmission system, the tap changer position of the converter transformer, the AC side winding voltage of the converter transformer, the control angle of the target converter, and the DC current of the target converter.

[0048] When the converter under test is a rectifier-side converter, the control angle of the converter under test in the first operating parameter refers to the conduction control angle of the converter under test, and the control angle of the target converter in the second operating parameter refers to the conduction control angle of the target converter. When the converter under test is an inverter-side converter, the control angle of the converter under test in the first operating parameter refers to the arc extinction control angle of the converter under test; and the control angle of the target converter in the second operating parameter refers to the arc extinction control angle of the target converter.

[0049] In one possible implementation, the computer device displays a human-computer interaction interface, and obtains first and second operating parameters input by the user based on the human-computer interaction interface.

[0050] In another possible implementation, the computer equipment is connected to a device (e.g., a sensor) in the DC transmission system that measures the operating parameters of the converter under test and the target converter, and periodically acquires the first and second operating parameters.

[0051] Step 202: Input the first operating parameter and the second operating parameter into the pre-trained compensation model of the converter under test to obtain the compensation voltage output by the compensation model of the converter under test.

[0052] The compensation model is a neural network model, such as the MLP (Multilayer Perceptron) model.

[0053] Depend on Figure 3 It can be seen that the two converters on the same pole and side share the voltage measurement UdM. The operating parameters of these two converters will have a significant mutual influence. Therefore, when calculating the DC voltage of a single converter, the characteristic of the input compensation model should be the operating parameters of the two converters on the same pole and side.

[0054] based on Figure 3 The DC transmission system shown has a compensation model F for the i-th converter. Δ(i) for:

[0055]

[0056] wherein G i represents the operating parameters of the i-th converter H i , i.e.:

[0057]

[0058] wherein G i may be an n x 5 matrix, n being the total step length; u ac represents the AC side voltage of the converter transformer; p represents the tap changer position of the converter transformer; i ac represents the AC side winding voltage of the converter transformer; a represents the control angle of the converter; I d represents the DC current of the converter.

[0059] The principle of the above compensation model is as follows. When calculating the compensation voltage of the first converter H1 with i equal to 1, the operating parameters G1 of the first converter H1 and the operating parameters G2 of the second converter H2 are input into the pre-trained compensation model F Δ(1) of the first converter H1, so as to obtain the compensation voltage output by the compensation model F Δ(1) of the first converter H1, i.e. the compensation voltage AU1 of the first converter H1. When calculating the compensation voltage of the fourth converter H4 with i equal to 4, the operating parameters G4 of the fourth converter H4 and the operating parameters G3 of the third converter H3 are input into the pre-trained compensation model F Δ(4) of the fourth converter H4, so as to obtain the compensation voltage output by the compensation model F Δ(4) of the fourth converter H4, i.e. the compensation voltage AU4 of the fourth converter H4.

[0060] In step 203, the theoretical voltage is obtained according to the first operating parameter and the DC voltage function, and the predicted voltage of the to-be-tested converter is obtained according to the compensation voltage and the theoretical voltage.

[0061] wherein the DC voltage function includes a first DC voltage function and a second DC voltage function, the first DC voltage function being as shown in formula (3) and the second DC voltage function being as shown in formula (4):

[0062]

[0063] wherein U c represents the theoretical voltage; u ac represents the AC side voltage of the converter transformer; k represents the transformation ratio of the converter transformer; p represents the tap changer position of the converter transformer; i ac represents the AC side winding voltage of the converter transformer; X t represents the equivalent reactance of the converter transformer; a represents the conduction control angle of the converter; g represents the extinction control angle of the converter; X r represents the commutation reactance; Id represents the DC current of the converter.

[0064] When the to-be-tested converter is a rectifier-side converter, the computer device obtains the theoretical voltage according to the first operating parameter and the first DC voltage function. When the to-be-tested converter is an inverter-side converter, the computer device obtains the theoretical voltage according to the first operating parameter and the second DC voltage function.

[0065] In a possible implementation, after the theoretical voltage is obtained, the predicted voltage of the to-be-tested converter is obtained according to the compensation voltage and the theoretical voltage, including: the computer device takes the sum of the compensation voltage and the theoretical voltage as the predicted voltage of the to-be-tested converter. Based on Figure 3 As shown in the DC power transmission system, the predicted voltage U d(i) is expressed by a data formula as follows:

[0066]

[0067] The above steps 201 to 203 can be regarded as a model combining a multi-layer perception and a DC voltage theoretical calculation formula, which can be named as an MLP-c model. The structure of the MLP-c model is as shown in Figure 4 .

[0068] In step 204, the detection result of the to-be-tested converter is obtained according to the predicted voltage and a measurement voltage measured by a voltage sensor on the to-be-tested converter.

[0069] In a possible implementation, the predicted voltage and the measurement voltage are subtracted to obtain a difference value; when the difference value is greater than or equal to an error threshold, the detection result includes that the to-be-tested converter is abnormal; and when the difference value is less than the error threshold, the detection result includes that the to-be-tested converter is normal.

[0070] Referring to Figure 5 , based on the DC power transmission system as shown in Figure 3 , the operating parameter G i of the i th converter H i , the operating parameter of the converter on the same pole and the same side as the i th converter H i , and the operating parameter of the converter on the same pole and the same side as the i th converter H i are input to the MLP-c model of the i th converter H i to obtain the predicted voltage U i of the i th converter H d(i) , and a measurement voltage U i measured by a voltage sensor on the i th converter H m(i) is obtained; and the i th converter H i is subjected to abnormality discrimination, that is, whether the predicted voltage U d(i) is equal to the measurement voltage U m(i)whether the absolute value of the difference between the predicted voltage and the measured voltage is greater than or equal to an error threshold U th , which is expressed in a mathematical formula as follows:

[0071]

[0072] If yes, the i-th converter H i is abnormal, the i-th converter H i is marked as a fault point; if no, the i-th converter H i is normal.

[0073] In addition, by predicting the difference between the voltage and the measured voltage, the severity of the voltage measurement abnormality can be determined.

[0074] The above-mentioned DC power transmission system voltage measurement abnormality detection method, by obtaining the first operating parameter of the to-be-tested converter, and obtaining the second operating parameter of the target converter, the target converter is the converter on the same side and the same pole as the to-be-tested converter, then the first operating parameter and the second operating parameter are input into the pre-selected trained compensation model of the to-be-tested converter, the compensation voltage output by the compensation model of the to-be-tested converter is obtained, then the theoretical voltage is obtained according to the first operating parameter and the DC voltage function, and the predicted voltage of the to-be-tested converter is obtained according to the compensation voltage and the theoretical voltage, and then the detection result of the to-be-tested converter is obtained according to the predicted voltage and the measured voltage measured by the voltage sensor on the to-be-tested converter, so that the predicted voltage is obtained by combining the trained compensation model and the DC voltage function. Compared with the way of using only the neural network model or directly using the DC voltage function to obtain the predicted voltage, the accuracy of the predicted voltage can be improved, and then the accuracy of the detection result obtained according to the predicted voltage and the measured voltage can be improved.

[0075] In one exemplary embodiment, as Figure 6 shown, a compensation model training method is provided, including steps 601 to 603. Wherein:

[0076] Step 601, obtaining the first sample operating parameter of the to-be-tested converter, the sample measured voltage of the to-be-tested converter and the second sample operating parameter of the target converter.

[0077] Wherein, the sample measured voltage of the to-be-tested converter is the real and accurate measured voltage of the to-be-tested converter. The sample operating parameter is the historical operating parameter.

[0078] Step 602, obtaining the label voltage according to the first sample operating parameter and the sample measured voltage; inputting the first sample operating parameter and the second sample operating parameter into the to-be-trained model to obtain the sample compensation voltage output by the to-be-trained model.

[0079] The to-be-trained model is a neural network model, such as an MLP. The label voltage represents the deviation between the theoretical voltage calculated by using the DC voltage function and the actual measured voltage.

[0080] In a possible implementation, the first sample operating parameter is substituted into the DC voltage function to obtain a sample theoretical voltage, and a difference between the sample theoretical voltage and the sample measured voltage is taken as the label voltage.

[0081] In step 603, the to-be-trained model is trained based on the label voltage and the sample compensation voltage to obtain a compensation model of the to-be-tested converter.

[0082] In a possible implementation, a loss value is obtained according to the mean square deviation of the label voltage and the sample compensation voltage; and parameters of the to-be-trained model are updated according to the loss value to obtain the compensation model of the to-be-tested converter.

[0083] In other words, the loss function of the to-be-trained model of the to-be-tested converter is the mean square deviation of the compensation voltage and the deviation between the actual measured voltage and the theoretical voltage. The loss function is expressed in a mathematical formula as follows:

[0084]

[0085] wherein loss i represents the loss value of the i th converter; T = {1, 2, …, n} is a time step contained in the small batch training data; ΔU i represents the sample compensation voltage of the i th converter; U mea(i) represents the sample measured voltage, U cal (G i ) represents the sample theoretical voltage of the i th converter; U mea(i) -U cal (G i ) represents the label voltage.

[0086] In the training process, the parameters of the to-be-trained model are updated by using a stochastic gradient descent (SGD) algorithm. That is:

[0087] θ t+1 = θ t - α · loss (8)

[0088] wherein θ is the parameter of the to-be-trained model, α is a learning rate, loss is the loss value, and t is the iteration number.

[0089] The training is ended when the iteration number is greater than or equal to a number threshold, and the iteration training is continued when the iteration number is less than the number threshold, until the iteration number is greater than or equal to the number threshold.

[0090] In addition, the application also conducts experiments on the real operation data of the DC power transmission system for 3 years. Compared with the prior art using only the DC voltage function and only the classical deep learning model, the application has obvious improvement in voltage prediction accuracy and abnormality detection accuracy. The comparison results of the application and the prior art are shown in Figure 7

[0091] Figure 7 In the formula, MLP-c predict refers to prediction by the method of the application; original data refers to real operation data; Formula predict refers to prediction by the DC voltage function; GRU predict refers to prediction by the deep learning model GRU (Gated Recurrent Unit); MLP predict refers to prediction by the deep learning model MLP; RNN predict refers to prediction by the deep learning model RNN (Recurrent Neural Network); LSTM predict refers to prediction by the deep learning model LSTM (Long Short-Term Memory); and pu refers to a unit value.

[0092] The determination method of abnormality detection accuracy is that, on the 207 groups of operation data with obvious voltage deviation collected in the DC power transmission system for 3 years, the DC voltages of 8 converters are respectively predicted at each sampling point by using different abnormality detection methods, the state (abnormal / normal) of each converter is determined by calculating the difference between the measured value and the predicted value, and the state of the converter with a deviation greater than 0.005pu between the measured value and the predicted value is determined as an abnormal state, that is, marked as a fault point. The model identifies one normal converter as normal or one converter with measurement deviation as fault in one time step as one correct identification. The identification accuracy rate of each model is shown in Table 1.

[0093] Table 1

[0094] MLP-c MLP Formula RNN GRU LSTM Accuracy 88.882％ 71.875％ 58.954％ 66.707％ 17.308％ 30.769％ Missed identification rate 5.409％ 10.577％ 10.397％ 9.375％ 1.442％ 3.005％ Misidentification rate 5.709％ 17.548％ 30.649％ 23.918％ 81.25％ 66.226％

[0095] ​It should be understood that although the steps in the flowcharts involved in the embodiments described above are shown in sequence according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of the steps is not strictly limited in sequence, and the steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the embodiments described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of the steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or steps or stages in other steps.

[0096] Based on the same inventive concept, the embodiments of the present application also provide a DC power transmission system voltage measurement anomaly detection device for implementing the above-mentioned DC power transmission system voltage measurement anomaly detection method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more DC power transmission system voltage measurement anomaly detection device embodiments provided below can refer to the limitations of the DC power transmission system voltage measurement anomaly detection method described above, which will not be repeated here.

[0097] In one exemplary embodiment, as shown in Figure 8 A DC power transmission system voltage measurement anomaly detection device is provided, and the DC power transmission system voltage measurement anomaly detection 800 includes an acquisition module 801, a first determination module 802, a second determination module 803, and a third determination module 804, wherein:

[0098] The acquisition module 801 is configured to acquire a first operating parameter of a to-be-tested converter and acquire a second operating parameter of a target converter, the target converter being a converter on the same side and of the same polarity as the to-be-tested converter.

[0099] The first determination module 802 is configured to input the first operating parameter and the second operating parameter into a preselected trained compensation model of the to-be-tested converter to obtain a compensation voltage output by the compensation model of the to-be-tested converter.

[0100] The second determination module 803 is configured to obtain a theoretical voltage according to the first operating parameter and a DC voltage function, and obtain a predicted voltage of the to-be-tested converter according to the compensation voltage and the theoretical voltage.

[0101] The third determination module 804 is configured to obtain a detection result of the to-be-tested converter according to the predicted voltage and a measured voltage of the to-be-tested converter measured by a voltage sensor.

[0102] In one of the embodiments, the apparatus further comprises a training module configured to obtain a first sample operating parameter of the to-be-tested converter, a sample measured voltage of the to-be-tested converter, and a second sample operating parameter of the target converter; obtain a label voltage according to the first sample operating parameter and the sample measured voltage; input the first sample operating parameter and the second sample operating parameter into the to-be-trained model to obtain a sample compensation voltage output by the to-be-trained model; and train the to-be-trained model based on the label voltage and the sample compensation voltage to obtain the compensation model of the to-be-tested converter.

[0103] In one of the embodiments, the DC voltage function comprises a first DC voltage function and a second DC voltage function, the control angle of the converter in the first DC voltage function is the conduction control angle of the converter, and the control angle of the converter in the second DC voltage function is the extinction control angle of the converter; the second determining module 803 is specifically configured to obtain the theoretical voltage according to the first operating parameter and the first DC voltage function when the to-be-tested converter is a converter on the rectifier side, and obtain the theoretical voltage according to the first operating parameter and the second DC voltage function when the to-be-tested converter is a converter on the inverter side.

[0104] In one of the embodiments, the first operating parameter comprises an AC side voltage of a converter transformer in the DC power transmission system, a tap switch gear position of the converter transformer, an AC side winding voltage of the converter transformer, a control angle of the to-be-tested converter, and a DC current of the to-be-tested converter.

[0105] In one of the embodiments, the third determining module 804 is specifically configured to obtain a difference value by subtracting the predicted voltage from the measured voltage; and when the difference value is greater than or equal to an error threshold value, the detection result comprises that the to-be-tested converter is abnormal.

[0106] In one of the embodiments, the training module is specifically configured to obtain a loss value according to a mean square error of the label voltage and the sample compensation voltage; and update parameters of the to-be-trained model according to the loss value to obtain the compensation model of the to-be-tested converter.

[0107] The above-mentioned various modules in the DC power transmission system voltage measurement abnormality detection apparatus can be realized by software, hardware, and combinations thereof, in whole or in part. The above-mentioned various modules can be embedded in or independent of a processor in a computer device in a hardware form, or can be stored in a memory in the computer device in a software form, so as to be called and executed by a processor to perform operations corresponding to the above-mentioned various modules.

[0108] In one exemplary embodiment, a computer device is provided, which can be a terminal, and an internal structure diagram of the computer device can be as shown in Figure 9As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with the external terminal in a wired or wireless manner. The wireless manner can be realized through WIFI, mobile cellular network, near field communication (Near Field Communication, NFC) or other technologies. The computer program is executed by the processor to realize a direct current power transmission system voltage measurement anomaly detection method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0109] Those skilled in the art can understand that, Figure 9 The skilled in the art can understand that,

[0110] In one exemplary embodiment, a computer device is provided, including a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the steps of the method in any one of the above method embodiments.

[0111] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps of the method in any one of the above method embodiments.

[0112] In one embodiment, a computer program product is provided, including a computer program, and the computer program is executed by a processor to implement the steps of the method in any one of the above method embodiments.

[0113] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0114] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present application.

[0115] The above-described embodiments are merely illustrative of several embodiments of the present application, which are described in more detail and in a specific manner, but should not be construed as limiting the scope of the patent of the present application. It should be noted that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method of detecting abnormality in voltage measurement in a direct current power transmission system, characterized by, The method comprises: obtaining a first operating parameter of a to-be-tested converter and a second operating parameter of a target converter, the target converter being a converter on the same pole and on the same side as the to-be-tested converter; inputting the first operating parameter and the second operating parameter into a preselected trained compensation model of the to-be-tested converter to obtain a compensation voltage output by the compensation model of the to-be-tested converter; obtaining a theoretical voltage according to the first operating parameter and a direct current voltage function, and obtaining a predicted voltage of the to-be-tested converter according to the compensation voltage and the theoretical voltage; obtaining a detection result of the to-be-tested converter according to the predicted voltage and a measured voltage measured by a voltage sensor on the to-be-tested converter.

2. The method of claim 1, wherein, The method further comprises: obtaining a first sample operating parameter of the to-be-tested converter, a sample measured voltage of the to-be-tested converter, and a second sample operating parameter of the target converter; obtaining a label voltage according to the first sample operating parameter and the sample measured voltage; inputting the first sample operating parameter and the second sample operating parameter into a to-be-trained model to obtain a sample compensation voltage output by the to-be-trained model; training the to-be-trained model based on the label voltage and the sample compensation voltage to obtain the compensation model of the to-be-tested converter.

3. The method of claim 1, wherein, The direct current voltage function comprises a first direct current voltage function and a second direct current voltage function, a control angle of a converter in the first direct current voltage function being a converter conduction control angle, and a control angle of a converter in the second direct current voltage function being a converter extinction control angle; The method further comprises: when the to-be-tested converter is a rectifier side converter, obtaining the theoretical voltage according to the first operating parameter and the first direct current voltage function; when the to-be-tested converter is an inverter side converter, obtaining the theoretical voltage according to the first operating parameter and the second direct current voltage function.

4. The method according to any one of claims 1 to 3, characterized in that, The first operating parameter comprises an alternating current side voltage of a converter transformer in the direct current power transmission system, a tap switch gear position of the converter transformer, an alternating current side winding voltage of the converter transformer, a control angle of the to-be-tested converter, and a direct current of the to-be-tested converter.

5. The method of claim 1, wherein, The method further comprises: differencing the predicted voltage and the measured voltage to obtain a difference value; when the difference value is greater than or equal to an error threshold, the detection result comprises an abnormality of the to-be-tested converter.

6. The method of claim 2, wherein, The method further comprises: obtaining a loss value according to a mean square error of the label voltage and the sample compensation voltage; updating parameters of the to-be-trained model according to the loss value to obtain the compensation model of the to-be-tested converter.

7. A DC power transmission system voltage measurement abnormality detection device characterized by comprising: The device comprises: an obtaining module configured to obtain a first operating parameter of a to-be-tested converter and a second operating parameter of a target converter, the target converter being a converter on the same pole and on the same side as the to-be-tested converter; a first determining module, configured to input the first operating parameter and the second operating parameter into a preselected compensation model of a to-be-tested converter, to obtain a compensation voltage output by the compensation model of the to-be-tested converter; a second determining module, configured to obtain a theoretical voltage according to the first operating parameter and a direct-current voltage function, and to obtain a predicted voltage of the to-be-tested converter according to the compensation voltage and the theoretical voltage; a third determining module, configured to obtain a detection result of the to-be-tested converter according to the predicted voltage and a measured voltage measured by a voltage sensor on the to-be-tested converter.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method in any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

Images