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

Abstract

The invention relates to a DC power transmission system voltage measurement anomaly detection method and device, computer equipment, a storage medium and a program product. The method comprises the steps that a first operation parameter of a to-be-tested converter is acquired, a second operation parameter of a target converter is acquired, and the target converter is a converter with the same pole and the same side as the to-be-tested converter; inputting the first operation parameter and the second operation parameter into a pre-selected and 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 operation parameter and a DC voltage function, and obtaining a predicted voltage of the to-be-tested 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 measurement voltage obtained by measuring the to-be-detected converter by the voltage sensor. By adopting the method, the voltage measurement anomaly detection precision can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of high-voltage direct current transmission, and in particular to a method, device, computer equipment, storage medium and program product for detecting abnormal voltage measurement in a direct current transmission system. Background Art

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

[0003] In conventional technologies, the voltage measurement anomaly of a DC output system is detected by comparison method, data analysis method or theoretical calculation method, but they all have the problem of low detection accuracy. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, storage medium and program product for detecting voltage anomaly in a DC power transmission system, which can improve the accuracy of voltage measurement anomaly detection, in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for detecting abnormal voltage measurement in a direct current transmission system, the method comprising: obtaining a first operating parameter of a converter to be tested, and obtaining a second operating parameter of a target converter, the target converter being a converter on the same pole and the same side as the converter to be tested; inputting the first operating parameter and the second operating parameter into a pre-selected and trained compensation model of the converter to be tested, and obtaining a compensation voltage output by the compensation model of the converter to be tested; obtaining a theoretical voltage based on the first operating parameter and a direct current voltage function, and obtaining a predicted voltage of the converter to be tested based on the compensation voltage and the theoretical voltage; obtaining a detection result of the converter to be tested based on the predicted voltage and a measured voltage measured by a voltage sensor on the converter to be tested.

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

[0007] In one embodiment, the DC voltage function includes 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 converter conduction control angle; the control angle of the converter in the second DC voltage function is the converter arc extinction control angle; according to the first operating parameter and the DC voltage function, a theoretical voltage is obtained, including: when the converter to be tested is a converter on the rectifier side, the theoretical voltage is obtained according to the first operating parameter and the first DC voltage function; when the converter to be tested is a converter on the inverter side, the theoretical voltage is obtained according to the first operating parameter and the second DC voltage function.

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

[0009] In one of the embodiments, a detection result of the converter to be tested is obtained based on the predicted voltage and the measured voltage measured by the voltage sensor on the converter to be tested, including: subtracting the predicted voltage from the measured voltage to obtain a difference; when the difference is greater than or equal to an error threshold, the detection result includes that the converter to be tested is abnormal.

[0010] In one of the embodiments, a model to be trained is trained based on a label voltage and a sample compensation voltage to obtain a compensation model of the converter to be tested, including: obtaining a loss value based on a mean square error between the label voltage and the sample compensation voltage; and updating parameters of the model to be trained based on the loss value to obtain a compensation model of the converter to be tested.

[0011] In a second aspect, the present application further provides a device for detecting abnormal voltage measurement in a DC power transmission system, the device comprising:

[0012] An acquisition module, used to acquire a first operating parameter of the converter to be tested, and to acquire a second operating parameter of a target converter, wherein the target converter is a converter on the same pole and the same side as the converter to be tested;

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

[0014] A second determination module is used to obtain a theoretical voltage according to the first operating parameter and the DC voltage function, and to obtain a predicted voltage of the converter to be tested according to the compensation voltage and the theoretical voltage;

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

[0016] In one embodiment, the device also includes a training module, which is used to obtain a first sample operating parameter of the converter to be tested, a sample measured voltage of the converter to be tested, and a second sample operating parameter of the target converter; obtain a label voltage based on the first sample operating parameter and the sample measured voltage; input the first sample operating parameter and the second sample operating parameter into the model to be trained to obtain a sample compensation voltage output by the model to be trained; and train the model to be trained based on the label voltage and the sample compensation voltage to obtain a compensation model of the converter to be tested.

[0017] In one embodiment, the DC voltage function includes 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 converter conduction control angle; the control angle of the converter in the second DC voltage function is the converter arc extinction control angle; the second determination module is specifically used to obtain the theoretical voltage according to the first operating parameters and the first DC voltage function when the converter to be tested is a converter on the rectifier side; when the converter to be tested is a converter on the inverter side, the theoretical voltage is obtained according to the first operating parameters and the second DC voltage function.

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

[0019] In one of the embodiments, the third determination module is specifically used to make a difference between the predicted voltage and the measured voltage to obtain a difference; when the difference is greater than or equal to an error threshold, the detection result includes that the converter to be tested is abnormal.

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

[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 any one of the methods described in 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, and when the computer program is executed by a processor, the steps of any one of the methods described in the first aspect are implemented.

[0023] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect.

[0024] The above-mentioned method, device, computer equipment, storage medium and program product for detecting abnormal voltage measurement in a direct current transmission system obtain a first operating parameter of the converter to be tested and a second operating parameter of the target converter, wherein the target converter is a converter on the same pole and the same side as the converter to be tested, and then the first operating parameter and the second operating parameter are input into a pre-selected and trained compensation model of the converter to be tested to obtain a compensation voltage output by the compensation model of the converter to be tested, and then a theoretical voltage is obtained based on the first operating parameter and the direct current voltage function, and a predicted voltage of the converter to be tested is obtained based on the compensation voltage and the theoretical voltage, and then a detection result of the converter to be tested is obtained based on the predicted voltage and the measured voltage measured by the voltage sensor on the converter to be tested. In this way, the predicted voltage is obtained by combining the trained compensation model and the direct current voltage function. Compared with the method of obtaining the predicted voltage by only using a neural network model or directly using the direct current voltage function, the accuracy of the predicted voltage can be improved, and thus the accuracy of the detection result obtained according to the predicted voltage and the measured voltage can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 A diagram showing an application environment of a method for detecting abnormal voltage measurement in a DC power transmission system according to an embodiment;

[0027] Figure 2 1 is a flow chart of a method for detecting abnormal voltage measurement in a DC power transmission system according to an embodiment;

[0028] Figure 3 is a schematic structural diagram of a direct current transmission system in one embodiment;

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

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

[0031] Figure 6 is a schematic flow chart of a method for training a compensation model in one embodiment;

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

[0033] Figure 8 It is a structural block diagram of a device for detecting abnormal voltage measurement in a DC power transmission system in one embodiment;

[0034] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0036] High-voltage direct current transmission has been increasingly widely used in long-distance transmission scenarios due to its low line cost, low transmission loss, and flexible regulation. The operating voltage of long-distance direct current transmission systems generally adopts ±500kV or ±800kV. Its control system cannot be directly connected to high voltage. The primary direct current voltage must be collected and converted by a measuring device before it can be used as an input signal for the control system. Abnormal voltage measurement will cause significant disturbances to the normal operation of the direct current transmission system. In severe cases, the protection of the direct current transmission system will cause an emergency shutdown.

[0037] In traditional technology, the voltage measurement anomaly of the DC output system is detected by comparison method, data analysis method or theoretical calculation method. Among them, the comparison method measures the DC voltage by observing the difference in key operating parameters of adjacent converters in the DC transmission system. For example, the simulation analysis is performed on the working conditions of the rectifier station side and the inverter station side respectively, and the changes in the operating parameters of each converter under different measurement anomalies are given. The fault point is identified by observing the difference in the operating parameters of adjacent converters. This method can only qualitatively determine which side the fault point is located on, and cannot give a specific measurement deviation. Moreover, since the method compares the operating parameters of two adjacent converters, it is not suitable for DC transmission systems with single poles and single converters.

[0038] The numerical analysis method detects voltage anomalies by calculating the numerical relationship between the DC voltage measurement value and the AC and DC power of the converter. For example, the abnormal point is located by combining the numerical relationship of the three voltage measurement quantities of the high-voltage DC bus voltage, the interconnecting bus voltage, and the grounding bus voltage at the same pole in a converter station with the AC and DC power deviation. This numerical analysis method will have different deviations under different operating conditions. When identifying voltage measurement anomalies, its threshold must be set to be greater than the maximum deviation that will occur during normal operation. Otherwise, normal voltage fluctuations will be frequently misidentified as abnormalities during system operation, so the detection accuracy is low.

[0039] The theoretical calculation method detects abnormalities in DC voltage measurements based on the circuit principle of the DC transmission system. The theoretical voltage is calculated by substituting the operating parameters such as the converter DC current, transformer gear, and conduction control angle into the formula. 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 judged to have a measurement abnormality. In actual operation, parameters such as voltage, current, and control angle can be measured in real time by a measuring device or control system, but the values ​​of the converter transformer short-circuit reactance and commutation reactance will change due to factors such as temperature and grid frequency, and cannot be measured directly. Calculating the DC voltage based solely on the measured operating parameters cannot obtain sufficiently accurate results under 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 in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, 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 an independent physical server, or it can be a server cluster or distributed system composed of multiple physical servers, or it can be a cloud server that provides cloud computing services.

[0041] In an exemplary embodiment, Figure 2 As shown, a method for detecting abnormal voltage measurement in a DC power transmission system is provided, and the method is applied to computer equipment ( Figure 1 The terminal 102 or the server 104 in the embodiment is described, and the method includes the following steps 201 to 204. Among them:

[0042] Step 201, obtaining a first operating parameter of a converter to be tested, and obtaining a second operating parameter of a target converter, wherein the target converter is a converter having the same pole and the same side as the converter to be tested.

[0043] DC transmission system Figure 3As shown, the converter in the DC power transmission system adopts a double twelve-pulse connection mode. Specifically, the DC power transmission system includes a converter module on the rectifier side and a converter module on the inverter side. The converter module on the rectifier side includes a first converter H 1 , the second converter H 2 , the third converter H 3 and the fourth inverter H 4 The inverter module on the inverter side includes a fifth inverter H 5 , the sixth inverter H 6 , the seventh inverter H 7 and the eighth inverter H 8 .

[0044] The first inverter H 1 , the second converter H 2 , the third converter H 3 and the fourth inverter H 4 On the rectifier side, the fifth converter H realizes the function of converting AC into DC. 5 , the sixth inverter H 6 , the seventh inverter H 7 and the eighth inverter H 8 The inverter side realizes the function of converting DC power into AC power. 1 , the second converter H 2 、The fifth inverter H 5 and the sixth inverter H 6 The loop formed is a DC pole, and the third converter H 3 , the fourth inverter H 4 , the seventh inverter H 7 and the eighth inverter H 8 The loop formed is another DC pole. In order to reduce the number of devices while measuring the DC voltage of each converter, voltage sensors are installed at both ends of the converter, and their distribution is as follows: Figure 3 As shown in the circle mark position, UdH j , UdM j ,UdN j Represent the voltage measurement quantity of each voltage sensor, where j∈1,2,3,4.

[0045] The first inverter H 1 and the second converter H 2 The two converters on the same side and the same pole, the third converter H 3 and the fourth inverter H 4 The fifth converter H is two converters with the same pole and the same side. 5 and the sixth inverter H 6 The seventh converter H is two converters with the same pole and the same side. 7and the eighth inverter H 8 The two converters are on the same side with the same pole. 1 Take the relationship between the converters as an example: the first converter H 1 and the third converter H 3 There are two converters with different poles on the same side. The first converter H 1 and the fifth inverter H 5 There are two converters on the same pole but on different sides. The first converter H 1 and the seventh inverter H 7 Two converters with different poles and on different sides.

[0046] The converter to be tested may be a converter on the rectifier side of a DC power transmission system, or may be a converter on the inverter side of a DC power transmission system. The target converter is a converter on the same pole and side as the converter to be tested. For example, when the converter to be tested is the first converter H 1 When the target converter is the second converter H 2 ; When the converter to be tested is the second converter H 2 When the target converter is the first converter H 1 .

[0047] The first operating parameter may be an operating parameter of the converter to be tested at the current moment, and the first operating parameter includes the voltage on the AC side of the converter transformer in the DC power transmission system, the tap position of the converter transformer, the voltage on the AC side of the converter transformer winding, the control angle of the converter to be tested, and the DC current of the converter to be tested. Similarly, the second operating parameter may be an operating parameter of the target converter at the current moment, and the second operating parameter includes the voltage on the AC side of the converter transformer in the DC power transmission system, the tap position of the converter transformer, the voltage on the AC side of the converter transformer winding, the control angle of the target converter, and the DC current of the target converter.

[0048] When the converter to be tested is a converter on the rectifier side, the control angle of the converter to be tested in the first operating parameter refers to the conduction control angle of the converter to be tested, 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 to be tested is a converter on the inverter side, the control angle of the converter to be tested in the first operating parameter refers to the arc extinction control angle of the converter to be tested; 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 a possible implementation manner, a computer device displays a human-computer interaction interface, and acquires a first operating parameter and a second operating parameter input by a user based on the human-computer interaction interface.

[0050] In another possible implementation, the computer device is connected to a device (such as a sensor) for measuring operating parameters of a converter to be tested and measuring operating parameters of a target converter in a DC power transmission system to periodically acquire the first operating parameter and the second operating parameter.

[0051] Step 202: input the first operating parameter and the second operating parameter into a pre-selected and trained compensation model of the converter to be tested, and obtain a compensation voltage output by the compensation model of the converter to be tested.

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

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

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

[0055]

[0056] Among them, G i represents the i-th converter H i The operating parameters are:

[0057]

[0058] Among them, G i It can be an n×5 matrix, where n is the total step length; u ac represents the voltage on the AC side of the converter transformer; p represents the tap position of the converter transformer; i ac represents the AC side winding voltage of the converter transformer; α represents the control angle of the converter; I d Indicates the DC current of the inverter.

[0059] The principle of the above compensation model is as follows: when i is equal to 1, the first converter H is calculated 1 When the compensation voltage is 1 The operating parameters G 1 and the second converter H 2 The operating parameters G 2 Input the pre-trained first inverter H 1 Compensation model F Δ(1) , get the first converter H 1 Compensation model FΔ(1) The output compensation voltage is the first converter H 1 The compensation voltage ΔU 1 . With i=4, calculate the fourth converter H 4 When the compensation voltage is 4 The operating parameters G 4 and the third converter H 3 The operating parameters G 3 Input the pre-trained fourth inverter H 4 Compensation model F Δ(4) , and obtain the fourth inverter H 4 Compensation model F Δ(4) The output compensation voltage is the fourth converter H 4 The compensation voltage ΔU 4 .

[0060] Step 203, obtaining a theoretical voltage according to the first operating parameter and the DC voltage function, and obtaining a predicted voltage of the converter to be tested according to the compensation voltage and the theoretical voltage.

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

[0062]

[0063] Among them, U c Indicates the theoretical voltage; u ac represents the voltage on the AC side of the converter transformer; k represents the transformation ratio of the converter transformer; p represents the tap position of the converter transformer; i ac Indicates the AC side winding voltage of the converter transformer; X t represents the equivalent reactance of the converter transformer; α represents the conduction control angle of the converter; γ represents the arc extinction control angle of the converter; X r Represents the commutation reactance; I d Indicates the inverter DC current.

[0064] When the converter to be tested is a converter on the rectifier side, the computer device obtains the theoretical voltage according to the first operating parameter and the first DC voltage function. When the converter to be tested is a converter on the inverter side, 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 obtaining the theoretical voltage, the predicted voltage of the converter to be tested is obtained according to the compensation voltage and the theoretical voltage, including: the computer device uses the sum of the compensation voltage and the theoretical voltage as the predicted voltage of the converter to be tested. Figure 3The predicted voltage U of the ith converter in the DC transmission system is d(i) The data formula is expressed as follows:

[0066]

[0067] The above steps 201 to 203 can be regarded as a model of a multi-layer perceptron combined with a DC voltage theoretical calculation formula. The model can be named MLP-c model. The structure of the MLP-c model is as follows: Figure 4 shown.

[0068] Step 204, obtaining a detection result of the converter to be tested according to the predicted voltage and the measured voltage obtained by the voltage sensor on the converter to be tested.

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

[0070] Reference Figure 5 As shown, based on Figure 3 For the DC transmission system shown in the figure, for the i-th converter H i , the i-th converter H i The operating parameters G i and the i-th converter H i The operating parameters of the converters on the same side of the same pole are input to the i-th converter H i The MLP-c model of the i-th converter H i The predicted voltage U d(i) , and obtain the voltage sensor for the i-th converter H i The measured voltage U m(i) ; For the i-th converter H i Perform abnormality judgment, that is, judge the predicted voltage U d(i) With the measured voltage U m(i) Is the absolute value of the difference greater than or equal to the error threshold U th , expressed mathematically as follows:

[0071]

[0072] If so, then the i-th converter H i abnormal, the i-th converter H i is marked as a fault point; if not, the i-th converter H i normal.

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

[0074] The above-mentioned method for detecting abnormal voltage measurement in a DC power transmission system obtains a first operating parameter of the converter to be tested and a second operating parameter of the target converter, wherein the target converter is a converter on the same pole and the same side as the converter to be tested, and then inputs the first operating parameter and the second operating parameter into a pre-selected and trained compensation model of the converter to be tested to obtain a compensation voltage output by the compensation model of the converter to be tested, and then obtains a theoretical voltage based on the first operating parameter and a DC voltage function, and obtains a predicted voltage of the converter to be tested based on the compensation voltage and the theoretical voltage, and then obtains a detection result of the converter to be tested based on the predicted voltage and the measured voltage measured by the voltage sensor on the converter to be tested, thereby achieving the predicted voltage obtained by combining the trained compensation model and the DC voltage function, and compared with the method of obtaining the predicted voltage by only using a neural network model or directly using the DC voltage function, the accuracy of the predicted voltage can be improved, and thus the accuracy of the detection result obtained according to the predicted voltage and the measured voltage can be improved.

[0075] In an exemplary embodiment, Figure 6 As shown, a compensation model training method is provided, including steps 601 to 603. Among them:

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

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

[0078] Step 602, 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 the model to be trained to obtain a sample compensation voltage output by the model to be trained.

[0079] The model to be trained is a neural network model, such as 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 a DC voltage function to obtain a sample theoretical voltage, and a difference between the sample theoretical voltage and the sample measured voltage is used as the tag voltage.

[0081] Step 603: training the model to be trained based on the label voltage and the sample compensation voltage to obtain a compensation model of the converter to be tested.

[0082] In a possible implementation, a loss value is obtained according to a mean square error between a tag voltage and a sample compensation voltage; and a parameter of a model to be trained is updated according to the loss value to obtain a compensation model of the converter to be tested.

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

[0084]

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

[0086] During the training process, the Stochastic Gradient Descent (SGD) algorithm is used to update the parameters of the model to be trained. That is:

[0087] θ t+1 =θ t -α·loss (8)

[0088] Among them, θ is the parameter of the model to be trained, α is the learning rate, loss is the loss value, and t is the number of iterations.

[0089] The training is terminated when the number of iterations is greater than or equal to the number threshold, and the iterative training is continued when the number of iterations is less than the number threshold until the number of iterations is greater than or equal to the number threshold.

[0090] In addition, this application also conducted experiments on the real operating data of the DC transmission system over the past three years. Compared with the existing technology that only uses the DC voltage function and the classic deep learning model, the voltage prediction accuracy and anomaly detection accuracy are significantly improved. The comparison results between this application and the existing technology are as follows: Figure 7 shown.

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

[0092] The method for determining the accuracy of anomaly detection is to use different anomaly detection methods to predict the DC voltage of 8 converters at each sampling point on 207 sets of operating data with obvious voltage deviations collected in the DC transmission system over the past three years, and to determine the state (abnormal / normal) of each converter by calculating the difference between the measured value and the predicted value. The state of the converter with a deviation between the measured value and the predicted value greater than 0.005pu is determined as an abnormal state, that is, marked as a fault point. The model regards a normal converter as normal or a converter with measurement deviation as a fault in one time step as a correct identification. The statistical results of the recognition accuracy of each model are shown in Table 1 below.

[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 recognition rate 5.409％ 10.577％ 10.397％ 9.375％ 1.442％ 3.005％ False recognition rate 5.709％ 17.548％ 30.649％ 23.918％ 81.25％ 66.226％

[0095] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

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

[0097] In an exemplary embodiment, Figure 8 As shown, a device for detecting abnormal voltage measurement in a DC power transmission system is provided. The device for detecting abnormal voltage measurement in a DC power transmission system 800 includes: an acquisition module 801, a first determination module 802, a second determination module 803 and a third determination module 804, wherein:

[0098] An acquisition module 801 is used to acquire a first operating parameter of the converter to be tested and to acquire a second operating parameter of a target converter, where the target converter is a converter on the same pole and side as the converter to be tested;

[0099] A first determination module 802 is used to input the first operating parameter and the second operating parameter into a pre-selected and trained compensation model of the converter to be tested, so as to obtain a compensation voltage output by the compensation model of the converter to be tested;

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

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

[0102] In one embodiment, the device also includes a training module, which is used to obtain a first sample operating parameter of the converter to be tested, a sample measured voltage of the converter to be tested, and a second sample operating parameter of the target converter; obtain a label voltage based on the first sample operating parameter and the sample measured voltage; input the first sample operating parameter and the second sample operating parameter into the model to be trained to obtain a sample compensation voltage output by the model to be trained; and train the model to be trained based on the label voltage and the sample compensation voltage to obtain a compensation model of the converter to be tested.

[0103] In one embodiment, the DC voltage function includes 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 converter conduction control angle; the control angle of the converter in the second DC voltage function is the converter arc extinction control angle; the second determination module 803 is specifically used to obtain the theoretical voltage according to the first operating parameters and the first DC voltage function when the converter to be tested is a converter on the rectifier side; when the converter to be tested is a converter on the inverter side, the theoretical voltage is obtained according to the first operating parameters and the second DC voltage function.

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

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

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

[0107] Each module in the above-mentioned DC power transmission system voltage measurement abnormality detection device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0108] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig. 9As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. 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 operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (Near Field Communication, NFC) or other technologies. When the computer program is executed by the processor, a method for detecting abnormal voltage measurement in a DC power transmission system is implemented. 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, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0109] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0110] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of any one of the method embodiments described above are implemented.

[0111] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the above method embodiments are implemented.

[0112] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps of any one of the method embodiments described above.

[0113] Those of ordinary skill 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, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the 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. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0114] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0115] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations 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 shall be subject to the attached claims.

Claims

1. A method for detecting abnormal voltage measurement in a DC power transmission system, characterized in that: The method comprises: Acquire a first operating parameter of the converter to be tested, and acquire a second operating parameter of a target converter, wherein the target converter is a converter on the same pole and the same side as the converter to be tested; Inputting the first operating parameter and the second operating parameter into a pre-selected and trained compensation model of the converter to be tested, to obtain a compensation voltage output by the compensation model of the converter to be tested; Obtaining a theoretical voltage according to the first operating parameter and the DC voltage function, and obtaining a predicted voltage of the converter to be tested according to the compensation voltage and the theoretical voltage; The detection result of the converter to be tested is obtained according to the predicted voltage and the measured voltage obtained by the voltage sensor on the converter to be tested.

2. The method according to claim 1, characterized in that: The method further comprises: Acquire a first sample operating parameter of the converter to be tested, a sample measured voltage of the converter to be tested, and a second sample operating parameter of the target converter; Obtaining a tag 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 model to be trained to obtain a sample compensation voltage output by the model to be trained; The model to be trained is trained based on the label voltage and the sample compensation voltage to obtain a compensation model of the converter to be tested.

3. The method according to claim 1, characterized in that The DC voltage function includes a first DC voltage function and a second DC voltage function, wherein the control angle of the converter in the first DC voltage function is a converter conduction control angle; and the control angle of the converter in the second DC voltage function is a converter arc extinction control angle; The obtaining of the theoretical voltage according to the first operating parameter and the DC voltage function includes: When the converter to be tested is a converter on the rectifier side, the theoretical voltage is obtained according to the first operating parameter and the first DC voltage function; When the converter to be tested is a converter on the inverter side, the theoretical voltage is obtained according to the first operating parameter and the second DC voltage function.

4. The method according to any one of claims 1 to 3, characterized in that: The first operating parameters include the AC side voltage of the converter transformer in the DC power transmission system, the tap switch position of the converter transformer, the AC side winding voltage of the converter transformer, the control angle of the converter to be tested, and the DC current of the converter to be tested.

5. The method according to claim 1, characterized in that The step of obtaining a detection result of the converter to be tested according to the predicted voltage and a measured voltage obtained by a voltage sensor on the converter to be tested comprises: Subtract the predicted voltage from the measured voltage to obtain a difference; When the difference is greater than or equal to the error threshold, the detection result includes that the converter to be tested is abnormal.

6. The method according to claim 2, characterized in that The training of the model to be trained based on the tag voltage and the sample compensation voltage to obtain the compensation model of the converter to be tested includes: Obtaining a loss value according to a mean square error between the tag voltage and the sample compensation voltage; The parameters of the model to be trained are updated according to the loss value to obtain a compensation model of the converter to be tested.

7. A device for detecting abnormal voltage measurement in a DC power transmission system, characterized in that: The device comprises: An acquisition module, used to acquire a first operating parameter of the converter to be tested, and to acquire a second operating parameter of a target converter, wherein the target converter is a converter on the same pole and the same side as the converter to be tested; A first determination module, configured to input the first operating parameter and the second operating parameter into a pre-selected and trained compensation model of the converter to be tested, to obtain a compensation voltage output by the compensation model of the converter to be tested; A second determination module, configured to obtain a theoretical voltage according to the first operating parameter and a DC voltage function, and obtain a predicted voltage of the converter to be tested according to the compensation voltage and the theoretical voltage; The third determination module is used to obtain the detection result of the converter to be tested according to the predicted voltage and the measured voltage measured by the voltage sensor on the converter to be tested.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable 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 6 are implemented.

10. A computer program product, comprising a computer program, 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 6 are implemented.

Images