A novel method and device for identifying stray inductance in a bidirectional DC / DC converter.

Abstract

This application provides a novel method and apparatus for identifying stray inductance in a bidirectional DC / DC converter, relating to the field of power equipment maintenance. The method includes: energizing an insulated-gate bipolar transistor (IGBT) within the converter to a light-load operating state, and obtaining a light-load distribution map of the stray inductance in the converter using a magnetic display sticker disposed on a special busbar of the converter; obtaining a corresponding predicted distribution map based on the light-load distribution map and a pre-trained image converter; and weakening or shielding the stray inductance based on the predicted distribution map. This application can effectively identify stray inductance in a novel bidirectional DC / DC converter.

Description

Technical Field

[0001] This application relates to the field of power equipment maintenance, specifically a novel method and device for identifying stray inductance in a bidirectional DC / DC converter. Background Technology

[0002] To meet the high-voltage, high-power transmission requirements of power transmission lines, existing technologies mostly employ an input-series-output-parallel (ISOP) topology to construct high-voltage-to-low-voltage DC-DC converters. This topology consists of multiple isolated power modules. The modules on the input side are connected in series to ensure they can withstand medium to high voltages, while the output side is connected in parallel to the low-voltage bus to output a large current. See [link to ISOP topology] for details. Figure 1 As shown.

[0003] Among them, the isolated dual active bridge converter (abbreviated as isolated DAB converter) is a typical example built based on the ISOP topology, and it is widely used due to its numerous excellent characteristics. The topology of the isolated DAB converter is relatively simple, consisting of a high-frequency inverter on the input side, a high-frequency transformer located in the middle, and a high-frequency rectifier on the output side. See the structure below. Figure 2 As shown. Multiple isolated DAB converters can be combined in series and parallel to obtain an ISOP-DAB DC transformer; see the structure below. Figure 3 As shown. Figure 3 All DAB modules in the project aim to have completely identical parameters. However, due to limitations in real-world manufacturing processes, each module contains numerous components, inevitably leading to differences in parameters.

[0004] Figure 9 A novel bidirectional DC / DC converter is illustrated. Since stray inductance is highly detrimental to the insulated-gate bipolar transistors (IGBTs, the basic components of ISOP-DAB DC transformers) in the converter, it is necessary to detect the stray inductance Ls of the converter after circuit assembly. The stray inductance Ls mainly consists of two parts: the commutation circuit stray inductance Ls and the drive circuit stray inductance Lg. Existing techniques reduce stray inductance by lowering the Q value of the absorption circuit (Q value is generally referred to as the quality factor, a dimensionless unit that measures the performance of a component or resonant circuit), but this method is relatively inefficient. Summary of the Invention

[0005] To address the problems in the prior art, this application provides a novel method and apparatus for identifying stray inductance in a bidirectional DC / DC converter, which can effectively identify stray inductance in the novel bidirectional DC / DC converter.

[0006] To solve the above-mentioned technical problems, this application provides the following technical solution:

[0007] In a first aspect, this application provides a novel method for identifying stray inductance in a bidirectional DC / DC converter, comprising:

[0008] The insulated gate bipolar transistor in the converter is powered on to a light-load operating state, and the light-load distribution diagram of stray inductance in the converter is obtained by using a magnetic display sticker set on the special busbar of the converter.

[0009] Based on the light load distribution map and the pre-trained image transformer, the corresponding predicted distribution map is obtained;

[0010] Stray inductance is reduced or shielded based on the predicted distribution map.

[0011] Further, the step of training the image transformer includes:

[0012] The insulated gate bipolar transistor in the converter is powered on to a light-load operating state, and the light-load training distribution diagram of stray inductance in the converter is obtained by using a magnetic display sticker set on the special busbar of the converter.

[0013] The insulated gate bipolar transistor is powered on to its rated operating state, and the rated training distribution diagram of the stray inductance in the converter is obtained using the magnetic display sticker.

[0014] The image features corresponding to the light-load training distribution map and the rated training distribution map are input into the image classification network for training to obtain the image transformer.

[0015] Furthermore, the step of training the image transformer also includes:

[0016] Adjust the capacity and connection method of the insulated gate bipolar transistor;

[0017] Based on the insulated gate bipolar transistor after adjusting the capacity and connection method, obtain the light-load training change distribution diagram and the rated training change distribution diagram of the stray inductance in the converter.

[0018] The image features corresponding to the light-load training change distribution map and the rated training change distribution map are input into the image classification network for training to obtain the image transformer.

[0019] Further, obtaining the corresponding predicted distribution map based on the lightly loaded distribution map and the pre-trained image transformer includes:

[0020] Image feature analysis is performed on the light load distribution map to obtain the corresponding light load image features;

[0021] The lightly loaded image features are input into the image transformer to obtain the corresponding predicted distribution map.

[0022] Secondly, this application provides a novel device for identifying stray inductance in a bidirectional DC / DC converter, comprising:

[0023] The light load distribution acquisition unit is used to control the insulated gate bipolar transistor in the converter to be powered on to the light load operating state, and to acquire the light load distribution diagram of stray inductance in the converter using a magnetic display sticker set on the special busbar of the converter.

[0024] A stray distribution prediction unit is used to obtain a corresponding predicted distribution map based on the light load distribution map and a pre-trained image transformer.

[0025] A stray inductance adjustment unit is used to weaken or shield stray inductance based on the predicted distribution map.

[0026] Furthermore, the stray inductance identification device in the novel bidirectional DC / DC converter further includes:

[0027] The light-load training distribution acquisition unit is used to control the insulated gate bipolar transistor in the converter to be powered on to the light-load operating state, and to acquire the light-load training distribution map of stray inductance in the converter using a magnetic display sticker set on the special busbar of the converter.

[0028] The rated training distribution acquisition unit is used to control the insulated gate bipolar transistor to power on to the rated operating state and to acquire the rated training distribution diagram of the stray inductance in the converter using the magnetic display sticker.

[0029] The first model generation unit is used to input the image features corresponding to the light-load training distribution map and the rated training distribution map into the image classification network for training, thereby obtaining the image transformer.

[0030] Furthermore, the stray inductance identification device in the novel bidirectional DC / DC converter further includes:

[0031] A capacity connection adjustment unit is used to adjust the capacity and connection method of the insulated gate bipolar transistor;

[0032] The change distribution acquisition unit is used to acquire the light-load training change distribution map and the rated training change distribution map of the stray inductance in the converter based on the insulated gate bipolar transistor after adjusting the capacity and connection method.

[0033] The second model generation unit is used to input the image features corresponding to the light-load training change distribution map and the rated training change distribution map into the image classification network for training, thereby obtaining the image transformer.

[0034] Furthermore, the stray distribution prediction unit includes:

[0035] The image feature extraction module is used to perform image feature analysis on the light load distribution map to obtain the corresponding light load image features;

[0036] The stray inductance prediction module is used to input the lightly loaded image features into the image transformer to obtain the corresponding predicted distribution map.

[0037] Thirdly, this application provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method for identifying stray inductance in the novel bidirectional DC / DC converter.

[0038] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for identifying stray inductance in the novel bidirectional DC / DC converter.

[0039] Fifthly, this application provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the method for identifying stray inductance in the novel bidirectional DC / DC converter.

[0040] To address the problems in the prior art, this application provides a novel method and apparatus for identifying stray inductance in a bidirectional DC / DC converter. This method and apparatus can effectively identify stray inductance in the novel bidirectional DC / DC converter and can predict the stray inductance distribution of the IGBT under other operating conditions based on the stray inductance of the IGBT under light load operation. This provides a good reference for subsequently installing stray inductance shielding and reduction devices outside the IGBT. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a schematic diagram of the ISOP structure in the prior art;

[0043] Figure 2 This is a schematic diagram of the structure of an isolated DAB converter in the prior art;

[0044] Figure 3 This is a schematic diagram of the structure of the ISOP-DAB DC transformer in the prior art;

[0045] Figure 4This is a schematic diagram of the bidirectional DC / DC converter topology in an embodiment of this application;

[0046] Figure 5 This is a flowchart of a method for identifying stray inductance in a novel bidirectional DC / DC converter according to an embodiment of this application;

[0047] Figure 6 This is one of the flowcharts for training an image recognizer in the embodiments of this application;

[0048] Figure 7 This is the second flowchart of the training image recognizer in the embodiments of this application;

[0049] Figure 8 This is a flowchart illustrating stray inductance prediction in an embodiment of this application;

[0050] Figure 9 This is one of the structural diagrams of the stray inductance identification device in the novel bidirectional DC / DC converter in the embodiments of this application;

[0051] Figure 10 This is the second structural diagram of the stray inductance identification device in the novel bidirectional DC / DC converter in this application embodiment;

[0052] Figure 11 This is the third structural diagram of the stray inductance identification device in the novel bidirectional DC / DC converter in this application embodiment;

[0053] Figure 12 This is a structural diagram of the stray distribution prediction unit in the embodiments of this application;

[0054] Figure 13 This is a schematic diagram of the structure of the electronic device in the embodiments of this application. Detailed Implementation

[0055] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0056] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0057] In one embodiment, see Figure 4 This novel bidirectional DC / DC converter topology includes: a converter input terminal and a converter output terminal.

[0058] The converter input terminal includes multiple stages of input full-bridge converters connected in series; the number of stages of the input full-bridge converter is 2N; the input full-bridge converters from the 1st stage to the 2Nth stage are connected in series; the positive DC terminal of the 1st stage input full-bridge converter is connected to the positive terminal of the high-voltage bus (UdcL+), and the negative DC terminal of the 2Nth stage input full-bridge converter is connected to the negative terminal of the high-voltage bus (UdcL-); the DC terminals of the Nth stage input full-bridge converter and the (N+1)th stage input full-bridge converter are both grounded; N is a positive integer greater than 2.

[0059] The converter output terminal includes a multi-stage output full-bridge converter connected in parallel; the positive DC terminal of each stage of the output full-bridge converter is connected to the positive terminal of the low-voltage bus (UdcL+), and the negative DC terminal of each stage of the output full-bridge converter is connected to the negative terminal of the low-voltage bus (UdcL-).

[0060] It should be noted that Udc+ and Udc- are the positive and negative terminals of the DC side (also known as the DC terminal), respectively. Udc represents the voltage difference between the positive and negative terminals of the DC side. Uac+ and Uac- represent the positive and negative terminals of the AC side, respectively. Uac represents the voltage difference between the positive and negative terminals of the AC side. Figure 4 In this context, FBC refers to the full-bridge converter.

[0061] In one embodiment, see Figure 5 In order to effectively identify stray inductance in a novel bidirectional DC / DC converter, this application provides a method for identifying stray inductance in a novel bidirectional DC / DC converter, including:

[0062] S101: Power on the insulated gate bipolar transistor in the converter to a light-load operating state, and use the magnetic display sticker set on the special busbar of the converter to obtain the light-load distribution diagram of the stray inductance in the converter.

[0063] S102: Obtain the corresponding predicted distribution map based on the light load distribution map and the pre-trained image transformer;

[0064] S103: Reduce or shield stray inductance based on the predicted distribution map.

[0065] Understandably, the stray inductance of a converter can cause high voltage spikes between the collector and emitter of the insulated-gate bipolar transistor (IGBT), resulting in significant electromagnetic interference and potentially damaging the IGBT. Measuring the converter's stray inductance can help predict these voltage spikes to some extent and allow for the design of appropriate buffer circuits.

[0066] To address the problems existing in the prior art, this application will first describe the impact of stray inductance in the novel bidirectional DC / DC converter on the turn-on of the insulated-gate bipolar transistor (IGBT), its turn-off, and its turn-off tail current. These three aspects demonstrate that the presence of stray inductance poses a threat to the stability and safety of IGBT operation.

[0067] Specifically, stray inductance is generated only when the current in the converter changes. The stray inductance includes the stray inductance of the bus capacitor, the stray inductance between the bus capacitor and the IGBT module, and the stray inductance inside each module of the converter (such as stray inductance between terminals, bonding wires, and stray inductance of the DCB copper layer).

[0068] The effect of stray inductance on IGBT turn-on is as follows:

[0069] The larger the stray inductance, the larger the collector-emitter voltage V. ce The greater the drop, the more its waveform can be observed using a double-pulse test;

[0070] The larger the stray inductance, the larger the collector current d. ic / d t The lower;

[0071] The larger the stray inductance, the higher the turn-on loss E. on Instead, it decreased.

[0072] It is evident that stray inductance is detrimental to the turn-on of IGBTs.

[0073] The effect of stray inductance on IGBT turn-off is as follows:

[0074] The larger the stray inductance, the larger the collector-emitter voltage V. ce The greater the voltage overshoot, the greater the risk of overvoltage breakdown;

[0075] The larger the stray inductance, the larger the collector current i. c The slower the descent slope, the longer it takes to reach the tail area;

[0076] The larger the stray inductance, the less noticeable the tail current, the harder the turn-off, and the higher the turn-off loss E. off The larger;

[0077] It is evident that stray inductance is highly detrimental to the turn-off of IGBTs.

[0078] In addition, stray inductance also affects the turn-off tail current:

[0079] An increase in turn-off overvoltage causes the electric field within the IGBT to expand and remove more charge carriers, with the remaining charge carriers forming the tail current. If the stray inductance is too large, under high bus voltage, the excessively high voltage spikes cause the tail current to decrease or even disappear, resulting in strong turn-off oscillations, i.e., sudden turn-off, which has a significant impact on the IGBT's FS layer.

[0080] Based on the above conclusions, this application provides a method for identifying stray inductance on an IGBT, which can clearly identify the location of stray inductance in the IGBT, so as to reduce the stray inductance at that location in practical engineering. Specifically, in the embodiments of this application, the insulated gate bipolar transistor in the converter is powered on and adjusted to a light-load operating state; a light-load distribution map of stray inductance in the converter is obtained using a magnetic display sticker set on a special busbar of the converter, wherein the so-called light-load distribution map refers to the distribution map of stray inductance when the converter is operating in a light-load state; based on the light-load distribution map and a pre-trained image converter, a corresponding predicted distribution map is obtained, wherein the so-called predicted distribution map refers to the distribution map of stray inductance when the converter is operating in other states (such as heavy-load state, normal operating state, and fault state, etc.); stray inductance is reduced or shielded based on the predicted distribution map.

[0081] As can be seen from the above description, the stray inductance identification method in the novel bidirectional DC / DC converter provided in this application can effectively identify the stray inductance in the novel bidirectional DC / DC converter, and can predict the stray inductance distribution of the IGBT under other operating conditions based on the stray inductance of the IGBT when it is running under light load, thereby providing a good reference for the subsequent installation of stray inductance shielding and reduction devices outside the IGBT.

[0082] The following provides a detailed explanation of steps S101 to S103.

[0083] Step S101: Power on the insulated gate bipolar transistor in the converter to a light-load operating state, and use the magnetic display sticker set on the special busbar of the converter to obtain the light-load distribution diagram of the stray inductance in the converter.

[0084] Understandably, a magnetic display sticker is applied to the flat wires and special busbars of the IGBT assembly. The IGBT, assembled in the previous step, is powered on and adjusted to a light-load operating state. The magnetic display sticker is observed statically for 15-30 minutes; it will then show the distribution of stray inductance, and this image is saved. After powering on and operating under rated conditions, the distribution of stray inductance is again displayed using the magnetic display sticker, and this image is saved again. This yields a set of comparative stray inductance distribution diagrams for light-load and rated-condition operation.

[0085] In a power system, a busbar refers to the copper or aluminum busbar connecting the main switch and the switches in each branch circuit within the electrical cabinet. Its surface is insulated, and its primary function is to serve as a conductor. A special-type busbar refers to a busbar customized for current new bidirectional DC / DC converters. Wrapping a magnetic display sticker around a group of IGBTs in a DC / DC converter can reveal the magnetic circuit around that group of IGBTs. Taking a photo of the magnetic display sticker allows for data entry into a computer.

[0086] As can be seen from the above description, the method for identifying stray inductance in a novel bidirectional DC / DC converter provided in this application can control the insulated gate bipolar transistor in the converter to be powered on to a light-load operating state, and use a magnetic display sticker set on the special busbar of the converter to obtain a light-load distribution map of stray inductance in the converter.

[0087] Step S102: Obtain the corresponding predicted distribution map based on the light load distribution map and the pre-trained image transformer.

[0088] It is understood that in this embodiment, the image features corresponding to the light load distribution map should be extracted first. Specific methods may include, but are not limited to:

[0089] Method 1: Take photos of key areas of the magnetic display sticker and then input them into the computer. Method 2: Quickly remove the magnetic display sticker, place it on a flat surface, and then take photos.

[0090] Figure 6 This is a specific embodiment of the method for identifying stray inductance in a novel bidirectional DC / DC converter, as described in this application.

[0091] In one embodiment, see Figure 6 The steps for training the image transformer include:

[0092] S201: Power on the insulated gate bipolar transistor in the converter to a light-load operating state, and use the magnetic display sticker set on the special busbar of the converter to obtain the light-load training distribution map of the stray inductance in the converter.

[0093] S202: Control the insulated gate bipolar transistor to power on to the rated operating state, and use the magnetic display sticker to obtain the rated training distribution diagram of the stray inductance in the converter;

[0094] S203: Input the image features corresponding to the light-load training distribution map and the rated training distribution map into the image classification network for training to obtain the image transformer.

[0095] Among them, the effective value of current is generally small, the effective value of voltage is generally near the rated value, and the power passing through the DC / DC converter is generally small.

[0096] It is understood that in the embodiments of this application, by setting different IGBT capacities and different IGBT connection methods, and repeating the process several times (e.g., more than 2000 times), several sets of stray inductance comparison diagrams of IGBT under light load operation and rated operating conditions under different capacities and connection methods can be obtained.

[0097] After accumulating comparative images, an image model can be trained to obtain the image features of the stray inductance distribution map of the input IGBT under light load conditions. This allows the output image converter to capture the features of the stray inductance distribution map of the IGBT under rated operating conditions. In some operating conditions, the IGBT can only operate under light load conditions and not under rated operating conditions for various reasons. In such cases, this image converter can be used to predict the stray inductance distribution of the IGBT under rated operating conditions.

[0098] The image model training process is described in detail below.

[0099] 6.1 A classification model is constructed using the ResNet50 network. Like other image classification networks, the ResNet50 network is a reliable image classification network. In the ResNet50 network, the 50 refers to 50 layers with weights, including 49 convolutional layers and 1 fully connected layer, excluding pooling layers and batch normalization (BN) layers. This classification model has inputs and outputs; each batch of data popped by the iterator serves as input, determining whether the electrical meter image is corrupted.

[0100] 6.2 Define the training function and start training, including model training, validation, and printing loss values. Generally, this is written as the following code snippet and implemented in a loop.

[0101] for eval_x,eval_y in eval_loader:

[0102] outs = model(eval_x)

[0103] loss = loss_func(outs, eval_y)

[0104] eval_loss += loss

[0105] Model training consists of several epochs; this example uses 20 epochs. The overall model training process is printed as follows:

[0106] ----------epoch:0,train_loss:0.729,eval_loss:0.773,eval_acc:0.734-------

[0107] ---------epoch:1,train_loss:0.408,eval_loss:0.367,eval_acc:0.859-------

[0108] ---------epoch:2,train_loss:0.307,eval_loss:0.431,eval_acc:0.828-------

[0109] ---------epoch:3,train_loss:0.256,eval_loss:0.541,eval_acc:0.828-------

[0110] ---------epoch:4,train_loss:0.270,eval_loss:0.404,eval_acc:0.922-------

[0111] ---------epoch:5,train_loss:0.271,eval_loss:0.535,eval_acc:0.906-------

[0112] ---------epoch:6,train_loss:0.245,eval_loss:0.584,eval_acc:0.906-------

[0113] ---------epoch:7,train_loss:0.158,eval_loss:0.394,eval_acc:0.922-------

[0114] ---------epoch:8,train_loss:0.100,eval_loss:0.446,eval_acc:0.938-------

[0115] ---------epoch:9,train_loss:0.096,eval_loss:0.438,eval_acc:0.938-------

[0116] ---------epoch:10,train_loss:0.094,eval_loss:0.414,eval_acc:0.938-------

[0117] ---------epoch:11,train_loss:0.081,eval_loss:0.436,eval_acc:0.938-------

[0118] ---------epoch:12,train_loss:0.057,eval_loss:0.444,eval_acc:0.938-------

[0119] ---------epoch:13,train_loss:0.068,eval_loss:0.580,eval_acc:0.922-------

[0120] ---------epoch:14,train_loss:0.073,eval_loss:0.479,eval_acc:0.938-------

[0121] ---------epoch:15,train_loss:0.053,eval_loss:0.507,eval_acc:0.938-------

[0122] ---------epoch:16,train_loss:0.031,eval_loss:0.545,eval_acc:0.938-------

[0123] ---------epoch:17,train_loss:0.031,eval_loss:0.511,eval_acc:0.953-------

[0124] ---------epoch:18,train_loss:0.039,eval_loss:0.436,eval_acc:0.938-------

[0125] ---------epoch:19,train_loss:0.049,eval_loss:0.508,eval_acc:0.906-------

[0126] 6.3 Plot the loss function curves. The vertical axis includes the curve of the loss value decreasing during training on the training set (train_loss), the curve of the loss value decreasing during training on the validation set (eval_loss), and the overall validation accuracy (eval_acc). We can see that the accuracy is highest in the 17th round, so we can choose the model trained in the 17th round. After training, save the obtained network model weight parameters.

[0127] As can be seen from the above description, the method for identifying stray inductance in a novel bidirectional DC / DC converter provided in this application can be used to train an image converter.

[0128] Figure 7 This is a specific embodiment of the method for identifying stray inductance in a novel bidirectional DC / DC converter, as described in this application.

[0129] In one embodiment, see Figure 7 The step of training the image transformer further includes:

[0130] S301: Adjust the capacity and connection method of the insulated gate bipolar transistor;

[0131] S302: Based on the insulated gate bipolar transistor after adjusting the capacity and connection method, obtain the light-load training change distribution diagram and the rated training change distribution diagram of the stray inductance in the converter.

[0132] S303: Input the image features corresponding to the light-load training change distribution map and the rated training change distribution map into the image classification network for training to obtain the image transformer.

[0133] It is understandable that steps S301 to S303 can be interpreted as a process of further training the model after steps S201 to S203. This includes adjusting the capacitance and connection method of the insulated-gate bipolar transistor (IGBT). Specific adjustment methods may include, but are not limited to: using computer simulation methods to change the capacitance parameters of the IGBT and changing the connection method of the IGBT.

[0134] After adjusting the capacity and connection method of the insulated-gate bipolar transistor, the distribution map of stray inductance in the converter is further obtained. Specifically, the distribution map of stray inductance under light load training and rated operating conditions is obtained. Next, image features are extracted from the light load training and rated operating conditions. The extraction method is described in steps S401 to S402. The extracted image features are input into an image classification network or into the image converter generated in step S203 to further adjust the image converter generated in step S203, thereby obtaining an image converter with better prediction performance.

[0135] As can be seen from the above description, the method for identifying stray inductance in a novel bidirectional DC / DC converter provided in this application can train and optimize the image converter.

[0136] Figure 8 This is a specific embodiment of the method for identifying stray inductance in a novel bidirectional DC / DC converter, as described in this application.

[0137] In one embodiment, see Figure 8 The step of obtaining the corresponding predicted distribution map based on the light load distribution map and the pre-trained image transformer includes:

[0138] S401: Perform image feature analysis on the light load distribution map to obtain the corresponding light load image features;

[0139] Understandably, the lightly loaded image features can be obtained by following these steps.

[0140] The first step is to record waveforms of the DC / DC converter under light load conditions, obtain light load images, and store them in a computer.

[0141] The second step involves using image editing software to crop the image edges and using a bandpass filter to remove background noise. This yields image information focusing on voltage and current waveforms under light load conditions.

[0142] The third step is to compare the results of the second step, analyze the outliers and bad pixels, and remove the outliers and bad pixels.

[0143] The fourth step is to compare the results of the third step, analyze the reasonable features of the light load image, such as the effective value of current and the effective value of voltage, and mark the reasonable features.

[0144] S402: Input the lightly loaded image features into the image transformer to obtain the corresponding predicted distribution map.

[0145] It is understandable that a light-load image has at least the following characteristics: a smaller effective current value, an effective voltage value near the rated value, and a smaller power passing through the DC / DC converter.

[0146] In practice, there are many tools available for image feature analysis, and this application does not limit the scope of such tools. In the embodiments of this application, image features include, but are not limited to, the effective value of current, the effective value of voltage, and the power passing through the DC / DC converter.

[0147] As can be seen from the above description, the stray inductance identification method in the novel bidirectional DC / DC converter provided in this application can obtain the corresponding predicted distribution map based on the light load distribution map and the pre-trained image converter.

[0148] Step S103: Reduce or shield stray inductance based on the predicted distribution map.

[0149] Understandably, predicting the stray inductance under IGBT rated operating conditions allows us to determine the location of the stray inductance, thus providing a good foundation for installing stray inductance shielding and mitigation devices outside the IGBT. These mitigation and shielding methods can include, but are not limited to, installing external magnets, coils, or shielding metal shells.

[0150] As can be seen from the above description, the stray inductance identification method in the novel bidirectional DC / DC converter provided in this application can weaken or shield stray inductance based on the predicted distribution map.

[0151] Based on the same inventive concept, this application also provides a novel stray inductance identification device in a bidirectional DC / DC converter, which can be used to implement the method described in the above embodiments, as described in the following embodiments. Since the principle of the novel stray inductance identification device in a bidirectional DC / DC converter is similar to the stray inductance identification method in a novel bidirectional DC / DC converter, the implementation of the novel stray inductance identification device in a bidirectional DC / DC converter can refer to the implementation of the software performance benchmark determination method, and will not be repeated. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the system described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0152] In one embodiment, see Figure 9 In order to effectively identify stray inductance in a novel bidirectional DC / DC converter, this application provides a stray inductance identification device for a novel bidirectional DC / DC converter, including: a light load distribution acquisition unit 901, a stray distribution prediction unit 902, and a stray adjustment unit 903.

[0153] The light load distribution acquisition unit 901 is used to control the insulated gate bipolar transistor in the converter to be powered on to the light load operating state, and to acquire the light load distribution diagram of stray inductance in the converter using a magnetic display sticker set on the special busbar of the converter.

[0154] The stray distribution prediction unit 902 is used to obtain the corresponding predicted distribution map based on the light load distribution map and the pre-trained image transformer.

[0155] The stray inductance adjustment unit 903 is used to weaken or shield stray inductance based on the predicted distribution map.

[0156] In one embodiment, see Figure 10 The stray inductance identification device in the novel bidirectional DC / DC converter further includes: a light-load training distribution acquisition unit 1001, a rated training distribution acquisition unit 1002, and a first model generation unit 1003.

[0157] The light-load training distribution acquisition unit 1001 is used to control the insulated gate bipolar transistor in the converter to be powered on to the light-load operating state, and to acquire the light-load training distribution map of stray inductance in the converter using the magnetic display sticker set on the special busbar of the converter.

[0158] The rated training distribution acquisition unit 1002 is used to control the insulated gate bipolar transistor to power on to the rated operating state and to acquire the rated training distribution diagram of the stray inductance in the converter using the magnetic display sticker.

[0159] The first model generation unit 1003 is used to input the image features corresponding to the light-load training distribution map and the rated training distribution map into the image classification network for training, so as to obtain the image transformer.

[0160] In one embodiment, see Figure 11 The stray inductance identification device in the novel bidirectional DC / DC converter further includes: a capacity connection adjustment unit 1101, a change distribution acquisition unit 1102, and a second model generation unit 1103.

[0161] The capacity connection adjustment unit 1101 is used to adjust the capacity and connection method of the insulated gate bipolar transistor;

[0162] The change distribution acquisition unit 1102 is used to acquire the light-load training change distribution map and the rated training change distribution map of the stray inductance in the converter based on the insulated gate bipolar transistor after adjusting the capacity and connection method.

[0163] The second model generation unit 1103 is used to input the image features corresponding to the light-load training change distribution map and the rated training change distribution map into the image classification network for training, so as to obtain the image transformer.

[0164] In one embodiment, see Figure 12 The stray distribution prediction unit 902 includes: an image feature extraction module 1201 and a stray inductance prediction module 1202.

[0165] Image feature extraction module 1201 is used to perform image feature analysis on the light load distribution map to obtain the corresponding light load image features;

[0166] The stray inductance prediction module 1202 is used to input the lightly loaded image features into the image transformer to obtain the corresponding predicted distribution map.

[0167] From a hardware perspective, in order to effectively identify stray inductance in a novel bidirectional DC / DC converter, this application provides an embodiment of an electronic device for implementing all or part of the method for identifying stray inductance in the novel bidirectional DC / DC converter. The electronic device specifically includes the following components:

[0168] The system comprises a processor, a memory, a communications interface, and a bus; wherein the processor, memory, and communications interface communicate with each other via the bus; the communications interface is used to realize information transmission between the stray inductor identification device in the novel bidirectional DC / DC converter and related equipment such as the core business system, user terminals, and related databases; the logic controller can be a desktop computer, tablet computer, or mobile terminal, etc., and this embodiment is not limited to these. In this embodiment, the logic controller can be implemented with reference to the embodiments of the stray inductor identification method and the stray inductor identification device in the novel bidirectional DC / DC converter described in the embodiments, the contents of which are incorporated herein, and repeated details will not be described again.

[0169] It is understood that the user terminal may include smartphones, tablet computers, network set-top boxes, portable computers, desktop computers, personal digital assistants (PDAs), in-vehicle devices, smart wearable devices, etc. Among these, the smart wearable devices may include smart glasses, smartwatches, smart bracelets, etc.

[0170] In practical applications, the method for identifying stray inductance in the novel bidirectional DC / DC converter can be partially executed on the electronic device side as described above, or all operations can be completed in the client device. The specific choice depends on the processing power of the client device and the limitations of the user's usage scenario. This application does not impose any limitations on this. If all operations are completed in the client device, the client device may further include a processor.

[0171] The aforementioned client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission. The server may include a server on the task scheduling center side; in other implementation scenarios, it may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, a server cluster consisting of multiple servers, or a distributed server structure.

[0172] Figure 13 This is a schematic block diagram illustrating the system configuration of the electronic device 9600 according to an embodiment of this application. Figure 13 As shown, the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It is worth noting that... Figure 13 This is an example; other types of structures can also be used to supplement or replace this structure to achieve telecommunications functions or other functions.

[0173] In one embodiment, the method for identifying stray inductance in the novel bidirectional DC / DC converter can be integrated into the central processing unit 9100. The central processing unit 9100 can be configured to perform the following control:

[0174] S101: Power on the insulated gate bipolar transistor in the converter to a light-load operating state, and use the magnetic display sticker set on the special busbar of the converter to obtain the light-load distribution diagram of the stray inductance in the converter.

[0175] S102: Obtain the corresponding predicted distribution map based on the light load distribution map and the pre-trained image transformer;

[0176] S103: Reduce or shield stray inductance based on the predicted distribution map.

[0177] As can be seen from the above description, the stray inductance identification method in the novel bidirectional DC / DC converter provided in this application can effectively identify the stray inductance in the novel bidirectional DC / DC converter, and can predict the stray inductance distribution of the IGBT under other operating conditions based on the stray inductance of the IGBT when it is running under light load, thereby providing a good reference for the subsequent installation of stray inductance shielding and reduction devices outside the IGBT.

[0178] In another embodiment, the stray inductance identification device in the novel bidirectional DC / DC converter can be configured separately from the central processing unit 9100. For example, the stray inductance identification device in the novel bidirectional DC / DC converter can be configured as a chip connected to the central processing unit 9100, and the function of the stray inductance identification method in the novel bidirectional DC / DC converter can be realized through the control of the central processing unit.

[0179] like Figure 13 As shown, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily need to include these components. Figure 13 All components shown; in addition, the electronic device 9600 may also include Figure 13 For components not shown, please refer to existing technologies.

[0180] like Figure 13 As shown, the central processing unit 9100, sometimes also referred to as a controller or operating control, may include a microprocessor or other processor device and / or logic device, which receives inputs and controls the operation of various components of the electronic device 9600.

[0181] The memory 9140 may be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It may store the aforementioned failure-related information, and also store a program for executing that information. The central processing unit 9100 may execute the program stored in the memory 9140 to perform information storage or processing, etc.

[0182] Input unit 9120 provides input to central processing unit 9100. Input unit 9120 may be, for example, a keypad or touch input device. Power supply 9170 provides power to electronic device 9600. Display 9160 displays images and text. Display may be, for example, an LCD display, but is not limited thereto.

[0183] The memory 9140 can be a solid-state memory, such as a read-only memory (ROM), random access memory (RAM), SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and contains more data; examples of this type of memory are sometimes referred to as EPROMs. The memory 9140 can also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142 for storing application programs and function programs or processes for executing the operation of the electronic device 9600 via the central processing unit 9100.

[0184] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for the electronic device's communication functions and / or for performing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0185] The communication module 9110 is a transmitter / receiver 9110 that transmits and receives signals via the antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processing unit 9100 to provide input signals and receive output signals, which can be the same as in a conventional mobile communication terminal.

[0186] Based on different communication technologies, multiple communication modules 9110 can be configured in the same electronic device, such as cellular network modules, Bluetooth modules, and / or wireless LAN modules. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby realizing typical telecommunications functions. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. Additionally, the audio processor 9130 is also coupled to a central processing unit 9100, enabling on-device recording via the microphone 9132 and on-device playback of stored sound via the speaker 9131.

[0187] Embodiments of this application also provide a computer-readable storage medium capable of implementing all steps of the novel bidirectional DC / DC converter stray inductance identification method with a server or client execution subject as described in the above embodiments. The computer-readable storage medium stores a computer program that, when executed by a processor, implements all steps of the novel bidirectional DC / DC converter stray inductance identification method with a server or client execution subject as described in the above embodiments. For example, when the processor executes the computer program, it implements the following steps:

[0188] S101: Power on the insulated gate bipolar transistor in the converter to a light-load operating state, and use the magnetic display sticker set on the special busbar of the converter to obtain the light-load distribution diagram of the stray inductance in the converter.

[0189] S102: Obtain the corresponding predicted distribution map based on the light load distribution map and the pre-trained image transformer;

[0190] S103: Reduce or shield stray inductance based on the predicted distribution map.

[0191] As can be seen from the above description, the stray inductance identification method in the novel bidirectional DC / DC converter provided in this application can effectively identify the stray inductance in the novel bidirectional DC / DC converter, and can predict the stray inductance distribution of the IGBT under other operating conditions based on the stray inductance of the IGBT when it is running under light load, thereby providing a good reference for the subsequent installation of stray inductance shielding and reduction devices outside the IGBT.

[0192] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0193] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0194] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0195] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0196] Specific embodiments have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

Claims

1. A novel method for identifying stray inductance in a bidirectional DC / DC converter, characterized in that, include: The insulated gate bipolar transistor in the converter is powered on to a light-load operating state, and the light-load distribution diagram of stray inductance in the converter is obtained by using a magnetic display sticker set on the special busbar of the converter. Based on the light load distribution map and the pre-trained image transformer, the corresponding predicted distribution map is obtained; Stray inductance is reduced or shielded based on the predicted distribution map; The step of training the image transformer includes: The insulated gate bipolar transistor in the converter is powered on to a light-load operating state, and the light-load training distribution diagram of stray inductance in the converter is obtained by using a magnetic display sticker set on the special busbar of the converter. The insulated gate bipolar transistor is powered on to its rated operating state, and the rated training distribution diagram of the stray inductance in the converter is obtained using the magnetic display sticker. The image features corresponding to the light-load training distribution map and the rated training distribution map are input into the image classification network for training to obtain the image transformer.

2. The method for identifying stray inductance in a novel bidirectional DC / DC converter according to claim 1, characterized in that, The step of training the image transformer further includes: Adjust the capacity and connection method of the insulated gate bipolar transistor; Based on the insulated gate bipolar transistor after adjusting the capacity and connection method, obtain the light-load training change distribution diagram and the rated training change distribution diagram of the stray inductance in the converter. The image features corresponding to the light-load training change distribution map and the rated training change distribution map are input into the image classification network for training to obtain the image transformer.

3. The method for identifying stray inductance in a novel bidirectional DC / DC converter according to claim 1, characterized in that, The process of obtaining the corresponding predicted distribution map based on the light-load distribution map and the pre-trained image transformer includes: Image feature analysis is performed on the light load distribution map to obtain the corresponding light load image features; The lightly loaded image features are input into the image transformer to obtain the corresponding predicted distribution map.

4. A novel device for identifying stray inductance in a bidirectional DC / DC converter, characterized in that, include: The light load distribution acquisition unit is used to control the insulated gate bipolar transistor in the converter to be powered on to the light load operating state, and to acquire the light load distribution diagram of stray inductance in the converter using a magnetic display sticker set on the special busbar of the converter. A stray distribution prediction unit is used to obtain a corresponding predicted distribution map based on the light load distribution map and a pre-trained image transformer. A stray inductance reduction or shielding unit is used based on the predicted distribution map. The light-load training distribution acquisition unit is used to control the insulated gate bipolar transistor in the converter to be powered on to the light-load operating state, and to acquire the light-load training distribution map of stray inductance in the converter using a magnetic display sticker set on the special busbar of the converter. The rated training distribution acquisition unit is used to control the insulated gate bipolar transistor to power on to the rated operating state and to acquire the rated training distribution diagram of the stray inductance in the converter using the magnetic display sticker. The first model generation unit is used to input the image features corresponding to the light-load training distribution map and the rated training distribution map into the image classification network for training, thereby obtaining the image transformer.

5. The stray inductance identification device in the novel bidirectional DC / DC converter according to claim 4, characterized in that, Also includes: A capacity connection adjustment unit is used to adjust the capacity and connection method of the insulated gate bipolar transistor; The change distribution acquisition unit is used to acquire the light-load training change distribution map and the rated training change distribution map of the stray inductance in the converter based on the insulated gate bipolar transistor after adjusting the capacity and connection method. The second model generation unit is used to input the image features corresponding to the light-load training change distribution map and the rated training change distribution map into the image classification network for training, so as to obtain the image transformer.

6. The stray inductance identification device in the novel bidirectional DC / DC converter according to claim 4, characterized in that, The stray distribution prediction unit includes: The image feature extraction module is used to perform image feature analysis on the light load distribution map to obtain the corresponding light load image features; The stray inductance prediction module is used to input the lightly loaded image features into the image transformer to obtain the corresponding predicted distribution map.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method for identifying stray inductance in the novel bidirectional DC / DC converter according to any one of claims 1 to 3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method for identifying stray inductance in the novel bidirectional DC / DC converter according to any one of claims 1 to 3.

9. A computer program product comprising a computer program / instructions, characterized in that, When executed by a processor, the computer program / instruction implements the steps of the method for identifying stray inductance in the novel bidirectional DC / DC converter according to any one of claims 1 to 3.

Images