A production process optimization method and system for high-voltage frequency converter

Abstract

The present disclosure provides a production process optimization method and system for high-voltage frequency converters, which relates to high-voltage frequency converter technology. The method includes: obtaining the expected working scenario of the high-voltage frequency converter, including working environment information and working space information; generating the convective heat transfer coefficient under the expected working scenario; obtaining the target heat dissipation performance after heat dissipation evaluation; obtaining heat dissipation control parameters, including the number of heat sinks, the number of air outlets, and the type of heat dissipation materials; optimizing with the target heat dissipation performance as the constraint condition and minimizing the resource consumption of the heat dissipation control parameters as the optimization purpose, and obtaining the optimal heat dissipation control parameters; producing the heat dissipation device based on the optimal heat dissipation control parameters. The method can solve the technical problem that the high-altitude environment causes the poor heat dissipation performance of the high-voltage frequency converter, resulting in poor operating stability of the high-voltage frequency converter, and can improve the adaptability of the heat dissipation performance of the high-altitude frequency converter to the high-altitude environment, so that the high-voltage frequency converter can operate stably and reliably for a long time.

Description

Technical Field

[0001] The present disclosure relates to high-voltage inverter technology, and more specifically, to a production process optimization method and system for a high-voltage inverter. Background Art

[0002] A high-frequency transformer is a power transformer with an operating frequency exceeding 10kHz. Compared with traditional low-frequency transformers, it has many advantages such as small size, low loss, and low noise. It is widely used in many fields such as wireless communication and radio frequency transmission.

[0003] At present, when high-frequency transformers work in high-altitude areas, due to the thin air, low air pressure and temperature in high-altitude areas, there is a poor regional convection heat transfer effect. As a result, traditional heat dissipation devices can no longer meet the heat dissipation needs of high-frequency transformers when working in high-altitude areas, resulting in poor operating quality and stability of high-frequency transformers.

[0004] The disadvantages of the existing high-voltage inverter heat dissipation device are: due to the high altitude environment, the heat dissipation performance of the high-voltage inverter is poor, resulting in the heat dissipation performance failing to meet the expected requirements, resulting in a technical problem of poor operating stability of the high-voltage inverter. Summary of the invention

[0005] Therefore, in order to solve the above technical problems, the technical solutions adopted by the embodiments of the present disclosure are as follows:

[0006] A method for optimizing the production process of a high-voltage inverter comprises the following steps: obtaining an expected working scenario of the high-voltage inverter, wherein the expected working scenario includes working environment information and working space information; generating a convective heat transfer coefficient under the expected working scenario, wherein the convective heat transfer coefficient is obtained by performing a heat transfer analysis on the working environment information; determining a target heat dissipation performance, wherein the target heat dissipation performance is obtained by performing a heat dissipation evaluation based on the working space information and the convective heat transfer coefficient; obtaining heat dissipation control parameters of the high-voltage inverter, wherein the heat dissipation control parameters include the number of heat sinks, the number of air vents and the type of heat dissipation material; optimizing with satisfying the target heat dissipation performance as a constraint condition and minimizing the resource consumption of the heat dissipation control parameters as the optimization purpose, thereby obtaining optimal heat dissipation control parameters, wherein resource consumption indicators include material loss, process complexity and processing time; and producing a heat dissipation device for the high-voltage inverter based on the optimal heat dissipation control parameters.

[0007] A production process optimization system for a high-voltage frequency converter comprises: an expected working scenario acquisition module, the expected working scenario acquisition module is used to acquire an expected working scenario of a high-voltage frequency converter, wherein the expected working scenario includes working environment information and working space information; a convective heat transfer coefficient generation module, the convective heat transfer coefficient generation module is used to generate a convective heat transfer coefficient under the expected working scenario, the convective heat transfer coefficient is obtained by performing a heat transfer analysis on the working environment information; a target heat dissipation performance determination module, the target heat dissipation performance determination module is used to determine a target heat dissipation performance, the target heat dissipation performance is obtained by performing a heat dissipation evaluation based on the working space information and the convective heat transfer coefficient; a heat dissipation performance determination module is used to determine a target heat dissipation performance, the target heat dissipation performance is obtained by performing a heat dissipation evaluation based on the working space information and the convective heat transfer coefficient; A thermal control parameter acquisition module, the heat dissipation control parameter acquisition module is used to obtain the heat dissipation control parameters of the high-voltage inverter, wherein the heat dissipation control parameters include the number of heat sinks, the number of air vents and the type of heat dissipation material; an optimal heat dissipation control parameter acquisition module, the optimal heat dissipation control parameter acquisition module is used to meet the target heat dissipation performance as a constraint condition, and minimize the resource consumption of the heat dissipation control parameters as the optimization purpose to obtain the optimal heat dissipation control parameters, wherein the resource consumption indicators include material loss, process complexity and processing time; a heat dissipation device production module, the heat dissipation device production module is used to produce the heat dissipation device of the high-voltage inverter based on the optimal heat dissipation control parameters.

[0008] Due to the adoption of the above technical method, the present disclosure has achieved the following technical advances compared with the prior art:

[0009] (1) It can solve the technical problem that the high-altitude environment causes the high-voltage inverter to have poor heat dissipation performance, resulting in the heat dissipation performance not meeting the requirements, and the high-voltage inverter has poor operating stability. First, the expected working scenario of the high-voltage inverter is obtained, wherein the expected working scenario refers to the target working area of ​​the high-voltage inverter, including the working environment information and the working space information; then the working environment information is subjected to heat exchange analysis to obtain the convective heat transfer coefficient under the expected working scenario; further, the heat dissipation performance required by the high-voltage inverter is evaluated based on the working space information and the convective heat transfer coefficient to obtain the target heat dissipation performance; the heat dissipation control parameters of the high-voltage inverter are obtained, including the number of heat sinks, the number of air outlets, and the type of heat dissipation materials; the target heat dissipation performance is taken as the optimization constraint, and the resource consumption of the heat dissipation control parameters is minimized as the optimization purpose, wherein the resource consumption indicators of the heat dissipation control parameters include material loss, process complexity, and processing time, and the optimal heat dissipation control parameters are generated; finally, the heat dissipation device of the high-voltage inverter is produced according to the optimal heat dissipation control parameters. The above method can improve the adaptability of the heat dissipation performance of the high-voltage inverter to the high-altitude environment, so that the high-voltage inverter can operate stably and reliably for a long time.

[0010] (2) By optimizing the heat dissipation control parameters of the high-voltage inverter heat dissipation device, the optimal heat dissipation control parameters are obtained, and the heat dissipation device of the high-voltage inverter is produced according to the optimal heat dissipation control parameters, which can reduce the resource consumption of heat dissipation performance optimization and save materials, labor and energy resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for describing the embodiments are briefly introduced below.

[0012] Figure 1 A schematic flow chart of a method for optimizing the production process of a high-voltage frequency converter is provided for this application;

[0013] Figure 2 A schematic diagram of a process for optimizing and adjusting the initial convection heat transfer coefficient according to temperature data in a production process optimization method for a high-voltage frequency converter is provided for this application;

[0014] Figure 3 A structural schematic diagram of a production process optimization system for a high-voltage inverter is provided for the present application. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0016] Based on the above description, if Figure 1 As shown, the present disclosure provides a method for optimizing the production process of a high-voltage frequency converter, comprising:

[0017] The method provided in the present application is used to optimize the production process of the heat dissipation device of a high-voltage inverter, so as to improve the adaptability of the heat dissipation performance of the high-voltage inverter to the high-altitude environment, so that the high-voltage inverter can operate stably and reliably for a long time. The method is specifically implemented in a production process optimization system for a high-voltage inverter.

[0018] Acquire an expected working scenario of the high-voltage inverter, wherein the expected working scenario includes working environment information and working space information;

[0019] In the embodiment of the present application, first, information is collected on the expected working scene of the high-voltage inverter, wherein the high-voltage inverter refers to the high-voltage inverter for which the heat dissipation device is to be optimized, and the expected working scene refers to the target working site of the high-voltage inverter, which mainly refers to the special working area at high altitude in the embodiment of the present application, wherein the high-altitude area has a relatively weak heat dissipation capacity due to the thin air and small wind flow. The expected working scene includes working environment information and working space information, wherein the working environment information refers to the environment in which the high-voltage inverter is working, including environmental parameters such as temperature and air pressure; wherein the working space information includes the spatial volume of the area in which the high-voltage inverter is working, wherein the larger the spatial volume, the more conducive to the heat dissipation of the high-voltage inverter. By obtaining the expected working scene of the high-voltage inverter, support is provided for the next step of analyzing the heat dissipation performance requirements of the high-voltage inverter, which can improve the adaptability of the heat dissipation performance requirements analysis results to the expected working scene.

[0020] generating a convective heat transfer coefficient under the expected working scenario, wherein the convective heat transfer coefficient is obtained by performing a heat transfer analysis on the working environment information;

[0021] In an embodiment of the present application, first, a heat exchange analysis is performed on the working environment information to obtain the convection heat transfer coefficient under the expected working scenario, wherein the heat exchange analysis refers to obtaining the natural convection heat transfer coefficient of the working area based on the environmental information, wherein natural convection heat transfer is a heat transfer method, which refers to the transfer of heat through the natural movement of the fluid in the absence of external forced convection. As the altitude increases, the atmospheric pressure gradually decreases, and the lower atmospheric pressure will cause the gas density to decrease. Therefore, in high-altitude areas, the heat transfer coefficient of natural convection is usually lower. At the same time, a lower heat transfer coefficient means that the efficiency of heat transfer is lower, which will increase the difficulty of heat dissipation of high-frequency transformers.

[0022] In one embodiment, the method further comprises:

[0023] The working environment information includes air pressure data and temperature data of the working area, wherein the air pressure data is the annual average air pressure value of the working area, and the temperature data is the annual average temperature value of the working area;

[0024] Construct the expression for the convective heat transfer coefficient: ;

[0025] in, is the convective heat transfer coefficient of the working area, is the standard convective heat transfer coefficient at sea level, and 4.25W / mk, is the air pressure data of the working area, is the standard atmospheric pressure data at sea level, and 101.325kpa;

[0026] Based on the convective heat transfer coefficient expression, the initial convective heat transfer coefficient of the working area is calculated by the air pressure data;

[0027] The initial convective heat transfer coefficient is optimized and adjusted according to the temperature data to obtain the convective heat transfer coefficient.

[0028] In an embodiment of the present application, a heat exchange analysis is performed on the working environment information, wherein the working environment information includes air pressure data and temperature data of the working area. First, historical air pressure data and historical temperature data within a preset time window of the working area are obtained.

[0029] The historical temperature data refers to the historical indoor temperature in the working area of ​​the high-frequency transformer. At the same time, the indoor temperature is relatively stable and changes little. The preset time window can be set according to actual conditions. The longer the preset time window, the higher the data accuracy. For example: the preset time window is set to the past 1 year, and then the historical air pressure data and the historical temperature data are averaged to obtain the annual average historical air pressure data and the annual average historical temperature data, and the annual average historical air pressure data is used as the air pressure data, and the annual average historical temperature data is used as the temperature data.

[0030] Construct the expression of convective heat transfer coefficient, where the expression of convective heat transfer coefficient is:

[0031] ;

[0032] The convective heat transfer coefficient refers to the natural convection heat transfer coefficient. In the expression of the convective heat transfer coefficient, is the convective heat transfer coefficient of the working area; is the standard convective heat transfer coefficient at sea level, and The value is 4.25W / mk; is the air pressure data of the working area, is the standard atmospheric pressure data at sea level, and The air pressure value is 101.325 kpa; by constructing the expression of the convective heat transfer coefficient, the efficiency and accuracy of the convective heat transfer coefficient calculation can be improved.

[0033] The air pressure data of the working area is input into the convective heat transfer coefficient expression, and the initial convective heat transfer coefficient of the working area is obtained by calculation. Then, the initial convective heat transfer coefficient is optimized and adjusted according to the temperature data to obtain the convective heat transfer coefficient. Since the increase in altitude will also lead to a decrease in temperature, the decrease in air temperature will lead to an increase in air flow, which will help increase natural convective heat transfer. Therefore, it is necessary to optimize the initial convective heat transfer coefficient according to the temperature data to improve the accuracy of the convective heat transfer coefficient.

[0034] like Figure 2 As shown, in one embodiment, the method further includes:

[0035] Using the air pressure data as an index condition, using big data technology to perform information search, obtaining a plurality of historical temperature data and a plurality of historical convective heat transfer coefficients, wherein the historical temperature data and the historical convective heat transfer coefficients correspond one to one;

[0036] Performing correlation analysis on the plurality of historical temperature data and the plurality of historical convection heat transfer coefficients to generate a temperature-heat transfer coefficient correlation curve;

[0037] The initial convective heat transfer coefficient is optimized and adjusted based on the temperature-heat transfer coefficient correlation curve and the temperature data to generate the convective heat transfer coefficient.

[0038] In the embodiment of the present application, first, the air pressure data is used as a search condition, that is, the air pressure data is used as quantitative data, and the temperature and convective heat transfer coefficient information is searched through big data technology, where big data technology refers to mining the required relevant data from massive data, which can improve the comprehensiveness and accuracy of data acquisition. Multiple historical temperature data and multiple historical convective heat transfer coefficients under the same scene of the air pressure data are obtained, and the historical temperature data and the historical convective heat transfer coefficient have a one-to-one correspondence.

[0039] The correlation analysis of the multiple historical temperature data and the multiple historical convective heat transfer coefficients is performed. First, a two-dimensional rectangular coordinate system is constructed with the historical temperature data as the X-axis of the coordinate axis and the historical convective heat transfer coefficient as the Y-axis of the coordinate axis. Then, the multiple historical temperature data and the multiple historical convective heat transfer coefficients are distributed in the two-dimensional rectangular coordinate system, and the data of the two-dimensional rectangular coordinate system are connected and curve-fitted in the order of temperature from small to large to obtain a temperature-heat transfer coefficient correlation curve. Then, the correlation coefficient between the temperature transformation and the convective heat transfer coefficient is obtained according to the temperature-heat transfer coefficient correlation curve. And the corresponding correlation value is obtained according to the temperature data, and finally, the initial convective heat transfer coefficient is optimized and adjusted according to the correlation value. For example, when the temperature drops, the correlation value is greater than 1 at this time, then the initial convective heat transfer coefficient will be increased to obtain the convective heat transfer coefficient. By obtaining the convective heat transfer coefficient, data support is provided for the next step of heat dissipation performance evaluation and obtaining the target heat dissipation performance.

[0040] Determining a target heat dissipation performance, wherein the target heat dissipation performance is obtained after heat dissipation evaluation based on the workspace information and the convection heat transfer coefficient;

[0041] In the embodiment of the present application, the required heat dissipation performance of the high-frequency transformer is evaluated according to the working space information and the convection heat transfer coefficient to obtain the target heat dissipation performance.

[0042] In one embodiment, the method further comprises:

[0043] The working space information includes the working area space data of the high voltage inverter;

[0044] Obtaining the size information of the high-voltage inverter and calculating the volume data of the high-voltage inverter;

[0045] Calculate and obtain remaining space data based on the working area space data and the high-voltage inverter volume data;

[0046] The heat dissipation performance evaluator performs heat dissipation performance evaluation on the convection heat transfer coefficient and the remaining space data to obtain target heat dissipation performance.

[0047] In an embodiment of the present application, the workspace information includes the work area space data of the high-voltage inverter, wherein the work area space data refers to the spatial volume of the work area of ​​the high-voltage inverter, which is obtained by calculation. The size information of the high-voltage inverter is obtained, including the length, width, and height of multiple components of the high-voltage inverter. Then, the volume calculation is performed according to the size information of the high-voltage inverter to obtain the volume data of the high-voltage inverter.

[0048] The spatial volume deviation value is obtained by subtracting the volume data of the high-voltage inverter from the spatial data of the working area, and the spatial volume deviation value is used as the remaining spatial data, wherein the larger the remaining spatial data is, the more conducive to the heat dissipation of the high-frequency transformer is. A heat dissipation performance evaluator is constructed based on the BP neural network, and the heat dissipation performance of the convection heat transfer coefficient and the remaining spatial data is evaluated by the heat dissipation performance evaluator to generate a target heat dissipation performance, wherein the target heat dissipation performance is represented by the heat dissipation per unit time, wherein the larger the heat dissipation per unit time is, the better the heat dissipation performance is.

[0049] In one embodiment, the method further comprises:

[0050] Acquire a plurality of historical convection heat transfer coefficients, a plurality of historical remaining space data, and a plurality of historical qualified heat dissipation performances, wherein the historical qualified heat dissipation performances are minimum heat dissipation performances that meet the heat dissipation requirements of the high-voltage inverter;

[0051] constructing an evaluation data set based on the plurality of historical convection heat transfer coefficients, the plurality of historical remaining space data, and the plurality of historical qualified heat dissipation performances;

[0052] Constructing a heat dissipation performance evaluator based on a BP neural network, and performing supervised training on the heat dissipation performance evaluator through the evaluation data set to obtain a heat dissipation performance evaluator that meets expected indicators;

[0053] The heat dissipation performance evaluator is used to perform heat dissipation performance evaluation on the convection heat transfer coefficient and the remaining space data to generate a target heat dissipation performance.

[0054] In the embodiment of the present application, based on big data, multiple historical convection heat transfer coefficients, multiple historical remaining space data, and multiple historical qualified heat dissipation performances are obtained, wherein the historical qualified heat dissipation performance is the minimum heat dissipation performance that meets the heat dissipation requirements of the high-voltage inverter, and the historical convection heat transfer coefficients, the historical remaining space data, and the historical qualified heat dissipation performance have a corresponding relationship. The multiple historical convection heat transfer coefficients, the multiple historical remaining space data, and the multiple historical qualified heat dissipation performances are used as evaluation data sets.

[0055] A heat dissipation performance evaluator is constructed based on a BP neural network, wherein the BP neural network is a common artificial neural network architecture, which is composed of neurons, weights, activation functions, loss functions and other parts. The heat dissipation performance evaluator is a neural network model that can be continuously iteratively optimized in machine learning. The heat dissipation performance evaluator includes an input layer, a hidden layer and an output layer, wherein the input data of the input layer is the convective heat transfer coefficient and the remaining space data, and the output data of the output layer is the qualified heat dissipation performance.

[0056] Then, supervised training is performed on the heat dissipation performance evaluator through the evaluation data set. First, a piece of evaluation data is randomly selected from the evaluation data set as the first set of training data, and supervised training is performed on the heat dissipation performance evaluator through the first set of training data to obtain the output result of the first set of training data, that is, the first qualified heat dissipation performance; then the first qualified heat dissipation performance is compared with the historical qualified heat dissipation performance of the first set of training data. When the results are consistent, supervised training is continued on the heat dissipation performance evaluator through the next set of training data; when the results are inconsistent, the deviation value between the first qualified heat dissipation performance and the historical qualified heat dissipation performance of the first set of training data is obtained, and the weight parameters of the heat dissipation performance evaluator are optimized and adjusted according to the deviation value, and then supervised training of the next set of training data is performed. A preset output accuracy index is obtained, and the preset output accuracy index can be set according to actual conditions, for example: the preset output accuracy index is set to 90%, until the accuracy of the output result of the heat dissipation performance evaluator is greater than or equal to the preset output accuracy index, and a trained heat dissipation performance evaluator is obtained. By constructing a heat dissipation performance evaluator based on a BP neural network to perform heat dissipation performance evaluation, the efficiency and accuracy of obtaining the target heat dissipation performance can be improved, thereby improving the accuracy of heat dissipation device production optimization.

[0057] Acquire heat dissipation control parameters of the high-voltage inverter, wherein the heat dissipation control parameters include the number of heat sinks, the number of air vents, and the type of heat dissipation material;

[0058] In the embodiment of the present application, the heat dissipation control parameters of the high-voltage inverter are obtained, wherein the heat dissipation control parameters refer to the index parameters for changing the heat dissipation performance of the heat dissipation device, including the number of heat sinks, the number of air outlets and the type of heat dissipation material, wherein the larger the number of heat sinks, the better the heat dissipation performance of the heat dissipation device; the larger the number of air outlets, the better the heat dissipation performance of the heat dissipation device; the better the heat dissipation material performance of the heat dissipation material, the better the heat dissipation performance of the heat dissipation device, for example: the heat dissipation performance of copper metal is higher than that of iron metal. By obtaining the heat dissipation control parameters, support is provided for the next step of optimizing the heat dissipation control parameters.

[0059] Taking satisfying the target heat dissipation performance as a constraint condition and minimizing the resource consumption of the heat dissipation control parameters as an optimization objective, an optimization is performed to obtain the optimal heat dissipation control parameters, wherein the resource consumption indicators include material loss, process complexity and processing time;

[0060] In an embodiment of the present application, satisfying the target heat dissipation performance is set as a constraint condition, and minimizing the resource consumption of the heat dissipation control parameters is set as the optimization purpose. An optimization algorithm is used to perform optimization, that is, to minimize the resource consumption while satisfying the target heat dissipation performance, wherein the resource consumption indicators include material loss, process complexity and processing time, so as to obtain the optimal heat dissipation control parameters.

[0061] In one embodiment, the method further comprises:

[0062] Acquire adjustment thresholds of the heat dissipation control parameters, wherein the adjustment thresholds include a heat sink quantity threshold, an air vent quantity threshold, and a material type threshold;

[0063] Randomly selecting a first number of heat sinks and a first number of air outlets without replacement from the heat sink number threshold and the air outlet number threshold; randomly selecting a first material type with replacement from the material type threshold, and constructing a first heat dissipation control parameter according to the first number of heat sinks, the first number of air outlets and the first material type;

[0064] Performing heat dissipation performance prediction on the first heat dissipation control parameter by a heat dissipation performance predictor to obtain a first heat dissipation performance;

[0065] Determine whether the first heat dissipation performance meets the target heat dissipation performance, and if so, randomly select a second number of heat sinks and a second number of air outlets from the heat sink number threshold and the air outlet number threshold without replacement; randomly select a second material type from the material type threshold with replacement, and construct a second heat dissipation control parameter according to the second number of heat sinks, the second number of air outlets and the second material type;

[0066] When the second heat dissipation control parameter meets the target heat dissipation performance, performing fitness calculation on the first heat dissipation control parameter and the second heat dissipation control parameter through a resource consumption fitness function to obtain a first fitness and a second fitness;

[0067] In an embodiment of the present application, first, an adjustment threshold of the heat dissipation control parameter is obtained, and the adjustment threshold refers to the adjustable range of the heat dissipation control parameter in the heat dissipation device, wherein the adjustment threshold includes a heat sink number threshold, an air outlet number threshold, and a material type threshold. Then, a number of heat sinks is randomly selected without replacement in the heat sink number threshold as the first heat sink number, a number of air outlets is randomly selected without replacement in the air outlet number threshold as the first air outlet number, and a material type is randomly selected with replacement in the material type threshold as the first material type, wherein the material type is selected with replacement because the number of material types is relatively small compared to the number of heat sinks and the number of air outlets, thereby improving the rationality of optimization. Then, a first heat dissipation control parameter is constructed based on the first number of heat sinks, the first number of air outlets, and the first material type.

[0068] A heat dissipation performance predictor is constructed based on a BP neural network, wherein the heat dissipation performance predictor and the heat dissipation performance evaluator are the same neural network model, wherein the input data of the heat dissipation performance prediction period are the number of heat sinks, the number of air outlets, and the material type, and the output data is the heat dissipation performance. Based on big data, multiple historical numbers of heat sinks, multiple historical numbers of air outlets, multiple historical material types, and multiple historical heat dissipation performances are obtained, and the historical numbers of heat sinks, the historical numbers of air outlets, the historical material types, and the historical heat dissipation performances have a corresponding relationship. A training data set for the heat dissipation performance predictor is constructed based on multiple historical numbers of heat sinks, multiple historical numbers of air outlets, multiple historical material types, and multiple historical heat dissipation performances, and the heat dissipation performance predictor is supervised and trained using the same method as the heat dissipation performance evaluator to obtain a heat dissipation performance predictor that meets the expected requirements.

[0069] Then the first heat dissipation control parameter is input into the heat dissipation performance predictor to predict the heat dissipation performance and obtain the first heat dissipation performance. The first heat dissipation performance is judged according to the target heat dissipation performance, and when the first heat dissipation performance is greater than or equal to the target heat dissipation performance, the second number of heat dissipation fins and the second number of air outlets are randomly selected without replacement from the heat dissipation fin number threshold and the air outlet number threshold, and the second material type is randomly selected with replacement from the material type threshold, and the second heat dissipation control parameter is constructed according to the second number of heat dissipation fins, the second number of air outlets and the second material type.

[0070] The heat dissipation performance of the second heat dissipation control parameter is predicted by a heat dissipation performance predictor to obtain a second heat dissipation performance, and the second heat dissipation performance is judged according to the target heat dissipation performance. When the second heat dissipation performance is greater than or equal to the target heat dissipation performance, the fitness of the first heat dissipation control parameter and the second heat dissipation control parameter is calculated according to a resource consumption fitness function to obtain a first fitness and a second fitness.

[0071] In one embodiment, the method further comprises:

[0072] The expression of the resource consumption fitness function is:

[0073] ;

[0074] in, is the fitness of the i-th heat dissipation control parameter, is the total material loss of the i-th heat dissipation control parameter, is the total process complexity of the i-th heat dissipation control parameter, is the total processing time of the i-th heat dissipation control parameter, It is the weight coefficient of total material loss, total process complexity and total processing time.

[0075] In the embodiment of the present application, the expression of the resource consumption fitness function is:

[0076] ;

[0077] In the resource consumption fitness function expression, is the fitness of the i-th heat dissipation control parameter, wherein the greater the fitness, the greater the resource consumption representing the heat dissipation control parameter, wherein the i-th heat dissipation control parameter is any one of the multiple heat dissipation control parameters, is the total material loss of the i-th heat dissipation control parameter, where the total material loss refers to the sum of the material consumption of the number of heat sinks, the number of air outlets and the material type in the i-th heat dissipation control parameter; is the total process complexity of the i-th heat dissipation control parameter, is the total processing time of the i-th heat dissipation control parameter, is the weight coefficient of total material loss, total process complexity and total processing time, where The value of can be set by technicians in this field according to the impact of material loss, process complexity, and processing time on resource consumption. The greater the impact on resource consumption, the greater the weight coefficient. The weight coefficient can be set using the existing coefficient of variation method, which is a weight setting method commonly used by technicians in this field and will not be explained in detail here.

[0078] When the first fitness is less than or equal to the second fitness, the first heat dissipation control parameter is used as the current optimal heat dissipation control parameter; when the first fitness is greater than the second fitness, the second heat dissipation control parameter is used as the current optimal heat dissipation control parameter;

[0079] Continue to iterate and optimize until the current number of optimization searches is equal to a preset number of optimization search thresholds, then output the current optimal heat dissipation control parameters to obtain the optimal heat dissipation control parameters.

[0080] In an embodiment of the present application, the first fitness and the second fitness are compared, where a smaller fitness indicates a smaller resource consumption and a better heat dissipation control parameter. When the first fitness is less than or equal to the second fitness, the first heat dissipation control parameter is used as the current optimal heat dissipation control parameter; when the first fitness is greater than the second fitness, the second heat dissipation control parameter is used as the current optimal heat dissipation control parameter.

[0081] Continue to iterate the optimization and obtain a preset optimization number threshold. The preset optimization number threshold can be set by a person skilled in the art according to the actual optimization needs. The higher the optimization requirement accuracy, the larger the preset optimization number threshold. For example, the preset optimization number threshold is set to 100 times. When the current optimization number is equal to the preset optimization number threshold, the current optimal control parameters are output, and the current optimal heat dissipation control parameters are used as the optimal heat dissipation control parameters, wherein the optimal heat dissipation control parameters include the optimal number of heat sinks, the optimal number of air vents and the optimal material type.

[0082] By optimizing the heat dissipation control parameters using an optimization algorithm, the accuracy and efficiency of obtaining the optimal heat dissipation control parameters can be improved.

[0083] The heat dissipation device of the high-voltage inverter is produced based on the optimal heat dissipation control parameters.

[0084] In the embodiment of the present application, the heat dissipation device of the high-voltage inverter is finally optimized and produced according to the optimal heat dissipation control parameters. The above method can solve the technical problem that the heat dissipation performance of the high-voltage inverter is poor due to the high-altitude environment, resulting in the heat dissipation performance not meeting the requirements, and the operation stability of the high-voltage inverter is poor. The adaptability of the heat dissipation performance of the high-voltage inverter to the high-altitude environment can be improved, so that the high-voltage inverter can operate stably and reliably for a long time, and at the same time, the resource consumption of heat dissipation performance optimization can be reduced, saving resources.

[0085] In one embodiment, Figure 3 A production process optimization system for a high-voltage inverter is provided, comprising:

[0086] An expected working scene acquisition module, the expected working scene acquisition module is used to acquire an expected working scene of the high-voltage inverter, wherein the expected working scene includes working environment information and working space information;

[0087] A convection heat transfer coefficient generation module, the convection heat transfer coefficient generation module is used to generate a convection heat transfer coefficient under the expected working scenario, the convection heat transfer coefficient is obtained by performing a heat transfer analysis on the working environment information;

[0088] a target heat dissipation performance determination module, the target heat dissipation performance determination module is used to determine a target heat dissipation performance, the target heat dissipation performance is obtained after heat dissipation evaluation based on the workspace information and the convection heat transfer coefficient;

[0089] A heat dissipation control parameter acquisition module, the heat dissipation control parameter acquisition module is used to obtain the heat dissipation control parameters of the high-voltage inverter, wherein the heat dissipation control parameters include the number of heat sinks, the number of air outlets and the type of heat dissipation material;

[0090] An optimal heat dissipation control parameter obtaining module, wherein the optimal heat dissipation control parameter obtaining module is used to obtain the optimal heat dissipation control parameter by taking the target heat dissipation performance as a constraint condition and minimizing the resource consumption of the heat dissipation control parameter as an optimization purpose, wherein the resource consumption index includes material loss, process complexity and processing time;

[0091] A heat dissipation device production module is used to produce the heat dissipation device of the high-voltage inverter based on the optimal heat dissipation control parameters.

[0092] In one embodiment, the system further comprises:

[0093] A working environment information summary module, wherein the working environment information summary module means that the working environment information includes air pressure data and temperature data of the working area, wherein the air pressure data is the annual average air pressure value of the working area, and the temperature data is the annual average temperature value of the working area;

[0094] Convective heat transfer coefficient expression building module, the convection heat transfer coefficient expression building module is used to build a convection heat transfer coefficient expression: ;

[0095] An expression parameter module, wherein the expression parameter module refers to one in which: is the convective heat transfer coefficient of the working area, is the standard convective heat transfer coefficient at sea level, and 4.25W / mk, is the air pressure data of the working area, is the standard atmospheric pressure data at sea level, and 101.325kpa;

[0096] An initial convection heat transfer coefficient obtaining module, the initial convection heat transfer coefficient obtaining module is used to obtain the initial convection heat transfer coefficient of the working area through the air pressure data based on the convection heat transfer coefficient expression;

[0097] An initial convective heat transfer coefficient optimization and adjustment module is used to optimize and adjust the initial convective heat transfer coefficient according to the temperature data to obtain the convective heat transfer coefficient.

[0098] In one embodiment, the system further comprises:

[0099] An information search module, wherein the information search module is used to use the air pressure data as an index condition and to perform information search using big data technology to obtain a plurality of historical temperature data and a plurality of historical convective heat transfer coefficients, wherein the historical temperature data and the historical convective heat transfer coefficients correspond to each other one by one;

[0100] A correlation analysis module, the correlation analysis module is used to perform correlation analysis on the plurality of historical temperature data and the plurality of historical convection heat transfer coefficients to generate a temperature-heat transfer coefficient correlation curve;

[0101] A convection heat transfer coefficient generation module is used to optimize and adjust the initial convection heat transfer coefficient based on the temperature-heat transfer coefficient correlation curve and the temperature data to generate the convection heat transfer coefficient.

[0102] In one embodiment, the system further comprises:

[0103] A working space information module, wherein the working space information module refers to the working space information including the working area space data of the high-voltage inverter;

[0104] A high-voltage inverter volume data acquisition module, the high-voltage inverter volume data acquisition module is used to obtain the size information of the high-voltage inverter and calculate the volume data of the high-voltage inverter;

[0105] A remaining space data calculation module, the remaining space data calculation module is used to calculate and obtain the remaining space data based on the working area space data and the high-voltage inverter volume data;

[0106] A heat dissipation performance evaluation module is used to perform heat dissipation performance evaluation on the convective heat transfer coefficient and the remaining space data through a heat dissipation performance evaluator to obtain a target heat dissipation performance.

[0107] In one embodiment, the system further comprises:

[0108] A historical data acquisition module, the historical data acquisition module is used to obtain a plurality of historical convection heat transfer coefficients, a plurality of historical remaining space data, and a plurality of historical qualified heat dissipation performances, wherein the historical qualified heat dissipation performance is a minimum heat dissipation performance that meets the heat dissipation requirements of the high-voltage inverter;

[0109] An evaluation data set construction module, the evaluation data set construction module is used to construct an evaluation data set according to the multiple historical convection heat transfer coefficients, the multiple historical remaining space data and the multiple historical qualified heat dissipation performances;

[0110] A heat dissipation performance evaluator construction module, wherein the heat dissipation performance evaluator construction module is used to construct a heat dissipation performance evaluator based on a BP neural network, and to perform supervised training on the heat dissipation performance evaluator through the evaluation data set to obtain a heat dissipation performance evaluator that meets expected indicators;

[0111] A heat dissipation performance evaluation module is used to use the heat dissipation performance evaluator to perform heat dissipation performance evaluation on the convection heat transfer coefficient and the remaining space data to generate a target heat dissipation performance.

[0112] In one embodiment, the system further comprises:

[0113] An adjustment threshold acquisition module, the adjustment threshold acquisition module is used to obtain the adjustment threshold of the heat dissipation control parameter, wherein the adjustment threshold includes a heat sink quantity threshold, an air outlet quantity threshold and a material type threshold;

[0114] a first heat dissipation control parameter construction module, the first heat dissipation control parameter construction module is used to randomly select a first number of heat sinks and a first number of air outlets from the heat sink number threshold and the air outlet number threshold without replacement; randomly select a first material type from the material type threshold with replacement, and construct a first heat dissipation control parameter according to the first number of heat sinks, the first number of air outlets and the first material type;

[0115] A first heat dissipation performance obtaining module, the first heat dissipation performance obtaining module is used to perform heat dissipation performance prediction on the first heat dissipation control parameter through a heat dissipation performance predictor to obtain a first heat dissipation performance;

[0116] a second heat dissipation control parameter construction module, the second heat dissipation control parameter construction module is used to determine whether the first heat dissipation performance meets the target heat dissipation performance, and when it meets the target heat dissipation performance, randomly select the second number of heat sinks and the second number of air outlets without replacement from the heat sink number threshold and the air outlet number threshold; randomly select the second material type with replacement from the material type threshold, and construct the second heat dissipation control parameter according to the second number of heat sinks, the second number of air outlets and the second material type;

[0117] a fitness calculation module, wherein the fitness calculation module is used to perform fitness calculation on the first heat dissipation control parameter and the second heat dissipation control parameter through a resource consumption fitness function to obtain a first fitness and a second fitness when the second heat dissipation control parameter meets the target heat dissipation performance;

[0118] a current optimal heat dissipation control parameter setting module, wherein the current optimal heat dissipation control parameter setting module is used to use the first heat dissipation control parameter as the current optimal heat dissipation control parameter when the first fitness is less than or equal to the second fitness; and use the second heat dissipation control parameter as the current optimal heat dissipation control parameter when the first fitness is greater than the second fitness;

[0119] The optimal heat dissipation control parameter acquisition module is used to continue iterative optimization until the current optimization times are equal to a preset optimization times threshold, then output the current optimal heat dissipation control parameters to obtain the optimal heat dissipation control parameters.

[0120] In one embodiment, the system further comprises:

[0121] Resource consumption fitness function module, the resource consumption fitness function module refers to the expression of the resource consumption fitness function:

[0122] ;

[0123] Function parameter module, wherein the function parameter module refers to one in which: is the fitness of the i-th heat dissipation control parameter, is the total material loss of the i-th heat dissipation control parameter, is the total process complexity of the i-th heat dissipation control parameter, is the total processing time of the i-th heat dissipation control parameter, It is the weight coefficient of total material loss, total process complexity and total processing time.

[0124] In summary, compared with the prior art, the embodiments of the present disclosure have the following technical effects:

[0125] (1) The technical problem that the heat dissipation performance of high-voltage inverters is poor due to high-altitude environments, resulting in the heat dissipation performance not meeting the requirements and the poor operating stability of high-voltage inverters is solved. By generating optimal heat dissipation control parameters for the production of heat dissipation devices for high-voltage inverters, the adaptability of the heat dissipation performance of high-voltage inverters to high-altitude environments can be improved, so that high-voltage inverters can operate stably and reliably for a long time. At the same time, the resource consumption for optimizing heat dissipation performance can be reduced, thus saving resources.

[0126] (2) By constructing a heat dissipation performance evaluator based on the BP neural network to evaluate the heat dissipation performance, the efficiency and accuracy of obtaining the target heat dissipation performance can be improved, thereby improving the accuracy of heat dissipation device production optimization.

[0127] (3) By optimizing the heat dissipation control parameters of the high-voltage inverter heat dissipation device and producing the heat dissipation device of the high-voltage inverter according to the optimal heat dissipation control parameters, the resource consumption of heat dissipation performance optimization can be reduced, and materials, labor and energy resources can be saved.

[0128] The above-described embodiments only express several implementation methods of the present disclosure, but they cannot be understood as limiting the scope of the invention patent. Therefore, without departing from the scope of the present disclosure concept as defined by the attached claims, a person of ordinary skill in the art may make various types of substitutions, modifications and changes, and these substitutions, modifications and changes all belong to the protection scope of the present disclosure.

Claims

1. A method for optimizing the production process of a high-voltage frequency converter, characterized in that: The method comprises: Acquire an expected working scenario of the high-voltage inverter, wherein the expected working scenario includes working environment information and working space information; generating a convective heat transfer coefficient under the expected working scenario, wherein the convective heat transfer coefficient is obtained by performing a heat transfer analysis on the working environment information; Determining a target heat dissipation performance, wherein the target heat dissipation performance is obtained after heat dissipation evaluation based on the workspace information and the convection heat transfer coefficient; Acquire heat dissipation control parameters of the high-voltage inverter, wherein the heat dissipation control parameters include the number of heat sinks, the number of air vents, and the type of heat dissipation material; Taking satisfying the target heat dissipation performance as a constraint condition and minimizing the resource consumption of the heat dissipation control parameters as an optimization objective, an optimization is performed to obtain the optimal heat dissipation control parameters, wherein the resource consumption indicators include material loss, process complexity and processing time; Producing the heat dissipation device of the high-voltage inverter based on the optimal heat dissipation control parameters; The generating of the convective heat transfer coefficient under the expected working scenario, wherein the convective heat transfer coefficient is obtained by performing heat transfer analysis on the working environment information, further includes: The working environment information includes air pressure data and temperature data of the working area, wherein the air pressure data is the annual average air pressure value of the working area, and the temperature data is the annual average temperature value of the working area; Construct the expression for the convective heat transfer coefficient: ； in, is the convective heat transfer coefficient of the working area, is the standard convective heat transfer coefficient at sea level, and is 4.25W / mk, p is the air pressure data in the working area, is the standard atmospheric pressure data at sea level, and 101.325kpa; Based on the convective heat transfer coefficient expression, the initial convective heat transfer coefficient of the working area is calculated by the air pressure data; The initial convective heat transfer coefficient is optimized and adjusted according to the temperature data to obtain the convective heat transfer coefficient.

2. The method according to claim 1, characterized in that The optimizing and adjusting the initial convection heat transfer coefficient according to the temperature data further includes: Using the air pressure data as an index condition, using big data technology to perform information search, obtaining a plurality of historical temperature data and a plurality of historical convective heat transfer coefficients, wherein the historical temperature data and the historical convective heat transfer coefficients correspond one to one; Performing correlation analysis on the plurality of historical temperature data and the plurality of historical convection heat transfer coefficients to generate a temperature-heat transfer coefficient correlation curve; The initial convective heat transfer coefficient is optimized and adjusted based on the temperature-heat transfer coefficient correlation curve and the temperature data to generate the convective heat transfer coefficient.

3. The method according to claim 1, characterized in that The determining of the target heat dissipation performance, wherein the target heat dissipation performance is obtained after heat dissipation evaluation based on the workspace information and the convection heat transfer coefficient, further includes: The working space information includes the working area space data of the high voltage inverter; Obtaining the size information of the high-voltage inverter and calculating the volume data of the high-voltage inverter; Calculate and obtain remaining space data based on the working area space data and the high-voltage inverter volume data; The heat dissipation performance evaluator performs heat dissipation performance evaluation on the convection heat transfer coefficient and the remaining space data to obtain target heat dissipation performance.

4. The method according to claim 3, characterized in that The heat dissipation performance evaluation of the convection heat transfer coefficient and the remaining space data by a heat dissipation performance evaluator further includes: Acquire a plurality of historical convection heat transfer coefficients, a plurality of historical remaining space data, and a plurality of historical qualified heat dissipation performances, wherein the historical qualified heat dissipation performances are minimum heat dissipation performances that meet the heat dissipation requirements of the high-voltage inverter; constructing an evaluation data set based on the plurality of historical convection heat transfer coefficients, the plurality of historical remaining space data, and the plurality of historical qualified heat dissipation performances; Constructing a heat dissipation performance evaluator based on a BP neural network, and performing supervised training on the heat dissipation performance evaluator through the evaluation data set to obtain a heat dissipation performance evaluator that meets expected indicators; The heat dissipation performance evaluator is used to perform heat dissipation performance evaluation on the convection heat transfer coefficient and the remaining space data to generate a target heat dissipation performance.

5. The method according to claim 1, characterized in that The optimization is performed with the goal of satisfying the target heat dissipation performance as a constraint condition and minimizing the resource consumption of the heat dissipation control parameters as the optimization purpose to obtain the optimal heat dissipation control parameters, and further includes: Acquire adjustment thresholds of the heat dissipation control parameters, wherein the adjustment thresholds include a heat sink quantity threshold, an air vent quantity threshold, and a material type threshold; Randomly selecting a first number of heat sinks and a first number of air outlets without replacement from the heat sink number threshold and the air outlet number threshold; randomly selecting a first material type with replacement from the material type threshold, and constructing a first heat dissipation control parameter according to the first number of heat sinks, the first number of air outlets and the first material type; Performing heat dissipation performance prediction on the first heat dissipation control parameter by a heat dissipation performance predictor to obtain a first heat dissipation performance; Determine whether the first heat dissipation performance meets the target heat dissipation performance, and if so, randomly select a second number of heat sinks and a second number of air outlets without replacement from the heat sink number threshold and the air outlet number threshold; randomly select a second material type with replacement from the material type threshold, and construct a second heat dissipation control parameter according to the second number of heat sinks, the second number of air outlets and the second material type; When the second heat dissipation control parameter meets the target heat dissipation performance, performing fitness calculation on the first heat dissipation control parameter and the second heat dissipation control parameter through a resource consumption fitness function to obtain a first fitness and a second fitness; When the first fitness is less than or equal to the second fitness, the first heat dissipation control parameter is used as the current optimal heat dissipation control parameter; when the first fitness is greater than the second fitness, the second heat dissipation control parameter is used as the current optimal heat dissipation control parameter; Continue to iterate and optimize until the current number of optimization searches is equal to a preset number of optimization search thresholds, then output the current optimal heat dissipation control parameters to obtain the optimal heat dissipation control parameters.

6. The method according to claim 5, characterized in that The method further comprises: The expression of the resource consumption fitness function is: ； in, is the fitness of the i-th heat dissipation control parameter, is the total material loss of the i-th heat dissipation control parameter, is the total process complexity of the i-th heat dissipation control parameter, is the total processing time of the i-th heat dissipation control parameter, , , It is the weight coefficient of total material loss, total process complexity and total processing time.

7. A production process optimization system for a high-voltage frequency converter, characterized in that: The system is used to perform the steps of any one of the methods for optimizing the production process of a high-voltage frequency converter described in claims 1-6, comprising: An expected working scene acquisition module, the expected working scene acquisition module is used to acquire an expected working scene of the high-voltage inverter, wherein the expected working scene includes working environment information and working space information; A convection heat transfer coefficient generation module, the convection heat transfer coefficient generation module is used to generate a convection heat transfer coefficient under the expected working scenario, the convection heat transfer coefficient is obtained by performing a heat transfer analysis on the working environment information; a target heat dissipation performance determination module, the target heat dissipation performance determination module is used to determine a target heat dissipation performance, the target heat dissipation performance is obtained after heat dissipation evaluation based on the workspace information and the convection heat transfer coefficient; A heat dissipation control parameter acquisition module, the heat dissipation control parameter acquisition module is used to obtain the heat dissipation control parameters of the high-voltage inverter, wherein the heat dissipation control parameters include the number of heat sinks, the number of air outlets and the type of heat dissipation material; An optimal heat dissipation control parameter obtaining module, wherein the optimal heat dissipation control parameter obtaining module is used to obtain the optimal heat dissipation control parameter by taking the target heat dissipation performance as a constraint condition and minimizing the resource consumption of the heat dissipation control parameter as an optimization purpose, wherein the resource consumption index includes material loss, process complexity and processing time; A heat dissipation device production module is used to produce the heat dissipation device of the high-voltage inverter based on the optimal heat dissipation control parameters.

Images