CN116992819B - IGBT junction temperature estimation method and system - Google Patents
IGBT junction temperature estimation method and system Download PDFInfo
- Publication number
- CN116992819B CN116992819B CN202311236571.0A CN202311236571A CN116992819B CN 116992819 B CN116992819 B CN 116992819B CN 202311236571 A CN202311236571 A CN 202311236571A CN 116992819 B CN116992819 B CN 116992819B
- Authority
- CN
- China
- Prior art keywords
- igbt
- junction temperature
- temperature
- layer
- initial
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000004364 calculation method Methods 0.000 claims description 40
- 230000006870 function Effects 0.000 claims description 18
- 238000013527 convolutional neural network Methods 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000011176 pooling Methods 0.000 description 6
- 230000004913 activation Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000015556 catabolic process Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/30—Circuit design
- G06F30/39—Circuit design at the physical level
- G06F30/398—Design verification or optimisation, e.g. using design rule check [DRC], layout versus schematics [LVS] or finite element methods [FEM]
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/26—Testing of individual semiconductor devices
- G01R31/2601—Apparatus or methods therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Abstract
The invention discloses an IGBT junction temperature estimation method and system, and relates to the technical field of automobiles, wherein the method comprises the following steps: measuring and collecting bus voltage waveforms of the IGBT module, and inputting the bus voltage waveforms into a signal processing circuit for preprocessing to obtain temperature-sensitive electrical parameters; collecting an instantaneous current waveform of the IGBT module, and calculating the loss of the IGBT module according to the working state of the IGBT module and the instantaneous current waveform; constructing a thermal resistance network model based on the loss and the thermal resistance heat capacity parameters to obtain temperature distribution of each layer in the IGBT module, and estimating initial IGBT junction temperature through the temperature distribution of each layer; based on the Wen Mindian parameters, the thermal resistance network model is optimized to obtain the final IGBT junction temperature, and the method can solve the technical problems that the temperature of each layer inside the IGBT module is difficult to detect and the junction temperature estimation accuracy is low in the prior art by estimating the IGBT junction temperature through the infrared thermal imager.
Description
Technical Field
The invention relates to the technical field of automobiles, in particular to an IGBT junction temperature estimation method and system.
Background
The IGBT module is used as one of the power elements and is widely applied to the fields of new energy automobiles, wind power generation, rail transit, industrial driving and the like. With the development of power electronics technology, the control and management of the junction temperature of the IGBT module face increasing challenges while increasing the power level and the switching frequency. Therefore, research and development of the efficient, accurate and stable IGBT junction temperature estimation method has important theoretical significance and practical value.
At present, a common method for monitoring the IGBT junction temperature is to perform non-contact temperature measurement on an IGBT module through an infrared thermal imager so as to estimate the IGBT junction temperature. The method has the advantages that the measuring process is lossless and interference-free, the defects that special equipment and software are needed, the method can only be carried out in a laboratory environment, on-line monitoring is difficult to realize, the temperature of each layer inside the IGBT module can not be detected, the temperature of the whole surface of the IGBT module can only be estimated, and junction temperature estimation is inaccurate.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide an IGBT junction temperature estimation method and an IGBT junction temperature estimation system, and aims to solve the technical problems that the temperature of each layer inside an IGBT module is difficult to detect and the junction temperature estimation accuracy is low in the prior art by estimating the IGBT junction temperature through an infrared thermal imager.
An aspect of the present invention provides a method for estimating an IGBT junction temperature, the method including:
measuring and collecting bus voltage waveforms of the IGBT module, and inputting the bus voltage waveforms into a signal processing circuit for preprocessing to obtain temperature-sensitive electrical parameters;
the method comprises the steps of collecting an instantaneous current waveform of an IGBT module, and calculating the loss of the IGBT module according to the working state of the IGBT module and the instantaneous current waveform, wherein the calculation formula of the loss of the IGBT module is as follows:
，
wherein,for conduction loss->For switching losses +.>For loss, < >>For on-resistance +.>In order to be an instantaneous current,is a direct current voltage>For the on time of the IGBT module, +.>For the turn-off time of the IGBT +.>Is the switching frequency;
based on the loss and the heat resistance and heat capacity parameters, constructing a heat resistance network model to obtain temperature distribution of each layer in the IGBT module, and estimating initial IGBT junction temperature through the temperature distribution of each layer, wherein a calculation formula constructed by the heat resistance network model is as follows:
，
wherein,for the temperature of the i-th layer, +.>For the temperature of the j-th layer>For the capacitance of the i-th layer, < >>Is the thermal resistance between the i-th layer and the j-th layer, and (2)>Loss of the i-th layer; i=1.. c, performing operation; j=1.. c, performing operation;
and optimizing the thermal resistance network model based on the Wen Mindian parameters to obtain the final IGBT junction temperature.
Compared with the prior art, the invention has the beneficial effects that: the IGBT junction temperature estimation method provided by the invention can effectively and accurately estimate the IGBT junction temperature, specifically, the instantaneous current waveform of the IGBT module is collected, and the loss of the IGBT module is calculated according to the working state of the IGBT module and the instantaneous current waveform; the conduction loss and the switching loss of the IGBT module are calculated to more accurately reflect the loss and the junction temperature change of the IGBT module, so that the performance and the service life of the system are improved; constructing a thermal resistance network model based on the loss and the thermal resistance heat capacity parameters to obtain temperature distribution of each layer in the IGBT module, and estimating initial IGBT junction temperature through the temperature distribution of each layer; the temperature distribution of each layer inside the IGBT module is calculated by utilizing a thermal resistance network model, the initial IGBT junction temperature is estimated more accurately according to the temperature of the innermost layer chip, the complexity and the cost of the system are reduced, the thermal resistance network model is optimized based on Wen Mindian parameters to obtain the final IGBT junction temperature, the coefficient is updated layer by calculating the error between the simulated junction temperature and the initial IGBT junction temperature and then reversely transmitting according to the error、/>Thereby the output and the real IGBT junction temperature are as close as possible, the error is reduced, the error function reaches the minimum value, the precision and the stability are improved, thereby the problem that the IGBT junction is estimated by the infrared thermal imager in the prior art is solvedThe temperature of each layer inside the IGBT module is difficult to detect, and the junction temperature estimation accuracy is low.
According to an aspect of the above technical solution, the step of estimating the initial IGBT junction temperature by the temperature distribution of each layer specifically includes:
acquiring the temperature of the innermost layer, and estimating the initial IGBT junction temperature through the temperature of the innermost layer, wherein the calculation formula of the initial IGBT junction temperature is as follows:
，
wherein,is->Temperature of the innermost layer,/->For the initial IGBT junction temperature, +.>Is IGBT junction temperature resistance->For instantaneous current, +.>、/>Are coefficients.
According to an aspect of the above technical solution, the step of optimizing the thermal resistance network model based on the Wen Mindian parameter to obtain the final IGBT junction temperature specifically includes:
constructing a junction temperature model through a convolutional neural network based on the Wen Mindian parameters to obtain a simulated junction temperature;
and performing error function calculation on the initial IGBT junction temperature through the simulation junction temperature and the initial IGBT junction temperature, and optimizing the initial IGBT junction temperature to obtain the final IGBT junction temperature.
According to an aspect of the above technical solution, the calculation formula of the junction temperature model is:
，
wherein,for Wen Mindian parameter, ++>To simulate junction temperature>、/>Are coefficients.
According to an aspect of the foregoing technical solution, the calculation formula of the error function is:
，
wherein E is an error value,to simulate junction temperature>And the initial IGBT junction temperature is obtained.
According to an aspect of the above technical solution, the step of optimizing the initial IGBT junction temperature to obtain the final IGBT junction temperature specifically includes:
and carrying out coefficient optimization on the initial IGBT junction temperature, wherein a calculation formula of the coefficient optimization is as follows:
，
wherein,for learning rate, E is error value, +.>、/>All are->Iteration of->、/>All are->Is performed in the first iteration;
according to the optimized coefficient、/>And calculating to obtain the final IGBT junction temperature.
According to one aspect of the above technical solution, the step of measuring and collecting a busbar voltage waveform of the IGBT module, and inputting the busbar voltage waveform into a signal processing circuit for preprocessing to obtain a temperature-sensitive electrical parameter specifically includes:
measuring and collecting bus voltage waveforms of the IGBT module;
inputting the busbar voltage waveform into a signal processing circuit for filtering, amplifying and rectifying pretreatment to obtain a voltage signal;
and carrying out direct-proportion or inverse-proportion conversion on the voltage signal to obtain the temperature-sensitive electrical parameter.
Another aspect of the present invention provides an IGBT junction temperature estimation system, where the IGBT junction temperature estimation system is configured to implement the above IGBT junction temperature estimation method, and the system includes:
the parameter acquisition module is used for measuring and collecting bus voltage waveforms of the IGBT module, and inputting the bus voltage waveforms into the signal processing circuit for preprocessing to obtain temperature-sensitive electrical parameters;
the loss calculation module is used for collecting the instantaneous current waveform of the IGBT module, calculating the loss of the IGBT module according to the working state of the IGBT module and the instantaneous current waveform, and the calculation formula of the loss of the IGBT module is as follows:
，
wherein,for conduction loss->For switching losses +.>For loss, < >>For on-resistance +.>In order to be an instantaneous current,is a direct current voltage>For the on time of the IGBT module, +.>For the turn-off time of the IGBT +.>Is the switching frequency;
the initial estimation module is used for constructing a thermal resistance network model based on the loss and the thermal resistance and heat capacity parameters to obtain the temperature distribution of each layer in the IGBT module, and estimating the initial IGBT junction temperature through the temperature distribution of each layer, wherein the calculation formula for constructing the thermal resistance network model is as follows:
，
wherein,for the temperature of the i-th layer, +.>For the temperature of the j-th layer>For the capacitance of the i-th layer, < >>Is the thermal resistance between the i-th layer and the j-th layer, and (2)>Loss of the i-th layer; i=1.. c, performing operation; j=1.. c, performing operation;
and the final estimation module is used for optimizing the thermal resistance network model based on the Wen Mindian parameters so as to obtain the final IGBT junction temperature.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:
fig. 1 is a flow chart of an IGBT junction temperature estimation method according to a first embodiment of the invention;
fig. 2 is a block diagram of a structure of an IGBT junction temperature estimation system according to a second embodiment of the invention;
description of the drawings element symbols:
the system comprises a parameter acquisition module 100, a loss calculation module 200, an initial estimation module 300 and a final estimation module 400.
Detailed Description
In order to make the objects, features and advantages of the present invention more comprehensible, embodiments accompanied with figures are described in detail below. Several embodiments of the invention are presented in the figures. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "mounted" on another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," "upper," "lower," and the like are used herein for descriptive purposes only and not to indicate or imply that the apparatus or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore should not be construed as limiting the invention.
In the present invention, unless explicitly stated and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Example 1
Referring to fig. 1, a method for estimating an IGBT junction temperature according to a first embodiment of the present invention includes steps S10 to S13:
step S10, measuring and collecting bus voltage waveforms of the IGBT module, and inputting the bus voltage waveforms into a signal processing circuit for preprocessing to obtain temperature-sensitive electrical parameters;
specifically, measuring and collecting bus voltage waveforms of the IGBT module;
inputting the busbar voltage waveform into a signal processing circuit for filtering, amplifying and rectifying pretreatment to obtain a voltage signal;
and carrying out direct-proportion or inverse-proportion conversion on the voltage signal to obtain the temperature-sensitive electrical parameter.
Because the bus voltage waveform and the IGBT junction temperature have linear dependency, when the IGBT module is turned on or turned off, the peak or valley appearing on the bus voltage waveform increases or decreases along with the rise of the junction temperature.
Step S11, collecting an instantaneous current waveform of the IGBT module, and calculating the loss of the IGBT module according to the working state of the IGBT module and the instantaneous current waveform, wherein the calculation formula of the loss of the IGBT module is as follows:
，
wherein,for conduction loss->For switching losses +.>For loss, < >>For on-resistance +.>In order to be an instantaneous current,is a direct current voltage>For the on time of the IGBT module, +.>For the turn-off time of the IGBT +.>Is the switching frequency;
specifically, a current sensor is installed between the grid electrode and the emitter electrode of the IGBT module and used for collecting the instantaneous current waveform of the IGBT module and calculating the conduction loss and the switching loss of the IGBT module so as to reflect the loss and the junction temperature change of the IGBT module more accurately, thereby improving the performance and the service life of the system.
Step S12, constructing a thermal resistance network model based on the loss and the thermal resistance and heat capacity parameters to obtain temperature distribution of each layer in the IGBT module, and estimating initial IGBT junction temperature through the temperature distribution of each layer, wherein a calculation formula constructed by the thermal resistance network model is as follows:
，
wherein,for the temperature of the i-th layer, +.>For the temperature of the j-th layer>For the capacitance of the i-th layer, < >>Is the thermal resistance between the i-th layer and the j-th layer, and (2)>Loss of the i-th layer; i=1.. c, performing operation; j=1.. c, performing operation;
and estimating the initial IGBT junction temperature through the temperature distribution of each layer, which comprises the following steps:
acquiring the temperature of the innermost layer, and estimating the initial IGBT junction temperature through the temperature of the innermost layer, wherein the calculation formula of the initial IGBT junction temperature is as follows:
，
wherein,is->Temperature of the innermost layer,/->For the initial IGBT junction temperature, +.>Is IGBT junction temperature resistance->For instantaneous current, +.>、/>Are coefficients.
The temperature distribution of each layer inside the IGBT module is calculated by utilizing the thermal resistance network model, and the initial IGBT junction temperature is estimated more accurately according to the temperature of the innermost chip, so that the complexity and the cost of the system are reduced.
And step S13, optimizing the thermal resistance network model based on the Wen Mindian parameters to obtain the final IGBT junction temperature.
Constructing a junction temperature model through a convolutional neural network based on the Wen Mindian parameters to obtain a simulated junction temperature;
the calculation formula of the junction temperature model is as follows:
，
wherein,is Wen Mindian Ginseng radixCount (n)/(l)>To simulate junction temperature>、/>Are coefficients.
In addition, the convolutional neural network takes the temperature-sensitive electrical parameter as input data and inputs the temperature-sensitive electrical parameter into the convolutional layer. Each convolution layer is composed of a plurality of convolution kernels, each convolution kernel performs local feature extraction on input data, and a feature map is obtained through an activation function. The feature map reflects feature information in different scales and directions in the input data.
And inputting the obtained characteristic diagram into three corresponding pooling layers. And each pooling layer samples the feature map, and the pooled feature map is obtained through methods such as maximum value or average value. The pooled feature map retains the most important feature information in the input data, and reduces the dimension and redundancy of the data.
The convolutional neural network splices the pooled feature map obtained by the pooling layer into a one-dimensional vector, and inputs the one-dimensional vector into a full-connection layer. The full connection layer performs linear transformation and activation function operation on the one-dimensional vector and outputs a scalar value as an imitation value of the IGBT junction temperature. The convolutional neural network is trained through experimental data to improve the accuracy and stability of estimation. In particular, the experimental data include temperature-sensitive electrical parameters and true IGBT junction temperatures under different operating conditions and package degradation conditions.
And performing error function calculation on the initial IGBT junction temperature through the simulation junction temperature and the initial IGBT junction temperature, and optimizing the initial IGBT junction temperature to obtain the final IGBT junction temperature.
The calculation formula of the error function is as follows:
，
wherein E is an error value,to simulate junction temperature>And the initial IGBT junction temperature is obtained.
Optimizing the initial IGBT junction temperature to obtain a final IGBT junction temperature, wherein the method specifically comprises the following steps:
and carrying out coefficient optimization on the initial IGBT junction temperature, wherein a calculation formula of the coefficient optimization is as follows:
，
wherein,for learning rate, E is error value, +.>、/>All are->Iteration of->、/>All are->Is performed in the first iteration;
according to the optimized coefficient、/>And calculating to obtain the final IGBT junction temperature.
By calculating the simulated junction temperature and the simulated junction temperatureThe error between the initial IGBT junction temperatures is then reversely transferred according to the error, and the coefficients are updated layer by layer、/>. Therefore, the junction temperature of the output and the real IGBT is as close as possible, the error is reduced, the error function reaches the minimum value, and the precision and the stability are improved.
Compared with the prior art, the IGBT junction temperature estimation method in the embodiment has the beneficial effects that: the IGBT junction temperature estimation method provided by the invention can effectively and accurately estimate the IGBT junction temperature, specifically, the instantaneous current waveform of the IGBT module is collected, and the loss of the IGBT module is calculated according to the working state of the IGBT module and the instantaneous current waveform; the conduction loss and the switching loss of the IGBT module are calculated to more accurately reflect the loss and the junction temperature change of the IGBT module, so that the performance and the service life of the system are improved; constructing a thermal resistance network model based on the loss and the thermal resistance heat capacity parameters to obtain temperature distribution of each layer in the IGBT module, and estimating initial IGBT junction temperature through the temperature distribution of each layer; the temperature distribution of each layer inside the IGBT module is calculated by utilizing a thermal resistance network model, the initial IGBT junction temperature is estimated more accurately according to the temperature of the innermost layer chip, the complexity and the cost of the system are reduced, the thermal resistance network model is optimized based on Wen Mindian parameters to obtain the final IGBT junction temperature, the coefficient is updated layer by calculating the error between the simulated junction temperature and the initial IGBT junction temperature and then reversely transmitting according to the error、/>Thereby the output and the real IGBT junction temperature are as close as possible, the error is reduced, the error function reaches the minimum value, the precision and the stability are improved, and the problem that the IGBT junction temperature is estimated by the infrared thermal imager in the prior art and is difficult to detect in the IGBT module is solvedAnd the temperature of each layer of the part and the junction temperature are estimated with low accuracy.
Example two
Referring to fig. 2, an IGBT junction temperature estimation system according to a second embodiment of the invention is shown, the system includes:
the parameter acquisition module 100 is used for measuring and collecting bus voltage waveforms of the IGBT module, and inputting the bus voltage waveforms into the signal processing circuit for preprocessing to obtain temperature-sensitive electrical parameters;
specifically, measuring and collecting bus voltage waveforms of the IGBT module;
inputting the busbar voltage waveform into a signal processing circuit for filtering, amplifying and rectifying pretreatment to obtain a voltage signal;
and carrying out direct-proportion or inverse-proportion conversion on the voltage signal to obtain the temperature-sensitive electrical parameter.
The loss calculation module 200 is configured to collect an instantaneous current waveform of the IGBT module, calculate a loss of the IGBT module according to a working state of the IGBT module and the instantaneous current waveform, and calculate a calculation formula of the loss of the IGBT module is:
，
wherein,for conduction loss->For switching losses +.>For loss, < >>For on-resistance +.>In order to be an instantaneous current,is a direct current voltage>For the on time of the IGBT module, +.>For the turn-off time of the IGBT +.>Is the switching frequency;
specifically, a current sensor is installed between the grid electrode and the emitter electrode of the IGBT module and used for collecting the instantaneous current waveform of the IGBT module and calculating the conduction loss and the switching loss of the IGBT module.
The initial estimation module 300 is configured to construct a thermal resistance network model based on the loss and the thermal resistance and heat capacity parameters, obtain temperature distribution of each layer in the IGBT module, and estimate an initial IGBT junction temperature according to the temperature distribution of each layer, where a calculation formula constructed by the thermal resistance network model is as follows:
，
wherein,for the temperature of the i-th layer, +.>For the temperature of the j-th layer>For the capacitance of the i-th layer, < >>Is the thermal resistance between the i-th layer and the j-th layer, and (2)>Loss of the i-th layer; i=1.. c, performing operation; j=1.. c, performing operation;
and estimating the initial IGBT junction temperature through the temperature distribution of each layer, which comprises the following steps:
acquiring the temperature of the innermost layer, and estimating the initial IGBT junction temperature through the temperature of the innermost layer, wherein the calculation formula of the initial IGBT junction temperature is as follows:
，
wherein,is->Temperature of the innermost layer,/->For the initial IGBT junction temperature, +.>Is IGBT junction temperature resistance->For instantaneous current, +.>、/>Are coefficients.
And the final estimation module 400 is configured to optimize the thermal resistance network model based on the Wen Mindian parameter, so as to obtain a final IGBT junction temperature.
Constructing a junction temperature model through a convolutional neural network based on the Wen Mindian parameters to obtain a simulated junction temperature;
the calculation formula of the junction temperature model is as follows:
，
wherein,for Wen Mindian parameter, ++>To simulate junction temperature>、/>Are coefficients.
In addition, the convolutional neural network takes the temperature-sensitive electrical parameter as input data and inputs the temperature-sensitive electrical parameter into the convolutional layer. Each convolution layer is composed of a plurality of convolution kernels, each convolution kernel performs local feature extraction on input data, and a feature map is obtained through an activation function. The feature map reflects feature information in different scales and directions in the input data.
And inputting the obtained characteristic diagram into three corresponding pooling layers. And each pooling layer samples the feature map, and the pooled feature map is obtained through methods such as maximum value or average value. The pooled feature map retains the most important feature information in the input data, and reduces the dimension and redundancy of the data.
The convolutional neural network splices the pooled feature map obtained by the pooling layer into a one-dimensional vector, and inputs the one-dimensional vector into a full-connection layer. The full connection layer performs linear transformation and activation function operation on the one-dimensional vector and outputs a scalar value as an imitation value of the IGBT junction temperature. The convolutional neural network is trained through experimental data to improve the accuracy and stability of estimation. In particular, the experimental data include temperature-sensitive electrical parameters and true IGBT junction temperatures under different operating conditions and package degradation conditions.
And performing error function calculation on the initial IGBT junction temperature through the simulation junction temperature and the initial IGBT junction temperature, and optimizing the initial IGBT junction temperature to obtain the final IGBT junction temperature.
The calculation formula of the error function is as follows:
，
wherein E is an error value,to simulate junction temperature>And the initial IGBT junction temperature is obtained.
Optimizing the initial IGBT junction temperature to obtain a final IGBT junction temperature, wherein the method specifically comprises the following steps:
and carrying out coefficient optimization on the initial IGBT junction temperature, wherein a calculation formula of the coefficient optimization is as follows:
，
wherein,for learning rate, E is error value, +.>、/>All are->Iteration of->、/>All are->Is performed in the first iteration;
according to the optimized coefficient、/>And calculating to obtain the final IGBT junction temperature.
Compared with the prior art, the IGBT junction temperature estimation system shown in the embodiment has the beneficial effects that: the IGBT junction temperature estimation system provided by the invention can effectively and accurately estimate the IGBT junction temperature, specifically, the temperature distribution of each layer inside the IGBT module is calculated through the initial estimation module, the initial IGBT junction temperature is estimated more accurately according to the temperature of the innermost layer chip, the complexity and the cost of the system are reduced, the error between the simulated junction temperature and the initial IGBT junction temperature is calculated through the final estimation module, and then the coefficient is updated layer by layer according to the reverse transmission of the error、/>Therefore, the output and the actual IGBT junction temperature are as close as possible, the error is reduced, the error function reaches the minimum value, and the precision and the stability are improved, so that the technical problems that the temperature of each layer inside the IGBT module is difficult to detect and the junction temperature estimation accuracy is low in the prior art are solved.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing examples illustrate only a few embodiments of the invention, and are described in detail, but are not to be construed as limiting the scope of the invention. It should be noted that it is possible for those skilled in the art to make several variations and modifications without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (4)
1. An IGBT junction temperature estimation method, the method comprising:
measuring and collecting bus voltage waveforms of the IGBT module, and inputting the bus voltage waveforms into a signal processing circuit for preprocessing to obtain temperature-sensitive electrical parameters;
the method comprises the steps of collecting an instantaneous current waveform of an IGBT module, and calculating the loss of the IGBT module according to the working state of the IGBT module and the instantaneous current waveform, wherein the calculation formula of the loss of the IGBT module is as follows:
，
wherein,for conduction loss->For switching losses +.>For loss, < >>For on-resistance +.>For instantaneous current, +.>Is a direct current voltage>For the on time of the IGBT module, +.>For the turn-off time of the IGBT +.>Is the switching frequency;
based on the loss and the heat resistance and heat capacity parameters, constructing a heat resistance network model to obtain temperature distribution of each layer in the IGBT module, and estimating initial IGBT junction temperature through the temperature distribution of each layer, wherein a calculation formula constructed by the heat resistance network model is as follows:
，
wherein,for the temperature of the i-th layer, +.>For the temperature of the j-th layer>For the capacitance of the i-th layer, < >>Is the thermal resistance between the i-th layer and the j-th layer, and (2)>Loss of the i-th layer; i=1.. c, performing operation; j=1.. c, performing operation;
optimizing the thermal resistance network model based on the Wen Mindian parameters to obtain a final IGBT junction temperature, including:
based on the Wen Mindian parameters, constructing a junction temperature model through a convolutional neural network to obtain a simulated junction temperature,
the calculation formula of the junction temperature model is as follows:
，
wherein,for Wen Mindian parameter, ++>To simulate junction temperature>、/>Are all the coefficients of the two-dimensional space,
performing error function calculation through the simulated junction temperature and the initial IGBT junction temperature, and optimizing the initial IGBT junction temperature to obtain a final IGBT junction temperature, wherein the method comprises the following steps:
the calculation formula of the error function is as follows:
，
wherein E is an error value,to simulate junction temperature>For the initial IGBT junction temperature,
and carrying out coefficient optimization on the initial IGBT junction temperature, wherein a calculation formula of the coefficient optimization is as follows:
，
wherein,for learning rate, E is error value, +.>、/>All are->Iteration of->、/>All are->Is used for the iteration of (a),
according to the optimized coefficient、/>And calculating to obtain the final IGBT junction temperature.
2. The method for estimating the IGBT junction temperature according to claim 1, wherein the step of estimating the initial IGBT junction temperature by the temperature distribution of each layer specifically includes:
acquiring the temperature of the innermost layer, and estimating the initial IGBT junction temperature through the temperature of the innermost layer, wherein the calculation formula of the initial IGBT junction temperature is as follows:
，
wherein,is->Temperature of the innermost layer,/->For the initial IGBT junction temperature, +.>Is IGBT junction temperature resistance->In order to be an instantaneous current,、/>are coefficients.
3. The method for estimating the junction temperature of the IGBT according to claim 2, wherein the step of measuring and collecting a bus voltage waveform of the IGBT module, and inputting the bus voltage waveform into a signal processing circuit for preprocessing to obtain the temperature-sensitive electrical parameter, specifically comprises:
measuring and collecting bus voltage waveforms of the IGBT module;
inputting the busbar voltage waveform into a signal processing circuit for filtering, amplifying and rectifying pretreatment to obtain a voltage signal;
and carrying out direct-proportion or inverse-proportion conversion on the voltage signal to obtain the temperature-sensitive electrical parameter.
4. An IGBT junction temperature estimation system for implementing the IGBT junction temperature estimation method according to any one of claims 1 to 3, the system comprising:
the parameter acquisition module is used for measuring and collecting bus voltage waveforms of the IGBT module, and inputting the bus voltage waveforms into the signal processing circuit for preprocessing to obtain temperature-sensitive electrical parameters;
the loss calculation module is used for collecting the instantaneous current waveform of the IGBT module, calculating the loss of the IGBT module according to the working state of the IGBT module and the instantaneous current waveform, and the calculation formula of the loss of the IGBT module is as follows:
，
wherein,for conduction loss->For switching losses +.>For loss, < >>For on-resistance +.>For instantaneous current, +.>Is a direct current voltage>For the on time of the IGBT module, +.>For the turn-off time of the IGBT +.>Is the switching frequency;
the initial estimation module is used for constructing a thermal resistance network model based on the loss and the thermal resistance and heat capacity parameters to obtain the temperature distribution of each layer in the IGBT module, and estimating the initial IGBT junction temperature through the temperature distribution of each layer, wherein the calculation formula for constructing the thermal resistance network model is as follows:
，
wherein,for the temperature of the i-th layer, +.>For the temperature of the j-th layer>For the capacitance of the i-th layer, < >>Is the thermal resistance between the i-th layer and the j-th layer, and (2)>Loss of the i-th layer; i=1.. c, performing operation; j=1.. c, performing operation;
the final estimation module is configured to optimize the thermal resistance network model based on the Wen Mindian parameter to obtain a final IGBT junction temperature, and includes:
based on the Wen Mindian parameters, constructing a junction temperature model through a convolutional neural network to obtain a simulated junction temperature,
the calculation formula of the junction temperature model is as follows:
，
wherein,for Wen Mindian parameter, ++>To simulate junction temperature>、/>Are all the coefficients of the two-dimensional space,
performing error function calculation through the simulated junction temperature and the initial IGBT junction temperature, and optimizing the initial IGBT junction temperature to obtain a final IGBT junction temperature, wherein the method comprises the following steps:
the calculation formula of the error function is as follows:
，
wherein E is an error value,to simulate junction temperature>For the initial IGBT junction temperature,
and carrying out coefficient optimization on the initial IGBT junction temperature, wherein a calculation formula of the coefficient optimization is as follows:
，
wherein,for learning rate, E is error value, +.>、/>All are->Iteration of->、/>All are->Is used for the iteration of (a),
according to the optimized coefficient、/>And calculating to obtain the final IGBT junction temperature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311236571.0A CN116992819B (en) | 2023-09-25 | 2023-09-25 | IGBT junction temperature estimation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311236571.0A CN116992819B (en) | 2023-09-25 | 2023-09-25 | IGBT junction temperature estimation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116992819A CN116992819A (en) | 2023-11-03 |
| CN116992819B true CN116992819B (en) | 2024-01-26 |
Family
ID=88523456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311236571.0A Active CN116992819B (en) | 2023-09-25 | 2023-09-25 | IGBT junction temperature estimation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116992819B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108680847A (en) * | 2018-05-16 | 2018-10-19 | 国网浙江省电力公司舟山供电公司 | Hot computational methods based on the IGBT junction temperatures under fault current |
| CN110133466A (en) * | 2019-05-16 | 2019-08-16 | 上海金脉电子科技有限公司 | The junction temperature calculation method and system of IGBT module |
| CN115616367A (en) * | 2021-07-13 | 2023-01-17 | 阆芯(上海)电子科技有限公司 | Power electronic device state information online monitoring method and system |
| CN116776747A (en) * | 2023-08-18 | 2023-09-19 | 江西五十铃汽车有限公司 | IGBT module service life calculation method and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110502805B (en) * | 2019-07-31 | 2023-04-25 | 中国人民解放军海军工程大学 | IGBT physical model parameter extraction method |
| CN112084651B (en) * | 2020-09-07 | 2022-08-26 | 武汉大学 | Multi-scale wind power IGBT reliability assessment method and system considering fatigue damage |
-
2023
- 2023-09-25 CN CN202311236571.0A patent/CN116992819B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108680847A (en) * | 2018-05-16 | 2018-10-19 | 国网浙江省电力公司舟山供电公司 | Hot computational methods based on the IGBT junction temperatures under fault current |
| CN110133466A (en) * | 2019-05-16 | 2019-08-16 | 上海金脉电子科技有限公司 | The junction temperature calculation method and system of IGBT module |
| CN115616367A (en) * | 2021-07-13 | 2023-01-17 | 阆芯(上海)电子科技有限公司 | Power electronic device state information online monitoring method and system |
| CN116776747A (en) * | 2023-08-18 | 2023-09-19 | 江西五十铃汽车有限公司 | IGBT module service life calculation method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116992819A (en) | 2023-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103399241B (en) | Based on substation transformer fault diagnosis system and the method for temperature rise and load relation | |
| US9164150B2 (en) | Device for calculating impedances of battery cell and battery impedance measuring system | |
| CN103293423B (en) | Photovoltaic module in high-temperature environment performance testing device and method of testing | |
| CN105071677B (en) | Current prediction control method for two-level three-phase grid-connected inverter | |
| CN110502777A (en) | IGBT module condition detecting system and method based on neural network prediction | |
| CN103808426B (en) | The indirect measurement method of cable core temperature | |
| CN109633301B (en) | Non-invasive electrical appliance load identification method based on quantum genetic optimization | |
| CN105825019A (en) | Temperature solving algorithm of insulated gate bipolar transistor (IGBT) module | |
| CN108448585B (en) | A kind of electric network swim equation solution method of linearization based on data-driven | |
| CN103258103A (en) | Thevenin equivalent parameter identification method based on partial least squares regression | |
| CN113759225B (en) | IGBT residual life prediction and state evaluation realization method | |
| KR102646875B1 (en) | Mock cell construction method and mock cell construction device | |
| CN109193635A (en) | A kind of power distribution network topological structure method for reconstructing based on adaptive sparse homing method | |
| CN105024644A (en) | Performance evaluation system and method of photovoltaic system | |
| CN104749999A (en) | Accurate guidance system for optimizing operation of turbo generator group cold end system of assembly wet-type cooling tower | |
| CN113850154A (en) | Inverter IGBT (insulated Gate Bipolar transistor) micro fault feature extraction method based on multi-modal data | |
| Besheer et al. | Single-diode model based photovoltaic module: analysis and comparison approach | |
| Pranith et al. | Modeling and parameter extraction methods of PV modules | |
| CN116992819B (en) | IGBT junction temperature estimation method and system | |
| CN104795811A (en) | Power system interval state estimation method | |
| CN106482848A (en) | One kind is based on the generalized inverse three-core cable conductor temperature dynamic acquisition method of M P | |
| CN116908619A (en) | Harmonic source positioning method based on space-time diagram attention convolution network | |
| CN115684908A (en) | State monitoring method for power GIS equipment, storage medium and electronic device | |
| CN110850717B (en) | Neural network heat pump defrosting control device and control method by utilizing fan current | |
| CN116595395A (en) | Inverter output current prediction method and system based on deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |