Solder paste temperature soft measurement method and system based on mechanism and support vector regression, electronic equipment and storage medium

Abstract

The application discloses a tin paste temperature soft measurement method and system based on mechanism and support vector regression, electronic equipment and a storage medium, the method comprising: obtaining a one-dimensional heat conduction differential equation, an inner surface boundary condition equation and an initial temperature distribution condition in a tin paste heating process according to the law of conservation of energy and the Fourier law; discretizing the one-dimensional heat conduction differential equation according to a finite difference method to obtain a first mathematical model, and simplifying the inner surface boundary condition equation to obtain a second mathematical model; obtaining an outer surface measured temperature of the tin paste, obtaining a mechanism model according to the outer surface measured temperature, the first mathematical model, the second mathematical model and the initial temperature distribution condition, and then obtaining an inner surface temperature of the tin paste according to the mechanism model. The application is simple to implement and the calculation result is accurate, can effectively improve the temperature measurement progress in the welding process, improve the welding quality, and can be widely applied to the technical field of laser soft soldering modeling.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of laser soldering modeling, and particularly relates to a tin paste temperature soft measurement method and system based on mechanism and support vector regression, an electronic device and a storage medium. BACKGROUND

[0002] The laser soldering technology is widely applied in microelectronic and microsystem packaging, optical fiber device manufacturing, medical instrument manufacturing, micro component manufacturing and aerospace fields. In the laser soldering process, the inner surface of the tin paste is directly in contact with the workpiece to be welded, and therefore the inner surface temperature of the tin paste is also a main factor affecting the welding effect. The existing temperature measurement methods mainly include infrared temperature measurement and thermocouple temperature measurement, and the two methods have respective advantages and disadvantages. The infrared temperature measurement method is simple and easy to operate, and has a fast temperature measurement speed, but the infrared temperature measurement method is susceptible to external interference when measuring the temperature, which also makes the infrared temperature measurement result not accurate enough, and in the actual welding process, the infrared temperature measurement method can only measure the temperature of the outer surface of the tin paste. In contrast to the infrared temperature measurement method, the thermocouple temperature measurement method has high temperature measurement result accuracy, and measures the temperature of the inner surface of the tin paste, but the thermocouple temperature measurement method is difficult to operate and has a slow temperature measurement speed. SUMMARY

[0003] To solve the above technical problems, the purpose of the present application is to provide a tin paste temperature soft measurement method and system based on mechanism and support vector regression, an electronic device and a storage medium, which can effectively detect the inner surface temperature of the tin paste.

[0004] To achieve the above purpose, one aspect of the embodiment of the present application provides a tin paste temperature soft measurement method based on mechanism and support vector regression, comprising the following steps:

[0005] According to the energy conservation law and the Fourier law, a one-dimensional heat conduction differential equation, an inner surface boundary condition equation and an initial temperature distribution condition in the tin paste heating process are obtained;

[0006] The one-dimensional heat conduction differential equation is discretized according to the finite difference method to obtain a first mathematical model, and the inner surface boundary condition equation is simplified to obtain a second mathematical model;

[0007] The outer surface measured temperature of the tin paste is obtained, a mechanism model is obtained according to the outer surface measured temperature, the first mathematical model, the second mathematical model and the initial temperature distribution condition, and then the inner surface temperature of the tin paste is obtained according to the mechanism model.

[0008] In some embodiments, the tin paste temperature soft measurement method further comprises a step of detecting the error of the inner surface temperature, which specifically comprises:

[0009] A plurality of sets of experimental data are obtained through a plurality of sets of control experiments with tin discs of different diameters, each set of the experimental data comprising a first tin disc diameter, a first defocus amount, a first heating power, infrared temperature measurement data, and thermocouple temperature measurement data;

[0010] The first inner surface temperature is obtained by inputting the infrared temperature measurement data into the mechanism model, and then the first tin disc diameter, the first defocus amount, the first heating power, and the infrared temperature measurement data are inputted into a pre-trained error prediction model to obtain an error value;

[0011] The second inner surface temperature is obtained by subtracting the error value from the first inner surface temperature, and then the second inner surface temperature is smoothed to obtain a third inner surface temperature;

[0012] The error range value is obtained by comparing the third inner surface temperature with the thermocouple temperature measurement data.

[0013] In some embodiments, the tin paste temperature soft measurement method further comprises the step of pre-training the error prediction model, which specifically comprises:

[0014] A plurality of sets of experimental data samples are obtained through a plurality of sets of control experiments with tin discs of different diameters, each set of the experimental data sample comprising a second tin disc diameter, a second defocus amount, a second heating power, inner surface temperature measurement data, and outer surface temperature measurement data;

[0015] The first inner surface temperature measurement data is calculated according to the first thermal conductivity coefficient and the mechanism model, and then the first inner surface temperature measurement data is compared with, adjusted, and mean value calculated with the inner surface temperature measurement data to obtain a thermal conductivity coefficient mean value;

[0016] The second inner surface temperature measurement data is calculated according to the thermal conductivity coefficient mean value and the mechanism model, and then the difference between the second inner surface temperature measurement data and the inner surface temperature measurement data is calculated;

[0017] The training data set is obtained by normalizing each of the second tin disc diameters, each of the second defocus amounts, each of the second heating powers, and each of the outer surface temperature measurement data, and then the pre-set support vector regression model is trained according to the training data set and the difference to obtain the error prediction model.

[0018] In some embodiments, the one-dimensional heat conduction differential equation is:

[0019]

[0020] Wherein, p represents the density of the solder paste, c represents the specific heat capacity of the solder paste, T represents the temperature of the solder paste, τ represents the heating time, λ represents the thermal conductivity, and z represents the one-dimensional spatial coordinate;

[0021] The inner surface boundary condition equation is:

[0022]

[0023] The initial temperature distribution condition is:

[0024]

[0025] Wherein, T z,1 represents the temperature of the solder paste at the one-dimensional spatial point z at time 1, and T0 represents the room temperature.

[0026] In some embodiments, the step of discretizing the one-dimensional heat conduction differential equation according to the finite difference method to obtain the first mathematical model specifically comprises:

[0027] The solder paste is evenly divided on the one-dimensional spatial axis and the time axis by the finite difference method to obtain a plurality of spatial points;

[0028] Each spatial point is substituted into the one-dimensional heat conduction differential equation to be discretized to obtain the first mathematical model.

[0029] In some embodiments, the first mathematical model is:

[0030]

[0031] Wherein, p represents the density of the solder paste, c represents the specific heat capacity of the solder paste, Δτ represents the heating time change, λ represents the thermal conductivity, Δz represents the one-dimensional spatial change, and T i,j represents the temperature of the solder paste at the one-dimensional spatial point i at time j, and , .

[0032] In some embodiments, the second mathematical model is:

[0033]

[0034] Wherein, Δz represents the one-dimensional spatial change, and T i,j represents the temperature of the solder paste at the one-dimensional spatial point i at time j, and .

[0035] To achieve the above object, another aspect of the embodiment of the present application proposes a solder paste temperature soft measurement system based on mechanism and support vector regression, comprising:

[0036] The tin paste heating condition analysis module is used for obtaining a one-dimensional heat conduction differential equation, an inner surface boundary condition equation and an initial temperature distribution condition in a tin paste heating process according to the law of conservation of energy and the Fourier law.

[0037] The mathematical model construction module is used for discretizing the one-dimensional heat conduction differential equation according to the finite difference method to obtain a first mathematical model, and simplifying the inner surface boundary condition equation to obtain a second mathematical model.

[0038] The temperature soft measurement module is used for acquiring an outer surface measured temperature of the tin paste, obtaining a mechanism model according to the outer surface measured temperature, the first mathematical model, the second mathematical model and the initial temperature distribution condition, and further obtaining an inner surface temperature of the tin paste according to the mechanism model.

[0039] To achieve the above object, another aspect of the embodiment of the present application provides an electronic device, which comprises a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection communication between the processor and the memory, and the program is executed by the processor to realize the tin paste temperature soft measurement method based on mechanism and support vector regression as described above.

[0040] To achieve the above object, another aspect of the embodiment of the present application provides a storage medium, which is a computer readable storage medium for computer readable storage, and the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to realize the tin paste temperature soft measurement method based on mechanism and support vector regression as described above.

[0041] The tin paste temperature soft measurement method, system, electronic device and storage medium based on mechanism and support vector regression have the following beneficial effects: one-dimensional heat conduction differential equation and boundary conditions in a tin paste heating process are obtained according to the law of conservation of energy and the Fourier law, the one-dimensional heat conduction differential equation and the boundary conditions are simplified based on the finite difference method to establish a first mathematical model and a second mathematical model, thereby a mechanism model is further constructed, the inner surface temperature is calculated according to the measured tin paste outer surface temperature through the constructed mechanism model, and an error prediction model trained in advance is used to describe errors caused by infrared temperature measurement and other reasons. The present application is suitable for different heating powers, different tin paste qualities and different tin pan diameters, is simple to implement, has accurate calculation results, can effectively improve the temperature measurement progress in the welding process, and further improves the welding quality. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following introduces the drawings needed to be used in the embodiments of the present application. It should be understood that the drawings introduced below are merely for facilitating the clear description of the technical solutions in the embodiments of the present application, and other drawings can also be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0043] Figure 1 A step flow chart of a tin paste temperature soft measurement method based on mechanism and support vector regression provided by the embodiments of the present application is shown in the figure.

[0044] Figure 2 An energy balance analysis diagram of a micro-element parallelepiped arbitrarily taken out from the tin paste provided by the embodiments of the present application is shown in the figure.

[0045] Figure 3 A one-dimensional space and time temperature field distribution diagram of the tin paste provided by the embodiments of the present application is shown in the figure.

[0046] Figure 4 A comparison diagram of the temperature data and the measured temperature data under the condition that the 4mm tin disc diameter is 0-12.997w irregularly changed power and heated for 5.5s provided by the embodiments of the present application is shown in the figure.

[0047] Figure 5 A temperature error range schematic diagram under the condition that the 4mm tin disc diameter is 0-12.997w irregularly changed power and heated for 5.5s provided by the embodiments of the present application is shown in the figure.

[0048] Figure 6 A comparison diagram of the temperature data and the measured temperature data under the condition that the 4mm tin disc diameter is 11-14w linearly increased power and heated for 5.5s provided by the embodiments of the present application is shown in the figure.

[0049] Figure 7 A temperature error range schematic diagram under the condition that the 4mm tin disc diameter is 11-14w linearly increased power and heated for 5.5s provided by the embodiments of the present application is shown in the figure.

[0050] Figure 8 A comparison diagram of the temperature data and the measured temperature data under the condition that the 4mm tin disc diameter is 14-11w linearly decreased power and heated for 5.5s provided by the embodiments of the present application is shown in the figure.

[0051] Figure 9 A temperature error range schematic diagram under the condition that the 4mm tin disc diameter is 14-11w linearly decreased power and heated for 5.5s provided by the embodiments of the present application is shown in the figure.

[0052] Figure 10 A comparison diagram of the temperature data and the measured temperature data under the condition that the 5mm tin disc diameter is 9.5628w constant power and heated for 15s provided by the embodiments of the present application is shown in the figure.

[0053] Figure 11 Temperature error range diagram of 5mm tin disc diameter 9.5628w constant power heating for 15s according to an embodiment of the present application;

[0054] Figure 12 Original infrared data and filtered infrared data comparison diagram of 4mm tin disc diameter 8.456w constant power heating for 10s according to an embodiment of the present application;

[0055] Figure 13 Difference diagram of tin paste inner surface temperature calculated by mechanism model and tin paste inner surface temperature measured by thermocouple according to an embodiment of the present application;

[0056] Figure 14 Structure diagram of a tin paste temperature soft measurement system based on mechanism and support vector regression according to an embodiment of the present application;

[0057] Figure 15 Hardware structure diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not used to limit the present application. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementation manners described in the following exemplary embodiments do not represent all the implementation manners consistent with the embodiments of the present application, but are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the appended claims.

[0059] It can be understood that the terms “first”, “second”, and the like used in the present application can be used herein to describe various concepts, but unless specifically stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present application, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as the first information. Depending on the context, the word “if” as used herein can be interpreted as “when” or “when” or “in response to determining”.

[0060] The terms “at least one”, “multiple”, “each”, “any”, and the like used in the present application include one, two or more than two, multiple includes two or more than two, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0061] Laser soldering technology has a wide range of applications in microelectronic and microsystem packaging, fiber device manufacturing, medical device manufacturing, micro-component manufacturing, and aerospace fields. It can achieve precise connection and packaging of micro-components, and ensure the quality and reliability of the welded parts. With the continuous progress of science and technology, the application prospect of laser soldering technology will continue to expand. In the process of laser soldering, temperature control of the heating area is extremely important, which can directly affect the final result of laser welding, and a more accurate temperature measurement method is particularly important for better temperature control of the heating area.

[0062] The existing temperature measurement methods mainly include infrared temperature measurement and thermocouple temperature measurement, and these two temperature measurement methods have their own advantages and disadvantages. The infrared temperature measurement method is simple and easy to operate, and the temperature measurement speed is fast, but the infrared temperature measurement method is easily affected by external interference when measuring temperature, which also makes the accuracy of the infrared temperature measurement result not enough, and in the actual welding process, it can only measure the temperature of the outer surface of the solder paste, and the inner surface of the solder paste is in direct contact with the workpiece, and the inner surface temperature of the solder paste also affects the welding effect. On the contrary, the accuracy of the temperature measurement result of the thermocouple temperature measurement is high, and the temperature of the inner surface of the solder paste is measured, but the operation is difficult and the temperature measurement speed is slow.

[0063] Therefore, the embodiment of the present application provides a tin paste temperature soft measurement method based on mechanism and support vector regression, one-dimensional heat conduction differential equation and boundary condition in the heating process of the tin paste are obtained according to the law of conservation of energy and Fourier's law, and the first mathematical model and the second mathematical model are established by simplifying the one-dimensional heat conduction differential equation and the boundary condition based on the finite difference method, so as to further construct a mechanism model, and the inner surface temperature is calculated according to the measured outer surface temperature of the tin paste through the constructed mechanism model, and an error prediction model trained in advance is used to describe the error caused by infrared temperature measurement and other reasons. The present application is suitable for different heating power, different tin paste quality and different tin disc diameter and other conditions, the implementation is simple, the calculation result is accurate, the temperature measurement progress in the welding process can be effectively improved, and the welding quality is improved.

[0064] Reference Figure 1 , Figure 1 A step flow chart of a tin paste temperature soft measurement method based on mechanism and support vector regression provided by the embodiment of the present application, the embodiment of the present application provides a tin paste temperature soft measurement method based on mechanism and support vector regression, which comprises steps S101-S103:

[0065] S101, one-dimensional heat conduction differential equation, inner surface boundary condition equation and initial temperature distribution condition in the heating process of the tin paste are obtained according to the law of conservation of energy and Fourier's law;

[0066] Further, as an optional implementation, the one-dimensional heat conduction differential equation is:

[0067]

[0068] Where ρ represents solder paste density, c represents solder paste specific heat capacity, T represents solder paste temperature, τ represents heating time, λ represents thermal conductivity, and z represents one-dimensional spatial coordinates;

[0069] The boundary condition equations for the inner surface are:

[0070]

[0071] The initial temperature distribution conditions are:

[0072]

[0073] Among them, T z,1 This represents the solder paste temperature at point z in one-dimensional space at time 1, and T0 represents room temperature.

[0074] Specifically, such as Figure 2 The diagram shows the energy balance analysis of an arbitrary parallelepiped element taken from the solder paste. The energy balance is analyzed by arbitrarily selecting a parallelepiped element from the solder paste. The heat flow in any direction in space is decomposed into heat flows along the x, y, and z coordinate axes, as shown below. Figure 2 middle , , As shown, the heat flow of the infinitesimal element is introduced through the x, y, and z surfaces. According to Fourier's law, the following equation can be obtained:

[0075]

[0076] Where λ represents the thermal conductivity. Indicates heat flow at Components of direction exist The value of a point, and so on for the rest.

[0077] pass , , The heat flux of the infinitesimal element derived from the three surfaces can also be obtained by applying Fourier's law as follows:

[0078]

[0079] According to the law of conservation of energy, the total heat flow introduced by the solder paste + the heat generated by the internal heat source = the total heat flow removed + the increase in internal energy, where the increase in internal energy = Heat generated by internal heat source = .

[0080] From the above formula, we can see that:

[0081]

[0082] The tin paste heating process does not consider internal heat source, and only considers one-dimensional temperature field distribution in the z-axis direction during the heating process when calculating the inner surface temperature from the outer surface temperature, so the one-dimensional heat conduction differential equation is as follows:

[0083]

[0084] Wherein, p represents the density of tin paste, c represents the specific heat capacity of tin paste, T represents the temperature of tin paste, τ represents the heating time, λ represents the thermal conductivity, and z represents the one-dimensional space coordinate.

[0085] The inner surface boundary condition during the tin paste heating process is analyzed. When the tin paste is heated on the tin tray, the inner surface of the tin paste is isolated from the external environment, and because the tin tray is relatively thick, it can slow down the speed of heat transfer outward, so that the inner surface of the tin paste can maintain a relatively stable temperature distribution. In a short time of tin paste heating, it can be approximately considered that the inner surface of the tin paste satisfies the adiabatic edge condition. That is, the inner surface boundary condition equation is as follows:

[0086]

[0087] Before heating, the temperature of any point in the tin paste is room temperature, so the initial temperature distribution condition of the tin paste is:

[0088]

[0089] Wherein, T z,1 represents the temperature of the tin paste at the one-dimensional space point z at time 1, and T0 represents room temperature.

[0090] S102, discretize the one-dimensional heat conduction differential equation according to the finite difference method to obtain a first mathematical model, and simplify the inner surface boundary condition equation to obtain a second mathematical model;

[0091] Further as an optional implementation, the step of discretizing the one-dimensional heat conduction differential equation according to the finite difference method to obtain the first mathematical model specifically includes the following steps S1021 and S1022:

[0092] S1021, average division of the tin paste on the one-dimensional space axis and the time axis is carried out by the finite difference method to obtain a plurality of space points;

[0093] S1022, each space point is substituted into the one-dimensional heat conduction differential equation to be discretized to obtain the first mathematical model.

[0094] Further as an optional implementation, the first mathematical model is:

[0095]

[0096] wherein, ρ represents the density of the tin paste, c represents the specific heat capacity of the tin paste, Δτ represents the heating time variation, λ represents the thermal conductivity, Δz represents the one-dimensional spatial variation, T i,j represents the tin paste temperature at one-dimensional spatial point i at time j, and , .

[0097] Specifically, as Figure 3 shown is a tin paste one-dimensional spatial and time temperature field distribution diagram. The embodiment of the present application uses the finite difference method to divide the tin paste in the z-axis direction into m segments, so there are m+1 points, and on the time axis, there are n time points. By analyzing the point (i+1, j), the following formula can be obtained:

[0098]

[0099] Substituting the above formula into the one-dimensional heat conduction differential equation, it can be known that the first mathematical model of the one-dimensional heat conduction differential equation after discretization by the finite difference method is as follows:

[0100]

[0101] After combining like terms for the first mathematical model, the following formula can be obtained:

[0102]

[0103] Further as an optional implementation, the second mathematical model is:

[0104]

[0105] wherein, Δz represents the one-dimensional spatial variation, T i,j represents the tin paste temperature at one-dimensional spatial point i at time j, and .

[0106] Specifically, the second mathematical model uses the finite difference method to simplify the inner surface boundary condition equation to obtain.

[0107] The specific information of the parameters involved in the above formula is shown in Table 1 as follows:

[0108]

[0109] Table 1

[0110] S103. Obtain the measured temperature of the outer surface of the solder paste, and obtain the mechanism model based on the measured temperature of the outer surface, the first mathematical model, the second mathematical model and the initial temperature distribution conditions, and then obtain the inner surface temperature of the solder paste based on the mechanism model.

[0111] Specifically, refer to Figure 3 The solder paste is divided into m segments along the z-axis, resulting in m+1 points. The point (z, τ) represents the solder paste temperature at point z in one-dimensional space at time τ. When calculating the inner surface temperature from the outer surface temperature, the outer surface temperature measured by infrared spectroscopy is known. With initial conditions , to calculate For example, from the one-dimensional thermal conductivity differential equation and the inner surface boundary conditions, we can obtain the following system of m-element linear equations:

[0112]

[0113] Simplifying the system of m linear equations yields the following matrix form:

[0114] From the invertibility condition of a tridiagonal matrix, we know that the m-order tridiagonal matrix in the above equation is invertible. Therefore, we can obtain the following mechanism model:

[0115] Similarly, T can be calculated. z,3 T z,4 Until T z,n The value of .

[0116] As a further optional implementation, the solder paste temperature soft measurement method also includes a step of error detection of the inner surface temperature, specifically including the following steps C101 to C104:

[0117] C101. Multiple sets of comparative experiments were conducted using tin trays of different diameters to obtain multiple sets of experimental data. Each set of experimental data included the diameter of the first tin tray, the first defocusing amount, the first heating power, infrared temperature measurement data, and thermocouple temperature measurement data.

[0118] C102. Input the infrared temperature measurement data into the mechanism model to obtain the first inner surface temperature. Then, input the first tin plate diameter, the first defocusing amount, the first heating power, and the infrared temperature measurement data into the pre-trained error prediction model to obtain the error value.

[0119] C103. Subtract the first inner surface temperature from the error value to obtain the second inner surface temperature, and then smooth the second inner surface temperature to obtain the third inner surface temperature.

[0120] C104. Compare the temperature of the third inner surface with the temperature measured by the thermocouple to obtain the error range value.

[0121] Specifically, experiments were conducted using solder pads of different diameters under different conditions to obtain experimental data. The infrared thermography data obtained from the experiments was then filtered and substituted into a mechanistic model to calculate the first inner surface temperature of the solder paste. The infrared thermography data, heating power, solder pad diameter, and defocusing amount were used as inputs to an error prediction model to obtain the output error value. The second inner surface temperature was then obtained by subtracting the output of the error prediction model from the calculated first inner surface temperature. Since thermocouples measure the temperature of the inner surface of the solder paste, and the change in inner surface temperature is caused by the change in outer surface temperature, the thermocouple measurement data will not fluctuate drastically. However, the output of the error prediction model may fluctuate drastically. Therefore, the result of the subtraction was smoothed to obtain the third inner surface temperature. The third inner surface temperature was then compared with the measured thermocouple data. The comparison results are as follows: Figure 4 , Figure 6 , Figure 8 as well as Figure 10 As shown, the error range for each group is as follows: Figure 5 , Figure 7 , Figure 9 as well as Figure 11 As shown in Table 2, the error detection experiment information and comparison results are as follows:

[0122]

[0123] Table 2

[0124] Test results show that the solder paste temperature soft measurement method provided in this embodiment of the invention can accurately calculate the inner surface temperature of the solder paste by measuring the temperature with an infrared thermometer, which makes it easier for relevant technicians to obtain the inner surface temperature of the solder paste during the soldering process and improve the soldering quality.

[0125] As an optional implementation, the solder paste temperature soft measurement method further includes a step of pre-training an error prediction model, specifically comprising the following steps D101 to D104:

[0126] D101. Multiple sets of comparative experiments were conducted using solder trays of different diameters to obtain multiple sets of experimental data samples. Each set of experimental data samples included the second solder tray diameter, the second defocusing amount, the second heating power, the inner surface temperature measurement data, and the outer surface temperature measurement data.

[0127] Specifically, multiple sets of control experiments were first designed for the model to obtain experimental data under various conditions. In this embodiment of the invention, tin trays with diameters of 4mm and 5mm were used to conduct experiments under various different conditions. To reduce the error of the experimental data, three experiments were conducted for each condition to obtain three sets of data, and the average value was taken. The specific information of the experimental data is shown in Table 3 below:

[0128]

[0129] Table 3

[0130] The internal surface temperature data can be obtained by thermocouple measurement, while the external surface temperature data can be obtained by infrared thermometer measurement.

[0131] D102. Obtain the first thermal conductivity of the solder paste, calculate the first inner surface temperature data based on the first thermal conductivity and the mechanism model, and then compare, adjust and calculate the average value of the first inner surface temperature data with the inner surface temperature data to obtain the average thermal conductivity value.

[0132] Specifically, because the measurement results of infrared thermometers are easily affected by external factors, the infrared data is first filtered. A comparison of the original infrared data and the filtered infrared data under constant power heating of 8.456W for 10 seconds with a 4mm diameter tin tray is shown in the figure. Figure 12 As shown in the figure. After obtaining the filtered infrared data, considering that infrared thermometry cannot measure temperatures below 100 degrees Celsius, the heating process of the solder paste with an outer surface temperature below 100 degrees Celsius is regarded as a linear temperature increase process. The method of calculating the inner surface temperature through the outer surface temperature is used. Based on experience, the first thermal conductivity of the solder paste is given and substituted into the mechanism model to calculate the first inner surface temperature data of the solder paste. The thermal conductivity is adjusted by comparing the calculated first inner surface temperature data with the corresponding thermocouple measurement data (i.e., inner surface temperature data) until a reasonable thermal conductivity is obtained. Since there are three states during the solder paste heating process: below 160 degrees Celsius, the solder paste is solid; between 160 degrees Celsius and 180 degrees Celsius, the solder paste is in a solid-liquid coexistence state; and above 180 degrees Celsius, the solder paste is in a liquid state, it is necessary to identify the thermal conductivity of the three states respectively. The thermal conductivity identification results are shown in Table 4 below. The obtained average thermal conductivity is then used as the mean thermal conductivity of the solder paste.

[0133]

[0134] Table 4

[0135] D103. Calculate the second inner surface temperature data based on the average thermal conductivity and the mechanism model, and then calculate the difference between the second inner surface temperature data and the inner surface temperature data.

[0136] Specifically, the average thermal conductivity value is substituted into the mechanistic model to calculate the second inner surface temperature data of the solder paste. Considering the error nature of infrared thermometry results, the second inner surface temperature data calculated based on infrared measurement data will inevitably have an error compared to the actual inner surface temperature of the solder paste measured by thermocouples. Therefore, a support vector regression model is used to model this error. After calculating the inner surface temperature of the solder paste from the infrared measurement data, the corresponding thermocouple measurement temperature (i.e., the inner surface temperature data) is subtracted to obtain the difference.

[0137] D104. Normalize the diameter of each second tin tray, the amount of each second decoking, the power of each second heating, and the temperature measurement data of each outer surface to obtain a training dataset. Then, train the preset support vector regression model based on the training dataset and the difference to obtain the error prediction model.

[0138] Specifically, such as Figure 13 The figure shows the difference between the inner surface temperature of the solder paste calculated by the mechanism model and the inner surface temperature of the solder paste measured by the thermocouple. It can be found that the trend of temperature error change is consistent in the three states of solder paste. In order to improve the accuracy of temperature error prediction, a support vector regression model is trained for each of the three states of solder paste. The infrared temperature measurement data, heating power, solder pad diameter and defocusing amount under various conditions are used as the input of the model, and the difference calculated by the mechanism model is used as the output of the model to train the model and obtain the error prediction model.

[0139] It is worth noting that since the heating time varies under different conditions, the amount of data in different test data will also vary. In order to ensure that the model performance after training is not biased towards a certain test data, the data of each stage of each experimental data sample should be processed to the same amount of data before being put into the support vector regression model for training.

[0140] The above describes the mechanistic and support vector regression-based soft measurement method for solder paste temperature according to embodiments of the present invention. It can be understood that, compared with existing solder paste temperature measurement methods, the embodiments of the present invention obtain the one-dimensional thermal conductivity differential equation and boundary conditions during the solder paste heating process based on the law of conservation of energy and Fourier's law. Based on the finite difference method, the one-dimensional thermal conductivity differential equation and boundary conditions are simplified to establish a first mathematical model and a second mathematical model, thereby further constructing a mechanistic model. The inner surface temperature is calculated based on the measured outer surface temperature of the solder paste using the constructed mechanistic model, and a pre-trained error prediction model is used to describe the errors caused by infrared thermometry and other factors. The present invention is applicable to various situations such as different heating powers, different solder paste qualities, and different solder pad diameters. It is simple to implement, provides accurate calculation results, and has good industrial performance, effectively improving the temperature measurement accuracy during the soldering process, thereby improving soldering quality.

[0141] Reference Figure 14 This invention also provides a soft measurement system for solder paste temperature based on mechanism and support vector regression, comprising:

[0142] The solder paste heating analysis module is used to obtain the one-dimensional thermal conductivity differential equation, the inner surface boundary condition equation, and the initial temperature distribution conditions during the solder paste heating process based on the law of conservation of energy and Fourier's law.

[0143] The mathematical model construction module is used to discretize the one-dimensional thermal conductivity differential equation according to the finite difference method to obtain the first mathematical model, and to simplify the inner surface boundary condition equation to obtain the second mathematical model.

[0144] The temperature soft measurement module is used to obtain the measured temperature of the outer surface of the solder paste. Based on the measured temperature of the outer surface, the first mathematical model, the second mathematical model, and the initial temperature distribution conditions, a mechanism model is obtained, and then the inner surface temperature of the solder paste is obtained based on the mechanism model.

[0145] The content of the above embodiments of the solder paste temperature soft measurement method based on mechanism and support vector regression is applicable to this embodiment of the solder paste temperature soft measurement system based on mechanism and support vector regression. The specific functions implemented by this embodiment of the solder paste temperature soft measurement system based on mechanism and support vector regression are the same as those of the above embodiments of the solder paste temperature soft measurement method based on mechanism and support vector regression, and the beneficial effects achieved are also the same as those achieved by the above embodiments of the solder paste temperature soft measurement method based on mechanism and support vector regression.

[0146] This invention also provides an electronic device, comprising: a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for communication between the processor and the memory. When the program is executed by the processor, it implements the aforementioned soft measurement method for solder paste temperature based on mechanistic and support vector regression. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0147] like Figure 15 The diagram shown is a hardware structure schematic of an electronic device provided in an embodiment of the present invention. (Refer to...) Figure 15 This invention provides an electronic device, comprising:

[0148] The processor 1001 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present invention.

[0149] The memory 1002 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 1002 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1002 and is called and executed by the processor 1001 to execute the solder paste temperature soft measurement method based on mechanism and support vector regression of the present invention.

[0150] Input / output interface 1003 is used to implement information input and output;

[0151] The communication interface 1004 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0152] Bus 1005 transmits information between various components of the device (e.g., processor 1001, memory 1002, input / output interface 1003, and communication interface 1004);

[0153] The processor 1001, memory 1002, input / output interface 1003 and communication interface 1004 are connected to each other within the device via bus 1005.

[0154] This invention also provides a storage medium, which is a computer-readable storage medium for computer-readable storage. The storage medium stores one or more programs, which can be executed by one or more processors to implement the above-mentioned soft measurement method for solder paste temperature based on mechanism and support vector regression.

[0155] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0156] This invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to perform... Figure 1 The method shown.

[0157] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the aforementioned blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0158] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the aforementioned functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0159] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0160] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0161] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the aforementioned program can be printed, because the aforementioned program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0162] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0163] In the foregoing description of this specification, references to terms such as "one embodiment," "another embodiment," or "some embodiments" indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0164] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0165] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A soft measurement method for solder paste temperature based on mechanism and support vector regression, characterized in that, Includes the following steps: Based on the law of conservation of energy and Fourier's law, the one-dimensional thermal conductivity differential equation, the inner surface boundary condition equation, and the initial temperature distribution conditions during the solder paste heating process are obtained. The one-dimensional thermal conductivity differential equation is discretized using the finite difference method to obtain the first mathematical model, and the inner surface boundary condition equation is simplified to obtain the second mathematical model. The measured temperature of the outer surface of the solder paste is obtained, and a mechanism model is obtained based on the measured temperature of the outer surface, the first mathematical model, the second mathematical model, and the initial temperature distribution conditions. Then, the inner surface temperature of the solder paste is obtained based on the mechanism model. The solder paste temperature soft measurement method further includes a step of error detection of the inner surface temperature, which specifically includes: Multiple sets of comparative experiments were conducted using tin trays of different diameters to obtain multiple sets of experimental data. Each set of experimental data includes the diameter of the first tin tray, the first defocusing amount, the first heating power, infrared temperature measurement data, and thermocouple temperature measurement data. The infrared temperature measurement data is input into the mechanism model to obtain the first inner surface temperature. Then, the diameter of the first tin tray, the first defocusing amount, the first heating power, and the infrared temperature measurement data are input into the pre-trained error prediction model to obtain the error value. Subtract the error value from the first inner surface temperature to obtain the second inner surface temperature, and then smooth the second inner surface temperature to obtain the third inner surface temperature. The temperature of the third inner surface is compared with the temperature data measured by the thermocouple to obtain the error range value; The solder paste temperature soft measurement method also includes a step of pre-training the error prediction model, which specifically includes: Multiple sets of comparative experiments were conducted using solder trays of different diameters to obtain multiple sets of experimental data samples. Each set of experimental data samples included the second solder tray diameter, the second defocusing amount, the second heating power, the inner surface temperature measurement data, and the outer surface temperature measurement data. The first thermal conductivity of the solder paste is obtained, and the first inner surface temperature data is calculated based on the first thermal conductivity and the mechanism model. Then, the first inner surface temperature data is compared with the inner surface temperature data, adjusted and averaged to obtain the average thermal conductivity. The second inner surface temperature data is calculated based on the average thermal conductivity and the mechanism model, and then the difference between the second inner surface temperature data and the inner surface temperature data is calculated. The diameter of each second tin tray, the amount of decoupling, the power of each second heating element, and the temperature measurement data of each outer surface are normalized to obtain a training dataset. Then, a preset support vector regression model is trained based on the training dataset and the difference to obtain the error prediction model. The one-dimensional heat conduction differential equation is: Where ρ represents solder paste density, c represents solder paste specific heat capacity, T represents solder paste temperature, τ represents heating time, λ represents thermal conductivity, and z represents one-dimensional spatial coordinates; The boundary condition equation for the inner surface is: The initial temperature distribution conditions are as follows: Among them, T z,1 This represents the solder paste temperature at point z in one-dimensional space at time 1, and T0 represents room temperature.

2. The soft measurement method for solder paste temperature based on mechanism and support vector regression according to claim 1, characterized in that, The step of discretizing the one-dimensional heat conduction differential equation using the finite difference method to obtain the first mathematical model specifically includes: The solder paste is divided equally along the one-dimensional spatial axis and time axis using the finite difference method to obtain multiple spatial points. Substituting each of the spatial points into the one-dimensional heat conduction differential equation for discretization, the first mathematical model is obtained.

3. The soft measurement method for solder paste temperature based on mechanism and support vector regression according to claim 1, characterized in that, The first mathematical model is: Where ρ represents the solder paste density, c represents the solder paste specific heat capacity, Δτ represents the change in heating time, λ represents the thermal conductivity, Δz represents the one-dimensional spatial change, and T... i,j Let represent the solder paste temperature at point i in one-dimensional space at time j, and , .

4. The soft measurement method for solder paste temperature based on mechanism and support vector regression according to claim 1, characterized in that, The second mathematical model is: Where Δz represents the change in one-dimensional space, T i,j Let represent the solder paste temperature at point i in one-dimensional space at time j, and .

5. A soft-sensing system for solder paste temperature based on mechanism and support vector regression, characterized in that, include: The solder paste heating analysis module is used to obtain the one-dimensional thermal conductivity differential equation, the inner surface boundary condition equation, and the initial temperature distribution conditions during the solder paste heating process based on the law of conservation of energy and Fourier's law. The mathematical model construction module is used to discretize the one-dimensional thermal conductivity differential equation according to the finite difference method to obtain the first mathematical model, and to simplify the inner surface boundary condition equation to obtain the second mathematical model. A temperature soft measurement module is used to obtain the measured temperature of the outer surface of the solder paste, obtain a mechanism model based on the measured temperature of the outer surface, the first mathematical model, the second mathematical model and the initial temperature distribution conditions, and then obtain the inner surface temperature of the solder paste based on the mechanism model. The solder paste temperature soft measurement method further includes a step of error detection of the inner surface temperature, which specifically includes: Multiple sets of comparative experiments were conducted using tin trays of different diameters to obtain multiple sets of experimental data. Each set of experimental data includes the diameter of the first tin tray, the first defocusing amount, the first heating power, infrared temperature measurement data, and thermocouple temperature measurement data. The infrared temperature measurement data is input into the mechanism model to obtain the first inner surface temperature. Then, the diameter of the first tin tray, the first defocusing amount, the first heating power, and the infrared temperature measurement data are input into the pre-trained error prediction model to obtain the error value. Subtract the error value from the first inner surface temperature to obtain the second inner surface temperature, and then smooth the second inner surface temperature to obtain the third inner surface temperature. The temperature of the third inner surface is compared with the temperature data measured by the thermocouple to obtain the error range value; The solder paste temperature soft measurement method also includes a step of pre-training the error prediction model, which specifically includes: Multiple sets of comparative experiments were conducted using solder trays of different diameters to obtain multiple sets of experimental data samples. Each set of experimental data samples included the second solder tray diameter, the second defocusing amount, the second heating power, the inner surface temperature measurement data, and the outer surface temperature measurement data. The first thermal conductivity of the solder paste is obtained, and the first inner surface temperature data is calculated based on the first thermal conductivity and the mechanism model. Then, the first inner surface temperature data is compared with the inner surface temperature data, adjusted and averaged to obtain the average thermal conductivity. The second inner surface temperature data is calculated based on the average thermal conductivity and the mechanism model, and then the difference between the second inner surface temperature data and the inner surface temperature data is calculated. The diameter of each second tin tray, the amount of decoupling, the power of each second heating element, and the temperature measurement data of each outer surface are normalized to obtain a training dataset. Then, a preset support vector regression model is trained based on the training dataset and the difference to obtain the error prediction model. The one-dimensional heat conduction differential equation is: Where ρ represents solder paste density, c represents solder paste specific heat capacity, T represents solder paste temperature, τ represents heating time, λ represents thermal conductivity, and z represents one-dimensional spatial coordinates; The boundary condition equation for the inner surface is: The initial temperature distribution conditions are as follows: Among them, T z,1 This represents the solder paste temperature at point z in one-dimensional space at time 1, and T0 represents room temperature.

6. An electronic device, characterized in that, The electronic device includes a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for enabling communication between the processor and the memory. When the program is executed by the processor, it implements the steps of the mechanistic and support vector regression-based soft measurement method for solder paste temperature as described in any one of claims 1 to 4.

7. A storage medium, said storage medium being a computer-readable storage medium for computer-readable storage, characterized in that, The storage medium stores one or more programs, which can be executed by one or more processors to implement the steps of the soft measurement method for solder paste temperature based on mechanism and support vector regression as described in any one of claims 1 to 4.

Images