Temperature measurement method and device for reflow soldering equipment, equipment and medium

Abstract

The invention discloses a temperature measurement method and device of reflow soldering equipment, the equipment and a medium, and relates to the technical field of reflow soldering, and the method comprises the steps: obtaining a thermoelectromotive force signal obtained through temperature measurement of a thermocouple; acquiring a cold end temperature signal acquired by a cold end compensation module; and taking the thermoelectromotive force signal and the cold end temperature signal as input of a preset neural network compensation model, and performing nonlinear correction on the thermoelectromotive force signal through the preset neural network compensation model to obtain a temperature measurement result. According to the temperature measurement method, the neural network model is adopted to carry out nonlinear correction on the thermoelectromotive force signal obtained by thermocouple temperature measurement, nonlinear errors existing in thermocouple temperature measurement can be effectively corrected through the neural network model, the precision and reliability of a temperature measurement result can be improved, and the wide-range and high-precision measurement requirements are met.

Description

Technical Field

[0001] The present application relates to the technical field of reflow soldering, and in particular to a temperature measurement method, device, equipment and medium for reflow soldering equipment. Background Art

[0002] Usually, it is necessary to measure the temperature of multiple points in the reflow soldering equipment. In terms of temperature measurement, thermocouples are widely used because of their advantages such as low cost and wide temperature measurement range. In order to obtain high-precision temperature measurement results, it is necessary to correct the nonlinear error of the thermocouple temperature measurement. Traditional correction methods include hardware compensation method, table lookup method, etc. However, hardware compensation method, table lookup method, etc. are difficult to meet the measurement requirements of wide range and high precision. Therefore, how to solve the above technical defects has become a technical problem that needs to be solved urgently by technicians in this field. Summary of the invention

[0003] The purpose of this application is to provide a temperature measurement method, device, equipment and medium for reflow soldering equipment, which can improve the accuracy and reliability of temperature measurement results and meet the measurement requirements of wide range and high precision.

[0004] In order to solve the above technical problems, the present application provides a temperature measurement method of a reflow soldering device, comprising:

[0005] Obtaining the thermoelectromotive force signal obtained by thermocouple temperature measurement;

[0006] Obtain the cold end temperature signal collected by the cold end compensation module;

[0007] The thermoelectromotive force signal and the cold end temperature signal are used as inputs of a preset neural network compensation model, and nonlinear correction is performed on the thermoelectromotive force signal through the preset neural network compensation model to obtain a temperature measurement result.

[0008] In some embodiments, the thermoelectromotive force signal and the cold end temperature signal are used as inputs of a preset neural network compensation model, and the thermoelectromotive force signal is subjected to nonlinear correction by the preset neural network compensation model to obtain a temperature measurement result, which includes:

[0009] The thermoelectromotive force signal and the cold end temperature signal are used as inputs of a kernel function extreme learning machine network model, and the kernel function extreme learning machine network model is used to perform nonlinear correction on the thermoelectromotive force signal to obtain a temperature measurement result.

[0010] In some embodiments, it also includes:

[0011] Create and optimize the target parameters of the kernel function extreme learning machine network model to obtain the optimal kernel function extreme learning machine network model, so as to perform nonlinear correction on the thermoelectromotive force signal through the optimal kernel function extreme learning network model.

[0012] In some embodiments, optimizing the target parameters of the kernel function extreme learning machine network model includes:

[0013] The whale optimization algorithm is used to optimize the target parameters of the kernel function extreme learning machine network model.

[0014] In some embodiments, using the whale optimization algorithm to optimize the target parameters of the kernel function extreme learning machine network model includes:

[0015] Determine the population size, the number of iterations and the search range of the target parameter, and initialize the target parameter;

[0016] Training the kernel function extreme learning machine network model, calculating the fitness values ​​of the individuals in the population, and updating the optimal value of the population;

[0017] Update the position of individual whales and generate new target parameters;

[0018] When the fitness meets the conditions or reaches the maximum number of iterations, the optimization process is terminated;

[0019] Save the searched global optimal target parameters and establish the optimal kernel function extreme learning machine network model.

[0020] In some embodiments, obtaining a thermoelectromotive force signal obtained by thermocouple temperature measurement includes:

[0021] A digital signal corresponding to a thermoelectromotive force signal obtained by thermocouple temperature measurement uploaded by a temperature measurement circuit is received; wherein the thermoelectromotive force signal obtained by the thermocouple temperature measurement is successively subjected to radio frequency interference filtering, amplification, and analog-to-digital conversion to obtain a digital signal corresponding to the thermoelectromotive force signal.

[0022] In some embodiments, the temperature measurement circuit includes multiple thermocouple channels, supporting the simultaneous acquisition of thermoelectromotive force signals obtained by measuring the temperature of multiple thermocouples.

[0023] In order to solve the above technical problems, the present application also provides a temperature measuring device for a reflow soldering device, comprising:

[0024] A first acquisition unit is used to acquire a thermoelectromotive force signal obtained by measuring the temperature of the thermocouple;

[0025] A second acquisition unit, used to acquire the cold end temperature signal collected by the cold end compensation module;

[0026] The correction unit is used to use the thermoelectromotive force signal and the cold end temperature signal as inputs of a preset neural network compensation model, perform nonlinear correction on the thermoelectromotive force signal through the preset neural network compensation model, and obtain a temperature measurement result.

[0027] In order to solve the above technical problems, the present application also provides a temperature measuring device for a reflow soldering device, comprising:

[0028] Memory for storing computer programs;

[0029] The processor is used to implement the steps of the temperature measurement method of the reflow soldering equipment as described above when executing the computer program.

[0030] In order to solve the above technical problems, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the temperature measurement method of the reflow soldering equipment as described above are implemented.

[0031] The temperature measurement method of the reflow soldering equipment provided in the present application includes: obtaining a thermoelectromotive force signal obtained by thermocouple temperature measurement; obtaining a thermoelectromotive force signal obtained by thermocouple temperature measurement; obtaining a cold end temperature signal collected by a cold end compensation module; using the thermoelectromotive force signal and the cold end temperature signal as inputs of a preset neural network compensation model, performing nonlinear correction on the thermoelectromotive force signal through the preset neural network compensation model, and obtaining a temperature measurement result.

[0032] It can be seen that the temperature measurement method for reflow soldering equipment provided in the present application adopts thermocouples for temperature acquisition, and adopts a neural network model to perform nonlinear correction on the thermoelectromotive force signal obtained by the thermocouple temperature measurement. The neural network model can effectively correct the nonlinear error existing in the thermocouple temperature measurement, improve the accuracy and reliability of the temperature measurement results, and meet the wide range and high-precision measurement requirements.

[0033] The temperature measuring device, equipment and computer-readable storage medium of the reflow soldering equipment provided in this application all have the above-mentioned technical effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the prior art and the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 A schematic flow chart of a temperature measurement method for a reflow soldering device provided in an embodiment of the present application;

[0036] Figure 2 A schematic diagram of the principle of a thermocouple provided in an embodiment of the present application;

[0037] Figure 3A schematic diagram of the principle of performing nonlinear correction using a neural network model provided in an embodiment of the present application;

[0038] Figure 4 A schematic diagram of a temperature measurement circuit provided in an embodiment of the present application;

[0039] Figure 5 A schematic diagram of a neural network compensation model modeling process provided in an embodiment of the present application;

[0040] Figure 6 A schematic diagram of a temperature measuring device for a reflow soldering device provided in an embodiment of the present application;

[0041] Figure 7 A schematic diagram of a temperature measuring device for a reflow soldering device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] The core of this application is to provide a temperature measurement method, device, equipment and medium for reflow soldering equipment, which can improve the accuracy and reliability of temperature measurement results and meet the measurement requirements of wide range and high precision.

[0043] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0044] Please refer to Figure 1 , Figure 1 A flow chart of a temperature measurement method for a reflow soldering device provided in an embodiment of the present application, referring to Figure 1 As shown, the method includes:

[0045] S101: Acquire a thermoelectromotive force signal obtained by measuring the temperature of a thermocouple;

[0046] S102: Acquire the cold end temperature signal collected by the cold end compensation module;

[0047] S103: Using the thermoelectromotive force signal and the cold end temperature signal as inputs of a preset neural network compensation model, performing nonlinear correction on the thermoelectromotive force signal through the preset neural network compensation model to obtain a temperature measurement result.

[0048] The execution subject of the temperature measurement method provided in this embodiment is a host computer. The host computer can obtain the thermoelectric electromotive force signal obtained by the thermocouple temperature measurement and the cold end temperature signal collected by the cold end compensation module from the temperature measurement circuit. The temperature measurement circuit uses a thermocouple as a temperature sensor, including a thermocouple, a cold end compensation module, a main control chip, etc. Among them, the main control chip can be an STM32F407 single-chip microcomputer. The thermocouple measures the temperature of the reflow soldering equipment to obtain a thermoelectric electromotive force signal. The main control chip can upload the thermoelectric electromotive force signal obtained by the thermocouple and the cold end temperature signal collected by the cold end compensation module to the host computer. The host computer uses the thermoelectric electromotive force signal and the cold end temperature signal as the input of the preset neural network compensation model, and uses the preset neural network compensation model to perform nonlinear correction on the thermoelectric electromotive force signal to obtain the actual measured temperature.

[0049] refer to Figure 2 As shown in the figure, the thermocouple is made of two wires A and B made of different metal materials. The node connected at the left end is called the measuring end or the working end. The two nodes formed by connecting the unconnected wire ends to the measuring device through two identical wires C are called cold ends. Assume that the temperature of the thermocouple measuring end is T, and the contact potential of the A and B wires is , the cold end temperature is T 0 , the contact potential of wires A and C is , the contact potential of wires B and C is Then the thermoelectric electromotive force E at the end of the C wire is:

[0050] .

[0051] The A and B wires are at a temperature of The contact potential at The temperature of the thermocouple at the cold end is , the temperature at the measuring end is The output potential at .

[0052] According to the principle of thermoelectric effect, the thermoelectric electromotive force output by the thermocouple is related to the thermocouple measuring end temperature T and the cold end temperature T 0 The following relationship exists:

[0053] .

[0054] In the above formula: is the Boltzmann constant, is the unit charge, , yes , Free electron density in the electrode. It can be seen that there is a complex nonlinear relationship between the thermoelectric potential output by the thermocouple and the measured temperature. In order to obtain an accurate measurement end temperature, this embodiment uses a preset neural network compensation model to correct the nonlinear error of the thermocouple.

[0055] refer to Figure 3 As shown in the figure, the output of the thermocouple is affected by the temperature of the measuring end and the temperature of the cold end. Therefore, the thermoelectric electromotive force output by the thermocouple can be simplified as:

[0056] .

[0057] The nonlinear target that the preset neural network compensation model needs to approximate is:

[0058] .

[0059] Therefore, the thermoelectromotive force output by the thermocouple and the cold end temperature are selected as input, and the measuring end temperature is selected as output, and a double-input single-output neural network compensation model is constructed to complete the nonlinear correction of the thermocouple.

[0060] In some embodiments, obtaining a thermoelectromotive force signal obtained by thermocouple temperature measurement includes:

[0061] A digital signal corresponding to a thermoelectromotive force signal obtained by thermocouple temperature measurement uploaded by a temperature measurement circuit is received; wherein the thermoelectromotive force signal obtained by the thermocouple temperature measurement is successively subjected to radio frequency interference filtering, amplification, and analog-to-digital conversion to obtain a digital signal corresponding to the thermoelectromotive force signal.

[0062] In some embodiments, the temperature measurement circuit includes multiple thermocouple channels, and supports simultaneous acquisition of thermoelectromotive force signals obtained by measuring the temperature of multiple thermocouples.

[0063] refer to Figure 4 As shown, the temperature measurement circuit in this embodiment mainly includes a thermocouple, a cold end compensation module, a communication module, and a main control chip data storage module. The temperature measurement circuit can simultaneously collect the thermoelectric electromotive force signals obtained by multiple thermocouples. The thermoelectric electromotive force signals are filtered by RFI (Radio Frequency Interference). Figure 4 The pre-filter shown in the figure removes common-mode and differential-mode noises, and then performs further amplification and AD (Analog Digital) conversion. After the main control chip performs preliminary processing on the obtained digital signal, it frames the data of the thermocouple measurement end and the cold end detection data, and then transmits the data to the host computer via serial communication, and then performs correction processing in the host computer.

[0064] Among them, the AD7124 ADC module can be used to realize the AD conversion of multiple signals after pre-filtering. The ADT7320 cold end compensation module can be used to collect the cold end temperature. The AD converted signal and the cold end temperature signal collected by the cold end compensation module are transmitted back to the main control chip through the SPI (Serial Peripheral Interface) protocol.

[0065] In some embodiments, the thermoelectromotive force signal and the cold end temperature signal are used as inputs of a preset neural network compensation model, and the thermoelectromotive force signal is subjected to nonlinear correction by the preset neural network compensation model to obtain a temperature measurement result, which includes:

[0066] The thermoelectromotive force signal and the cold end temperature signal are used as inputs of a kernel function extreme learning machine network model, and the kernel function extreme learning machine network model is used to perform nonlinear correction on the thermoelectromotive force signal to obtain a temperature measurement result.

[0067] This embodiment uses a KELM (Kernelized Extreme Learning Machine) neural network model for correction.

[0068] For input and output data, assume that Different samples ; Input samples to the network, is the network output sample. Among them, = , = , is a real number set. Set the number of nodes in the hidden layer of the KELM neural network to , the hidden layer activation function is , the output of the KELM neural network can be expressed as:

[0069] .

[0070] In the above formula, is the randomly generated hidden layer The connection weight between the node and the input node, The hidden layer The bias of a neuron, is the required hidden layer The connection weights of neurons and output nodes. The above formula can be expressed as matrix multiplication:

[0071] .

[0072] In the formula, is the hidden layer output matrix, is the expected output vector. In order to enhance the stability of the neural network, the regularization coefficient is introduced and the identity matrix , the output weights of the KELM neural network are determined by the least squares method:

[0073] .

[0074] The output function of the KELM neural network can be expressed as:

[0075] .

[0076] The calculation formula for defining the kernel function is as follows:

[0077] .

[0078] in, , is the experimental input vector, and K represents the kernel function.

[0079] The output expression of the KELM neural network is:

[0080] .

[0081] It is clear that in addition to the KELM neural network model, other neural network models may also be used, such as a radial basis function neural network.

[0082] In some embodiments, it also includes:

[0083] Create and optimize the target parameters of the kernel function extreme learning machine network model to obtain the optimal kernel function extreme learning machine network model, so as to perform nonlinear correction on the thermoelectromotive force signal through the optimal kernel function extreme learning network model.

[0084] Among them, in some embodiments, optimizing the target parameters of the kernel function extreme learning machine network model includes:

[0085] The whale optimization algorithm is used to optimize the target parameters of the kernel function extreme learning machine network model.

[0086] WOA (Whale Optimization Algorithm) is a swarm intelligence optimization algorithm inspired by the unique foraging behavior of whales. The search and optimization process of the Whale Optimization Algorithm can be divided into the following three stages, among which the switching between the first two stages is determined by a random parameter A in the interval [-2, 2].

[0087] Wandering foraging: When |A|>1, whale individuals will search for prey by selecting random individual coordinates. To perform a roaming search:

[0088] .

[0089] In the above formula, For the The updated coordinates of the individual position, is the individual distance from a random individual Length, is a random number in the interval [0, 2].

[0090] Surrounding contraction: When |A|≤1, the whale begins to surround the prey and narrow the hunting range. Find the position vector of the global optimal solution for the whale group, and the whale position update becomes:

[0091] .

[0092] Spiral predation: As whales shrink and surround their prey, they swim along a spiral path to form a bubble net attack. The mathematical model of spiral predation is:

[0093] .

[0094] In the above formula, For individuals To the optimal solution individual The distance between is a constant coefficient, is a random vector.

[0095] Using the whale optimization algorithm to optimize the kernel function extreme learning machine network can improve the fitting accuracy and training speed of the model.

[0096] In some embodiments, using the whale optimization algorithm to optimize the target parameters of the kernel function extreme learning machine network model includes:

[0097] Determine the population size, the number of iterations and the search range of the target parameter, and initialize the target parameter;

[0098] Training the kernel function extreme learning machine network model, calculating the fitness values ​​of the individuals in the population, and updating the optimal value of the population;

[0099] Update the position of individual whales and generate new target parameters;

[0100] When the fitness meets the conditions or reaches the maximum number of iterations, the optimization process is terminated;

[0101] Save the searched global optimal target parameters and establish the optimal kernel function extreme learning machine network model.

[0102] parameter and It is an important factor affecting KELM regression prediction. This embodiment uses the whale optimization algorithm to optimize the KELM parameters to find the parameters that make the KELM model perform best. The construction process of the neural network compensation model can be referred to Figure 5 The main steps include:

[0103] (1) Divide the samples into training sample set, validation sample set and test sample set. The training set and validation set samples are used to train parameters, and the test samples are used to test the generalization ability of the model.

[0104] (2) Perform normalization preprocessing on all samples. Determine the population size, number of iterations, and parameters and The search range is initialized to optimize the parameter combination .

[0105] (3) Based on the combination of parameters to be optimized Train KELM, calculate the fitness value of the individuals in the population, and update the optimal value of the population.

[0106] (4) Update the position of individual whales and generate new parameter combinations.

[0107] (5) When the fitness meets the conditions or reaches the maximum number of iterations, the optimization process is terminated, otherwise return to step (3).

[0108] (6) Save the searched global optimal parameters , establish the prediction regression model of KELM.

[0109] Constructing a neural network compensation model is essentially constructing a neural network compensation model function The data-driven neural network modeling method requires a series of thermocouple input and output sample data sets, where the output is the desired working end temperature. , the input is the original characteristic of the thermocouple and the output is the intermediate quantity and the thermocouple cold junction temperature The model is trained using the training set and validation set. The essence of the training is to find the optimal parameters of KELM so that the model fits the training set data.

[0110] In summary, the temperature measurement method for reflow soldering equipment provided in the present application uses a thermocouple for temperature acquisition, and uses a neural network model to perform nonlinear correction on the thermoelectromotive force signal obtained by the thermocouple temperature measurement. The neural network model can effectively correct the nonlinear error existing in the thermocouple temperature measurement, improve the accuracy and reliability of the temperature measurement results, and meet the wide range and high-precision measurement requirements.

[0111] The present application also provides a temperature measuring device for reflow soldering equipment. The device described below can be referred to in correspondence with the method described above. Figure 6 , Figure 6 A schematic diagram of a temperature measuring device for a reflow soldering device provided in an embodiment of the present application, combined with Figure 6 As shown, the device comprises:

[0112] A first acquisition unit 10 is used to acquire a thermoelectromotive force signal obtained by measuring the temperature of a thermocouple;

[0113] The second acquisition unit 20 is used to acquire the cold end temperature signal collected by the cold end compensation module;

[0114] The correction unit 30 is used to use the thermoelectromotive force signal and the cold end temperature signal as inputs of a preset neural network compensation model, perform nonlinear correction on the thermoelectromotive force signal through the preset neural network compensation model, and obtain a temperature measurement result.

[0115] Based on the above embodiment, as a specific implementation, the correction unit 30 is specifically used for:

[0116] The thermoelectromotive force signal and the cold end temperature signal are used as inputs of a kernel function extreme learning machine network model, and the kernel function extreme learning machine network model is used to perform nonlinear correction on the thermoelectromotive force signal to obtain a temperature measurement result.

[0117] Based on the above embodiment, as a specific implementation method, it also includes:

[0118] A creation and optimization unit is used to create and optimize the target parameters of the kernel function extreme learning machine network model to obtain the optimal kernel function extreme learning machine network model, so as to perform nonlinear correction on the thermoelectromotive force signal through the optimal kernel function extreme learning network model.

[0119] Based on the above embodiment, as a specific implementation mode, the creation and optimization unit is specifically used for:

[0120] The whale optimization algorithm is used to optimize the target parameters of the kernel function extreme learning machine network model.

[0121] Based on the above embodiment, as a specific implementation mode, the creation and optimization unit is specifically used for:

[0122] Determine the population size, the number of iterations and the search range of the target parameter, and initialize the target parameter;

[0123] Training the kernel function extreme learning machine network model, calculating the fitness values ​​of the individuals in the population, and updating the optimal value of the population;

[0124] Update the position of individual whales and generate new target parameters;

[0125] When the fitness meets the conditions or reaches the maximum number of iterations, the optimization process is terminated;

[0126] Save the searched global optimal target parameters and establish the optimal kernel function extreme learning machine network model.

[0127] Based on the above embodiment, as a specific implementation mode, the first acquisition unit is specifically used for:

[0128] A digital signal corresponding to a thermoelectromotive force signal obtained by thermocouple temperature measurement uploaded by a temperature measurement circuit is received; wherein the thermoelectromotive force signal obtained by the thermocouple temperature measurement is successively subjected to radio frequency interference filtering, amplification, and analog-to-digital conversion to obtain a digital signal corresponding to the thermoelectromotive force signal.

[0129] Based on the above embodiment, as a specific implementation method, the temperature measurement circuit includes multiple thermocouple channels, and supports the simultaneous acquisition of thermoelectromotive force signals obtained by measuring the temperature of multiple thermocouples.

[0130] The temperature measuring device of the reflow soldering equipment provided in the present application adopts a thermocouple for temperature acquisition, and adopts a neural network model to perform nonlinear correction on the thermoelectromotive force signal obtained by the thermocouple temperature measurement. The neural network model can effectively correct the nonlinear error existing in the thermocouple temperature measurement, improve the accuracy and reliability of the temperature measurement results, and meet the wide range and high-precision measurement requirements.

[0131] The present application also provides a temperature measuring device for a reflow soldering device, referring to Figure 7 As shown, the device includes a memory 1 and a processor 2 .

[0132] Memory 1, used for storing computer programs;

[0133] Processor 2 is used to execute the computer program to implement the following steps:

[0134] Acquire a thermoelectromotive force signal obtained by thermocouple temperature measurement; acquire a cold end temperature signal collected by a cold end compensation module; use the thermoelectromotive force signal and the cold end temperature signal as inputs of a preset neural network compensation model, perform nonlinear correction on the thermoelectromotive force signal through the preset neural network compensation model, and obtain a temperature measurement result.

[0135] For an introduction to the equipment provided in this application, please refer to the above method embodiments, and this application will not go into details here.

[0136] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps can be implemented:

[0137] Acquire a thermoelectromotive force signal obtained by thermocouple temperature measurement; acquire a cold end temperature signal collected by a cold end compensation module; use the thermoelectromotive force signal and the cold end temperature signal as inputs of a preset neural network compensation model, perform nonlinear correction on the thermoelectromotive force signal through the preset neural network compensation model, and obtain a temperature measurement result.

[0138] The computer-readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0139] For an introduction to the computer-readable storage medium provided in this application, please refer to the above method embodiment, and this application will not go into details here.

[0140] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other. For the devices, equipment, and computer-readable storage media disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0141] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0142] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0143] The temperature measurement method, device, equipment and medium of the reflow soldering equipment provided by the present application are introduced in detail above. Specific examples are used in this article to illustrate the principle and implementation method of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the principle of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the claims of the present application.

Claims

1. A temperature measurement method for a reflow soldering device, characterized in that: include: Obtaining the thermoelectromotive force signal obtained by thermocouple temperature measurement; Obtain the cold end temperature signal collected by the cold end compensation module; The thermoelectromotive force signal and the cold end temperature signal are used as inputs of a preset neural network compensation model, and nonlinear correction is performed on the thermoelectromotive force signal through the preset neural network compensation model to obtain a temperature measurement result.

2. The temperature measurement method according to claim 1, characterized in that: The thermoelectromotive force signal and the cold end temperature signal are used as inputs of a preset neural network compensation model, and the thermoelectromotive force signal is subjected to nonlinear correction by the preset neural network compensation model to obtain a temperature measurement result including: The thermoelectromotive force signal and the cold end temperature signal are used as inputs of a kernel function extreme learning machine network model, and the kernel function extreme learning machine network model is used to perform nonlinear correction on the thermoelectromotive force signal to obtain a temperature measurement result.

3. The temperature measurement method according to claim 2, characterized in that: Also includes: Create and optimize the target parameters of the kernel function extreme learning machine network model to obtain the optimal kernel function extreme learning machine network model, so as to perform nonlinear correction on the thermoelectromotive force signal through the optimal kernel function extreme learning network model.

4. The temperature measurement method according to claim 3, characterized in that: The target parameters for optimizing the kernel function extreme learning machine network model include: The whale optimization algorithm is used to optimize the target parameters of the kernel function extreme learning machine network model.

5. The temperature measurement method according to claim 4, characterized in that: The target parameters of the kernel function extreme learning machine network model optimized by the whale optimization algorithm include: Determine the population size, the number of iterations and the search range of the target parameter, and initialize the target parameter; Training the kernel function extreme learning machine network model, calculating the fitness values ​​of the individuals in the population, and updating the optimal value of the population; Update the position of individual whales and generate new target parameters; When the fitness meets the conditions or reaches the maximum number of iterations, the optimization process is terminated; Save the searched global optimal target parameters and establish the optimal kernel function extreme learning machine network model.

6. The temperature measurement method according to claim 1, characterized in that: The thermoelectric electromotive force signal obtained by thermocouple temperature measurement includes: A digital signal corresponding to a thermoelectromotive force signal obtained by thermocouple temperature measurement uploaded by a temperature measurement circuit is received; wherein the thermoelectromotive force signal obtained by the thermocouple temperature measurement is successively subjected to radio frequency interference filtering, amplification, and analog-to-digital conversion to obtain a digital signal corresponding to the thermoelectromotive force signal.

7. The temperature measurement method according to claim 6, characterized in that: The temperature measurement circuit includes multiple thermocouple channels, and supports the simultaneous acquisition of thermoelectromotive force signals obtained by measuring the temperature of multiple thermocouples.

8. A temperature measuring device for reflow soldering equipment, characterized in that: include: A first acquisition unit is used to acquire a thermoelectromotive force signal obtained by measuring the temperature of the thermocouple; A second acquisition unit, used to acquire the cold end temperature signal collected by the cold end compensation module; The correction unit is used to use the thermoelectromotive force signal and the cold end temperature signal as inputs of a preset neural network compensation model, perform nonlinear correction on the thermoelectromotive force signal through the preset neural network compensation model, and obtain a temperature measurement result.

9. A temperature measuring device for a reflow soldering device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the temperature measurement method for the reflow soldering equipment as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the temperature measurement method for the reflow soldering equipment according to any one of claims 1 to 7 are implemented.

Images