Reflow oven temperature determination method, electronic equipment and storage medium

Abstract

The invention provides a reflow oven temperature determination method, electronic equipment and a storage medium. The method comprises the steps that the initial set temperature of at least one furnace area in the reflow furnace is obtained; predicting the initial set temperature by using a preset machine learning model to obtain target feature data corresponding to the at least one furnace area, and judging whether the initial set temperature meets production requirements or not according to preset conditions and the target feature data; if the initial set temperature meets the production requirement, actual furnace area data of the initial set temperature in the reflow furnace are obtained; and according to the preset condition, the initial set temperature and the actual furnace area data, the target set temperature of the at least one furnace area is determined. By using the method, the temperature control efficiency and the production efficiency of the printed circuit board can be improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent manufacturing, and in particular to a method for determining the temperature of a reflow furnace, an electronic device, and a storage medium. Background Art

[0002] With the rapid development of information products, the production of printed circuit boards (PCBs) is becoming more and more sophisticated and complex. Soldering in a reflow oven is a key step in the PCB production process. The different temperatures of each zone in the reflow oven (such as the preheating zone and the cooling zone, etc.) will affect the production quality of the PCB. Therefore, it is very important to set the temperature of each zone in the reflow oven.

[0003] In the related art, the temperature setting of each furnace zone in the reflow furnace mainly depends on the experience of engineers. It is necessary to collect data and perform calculations through equipment such as thermometers to obtain multiple reference data (for example, peak temperature, etc.), and to determine whether the set furnace zone temperature meets the production conditions based on these reference data. If the set furnace zone temperature does not meet the production conditions, it is necessary to wait for each furnace zone to cool down before resetting the furnace zone temperature, which is not only time-consuming but also affects the production efficiency of PCBs. Summary of the invention

[0004] In view of the above, it is necessary to provide a method for determining the temperature of a reflow furnace, an electronic device and a storage medium, which can solve the technical problem of affecting the production efficiency of printed circuit boards due to low temperature control efficiency.

[0005] On the one hand, the present application provides a method for determining the temperature of a reflow furnace, the method comprising: obtaining an initial set temperature for at least one furnace zone in the reflow furnace, predicting the initial set temperature using a preset machine learning model, obtaining target feature data corresponding to the at least one furnace zone, and judging whether the initial set temperature meets production requirements based on preset conditions and the target feature data; if the initial set temperature meets production requirements, obtaining actual furnace zone data of the initial set temperature in the reflow furnace, and determining the target set temperature of the at least one furnace zone based on the preset conditions, the initial set temperature and the actual furnace zone data.

[0006] In some embodiments of the present application, if there are multiple at least one furnace zones, the use of a preset machine learning model to predict the initial set temperature to obtain the target feature data corresponding to the at least one furnace zone includes: using the machine learning model to predict the initial set temperature of each furnace zone to obtain the target feature data corresponding to each furnace zone.

[0007] In some embodiments of the present application, if the target characteristic data corresponding to the multiple furnace zones include a slope, a peak temperature and a duration of each furnace zone, determining whether the initial set temperature meets the production requirements based on the preset conditions and the target characteristic data includes: if the slope, the peak temperature and multiple durations all meet the preset conditions, determining that the multiple initial set temperatures of the multiple furnace zones meet the production requirements.

[0008] In some embodiments of the present application, before using a preset machine learning model to predict the initial set temperature, the method also includes: obtaining historical set temperatures for at least one furnace zone and historical feature data corresponding to the historical set temperatures, using a machine learning algorithm to predict the historical set temperatures to obtain predicted feature data, calculating a loss value of the machine learning algorithm based on the historical feature data and the predicted feature data, and adjusting the machine learning algorithm based on the loss value until the loss value drops to a preset range, stopping the adjustment, and using the adjusted machine learning algorithm as the machine learning model.

[0009] In some embodiments of the present application, if both the historical feature data and the predicted feature data are multiple, calculating the loss value of the machine learning algorithm based on the historical feature data and the predicted feature data includes: determining the error between multiple historical feature data and the corresponding predicted feature data as the loss value.

[0010] In some embodiments of the present application, obtaining the actual furnace zone data of the initial set temperature in the reflow furnace includes: receiving data sent from multiple acquisition tools arranged at different positions in the at least one furnace zone, and combining the received multiple data to obtain the actual furnace zone data.

[0011] In some embodiments of the present application, if the target set temperature is used to produce printed circuit boards, the method further includes: obtaining historical yield data of multiple printed circuit boards that have been produced and historical board entry time intervals of the multiple printed circuit boards between multiple furnace zones of the reflow furnace, calling a preset model to predict the historical yield data and the historical board entry time intervals, and obtaining the target board entry time intervals of the multiple printed circuit boards between the multiple furnace zones.

[0012] In some embodiments of the present application, the method further includes: controlling the production of printed circuit boards by means of the target set temperature and the target board entry time interval.

[0013] On the other hand, the present application provides an electronic device, which includes: a memory storing at least one instruction; and a processor executing at least one instruction to implement the reflow furnace temperature determination method.

[0014] On the other hand, the present application provides a computer-readable storage medium, wherein at least one instruction is stored in the computer-readable storage medium, and the at least one instruction is executed by a processor in an electronic device to implement the reflow furnace temperature determination method.

[0015] Through the above implementation, since the machine learning model is trained by the historical set temperature and historical feature data of the printed circuit board, the machine learning model can learn the correlation between temperature and feature data. When the machine learning model is used to predict the initial set temperature, the reliability of the predicted target feature data can be ensured. According to the preset conditions and the target feature data, it is judged whether the initial set temperature meets the production requirements. Only when the initial set temperature meets the production requirements, the actual furnace zone data corresponding to the initial set temperature will be obtained, so the probability that the initial set temperature meets the production requirements can be increased. Since the actual furnace zone data corresponding to the initial set temperature will not be obtained when the initial set temperature does not meet the production requirements, the situation of waiting for each furnace zone to cool down and then resetting the furnace zone temperature is reduced, thereby reducing the temperature setting time and improving the efficiency of temperature control. By determining the target set temperature of each furnace zone through the preset conditions, the initial set temperature and the actual furnace zone data, the probability that the target set temperature meets the production requirements can be further increased. When using accurate target set temperatures to produce printed circuit boards, the production efficiency of printed circuit boards can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a structural diagram of an electronic device provided in one embodiment of the present application.

[0017] Figure 2 It is a flow chart of a method for determining the temperature of a reflow furnace provided in one embodiment of the present application.

[0018] Figure 3 Schematic diagram of a time-temperature curve provided in an embodiment of the present application.

[0019] Figure 4 It is a flowchart of a training method for a machine learning model provided in one embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application is described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] It should be noted that in this application, "at least one" means one or more, and "more than one" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0022] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0023] With the rapid development of information products, the design of printed circuit boards (PCBs) has become more sophisticated and complex. In the surface mount technology production line, the manufacture of a printed circuit board requires the step of soldering in a reflow furnace. When the printed circuit board is soldered in the reflow furnace, it will pass through multiple furnace zones with different temperatures (such as preheating zone, hot soaking zone, reflow zone and cooling zone, etc.). Different reflow furnaces have different numbers of furnace zones. The temperature of each furnace zone affects the quality of the produced printed circuit boards. If the temperature is too high, it is easy to cause damage to parts, solder balls or oxidation of solder paste. On the contrary, if the furnace temperature is too low, it may lead to insufficient activation of the flux, so the setting of the furnace zone temperature is crucial to the quality of the printed circuit board.

[0024] In the related art, the temperature setting of each furnace zone in the reflow furnace mainly depends on the experience of engineers. It is necessary to collect data and perform calculations through equipment such as thermometers to obtain multiple reference data (for example, peak temperature, etc.), and to determine whether the set furnace zone temperature meets the production conditions based on these reference data. If the set furnace zone temperature does not meet the production conditions, it is necessary to wait for each furnace zone to cool down before resetting the furnace zone temperature, which is not only time-consuming but also affects the production efficiency of PCBs.

[0025] In order to solve the above technical problems, the present application provides a method for determining the temperature of a reflow oven, an electronic device and a storage medium, which can improve the temperature control efficiency and the production efficiency of printed circuit boards. The method for determining the temperature of a reflow oven provided in the embodiment of the present application can be applied to one or more electronic devices.

[0026] like Figure 1FIG. 1 is a block diagram of an electronic device provided by an embodiment of the present application. The electronic device 10 may be a mobile phone, a computer, a tablet computer, an industrial computer, or other electronic devices.

[0027] In other embodiments of the present application, the electronic device 10 may also be a reflow furnace, and the embodiments of the present application do not impose any limitation on the specific type of the electronic device.

[0028] like Figure 1 As shown, the electronic device 10 may include a communication module 101, a memory 102, a processor 103, an input / output (I / O) interface 104 and a bus 105. The processor 103 is coupled to the communication module 101, the memory 102 and the input / output interface 104 through the bus 105.

[0029] The communication module 101 may include a wired communication module and / or a wireless communication module. The wired communication module may provide one or more wired communication solutions such as universal serial bus (USB), controller area network bus (CAN, Controller Area Network). The wireless communication module may provide one or more wireless communication solutions such as wireless fidelity (Wi-Fi), Bluetooth (BT), mobile communication network, frequency modulation (FM), near field communication technology (NFC), infrared technology (IR), etc.

[0030] The memory 102 may include one or more random access memories (RAM) and one or more non-volatile memories (NVM). The random access memory can be directly read and written by the processor 103, and can be used to store executable programs (such as machine instructions) of other running programs, and can also be used to store user and application data. The random access memory may include static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), etc.

[0031] The non-volatile memory may also store executable programs and user and application data, etc., and may be loaded into the random access memory in advance for direct reading and writing by the processor 110. The non-volatile memory may include a disk storage device and a flash memory.

[0032] The memory 102 is used to store one or more computer programs. The one or more computer programs are configured to be executed by the processor 103. The one or more computer programs include multiple instructions. When the multiple instructions are executed by the processor 103, the reflow furnace temperature determination method executed on the electronic device 10 can be implemented.

[0033] In other embodiments, Figure 1 The electronic device 10 shown also includes an external memory interface for connecting to an external memory to expand the storage capacity of the electronic device 10 .

[0034] The processor 103 may include one or more processing units, for example, the processor 103 may include an application processor (application processor, AP), a modem processor, a graphics processor (graphics processing unit, GPU), an image signal processor (image signal processor, ISP), a controller, a video codec, a digital signal processor (digital signal processor, DSP), and / or a neural network processor (neural-network processing unit, NPU), etc. Among them, different processing units may be independent devices or integrated in one or more processors.

[0035] The processor 103 provides computing and control capabilities. For example, the processor 103 is used to execute a computer program stored in the memory 102 to implement the above-mentioned method for determining the temperature of the reflow furnace.

[0036] The input / output interface 104 is used to provide a channel for user input or output. For example, the input / output interface 104 can be used to connect various input and output devices, such as a mouse, keyboard, touch device, display screen, etc., so that the user can enter information or visualize information.

[0037] The bus 105 is at least used to provide a channel for mutual communication among the communication module 101 , the memory 102 , the processor 103 , and the input / output interface 104 in the electronic device 10 .

[0038] It is to be understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device 10. In other embodiments of the present application, the electronic device 10 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0039] like Figure 2 FIG. 1 is a flow chart of a method for determining the temperature of a reflow furnace provided in an embodiment of the present application. According to different requirements, the order of each step in the flow chart can be adjusted according to actual requirements, and some steps can be omitted. The execution subject of the method is an electronic device, such as Figure 1 An electronic device 10 is shown.

[0040] S11, obtaining an initial set temperature of at least one furnace zone in a reflow furnace.

[0041] In some embodiments of the present application, all furnace zones of the reflow furnace may be multiple, and the number of furnace zones in different reflow furnaces is different. For example, if the reflow furnace includes four furnace zones, namely a preheating zone, a hot soaking zone, a reflow zone, and a cooling zone, at least one furnace zone may be one or more of the preheating zone, the hot soaking zone, the reflow zone, and the cooling zone.

[0042] In some embodiments of the present application, the initial set temperature may be the desired temperature of at least one furnace zone. After a furnace zone in the reflow furnace is configured according to an initial set temperature, the original temperature of the furnace zone will change until the initial set temperature is reached. The reflow furnace configured with the initial set temperature may be used to produce printed circuit boards and other product devices such as semiconductors, and the present application does not limit this. The electronic device may use the temperature input by the user (such as an engineer) on the electronic device as the initial set temperature.

[0043] In other embodiments of the present application, the electronic device can be connected to the reflow furnace. For example, the electronic device can be connected to the reflow furnace via a bus, a wireless network Wi-Fi, and Bluetooth, so that the electronic device can obtain the temperature configured by the user for at least one furnace zone on the reflow furnace (such as on the control panel of the reflow furnace) from the database or operation log of the reflow furnace as the initial set temperature.

[0044] In some embodiments of the present application, the initial set temperature of each furnace zone may be different. For example, if the reflow furnace includes four furnace zones, namely a preheating zone, a hot soaking zone, a reflow zone, and a cooling zone, the initial set temperature of the preheating zone may be any value between 130°C and 160°C, the initial set temperature of the hot soaking zone may be any value between 200°C and 220°C, the initial set temperature of the reflow zone may be any value between 230°C and 250°C, and the initial set temperature of the cooling zone may be any value between 30°C and 40°C.

[0045] In this embodiment, the initial set temperature is only the temperature configured for each furnace zone in the reflow furnace, and is not equivalent to the actual temperature of each furnace zone in the reflow furnace. The actual temperature of each furnace zone in the reflow furnace, the speed of change between the temperatures, and the change time all affect the production quality of printed circuit boards, semiconductors and other devices. In order to ensure the production quality of printed circuit boards, semiconductors and other devices, it is usually necessary to adjust the temperature of the furnace zone in the reflow furnace multiple times so that the actual temperature of each furnace zone in the reflow furnace meets the production requirements of printed circuit boards, semiconductors and other product devices. The selection of at least one furnace zone can be determined according to the production process of printed circuit boards, semiconductors and other product devices.

[0046] S12, using a preset machine learning model to predict the initial set temperature to obtain target feature data corresponding to at least one furnace zone.

[0047] In some embodiments of the present application, if there are multiple furnace zones, the target characteristic data of the multiple furnace zones include, but are not limited to: slope, peak temperature, and duration of each furnace zone. For example, if at least one furnace zone includes a preheating zone, a hot soaking zone, a reflow zone, and a cooling zone, the target characteristic data of at least one furnace zone may include data such as preheating duration, preheating slope, hot soaking duration, reflow duration, peak temperature, cooling duration, and cooling slope. The target characteristic data of each furnace zone may be different. For example, the target characteristic data of the preheating zone may be the preheating slope and the preheating duration, and the target characteristic data of the hot soaking zone may be the hot soaking duration.

[0048] In some embodiments of the present application, the machine learning model may be a model obtained by training a machine learning algorithm to convergence using the historical set temperature of at least one furnace zone and the historical feature data corresponding to the historical set temperature. Among them, the machine learning algorithm includes, but is not limited to: regression algorithm, decision tree, random forest, support vector machine and other algorithms. The data type of the historical feature data is basically the same as the data type of the target feature data, so this application will not repeat the description here. The generation process of the machine learning model can refer to steps S21-S25 below.

[0049] In some embodiments of the present application, the machine learning algorithm can also be replaced by a deep learning algorithm, such as a convolutional neural network.

[0050] In some embodiments of the present application, since the machine learning model is a model obtained by training the machine learning algorithm to convergence using the historical set temperature of at least one furnace zone and the historical feature data corresponding to the historical set temperature, the machine learning model learns the correlation between the historical set temperature and the corresponding historical feature data, so the electronic device uses the machine learning model to predict each initial set temperature of each furnace zone, and can directly obtain the target feature data corresponding to the initial set temperature of each furnace zone. In this embodiment, the target feature data can reflect the characteristics of the change speed, peak temperature, and change time between the temperatures of each furnace zone.

[0051] S13, judging whether the initial set temperature meets the production requirements according to the preset conditions and the target characteristic data.

[0052] In some embodiments of the present application, the preset condition may include a production index corresponding to each target characteristic data, each production index is used to preliminarily determine whether the initial set temperature corresponding to the corresponding target characteristic data meets the production requirements, and each production index may be a range or a value, which is not limited by the present application. When each target characteristic data is equal to the production index or is within the production index, it is preliminarily determined that the initial set temperature corresponding to the target characteristic data meets the production requirements, or, when each target characteristic data is not equal to the production index or is outside the production index, it is determined that the initial set temperature corresponding to the target characteristic data does not meet the production requirements.

[0053] In some embodiments of the present application, if there are multiple at least one furnace zones and multiple target characteristic data corresponding to the multiple furnace zones, when each target characteristic data meets the corresponding production index, the electronic device determines that the multiple initial set temperatures corresponding to the multiple target characteristic data meet the production requirements, or, when there is at least one target characteristic data that does not meet the corresponding production index, the electronic device determines that the multiple initial set temperatures corresponding to the multiple target characteristic data do not meet the production requirements.

[0054] For example, if the target characteristic data includes a peak temperature of 245°C, a preheating duration of 30s, a preheating slope of 1.2, a soaking duration of 40s, a reflow duration of 25s, a cooling duration of 35s, and a cooling slope of -1.5. In the preset conditions, the production index corresponding to the peak temperature is 240°C to 275°C, the production index corresponding to the preheating duration is 30s to 60s, the production index corresponding to the preheating slope is 1 to 1.5, the production index corresponding to the soaking duration is 30s to 60s, the production index corresponding to the reflow duration is 30s to 60s, the production index corresponding to the cooling duration is 30s to 60s, and the production index corresponding to the cooling slope is -1.2 to -1.5. Each target characteristic data is compared with the corresponding production index in the preset conditions, and it is determined that the reflow duration of 25s is outside the production index of 30s to 60s, so the electronic device determines that the multiple initial set temperatures corresponding to the target characteristic data do not meet the production requirements.

[0055] In some embodiments of the present application, if there are multiple initial set temperatures, when each initial set temperature meets the production requirements, the electronic device executes step S14, or, when there is at least one initial set temperature that does not meet the production requirements, the electronic device executes step S16.

[0056] In this embodiment, since the target characteristic data can reflect the characteristics of the temperature change rate, peak temperature and conversion time of each furnace zone, by judging the target characteristic data, it can be preliminarily determined whether the initial set temperature corresponding to the target characteristic data meets the production requirements.

[0057] In other embodiments of the present application, if the production index is a range, there are multiple initial set temperatures in any furnace zone, and the multiple initial set temperatures in any furnace zone meet the production requirements, the electronic device can obtain the target characteristic data of each initial set temperature, determine the center value of the range of the production index, and select the initial set temperature corresponding to the target characteristic data with the smallest distance from the center value as the target set temperature. For example, if the production index corresponding to the preheating slope is 1 to 1.5, the first initial set temperature of the preheating zone is 130°C, and the corresponding preheating slope is 1.3, and the second initial set temperature of the preheating zone is 140°C, and the corresponding preheating slope is 1.4. Since the preheating slope of 1.3 and the preheating slope of 1.4 are both within the production index of 1.5, the first initial set temperature of 130°C and the second initial set temperature of 140°C both meet the production requirements. The central value of production indicators 1 to 1.5 is 1.25, the difference between the preheating slope 1.3 and the central value 1.25 is 0.05, the difference between the preheating slope 1.4 and the central value 1.25 is 0.15, and the difference between the preheating slope 1.3 and the central value 1.25 is smaller than the difference between the preheating slope 1.4 and the central value 1.25. Therefore, the first initial setting temperature of 130°C corresponding to the preheating slope 1.3 can be selected as the target setting temperature.

[0058] In this embodiment, by selecting the initial set temperature corresponding to the target characteristic data with the smallest distance to the center value as the target set temperature, the probability that the actual characteristic data of the actual furnace zone data below meets the preset conditions can be increased.

[0059] S14, obtaining actual furnace zone data of the initial set temperature in the reflow furnace.

[0060] In some embodiments of the present application, the actual furnace zone data is a plurality of data collected by a collection tool set in the reflow furnace after the reflow furnace is configured according to the initial set temperature. The actual furnace zone data may include each actual furnace zone temperature and the time corresponding to each actual furnace zone temperature. The collection tool includes, but is not limited to: a temperature sensor, a temperature measuring board, a temperature measuring line, and a temperature measuring instrument. If there are multiple collection tools, the multiple collection tools can be set at different positions in the reflow furnace.

[0061] In some embodiments of the present application, the electronic device obtains the actual furnace zone data of the initial set temperature in the reflow furnace, including: the electronic device receives data sent from multiple acquisition tools arranged at different positions in at least one furnace zone, and combines the received multiple data to obtain the actual furnace zone data. A time-temperature curve can be drawn according to each actual furnace zone temperature in the actual furnace zone data and the time corresponding to each actual furnace zone temperature.

[0062] For example, if the reflow furnace includes four furnace zones, namely the preheating zone, the hot soaking zone, the reflow zone and the cooling zone, Figure 3, which is a schematic diagram of a time-temperature curve provided by an embodiment of the present application. Figure 3 In the curve corresponding to the preheating zone, the actual furnace zone temperature is less than the actual furnace zone temperature of the hot soaking zone, the actual furnace zone temperature of the hot soaking zone is less than the actual furnace zone temperature of the reflow zone, and the cooling zone decreases on the basis of the actual furnace zone temperature of the reflow zone. In the curve corresponding to the preheating zone, the actual furnace zone temperature is linearly related to time, and the slope of the curve is greater than zero. In the curve corresponding to the hot soaking zone, the actual furnace zone temperature does not change with the change of time, and the slope of the curve is zero. In the curve corresponding to the reflow zone, the actual furnace zone temperature is linearly related to time, and the slope of the curve is first greater than zero, then equal to zero, and then less than zero, and the curve corresponding to the reflow zone has a peak temperature. In the curve corresponding to the cooling zone, the actual furnace zone temperature is linearly related to time, and the slope of the curve is less than zero. The common target feature data of the preheating zone, the hot soaking zone, the reflow zone and the cooling zone may include one or more of the peak temperature, the duration of each furnace zone and multiple slopes. The multiple durations include preheating duration, soaking duration, reflow duration and cooling duration, and the multiple slopes include a preheating slope of a curve corresponding to a preheating zone and a cooling zone slope of a curve corresponding to a cooling zone.

[0063] In this embodiment, since multiple acquisition tools can be set at different positions in the reflow furnace, data such as actual furnace zone temperatures at different positions in the reflow furnace can be fully acquired, thereby ensuring the comprehensiveness of the actual furnace zone data.

[0064] S15, determining a target set temperature of at least one furnace zone according to preset conditions, the initial set temperature and actual furnace zone data.

[0065] In some embodiments of the present application, the electronic device determines the target set temperature of at least one furnace zone based on preset conditions, the initial set temperature and the actual furnace zone data, including: the electronic device again determines whether the initial set temperature meets the production requirements based on the actual characteristic data corresponding to the preset conditions and the actual furnace zone data.

[0066] The data types of the actual characteristic data and the target characteristic data are basically the same. The electronic device determines whether the initial set temperature meets the production requirements based on the actual characteristic data corresponding to the preset conditions and the actual furnace zone data, and the process of the electronic device determining whether the initial set temperature meets the production requirements based on the preset conditions and the target characteristic data is basically the same, so this application will not repeat the description.

[0067] In this embodiment, if there are multiple initial set temperatures, when each initial set temperature meets the production requirements, the electronic device determines the initial set temperature of each furnace zone as the target set temperature corresponding to the furnace zone; or, when there is at least one initial set temperature that does not meet the production requirements, the electronic device returns to step S12 and continues to use the machine learning model to predict the initial set temperature until multiple initial set temperatures meet the production requirements again.

[0068] In this embodiment, since the actual furnace zone data is comprehensive, the initial set temperature is further judged through the actual furnace zone data to determine whether the initial set temperature is determined as the target set temperature. This can improve the accuracy and reliability of the target set temperature. When using the target set temperature to produce components such as printed circuit boards, the production quality of products such as printed circuit boards can be ensured.

[0069] S16, outputting a prompt message, the prompt message is used to indicate that the initial set temperature does not meet the production requirements.

[0070] In this embodiment, since the actual furnace zone data corresponding to the initial set temperature will not be obtained when the initial set temperature does not meet the production requirements, the situation of waiting for each furnace zone to cool down and then resetting the furnace zone temperature is reduced, thereby reducing the temperature setting time and improving the efficiency of temperature control.

[0071] Through the above implementation, since the machine learning model is trained by the historical set temperature and historical feature data of the printed circuit board, the machine learning model can learn the correlation between temperature and feature data. When the machine learning model is used to predict the initial set temperature, the reliability of the predicted target feature data can be ensured. According to the preset conditions and the target feature data, it is judged whether the initial set temperature meets the production requirements. Only when the initial set temperature meets the production requirements, the actual furnace zone data corresponding to the initial set temperature will be obtained, so the probability that the initial set temperature meets the production requirements can be increased. Since the actual furnace zone data corresponding to the initial set temperature will not be obtained when the initial set temperature does not meet the production requirements, the situation of waiting for each furnace zone to cool down and then resetting the furnace zone temperature is reduced, thereby reducing the temperature setting time and improving the efficiency of temperature control. By determining the target set temperature of each furnace zone through the preset conditions, the initial set temperature and the actual furnace zone data, the probability that the target set temperature meets the production requirements can be further increased. When using accurate target set temperatures to produce printed circuit boards, the production efficiency of printed circuit boards can be improved.

[0072] In other embodiments of the present application, if the target set temperature is used to produce printed circuit boards, the method also includes: the electronic device obtains historical yield data of multiple printed circuit boards that have been produced and historical board entry time intervals of multiple printed circuit boards between multiple furnace zones of a reflow furnace; further, the electronic device calls a preset model to predict the historical yield data and the historical board entry time intervals to obtain the target board entry time intervals of multiple printed circuit boards between multiple furnace zones.

[0073] The historical yield data is used to evaluate the quality of multiple printed circuit boards that have been produced, and the historical board entry time interval is the time difference between any two printed circuit boards entering the reflow furnace. The preset model includes, but is not limited to: a regression model and a support vector machine model. Alternatively, the preset model can also be the above-mentioned machine learning model.

[0074] The electronic device calls the preset model to predict the historical yield data and the historical board-feeding time interval, so that the preset model can learn the correlation between the quality of the printing plate and the board-feeding time interval, so that the target board-feeding time interval output by the preset model is the time interval corresponding to the better quality.

[0075] In some embodiments of the present application, after obtaining the target set temperature and the target board entry time interval, the electronic device controls the production of printed circuit boards through the target set temperature and the target board entry time interval.

[0076] In other embodiments of the present application, if the target set temperature is used to produce printed circuit boards, the user can configure the reflow furnace according to the target set temperature and the target board-feeding time interval, or the electronic device can configure the reflow furnace according to the target set temperature and the target board-feeding time interval, so that the reflow furnace can generate a board-request signal according to the target board-feeding time interval and control the opening of the furnace door, so that the conveyor belt or the board-feeding machine can deliver the printed circuit board to the reflow furnace according to the board-requesting signal and the opened furnace door. When the reflow furnace generates a board-requesting signal, the furnace door will open, and the printed circuit board can be delivered to the reflow furnace at this time. After a printed circuit board is delivered, the furnace door is closed.

[0077] In this embodiment, since the target board-feeding time interval is the time interval corresponding to better quality, the production of printed circuit boards can be controlled by the target setting temperature and the target board-feeding time interval, thereby ensuring the production quality of the printed circuit boards.

[0078] In some embodiments of the present application, before using a preset machine learning model to predict the initial set temperature, the machine learning model can be obtained by training a machine learning algorithm. Figure 4 FIG. 1 is a flowchart of a method for training a machine learning model provided in an embodiment of the present application, comprising the following steps:

[0079] S21, obtaining a historical set temperature of at least one furnace zone and historical characteristic data corresponding to the historical set temperature.

[0080] In some embodiments of the present application, the historical set temperature corresponds to the initial set temperature. For example, if the initial set temperature is the temperature set when the reflow furnace produces a printed circuit board, the historical set temperature is the recorded temperature of one or more printed circuit boards produced in the reflow furnace. The electronic device can obtain the historical set temperature from the database or operation log of the reflow furnace, and the historical set temperature can be multiple.

[0081] In some embodiments of the present application, the historical characteristic data is characteristic data of a time-temperature curve of historical furnace zone data of a reflow furnace in producing one or more printed circuit boards. The data types of the historical characteristic data and the predicted characteristic data are substantially the same as those of the target characteristic data, so this application will not repeat the description.

[0082] In some embodiments of the present application, the historical furnace zone data may include each historical furnace zone temperature and the historical time corresponding to each historical furnace zone temperature, etc. The acquisition process of the historical furnace zone data is basically the same as the acquisition process of the actual furnace zone data, so this application will not repeat the description.

[0083] S22, using a machine learning algorithm to predict the historical set temperature to obtain prediction feature data.

[0084] In some embodiments of the present application, the machine learning algorithm includes, but is not limited to: regression algorithm, decision tree algorithm, random forest algorithm, support vector machine, etc. Alternatively, the machine learning algorithm can also be replaced by a deep learning algorithm such as a convolutional neural network.

[0085] S23, calculating the loss value of the machine learning algorithm according to the historical feature data and the predicted feature data, and adjusting the machine learning algorithm according to the loss value.

[0086] In some embodiments of the present application, if there are multiple historical feature data and multiple predicted feature data, calculating the loss value of the machine learning algorithm based on the historical feature data and the predicted feature data includes: the electronic device determines the error between the multiple historical feature data and the corresponding predicted feature data as the loss value.

[0087] The error may be mean absolute error (MAE), mean error (ME), mean square error (MSE), root mean square error (RMSE), etc. The error may be calculated in a corresponding manner. For example, when the error is the root mean square error, the error calculation method may refer to the following formula:

[0088]

[0089] Among them, RMSE represents the mean square error, n represents the number of multiple historical feature data, and x i represents the i-th historical feature data, y i Represents the predicted feature data corresponding to the i-th historical feature data.

[0090] S24, determining whether the loss value drops to a preset range.

[0091] In some embodiments of the present application, the preset range can be set arbitrarily, and the present application does not limit this. For example, the preset range can be [0.1, 0.2].

[0092] In this embodiment, if the loss value does not drop to the preset range, the electronic device returns to step S22 and continues to use the machine learning algorithm to predict the historical set temperature. Alternatively, if the loss value drops to the preset range, the electronic device executes step S25.

[0093] S25, stop adjusting, and use the adjusted machine learning algorithm as the machine learning model.

[0094] For example, when the loss value is between [0.1, 0.2], the electronic device stops adjusting the machine learning algorithm and uses the adjusted machine learning algorithm as the machine learning model.

[0095] In this embodiment, the machine learning algorithm is trained by using the historical set temperatures and the historical feature data corresponding to the historical set temperatures, so that the trained machine learning model can learn the correlation between the set temperatures and the feature data. The adjustment of the machine learning algorithm will be stopped only when the loss value drops to a preset range, thereby ensuring the predictive ability of the machine learning model.

[0096] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the methods in the above-mentioned embodiments of the present application.

[0097] The computer-readable storage medium may be an internal memory of the electronic device of the above-mentioned embodiment, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), etc. equipped on the electronic device.

[0098] In some embodiments, the computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the electronic device, etc.

[0099] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0100] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can 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.

[0101] In the embodiments provided in the present application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0102] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0103] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for determining the temperature of a reflow furnace, characterized in that: The method comprises: Obtaining an initial set temperature for at least one furnace zone in a reflow furnace; Predicting the initial set temperature using a preset machine learning model to obtain target feature data corresponding to the at least one furnace zone, and judging whether the initial set temperature meets the production requirements based on preset conditions and the target feature data; If the initial set temperature meets the production requirements, obtaining actual furnace zone data of the initial set temperature in the reflow furnace; A target set temperature of the at least one furnace zone is determined according to the preset condition, the initial set temperature and the actual furnace zone data.

2. The method for determining the temperature of a reflow furnace according to claim 1, wherein: If there are multiple furnace zones, the using of a preset machine learning model to predict the initial set temperature to obtain target feature data corresponding to the at least one furnace zone includes: The machine learning model is used to predict the initial set temperature of each furnace zone to obtain the target feature data corresponding to each furnace zone.

3. The method for determining the temperature of a reflow furnace according to claim 2, wherein: If the target characteristic data corresponding to the multiple furnace zones include a slope, a peak temperature, and a duration of each furnace zone, judging whether the initial set temperature meets the production requirements based on the preset conditions and the target characteristic data includes: If the slope, the peak temperature, and the multiple durations all meet the preset conditions, it is determined that the multiple initial set temperatures of the multiple furnace zones meet the production requirements.

4. The method for determining the temperature of a reflow furnace according to claim 1, wherein: Before using a preset machine learning model to predict the initial set temperature, the method further includes: Acquire a historical set temperature of the at least one furnace zone and historical characteristic data corresponding to the historical set temperature; Using a machine learning algorithm to predict the historical set temperature to obtain prediction feature data; The loss value of the machine learning algorithm is calculated according to the historical feature data and the predicted feature data, and the machine learning algorithm is adjusted according to the loss value until the loss value drops to a preset range, then the adjustment is stopped and the adjusted machine learning algorithm is used as the machine learning model.

5. The method for determining the temperature of a reflow furnace according to claim 4, wherein: If both the historical feature data and the predicted feature data are multiple, calculating the loss value of the machine learning algorithm according to the historical feature data and the predicted feature data includes: The errors between the plurality of historical feature data and the corresponding predicted feature data are determined as the loss value.

6. The method for determining the temperature of a reflow furnace according to claim 1, wherein: The obtaining of the actual furnace zone data of the initial set temperature in the reflow furnace comprises: The data transmitted from a plurality of acquisition tools arranged at different positions in the at least one furnace zone are received, and the received plurality of data are combined to obtain the actual furnace zone data.

7. The method for determining the temperature of a reflow furnace according to claim 1, wherein: If the target set temperature is used to produce printed circuit boards, the method further includes: Acquire historical yield data of a plurality of produced printed circuit boards and historical board entry time intervals of the plurality of printed circuit boards between a plurality of furnace zones of the reflow furnace; The preset model is called to predict the historical yield data and the historical board-entry time interval to obtain the target board-entry time interval of the multiple printed circuit boards between the multiple furnace zones.

8. The method for determining the temperature of a reflow furnace according to claim 7, wherein: The method further comprises: The production of printed circuit boards is controlled by the target set temperature and the target board feeding time interval.

9. An electronic device, characterized in that: The electronic device comprises: a memory storing at least one instruction; and The processor executes the at least one instruction to implement the reflow furnace temperature determination method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the method for determining the temperature of a reflow oven as claimed in any one of claims 1 to 8.

Images