Packaging temperature control method and system for LED braider

Abstract

The invention relates to the technical field of temperature control, in particular to a packaging temperature control method and system for an LED taping machine, and the method comprises the steps: collecting the temperature data and current data of the LED taping machine at a plurality of historical time nodes, obtaining the optimal solution of the temperature data of the LED taping machine at the current time node through a random hill climbing algorithm, and obtaining the optimal solution of the temperature data of the LED taping machine at the current time node; adjusting the temperature of the current time node based on the optimal solution; wherein the initial solution of using the random hill climbing algorithm is as follows: obtaining # imgabs0 nearest neighbor temperature data of temperature data of a plurality of historical time nodes, calculating a noise factor of the temperature data of each historical time node, taking the temperature data of which the noise factor is greater than a set threshold value as noise, and removing the noise; and the mean value of the # imgabs 1 # nearest neighbor temperature data after noise elimination is used as an initial solution. According to the invention, the problem of low accuracy during packaging temperature control is solved.

Description

Technical Field

[0001] The present invention relates to the field of temperature control technology, and more particularly to a packaging temperature control method and system for an LED taping machine. Background Art

[0002] LED taping machines play a key role in the LED packaging production process. Precise control of packaging temperature directly impacts the soldering quality, luminous efficacy stability, and lifespan of LED chips. Traditional packaging temperature control methods typically rely on fixed temperature control parameters or simple regression predictions based on historical data. However, these methods struggle to dynamically adjust temperature in production environments subject to temperature fluctuations, equipment aging, and process variations. This can lead to unstable packaging quality and even soldering defects.

[0003] Currently, some intelligent temperature control methods incorporate machine learning or optimization algorithms for temperature prediction and control to improve package stability. However, existing methods can still suffer from insufficient prediction accuracy, slow response, or over-reliance on local optimal solutions under complex operating conditions.

[0004] Therefore, to address the optimization needs of LED taping machine packaging temperature control, a packaging temperature control method and system based on an improved random hill climbing algorithm was proposed. By collecting and analyzing historical temperature data, the optimal output value before package temperature control is predicted and the temperature control strategy is dynamically adjusted to improve packaging stability and ensure production quality. In a random hill climbing algorithm, the choice of initial solution has a significant impact on the algorithm's convergence speed and final results. Initial solutions are typically generated randomly to ensure algorithm diversity and exploration capabilities. If the initial solution is near a more optimal solution, the algorithm may converge quickly, but it may also become trapped in a local optimum, affecting global search capabilities. Therefore, the rationality of the initial solution not only affects the algorithm's convergence efficiency but also determines the quality of the final solution.

[0005] Although some existing intelligent temperature control methods can achieve intelligent temperature control of the package temperature to a certain extent, when collecting temperature data, the LED taping machine usually has a high-frequency operating current, which may generate electromagnetic interference, thereby causing some noise data to be mixed into the temperature data. The presence of noise data will cause the random hill climbing algorithm to greatly reduce the prediction accuracy of the initial solution for each temperature control, thereby leading to the problem of low accuracy in package temperature control. Summary of the Invention

[0006] In order to solve the problem of low accuracy in package temperature control raised in the above background art, the present invention provides solutions in the following aspects.

[0007] In a first aspect, the present invention provides a packaging temperature control method for an LED taping machine, comprising: collecting temperature data and current data of the LED taping machine at multiple historical time nodes, using a random hill climbing algorithm to obtain an optimal solution for the temperature data of the LED taping machine at a current time node, and adjusting the temperature of the current time node based on the optimal solution; wherein the initial solution of the random hill climbing algorithm is: obtaining the temperature data of multiple historical time nodes The nearest neighbor temperature data is calculated Noise factor of temperature data at historical time nodes , , where For the The degree of isolation of temperature data at each historical time node, For the The temperature data of the historical time nodes are ranked in descending order among all historical time nodes. For the The current data corresponding to the temperature data of each historical time node is ranked in descending order among all historical time nodes. To preset hyperparameters, is a normalized function, and the degree of isolation characterizes the abnormality of the temperature data. The nearest neighbor temperature data with a noise factor greater than a set threshold are treated as noise and removed, and the mean of the nearest neighbor temperature data after noise removal is used as the initial solution.

[0008] The above technical solution collects the temperature data and current data of the LED taping machine at multiple historical time nodes, and uses the random hill climbing algorithm to obtain the optimal solution for the temperature data of the LED taping machine at the current time node, which can effectively improve the accuracy of packaging temperature control.

[0009] Furthermore, the degree of isolation , , where 、 Respectively The distance between the upper and lower bounds of the boxplot and the temperature data of multiple historical time nodes, is the variance of temperature data at multiple historical time points, To preset hyperparameters, is the normalization function.

[0010] This technical solution effectively identifies abnormal temperature data by calculating the degree of deviation of temperature data at historical time points relative to the overall data distribution. The distance between the upper and lower bounds of the boxplot is used to measure the degree of outliers, making the calculation of isolation more accurate. Normalization is also performed based on the overall data fluctuations, improving the comparability of temperature data at different time points. By setting hyperparameters to avoid numerical instability in the calculation, the stability and robustness of the isolation calculation are ensured, thereby improving the overall reliability of temperature data optimization and anomaly detection.

[0011] Furthermore, it also includes correcting the initial solution, specifically: Randomly select a value from the set error range of the initial solution as the new solution, compare the new solution with the objective function value of the initial solution, and take the solution corresponding to the largest objective function value as the revised solution. The objective function value is calculated as follows: , where For the The objective function value of the solution, For the The energy consumption of the temperature data corresponding to each solution for one minute, For the The qualified rate of the package temperature corresponding to each solution is The natural constant An exponential function with base .

[0012] This technical solution refines package temperature control by modifying the initial solution and selecting the solution with the largest objective function value. By randomly selecting new solutions within a set error range and evaluating the objective function, local optimality can be effectively avoided, improving the global nature of the optimization results. The objective function comprehensively considers two key factors: energy consumption and pass rate. It reduces the impact of energy consumption on the objective function in an exponentially decaying manner, ensuring that the optimized temperature setting reduces energy consumption while ensuring package quality. This solution can improve production efficiency, reduce energy consumption, and enhance the adaptability of package temperature control while meeting process requirements, making it more stable and efficient in actual production.

[0013] Furthermore, a temperature sensor is used to collect temperature data of the LED tape braiding machine at multiple historical time points, and a current sensor is used to collect current data of the LED tape braiding machine at multiple historical time points.

[0014] Furthermore, the temperature at the current time node is adjusted as follows: The optimal solution is used as the target temperature, and the difference between the temperature of the current time node and the target temperature is detected in real time. If the temperature of the current time node deviates from the target temperature, the heating or cooling equipment is automatically adjusted to adjust the temperature of the current time node to the target temperature.

[0015] Further, using The nearest neighbor algorithm obtains temperature data of multiple historical time nodes Nearest neighbor temperature data.

[0016] Furthermore, the method further includes performing data cleaning on the package temperature data. The data cleaning includes detecting and processing abnormal values in the package temperature data, and eliminating the abnormal values by setting a temperature change threshold.

[0017] This technical solution effectively improves the accuracy and stability of temperature control by cleaning package temperature data. By setting temperature change thresholds to detect and eliminate outliers, it prevents extreme temperature data from interfering with calculation results and reduces the impact of noise on package temperature adjustments, thereby improving the reliability of temperature predictions. The introduction of data cleaning allows subsequent temperature optimization and control to be calculated based on more realistic and stable data, thereby improving temperature balance during the packaging process, reducing the impact of temperature fluctuations on product quality, and enhancing production consistency and yield.

[0018] Furthermore, the normalization function adopts maximum-minimum normalization.

[0019] This technical solution utilizes maximum-minimum normalization to process data, maintaining variables such as package temperature data, noise factors, and objective function values within a uniform numerical range, thereby improving computational stability and comparability. Normalization reduces the impact of varying data scales on the optimization process, ensuring that all parameters have equal weight during calculations, and improving the algorithm's convergence speed and computational efficiency. Furthermore, maximum-minimum normalization preserves the distribution characteristics of the original data, ensuring that the optimization results are more aligned with actual package temperature control requirements, thereby enhancing packaging quality and production stability.

[0020] Furthermore, the set threshold is 0.5.

[0021] In a second aspect, the present invention provides a packaging temperature control system for an LED taping machine, comprising a memory and a processor, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, any one of the above-described packaging temperature control methods for an LED taping machine is implemented.

[0022] The beneficial effects of the present invention are: This invention utilizes a randomized hill climbing algorithm to determine the optimal solution for the temperature data of an LED taping machine at the current time point, and adjusts the temperature at the current time point based on this optimal solution, effectively improving the control accuracy of the LED taping machine's packaging temperature. By removing noise from historical packaging temperature data and calculating the degree of temperature isolation, abnormal data can be identified and removed, thereby preventing noise from interfering with temperature control. This invention effectively improves the stability and production efficiency of the LED taping machine under different operating conditions, ensuring packaging temperature accuracy while reducing energy consumption and improving production quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flow chart schematically illustrating a packaging temperature control method for an LED taping machine according to an embodiment of the present invention; Figure 2 FIG. 4 is a block diagram schematically illustrating a structure of a packaging temperature control system for an LED taping machine according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] An embodiment of a packaging temperature control method for an LED taping machine.

[0025] like Figure 1 As shown, a flow chart of a packaging temperature control method for an LED taping machine according to an embodiment of the present invention includes the following steps: S1: Collect temperature and current data of the LED taping machine at multiple historical time points.

[0026] In one embodiment, to accurately capture temperature changes during the LED taping machine packaging process, high-precision temperature and current sensors can be used to continuously monitor temperature and current, ensuring real-time and accurate data acquisition. The temperature and current sensors are set to acquire data once per second, enabling the recording of every subtle temperature and current fluctuation during the packaging process. This high-frequency data acquisition method not only provides more detailed historical temperature and current data but also enhances the ability to detect sudden temperature and current anomalies, helping to identify anomalies that may affect packaging quality in advance and providing accurate data support for subsequent packaging temperature control.

[0027] Furthermore, using high-precision temperature and current sensors to collect temperature and current data can reduce the impact of environmental noise on temperature measurements and improve the reliability of measurement data. For example, during operation, an LED taping machine may be affected by factors such as ambient temperature, air flow, and mechanical vibration, leading to fluctuations in package temperature. Therefore, data collection can be combined with the sensor's self-calibration function to ensure high-precision temperature and current data is obtained even under complex operating conditions. By collecting and storing temperature and current data from multiple historical time points, a time series database of temperature and current can be constructed, providing reliable data support for subsequent package temperature optimization.

[0028] S2: Use the random hill climbing algorithm to obtain the optimal solution for the temperature data of the LED taping machine at the current time node.

[0029] In one embodiment, the process of obtaining the optimal solution of the temperature data of the LED tape machine at the current time node based on the initial solution of the random hill climbing algorithm is a well-known technology and will not be described in detail in this solution. Nearest neighbor temperature data, where The nearest neighbor algorithm obtains temperature data of multiple historical time nodes Nearest neighbor temperature data, The nearest neighbor algorithm is a well-known technology and will not be described in detail in this solution. Noise factor of temperature data at historical time nodes , , where For the The degree of isolation of temperature data at each historical time node, For the The temperature data of the historical time nodes are ranked in descending order among all historical time nodes. For the The current data corresponding to the temperature data of each historical time node is ranked in descending order among all historical time nodes. To preset hyperparameters, is a normalization function; the nearest neighbor temperature data with a noise factor greater than the set threshold is treated as noise and removed, and the mean of the nearest neighbor temperature data after noise removal is used as the initial solution.

[0030] By combining the nearest neighbor information of historical temperature data and selecting representative temperature data as the initial solution, the algorithm's stability and rationality are improved. By calculating the degree of isolation of temperature data, the degree of data anomaly can be effectively measured. A noise factor is constructed by combining the ranking differences of temperature and current data to identify anomalous data from multiple perspectives. Normalization ensures the comparability of data of different dimensions. Presetting adjustment parameters enhances the model's adaptability to different data distributions, thereby improving the optimization effect of the random hill climbing algorithm in temperature control and making the resulting temperature data more reliable and accurate.

[0031] In another embodiment, the initial solution is modified as follows: Randomly select a value from the set error range of the initial solution as the new solution, compare the new solution with the objective function value of the initial solution, and take the solution corresponding to the largest objective function value as the revised solution. The objective function value is calculated as follows: , where For the The objective function value of the solution, For the The energy consumption of the temperature data corresponding to each solution for one minute, For the The qualified rate of the package temperature corresponding to each solution is The natural constant An exponential function with base .

[0032] By randomly selecting new solutions within a set error range of the initial solution and optimizing them by comparing the objective function values, the system achieves both optimal energy efficiency and a high pass rate during package temperature control. By combining energy consumption and pass rate into the objective function, the system's efficiency and stability are balanced to find the optimal package temperature control strategy. Adjusting the objective function value using an exponential function further refines the trade-off between energy consumption and pass rate, thereby improving package quality and energy efficiency while effectively reducing overall energy consumption.

[0033] In one embodiment, the calculation The degree of isolation of temperature data at each historical time point , , where 、 Respectively The distance between the upper and lower bounds of the boxplot and the temperature data of multiple historical time nodes, is the variance of temperature data at multiple historical time nodes, To preset hyperparameters, is a normalization function that uses maximum and minimum normalization.

[0034] Calculating the degree of deviation of historical temperature data from the overall data distribution helps identify anomalous temperature points. Using the upper and lower bounds of the boxplot to measure the degree of data outliers makes isolation more accurate and enhances the stability of anomaly detection by combining it with overall data fluctuations. Normalization uses maximum and minimum normalization to ensure that calculation results at different time points remain within a consistent range, improving data comparability and adaptability. By setting adjustment parameters, numerical instability during the calculation process is further avoided, making temperature data optimization and anomaly detection more reliable, thereby improving the accuracy and stability of temperature control.

[0035] In another embodiment, the calculation The degree of isolation of temperature data at each historical time point , , where 、 Respectively The distance between the upper and lower bounds of the boxplot and the temperature data of multiple historical time nodes, is the median of the temperature data at multiple historical time points, To preset hyperparameters, is a normalization function that uses maximum and minimum normalization.

[0036] By calculating the degree of deviation of temperature data from the overall data distribution, anomalous data points can be effectively identified. The upper and lower bounds of the boxplot are used to measure the degree of data outliers, making isolation calculation more accurate. Incorporating the median of historical data instead of variance improves adaptability to uneven data distribution. Normalization uses maximum and minimum normalization to ensure that calculation results at different time points remain within a consistent range, improving data comparability. By setting adjustment parameters, numerical instability during the calculation process is avoided, making temperature data optimization and anomaly detection more reliable, thereby improving the accuracy and stability of temperature control.

[0037] S3: Adjust the package temperature in real time based on the optimal solution.

[0038] In one embodiment, the optimal package temperature solution obtained by the optimization algorithm is used as the target temperature. The difference between the current temperature and the target temperature is monitored in real time. If the temperature deviates from the target value, the heating or cooling equipment is automatically adjusted to ensure that the temperature remains within the optimal range. This process ensures precise temperature control through real-time feedback and adjustment, thereby improving production efficiency and product quality.

[0039] The solution of the present invention is improved The nearest neighbor algorithm and noise rejection technology effectively improve the accuracy and stability of package temperature control. By collecting package temperature data from multiple historical time points and combining it with noise factor analysis, abnormal temperature data can be accurately identified and eliminated, optimizing the initial solution and further correcting it to obtain the optimal solution, thereby achieving precise control of package temperature. This solution can adjust the temperature in real time, ensuring the operating stability of the LED taping machine, improving production efficiency and product quality, while also reducing energy consumption and the impact of abnormal temperature fluctuations.

[0040] An embodiment of a packaging temperature control system for an LED taping machine: like Figure 2 As shown, a structural block diagram of a packaging temperature control system for an LED taping machine according to an embodiment of the present invention includes a processor and a memory.

[0041] The present invention also provides a packaging temperature control system for an LED taping machine. Figure 2 As shown, the system includes a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, the packaging temperature control method for the LED taping machine according to the present invention is implemented.

[0042] The packaging temperature control system for the LED taping machine also includes other components well known to those skilled in the art, such as a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0043] In the present invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, the computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application, module, or both. Any such computer storage medium can be part of, accessible to, or connectable to a device. Any application or module described in the present invention can be implemented using computer-readable / executable instructions stored or otherwise maintained by such a computer-readable medium.

[0044] In the description of this specification, "multiple" and "several" mean at least two, such as two, three or more, unless otherwise clearly defined.

[0045] While several embodiments of the present invention have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous modifications, variations, and alternatives will occur to those skilled in the art without departing from the concept and spirit of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in practicing the present invention.

Claims

1. A packaging temperature control method and system for an LED taping machine, characterized in that: include: Collect temperature and current data of the LED taping machine at multiple historical time nodes, use a random hill climbing algorithm to obtain the optimal solution for the temperature data of the LED taping machine at the current time node, and adjust the temperature of the current time node based on the optimal solution; Among them, the initial solution when using the random hill climbing algorithm is: obtain the temperature data of multiple historical time nodes The nearest neighbor temperature data is calculated Noise factor of temperature data at historical time nodes , , where For the The degree of isolation of temperature data at each historical time node, For the The temperature data of the historical time nodes are ranked in descending order among all historical time nodes. For the The current data corresponding to the temperature data of each historical time node is ranked in descending order among all historical time nodes. To preset hyperparameters, is a normalized function, and the isolation degree represents the abnormality degree of the temperature data; The nearest neighbor temperature data with a noise factor greater than a set threshold are treated as noise and removed, and the mean of the nearest neighbor temperature data after noise removal is used as the initial solution.

2. A packaging temperature control method and system for an LED taping machine according to claim 1, characterized in that: The degree of isolation , , where 、 Respectively The distance between the upper and lower bounds of the boxplot and the temperature data of multiple historical time nodes, is the variance of temperature data at multiple historical time points, To preset hyperparameters, is the normalization function.

3. A packaging temperature control method and system for an LED taping machine according to claim 1, characterized in that: It also includes correcting the initial solution, specifically: A value is randomly selected from the set error range of the initial solution as the new solution, and the objective function value of the new solution is compared with the initial solution. The solution corresponding to the largest objective function value is taken as the revised solution. The objective function value is calculated as follows: , where For the The objective function value of the solution, For the The energy consumption of the temperature data corresponding to each solution for one minute, For the The qualified rate of the package temperature corresponding to each solution is The natural constant An exponential function with base .

4. A packaging temperature control method and system for an LED taping machine according to claim 1, characterized in that: The temperature sensor is used to collect the temperature data of the LED taping machine at multiple historical time nodes, and the current sensor is used to collect the current data of the LED taping machine at multiple historical time nodes.

5. A packaging temperature control method and system for an LED taping machine according to claim 1, characterized in that: The temperature of the current time node is adjusted as follows: The optimal solution is used as the target temperature, and the difference between the temperature of the current time node and the target temperature is detected in real time. If the temperature of the current time node deviates from the target temperature, the heating or cooling equipment is automatically adjusted to adjust the temperature of the current time node to the target temperature.

6. A packaging temperature control method and system for an LED taping machine according to claim 1, characterized in that: use The nearest neighbor algorithm obtains temperature data of multiple historical time nodes Nearest neighbor temperature data.

7. A packaging temperature control method and system for an LED taping machine according to claim 1, characterized in that: The method further includes performing data cleaning on the temperature data and the current data, wherein the data cleaning includes detecting and processing abnormal values, and the abnormal values are eliminated by setting a change threshold.

8. A packaging temperature control method and system for an LED taping machine according to claim 1, characterized in that: The normalization function adopts maximum and minimum normalization.

9. The packaging temperature control method and system for an LED taping machine according to claim 1, wherein: The threshold value is set to 0.

5.

10. A packaging temperature control system for an LED taping machine, characterized in that: The invention comprises a memory and a processor, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a packaging temperature control method for an LED taping machine according to any one of claims 1 to 9 is implemented.

Images