A superpulse thulium fiber laser therapy machine with adaptive air-cooling function

Abstract

This invention relates to the field of medical device technology and discloses an ultrapulse thulium fiber laser therapy machine with adaptive air-cooling function. It includes: a support platform, a heat dissipation module, a joint support arm, and a six-axis robotic arm. The heat dissipation module is fixedly connected to the side of the support platform, and the joint support arm and the six-axis robotic arm are fixedly connected to the top of the support platform. A heat dissipation control module is installed inside the heat dissipation module. A base is fixedly connected to the bottom of the support platform. The joint support arm includes a first support arm, a second support arm, and a screen support arm. One end of the first support arm is slidably connected to the second support arm, and the other end of the first support arm is fixedly connected to a control console. The second support arm and the screen support arm are slidably connected. The six-axis robotic arm includes a robotic arm body, a connecting block, and a laser. One end of the connecting block is connected to the robotic arm body, and the other end of the connecting block is fixedly connected to the laser. This invention ensures reliable heat dissipation through the adaptive adjustment of the heat dissipation control module.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and more specifically, to an ultrapulse thulium fiber laser therapy machine with adaptive air-cooling function. Background Technology

[0002] Thulium fiber laser therapy machines are widely used in medical aesthetics and surgical treatments. Ultrapulse thulium fiber laser therapy machines, with their output laser wavelength matched to human tissue, can achieve efficient tissue cutting, vaporization, or coagulation while minimizing thermal damage to surrounding tissues. However, as the output power of ultrapulse thulium fiber laser therapy machines continues to increase, the heat generated also increases. If this heat cannot be dissipated in time, the internal temperature of the equipment will continue to rise, leading to a series of problems: firstly, the stability of the laser output decreases, manifested as pulse energy fluctuations and wavelength drift; secondly, components exposed to high temperatures for extended periods will have a shorter lifespan, increasing maintenance costs and the risk of downtime. Currently, heat dissipation in ultrapulse thulium fiber laser therapy machines typically relies on manual operation. Operators manually set the air-cooling speed based on the output power, relying on manual judgment and unable to dynamically adjust the air-cooling speed according to actual conditions. The lack of a feedback adjustment mechanism results in low reliability of heat dissipation.

[0003] Therefore, it is necessary to design an ultrapulse thulium fiber laser therapy machine with adaptive air-cooling function to solve the problems existing in the current technology. Summary of the Invention

[0004] In view of this, the present invention proposes an ultrapulse thulium fiber laser therapy machine with adaptive air-cooling function, which aims to solve the above problems.

[0005] This invention proposes an ultrapulse thulium fiber laser therapy machine with adaptive air-cooling function, comprising:

[0006] Support platform, heat dissipation module, articulated support arm and six-axis robotic arm;

[0007] The heat dissipation module is fixedly connected to the side of the support platform, the joint support arm and the six-axis robotic arm are fixedly connected to the top of the support platform, a heat dissipation control module is installed inside the heat dissipation module, and a base is fixedly connected to the bottom of the support platform.

[0008] The joint support arm includes a first support arm, a second support arm, and a screen support arm;

[0009] One end of the first support arm is slidably connected to the second support arm, and the other end of the first support arm is fixedly connected to the console, which is equipped with a first screen.

[0010] The second support arm and the screen support arm are slidably connected, and the screen support arm is fixedly connected to the second screen;

[0011] The six-axis robotic arm includes a robotic arm body, a connecting block, and a laser;

[0012] One end of the connecting block is connected to the robotic arm body, and the other end of the connecting block is fixedly connected to the laser.

[0013] Furthermore, the heat dissipation control module includes:

[0014] The acquisition and analysis unit is configured to acquire the output power of the laser, compare the output power with a historical heat dissipation dataset, and determine whether to execute a heat dissipation control strategy or a heat dissipation prediction strategy based on the comparison results.

[0015] The heat dissipation analysis unit is configured to determine the air cooling speed based on the number of times the output power appears in the historical heat dissipation dataset when it is determined that the heat dissipation control strategy is to be executed, or to determine the air cooling speed based on the output power and a clustering algorithm; and to determine the air cooling speed based on the output power and a heat dissipation prediction model when it is determined that the heat dissipation prediction strategy is to be executed.

[0016] The heat dissipation unit is configured to acquire real-time images and heat dissipation efficiency of the heat dissipation module. When the heat dissipation efficiency does not meet the heat dissipation requirements, it performs dust identification based on the real-time images, determines a first heat dissipation adjustment coefficient, and determines a second heat dissipation adjustment coefficient based on the heat dissipation dust model.

[0017] The heat dissipation adjustment unit is configured to determine a target heat dissipation adjustment coefficient based on the first heat dissipation adjustment coefficient and the second heat dissipation adjustment coefficient, adjust the air cooling speed according to the target heat dissipation adjustment coefficient, and perform heat dissipation at the adjusted air cooling speed.

[0018] Furthermore, when comparing the output power with historical heat dissipation datasets and determining whether to implement a heat dissipation control strategy or a heat dissipation prediction strategy based on the comparison results, the process includes:

[0019] The historical heat dissipation dataset includes several historical output powers and several historical air-cooling speeds, with each historical output power corresponding to a historical air-cooling speed.

[0020] If the historical heat dissipation dataset contains a historical output power that is the same as the output power, then the heat dissipation control strategy is determined to be executed.

[0021] If there is no historical output power in the historical heat dissipation dataset that is the same as the output power, then the heat dissipation prediction strategy will be executed.

[0022] Furthermore, when it is determined that the heat dissipation control strategy should be executed, the air cooling speed is determined based on the number of times the output power appears in the historical heat dissipation dataset, or, when the air cooling speed is determined based on the output power and a clustering algorithm, the following steps are included:

[0023] When the number of occurrences of the same historical output power as the output power in the historical heat dissipation data is greater than or equal to 3, the average of the historical air-cooling speeds corresponding to the same historical output power is determined as the air-cooling speed.

[0024] If the number of occurrences of the same historical output power as the output power in the historical heat dissipation dataset is less than 3, then the air-cooling speed is determined based on the output power and the clustering algorithm.

[0025] Furthermore, when determining the air-cooled rotation speed based on the output power and clustering algorithm, the following steps are included:

[0026] The output power and the historical heat dissipation dataset are used as the dataset to be clustered. The historical air-cooling speed corresponding to each historical output power in the dataset to be clustered is extracted, and the expected number of clusters k is determined to be 2. The parameters of the Gaussian distribution are initialized, and the probability of each data in the dataset to be clustered belonging to each Gaussian distribution is determined to determine the responsibility value. Based on the responsibility value, the clustering dataset corresponding to the output power is determined.

[0027] The average historical air-cooling speed in the clustered dataset is determined as the air-cooling speed.

[0028] Furthermore, when it is determined that the heat dissipation prediction strategy should be executed, determining the air-cooling speed based on the output power and the heat dissipation prediction model includes:

[0029] Obtain the operational dataset of the ultrapulse thulium fiber laser therapy machine, and merge the historical heat dissipation dataset and the operational dataset to determine the model dataset;

[0030] The model dataset is divided into a model training set and a model test set;

[0031] The random forest model is trained based on the model training set, and the trained random forest model is tested based on the model test set. Finally, a heat dissipation prediction model with the input as output power and the output as air-cooled speed is determined.

[0032] Furthermore, when the heat dissipation efficiency does not meet the heat dissipation requirements, it includes:

[0033] Obtain the heat dissipation efficiency of the heat dissipation module per unit time, and obtain the historical average heat dissipation efficiency of the heat dissipation module;

[0034] When the heat dissipation efficiency is greater than or equal to the historical average heat dissipation efficiency, it is determined that the heat dissipation requirement is met, and heat dissipation is performed at the current air cooling speed.

[0035] If the heat dissipation efficiency is less than the historical average heat dissipation efficiency, then the heat dissipation requirement is not met.

[0036] Furthermore, when the heat dissipation efficiency does not meet the heat dissipation requirements, dust is identified based on the real-time image to determine a first heat dissipation adjustment coefficient, and a second heat dissipation adjustment coefficient is determined based on the heat dissipation dust model, including:

[0037] Obtain a standard real-time image corresponding to the real-time image;

[0038] Extract all the dust pixels to be identified from the real-time image, and extract the standard pixels corresponding to each dust pixel to be identified from the standard real-time image;

[0039] Determine the dust pixel value corresponding to all dust pixels to be identified, and determine the standard pixel value corresponding to all standard pixels;

[0040] Delete the dust pixels whose dust pixel value is equal to the standard pixel value, and determine the remaining dust pixels as dust pixels. Determine the first heat dissipation adjustment coefficient based on the dust pixels.

[0041] A twin neural network model is pre-trained, and the trained twin neural network model is determined as the heat dissipation dust model. The second heat dissipation adjustment coefficient is determined based on the real-time image and the heat dissipation dust model.

[0042] Furthermore, when determining the first heat dissipation adjustment coefficient based on the dust pixels, the process includes:

[0043] The number of pixels of the dust pixels is determined, and a first preset number of pixels and a second preset number of pixels are preset, wherein the first preset number of pixels is greater than the second preset number of pixels;

[0044] A first preset heat dissipation adjustment coefficient, a second preset heat dissipation adjustment coefficient, and a third preset heat dissipation adjustment coefficient are preset, wherein the first preset heat dissipation adjustment coefficient is greater than the second preset heat dissipation adjustment coefficient, and the second preset heat dissipation adjustment coefficient is greater than the third preset heat dissipation adjustment coefficient;

[0045] When the number of pixels is greater than the number of first preset pixels, the first preset heat dissipation adjustment coefficient is determined as the first heat dissipation adjustment coefficient.

[0046] When the number of pixels is less than or equal to the first preset number of pixels and greater than or equal to the second preset number of pixels, the second preset heat dissipation adjustment coefficient is determined as the first heat dissipation adjustment coefficient.

[0047] When the number of pixels is less than the second preset number of pixels, the third preset heat dissipation adjustment coefficient is determined as the first heat dissipation adjustment coefficient.

[0048] Furthermore, when determining the target heat dissipation adjustment coefficient based on the first heat dissipation adjustment coefficient and the second heat dissipation adjustment coefficient, and adjusting the air-cooling speed according to the target heat dissipation adjustment coefficient, the process includes:

[0049] The target heat dissipation adjustment coefficient is the average of the first heat dissipation adjustment coefficient and the second heat dissipation adjustment coefficient, and the air cooling speed is directly proportional to the target heat dissipation adjustment coefficient.

[0050] Compared with existing technologies, the advantages of this invention are as follows: the wheels on the base provide convenient mobility for the ultrapulse thulium fiber laser therapy machine, allowing it to flexibly adapt to different spatial layouts in medical scenarios. The support platform stably connects the heat dissipation module, the articulated support arm, and the six-axis robotic arm, providing a stable platform for the stable operation of each component. The articulated support arm and the six-axis robotic arm allow for free adjustment of the spatial positions of the first screen, the second screen, and the laser according to the user's operating habits and visual needs. The heat dissipation control module inside the heat dissipation module senses the laser's output power in real time, thereby dynamically adjusting the intensity of air cooling to precisely match the heat generation changes during ultrapulse thulium fiber laser operation. This avoids overheating caused by insufficient heat dissipation and prevents energy waste caused by excessive heat dissipation, achieving efficient and energy-saving heat dissipation management. Furthermore, adaptive air cooling ensures the accuracy and consistency of laser energy output, effectively reducing the risk of aging and damage to internal components due to high temperatures, reducing the maintenance frequency of the ultrapulse thulium fiber laser therapy machine, and thus ensuring work efficiency. Attached Figure Description

[0051] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0052] Figure 1 This is a schematic diagram of the structure of an ultrapulse thulium fiber laser therapy machine with adaptive air-cooling function provided in an embodiment of the present invention;

[0053] Figure 2A side view of an ultrapulse thulium fiber laser therapy machine with adaptive air-cooling function provided in an embodiment of the present invention;

[0054] Figure 3 This is a functional block diagram of the heat dissipation control module provided in an embodiment of the present invention.

[0055] The components include: 1. Base; 2. Support platform; 3. Heat dissipation module; 4. Joint support arm; 40. First support arm; 41. Second support arm; 42. Screen support arm; 5. Control console; 6. First screen; 7. Second screen; 8. Six-axis robotic arm; 80. Robotic arm body; 81. Connecting block; 82. Laser. Detailed Implementation

[0056] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0057] See Figure 1-2 As shown in some embodiments of this application, an ultrapulse thulium fiber laser therapy machine with adaptive air-cooling function includes: a support platform 2, a heat dissipation module 3, a joint support arm 4, and a six-axis robotic arm 8. The heat dissipation module 3 is fixedly connected to the side of the support platform 2, and the joint support arm 4 and the six-axis robotic arm 8 are fixedly connected to the top of the support platform 2. A heat dissipation control module is provided inside the heat dissipation module 3. A base 1 is fixedly connected to the bottom of the support platform 2. The joint support arm 4 includes a first support arm 40, a second support arm 41, and a screen support arm 42. One end of the first support arm 40 is slidably connected to the second support arm 41, and the other end of the first support arm 40 is fixedly connected to a console 5. The console 5 is provided with a first screen 6. The second support arm 41 and the screen support arm 42 are slidably connected, and the screen support arm 42 is fixedly connected to a second screen 7. The six-axis robotic arm 8 includes a robotic arm body 80, a connecting block 81, and a laser 82. One end of the connecting block 81 is connected to the robotic arm body 80, and the other end of the connecting block 81 is fixedly connected to the laser 82.

[0058] Specifically, the support platform 2, as the core load-bearing component, provides a stable working environment for the heat dissipation module 3, the articulated support arm 4, and the six-axis robotic arm 8. Furthermore, the base 1 with casters at the bottom of the support platform 2 allows the entire ultrapulse thulium fiber laser therapy machine to move freely, adapting to the positional adjustment needs of different treatment scenarios. The heat dissipation module 3 is fixed to the side of the support platform 2, saving space and providing structural support for the adaptive air-cooling intelligent adjustment. The integrated heat dissipation control module within the heat dissipation module 3 combines autonomous control with heat dissipation functions, thereby monitoring the output power of the laser 82 of the six-axis robotic arm 8 in real time. During operation of the ultrapulse thulium fiber laser therapy machine, the high-power laser output generates a large amount of heat. If this heat accumulates on the support platform 2 and cannot be dissipated in time, it will not only lead to a decrease in the stability and accuracy of the laser output but also accelerate the aging and damage of the internal circuitry and optical components. The adaptive adjustment mechanism of the heat dissipation control module can accurately and efficiently match the heat dissipation intensity to ensure reliable heat dissipation. The articulated support arm 4 consists of a first support arm 40, a second support arm 41, and a screen support arm 42. The first support arm 40 and the second support arm 41 are slidably connected and can move along the Z-axis of space to accommodate operators of different heights. The second support arm 41 is slidably engaged with the screen support arm 42, allowing the second screen 7 to move along the Y-axis of space, ensuring the needs of different users. The control console 5 is fixedly connected to the first support arm 40, allowing its position to be flexibly adjusted to suit the operating habits of different users. The control console 5 integrates operation buttons and knobs, which can convert human operation into corresponding power control in real time. The first screen 6 is responsible for displaying operation parameters in real time, while the second screen 7 expands the display space through the articulated support arm 4, and can present information such as laser images. The dual-screen setup of the first screen 6 and the second screen 7 not only enriches the information display dimensions but also avoids the risk of overlap between the operation process display and laser imaging, thereby improving the reliability of operation and observation. The six-axis robotic arm 8 possesses a high degree of freedom. Its main body 80 employs a multi-joint structure, providing freedom for the spatial movement of the laser 82. This allows the laser 82 to precisely reach various desired positions. One end of the connecting block 81 is connected to the robotic arm body 80, while the other end is fixedly connected to the laser 82. This ensures the flexibility of the robotic arm body 80's movement while shortening the transmission path of the laser 82, improving the accuracy and stability of laser positioning. The adaptive heat dissipation module 3 can adjust the air-cooling speed in real time according to the output power to quickly dissipate heat, ensuring that the laser 82 and other components are at a suitable operating temperature, reducing the risk of treatment device malfunctions due to high temperatures.

[0059] See Figure 3As shown, in some embodiments of this application, the heat dissipation control module includes: a data acquisition and analysis unit configured to acquire the output power of the laser, compare the output power with a historical heat dissipation dataset, and determine whether to execute a heat dissipation control strategy or a heat dissipation prediction strategy based on the comparison results; a heat dissipation analysis unit configured to, when it is determined that a heat dissipation control strategy should be executed, determine the air cooling speed based on the number of times the output power appears in the historical heat dissipation dataset, or determine the air cooling speed based on the output power and a clustering algorithm; when it is determined that a heat dissipation prediction strategy should be executed, determine the air cooling speed based on the output power and a heat dissipation prediction model; a heat dissipation processing unit configured to acquire real-time images and heat dissipation efficiency of the heat dissipation module, and when the heat dissipation efficiency does not meet the heat dissipation requirements, perform dust identification based on the real-time images, determine a first heat dissipation adjustment coefficient, and determine a second heat dissipation adjustment coefficient based on a heat dissipation dust model; and a heat dissipation adjustment unit configured to, based on the first and second heat dissipation adjustment coefficients, determine a target heat dissipation adjustment coefficient, adjust the air cooling speed according to the target heat dissipation adjustment coefficient, and perform heat dissipation at the adjusted air cooling speed.

[0060] Specifically, the acquisition and analysis unit obtains the laser's output power in real time and compares the current output power with historical heat dissipation datasets. These historical datasets contain records of operating conditions at different output powers and corresponding air-cooling speeds. By comparing the data, the acquisition and analysis unit determines whether the current output power represents a frequently encountered, routine situation (i.e., output power that appears frequently in historical data) or a rare, special situation (i.e., output power that appears very infrequently or for the first time in historical data). Based on this, it determines whether to implement a heat dissipation control strategy or a heat dissipation prediction strategy. When a heat dissipation control strategy is determined, the heat dissipation analysis unit initiates two methods to determine the air cooling speed for typical scenarios. First, it counts the frequency of the output power in historical heat dissipation datasets; if the frequency is high, it directly retrieves historical records of the corresponding air cooling speed for that output power. Second, it uses a clustering algorithm to group samples with similar output power from historical data into a single category. By calculating the typical heat dissipation requirements of this category, it generates an appropriate air cooling speed to address scenarios with similar heat dissipation needs under the same output power. When a heat dissipation prediction strategy is determined, indicating a more specific output power, the heat dissipation analysis unit calls a pre-trained heat dissipation prediction model. This model integrates multi-dimensional data such as output power changes and device runtime, enabling it to predict heat dissipation needs based on the current output power and thus determine the appropriate air cooling speed. The heat dissipation processing unit performs real-time monitoring, continuously acquiring real-time images of the heat dissipation module (for observing fan status) and heat dissipation efficiency. If the heat dissipation efficiency is found to be insufficient to meet the heat dissipation requirements, meaning the heat dissipation speed cannot keep up with the heat generation rate of the laser, it indicates that the current air-cooling speed cannot meet the heat dissipation needs. This suggests that there is a certain amount of dust in the heat dissipation module, thus hindering the heat dissipation effect. By analyzing the amount of dust in the real-time image, a first heat dissipation adjustment coefficient is determined to compensate for the dust's obstruction of heat dissipation. Simultaneously, a heat dissipation dust model is invoked. Based on the heat dissipation attenuation law under different dust conditions, a second heat dissipation adjustment coefficient corresponding to the current dust situation is determined. The heat dissipation adjustment unit combines the first and second heat dissipation adjustment coefficients to obtain a target heat dissipation adjustment coefficient to compensate for the dust's influence. Then, based on the target heat dissipation adjustment coefficient, the previously determined air-cooling speed is dynamically adjusted so that the adjusted air-cooling speed can both meet the heat dissipation requirements under the current output power and offset the heat dissipation loss caused by dust, ultimately achieving stable and efficient heat dissipation.

[0061] Understandably, the heat dissipation control module achieves precise classification of heat dissipation scenarios, avoiding a "one-size-fits-all" heat dissipation strategy. By combining historical data, clustering algorithms, and heat dissipation prediction models, it enables the air cooling speed under different output power scenarios to match the actual heat dissipation requirements, forming a closed-loop feedback mechanism of power sensing, strategy selection, basic adjustment, and dynamic correction. This ensures the reliability of components at suitable temperatures, thereby avoiding laser instability, reducing aging and damage caused by high temperatures, avoiding the blindness of human experience settings, and ultimately achieving intelligent control of heat dissipation.

[0062] In some embodiments of this application, when comparing the output power in a historical heat dissipation dataset and determining whether to execute a heat dissipation control strategy or a heat dissipation prediction strategy based on the comparison results, the following steps are taken: the historical heat dissipation dataset includes several historical output powers and several historical air-cooling speeds, and each historical output power corresponds to a historical air-cooling speed. When there is a historical output power in the historical heat dissipation dataset that is the same as the output power, it is determined to execute a heat dissipation control strategy; when there is no historical output power in the historical heat dissipation dataset that is the same as the output power, it is determined to execute a heat dissipation prediction strategy.

[0063] In some embodiments of this application, when it is determined that a heat dissipation control strategy is to be executed, the air cooling speed is determined based on the number of times the output power appears in the historical heat dissipation dataset, or the air cooling speed is determined based on the output power and a clustering algorithm, including: when the number of times the historical output power with the same output power appears in the historical heat dissipation dataset is greater than or equal to 3, the average of the historical air cooling speeds corresponding to each historical output power with the same output power is determined as the air cooling speed; when the number of times the historical output power with the same output power appears in the historical heat dissipation dataset is less than 3, the air cooling speed is determined based on the output power and a clustering algorithm.

[0064] Specifically, the data acquisition and analysis unit compares the output power with historical output power in the historical heat dissipation dataset one by one. If the same historical output power exists, it means that the output power has occurred in past operations and there is reference heat dissipation data. Therefore, the heat dissipation control strategy is executed. If the same historical output power does not exist, it means that the output power has encountered a completely new situation and lacks directly corresponding historical heat dissipation data. In this case, the heat dissipation prediction strategy is executed. When executing the heat dissipation control strategy, if the number of times the historical output power that is the same as the current output power in the historical heat dissipation dataset is greater than or equal to 3, it means that there are enough historical heat dissipation records for this output power. The average of the historical air-cooling speeds corresponding to these historical output powers is then taken as the current air-cooling speed to balance the random fluctuations in multiple data sets. If the number of occurrences is less than 3, it means that there is insufficient directly referenced historical data. Therefore, based on the output power, a clustering algorithm is used to group the historical output power values ​​that are similar in value to those in the historical heat dissipation dataset into one category. The air-cooling speed is determined by analyzing the commonalities in the heat dissipation requirements of this category to compensate for the lack of data. When there are enough historical output powers, recording the average of historical air-cooling speeds multiple times can more stably reflect the heat dissipation requirements under that output power, avoiding the bias of single data. When there is insufficient historical data, clustering algorithms use the heat dissipation patterns of similar output power scenarios to provide a reliable reference, avoiding inaccurate heat dissipation due to data scarcity, thus ensuring the reliability and consistency of the heat dissipation process. Through data-driven automated adjustment, the reliance on human experience and intuition is reduced, and the uncertainty and operational risks caused by human judgment are lowered, thereby improving the level of automation in heat dissipation and ensuring the stability of the use of the ultrapulse thulium fiber laser therapy machine.

[0065] In some embodiments of this application, when determining the air-cooling speed based on output power and clustering algorithm, the method includes: taking the output power and historical heat dissipation dataset as the dataset to be clustered, extracting the historical air-cooling speed corresponding to each historical output power in the dataset to be clustered, determining the expected number of clusters k as 2, initializing the parameters of the Gaussian distribution, determining the probability that each data in the dataset to be clustered belongs to each Gaussian distribution to determine the responsibility value, determining the clustering dataset corresponding to the output power based on the responsibility value, and determining the mean of the historical air-cooling speed in the clustering dataset as the air-cooling speed.

[0066] Specifically, by analyzing historical heat dissipation datasets using clustering algorithms, the cluster datasets that are closest to the output power conditions are found, which improves the accuracy of determining the air-cooling speed. The dynamic adjustment mechanism based on output power ensures that the air-cooling speed can be adaptively determined under different power conditions, thereby maintaining the stability and efficiency of the ultrapulse thulium fiber laser therapy machine, reducing reliance on human experience and judgment, reducing human error, and improving the overall level of automation and reliability.

[0067] In some embodiments of this application, when it is determined that a heat dissipation prediction strategy is to be executed, the air-cooling speed is determined based on the output power and the heat dissipation prediction model, including: obtaining the operating dataset of the ultrapulse thulium fiber laser therapy machine, merging the historical heat dissipation dataset and the operating dataset to determine the model dataset, dividing the model dataset into a model training set and a model test set, training the random forest model based on the model training set, and testing the trained random forest model based on the model test set, and finally determining the heat dissipation prediction model with the output power as the input and the air-cooling speed as the output.

[0068] Specifically, when it is determined that a heat dissipation prediction strategy should be implemented, the first step is to obtain the operational dataset of the ultrapulse thulium fiber laser therapy machine. This dataset contains various parameters during operation, including runtime, motor temperature of the six-axis robotic arm, movement frequency of the six-axis robotic arm, and movement amplitude of the six-axis robotic arm. Then, the historical heat dissipation dataset is merged with the operational dataset to form a model dataset encompassing multi-dimensional information. Subsequently, the model dataset is divided into a training set and a test set, typically in a 7:3 ratio, to ensure the model's generalization ability. The training set is used for parameter learning, while the test set is used to verify the model's prediction performance. The random forest model has the ability to handle complex nonlinear relationships and can effectively uncover the potential patterns between output power and air-cooling speed. While learning these patterns, the random forest model uses a set of... By constructing multiple decision trees, overfitting to the training data is effectively avoided, ensuring adaptability to new data. The random forest model is trained on the model training set, and then tested on the model test set to evaluate its metrics, including accuracy, recall, and F1 score. After repeated adjustments and optimizations, a heat dissipation prediction model with output power as input and air-cooling speed as output is finally determined. This effectively avoids errors caused by human experience in setting parameters. When a new output power is encountered, inputting it into the heat dissipation prediction model yields the corresponding air-cooling speed, avoiding the risk of unstable laser output or component damage due to insufficient heat dissipation. At the same time, the learning ability of the random forest model and the support of multi-dimensional data improve the reliability of predictions and enhance the intelligent level of heat dissipation control in the ultrapulse thulium fiber laser therapy machine.

[0069] In some embodiments of this application, when the heat dissipation efficiency does not meet the heat dissipation requirements, the method includes: obtaining the heat dissipation efficiency of the heat dissipation module per unit time, and obtaining the historical average heat dissipation efficiency of the heat dissipation module. When the heat dissipation efficiency is greater than or equal to the historical average heat dissipation efficiency, it is determined that the heat dissipation requirements are met, and heat dissipation is performed at the current air cooling speed. When the heat dissipation efficiency is less than the historical average heat dissipation efficiency, it is determined that the heat dissipation requirements are not met.

[0070] Specifically, the heat dissipation unit obtains the actual heat dissipation efficiency of the heat dissipation module per unit time. The unit time is dynamically determined based on the required operating time of the ultrapulse thulium fiber laser therapy machine. This embodiment does not impose a specific limitation. The heat dissipation efficiency refers to the ratio of the heat removed from the ultrapulse thulium fiber laser therapy machine per unit time to the heat generated in the same time. Most of the generated heat comes from the laser, so the generated heat is determined as the heat output of the laser. Furthermore, the average historical heat dissipation efficiency of the heat dissipation module during past operation is retrieved, and the currently obtained heat dissipation efficiency is compared with the historical average heat dissipation efficiency. If the current heat dissipation efficiency is greater than or equal to the historical average heat dissipation efficiency, it indicates that the current heat dissipation efficiency of the heat dissipation module is good. The thermal capacity is sufficient to meet the current heat generation requirements of the ultrapulse thulium fiber laser therapy machine. Therefore, it is determined that the heat dissipation requirements are met, and the current air-cooling speed is maintained to continue heat dissipation. If the current heat dissipation efficiency is less than the historical average heat dissipation efficiency, it indicates that the heat dissipation capacity of the current heat dissipation module is lower than the past level and cannot effectively dissipate the heat generated by the ultrapulse thulium fiber laser therapy machine. It is difficult to match the current heat dissipation requirements, so it is determined that the heat dissipation requirements are not met. The historical average heat dissipation efficiency is used as an objective and reliable judgment benchmark, avoiding errors caused by human subjective judgment, reducing the risk of decreased laser output stability and component damage due to insufficient heat dissipation, and effectively adapting to the real-time heat dissipation requirements of the ultrapulse thulium fiber laser therapy machine.

[0071] In some embodiments of this application, when the heat dissipation efficiency does not meet the heat dissipation requirements, dust identification is performed based on real-time images to determine a first heat dissipation adjustment coefficient, and a second heat dissipation adjustment coefficient is determined based on a heat dissipation dust model. This includes: acquiring a standard real-time image corresponding to the real-time image; extracting all dust pixels to be identified from the real-time image; extracting standard pixels corresponding to each dust pixel to be identified from the standard real-time image; determining the dust pixel values ​​to be identified for all dust pixels to be identified; determining the standard pixel values ​​corresponding to all standard pixels; deleting dust pixels whose dust pixel values ​​are equal to the standard pixel values; identifying the remaining dust pixels to be identified as dust pixels; determining the first heat dissipation adjustment coefficient based on the dust pixels; pre-training a Siamese neural network model; determining the trained Siamese neural network model as a heat dissipation dust model; and determining the second heat dissipation adjustment coefficient based on the real-time image and the heat dissipation dust model.

[0072] Specifically, a standard real-time image corresponding to the current real-time image is acquired. The standard real-time image is an image of the heat dissipation module without dust adhesion, and the shooting angle is the same as the real-time image. The standard real-time image can be obtained through factory testing or taking photos in a cleanroom. All dust pixels to be identified are extracted from the real-time image. These dust pixels may represent dust. Standard pixels corresponding one-to-one with the positions of these dust pixels to be identified are extracted from the standard real-time image. The dust pixel value to be identified for each dust pixel to be identified and the standard pixel value for each standard pixel are determined. Dust pixels whose dust pixel value is the same as the corresponding standard pixel value are deleted. These dust pixels have no dust difference and are not real dust. The remaining dust pixels are the dust pixels that truly reflect the dust adhesion situation. Finally, the first heat dissipation adjustment coefficient is determined based on the number of dust pixels. When determining the second heat dissipation adjustment coefficient, a Siamese neural network model is pre-trained using a large number of image samples of the heat dissipation module under different dust conditions and parameters of fan speed attenuation. The parameters of fan speed attenuation include the set first heat dissipation adjustment coefficient and fan shaft noise. The training process is consistent with that of the random forest model and will not be repeated here. Finally, the Siamese neural network model that has been trained and meets the accuracy requirements is determined as the heat dissipation dust model. Real-time images of the current heat dissipation module are input into the heat dissipation dust model, and the model outputs the corresponding second heat dissipation adjustment coefficient by comparing the dust features in the image with the training samples. The first heat dissipation adjustment coefficient is determined by comparing the real-time image with a standard real-time image, effectively eliminating interference factors such as the texture of the heat dissipation module's own structure, thus avoiding misjudgment that could lead to deviations in the first heat dissipation adjustment coefficient. The Siamese neural network model has powerful image feature extraction and comparison capabilities, capable of capturing subtle dust distribution and accumulation density features that are difficult to identify manually or through simple pixel comparison. This allows the second heat dissipation adjustment coefficient to accurately reflect the actual impact of dust on heat dissipation efficiency, effectively compensating for the limitations of single-pixel comparison and recognition.

[0073] In some embodiments of this application, determining the first heat dissipation adjustment coefficient based on dust pixels includes: determining the number of dust pixels, and presetting a first preset number of pixels and a second preset number of pixels, wherein the first preset number of pixels is greater than the second preset number of pixels; presetting a first preset heat dissipation adjustment coefficient, a second preset heat dissipation adjustment coefficient, and a third preset heat dissipation adjustment coefficient, wherein the first preset heat dissipation adjustment coefficient is greater than the second preset heat dissipation adjustment coefficient, and the second preset heat dissipation adjustment coefficient is greater than the third preset heat dissipation adjustment coefficient; when the number of pixels is greater than the first preset number of pixels, the first preset heat dissipation adjustment coefficient is determined as the first heat dissipation adjustment coefficient; when the number of pixels is less than or equal to the first preset number of pixels and greater than or equal to the second preset number of pixels, the second preset heat dissipation adjustment coefficient is determined as the first heat dissipation adjustment coefficient; when the number of pixels is less than the second preset number of pixels, the third preset heat dissipation adjustment coefficient is determined as the first heat dissipation adjustment coefficient.

[0074] Specifically, the total number of dust pixels that accurately reflect dust adhesion after screening is counted, i.e., the number of pixels. At the same time, two preset pixel number standards are set to classify the degree of dust accumulation: the first preset pixel number and the second preset pixel number. The actual number of pixels is compared with the two preset pixel numbers. When the number of pixels exceeds the first preset pixel number, it indicates that there is a lot of dust accumulation on the surface of the heat dissipation module. In this case, the larger first preset heat dissipation adjustment coefficient is determined as the first heat dissipation adjustment coefficient. When the number of pixels does not exceed the first preset pixel number but reaches or exceeds the second preset pixel number, it indicates that the dust accumulation is at a medium level. In this case, the relatively lower second preset heat dissipation adjustment coefficient is determined as the first heat dissipation adjustment coefficient. When the number of pixels is lower than the second preset pixel number, it indicates that there is less dust accumulation. In this case, the smallest third preset heat dissipation adjustment coefficient is determined as the first heat dissipation adjustment coefficient. The number of pixels directly corresponds to the degree of dust accumulation on the surface of the heat dissipation module. The more dust there is, the more severely it will hinder the heat exchange between the heat dissipation module and the outside world, resulting in a more significant decrease in heat dissipation efficiency. Therefore, a larger first heat dissipation adjustment coefficient is needed to compensate for the loss. This avoids the risk of being unable to compensate for heat dissipation loss due to excessive dust, and also avoids the energy waste caused by over-adjustment when there is less dust, further ensuring the working reliability of the ultrapulse thulium fiber laser therapy machine.

[0075] In some embodiments of this application, when determining a target heat dissipation adjustment coefficient based on a first heat dissipation adjustment coefficient and a second heat dissipation adjustment coefficient, and adjusting the air cooling speed according to the target heat dissipation adjustment coefficient, the target heat dissipation adjustment coefficient is the average of the first heat dissipation adjustment coefficient and the second heat dissipation adjustment coefficient, and the air cooling speed is proportional to the target heat dissipation adjustment coefficient.

[0076] Specifically, the first heat dissipation adjustment coefficient is determined based on the number of pixels, focusing on reflecting the degree of dust accumulation. The second heat dissipation adjustment coefficient is derived from the heat dissipation dust model, effectively capturing the correlation between fine dust features and heat dissipation attenuation. The average value is used to determine the target heat dissipation adjustment coefficient, avoiding adjustment deviations caused by relying solely on a single heat dissipation adjustment coefficient, thus ensuring the stability of the heat dissipation module. The air cooling speed is adjusted according to the target heat dissipation adjustment coefficient. Assuming the air cooling speed is V and the target heat dissipation adjustment coefficient is P, the adjusted air cooling speed is determined to be V*P. By establishing a direct proportional relationship between the air cooling speed and the target heat dissipation adjustment coefficient, precise control of the air cooling speed is achieved during the heat dissipation control process. The adaptive air cooling adjustment and feedback mechanism ensures the heat dissipation reliability of the ultrapulse thulium fiber laser therapy machine.

[0077] In summary, the beneficial effects of this invention are as follows: Compared with the prior art, the base provides convenient mobility for the ultrapulse thulium fiber laser therapy machine, allowing for flexible adaptation to different medical scenarios. The support platform stably connects the heat dissipation module, the articulated support arm, and the six-axis robotic arm, providing a stable platform for the stable operation of each component. The articulated support arm and the six-axis robotic arm allow for free adjustment of the spatial positions of the first screen, the second screen, and the laser according to the user's operating habits and visual needs. The heat dissipation control module inside the heat dissipation module senses the laser's output power in real time, thereby dynamically adjusting the air-cooling intensity to precisely match the heat generation changes during ultrapulse thulium fiber laser operation. This avoids overheating caused by insufficient heat dissipation and prevents energy waste caused by excessive heat dissipation, achieving efficient and energy-saving heat dissipation management. Furthermore, adaptive air cooling ensures the accuracy and consistency of laser energy output, effectively reducing the risk of aging and damage to internal components due to high temperatures, reducing the maintenance frequency of the ultrapulse thulium fiber laser therapy machine, and thus ensuring work efficiency.

[0078] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program goods. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program goods embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program goods according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0080] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0081] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0082] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A superpulse thulium fiber laser therapy machine with adaptive air-cooling function, characterized in that, include: Support platform, heat dissipation module, articulated support arm and six-axis robotic arm; The heat dissipation module is fixedly connected to the side of the support platform, the joint support arm and the six-axis robotic arm are fixedly connected to the top of the support platform, a heat dissipation control module is installed inside the heat dissipation module, and a base is fixedly connected to the bottom of the support platform. The joint support arm includes a first support arm, a second support arm, and a screen support arm; One end of the first support arm is slidably connected to the second support arm, and the other end of the first support arm is fixedly connected to the console, which is equipped with a first screen. The second support arm and the screen support arm are slidably connected, and the screen support arm is fixedly connected to the second screen; The six-axis robotic arm includes a robotic arm body, a connecting block, and a laser; One end of the connecting block is connected to the robotic arm body, and the other end of the connecting block is fixedly connected to the laser. The heat dissipation control module includes: The acquisition and analysis unit is configured to acquire the output power of the laser, compare the output power with a historical heat dissipation dataset, and determine whether to execute a heat dissipation control strategy or a heat dissipation prediction strategy based on the comparison results. The heat dissipation analysis unit is configured to determine the air cooling speed based on the number of times the output power appears in the historical heat dissipation dataset when it is determined that the heat dissipation control strategy is to be executed, or to determine the air cooling speed based on the output power and a clustering algorithm; and to determine the air cooling speed based on the output power and a heat dissipation prediction model when it is determined that the heat dissipation prediction strategy is to be executed. The heat dissipation unit is configured to acquire real-time images and heat dissipation efficiency of the heat dissipation module. When the heat dissipation efficiency does not meet the heat dissipation requirements, it performs dust identification based on the real-time images, determines a first heat dissipation adjustment coefficient, and determines a second heat dissipation adjustment coefficient based on the heat dissipation dust model. The heat dissipation adjustment unit is configured to determine a target heat dissipation adjustment coefficient based on the first heat dissipation adjustment coefficient and the second heat dissipation adjustment coefficient, adjust the air cooling speed according to the target heat dissipation adjustment coefficient, and perform heat dissipation at the adjusted air cooling speed; When the heat dissipation efficiency does not meet the heat dissipation requirements, dust is identified based on the real-time image to determine a first heat dissipation adjustment coefficient, and a second heat dissipation adjustment coefficient is determined based on the heat dissipation dust model, including: Obtain a standard real-time image corresponding to the real-time image; Extract all the dust pixels to be identified from the real-time image, and extract the standard pixels corresponding to each dust pixel to be identified from the standard real-time image; Determine the dust pixel value corresponding to all dust pixels to be identified, and determine the standard pixel value corresponding to all standard pixels; Delete the dust pixels whose dust pixel value is equal to the standard pixel value, and determine the remaining dust pixels as dust pixels. Determine the first heat dissipation adjustment coefficient based on the dust pixels. A twin neural network model is pre-trained, and the trained twin neural network model is determined as the heat dissipation dust model. The second heat dissipation adjustment coefficient is determined based on the real-time image and the heat dissipation dust model.

2. The ultrapulse thulium fiber laser therapy machine with adaptive air-cooling function according to claim 1, characterized in that, When comparing the output power with historical heat dissipation datasets and determining whether to implement a heat dissipation control strategy or a heat dissipation prediction strategy based on the comparison results, the following steps are included: The historical heat dissipation dataset includes several historical output powers and several historical air-cooling speeds, with each historical output power corresponding to a historical air-cooling speed. If the historical heat dissipation dataset contains a historical output power that is the same as the output power, then the heat dissipation control strategy is determined to be executed. If there is no historical output power in the historical heat dissipation dataset that is the same as the output power, then the heat dissipation prediction strategy will be executed.

3. The ultrapulse thulium fiber laser therapy machine with adaptive air-cooling function according to claim 2, characterized in that, When it is determined that the heat dissipation control strategy should be executed, the air cooling speed is determined based on the number of times the output power appears in the historical heat dissipation dataset, or, when determining the air cooling speed based on the output power and a clustering algorithm, the following methods are included: When the number of occurrences of the same historical output power as the output power in the historical heat dissipation data is greater than or equal to 3, the average of the historical air-cooling speeds corresponding to the same historical output power is determined as the air-cooling speed. If the number of occurrences of the same historical output power as the output power in the historical heat dissipation dataset is less than 3, then the air-cooling speed is determined based on the output power and the clustering algorithm.

4. The ultrapulse thulium fiber laser therapy machine with adaptive air-cooling function according to claim 3, characterized in that, When determining the air-cooled rotation speed based on the output power and clustering algorithm, the following steps are included: The output power and the historical heat dissipation dataset are used as the dataset to be clustered. The historical air-cooling speed corresponding to each historical output power in the dataset to be clustered is extracted, and the expected number of clusters k is determined to be 2. The parameters of the Gaussian distribution are initialized, and the probability of each data in the dataset to be clustered belonging to each Gaussian distribution is determined to determine the responsibility value. Based on the responsibility value, the clustering dataset corresponding to the output power is determined. The average historical air-cooling speed in the clustered dataset is determined as the air-cooling speed.

5. The ultrapulse thulium fiber laser therapy machine with adaptive air-cooling function according to claim 4, characterized in that, When it is determined that the heat dissipation prediction strategy should be executed, the air-cooled rotation speed is determined based on the output power and the heat dissipation prediction model, including: Obtain the operational dataset of the ultrapulse thulium fiber laser therapy machine, and merge the historical heat dissipation dataset and the operational dataset to determine the model dataset; The model dataset is divided into a model training set and a model test set; The random forest model is trained based on the model training set, and the trained random forest model is tested based on the model test set. Finally, a heat dissipation prediction model with the input as output power and the output as air-cooled speed is determined.

6. The ultrapulse thulium fiber laser therapy machine with adaptive air-cooling function according to claim 5, characterized in that, When the heat dissipation efficiency does not meet the heat dissipation requirements, including: Obtain the heat dissipation efficiency of the heat dissipation module per unit time, and obtain the historical average heat dissipation efficiency of the heat dissipation module; When the heat dissipation efficiency is greater than or equal to the historical average heat dissipation efficiency, it is determined that the heat dissipation requirement is met, and heat dissipation is performed at the current air cooling speed. If the heat dissipation efficiency is less than the historical average heat dissipation efficiency, then the heat dissipation requirement is not met.

7. The ultrapulse thulium fiber laser therapy machine with adaptive air-cooling function according to claim 6, characterized in that, Determining the first heat dissipation adjustment coefficient based on the dust pixels includes: The number of pixels of the dust pixels is determined, and a first preset number of pixels and a second preset number of pixels are preset, wherein the first preset number of pixels is greater than the second preset number of pixels; A first preset heat dissipation adjustment coefficient, a second preset heat dissipation adjustment coefficient, and a third preset heat dissipation adjustment coefficient are preset, wherein the first preset heat dissipation adjustment coefficient is greater than the second preset heat dissipation adjustment coefficient, and the second preset heat dissipation adjustment coefficient is greater than the third preset heat dissipation adjustment coefficient; When the number of pixels is greater than the number of first preset pixels, the first preset heat dissipation adjustment coefficient is determined as the first heat dissipation adjustment coefficient. When the number of pixels is less than or equal to the first preset number of pixels and greater than or equal to the second preset number of pixels, the second preset heat dissipation adjustment coefficient is determined as the first heat dissipation adjustment coefficient. When the number of pixels is less than the second preset number of pixels, the third preset heat dissipation adjustment coefficient is determined as the first heat dissipation adjustment coefficient.

8. The ultrapulse thulium fiber laser therapy machine with adaptive air-cooling function according to claim 7, characterized in that, When determining a target heat dissipation adjustment coefficient based on the first heat dissipation adjustment coefficient and the second heat dissipation adjustment coefficient, and adjusting the air-cooling speed according to the target heat dissipation adjustment coefficient, the process includes: The target heat dissipation adjustment coefficient is the average of the first heat dissipation adjustment coefficient and the second heat dissipation adjustment coefficient, and the air cooling speed is directly proportional to the target heat dissipation adjustment coefficient.

Images