Servo driver heat dissipation method and system based on artificial intelligence

Abstract

The invention provides a heat dissipation method and system for a servo driver based on artificial intelligence, and relates to the technical field of equipment heat dissipation, and the method comprises the steps: determining a plurality of initial heat dissipation installation points based on an infrared working video of the servo driver; determining a heat dissipation effect score of each point based on the infrared working video after the initial installation point is installed; determining multiple sets of subsequent heat dissipation mounting point schemes based on the heat dissipation effect score of each point and the infrared working video after the initial mounting point is mounted; based on the infrared working video of the servo driver, the infrared working video after the initial mounting point is mounted and the multiple sets of subsequent heat dissipation mounting point schemes, using a generation model to generate multiple sets of subsequent simulated infrared working videos; determining a target installation point scheme based on the plurality of sets of subsequent simulated infrared working videos; the heat dissipation equipment is installed based on the target installation point scheme, heat dissipation control is carried out based on the installed heat dissipation equipment, and the method can quickly and accurately determine the target installation scheme of the heat dissipation equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment heat dissipation, and particularly relates to a heat dissipation method and system for a servo driver based on artificial intelligence. Background Art

[0002] In modern industrial automation, servo drivers are key devices for precision motion control and are widely used in scenarios such as numerical control machine tools and robots. As industry develops towards high precision, high speed, and high load, the power density of servo drivers increases, and the heat generated during operation increases significantly. If effective heat dissipation is not carried out in a timely manner, the excessive temperature will cause the performance of internal electronic components to decrease, the service life to be shortened, and even faults to occur, thus seriously affecting the operation of the equipment and production efficiency. Traditional heat dissipation methods for servo drivers are mostly designed based on experience, such as simply increasing the area of heat sinks or installing fans. This method cannot accurately analyze the actual operating heat distribution and is difficult to adapt to complex working environments. There may be insufficient heat dissipation, resulting in local overheating and affecting the equipment performance; or there may be excessive heat dissipation, causing energy waste and cost increase. Although some advanced heat dissipation technologies have been applied, in the field of servo driver heat dissipation, the existing technologies are difficult to comprehensively consider the changes in heat characteristics under different working conditions and lack accurate and intelligent planning of heat dissipation installation points and installation schemes.

[0003] Therefore, how to quickly and accurately determine the target installation scheme of the heat dissipation equipment is an urgent problem to be solved at present. Summary of the Invention

[0004] The main technical problem to be solved by the present invention is how to quickly and accurately determine the target installation scheme of the heat dissipation equipment.

[0005] According to a first aspect, the present invention provides a heat dissipation method for a servo driver based on artificial intelligence, including: obtaining an infrared working video of the servo driver; determining a plurality of initial heat dissipation installation points based on the infrared working video of the servo driver; obtaining an infrared working video after the initial installation points are installed; determining a heat dissipation effect score for each point based on the infrared working video after the initial installation points are installed; determining multiple sets of subsequent heat dissipation installation point schemes based on the heat dissipation effect score for each point and the infrared working video after the initial installation points are installed; generating multiple sets of subsequent simulated infrared working videos using a generation model based on the infrared working video of the servo driver, the infrared working video after the initial installation points are installed, and the multiple sets of subsequent heat dissipation installation point schemes; determining a target installation point scheme based on the multiple sets of subsequent simulated infrared working videos; installing a heat dissipation device based on the target installation point scheme, and performing heat dissipation control based on the installed heat dissipation device.

[0006] In a possible implementation, the method for determining the target installation point solution based on the multiple sets of subsequent simulated infrared working videos includes: determining multiple excellent heat dissipation points and a set of excellent subsequent heat dissipation installation point solutions based on the multiple sets of subsequent simulated infrared working videos; generating multiple sets of excellent preliminary solutions based on the multiple excellent heat dissipation points and the set of excellent subsequent heat dissipation installation point solutions; constructing a knowledge graph, where each knowledge graph includes multiple excellent preliminary solution nodes and multiple edges between the nodes, and the node features of each excellent preliminary solution node include a set of excellent preliminary solutions and the simulated infrared working videos of a set of excellent preliminary solutions, and the edges between the nodes represent the similarity between the excellent preliminary solutions; and determining the target installation point solution by processing the knowledge graph based on a graph neural network.

[0007] In a possible implementation, the target installation point solution is one of the multiple sets of excellent preliminary solutions.

[0008] In a possible implementation, the generation model is a generative adversarial network.

[0009] According to a second aspect, the present invention provides a heat dissipation system for a servo drive based on artificial intelligence, including: a first acquisition module for acquiring the infrared working video of the servo drive;

[0010] An initial heat dissipation point determination module for determining multiple initial heat dissipation installation points based on the infrared working video of the servo drive;

[0011] A second acquisition module for acquiring the infrared working video after the initial installation points are installed;

[0012] A scoring module for determining the heat dissipation effect score of each point based on the infrared working video after the initial installation points are installed;

[0013] A subsequent solution determination module for determining multiple sets of subsequent heat dissipation installation point solutions based on the heat dissipation effect score of each point and the infrared working video after the initial installation points are installed;

[0014] A simulated video generation module for generating multiple sets of subsequent simulated infrared working videos using a generation model based on the infrared working video of the servo drive, the infrared working video after the initial installation points are installed, and the multiple sets of subsequent heat dissipation installation point solutions;

[0015] A target solution determination module for determining the target installation point solution based on the multiple sets of subsequent simulated infrared working videos;

[0016] A heat dissipation execution module for installing heat dissipation devices based on the target installation point solution and performing heat dissipation control based on the installed heat dissipation devices.

[0017] In a possible implementation, the target solution determination module is further configured to: determine a plurality of excellent heat dissipation points and a set of excellent subsequent heat dissipation installation point solutions based on the multiple sets of subsequent simulated infrared working videos; generate multiple sets of excellent preliminary solutions based on the plurality of excellent heat dissipation points and the set of excellent subsequent heat dissipation installation point solutions; construct a knowledge graph, each knowledge graph includes a plurality of excellent preliminary solution nodes and multiple edges between the nodes, and the node features of each excellent preliminary solution node include a set of excellent preliminary solutions and the simulated infrared working videos of a set of excellent preliminary solutions, and the edges between the nodes represent the similarity between the excellent preliminary solutions; determine the target installation point solution by processing the knowledge graph based on a graph neural network.

[0018] In a possible implementation, the target installation point solution is one of the multiple sets of excellent preliminary solutions.

[0019] In a possible implementation, the generation model is a generative adversarial network.

[0020] According to a third aspect, an embodiment of the present invention provides an electronic device, including: a processor; a memory; and a computer program; wherein, the computer program is stored in the memory and is configured to be executed by the processor to implement the method as described above. The method includes: obtaining an infrared working video of a servo driver; determining a plurality of initial heat dissipation installation points based on the infrared working video of the servo driver; obtaining the infrared working video after the initial installation points are installed; determining the heat dissipation effect score of each point based on the infrared working video after the initial installation points are installed; determining multiple sets of subsequent heat dissipation installation point solutions based on the heat dissipation effect score of each point and the infrared working video after the initial installation points are installed; generating multiple sets of subsequent simulated infrared working videos using a generation model based on the infrared working video of the servo driver, the infrared working video after the initial installation points are installed, and the multiple sets of subsequent heat dissipation installation point solutions; determining the target installation point solution based on the multiple sets of subsequent simulated infrared working videos; installing a heat dissipation device based on the target installation point solution, and performing heat dissipation control based on the installed heat dissipation device.

[0021] According to a fourth aspect, the present embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the aforementioned heat dissipation method for an artificial intelligence-based servo driver. The method includes: obtaining an infrared working video of the servo driver; determining a plurality of initial heat dissipation installation points based on the infrared working video of the servo driver; obtaining an infrared working video after the initial installation points are installed; determining a heat dissipation effect score for each point based on the infrared working video after the initial installation points are installed; determining multiple sets of subsequent heat dissipation installation point schemes based on the heat dissipation effect score for each point and the infrared working video after the initial installation points are installed; generating multiple sets of subsequent simulated infrared working videos using a generation model based on the infrared working video of the servo driver, the infrared working video after the initial installation points are installed, and the multiple sets of subsequent heat dissipation installation point schemes; determining a target installation point scheme based on the multiple sets of subsequent simulated infrared working videos; installing a heat dissipation device based on the target installation point scheme, and performing heat dissipation control based on the installed heat dissipation device.

[0022] A heat dissipation method and system for an artificial intelligence-based servo driver provided by the present invention. The method includes: obtaining an infrared working video of the servo driver; determining a plurality of initial heat dissipation installation points based on the infrared working video of the servo driver; obtaining an infrared working video after the initial installation points are installed; determining a heat dissipation effect score for each point based on the infrared working video after the initial installation points are installed; determining multiple sets of subsequent heat dissipation installation point schemes based on the heat dissipation effect score for each point and the infrared working video after the initial installation points are installed; generating multiple sets of subsequent simulated infrared working videos using a generation model based on the infrared working video of the servo driver, the infrared working video after the initial installation points are installed, and the multiple sets of subsequent heat dissipation installation point schemes; determining a target installation point scheme based on the multiple sets of subsequent simulated infrared working videos; installing a heat dissipation device based on the target installation point scheme, and performing heat dissipation control based on the installed heat dissipation device. This method can quickly and accurately determine the target installation scheme of the heat dissipation device. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic flowchart of a heat dissipation method for an artificial intelligence-based servo driver provided by an embodiment of the present invention;

[0024] Figure 2 It is a schematic flowchart of a process for determining a target installation point scheme provided by an embodiment of the present invention;

[0025] Figure 3 It is a schematic diagram of a heat dissipation system for an artificial intelligence-based servo driver provided by an embodiment of the present invention; DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] The present invention will be further described in detail below in conjunction with the specific embodiments and the accompanying drawings. Similar elements in different embodiments are denoted by related similar element numbers. In the following embodiments, many detailed descriptions are provided to enable a better understanding of the present invention. However, those skilled in the art can easily recognize that some of the features can be omitted in different situations, or can be replaced by other elements, materials, or methods. In some cases, some operations related to the present invention are not shown or described in the specification to avoid overwhelming the core part of the present invention with excessive descriptions. For those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations based on the descriptions in the specification and the general technical knowledge in the art.

[0027] In an embodiment of the present invention, there is provided a heat dissipation method for a servo drive based on artificial intelligence as shown in Figure 1 The heat dissipation method for the servo drive based on artificial intelligence includes steps S1 to S8:

[0028] Step S1, obtain an infrared working video of the servo drive.

[0029] A servo drive is a device for controlling a servo motor. The servo drive can precisely adjust the position, speed, and torque of the motor. In industrial automation production, the servo drive can provide power drive and motion control support for various devices that require precise motion control. It is a key component for achieving high-precision and high-speed motion in automated production.

[0030] The infrared working video is a video taken using infrared imaging technology to reflect the temperature distribution on the surface of the servo drive during operation. The infrared working video can visually present the thermal state of the servo drive during operation.

[0031] Step S2, determine a plurality of initial heat dissipation installation points based on the infrared working video of the servo drive.

[0032] In some embodiments, a plurality of initial heat dissipation installation points can be determined based on the infrared working video of the servo drive through an installation point analysis model. The installation point analysis model is a gated recurrent unit. The input of the installation point analysis model is the infrared working video of the servo drive, and the output of the installation point analysis model is a plurality of initial heat dissipation installation points.

[0033] The Gated Recurrent Unit (GRU) is an optimized recurrent neural network (RNN) structure. The GRU can solve the gradient vanishing and gradient exploding problems faced by traditional RNNs when processing sequence data. The GRU improves the flow and storage mechanism of information by introducing update gates and reset gates. It is widely used in many fields such as natural language processing and time series prediction. The GRU can handle long-term dependencies in sequence data and learn complex temporal feature patterns in the data.

[0034] The initial heat dissipation installation point is the preliminary installation position point of the heat dissipation device determined by the installation point analysis model based on the analysis of the servo drive infrared working video.

[0035] Heat dissipation devices can be used to reduce the heat generated by servo drives and other equipment during operation to ensure that they can operate stably at an appropriate temperature. Heat dissipation device types include heat sinks, cooling fans, etc. Heat dissipation devices can achieve heat dissipation through conduction, convection, radiation, etc.

[0036] The gated loop unit has a powerful ability to process time series data. The infrared working video is a sequence of images arranged in chronological order, which contains the temperature distribution information of the servo drive at different times, and this information has a temporal dependency. The gated loop unit can process video data frame by frame through the gating mechanism and effectively capture this temporal dependency. During the processing, the gated loop unit can remember the temperature change trend of key areas in early video frames, and will not lose key information due to the long sequence. For example, if the temperature of a certain area continues to rise in multiple frames of video, the gated loop unit can identify this trend. By learning the entire video sequence, the gated loop unit can analyze the areas prone to high temperatures from the dynamic process of temperature changes, and then determine multiple initial heat dissipation installation points.

[0037] In some embodiments, the installation point analysis model may include a temperature point analysis layer, a heat diffusion path analysis layer, and an installation point strategy generation layer. The input of the temperature point analysis layer is the infrared working video of the servo drive, and the output of the temperature point analysis layer is a high temperature point set, a low temperature point set, and a temperature distribution thermogram sequence. The input of the heat diffusion path analysis layer is a high temperature point set, a low temperature point set, and a temperature distribution thermogram sequence, and the output of the heat diffusion path analysis layer is a heat diffusion key path diagram, a thermal runaway risk point list, multiple high temperature area information, and multiple low temperature area information. The input of the installation point strategy generation layer is a heat diffusion key path diagram, a thermal runaway risk point list, multiple high temperature area information, and multiple low temperature area information, and the output of the installation point strategy generation layer is multiple initial heat dissipation installation points.

[0038] The high temperature point set is a set of coordinate points whose temperature exceeds a preset threshold value, so as to represent locations where the surface temperature of the servo drive is relatively high.

[0039] The set of low-temperature points is the set of coordinate points with temperatures lower than the preset threshold in the infrared working video, which reflects the positions on the surface of the servo drive with lower temperatures and better heat dissipation.

[0040] The sequence of heat distribution thermograms is a set of thermograms generated frame by frame, and presents the temperature distribution of each position on the surface of the servo drive with visual color shades. Each picture corresponds to a moment in the video.

[0041] The critical path diagram of heat diffusion is a schematic diagram formed by analyzing the movement trajectories of high-temperature points and connecting the main paths of heat propagation with arrows. The thickness of the arrows represents the intensity of heat diffusion.

[0042] The list of thermal runaway risk points is a list of coordinate points that are screened out in the heat diffusion path, continuously move in the opposite direction to the low-temperature area and the temperature continues to rise, thus there is a risk of overheating.

[0043] The information of multiple high-temperature areas is related information such as the boundaries and ranges of multiple higher-temperature areas delineated around the high-temperature point dense areas and the critical path of heat diffusion.

[0044] The information of multiple low-temperature areas is related information such as the boundaries and ranges of multiple lower-temperature areas divided according to the distribution of low-temperature points.

[0045] The temperature point analysis layer mainly extracts the set of high-temperature points and the set of low-temperature points from the infrared working video of the servo drive, and generates a sequence of heat distribution thermograms to complete the preliminary analysis and quantification of the temperature information in the video. The heat diffusion path analysis layer can construct a critical path diagram of heat diffusion to clarify the main channels of heat propagation, screen out the list of thermal runaway risk points to locate high-risk areas, and at the same time delimit the boundaries of high-temperature and low-temperature areas, so as to obtain the information of multiple high-temperature areas and the information of multiple low-temperature areas to achieve in-depth analysis of the dynamic diffusion and regional distribution of heat. The installation point strategy generation layer integrates the analysis results of the previous two layers, and finally can determine the initial heat dissipation installation points at the heat propagation hubs, risk points and weak positions within the high-temperature areas.

[0046] Through this hierarchical design, complex problems can be decomposed into three ordered steps: data extraction, path analysis, and solution decision-making, and the logic is clear and easy to understand and optimize. By such layering, it can also significantly improve the interpretability of the model while enhancing the scalability, thereby effectively improving the efficiency and accuracy of the system to confirm the heat dissipation installation points, as well as the stability of the system.

[0047] Step S3, obtain the infrared working video after the initial installation point is installed.

[0048] The infrared working video after the initial installation point is installed is a video that reflects the surface temperature distribution during its operation, obtained by infrared imaging technology after the heat dissipation device is installed at the initial installation point on the servo drive.

[0049] Step S4: Determine the heat dissipation effect score for each point based on the infrared working video after the initial installation point is installed.

[0050] In some embodiments, the heat dissipation score model can be used to determine the heat dissipation effect score for each point based on the infrared working video after the initial installation point is installed. The heat dissipation score model is a convolutional neural network model. The input of the heat dissipation score model is the infrared working video after the initial installation point is installed, and the output of the heat dissipation score model is the heat dissipation effect score for each point.

[0051] The convolutional neural network model includes a convolutional neural network. The convolutional neural network (CNN) is a deep learning model that is good at processing data with grid structures such as images and videos. The convolutional neural network is mainly composed of convolutional layers, pooling layers, and fully connected layers. The convolutional neural network can effectively reduce the model parameters by using the characteristics of weight sharing and local connection, thereby reducing the computational complexity. The convolutional neural network is widely used in fields such as image recognition and object detection.

[0052] The heat dissipation effect score is a numerical value obtained by quantitatively evaluating the heat dissipation ability of the heat dissipation device at the initial installation point through the heat dissipation score model. The role of the heat dissipation effect score is to convert the abstract heat dissipation effect into a specific numerical value to facilitate the comparison and analysis of the heat dissipation conditions at different initial installation points.

[0053] The convolutional neural network has a powerful image feature extraction ability, so it can determine the heat dissipation effect score for each point based on the infrared working video after the initial installation point is installed. The infrared working video is essentially a sequence of images. The convolutional neural network can automatically extract the spatial features of the temperature distribution in the video frame through the convolutional layer, such as the shape, size, position, and temperature gradient change of the hot spot area, and then map these features to the heat dissipation effect score by combining the pooling layer and the fully connected layer.

[0054] Step S5: Determine multiple sets of subsequent heat dissipation installation point schemes based on the heat dissipation effect score for each point and the infrared working video after the initial installation point is installed.

[0055] In some embodiments, a Transformer model can be used to determine multiple sets of subsequent heat dissipation installation point solutions based on the heat dissipation effect score of each point and the infrared working video after the initial installation point is installed. The input of the Transformer model is the heat dissipation effect score of each point and the infrared working video after the initial installation point is installed, and the output of the Transformer model is multiple sets of subsequent heat dissipation installation point solutions.

[0056] The Transformer model is a deep learning model architecture based on the attention mechanism. The Transformer model can focus on different parts of the input data at the same time through the multi-head attention mechanism and capture long-distance dependencies, thereby efficiently extracting data features. Widely used in natural language processing, computer vision and other fields, the Transformer model has powerful feature representation and modeling capabilities.

[0057] Multiple sets of subsequent heat dissipation installation point solutions are multiple installation solutions for heat dissipation equipment calculated by Transformer to further optimize heat dissipation.

[0058] The heat dissipation effect score and video data contain complex information. Through the multi-head attention mechanism, Transformer can flexibly weight the key features of these data and explore the intrinsic connection between the score and the temperature distribution and heat dissipation weak points in the video, so as to comprehensively formulate multiple sets of subsequent heat dissipation installation point plans to achieve the optimal design of the heat dissipation layout.

[0059] Step S6, generating multiple sets of subsequent simulated infrared working videos using a generation model based on the infrared working video of the servo drive, the infrared working video after the initial installation point is installed, and the multiple sets of subsequent heat dissipation installation point solutions.

[0060] The generative model is a generative adversarial network, the input of which is the infrared working video of the servo drive, the infrared working video after the initial installation point is installed, and the multiple sets of subsequent heat dissipation installation point solutions, and the output of the generative model is multiple sets of subsequent simulated infrared working videos.

[0061] Generative Adversarial Network (GAN) is a deep learning model composed of a generator and a discriminator. The generator is responsible for creating new data samples, and the discriminator can evaluate the authenticity of these samples. The two continuously improve their performance through adversarial training, which ultimately enables the generator to generate high-quality data.

[0062] The subsequent simulated infrared working video is a simulated video of the surface temperature distribution of the servo drive after adopting different subsequent heat dissipation installation point schemes, which is generated by a generative model. The subsequent simulated infrared working video can predict the heat dissipation effects after implementing multiple subsequent heat dissipation installation point schemes.

[0063] The generative adversarial network can extract real heat distribution data from the infrared working video of the servo drive and the infrared working video after the initial installation point is installed, and can learn the characteristics and laws of the temperature distribution in different states. Multiple subsequent heat dissipation installation point schemes are informed to the model as conditional information to generate corresponding results under different heat dissipation strategies. The generator can combine the features and laws learned by itself according to these input information to try to generate subsequent simulated infrared working videos that conform to different heat dissipation installation point schemes, and the discriminator can help the generator continuously adjust, so that the generator can generate more realistic and practical simulated videos.

[0064] Step S7, determine the target installation point scheme based on the multiple subsequent simulated infrared working videos.

[0065] In some embodiments, Figure 2 is a schematic flowchart of a process for determining a target installation point scheme provided by an embodiment of the present invention. The determining the target installation point scheme includes steps S21 to S24:

[0066] Step S21, determine multiple excellent heat dissipation points and a set of excellent subsequent heat dissipation installation point schemes based on the multiple subsequent simulated infrared working videos.

[0067] In some embodiments, multiple excellent heat dissipation points and a set of excellent subsequent heat dissipation installation point schemes can be determined based on the multiple subsequent simulated infrared working videos by a variational autoencoder. The input of the variational autoencoder is the multiple subsequent simulated infrared working videos, and the output of the variational autoencoder is multiple excellent heat dissipation points and a set of excellent subsequent heat dissipation installation point schemes.

[0068] The variational autoencoder (VAE) is a generative model that combines an autoencoder and variational inference. It consists of an encoder and a decoder. The encoder can map the input data to the probability distribution in the latent space. In this latent space, the variational autoencoder assumes that the data conforms to a certain probability distribution and samples through the reparameterization trick. The decoder can then restore the sampled latent vector to the original data. The unique feature of the variational autoencoder is that it focuses on learning the latent structure and distribution of the data and makes the latent space continuous and interpretable. Therefore, the variational autoencoder can be used for tasks such as data generation and feature extraction.

[0069] An excellent heat dissipation point is a location point on the surface of the servo drive that has been confirmed by a variational autoencoder to have significantly better heat dissipation effect than other areas.

[0070] A set of excellent subsequent heat dissipation installation point solutions is selected from multiple subsequent heat dissipation installation point solutions after comprehensively considering the heat dissipation effect, and can effectively improve the heat dissipation condition of the servo drive. A set of excellent subsequent heat dissipation installation point solutions defines the ideal installation method of heat dissipation equipment, and more reference-worthy heat dissipation installation point solutions can be determined based on this for expansion, deformation, or combination.

[0071] The variational autoencoder can learn the potential features of temperature distribution and heat dissipation effect in the subsequent simulated infrared working video. The encoder can map the video data to the latent space and capture key information such as temperature change patterns and hot spot distribution rules. Due to the continuity of the latent space, the variational autoencoder can analyze and compare samples in the latent space to find out the feature combinations corresponding to excellent heat dissipation effects. The decoder can restore the corresponding heat dissipation scenarios based on these feature combinations to determine multiple excellent heat dissipation points. At the same time, by comprehensively considering the heat dissipation installation point solutions and their effects represented by different samples in the latent space, the variational autoencoder can screen out a set of excellent subsequent heat dissipation installation point solutions.

[0072] Step S22: Generate multiple sets of excellent preliminary solutions based on the multiple excellent heat dissipation points and the set of excellent subsequent heat dissipation installation point solutions.

[0073] In some embodiments, multiple sets of excellent preliminary solutions can be generated using a deep neural network model based on the multiple excellent heat dissipation points and the set of excellent subsequent heat dissipation installation point solutions. The input of the deep neural network model is the multiple excellent heat dissipation points and the set of excellent subsequent heat dissipation installation point solutions, and the output of the deep neural network model is multiple sets of excellent preliminary solutions.

[0074] The deep neural network model is a type of neural network that contains multiple hidden layers. Through the connection and interaction between a large number of neurons, the deep neural network model can automatically learn deep features and patterns from complex data. The deep neural network model includes Deep Neural Networks (DNN), which consists of an input layer, multiple hidden layers, and an output layer. The deep neural network has a powerful non-linear mapping ability and generalization ability, enabling it to handle complex tasks such as predictive analysis.

[0075] Multiple sets of excellent preliminary solutions are a series of candidate heat dissipation installation point solutions that perform well in multiple aspects such as heat dissipation effect, cost, and feasibility generated by the deep neural network model.

[0076] Multiple excellent heat dissipation points and a set of excellent subsequent heat dissipation installation point solutions contain rich heat dissipation-related information. The deep neural network model can deeply analyze and mine this information, and can learn the internal relationships and laws between this information. Through learning and understanding this information, the model can search and explore in the potential solution space to generate a variety of different combinations and variations, so as to obtain multiple sets of primary selection solutions with different characteristics but all performing excellently. In addition, the generalization ability of the deep neural network enables it to adapt to different actual situations and constraints, and thus the generated solutions can have high generality and high practicality.

[0077] Step S23, construct a knowledge graph. Each knowledge graph includes multiple excellent primary selection solution nodes and multiple edges between the nodes. The node features of each excellent primary selection solution node include a set of excellent primary selection solutions and the simulated infrared working video of a set of excellent primary selection solutions. The edges between the nodes represent the similarity between the excellent primary selection solutions.

[0078] A knowledge graph is a data structure that graphically displays entities and the relationships between entities. A knowledge graph consists of nodes (vertices) and edges, and can represent complex knowledge in a structured manner. In some embodiments, the knowledge graph can be used to integrate and present excellent primary selection solutions and the relationships between them.

[0079] The excellent primary selection solution node is the basic unit in the knowledge graph. Each node represents a specific excellent primary selection solution and contains various characteristic information related to this solution.

[0080] The node features can be used to describe the attributes and characteristics of the excellent primary selection solution node. The node features include a set of excellent primary selection solutions and the simulated infrared working video of this set of excellent primary selection solutions.

[0081] In some embodiments, the simulated infrared working video of each set of excellent primary selection solutions can be generated by a generation model based on each set of excellent primary selection solutions.

[0082] An edge is a relationship line connecting different excellent primary selection solution nodes in the knowledge graph to reflect the degree of association between different excellent primary selection solutions. The edge represents the similarity between the excellent primary selection solutions.

[0083] In some embodiments, the similarity between excellent primary selection solutions can be calculated by a deep neural network model.

[0084] Step S24, process the knowledge graph based on a graph neural network to determine the target installation point solution.

[0085] A graph neural network is a neural network model specifically designed to process knowledge graph data. The graph neural network can learn and reason about the nodes and edges in the graph, and aggregate the neighbor information of the nodes through a message passing mechanism, so as to model the structure and attributes of the knowledge graph. The input of the graph neural network is the knowledge graph, and the output of the graph neural network is the target installation point solution.

[0086] The target installation point solution is a solution about the installation point that is most suitable for the actual application scenario, which is selected by the graph neural network from multiple sets of excellent preliminary selection solutions by comprehensively considering various factors such as heat dissipation effect, installation feasibility, equipment performance, and cost.

[0087] The nodes in the knowledge graph represent each excellent preliminary selection solution. The nodes carry the information of the specific solution and are the basic units in the knowledge graph. Node features can enable each solution to be presented more comprehensively and three-dimensionally, so that the graph neural network can deeply understand the characteristics and advantages of the solution. The edges establish the connections between the nodes and can visualize the relationships between the solutions. The edges use the solution similarity as a link to connect the scattered nodes, so as to clearly present the degree of association between the solutions. Through such a design, it is convenient for the graph neural network to discover the commonalities and differences between the excellent preliminary selection solutions.

[0088] The graph neural network can process the knowledge graph to determine the target installation point solution. The main reason lies in the adaptability and learning ability of the graph neural network to the graph neural network. As a network model designed for the structure of the knowledge graph, the graph neural network can aggregate the neighbor information of the nodes through a message passing mechanism, so as to accurately model the excellent preliminary selection solutions and their similarity relationships in the knowledge graph. The graph neural network can also automatically mine the potential patterns in the data to extract valuable features, and at the same time it has a strong non-linear fitting ability, so as to capture the complex non-linear relationships between the excellent preliminary selection solutions. And through training and learning, the graph neural network can continuously optimize its own parameters and adjust the processing method of the knowledge graph, so as to more accurately and reliably determine the target installation point solution.

[0089] Step S8, install the heat dissipation device based on the target installation point solution, and perform heat dissipation control based on the installed heat dissipation device.

[0090] After the target installation solution is determined, install the heat dissipation device for the servo drive based on the target installation solution, and perform heat dissipation control on the servo drive based on the installed heat dissipation device.

[0091] Based on the same inventive concept, Figure 3 FIG. is a schematic diagram of a heat dissipation system for a servo drive based on artificial intelligence provided by an embodiment of the present invention. The heat dissipation system for a servo drive based on artificial intelligence includes:

[0092] The first acquisition module 31 is configured to acquire the infrared working video of the servo driver;

[0093] The initial heat dissipation point determination module 32 is configured to determine a plurality of initial heat dissipation installation points based on the infrared working video of the servo driver;

[0094] The second acquisition module 33 is configured to acquire the infrared working video after the initial installation points are installed;

[0095] The scoring module 34 is configured to determine the heat dissipation effect score of each point based on the infrared working video after the initial installation points are installed;

[0096] The subsequent solution determination module 35 is configured to determine multiple sets of subsequent heat dissipation installation point solutions based on the heat dissipation effect scores of each point and the infrared working video after the initial installation points are installed;

[0097] The simulation video generation module 36 is configured to generate multiple sets of subsequent simulated infrared working videos using a generation model based on the infrared working video of the servo driver, the infrared working video after the initial installation points are installed, and the multiple sets of subsequent heat dissipation installation point solutions;

[0098] The target solution determination module 37 is configured to determine the target installation point solution based on the multiple sets of subsequent simulated infrared working videos;

[0099] The heat dissipation execution module 38 is configured to install heat dissipation devices based on the target installation point solution and perform heat dissipation control based on the installed heat dissipation devices.

[0100] In addition, unless clearly stated in the claims, the order of the processing elements and sequences described in this specification, the use of numbers, letters, or other names, is not used to limit the order of the processes and methods in this specification. Although various examples are discussed in the above disclosure for some currently useful embodiments of the invention, it should be understood that such details are for illustrative purposes only. The appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through software solutions, such as installing the described system on existing servers or mobile devices.

[0101] Similarly, it should be noted that, in order to simplify the presentation disclosed in this specification and thus assist in the understanding of one or more embodiments of the invention, in the foregoing description of the embodiments of this specification, sometimes multiple features are incorporated into one embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the features required by the subject matter of this specification are more than those recited in the claims. In fact, the features of the embodiments are fewer than all the features of the individual embodiments disclosed above.

[0102] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be regarded as consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly presented and described in this specification.

Claims

1. A heat dissipation method for a servo driver based on artificial intelligence, characterized in that, Including: Obtain the infrared working video of the servo driver; Determine multiple initial heat dissipation installation points based on the infrared working video of the servo driver; Obtain the infrared working video after the initial installation points are installed; Determine the heat dissipation effect score for each point based on the infrared working video after the initial installation points are installed; Determine multiple sets of subsequent heat dissipation installation point schemes based on the heat dissipation effect score for each point and the infrared working video after the initial installation points are installed; Generate multiple sets of subsequent simulated infrared working videos using a generation model based on the infrared working video of the servo driver, the infrared working video after the initial installation points are installed, and the multiple sets of subsequent heat dissipation installation point schemes; Determine the target installation point scheme based on the multiple sets of subsequent simulated infrared working videos; Install heat dissipation equipment based on the target installation point scheme, and perform heat dissipation control based on the installed heat dissipation equipment.

2. The heat dissipation method of the servo driver based on artificial intelligence according to claim 1, wherein, The determining the target installation point scheme based on the multiple sets of subsequent simulated infrared working videos includes: Determine multiple excellent heat dissipation points and a set of excellent subsequent heat dissipation installation point schemes based on the multiple sets of subsequent simulated infrared working videos; Generate multiple sets of excellent primary selection schemes based on the multiple excellent heat dissipation points and the set of excellent subsequent heat dissipation installation point schemes; Construct a knowledge graph, each knowledge graph includes multiple excellent primary selection scheme nodes and multiple edges between the nodes, the node features of each excellent primary selection scheme node include a set of excellent primary selection schemes and the simulated infrared working video of a set of excellent primary selection schemes, and the edges between the nodes represent the similarity between the excellent primary selection schemes; Process the knowledge graph based on a graph neural network to determine the target installation point scheme.

3. The heat dissipation method of the servo driver based on artificial intelligence according to claim 2, characterized in that, The target installation point scheme is one of the multiple sets of excellent primary selection schemes.

4. The heat dissipation method of the servo driver based on artificial intelligence according to claim 1, wherein The generation model is a generative adversarial network.

5. A heat dissipation system for a servo driver based on artificial intelligence, characterized in that, Including: A first acquisition module for obtaining the infrared working video of the servo driver; An initial heat dissipation point determination module for determining multiple initial heat dissipation installation points based on the infrared working video of the servo driver; A second acquisition module for obtaining the infrared working video after the initial installation points are installed; A scoring module for determining the heat dissipation effect score for each point based on the infrared working video after the initial installation points are installed; A subsequent scheme determination module for determining multiple sets of subsequent heat dissipation installation point schemes based on the heat dissipation effect score for each point and the infrared working video after the initial installation points are installed; A simulated video generation module for generating multiple sets of subsequent simulated infrared working videos using a generation model based on the infrared working video of the servo driver, the infrared working video after the initial installation points are installed, and the multiple sets of subsequent heat dissipation installation point schemes; A target scheme determination module for determining the target installation point scheme based on the multiple sets of subsequent simulated infrared working videos; A heat dissipation execution module for installing heat dissipation equipment based on the target installation point scheme and performing heat dissipation control based on the installed heat dissipation equipment.

6. The heat dissipation system of the servo driver based on artificial intelligence according to claim 5, characterized in that The target scheme determination module is further used for: Determine multiple excellent heat dissipation points and a set of excellent subsequent heat dissipation installation point schemes based on the multiple sets of subsequent simulated infrared working videos; Generate multiple sets of excellent primary solutions based on the multiple excellent heat dissipation points and the set of excellent subsequent heat dissipation installation point solutions; Construct a knowledge graph, each knowledge graph includes multiple excellent primary solution nodes and multiple edges between the nodes. The node features of each excellent primary solution node include a set of excellent primary solutions and a simulated infrared working video of a set of excellent primary solutions. The edges between the nodes represent the similarity between the excellent primary solutions; Process the knowledge graph based on a graph neural network to determine the target installation point solution.

7. The heat dissipation system of the servo driver based on artificial intelligence according to claim 6, characterized in that, The target installation point solution is one of the multiple sets of excellent primary solutions.

8. The heat dissipation system of the servo driver based on artificial intelligence according to claim 5, characterized in that, The generation model is a generative adversarial network.

Images