Network card installation method and device of electronic equipment

Abstract

The invention discloses a network card installation method and device for electronic equipment, and relates to the technical field of data encryption, and the method comprises the steps: predicting an optimal insertion parameter through a machine learning model based on a physical parameter and slot information of a network card, converting the optimal insertion parameter through state machine conversion to generate a control instruction, and guiding automatic insertion; after the insertion is completed, the bionic bulge array in the slot realizes preliminary adsorption through Van der Waals force, and a pressure sensor is combined to trigger a self-locking mechanism through an electric control unit to fix the network card; after the network card is fixed, the built-in vibration test unit simulates the actual use environment, monitors the vibration response of the network card in real time, detects the installation stability, and optimizes the machine learning model according to the detection result. According to the invention, through the fixing and self-locking module, the bionic projection array is utilized to preliminarily adsorb the network card by Van der Waals force, and the pressure sensor and the electric control unit are combined to trigger a self-locking mechanism, so that the installation stability is enhanced, and long-term reliable operation of equipment is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic equipment assembly, in particular to a method and device for installing a network card of an electronic equipment. Background Art

[0002] With the development of information technology, the performance of electronic devices has improved, and the technology for installing internal components has made significant progress. As a core component in the computer and communications field, the installation of network cards directly affects the performance, stability, and reliability of the equipment. Early installation relied on manual operation, which was inefficient and prone to damage. Automation technology introduces sensors and control systems to improve precision and efficiency. Micro-nano manufacturing and bionics provide new ideas, such as bionic protrusion arrays to enhance stability and machine learning to optimize parameters to guide operations. However, existing technologies have problems such as insufficient dynamic parameter adjustment and lack of efficient fixing mechanisms. It is difficult to ensure long-term stable connections in complex environments, and further improvements are needed to meet high performance requirements.

[0003] The main challenges faced by existing technologies during network card installation include: First, during the insertion phase, the real-time monitoring and adaptive adjustment capabilities of dynamic physical parameters are limited, making it difficult to meet the needs of high-precision application scenarios. Second, after installation, there is a lack of an efficient fixing mechanism. Especially in vibration or other complex environments, traditional fixing methods may not ensure long-term stable connection performance. These issues limit the further promotion of existing technologies in high-performance, high-reliability practical applications. Therefore, how to achieve accurate dynamic parameter monitoring and adjustment while ensuring long-term stability after installation has become a key issue that needs to be urgently addressed in current network card installation technology. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a network card installation method based on an electronic device to solve the problems of dynamic parameter monitoring optimization and insufficient stability after installation in the existing network card installation technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for installing a network card in an electronic device, which includes using multiple types of sensors and cameras to collect physical parameters and slot information of the network card during the insertion process, the multiple types of sensors including pressure sensors, angle sensors and position sensors; based on the physical parameters and slot information of the network card, predicting optimal insertion parameters through a machine learning model, converting the optimal insertion parameters into control instructions through state machine conversion, and guiding automated insertion; after the insertion is completed, the bionic protrusion array in the slot achieves preliminary adsorption through van der Waals force, combines with the pressure sensor and triggers the self-locking mechanism through the electronic control unit to fix the network card; after the network card is fixed, the actual use environment is simulated through a built-in vibration test method, the vibration response of the network card is monitored in real time, the installation stability is detected, and the machine learning model is optimized according to the detection results.

[0008] As a preferred solution of the network card installation method for the electronic device described in the present invention, the physical parameters of the network card include pressure data, angle data, position data, image data and time series; the slot information includes size, material properties, environmental conditions, interface type, power requirements, heat dissipation requirements and supported communication protocols.

[0009] As a preferred solution of the network card installation method of the electronic device described in the present invention, wherein: the optimal insertion parameters are predicted by a machine learning model based on the physical parameters and slot information of the network card, and the specific steps are as follows:

[0010] The collected network card physical parameters and slot information are de-noised, missing values ​​filled, and normalized. Principal component analysis is used to identify the features that have the greatest impact on the insertion process and generate feature engineering.

[0011] Build a machine learning model based on feature engineering. Randomly partition the network card physical parameters and slot information into training, validation, and test sets. Use the training set to train the machine learning model, use the validation set to adjust hyperparameters, and use the test set to evaluate the model's performance and optimize the machine learning model's performance metrics.

[0012] The physical parameters and slot information of the network card are input into the trained machine learning model to predict the optimal insertion parameter P.

[0013] As a preferred solution of the network card installation method of the electronic device of the present invention, wherein: the optimal insertion parameters are converted into control instructions through state machine conversion, and the automatic insertion is guided. The specific steps are as follows:

[0014] Based on the optimal insertion parameter P, set the current state, condition, action and next state of the state machine;

[0015] Based on the current state, conditions, actions, and next states of the state machine, a state transition diagram is constructed to describe all paths from the initial state to the final state of the network card insertion and the corresponding actions.

[0016] Write the switch-case structure in C language based on the state transition diagram to implement the state machine logic;

[0017] Based on the state machine logic, the state machine reaches a specific state and generates corresponding control instructions;

[0018] The control instructions are decomposed into specific action parameters, mapped to the automation equipment, and converted into digital commands. The control equipment approaches the slot at a low speed while monitoring the sensor data in real time. When the insertion depth reaches the target value and the sensor feedback is stable, the insertion is determined to be complete.

[0019] As a preferred solution of the network card installation method of the electronic device of the present invention, wherein: after the insertion is completed, the bionic protrusion array in the slot is initially adsorbed by van der Waals force, and the specific steps are as follows:

[0020] Based on biomimetics, we selected organisms with strong adhesion in nature and used scanning electron microscopy (SEM) and X-ray photoelectron spectroscopy (XPS) to analyze the microstructural characteristics and chemical composition of the target organisms' attachment sites.

[0021] Defining the geometric shape and size parameters of the biomimetic protrusion array within the slot based on microstructural features and chemical composition;

[0022] constructing the overall layout of the protrusion array based on geometric shape and size parameters;

[0023] Based on the layout of the bionic protrusion array in the slot, a three-dimensional micro-nanostructure of the bionic protrusion array in the slot is constructed by femtosecond laser;

[0024] The three-dimensional micro-nanostructure of the biomimetic protrusion array in the slot increases the contact area with the network card. When the distance between the biomimetic protrusion array and the network card surface reaches the molecular level, it enters the range of van der Waals force.

[0025] During the contact process, the elastic deformation of the bionic protrusion array increases the van der Waals force and forms initial adsorption.

[0026] As a preferred solution of the method for installing a network card in an electronic device of the present invention, wherein: the pressure sensor is combined and the self-locking mechanism is triggered by the electronic control unit to fix the network card. The specific steps are as follows:

[0027] Set the pressure threshold based on the pressure change generated when the network card is inserted;

[0028] During the insertion process, the pressure is monitored in real time through the pressure sensor. When the pressure reaches the pressure threshold, the electronic control unit receives the pressure sensor signal and converts it into a control instruction;

[0029] Based on the control instructions, the actuator in the self-locking mechanism is activated, the motor is driven to adjust the mechanical structure, and the self-locking mechanism is triggered to fix the network card;

[0030] The actuator refers to a component that receives control instructions and drives mechanical parts to move.

[0031] As a preferred solution of the network card installation method of the electronic device described in the present invention, wherein: the actual use environment is simulated by a built-in vibration test unit, the vibration response of the network card is monitored in real time by an acceleration sensor, the installation stability is detected, and the machine learning model is optimized according to the detection results. The specific steps are as follows:

[0032] A built-in vibration test unit is constructed based on sine wave, random vibration and impact vibration that simulate the actual environment. The built-in vibration test unit consists of a vibration table, controller, acceleration sensor and data acquisition equipment;

[0033] The built-in vibration test unit uses an accelerometer to monitor the vibration response of the network card in real time and record the data. The data recorded by the accelerometer is then analyzed in depth to calculate the looseness index S.

[0034] Based on the historical data of the network card stable state and the network card unstable state, the average loose index S is calculated respectively, and the boundary value between the two is set to define the loose threshold S1.

[0035] When S>S1, it is determined that the network card is loose;

[0036] When S≤S1, the network card is determined to be well fixed;

[0037] During the network card insertion process, pressure, angle, position data and the final fixation effect are collected in real time, stored in the cloud database, and the machine learning model is optimized.

[0038] In the second aspect, the present invention provides a network card installation device for an electronic device, including a data acquisition module, an insertion parameter prediction module, a state machine control module, a fixing and self-locking module, and a vibration testing and optimization module; the data acquisition module is used to use multiple types of sensors and cameras to collect the physical parameters and slot information of the network card during the insertion process; the insertion parameter prediction module is used to predict the optimal insertion parameters through a machine learning model based on the physical parameters and slot information of the network card; the state machine control module is used to convert the optimal insertion parameters into control instructions through state machine conversion, and guide automated insertion; the fixing and self-locking module is used to complete the insertion, and the bionic protrusion array in the slot is initially adsorbed through the van der Waals force, combined with the pressure sensor and the self-locking mechanism is triggered by the electronic control unit to fix the network card; the vibration testing and optimization module is used to simulate the actual use environment through the built-in vibration testing unit after the network card is fixed, monitor the vibration response of the network card in real time, detect the installation stability, and optimize the machine learning model according to the detection results.

[0039] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the network card installation method for an electronic device as described in the first aspect of the present invention is implemented.

[0040] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the method for installing a network card for an electronic device as described in the first aspect of the present invention is implemented.

[0041] The beneficial effects of the present invention are as follows: through the data acquisition module, comprehensive perception of the physical parameters and slot information of the network card during the insertion process is achieved, ensuring high-precision control during the installation process, and finally achieving the effect of improving the installation success rate and reducing human errors; through the fixing and self-locking module, the bionic protrusion array is used to initially adsorb the network card with van der Waals force, and the self-locking mechanism is triggered by the pressure sensor and the electronic control unit, thereby enhancing the installation stability and ensuring the long-term reliable operation of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 This is a flow chart of the method for installing a network card in an electronic device in Example 1.

[0044] Figure 2This is a schematic diagram of the network card installation device for the electronic device in Example 1. DETAILED DESCRIPTION

[0045] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0046] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0047] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0048] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a method for installing a network card in an electronic device, comprising the following steps:

[0049] S1. Utilize multiple types of sensors and cameras to collect physical parameters and slot information of the network card during insertion, wherein the multiple types of sensors include a pressure sensor, an angle sensor, and a position sensor.

[0050] The physical parameters of the network card include pressure data, angle data, position data, image data and time series, and the slot information includes size, material properties, environmental conditions, interface type, power requirements, heat dissipation requirements and supported communication protocols.

[0051] It should be noted that a variety of sensors and technologies can be used to collect the physical parameters of the network card and slot information, such as pressure sensors, angle sensors, displacement sensors, cameras, temperature and humidity sensors, power meters, and protocol analyzers. By installing these sensors in key locations on the network card, slot, or its surroundings, combined with an automated testing platform and data fusion technology, comprehensive monitoring and analysis of the insertion process can be achieved.

[0052] S2. Based on the physical parameters and slot information of the network card, the optimal insertion parameters are predicted through a machine learning model. The optimal insertion parameters are converted into control instructions through state machine conversion, and the automated insertion is guided.

[0053] The collected physical parameters and slot information of the network card are de-noised, missing values ​​are filled, and normalized. The principal component analysis method is used to screen out the features that have the greatest impact on the insertion process and generate feature engineering.

[0054] Furthermore, data preprocessing is performed to improve data quality. Low-pass or Gaussian filters are used to remove high-frequency noise from time series data (e.g., pressure and position). Smoothing techniques such as moving averages are used to reduce fluctuations in discrete data (e.g., angles and dimensions). Outliers are detected and corrected using the 3σ principle or boxplots to achieve denoising. For missing values, continuous variables (e.g., pressure and temperature) are imputed using the mean, median, or interpolation, while categorical variables (e.g., interface type and communication protocol) are imputed using the mode or rule prediction. If the missing value ratio is too high, features are deleted or data is recollected. Finally, standardization is used to unify the dimensions to minimize the impact of differences in numerical ranges on the analysis results. Principal component analysis (PCA) is then used for dimensionality reduction. The covariance matrix of the original feature matrix is ​​calculated to analyze the correlation between features. The covariance matrix is ​​then decomposed and sorted by eigenvalue size. The top principal components with cumulative contributions of 85% to 95% are selected. The original data are then projected into the new feature space to preserve key information and reduce dimensionality. Feature engineering is then performed to generate new features based on domain knowledge (such as pressure change rate and relative offset), extract time series features (such as mean, variance, and peak), and evaluate feature importance through correlation analysis or machine learning models (such as random forest and Lasso regression) to screen key features. Categorical variables are also encoded using one-hot or label encoding, and ordered categorical variables are assigned ascending numerical codes to convert non-numeric features into numerical values. This process effectively extracts the features that most impact the network card insertion process, providing high-quality data support for subsequent modeling and optimization, thereby improving analysis accuracy and model performance.

[0055] Build a machine learning model based on feature engineering. Use random partitioning to divide physical parameters and slot information into training, validation, and test sets. Use the training set to train the machine learning model, use the validation set to adjust hyperparameters, and use the test set to evaluate the performance of the machine learning model and optimize the machine learning model performance indicators.

[0056] Furthermore, first, the collected network card physical parameters and slot information are randomly divided (such as a ratio of 7:1.5:1.5 or 8:1:1) into a training set, a validation set, and a test set. The training set is used for the model to learn the mapping relationship between input features and target variables, the validation set is used to adjust hyperparameters to optimize model performance, and the test set is used to finally evaluate the generalization ability of the model. Then, according to the task requirements, a suitable machine learning model is selected (such as random forest, support vector machine in classification tasks or linear regression, decision tree regression in regression tasks, etc.), and the training set is used to train the model. In this process, the loss function is minimized through optimization algorithms (such as gradient descent), and the model convergence is recorded to avoid overfitting or underfitting. Subsequently, the validation set is used to adjust the hyperparameters, and grid search, random search, or Bayesian optimization methods are used to find the optimal hyperparameter combination. The performance indicators on the validation set (such as accuracy, mean square error, etc.) are used to evaluate the effects of different parameter configurations. After completing model training and tuning, use the test set to perform a final evaluation of the model and select an evaluation metric that is appropriate for the task type (such as F1 score, AUC value in classification tasks or RMSE, R in regression tasks). 2 The model's performance on unseen data is measured using metrics like scores (e.g., ensemble learning, bagging, and boosting), feature selection (eliminating redundant features to simplify the model), data augmentation (generating more diverse training data), or model fusion (combining predictions from multiple models) to further improve model performance. This detailed process builds an efficient and reliable machine learning model, ensuring its stability and accuracy in analyzing and optimizing network card insertions while also providing excellent practical application value.

[0057] After training is completed, the physical parameters and slot information of the network card are input into the machine learning model as prediction data to predict the optimal insertion parameter P, which is expressed as:

[0058]

[0059] Where P is the predicted optimal insertion parameter, X i is the physical parameter of the i-th network card, Z i is the i-th slot information, w i is the importance weight of the i-th parameter, λ is the amplitude control parameter of the periodic adjustment item, λ is the frequency control parameter of the periodic adjustment item, T is the initial phase angle of the periodic adjustment item, φ is the initial phase angle of the periodic adjustment item, n is the total number of physical parameters and slot information of the network card, and i is the i-th feature being processed.

[0060] Furthermore, the physical parameters of the network card (such as size, interface type, power requirements, heat dissipation requirements, etc.) and slot information (such as size specifications, interface type, supported communication protocols, environmental conditions, etc.) are collected from actual scenarios. Then, the collected data is preprocessed in the same way as in the training phase, including data cleaning (denoising, filling missing values), normalization or standardization, to ensure that the input data format is the same as in the training phase. Then, the trained machine learning model and its weight parameters are loaded, and the preprocessed feature data is input into the model, and the prediction results are output through the forward propagation calculation of the model. According to the task requirements, the predicted value output by the model is parsed into specific insertion parameters (such as angle, force or depth), and appropriately adjusted in combination with real-time environmental conditions (such as temperature, humidity, etc.) to adapt to the current scenario. Finally, the optimized insertion parameters are applied to the automated insertion equipment or control system to guide the actual insertion operation, and new data is continuously collected during the insertion process to update the prediction results, so as to achieve dynamic optimization and precise control, thereby effectively improving the insertion success rate and equipment reliability.

[0061] S3. Convert the optimal insertion parameters into control instructions through state machine conversion, and guide the automated insertion.

[0062] Based on the optimal insertion parameter P, set the current state, condition, action, and next state of the state machine

[0063] The basic structure of a state machine should be explained, including the current state (the current state), conditions (the basis for triggering state transitions), actions (the operations performed in a specific state), and next states (the new states to which the conditions are met). Next, the current state is clearly defined, such as S0 (initial alignment), S1 (gradual insertion), S2 (contact detection), and S3 (complete insertion), corresponding to different stages of network card insertion. Next, state transition conditions are set, such as C1 (alignment completed), C2 (insertion progress meets target), and C3 (contact detection passed), to determine whether to transition from one state to the next. Furthermore, specific actions are defined for each state, such as A0 (adjusting position to align with the slot), A1 (controlling insertion force or angle based on P), A2 (detecting contact between the network card and the slot), and A3 (confirming insertion completion). Finally, state transitions are implemented by monitoring the conditions in real time. For example, when C1 is met, the state transitions from S0 to S1, and so on, until the final state S3 is reached. If an anomaly is detected, the error handling process is triggered, and the process may return to the previous state or terminate the operation. This detailed process ensures that the state machine can dynamically adjust the insertion logic based on the optimal insertion parameter P and real-time feedback data, thereby achieving efficient, secure, and reliable network card insertion operations.

[0064] Based on the current state, conditions, actions, and next states of the state machine, a state transition diagram is constructed to describe all paths from the initial state to the final state of the network card insertion and the corresponding actions.

[0065] The specific process involves defining the basic elements of the state machine, including the current state (S0: initial alignment, S1: gradual insertion, S2: contact detection, S3: insertion completed), conditions (C1: position alignment completed, C2: insertion progress met, C3: contact detection passed, C4: exception detection failed), and actions (A0: position adjustment, A1: gradual insertion, A2: contact detection, A3: operation completed). Next, a state transition diagram is drawn to clearly define each path and its logic: In the initial state S0, action A0 (position adjustment) is executed. When condition C1 is met, the process transitions to S1; if condition C4 is met, A0 is re-executed or the error handling state is entered. In state S1, action A1 (gradual insertion) is executed. When condition C2 is met, the process transitions to S2; if condition C4 is met, the process returns to S0 or the error handling state is entered. In state S2, action A2 (contact detection) is executed. When condition C3 is met, the process transitions to S3; if condition C4 is met, the process returns to S1 or the error handling state is entered. Finally, in state S3, action A3 (operation completed) is executed. If an exception is detected, the process returns to S2 or enters the error handling state. Furthermore, all possible exception paths must be considered, such as S0→S0 (position adjustment failure), S1→S0 (insertion exception), S2→S1 (contact detection failure), and S3→S2 (detection exception after insertion is complete), with specific recovery or error handling logic defined for each case. This detailed state transition diagram design not only covers the normal insertion process (S0→S1→S2→S3), but also fully considers the handling mechanisms for various exceptions, ensuring the security, reliability, and efficiency of the entire network card insertion process.

[0066] Write the switch-case structure in C language based on the state transition diagram to implement the state machine logic;

[0067] The specific process begins by defining the required states (e.g., S0: initial alignment, S1: gradual insertion, S2: contact detection, S3: insertion completion), conditions (e.g., position alignment, insertion progress, contact detection), and actions (e.g., position adjustment, insertion control, contact detection, and operation completion) for the state machine. These are then implemented using enumerated types, Boolean variables or functions to determine the conditions, and encapsulated action functions. Next, a switch-case structure is used in the main logic to implement state transitions. Each case corresponds to a state, in which the corresponding action is executed and the next state is transitioned to based on the condition. For example, after performing the position adjustment action in state S0, if the condition is met, the state transition is to S1; otherwise, exception handling is performed. Similarly, the insertion and contact detection actions are executed in states S1 and S2, respectively, and subsequent state transitions are determined based on the conditions. Finally, the main program initializes the state machine and starts the main loop, calling the state machine function to drive the entire process until the final state S3 is reached, indicating insertion completion. This process not only covers the normal insertion path (S0→S1→S2→S3), but also fully considers the handling mechanisms of various abnormal situations to ensure the security, reliability and efficiency of the network card insertion process.

[0068] Based on the state machine logic, the state machine reaches a specific state and generates corresponding control instructions;

[0069] The specific process is as follows: First, the mapping relationship between each state and control instruction is clarified. For example, in the state machine for network card insertion, S0 (initial alignment) corresponds to the "adjust position" instruction, S1 (gradual insertion) corresponds to the "execute insertion action" instruction, S2 (contact detection) corresponds to the "verify contact status" instruction, and S3 (complete insertion) corresponds to the "record completion information" instruction. Next, the current state is monitored in real time through state variables, and the state value is updated after each state transition. When the state machine enters a specific state, the control instruction generation logic corresponding to that state is triggered. This logic can be implemented through a switch-case. Subsequently, specific control instructions are generated based on the predefined mapping relationship. These instructions may be hardware control signals (such as driving a motor or adjusting force), software operation commands (such as logging or sending notifications), or external device interaction instructions (such as communication protocol data packets). The generated control instructions are sent to the target execution unit or executed directly locally. At the same time, the execution results are collected as feedback information to verify whether the instructions have been successfully completed and to determine whether further state adjustments or regeneration of instructions are required. This detailed process achieves a seamless connection between the state machine logic and actual operations, ensuring accurate and reliable system operation.

[0070] The control instructions are decomposed into specific action parameters, mapped to the automation equipment, and converted into digital commands. The control equipment approaches the slot at a low speed while monitoring the sensor data in real time. When the insertion depth reaches the target value and the sensor feedback is stable, the insertion is determined to be complete.

[0071] The specific process is as follows: First, based on the control instruction (such as "approach the slot at low speed"), specific action parameters such as speed, force, angle and target depth are decomposed. For example, a low speed is set (0.5mm / s), the force range is limited (no more than 2N), and the target insertion depth is set (such as 20mm); then, these parameters are mapped to the control interface of the automation equipment. For example, the speed and force are controlled by the motor drive module, the insertion status is monitored by sensors, and the parameters are converted into a digital command format recognizable by the equipment with the help of a communication protocol (such as Modbus or CAN bus), such as pulse frequency or position code value; then, a digital command is sent to start the equipment to approach the slot at low speed. During this process, sensor data is collected in real time, and key indicators such as insertion depth, contact pressure and stability are monitored. The equipment action is dynamically adjusted based on the feedback to ensure precise alignment and stable insertion; finally, when the insertion depth reaches the target value and the sensor feedback shows stability, the insertion is determined to be complete, thereby ensuring the accuracy and reliability of the entire operation, while reducing the risk of failure through real-time monitoring and anomaly detection mechanisms.

[0072] S3. After the insertion is completed, the bionic protrusion array in the slot achieves initial adsorption through van der Waals force, combines with the pressure sensor and triggers the self-locking mechanism through the electronic control unit to fix the network card.

[0073] Based on biomimetics, we selected organisms with strong adhesion in nature and used scanning electron microscopy (SEM) and X-ray photoelectron spectroscopy (XPS) to analyze the microstructural characteristics and chemical composition of the target organisms' attachment sites.

[0074] The specific process is as follows: first, the target biological sample is collected and the attachment site is prepared to ensure the structural integrity; then, SEM is used to observe its microscopic morphology, revealing key features such as fibrous structure, surface texture and arrangement; at the same time, XPS is used to analyze the chemical composition of the attachment site, determine the surface elements and their chemical states, and identify functional molecules (such as dopamine or keratin); through the integrated analysis of SEM and XPS data, a correlation model between microstructure and chemical composition is established, and how the physical structure and chemical properties work together to achieve strong adhesion, providing a theoretical basis and design inspiration for bionic materials and technologies; taking the gecko toe as an example, SEM found that its micro-nanoscale bristle structure can increase the contact area and generate van der Waals force, and combined with XPS analysis, it is further confirmed that keratin and functional functional groups in the bristles enhance the adhesion effect, thus revealing the bionic attachment mechanism of the synergistic effect of physical structure and chemical properties.

[0075] Defining the geometric shape and size parameters of the biomimetic protrusion array within the slot based on microstructural features and chemical composition;

[0076] The specific process is as follows: first, the microscopic morphology of the target organism's attachment site is analyzed in detail by scanning electron microscopy (SEM), and key geometric features such as fiber diameter, length, number of branches, and arrangement density are extracted. The chemical composition and the mechanism of action of functional molecules are analyzed by X-ray photoelectron spectroscopy (XPS) to clarify how these characteristics synergistically enhance adhesion. Next, the geometric shape of the protrusion array in the slot is designed according to the structural characteristics of the target organism. For example, cylindrical or conical protrusions are designed based on the regular arrangement of gecko bristles, or multi-level protrusion shapes are created by imitating branched structures to maximize the contact area and optimize force distribution. At the same time, the key dimensions of the protrusion array, including diameter, height, spacing, and density, are defined based on the dimensional parameters of the target organism to ensure that they match the actual application requirements, and are appropriately adjusted considering material properties and manufacturing process limitations. Finally, the performance of the protrusion array under different conditions is evaluated by computer simulation (such as finite element analysis), and its contact area, adhesion, and stability indicators are verified. The geometric shape and dimensional parameters are further optimized in combination with experimental test results to achieve efficient and reliable bionic design.

[0077] constructing the overall layout of the protrusion array based on geometric shape and size parameters;

[0078] It should be noted that the geometric shape and size parameters of the target organism are used as the design basis for individual protrusions. The protrusions are assembled into arrays according to regular or random arrangement patterns. The rationality of the layout is continuously optimized through computer simulation and experimental verification, and ultimately a design scheme that meets the requirements of practical applications is generated. This method not only reproduces the strong adhesion of the target organism, but also provides a theoretical basis and technical support for the design of bionic materials and devices. For example, the application of bionic protrusion arrays in network card slots can significantly improve the stability and reliability of the insertion process and reduce the risk of wear and failure. This integration of bionic principles, geometric design methods and engineering optimization technologies lays a solid foundation for the development of high-performance bionic materials and devices.

[0079] Based on the layout of the bionic protrusion array in the slot, a three-dimensional micro-nanostructure of the bionic protrusion array in the slot is constructed by femtosecond laser;

[0080] It should be noted that, first, computer-aided design (CAD) software is used to construct a three-dimensional micro-nanostructure model based on the overall layout of the protrusion array to ensure that its geometric shape and dimensional parameters meet the design requirements; then, materials suitable for femtosecond laser processing are selected and laser parameters (such as pulse width, energy density and scanning speed) are adjusted to achieve high-precision material removal or modification through layer-by-layer processing; during the processing, the focal position and scanning path of the laser beam are precisely controlled to reproduce the spatial distribution and morphology of complex structures (such as branched protrusions); then, the processed protrusion array is post-processed (such as cleaning, polishing or functionalization) to optimize surface properties and functionality; finally, scanning electron microscopy (SEM) and atomic force microscopy (AFM) are used to verify the geometric shape, dimensional parameters and surface quality of the structure, and its performance is evaluated through experimental tests. Based on the results, the design model and processing parameters are optimized to achieve efficient and precise manufacturing of bionic protrusion arrays.

[0081] When the distance between the three-dimensional micro-nanostructure of the bionic protrusion array and the surface of the network card reaches the molecular level, it enters the range of van der Waals force;

[0082] Furthermore, when the distance between the three-dimensional micro-nanostructure of the biomimetic protrusion array and the surface of the network card reaches the molecular level, it enters the range of van der Waals forces (approximately 0.1-1 nanometers). At this time, the micro-nanostructure of the protrusion array forms a large number of microscopic contact points with the surface of the network card. The van der Waals force generated by the instantaneous dipole moment of each contact point accumulates into a strong adhesion force on a macroscopic scale. This mechanism simulates the attachment method of organisms such as gecko bristles in nature. To fully utilize the effect of van der Waals forces, it is necessary to optimize the geometric shape and dimensional parameters of the protrusion array, while considering the effects of surface roughness, material properties, and environmental conditions on stability. In addition, real-time monitoring and dynamic adjustment are combined to ensure that a stable contact state is maintained within the molecular level, thereby achieving efficient and reliable adhesion.

[0083] During the contact process, the elastic deformation of the bionic protrusion array increases the van der Waals force and forms initial adsorption.

[0084] It should be noted that the bionic protrusion array uses polymer materials, and its elastic deformation characteristics play a key role in the contact process. First, through elastic deformation, the protrusion array can adapt to the microscopic unevenness of the network card surface, thereby effectively increasing the actual contact area and providing more intermolecular contact points. Secondly, elastic deformation optimizes the distance distribution between the protrusion array and the network card surface, ensuring that more contact points enter the effective range of van der Waals force, further enhancing adhesion. In addition, elastic deformation also has the ability to buffer external impacts, avoiding contact failure due to excessive local stress, and at the same time giving the array dynamic adaptability, so that it maintains a stable adsorption state during continuous contact. These characteristics work together to significantly improve the adhesion ability of the protrusion array, providing efficient and reliable guarantees for initial adsorption.

[0085] Set the pressure threshold based on the pressure change generated when the network card is inserted;

[0086] It should be noted that pressure changes arise from the interaction between the network card and the protrusion array at different stages of insertion, including initial contact, elastic deformation, and deep insertion. Through experimental testing and material property analysis, combined with safety margin considerations, a reasonable pressure threshold is set to effectively prevent damage to the device caused by excessive pressure, while optimizing the insertion process and promptly detecting anomalies. In actual operation, high-precision pressure sensors are used to monitor pressure changes in real time and compare them with the threshold value, enabling dynamic adjustment of insertion speed and force to ensure a smooth and efficient insertion process.

[0087] During the insertion process, the pressure is monitored in real time through the pressure sensor. When the pressure reaches the pressure threshold, the electronic control unit receives the pressure sensor signal and converts it into a control instruction;

[0088] The specific process is that during the network card insertion process, the pressure sensor monitors the pressure changes in real time and converts the physical pressure signal into an electrical signal. After the data is transmitted to the electronic control unit (ECU), the electronic control unit performs analog-to-digital conversion and analysis on the received electrical signal to obtain a specific digital pressure value; then, the electronic control unit compares the pressure value with the preset pressure threshold. When the pressure value reaches the threshold, it generates control instructions according to the preset logic, such as slowing down the insertion speed, pausing the insertion action, or adjusting the insertion angle; finally, the control instructions are transmitted to the actuator through the drive circuit to achieve precise control of the insertion action. At the same time, the electronic control unit continuously monitors the pressure changes and dynamically adjusts the control strategy to ensure the safety and reliability of the insertion process.

[0089] Based on the control command, the actuator in the self-locking mechanism is activated, the motor is driven to adjust the mechanical structure, and the self-locking mechanism is triggered to fix the network card. The actuator specifically refers to the component that receives the control command and drives the mechanical component to move;

[0090] The specific process is as follows: first, the controller in the actuator receives and analyzes the control instructions issued by the electronic control unit and converts them into drive signals; then, the drive motor starts and adjusts the operating status according to the signal, pushes the mechanical components to move through the transmission system, and adjusts the position or shape of the mechanical structure; then, the mechanical structure is adjusted into place and the self-locking mechanism is triggered, such as by moving the slider, rotating the cam or locking the ratchet to achieve the fixation of the network card; finally, the system uses sensors to detect the self-locking status to confirm whether the network card is successfully fixed. If an abnormality is detected, it will be readjusted until the self-locking is completed.

[0091] S4. After the network card is fixed, the built-in vibration test unit simulates the actual usage environment, monitors the vibration response of the network card in real time, detects the installation stability, and optimizes the machine learning model based on the test results.

[0092] A built-in vibration test unit is constructed based on sine wave, random vibration and impact vibration that simulate the actual environment. The built-in vibration test unit consists of a vibration table, controller, acceleration sensor and data acquisition equipment;

[0093] It should be noted that the built-in vibration test unit, which is constructed based on sine waves, random vibrations and impact vibrations that simulate actual environments, consists of a vibration table, a controller, an accelerometer and a data acquisition device. The components work together to achieve comprehensive vibration testing functions; the vibration table is responsible for generating accurate vibration signals, covering various types such as sine waves, random vibrations and impact vibrations; the controller adjusts the vibration parameters according to the test requirements and monitors the output of the vibration table in real time; the accelerometer is installed on the object under test to collect actual vibration data and convert it into electrical signals; the data acquisition device processes, analyzes and stores the signals to generate results that can be used to evaluate the vibration resistance of the system.

[0094] The built-in vibration test unit uses an accelerometer to monitor the vibration response of the network card in real time and record the data. The data recorded by the accelerometer is analyzed in depth to calculate the looseness index S, which is expressed as:

[0095]

[0096] Among them, S loose index, a i is the acceleration value of the i-th vibration, a avg Average acceleration value, n is the number of sampling points, i is the acceleration value of the i-th vibration;

[0097] Based on the historical data of the network card stable state and the network card unstable state, the average loose index S is calculated respectively, and the boundary value between the two is set to define the loose threshold S1;

[0098] When S>S1, it is determined that the network card is loose;

[0099] When S≤S1, the network card is determined to be well fixed;

[0100] The specific process is as follows: first, an accelerometer is used to collect acceleration data of the network card at a high frequency in a vibration environment. Next, the average acceleration value of all sampling points is calculated. Then, the square of the deviation between the acceleration value of each sampling point and the average value is calculated and summed to obtain the looseness index. Finally, the calculated looseness index is compared with a preset threshold to evaluate the stability of the network card. This process provides a scientific basis for evaluating the stability of the network card.

[0101] During the network card insertion process, pressure, angle, position data and the final fixation effect are collected in real time, stored in the cloud database, and the machine learning model is optimized.

[0102] Furthermore, first, pressure sensors, angle sensors and displacement sensors are used to respectively collect pressure changes, angle information and position data during the insertion process, and the data is labeled in combination with the fixation effect evaluation results; secondly, the data is uploaded to a cloud database, and key features are extracted from it to build a machine learning model, and the model prediction accuracy is continuously improved through training and verification; finally, the optimized model can be applied to actual insertion operations, dynamically adjusting the insertion parameters to improve the success rate and fixation effect, and at the same time, closed-loop optimization is achieved by continuously collecting new data to ensure continuous improvement of system performance.

[0103] This embodiment also provides a network card installation device for an electronic device, including: a data acquisition module, an insertion parameter prediction module, a state machine control module, a fixing and self-locking module, and a vibration testing and optimization module; the data acquisition module is used to use multiple types of sensors and cameras to collect the physical parameters and slot information of the network card during the insertion process; the insertion parameter prediction module is used to predict the optimal insertion parameters through a machine learning model based on the physical parameters and slot information of the network card; the state machine control module is used to convert the optimal insertion parameters into control instructions through state machine conversion, and guide automated insertion; the fixing and self-locking module is used to complete the insertion, and the bionic protrusion array in the slot is used to achieve preliminary adsorption through van der Waals force, combined with the pressure sensor and the self-locking mechanism triggered by the electronic control unit to fix the network card; the vibration testing and optimization module is used to simulate the actual use environment through the built-in vibration testing unit after the network card is fixed, monitor the vibration response of the network card in real time, detect the installation stability, and optimize the machine learning model according to the detection results.

[0104] This embodiment also provides a computer device, which is suitable for the network card installation method of an electronic device, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the network card installation method of the electronic device proposed in the above embodiment.

[0105] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0106] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the network card installation method for an electronic device as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0107] In summary, the present invention realizes comprehensive perception of the physical parameters and slot information of the network card during the insertion process through: the data acquisition module, which ensures high-precision control during the installation process, and finally achieves the effect of improving the installation success rate and reducing human errors; through the fixing and self-locking module, it realizes the initial adsorption of the network card through the van der Waals force by the bionic protrusion array after the network card is inserted, and combines the pressure sensor and the electronic control unit to trigger the self-locking mechanism to fix the network card, thereby enhancing the long-term stability of the network card after installation, and finally achieving the effect of ensuring the long-term reliable operation of the equipment.

[0108] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for installing a network card in an electronic device, characterized in that: include, Using multiple types of sensors and cameras to collect physical parameters and slot information of the network card during insertion, the multiple types of sensors include pressure sensors, angle sensors, and position sensors; Based on the physical parameters and slot information of the network card, a machine learning model is used to predict the optimal insertion parameters. This is then converted into control instructions through state machine transitions, guiding automated insertion. After insertion, the bionic protrusion array in the slot achieves initial adsorption through van der Waals force, and then combines with the pressure sensor and triggers the self-locking mechanism through the electronic control unit to fix the network card; After the network card is fixed, the built-in vibration test unit simulates the actual usage environment, monitors the vibration response of the network card in real time, detects the installation stability, and optimizes the machine learning model based on the test results.

2. The method for installing a network card in an electronic device according to claim 1, wherein: The physical parameters of the network card include pressure data, angle data, position data, image data and time series; The slot information includes size, material characteristics, environmental conditions, interface type, power requirements, heat dissipation requirements, and supported communication protocols.

3. The method for installing a network card in an electronic device according to claim 2, wherein: The optimal insertion parameters are predicted by a machine learning model based on physical parameters and slot information. The specific steps are as follows: The collected network card physical parameters and slot information are de-noised, missing values ​​filled, and normalized. Principal component analysis is used to identify the features that have the greatest impact on the insertion process and generate feature engineering. Build a machine learning model based on feature engineering. Use random partitioning to divide physical parameters and slot information into training, validation, and test sets. Use the training set to train the machine learning model, use the validation set to adjust hyperparameters, and use the test set to evaluate the performance of the machine learning model and optimize the machine learning model performance indicators. After the training is completed, the physical parameters and slot information of the network card are input into the machine learning model as prediction data to predict the optimal insertion parameter P.

4. The method for installing a network card in an electronic device according to claim 3, wherein: The optimal insertion parameters are converted into control instructions through state machine conversion, and the automatic insertion is guided. The specific steps are as follows: Based on the optimal insertion parameter P, set the current state, condition, action and next state of the state machine; Based on the current state, conditions, actions, and next states of the state machine, a state transition diagram is constructed to describe all paths from the initial state to the final state of the network card insertion and the corresponding actions. Write the switch-case structure in C language based on the state transition diagram to implement the state machine logic; Based on the state machine logic, the state machine reaches a specific state and generates corresponding control instructions; The control instructions are decomposed into specific action parameters, mapped to the automation equipment, and converted into digital commands. The control equipment approaches the slot at a low speed while monitoring the sensor data in real time. When the insertion depth reaches the target value and the sensor feedback is stable, the insertion is determined to be complete.

5. The method for installing a network card in an electronic device according to claim 4, wherein: After the insertion is completed, the bionic protrusion array in the slot is initially adsorbed by van der Waals force. The specific steps are as follows: Based on biomimetics, we selected organisms with strong adhesion in nature and used scanning electron microscopy (SEM) and X-ray photoelectron spectroscopy (XPS) to analyze the microstructural characteristics and chemical composition of the target organisms' attachment sites. Defining the geometric shape and size parameters of the biomimetic protrusion array within the slot based on microstructural features and chemical composition; constructing the overall layout of the protrusion array based on geometric shape and size parameters; Based on the layout of the bionic protrusion array in the slot, a three-dimensional micro-nanostructure of the bionic protrusion array in the slot is constructed by femtosecond laser; When the distance between the three-dimensional micro-nanostructure of the bionic protrusion array and the surface of the network card reaches the molecular level, it enters the range of van der Waals force; During the contact process, the elastic deformation of the bionic protrusion array increases the van der Waals force and forms initial adsorption.

6. The method for installing a network card in an electronic device according to claim 5, wherein: The specific steps of combining the pressure sensor and triggering the self-locking mechanism through the electronic control unit to fix the network card are as follows: Set the pressure threshold based on the pressure change generated when the network card is inserted; During the insertion process, the pressure is monitored in real time through the pressure sensor. When the pressure reaches the pressure threshold, the electronic control unit receives the pressure sensor signal and converts it into a control instruction; Based on the control instructions, the actuator in the self-locking mechanism is activated, the motor is driven to adjust the mechanical structure, and the self-locking mechanism is triggered to fix the network card; The actuator specifically refers to a component that receives control instructions and drives mechanical parts to move.

7. The method for installing a network card in an electronic device according to claim 6, wherein: The built-in vibration test unit simulates the actual use environment, the acceleration sensor monitors the vibration response of the network card in real time, detects the installation stability, and optimizes the machine learning model based on the test results. The specific steps are as follows: A built-in vibration test unit is constructed based on sine wave, random vibration and impact vibration that simulate the actual environment. The built-in vibration test unit consists of a vibration table, controller, acceleration sensor and data acquisition equipment; The built-in vibration test unit uses an accelerometer to monitor the vibration response of the network card in real time and record the data. The data recorded by the accelerometer is then analyzed in depth to calculate the looseness index S. Based on the historical data of the network card stable state and the network card unstable state, the average loose index S is calculated respectively, and the boundary value between the two is set to define the loose threshold S1; When S>S1, it is determined that the network card is loose; When S≤S1, the network card is determined to be well fixed; During the network card insertion process, pressure, angle, position data and the final fixation effect are collected in real time, stored in the cloud database, and the machine learning model is optimized.

8. A network card installation device for an electronic device, based on the network card installation method for an electronic device according to any one of claims 1 to 7, characterized in that: Including data acquisition module, insertion parameter prediction module, state machine control module, fixing and self-locking module and vibration testing and optimization module; The data acquisition module is used to collect the physical parameters and slot information of the network card during the insertion process using multiple types of sensors and cameras; Insertion parameter prediction module, which uses a machine learning model to predict optimal insertion parameters based on the physical parameters and slot information of the network card; A state machine control module is used to convert the optimal insertion parameters into control instructions through state machine conversion and guide the automatic insertion; The fixing and self-locking module is used to fix the network card after insertion. The bionic protrusion array in the slot achieves initial adsorption through van der Waals force, and the pressure sensor is combined with the electronic control unit to trigger the self-locking mechanism to fix the network card; The vibration testing and optimization module is used to simulate the actual usage environment through the built-in vibration testing unit after the network card is fixed, monitor the vibration response of the network card in real time, detect the installation stability, and optimize the machine learning model based on the test results.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for installing a network card in an electronic device according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for installing a network card in an electronic device according to any one of claims 1 to 7 are implemented.

Images