Omnibearing plastic spraying optimization method and system for folding sofa bed frame

Abstract

The invention relates to the technical field of data processing, in particular to an omnibearing plastic spraying optimization method and system for a folding sofa bed frame. Comprising the steps that geometric data of the surface of the folding sofa bed frame are obtained in real time through a sensor array, shape features are obtained based on the data, then a surface area is divided, and geometric partitions of a plane and a corner area are determined; generating a preliminary electric field configuration scheme according to the electric field intensity demand characteristics of each geometric partition, analyzing the scheme through a neural network model, and optimizing electric field intensity distribution; further, a control signal is generated based on the refined electric field intensity distribution, a dynamic response sequence is obtained, and control parameters are optimized by extracting deposition effect indexes; and geometric changes are monitored in real time according to the updated control parameters, and a final electric field parameter set is obtained. The problem of uneven electric field distribution caused by geometric changes in different states in the plastic spraying process of the folding sofa bed frame is solved, and dynamic optimization of the electric field intensity and uniformity of the plastic spraying effect are achieved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for optimizing all-around powder coating for folding sofa bed frames. Background Technology

[0002] With the continuous development of modern furniture design, folding sofa bed frames, as a furniture product that combines comfort and functionality, are increasingly favored by consumers. Folding sofa bed frames have complex geometric shapes and exhibit dynamic changes during use, folding and unfolding. This characteristic presents many challenges to traditional surface treatment technologies, especially powder coating processes, in practical applications.

[0003] Traditional powder coating technology relies on a fixed electric field intensity distribution, ensuring a uniform coating effect in a static state. However, due to the dynamic nature of the surface geometry of folding sofa bed frames, especially the changes in surface shape during folding and unfolding, traditional powder coating methods cannot adapt to these geometric changes in real time, leading to unstable coating quality, particularly in high-curvature corner areas. Common problems include uneven coating thickness, insufficient adhesion, and unsatisfactory coating results, especially in corner areas when folded, where the coating effect is often less uniform than on flat areas.

[0004] The root of these problems lies in the fact that traditional powder coating processes cannot acquire real-time data on the geometric changes of the folding sofa bed frame surface, nor can they adjust the electric field intensity of the coating according to the characteristics of different areas. Therefore, how to solve the problem of uneven electric field distribution under dynamic geometric changes and achieve comprehensive powder coating optimization for folding sofa bed frames has become a technical challenge that the industry urgently needs to solve.

[0005] To address the challenges posed by variations in the surface geometry of folding sofa bed frames, this invention proposes a comprehensive powder coating optimization method and system for folding sofa bed frames. This method combines a sensor array, a neural network model, and electric field strength optimization control technology. It can sense changes in the surface geometry of the sofa bed frame in real time and dynamically adjust the electric field strength according to the needs of different areas, thereby achieving precise powder coating distribution. Summary of the Invention

[0006] This invention provides a comprehensive powder coating optimization method and system for folding sofa bed frames. It addresses the problem that traditional powder coating processes cannot effectively adapt to folding and unfolding states during geometric changes on the sofa bed frame surface by employing precise electric field distribution optimization technology. In a first aspect, a method for optimizing all-around powder coating for folding sofa bed frames, the method comprising: Step S1: Acquire real-time geometric data of the surface of the folding sofa bed frame through a sensor array, and obtain shape features based on the real-time geometric data; divide the surface area according to the shape features using a region segmentation algorithm to determine the geometric partitions representing the planar area and the corner area; Step S2: Extract the corresponding electric field strength requirement features from the geometric partition, and obtain a preliminary electric field configuration scheme based on the electric field strength requirement features; analyze the preliminary electric field configuration scheme through a neural network model to obtain a refined electric field strength distribution; Step S3: Generate a control signal based on the refined electric field intensity distribution to obtain a dynamic response sequence; extract deposition effect indicators from the dynamic response sequence; optimize the dynamic response sequence parameters based on the deposition effect indicators; generate an adaptive adjustment path based on the optimized dynamic response sequence parameters; and obtain updated control parameters based on the adaptive adjustment path. Step S4: Monitor the geometric changes of the folding sofa bed frame according to the updated control parameters, and adjust the electric field intensity distribution by rapid electric field redistribution according to the geometric changes to obtain the final electric field parameter set.

[0007] As a preferred embodiment of the present invention, step S1 involves obtaining the shape features of the sofa bed frame, including: Real-time geometric data of the surface of the folding sofa bed frame is collected by a sensor array; the real-time geometric data is preprocessed to extract feature points in the planar and corner areas; shape feature data representing the distribution of the planar and corner areas is generated based on the feature points; the shape feature data is normalized to obtain standardized shape features; the standardized shape features are filtered and denoised to determine the final shape features of the sofa bed frame.

[0008] As a preferred embodiment of the present invention, step S1, determining the geometric partitions representing the plane and corner regions, includes: The geometric data of the folding sofa bed frame is processed using a region segmentation algorithm based on the shape features. The shape features are divided into planar regions and high-curvature corner regions. For the planar regions and high-curvature corner regions, the boundary features of each region are extracted. The type and boundary range of each region are determined based on the boundary features. The boundary range is verified. If the boundary range deviation exceeds a preset threshold, the segmentation parameters are readjusted. The classified geometric partition data is generated based on the adjusted segmentation parameters.

[0009] As a preferred embodiment of the present invention, step S2, obtaining a preliminary electric field configuration scheme, includes: Geometric features of planar regions and high-curvature corner regions are extracted from the geometric partitions; uniform electric field strength parameters are calculated for the planar regions; differential electric field strength parameters are calculated for the high-curvature corner regions; if the proportion of the planar regions is higher than a preset threshold, uniform electric field strength is preferentially allocated; a preliminary electric field configuration scheme is generated based on the uniform electric field strength and the differential electric field strength; the preliminary electric field configuration scheme is normalized to obtain standardized configuration data.

[0010] As a preferred embodiment of the present invention, step S2, obtaining the refined electric field intensity distribution, includes: The preliminary electric field configuration scheme is input into a pre-trained neural network model; the matching degree between the preliminary electric field configuration scheme and historical deposition data is analyzed through the neural network model; an optimization adjustment vector is generated based on the matching degree; pulse mode parameters for high curvature corner regions are determined based on the optimization adjustment vector; the preliminary electric field configuration scheme is adjusted based on the pulse mode parameters; and refined electric field intensity distribution data is generated.

[0011] As a preferred embodiment of the present invention, step S3, obtaining the dynamic response sequence, includes: Voltage and current control signals are generated based on the refined electric field intensity distribution; the output acceleration of each node is adjusted; it is determined whether the field intensity deviation in the high curvature corner region exceeds a preset threshold. If so, the control signal is corrected through feedback loop; a dynamic response sequence is generated based on the corrected control signal.

[0012] As a preferred embodiment of the present invention, step S3, obtaining the updated control parameters, includes: Real-time deposition performance indicators are extracted from the dynamic response sequence; the dynamic response sequence parameters are optimized using a gradient descent algorithm based on the real-time deposition performance indicators; updated voltage and current values ​​are calculated based on the optimized dynamic response sequence parameters; an adaptive adjustment path is generated for the updated voltage and current values; the stability of the adaptive adjustment path is verified, and if the path deviation exceeds a preset threshold, the parameters are re-optimized; updated control parameters are generated based on the verification results.

[0013] As a preferred embodiment of the present invention, in step S4, the final electric field parameter set is obtained, including: The system monitors the geometric change events of the folding sofa bed frame in real time according to the updated control parameters; if the system switches from a planar state to a folded state, it triggers a rapid electric field reconfiguration; the electric field intensity distribution is adjusted according to the rapid electric field reconfiguration; dynamic electric field parameters are generated for the geometric change; the dynamic electric field parameters are verified to determine whether the parameter deviation exceeds a preset threshold, and if so, they are readjusted; the final electric field parameter set is generated according to the adjustment result.

[0014] Secondly, the present invention also provides an all-around powder coating optimization system for folding sofa bed frames, for implementing the above-mentioned method, the system comprising: The geometric partitioning unit is used to acquire real-time geometric data of the surface of the folding sofa bed frame through a sensor array, obtain shape features based on the real-time geometric data, and divide the surface area according to the shape features using a region segmentation algorithm to determine the geometric partitions that characterize the planar area and the corner area. An electric field distribution acquisition unit is used to extract corresponding electric field intensity requirement features from the geometric partitions, obtain a preliminary electric field configuration scheme based on the electric field intensity requirement features, and analyze the preliminary electric field configuration scheme through a neural network model to obtain a refined electric field intensity distribution. A control signal generation unit is used to generate a control signal based on the refined electric field intensity distribution to obtain a dynamic response sequence; extract deposition effect indicators from the dynamic response sequence; optimize the dynamic response sequence parameters based on the deposition effect indicators; generate an adaptive adjustment path based on the optimized dynamic response sequence parameters; and obtain updated control parameters based on the adaptive adjustment path. A geometric change monitoring unit is used to monitor the geometric changes of the folding sofa bed frame according to the updated control parameters; An electric field redistribution unit is used to adjust the electric field intensity distribution through rapid electric field redistribution based on the geometric changes, thereby obtaining the final electric field parameter set.

[0015] Thirdly, the present invention also provides a computer-readable storage medium storing instructions that, when executed by a processor, implement the above-described method.

[0016] The beneficial effects of this invention are as follows: This invention acquires real-time geometric data of the surface of a folding sofa bed frame using a sensor array. This data includes the shape features of planar and corner areas. A region segmentation algorithm accurately divides the surface areas of the sofa bed frame and determines the geometric partitions of each area, providing a foundation for subsequent electric field configuration. This ensures that the characteristics of different geometric areas, such as planar and corner areas, are effectively identified and analyzed. Electric field strength requirement features are extracted from the geometric partitions, and a preliminary electric field configuration scheme is generated. A neural network model analyzes the preliminary scheme to obtain a refined electric field strength distribution. This scheme can learn from historical data and optimize the electric field configuration, ensuring that the electric field strength accurately adapts to the needs of each area. This not only improves the accuracy of the electric field configuration but also effectively avoids the uneven electric field distribution defects of traditional methods. A control signal is generated based on the refined electric field strength distribution to obtain a dynamic response sequence. Real-time data is extracted from the dynamic response sequence... The system optimizes dynamic response sequence parameters and generates an adaptive adjustment path to ensure real-time adjustment of the electric field strength, adapting to changes in the sofa bed frame's geometry under different conditions. When the sofa bed frame switches from a planar state to a folded state, the system monitors its geometric changes based on updated control parameters. By rapidly calculating the electric field strength distribution, it ensures that corner areas are fully compensated during folding, avoiding electric field attenuation caused by curvature changes and ensuring uniformity of the deposition effect. Continuous adjustments are made through a dynamic feedback mechanism to generate the final electric field parameter set, ensuring the efficiency and stability of the powder coating process. The synergy of these technical solutions solves the challenges of traditional methods in handling the complex geometry of folding sofa bed frames, improves the uniformity and stability of the powder coating, and significantly optimizes production efficiency and product quality. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the all-around powder coating optimization method for folding sofa bed frames in the embodiment; Figure 2 This is a structural diagram of the all-around powder coating optimization system used for folding sofa bed frames in the embodiment; Figure 3 This is a diagram illustrating the electric field strength compensation effect of the bed frame angle change in the embodiment. Detailed Implementation

[0019] This invention provides a method and system for omnidirectional powder coating optimization of a folding sofa bed frame. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] For ease of understanding, the specific process of the embodiments of the present invention will be described below, such as... Figure 1 As shown, one embodiment of the all-around powder coating optimization method for folding sofa bed frames in this invention includes: Step S1: Acquire real-time geometric data of the surface of the folding sofa bed frame through a sensor array, and obtain shape features based on the real-time geometric data; divide the surface area according to the shape features using a region segmentation algorithm to determine the geometric partitions representing the planar area and the corner area; In step S1, the shape features of the sofa bed frame are obtained, including: Real-time geometric data of the surface of the folding sofa bed frame is collected by a sensor array; the real-time geometric data is preprocessed to extract feature points in the planar and corner areas; shape feature data representing the distribution of the planar and corner areas is generated based on the feature points; the shape feature data is normalized to obtain standardized shape features; the standardized shape features are filtered and denoised to determine the final shape features of the sofa bed frame.

[0021] Specifically, as a type of furniture product with a dynamically changing form, the surface geometry of a folding sofa bed frame undergoes significant changes during unfolding and folding. These geometric changes place high demands on surface treatment processes such as powder coating. Maintaining the uniformity and stability of the powder coating effect during folding and unfolding is a significant technical challenge. Traditional surface treatment methods cannot adjust process parameters in real time according to the changes in the bed frame's surface shape, leading to problems such as uneven electric field distribution and uneven coating during powder coating. Particularly in high-curvature corner areas, the coating often suffers from insufficient deposition or excessive thickness. Therefore, in the embodiments of this invention, a sensor array is first used to collect real-time geometric data of the folding sofa bed frame surface. The data is used to obtain shape features. A specific sensor array is arranged around the perimeter of the folding sofa bed frame to capture the surface point cloud data of the sofa bed frame in real time, generating an initial geometric dataset. The real-time collected geometric data is preprocessed, with a focus on extracting feature points in the planar and corner areas. By calculating the curvature value of each point in the initial geometric dataset, points with curvature below a preset threshold can be effectively identified as feature points in the planar area. Meanwhile, points with higher curvature are processed by a clustering algorithm. The clustering results can accurately extract feature points in the corner areas, thus forming a feature point set. For example, during the transition of the folding sofa bed frame from a planar to a folded state, this step ensures that the feature points capture dynamic changes and reduces errors.

[0022] Based on this, shape feature data representing the distribution of planar and corner regions is generated by combining the feature point set. Specifically, the area ratio of the planar region is first calculated, and a distribution vector is generated. Boundary contour data is generated by combining the position of the corner points. The above data constitutes the complete shape feature data. To ensure data consistency and smooth subsequent processing, the above shape feature data needs to be normalized. The minimum-maximum normalization method is used to map the data to the interval between 0 and 1, thereby obtaining standardized shape feature data, which can avoid noise interference caused by data scale differences in subsequent filtering processes. Based on the standardized shape feature data, a filtering algorithm is used to remove noise to ensure that the extracted data is more accurate and reliable. Specifically, a Gaussian filter is used to smooth the standardized data, effectively eliminating isolated noise points and improving data accuracy. After filtering, the consistency of the data is verified to determine the final shape features, which are then stored as input data for subsequent region segmentation. During storage, the final shape features are converted into matrix format to ensure that the data can be successfully used by subsequent region segmentation algorithms, providing necessary geometric information for subsequent electric field configuration and optimization.

[0023] Through the above technical solution, from real-time geometric data acquisition from the sensor array to final shape feature storage, by accurately extracting and processing feature point data of planar and corner areas, combined with the fine processing of filtering algorithms, it is possible to ensure that changes in surface geometry are reflected in a timely manner, thereby realizing dynamic adjustment of electric field strength. This not only effectively improves the uniformity of powder coating, but also enhances the ability to adapt to complex geometries, ensuring the consistency and stability of powder coating effect during folding and unfolding.

[0024] Further, in step S1, determining the geometric partitions representing the plane and corner regions includes: The geometric data of the folding sofa bed frame is processed using a region segmentation algorithm based on the shape features. The shape features are divided into planar regions and high-curvature corner regions. For the planar regions and high-curvature corner regions, the boundary features of each region are extracted. The type and boundary range of each region are determined based on the boundary features. The boundary range is verified. If the boundary range deviation exceeds a preset threshold, the segmentation parameters are readjusted. The classified geometric partition data is generated based on the adjusted segmentation parameters.

[0025] Specifically, in the embodiments of the present invention, real-time geometric data of the surface of the folding sofa bed frame is collected by a sensor array, and shape features are generated based on the collected data. Then, a region segmentation algorithm is used to segment the shape features of the folding sofa bed frame surface. Specifically, a watershed algorithm is used to initially group the above-mentioned shape features, thereby forming a preliminary outline of the surface region. Then, based on the shape features, the surface region is divided into planar regions and high-curvature corner regions, wherein the curvature value is obtained by the Gaussian curvature formula, that is, for a surface point P, its Gaussian curvature K is equal to the product of the maximum principal curvature k1 and the minimum principal curvature k2. If K is less than a set curvature, it is determined to be a plane; if K is greater than or equal to a set curvature, such as 0.3, it is determined to be a high curvature corner. Regions with curvature lower than the set curvature are determined to be plane regions, while regions with curvature greater than or equal to the set curvature are determined to be corner regions. For high curvature corner regions, clustering algorithms such as k-means are used to accurately identify the boundaries of the regions, ensuring more accurate division between corner regions and plane regions. To ensure the accuracy of region division, the boundary features of each region are further extracted, especially by using the Canny edge detection algorithm to identify the boundaries of each region, thereby forming a boundary chain code representation. Through the analysis of the above boundary features, the type of each region and its corresponding boundary range can be effectively determined. For plane regions, a rectangular bounding box is usually used to represent their boundary range, while high curvature corner regions may use a more complex geometric representation to accurately capture the shape features of these regions.

[0026] Building upon this foundation, to further improve the accuracy of region segmentation, a verification mechanism is employed to determine the deviation of the boundary range. Specifically, when the deviation exceeds a preset threshold, the parameters of the region segmentation are adjusted to ensure segmentation accuracy. For example, if the difference between the boundary range and the original geometric data exceeds the preset threshold, Hausdorff distance measurement is used. If the distance is greater than the threshold, the deviation is considered excessive, and the parameters of the segmentation algorithm are adjusted, such as increasing the merging threshold of the watershed algorithm. This process is iterated until the boundary deviation drops below the predetermined threshold, thereby achieving a rapid response to geometric changes and ensuring the accuracy of region segmentation. This is especially important during the folding process of sofa bed frames. Verification and adjustment of the boundary range ensures accurate identification and rapid response in corner areas, effectively avoiding uneven deposition caused by uneven field strength distribution. The verified and adjusted boundary data will be encapsulated into classified geometric partition data and stored as input data for subsequent electric field strength requirement feature extraction. Through the above technical solution, the surface geometry of the folding sofa bed frame can be accurately captured and analyzed in different states, such as switching from unfolded to folded, thereby providing high-quality geometric data support for subsequent electric field distribution optimization. This ensures that the powder coating process can adapt to changes in the surface morphology of the sofa bed frame in real time, improving the uniformity and stability of the powder coating effect.

[0027] Step S2: Extract the corresponding electric field strength requirement features from the geometric partition, and obtain a preliminary electric field configuration scheme based on the electric field strength requirement features; analyze the preliminary electric field configuration scheme through a neural network model to obtain a refined electric field strength distribution; In step S2, a preliminary electric field configuration scheme is obtained, including: Geometric features of planar regions and high-curvature corner regions are extracted from the geometric partitions; uniform electric field strength parameters are calculated for the planar regions; differential electric field strength parameters are calculated for the high-curvature corner regions; if the proportion of the planar regions is higher than a preset threshold, uniform electric field strength is preferentially allocated; a preliminary electric field configuration scheme is generated based on the uniform electric field strength and the differential electric field strength; the preliminary electric field configuration scheme is normalized to obtain standardized configuration data.

[0028] Specifically, based on the aforementioned geometric partitioning, electric field strength requirement features are extracted from the surface geometric data of the folding sofa bed frame to obtain a preliminary electric field configuration scheme. First, the geometric features of planar regions and high-curvature corner regions are extracted by analyzing the geometric partitioning data. Specifically, the geometric characteristics of each region are calculated, such as the flatness of the planar regions and the radius of curvature of the corner regions. This ensures that the extracted features accurately reflect the real-time shape of the sofa bed frame. The flatness of the planar regions is calculated using the consistency of surface normal vectors, while the radius of curvature of the corner regions is derived using the Gaussian curvature formula, ensuring that the shapes of different regions can be correctly divided to support the reasonable allocation of subsequent electric field strength requirements. After extracting the above geometric features, the area ratio of the planar regions and the high-curvature corner regions are further quantified through geometric statistics of the partitioning data. Edge length: The aforementioned area ratio and edge length provide necessary input data for subsequent electric field strength calculations, helping to accurately identify different electric field requirements in planar and corner regions, and supporting electric field configuration. For planar regions, uniform electric field strength parameters are calculated. The planar region is considered an ideal flat plate structure, and a uniform distribution model is applied based on its geometric characteristics to calculate the electric field strength, thereby ensuring a stable electric field strength distribution and supporting the uniformity of the deposition process. The training data for the uniform distribution model includes the geometric characteristics of historical planar regions and their corresponding electric field strength parameters. The determination of these parameter values ​​depends not only on the geometric characteristics but also on the material properties of the sofa bed frame, such as the conductivity of metals, to match with historical data and ensure the effectiveness and stability of the calculated electric field strength parameters in practical applications.

[0029] For high-curvature corner regions, a differentiated approach to electric field intensity configuration is adopted. This involves analyzing the geometric characteristics of these regions and applying a local enhancement model to calculate differentiated electric field intensity parameters. This model is based on the inverse relationship between the radius of curvature and the electric field intensity; that is, the smaller the radius of curvature, the higher the required electric field intensity, thus compensating for field attenuation at the corner. Furthermore, pulse mode adjustment is introduced through the calculation of these differentiated electric field intensity parameters. Pulse mode adjustment refers to dynamically optimizing the electric field in high-curvature corner regions by adjusting the pulse characteristics of the electric field, including pulse frequency, amplitude, and duty cycle. The intensity distribution ensures uniform coating deposition in these areas, compensating for electric field attenuation or non-uniformity caused by geometric changes, such as increased curvature at corners. Especially for areas with large curvature, the electric field intensity parameters are dynamically adjusted according to real-time curvature changes to respond to changes in the folding state, ensuring that the electric field intensity distribution is stable under different states and can effectively cope with the effects of geometric changes. The training data for the local enhancement model consists of the geometric features of historical high curvature corner areas and the corresponding differentiated electric field intensity parameters. The local enhancement model is trained based on machine learning algorithms using the above training data.

[0030] After obtaining the aforementioned electric field strength parameters, it is determined whether the proportion of the planar region exceeds a preset threshold. If the proportion of the planar region exceeds the preset threshold, a uniform electric field strength is preferentially allocated. This is determined by calculating the ratio of the area of ​​the planar region to the total area. If the proportion exceeds the preset threshold (e.g., 70%), the uniform electric field strength parameters are applied to the entire configuration to prioritize ensuring the deposition efficiency of large, flat areas. The area is calculated by integrating the geometric boundaries of the partitions, thus quickly determining the electric field strength configuration for that area. In particular, the real-time monitoring and dynamic adjustment mechanism ensures that the electric field allocation can respond rapidly during the process of the sofa bed frame folding and unfolding. The electric field priority allocation in planar areas ensures deposition efficiency over large areas. The electric field intensity configuration data for the planar areas and high-curvature corner areas are normalized and used as the electric field configuration scheme. This technical solution ensures that the powder coating optimization process of the folding sofa bed frame can adapt to changes in the bed frame's geometry in real time, achieving precise electric field intensity allocation. By extracting electric field demand characteristics from geometric data, applying differentiated electric field intensity calculations for different areas, and performing real-time feedback and adjustments, uniformity and stability during the powder coating process are ensured, thereby optimizing the deposition effect, reducing material waste, and improving process efficiency.

[0031] Further, in step S2, the refined electric field intensity distribution is obtained, including: The preliminary electric field configuration scheme is input into a pre-trained neural network model; the matching degree between the preliminary electric field configuration scheme and historical deposition data is analyzed through the neural network model; an optimization adjustment vector is generated based on the matching degree; pulse mode parameters for high curvature corner regions are determined based on the optimization adjustment vector; the preliminary electric field configuration scheme is adjusted based on the pulse mode parameters; and refined electric field intensity distribution data is generated.

[0032] Specifically, the aforementioned preliminary electric field configuration scheme is analyzed using a pre-trained neural network model to obtain a refined electric field intensity distribution. First, the preliminary electric field configuration scheme is input into the neural network model, which is trained based on a convolutional neural network (CNN) architecture specifically designed to process electric field data related to geometric partitioning. In the input layer, the neural network model receives data on the proportion of planar regions and the field intensity parameters of high-curvature corner regions from the preliminary electric field configuration scheme and passes this data as an input vector to the model. The neural network model then processes the input data, analyzing the matching degree between the preliminary electric field configuration scheme and historical deposition data, particularly the deposition effect indicators under different folding states. Through the model's hidden layers, the neural network extracts the input features and calculates the field intensity distribution in the preliminary electric field configuration scheme and the corresponding deposition thickness in the historical deposition data. The similarity between the degrees is typically calculated using the cosine similarity formula. This formula calculates the similarity by multiplying the dot product of the input vector and the historical deposition data vector by the modulus. If the matching degree of the initial electric field configuration scheme is higher than a preset threshold, the configuration scheme is considered to have high accuracy; otherwise, it enters the low-matching adjustment process. In particular, the neural network model prioritizes historical deposition data in high-curvature corner regions during the matching degree analysis to ensure that the electric field intensity configuration in the corner regions can meet the actual powder coating requirements. After the matching degree analysis is completed, an optimized adjustment vector is generated based on the calculated matching degree. The optimized vector is extracted from the deviation value in the matching degree result. Each dimension corresponds to the adjustment range of a region type, such as the uniform field strength increment in planar regions and the pulse mode adjustment range in corner regions. The training data of the neural network model includes historical initial electric field configuration schemes and corresponding optimized adjustment vectors.

[0033] After generating the optimized adjustment vector, the pulse mode parameters for the high-curvature corner region are determined. The pulse mode is adjusted by analyzing the corner-related dimensions in the optimized adjustment vector. The specific pulse frequency and amplitude are calculated based on the amplitude information in the adjustment vector. The pulse frequency is determined by multiplying the vector amplitude by a preset coefficient, while the amplitude is derived from successfully deposited pulse modes in historical data to ensure that the field strength deviation in the corner region does not exceed a preset threshold. If the adjustment requirement exceeds the threshold, a feedback loop mechanism is introduced to dynamically correct the pulse mode parameters to adapt to the rapid geometric changes when the sofa bed frame switches from a flat state to a folded state. This feedback mechanism ensures that the electric field in the corner region remains constant from unfolding to folding. Rapid response and optimization of intensity: After adjusting the pulse mode parameters, the initial electric field configuration scheme is optimized. The updated electric field intensity distribution is superimposed on the field intensity distribution in the corner area of ​​the initial scheme, thereby generating refined electric field intensity distribution data. The refined electric field intensity distribution data will be used as the final electric field configuration for subsequent voltage and current control signal generation, ensuring that the electric field distribution is more accurate and stable, meeting the powder coating requirements under different geometric states. The above refining process, through intelligent optimization by a neural network model, can respond in real time to changes in the geometric shape of the sofa bed frame surface, ensuring dynamic adjustment of the electric field intensity, thereby improving the uniformity, stability and overall effect of the powder coating process, reducing material waste and improving production efficiency.

[0034] Step S3: Generate a control signal based on the refined electric field intensity distribution to obtain a dynamic response sequence; extract deposition effect indicators from the dynamic response sequence; optimize the dynamic response sequence parameters based on the deposition effect indicators; generate an adaptive adjustment path based on the optimized dynamic response sequence parameters; and obtain updated control parameters based on the adaptive adjustment path. In step S3, the dynamic response sequence is obtained, including: Voltage and current control signals are generated based on the refined electric field intensity distribution; the output acceleration of each node is adjusted; it is determined whether the field intensity deviation in the high curvature corner region exceeds a preset threshold. If so, the control signal is corrected through feedback loop; a dynamic response sequence is generated based on the corrected control signal.

[0035] Specifically, the process of generating control signals and obtaining dynamic response sequences based on the refined electric field intensity distribution includes: first, converting the refined electric field intensity distribution data into voltage and current control signals; wherein, based on the refined electric field intensity distribution, voltage and current parameters are directly mapped to generate corresponding control signals to adjust the electric field intensity distribution; and adjusting the output of the control signals, especially the acceleration of each node. The nodes are specific locations on the surface of the folding sofa bed frame, such as corner areas, planar areas, or folding transition areas, and are typically associated with a sensor array for real-time monitoring and adjustment of the electric field distribution, acceleration, and other deposition parameters. Relevant parameters are used to optimize the powder coating process, ensuring the uniformity and stability of the coating. Based on the position of the nodes on the sofa bed frame surface and the refined electric field intensity distribution, the initial output acceleration of each node is calculated. Output acceleration represents the acceleration value of particles moving at the node under the control signal. These particles refer to the substances used for spraying, such as powder coatings, pigments, or other tiny particles. These particles are accelerated and deposited on the surface of the folding sofa bed frame under the action of the electrostatic field, forming a uniform coating. The calculated initial output acceleration is adjusted to adapt to the different needs between the planar and corner areas, ensuring that the deposition effect in different areas reaches the optimal level. In the unfolded state, the node acceleration in the planar area is adjusted to a uniform value to ensure consistent deposition. In the corner area, a curvature factor is introduced during adjustment. The curvature factor is calculated based on the geometric data collected by the sensor array and represents a quantitative value of the corner curvature. The curvature factor affects the magnitude of acceleration adjustment, ensuring concentrated field strength in the corner area, thereby improving the deposition response in the corner area. For example, when the sofa bed frame is in the unfolded state, the node output acceleration is adjusted to a uniform value to ensure consistent deposition effect in the planar area; this improves the uniformity and efficiency of deposition and avoids material waste.

[0036] If the sofa bed frame changes state, such as switching from a flat state to a folded state, the node output acceleration will dynamically increase to compensate for the field strength attenuation caused by the geometric change. For example, when the sofa bed frame switches from a flat state to a folded state, the node output acceleration will dynamically increase by 15% to compensate for the field strength attenuation caused by the geometric change, achieving rapid response and precise distribution. The above dynamic adjustment ensures that the system can respond to geometric changes in real time and maintain the consistency and stability of the deposition effect, optimize the deposition process, and reduce material waste. Furthermore, if the field strength deviation in the high curvature corner area exceeds the preset threshold, the deviation value is monitored and calculated in real time, and a feedback loop is started to correct the control signal. The feedback loop corrects the signal by iteratively adjusting the voltage and current parameters. Each iteration is fine-tuned based on the previous deviation value to ensure that the field strength deviation quickly converges to the allowable range, and finally outputs the corrected control signal. To ensure the deposition accuracy in the corner area, the above correction process further optimizes the voltage and current parameters by calculating the deviation gradient. For example, when the deviation gradient is positive, the voltage parameter is increased to improve the field strength, quickly responding to and optimizing the deposition effect in the corner area.

[0037] After the control signal is corrected, a dynamic response sequence is generated based on the corrected control signal. The above sequence is presented in the form of a time series for subsequent time series analysis. The above technical solution ensures that the powder coating effect of the folding sofa bed frame in different geometric states always meets expectations through precise control signal adjustment, acceleration regulation, feedback correction and dynamic response analysis. It improves the stability, accuracy and efficiency of the powder coating process and avoids deposition instability and material waste caused by uneven electric field.

[0038] Further, in step S3, the updated control parameters are obtained, including: Real-time deposition performance indicators are extracted from the dynamic response sequence; the dynamic response sequence parameters are optimized using a gradient descent algorithm based on the real-time deposition performance indicators; updated voltage and current values ​​are calculated based on the optimized dynamic response sequence parameters; an adaptive adjustment path is generated for the updated voltage and current values; the stability of the adaptive adjustment path is verified, and if the path deviation exceeds a preset threshold, the parameters are re-optimized; updated control parameters are generated based on the verification results.

[0039] Specifically, according to the embodiments of the present invention, the process of extracting real-time deposition effect indicators from the dynamic response sequence and obtaining updated control parameters first includes extracting real-time deposition effect indicators from the dynamic response sequence; specifically, by parsing the timestamp data in the dynamic response sequence, key frames related to the deposition process are identified, and then indicators such as deposition thickness uniformity and adhesion rate are calculated to form a set of real-time deposition effect indicators. The above indicators directly reflect the influence of electric field configuration on the deposition effect, ensuring that the changes in different areas of the sofa bed frame surface during the deposition process can be accurately captured; for example, in the electrostatic deposition process of a folding sofa bed frame, the real-time deposition effect indicators include thickness deviation values. If the sequence shows that the thickness of the planar area is 2.5 mm and the corner area is 1.8 mm, then the deviation indicator is extracted for subsequent optimization.

[0040] Based on the extracted real-time deposition performance indicators, a gradient descent algorithm is used to optimize the sequence parameters. The real-time deposition performance indicators are input into the gradient descent algorithm, and a loss function is calculated. The loss function is defined as the mean square error between the actual deposition thickness and the target thickness. The gradient descent algorithm iteratively optimizes the parameters, adjusting electric field parameters such as pulse frequency and amplitude, to reduce the value of the loss function until the set accuracy requirements are met. In the above process, the gradient descent algorithm not only adjusts the differentiated parameters in the corner region, but also introduces a momentum term to accelerate convergence and avoid getting trapped in local minima, thereby improving deposition efficiency and reducing material waste.

[0041] Based on the optimized sequence parameters, updated voltage and current values ​​are calculated. Specifically, the optimized parameters are converted into voltage values ​​using a linear mapping function, and the corresponding current is further calculated to ensure power balance. The above adjustments directly utilize the optimized electric field parameters to generate voltage and current values, providing a necessary foundation for subsequent control signal generation and electric field adjustment. On this basis, an adaptive adjustment path is generated for the generated voltage and current values. This adaptive adjustment path is a control sequence of voltage and current values ​​changing over time. The path automatically adjusts the electric field strength according to the geometric changes on the sofa bed frame surface, ensuring the uniformity and stability of the electric field distribution under different geometric states, such as the transition from a flat to a folded state. Specifically, by constructing a path sequence, the voltage and current values ​​are arranged in chronological order, and geometric change detection points are inserted to form an adaptive path to respond to folding events. This path is used to handle the transition of the sofa bed frame from a flat to a folded state. The adaptive adjustment path ensures a smooth transition of electric field strength during geometric changes, maintaining the continuity of deposition and avoiding uneven deposition caused by increased angles during folding. The stability of the generated path needs to be verified. If the deviation of the path exceeds a preset threshold, a re-optimization process is triggered. The stability of the path is determined by calculating the variance of the path. If the deviation is greater than the set threshold, the gradient descent algorithm will be run again to adjust the relevant parameters until the path stability meets the requirements, ensuring that the electric field configuration can adapt to the changes in the sofa bed frame under different geometric shapes.

[0042] Furthermore, for rapid folding scenarios, the feedback loop mechanism can be further extended. During rapid folding, if the path deviation exceeds a threshold, the system will trigger an additional correction loop, prioritizing the adjustment of parameters in corner areas to ensure the deposition effect in these areas remains unaffected. For slowly changing scenarios, a rolling window method is used to calculate the deviation and perform local optimization as needed to maintain deposition uniformity and extend equipment lifespan. Based on the verification results, updated control parameters are generated. These parameters include optimized voltage and current control signals, as well as other control parameters required for adaptive path adjustment. This ensures the uniformity and stability of the electric field intensity on the sofa bed frame surface during deposition, achieving precise electric field distribution and rapid response. This effectively improves the stability of the powder coating process, reduces material waste, and ensures deposition quality and efficiency in complex geometries.

[0043] Step S4: Monitor the geometric changes of the folding sofa bed frame according to the updated control parameters, and adjust the electric field intensity distribution through rapid electric field redistribution based on the geometric changes to obtain the final electric field parameter set; specifically including: The geometric changes of the folding sofa bed frame are monitored in real time according to the updated control parameters; if the switch from a planar state to a folded state is detected, a rapid electric field reconfiguration is triggered; the electric field intensity distribution is adjusted according to the rapid electric field reconfiguration; dynamic electric field parameters are generated for the geometric changes; the dynamic electric field parameters are verified to determine whether the parameter deviation exceeds a preset threshold. If so, the parameters are readjusted; and the final electric field parameter set is generated based on the adjustment results.

[0044] Specifically, based on the updated control parameters, the geometric change events of the folding sofa bed frame are monitored in real time to ensure precise adjustment of the electric field intensity distribution. This is achieved by continuously collecting surface geometric data of the folding sofa bed frame using a sensor array, and dynamically adjusting the monitoring frequency according to the updated voltage and current control parameters. The sensor array includes displacement and angle sensors arranged on key nodes of the bed frame. These sensors can output real-time surface shape feature data of the sofa bed frame, providing necessary data support for subsequent geometric change monitoring. When the sofa bed frame switches from a planar state to a folded state, this change is detected and a rapid electric field reconfiguration process is triggered. During this process, the electric field intensity distribution is adjusted from real-time monitoring to... The system extracts current state indicators, such as the proportion of planar areas and the distribution of corner areas, from the geometric change events and compares them with preset planar state thresholds. If the proportion of planar areas is lower than the preset threshold and the proportion of corner areas increases beyond a predetermined range, it is determined that the bed frame has switched to the folded state. At this time, the folding mode parameters in the historical deposition data are called to initialize the reconfiguration vector and quickly recalculate the electric field intensity distribution to adapt to the high curvature requirements of the corner areas in the folded state. The calculation process of rapid electric field reconfiguration is accelerated by the pre-stored neural network model mentioned above to ensure that the reconfiguration process is completed within a set time after the geometric change occurs, avoiding the interruption of the deposition effect and maintaining the uniformity of the surface coating.

[0045] Based on the reconfiguration vector, the electric field intensity distribution is updated, and the electric field intensity parameters are adjusted for the planar and corner regions respectively to generate dynamic electric field parameters. Specifically, this includes extracting the pulse mode parameters for the corner region and the uniform field intensity parameters for the planar region. The aforementioned uniform field intensity parameters are optimized based on previous reconfiguration adjustments and real-time deposition results. The optimization process employs a gradient descent algorithm, which calculates the gradient of the electric field intensity parameters and gradually reduces the loss function along the negative gradient direction to refine the electric field parameters, ensuring that the electric field configuration can adapt to geometric changes in the folded state. After the dynamic electric field parameters are generated, they are verified and compared with preset targets using real-time deposition results indicators. If the parameter deviation exceeds a preset threshold, a readjustment process is triggered. The control signal is optimized through a feedback loop to further improve the deposition accuracy. By introducing the aforementioned neural network model, the adjustments in the feedback loop can not only be optimized based on historical deposition data but also automatically generate adjustment vectors based on current geometric changes, thereby ensuring the accuracy of the electric field parameters. During the adjustment process, the aforementioned neural network model analyzes the input real-time geometric features and historical deposition data through a multilayer perceptron structure, outputting optimized adjustment vectors to make the electric field configuration more closely match actual deposition requirements.

[0046] Finally, based on the verification results, a final electric field parameter set is generated. This parameter set includes optimized dynamic electric field parameters and is used for subsequent electric field distribution control. The final electric field parameter set ensures a smooth transition from the planar state to the folded state, maintains the continuity of the deposition process, avoids deposition unevenness caused by geometric changes, and achieves precise electric field distribution and rapid response. For example, as... Figure 3 As shown, when the bed frame angle changes from 0 degrees to 90 degrees, the sensor detects an increase in curvature in the corner area. After triggering reconfiguration, the electric field strength at the corner increases by 30%, which effectively compensates for the field strength deviation in the high curvature area and ensures uniform adhesion of the deposited particles. In another embodiment, if the folding speed is 10 degrees per second, the system prioritizes the allocation of pulse mode parameters, which shortens the reconfiguration time to 0.5 seconds, resulting in a fast response and reducing uneven deposition caused by geometric changes. This optimization process not only improves deposition efficiency but also reduces material waste, ensuring the high efficiency and stability of the powder coating process.

[0047] This invention also provides an all-around powder coating optimization system for folding sofa bed frames, used to achieve the above-mentioned method, such as... Figure 2 As shown, the system includes: The geometric partitioning unit is used to acquire real-time geometric data of the surface of the folding sofa bed frame through a sensor array, obtain shape features based on the real-time geometric data, and divide the surface area according to the shape features using a region segmentation algorithm to determine the geometric partitions that characterize the planar area and the corner area. An electric field distribution acquisition unit is used to extract corresponding electric field intensity requirement features from the geometric partitions, obtain a preliminary electric field configuration scheme based on the electric field intensity requirement features, and analyze the preliminary electric field configuration scheme through a neural network model to obtain a refined electric field intensity distribution. A control signal generation unit is used to generate a control signal based on the refined electric field intensity distribution to obtain a dynamic response sequence; extract deposition effect indicators from the dynamic response sequence; optimize the dynamic response sequence parameters based on the deposition effect indicators; generate an adaptive adjustment path based on the optimized dynamic response sequence parameters; and obtain updated control parameters based on the adaptive adjustment path. A geometric change monitoring unit is used to monitor the geometric changes of the folding sofa bed frame according to the updated control parameters; An electric field redistribution unit is used to adjust the electric field intensity distribution through rapid electric field redistribution based on the geometric changes, thereby obtaining the final electric field parameter set.

[0048] The present invention also provides a computer-readable storage medium storing instructions that, when executed by a processor, implement the above-described method.

[0049] In summary, this invention acquires geometric data of the folding sofa bed frame surface in real time using a sensor array. This data includes the shape features of planar and corner areas. Through a region segmentation algorithm, the surface areas of the sofa bed frame are accurately divided, and the geometric partitions of each area are determined, providing a foundation for subsequent electric field configuration. This ensures that the characteristics of different geometric areas, such as planar and corner areas, are effectively identified and analyzed. Electric field strength requirement features are extracted from the geometric partitions, and a preliminary electric field configuration scheme is generated. The preliminary scheme is analyzed using a neural network model to obtain a refined electric field strength distribution. This allows the electric field configuration to learn from and optimize historical data, enabling the electric field strength to accurately adapt to the needs of each area. This not only improves the accuracy of the electric field configuration but also effectively avoids the uneven electric field distribution defects of traditional methods. A control signal is generated based on the refined electric field strength distribution to obtain a dynamic response sequence. Real-time data is extracted from the dynamic response sequence... The system optimizes dynamic response sequence parameters and generates an adaptive adjustment path to ensure real-time adjustment of the electric field strength, adapting to changes in the sofa bed frame's geometry under different conditions. When the sofa bed frame switches from a planar state to a folded state, the system monitors its geometric changes based on updated control parameters. By rapidly calculating the electric field strength distribution, it ensures that corner areas are fully compensated during folding, avoiding electric field attenuation caused by curvature changes and ensuring uniformity of the deposition effect. Continuous adjustments are made through a dynamic feedback mechanism to generate the final electric field parameter set, ensuring the efficiency and stability of the powder coating process. The synergy of these technical solutions solves the challenges of traditional methods in handling the complex geometry of folding sofa bed frames, improves the uniformity and stability of the powder coating, and significantly optimizes production efficiency and product quality.

[0050] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0051] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0052] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing all-around powder coating for folding sofa bed frames, characterized in that, The method includes: Step S1: Acquire real-time geometric data of the surface of the folding sofa bed frame through a sensor array, and obtain shape features based on the real-time geometric data; divide the surface area according to the shape features using a region segmentation algorithm to determine the geometric partitions representing the planar area and the corner area; Step S2: Extract the corresponding electric field strength requirement features from the geometric partition, and obtain a preliminary electric field configuration scheme based on the electric field strength requirement features; analyze the preliminary electric field configuration scheme through a neural network model to obtain a refined electric field strength distribution; Step S3: Generate a control signal based on the refined electric field intensity distribution to obtain a dynamic response sequence; extract deposition effect indicators from the dynamic response sequence; optimize the dynamic response sequence parameters based on the deposition effect indicators; generate an adaptive adjustment path based on the optimized dynamic response sequence parameters; and obtain updated control parameters based on the adaptive adjustment path. Step S4: Monitor the geometric changes of the folding sofa bed frame according to the updated control parameters, and adjust the electric field intensity distribution by rapid electric field redistribution according to the geometric changes to obtain the final electric field parameter set.

2. The method as described in claim 1, characterized in that, In step S1, the shape features of the sofa bed frame are obtained, including: Real-time geometric data of the surface of the folding sofa bed frame is collected by a sensor array; the real-time geometric data is preprocessed to extract feature points in the planar and corner areas; shape feature data representing the distribution of the planar and corner areas is generated based on the feature points; the shape feature data is normalized to obtain standardized shape features; the standardized shape features are filtered and denoised to determine the final shape features of the sofa bed frame.

3. The method as described in claim 2, characterized in that, In step S1, the geometric partitions representing the plane and corner regions are determined, including: The geometric data of the folding sofa bed frame is processed using a region segmentation algorithm based on the shape features. The shape features are divided into planar regions and high-curvature corner regions. For the planar regions and high-curvature corner regions, the boundary features of each region are extracted. The type and boundary range of each region are determined based on the boundary features. The boundary range is verified. If the boundary range deviation exceeds a preset threshold, the segmentation parameters are readjusted. The classified geometric partition data is generated based on the adjusted segmentation parameters.

4. The method as described in claim 1, characterized in that, In step S2, a preliminary electric field configuration scheme is obtained, including: Geometric features of planar regions and high-curvature corner regions are extracted from the geometric partitions; uniform electric field strength parameters are calculated for the planar regions; differential electric field strength parameters are calculated for the high-curvature corner regions; if the proportion of the planar regions is higher than a preset threshold, uniform electric field strength is preferentially allocated; a preliminary electric field configuration scheme is generated based on the uniform electric field strength and the differential electric field strength; the preliminary electric field configuration scheme is normalized to obtain standardized configuration data.

5. The method as described in claim 1, characterized in that, In step S2, the refined electric field intensity distribution is obtained, including: The preliminary electric field configuration scheme is input into a pre-trained neural network model; the matching degree between the preliminary electric field configuration scheme and historical deposition data is analyzed through the neural network model; an optimization adjustment vector is generated based on the matching degree; pulse mode parameters for high curvature corner regions are determined based on the optimization adjustment vector; the preliminary electric field configuration scheme is adjusted based on the pulse mode parameters; and refined electric field intensity distribution data is generated.

6. The method as described in claim 1, characterized in that, In step S3, the dynamic response sequence is obtained, including: Voltage and current control signals are generated based on the refined electric field intensity distribution; the output acceleration of each node is adjusted; it is determined whether the field intensity deviation in the high curvature corner region exceeds the preset threshold. If so, the control signal is corrected through feedback loop; and a dynamic response sequence is generated based on the corrected control signal.

7. The method as described in claim 6, characterized in that, In step S3, the updated control parameters are obtained, including: Real-time deposition performance indicators are extracted from the dynamic response sequence; the dynamic response sequence parameters are optimized using a gradient descent algorithm based on the real-time deposition performance indicators; updated voltage and current values ​​are calculated based on the optimized dynamic response sequence parameters; an adaptive adjustment path is generated for the updated voltage and current values; the stability of the adaptive adjustment path is verified, and if the path deviation exceeds a preset threshold, the parameters are re-optimized; updated control parameters are generated based on the verification results.

8. The method as described in claim 1, characterized in that, In step S4, the final electric field parameter set is obtained, including: The system monitors geometric change events of the folding sofa bed frame in real time according to the updated control parameters; if the system switches from a planar state to a folded state, it triggers a rapid electric field reconfiguration; the electric field intensity distribution is adjusted according to the rapid electric field reconfiguration; dynamic electric field parameters are generated for the geometric change; the dynamic electric field parameters are verified to determine whether the parameter deviation exceeds a preset threshold, and if so, they are readjusted; the final electric field parameter set is generated based on the adjustment results.

9. An all-around powder coating optimization system for folding sofa bed frames, for implementing the method as described in any one of claims 1-8, characterized in that, The system includes: The geometric partitioning unit is used to acquire real-time geometric data of the surface of the folding sofa bed frame through a sensor array, obtain shape features based on the real-time geometric data, and divide the surface area according to the shape features using a region segmentation algorithm to determine the geometric partitions that characterize the planar area and the corner area. An electric field distribution acquisition unit is used to extract corresponding electric field intensity requirement features from the geometric partitions, obtain a preliminary electric field configuration scheme based on the electric field intensity requirement features, and analyze the preliminary electric field configuration scheme through a neural network model to obtain a refined electric field intensity distribution. A control signal generation unit is used to generate a control signal based on the refined electric field intensity distribution to obtain a dynamic response sequence; extract deposition effect indicators from the dynamic response sequence; optimize the dynamic response sequence parameters based on the deposition effect indicators; generate an adaptive adjustment path based on the optimized dynamic response sequence parameters; and obtain updated control parameters based on the adaptive adjustment path. A geometric change monitoring unit is used to monitor the geometric changes of the folding sofa bed frame according to the updated control parameters; An electric field redistribution unit is used to adjust the electric field intensity distribution through rapid electric field redistribution based on the geometric changes, thereby obtaining the final electric field parameter set.

10. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the method as described in any one of claims 1-8.

Images