Processing parameter regulation and control method and device for tablet protection shell and electronic equipment

Abstract

The invention relates to the technical field of industry, in particular to a processing parameter regulation and control method and device for a panel protection shell and electronic equipment, and the method comprises the steps: obtaining the actual material characteristics and actual structural characteristics of a to-be-processed protection shell through a multi-modal large model based on the surface image and spectral data of the to-be-processed protection shell; if the model suitable for the to-be-machined protective shell is a known model, historical machining parameters are matched in a machining parameter library based on the actual material characteristics and the actual structural characteristics; if the historical processing parameters are matched, processing parameters of the to-be-processed protective shell are obtained based on the historical processing parameters; and if the historical machining parameters are not matched, target machining materials with similar chemical properties and structures are retrieved, and machining parameters of the to-be-machined protective shell are obtained based on the structure parameters and the historical machining parameters of the target machining materials. In this way, the machining parameters can be automatically matched, self-adaptive reasoning can be carried out on new materials, and therefore the machining efficiency of the flat plate protection shell is improved.

Description

Technical Field

[0001] This disclosure relates to the field of industrial technology, specifically to a method, apparatus, and electronic device for adjusting processing parameters of a flat panel protective shell. Background Technology

[0002] The manufacturing of flat panel protective shells typically involves precision CNC machining processes, such as using CNC milling machines and CNC (Computer Numerical Control) engraving machines to cut, mill, and shape their outer edges, openings, and surface textures. In this process, the setting of machining parameters is crucial, including cutting speed, feed rate, spindle speed, and coolant flow rate. These parameters directly affect machining efficiency, surface quality, and dimensional accuracy.

[0003] In related technologies, the determination of the aforementioned processing parameters mainly relies on the operator's experience. In actual production, due to the diverse materials of protective shells (such as silicone, leather, metal composites, etc.) and their complex and varied structures, relying on manual experience makes it difficult to achieve rapid, accurate, and adaptive matching of processing parameters. This leads to frequent processing defects caused by improper parameters on the production line, and a long debugging period is required when introducing new processing materials. Summary of the Invention

[0004] To overcome the problems existing in the related technologies, the present disclosure provides a method, apparatus and electronic device for adjusting the processing parameters of a flat panel protective shell, so as to solve the defects in the related technologies.

[0005] According to a first aspect of the present disclosure, a method for adjusting processing parameters of a flat panel protective shell is provided, comprising: The surface image and spectral data of the protective shell to be processed are collected, and the actual material characteristics and actual structural characteristics of the protective shell to be processed are obtained based on the surface image and spectral data through a multimodal large model. If the model to which the protective shell to be processed is applicable is a known model that has been processed in the past, then based on the actual material characteristics and the actual structural characteristics, historical processing parameters are matched in the processing parameter library, wherein the processing parameter library is used to store the correspondence between historical processing parameters, material characteristics and structural characteristics of historically processed protective shells; If historical processing parameters are matched, the processing parameters of the protective shell to be processed are obtained based on the historical processing parameters. If no historical processing parameters are matched, a candidate processing material with chemical properties similar to the protective shell to be processed is searched in the processing parameter library, and a target processing material with structural parameters similar to the protective shell to be processed is determined from the candidate processing materials. Based on the structural parameters of the target processing material and the historical processing parameters, the processing parameters of the protective shell to be processed are obtained.

[0006] According to a second aspect of the present disclosure, a processing parameter control device for a flat panel protective shell is provided, comprising: The identification module is used to collect surface images and spectral data of the protective shell to be processed, and to obtain the actual material characteristics and actual structural characteristics of the protective shell to be processed based on the surface images and spectral data through a multimodal large model. The matching module is used to match historical processing parameters in the processing parameter library based on the actual material characteristics and the actual structural characteristics when the model to which the protective shell to be processed is applicable is a known model that has been processed in the past. The processing parameter library is used to store the correspondence between historical processing parameters, material characteristics and structural characteristics of the historically processed protective shells. The first processing module is used to obtain the processing parameters of the protective shell to be processed based on the historical processing parameters when they are matched. The second processing module is used to search for candidate processing materials with similar chemical properties to the protective shell to be processed in the processing parameter library when no historical processing parameters are matched, and to determine the target processing material with similar structural parameters to the protective shell to be processed from the candidate processing materials. Based on the structural parameters of the target processing material and the historical processing parameters, the processing parameters of the protective shell to be processed are obtained.

[0007] According to a third aspect of the present disclosure, an electronic device is provided, the electronic device including a memory and a processor, the memory being used to store computer instructions executable on the processor, and the processor being used to implement the method of the first aspect when executing the computer instructions.

[0008] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects: The processing parameter control method for flat panel protective shells provided in this disclosure can identify the material and structural characteristics of the flat panel protective shell to be processed based on a multimodal large model, and then automatically match the processing parameters. This automatically adapts to the natural fluctuations of the processed material and the introduction of new materials, reducing the problems of poor compatibility between different materials and reliance on experience for parameter debugging during the processing of flat panel protective shells. Furthermore, a two-level intelligent parameter matching mechanism is adopted. When sufficient historical data is available, the optimal historical processing parameters are reused to ensure consistency in processing efficiency and quality. When faced with a new material not included in the historical data, an adaptive reasoning mechanism is automatically activated (i.e., searching for candidate processing materials with the most similar chemical properties) to generate processing parameters for the new material, reducing manual debugging time and shortening process preparation time, thereby improving the processing efficiency of flat panel protective shells. Attached Figure Description

[0009] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0010] Figure 1 This is a flowchart illustrating a method for adjusting processing parameters for a flat panel protective shell, as shown in an exemplary embodiment of this disclosure; Figure 2 This is a schematic diagram of the structure of a processing parameter control device for a flat panel protective shell, as shown in an exemplary embodiment of this disclosure; Figure 3 This is a structural block diagram of an electronic device illustrated in an exemplary embodiment of the present disclosure. Detailed Implementation

[0011] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure.

[0012] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The singular forms “a,” “the,” and “the” as used herein are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0013] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0014] As mentioned in the background section, in the field of CNC machining of flat protective shells, traditional machining parameter setting and control methods heavily rely on manual experience and trial and error, resulting in the following technical problems that urgently need to be solved in the production process: 1. Poor material identification and processing parameter adaptability: Existing systems typically rely on production orders or material tags to obtain material information, making it impossible to quickly and accurately identify the physical properties of actual incoming materials. When a feeding error occurs and is not synchronized in time, the system will still use parameters set based on outdated or erroneous information for processing, which can easily lead to batch quality problems, such as using metal parameters to process PC (polycarbonate) materials, causing melt damage. 2. Parameter debugging is highly dependent on experience: Operators usually set processing parameters based on historical experience manuals or limited databases. However, when encountering new materials or fine-tuning structures that have not been used in a particular machine model, operators must start from scratch to conduct time-consuming and material-intensive process experiments. The debugging cycle is long, the trial and error costs are high, and this seriously restricts the speed of introducing new materials and product iteration. 3. Low utilization of historical data: There is a lack of in-depth mining and correlation analysis of massive historical processing data. When faced with similar but different processing tasks, it is impossible to automatically deduce the applicable parameter combination from past successful or failed cases. Valuable production experience has not been transformed into structured process knowledge that can be automatically called.

[0015] Based on this, in a first aspect, at least one embodiment of this disclosure provides a method for adjusting processing parameters for a flat panel protective shell, please refer to the appendix. Figure 1 The diagram illustrates the process of the method, including steps S101 to S104.

[0016] In step S101, surface images and spectral data of the protective shell to be processed are acquired, and the actual material characteristics and actual structural characteristics of the protective shell to be processed are obtained based on the surface images and spectral data through a multimodal large model.

[0017] In step S102, if the model to which the protective shell to be processed is applicable is a known model that has been processed in the past, historical processing parameters are matched in the processing parameter library based on the actual material characteristics and actual structural characteristics. The processing parameter library stores the correspondence between historical processing parameters, material characteristics, and structural characteristics of previously processed protective shells.

[0018] In step S103, if historical processing parameters are matched, the processing parameters of the protective shell to be processed are obtained based on the historical processing parameters.

[0019] In step S104, if no historical processing parameters are matched, the candidate processing materials with similar chemical properties to the protective shell to be processed are searched in the processing parameter library, and the target processing material with similar structural parameters to the protective shell to be processed is determined from the candidate processing materials. Based on the structural parameters of the target processing material and the historical processing parameters, the processing parameters of the protective shell to be processed are obtained.

[0020] Therefore, based on a multimodal large model, the material and structural characteristics of the protective shell can be identified, and processing parameters can be automatically matched. This allows for automatic adaptation to natural fluctuations in the processed material and the introduction of new materials, reducing the problems of poor material compatibility and reliance on experience for parameter tuning during the processing of flat panel protective shells. Furthermore, a two-level intelligent parameter matching mechanism is adopted. When sufficient historical data is available, the optimal historical processing parameters are reused to ensure consistency in processing efficiency and quality. When faced with a new material not included in the historical data, an adaptive inference mechanism is automatically activated (i.e., searching for candidate processing materials with the most similar chemical properties) to generate processing parameters for the new material. This reduces manual tuning time and shortens process preparation time, thereby improving the processing efficiency of flat panel protective shells.

[0021] To facilitate understanding, the steps described above will be further explained below.

[0022] For example, in step S101, an surface image of the protective shell to be processed can be acquired using an industrial camera, and spectral data of the protective shell to be processed can be acquired using a near-infrared spectral sensor. The surface image can include the color, texture, and macroscopic structure of the protective shell to be processed, while the spectral data can reflect the molecular chemical bond information of the material of the protective shell to be processed.

[0023] For example, the multimodal large model is a pre-trained multimodal deep learning model, including an image recognition branch and a spectral recognition branch. The image recognition branch can be a convolutional neural network, used to automatically extract structural features from images, such as edges, contours, hole locations, curvature, etc., and identify the visual texture patterns of the surface. The spectral recognition branch can be a fully connected network, used to analyze spectral curves and identify fingerprint feature peaks characterizing materials such as silicone (Si-O bonds), PC (benzene ring feature peaks), and leather (protein / organic features). Then, a feature fusion layer performs feature fusion analysis on the high-level structural feature vectors extracted by the image recognition branch and the material feature vectors extracted by the spectral recognition branch, ultimately outputting the actual material features and actual structural features of the protective shell to be processed. For example, the multimodal large model can output: {Material: Matte PC; Structure: Thickness 1.5mm, Curvature R2.5}.

[0024] Therefore, by integrating industrial vision and near-infrared spectroscopy for multimodal recognition, the actual material and structural characteristics of the protective shell to be processed can be accurately obtained, ensuring that the matching of processing parameters is based on the actual protective shell to be processed, thereby improving processing stability and first-pass yield.

[0025] For example, the following method can be used to identify whether the model to which the protective shell to be processed is a known model that has been processed in the past: In response to receiving the processing task information of the protective shell to be processed, the machine model identifier corresponding to the protective shell to be processed is obtained from the processing task information. The machine model identifier is compared with the machine model identifier recorded in the processing parameter knowledge base. If the comparison is consistent, it is determined that the machine model corresponding to the protective shell to be processed is a known model that has been processed in the past. If the comparison is inconsistent, the actual structural features are compared with the structural features recorded in the processing parameter knowledge base. If the similarity calculation result indicates that the highest similarity is lower than the first preset similarity threshold, it is determined that the machine model corresponding to the protective shell to be processed is not a known model that has been processed in the past.

[0026] When the machine model to which the protective shell to be processed is applicable is a known model that has been processed in the past, historical processing parameters can be matched with those in the processing parameter library based on the actual material and structural characteristics of the protective shell. Therefore, for known machine models, the actual material and structural characteristics identified in real time by sensors are used as the basis for querying the processing parameter library. This ensures that the historical processing experience used is matched with the physical characteristics of the current workpiece with the highest accuracy, effectively addressing the drift between the actual product and the design theory caused by differences in material batches, supplier changes, or incorrect incoming materials, thus improving the adaptability and reliability of the processing process.

[0027] For example, actual material features and actual structural features can be converted into a first feature vector, and the similarity between the first feature vector and a second feature vector in a processing parameter library can be determined. The processing parameter library stores the correspondence between historical processing parameters and the second feature vector, which is obtained based on the material and structural features corresponding to the historical processing parameters. If a target feature vector with a similarity higher than a second preset similarity threshold exists in the second feature vector, a historical processing parameter is identified as matched. Therefore, the processing parameters for the protective shell to be processed can be obtained based on the matched historical processing parameter. For example, if one historical processing parameter is matched, it can be directly used as the processing parameter for the protective shell. If multiple historical processing parameters are matched, they can be weighted to obtain the processing parameters for the protective shell. For example, based on the historical processing parameters corresponding to the target feature vector, candidate processing parameters are determined, and the similarity of the candidate processing parameters is used as weights to perform a weighted summation of the candidate processing parameters to obtain the processing parameters for the protective shell.

[0028] If no target feature vector with a similarity higher than the second preset similarity threshold exists in the second feature vector, it is determined that no historical processing parameters have been matched. Therefore, candidate processing materials with chemical properties similar to the protective shell to be processed can be searched in the processing parameter database. From these candidate materials, a target processing material with structural parameters similar to the protective shell to be processed is determined. Based on the structural parameters and historical processing parameters of the target processing material, the processing parameters of the protective shell to be processed are obtained. In some embodiments, the processing parameters of the protective shell to be processed are obtained based on the structural parameters and historical processing parameters of the target processing material, including: performing interpolation calculation based on the structural parameters and historical processing parameters of the target processing material to obtain interpolated processing parameters; obtaining the material physical parameters of the target processing material and the protective shell to be processed from the material property database, and correcting the interpolated processing parameters based on the difference rate between the physical material parameters of the target processing material and the protective shell to be processed and a preset correction strategy to obtain the processing parameters of the protective shell to be processed.

[0029] For example, the preset correction strategy could be: for every 10% decrease in heat distortion temperature, reduce the cutting speed by 5% (to prevent overheating); for every 20% decrease in elastic modulus, reduce the feed rate by 3% (to prevent overcutting), etc.

[0030] For example, when processing a flat protective shell made of TPU (thermoplastic polyurethane) material with a thickness of 1.8mm and a corner radius of 4.0mm, no historical processing records for TPU material were found in the processing parameter library. However, there were processing records for PU (polyurethane) and rubber (similar elastomer), as well as records for PC (polycarbonate) and ABS (acrylonitrile-butadiene-styrene copolymer) with different thicknesses and radii.

[0031] First, similar materials and structures were identified and interpolated. Based on the chemical properties of the materials, the two most similar materials to TPU were found: PU (similarity 0.75) and rubber (similarity 0.70). Then, records with similar thickness and curvature were found among the two similar materials. Two records were found: Record A (material PU, thickness 1.5mm, curvature R=4.0mm, machining parameters: cutting speed 120m / min, feed rate 0.05 mm / tooth); and Record B (material rubber, thickness 2.0mm, curvature R=4.0mm, machining parameters: cutting speed 100 m / min, feed rate 0.04 mm / tooth).

[0032] The cutting speed for a thickness of 1.8mm was calculated using linear interpolation: the cutting speed was recorded from 120 for A to 100 for B, with the thickness ranging from 1.5 to 2.0. The interpolated cutting speed was 120 - (120 - 100) × (1.8 - 1.5) / (2.0 - 1.5) = 120 - 20 × 0.6 = 108 m / min. The feed rate for a thickness of 1.8mm was calculated using linear interpolation: the feed rate was recorded from 0.05 for A to 0.04 for B. The interpolated feed rate was 0.05 - (0.05 - 0.04) × 0.6 = 0.05 - 0.006 = 0.044 mm / tooth.

[0033] Key physical parameters (such as elastic modulus, heat distortion temperature, and elongation at break) of TPU, PU, ​​and rubber were obtained from a material property database. Taking heat distortion temperature as an example, TPU (80°C) has a heat distortion temperature approximately 11.1% lower than PU (90°C) and approximately 14.3% higher than rubber (70°C). Since PU is more similar to TPU, using PU as the baseline, the difference in heat distortion temperature is: (80-90) / 90 = -0.111 (i.e., 11.1% lower). With the heat distortion temperature decreasing by 11.1%, based on a preset correction strategy of reducing the cutting speed by 5% for every 10% decrease, the cutting speed compensation coefficient is: 1 + (-0.111) × (0.5) = 0.9445. Therefore, the corrected cutting speed is: 108 m / min × 0.9445 ≈ 102 m / min.

[0034] Therefore, by using cross-material similarity search and structural interpolation, combined with quantitative compensation based on material physical properties, intelligent reasoning of processing parameters for new material and structural combinations can be achieved, reducing debugging costs in the processing of flat panel protective shells and improving the success rate of first-piece processing of new materials.

[0035] In some embodiments, when the applicable model of the protective shell to be processed is not a known model, the processing task information of the protective shell to be processed can be obtained. Based on the processing task information, the target attribute node is located in the processing knowledge graph. The processing task information includes at least one of the applicable model, material characteristics, structural characteristics, processing equipment and processing tools. The processing knowledge graph is used to store the process logic relationship in the historical processing process. If a first processing parameter node that is connected to all target attribute nodes is found in the processing knowledge graph, the processing parameters of the protective shell to be processed are obtained based on the processing quality and processing parameters corresponding to the first processing parameter node.

[0036] For example, the machining knowledge graph contains various types of entity nodes, such as machine type nodes, material nodes, structural feature nodes, machining equipment nodes, tool nodes, machining parameter nodes, and machining quality nodes. Edges between nodes in the machining knowledge graph represent various types of semantic relationships, such as the usage relationship between machine type nodes and material nodes, the possession relationship between machine type nodes and structural feature nodes, the assembly and usage relationship between machining equipment nodes and tool nodes, the application relationship where machine type, material, structure, equipment, and tool nodes all point to machining parameter nodes, and the result relationship where machining parameter nodes point to machining quality nodes.

[0037] Therefore, processing knowledge graphs can not only store data, but also complex process logic relationships and experiential knowledge, facilitating queries and reasoning from multiple dimensions (such as machine type, material, structure, equipment, and cutting tools) to locate target attribute nodes. Furthermore, similarity matching can be performed based on the relationships between nodes, making it more flexible than traditional relational databases and capable of handling more complex multi-condition queries and fuzzy matching, providing a solid foundation for subsequent intelligent retrieval, reasoning, and parameter fusion.

[0038] If the first processing parameter node, which is connected to all target attribute nodes, is found in the processing knowledge graph, then the processing parameters of the protective shell to be processed are obtained based on the processing quality and processing parameters corresponding to the first processing parameter node.

[0039] In some embodiments, the processing parameters of the protective shell to be processed are obtained based on the processing quality and processing parameters corresponding to the first processing parameter node, including: if the processing quality corresponding to the first processing parameter node is not up to standard, the processing parameters of the first processing parameter node are used as comparison parameters, and the processing knowledge graph is queried for the second processing parameter node that meets the processing quality and is simultaneously connected to the most target attribute nodes. The node with the best processing quality is selected from the second processing parameter nodes, and the processing parameters of the node with the best processing quality are determined as the benchmark parameters; based on the benchmark parameters, comparison parameters, and the processing quality corresponding to the first and second processing parameter nodes, the reasons for the substandard processing quality of the first processing parameter node are analyzed, and a parameter compensation strategy is obtained from a predefined compensation rule base according to the reasons for the substandard processing quality of the first processing parameter node; the benchmark parameters are adjusted based on the parameter compensation strategy to obtain the processing parameters of the protective shell to be processed.

[0040] For example, consider a machining task for a new machine model C: the material is 6000 series aluminum alloy, the structure is 1.5mm thick, the right-angle side R=3mm, the equipment is a five-axis CNC milling machine, and the cutting tool is a carbide end mill. In the machining knowledge graph, machining parameter node D1 is found that perfectly matches all the above attributes, but its machining quality is substandard. Conversely, machining parameter node D2 is found that matches all four attributes, and its cutting tool is a diamond-coated end mill, resulting in excellent machining quality. Analyzing the machining quality of machining parameter node D1 reveals that using a carbide end mill while maintaining the same key attributes leads to burr defects. Analyzing the machining quality of machining parameter node D2 confirms that, under the condition of identical key attributes, using a diamond-coated end mill results in excellent machining quality.

[0041] Therefore, by analyzing the machining quality of these two machining parameter nodes, a causal relationship can be established: "Under the conditions of machine type C, material - aluminum alloy 6000 series, and equipment - five-axis CNC milling machine, the use of carbide end mills is a potential cause of burr generation. Furthermore, using the successful machining parameter node D2 as a performance benchmark, the embedded tool-material-parameter compensation rule library is invoked. This rule library contains rules such as: 'Compared to diamond-coated tools, carbide tools have poorer wear resistance and thermal conductivity when machining aluminum alloys. It is recommended to reduce the feed rate (fz) by approximately 10-15% under the same conditions to reduce the load per tooth and heat accumulation, thereby suppressing burr generation.'" Finally, the key parameters of machining parameter node D2 are adjusted accordingly. For example, if the feed rate of machining parameter node D2 is 0.05 mm / tooth, the compensation rule is applied to reduce it by 12%, resulting in a feed rate of 0.044 mm / tooth.

[0042] Therefore, by combining knowledge graph-based relational queries with causal-based process reasoning, the system first finds all relevant experiences (both positive and negative) through graph traversal. Then, by comparing quality results under different attributes, it identifies potential variables leading to defects. Finally, it invokes domain knowledge (i.e., a compensation rule base) to make targeted and preventative adjustments to the baseline parameters, proactively reasoning for safer and more reliable processing parameters. This supports rapid parameter retrieval and iterative optimization for new models, reducing production line changeover and debugging time. Furthermore, in the rapid parameter retrieval process for new models, material and structural characteristics from design data are used as the basis for graph queries to ensure the accuracy and authority of the planning phase.

[0043] After obtaining the processing parameters of the protective shell to be processed, the processing operation can be performed based on the processing parameters.

[0044] In some embodiments, the theoretical material characteristics and theoretical structural characteristics of the protective shell to be processed can be obtained from the design data of the protective shell to be processed. Then, the actual material characteristics are compared with the theoretical material characteristics to obtain a first comparison result, and the actual structural characteristics are compared with the theoretical structural characteristics to obtain a second comparison result. If both the first comparison result and the second comparison result are consistent, then the protective shell to be processed is processed based on the processing parameters.

[0045] It should be understood that in related technologies, the design theory and physical reality lack a closed-loop verification process. Processing parameters are directly issued after being obtained, lacking an automated verification step to check whether the actual materials in the workshop match the design specifications. This fails to prevent material errors caused by supply chain mistakes or warehouse management errors, resulting in weak error prevention and tolerance capabilities in the production system. However, in this embodiment, through automated comparison and verification between the actual material and the design-specified material, as well as between the actual structure and the design-specified structure, production accidents caused by incorrect incoming materials and information asynchrony can be reduced, preventing batch processing errors. This improves the robustness and safety of the tablet protective shell production process and effectively addresses uncertainties in the production environment.

[0046] In some embodiments, during the machining of the protective shell, temperature data, tool wear data, and pressure data of the machining area can be collected in real time. Then, based on the temperature data, tool wear data, and pressure data, the machining parameters of the protective shell can be adjusted through an adaptive control model. This allows for real-time monitoring of temperature, tool wear, and pressure data during machining, and dynamic fine-tuning of parameters such as cutting speed and feed rate, avoiding defects such as cracking, burrs, and dimensional deviations, thereby improving the machining quality of the flat protective shell.

[0047] In some embodiments, based on temperature data, tool wear data, and pressure data, the machining parameters of the protective shell to be machined are adjusted through an adaptive control model. This includes: converting the temperature data, tool wear data, and pressure data into fuzzy language based on the numerical relationships between temperature data and preset temperature thresholds, tool wear data and preset wear thresholds, and pressure data and preset pressure thresholds. The fuzzy language is used to describe parameter deviations and parameter changes. Parameter adjustment suggestions are obtained through reasoning using a fuzzy rule base built based on expert experience and the fuzzy language. These suggestions are then used as changes in setpoints and input into a PID controller for calculation, generating a numerical control instruction correction signal for adjusting the machining parameters.

[0048] For example, precise values ​​such as real-time collected temperature deviation, tool wear index, and cutting force fluctuation can be converted into fuzzy logic, such as high temperature, moderate wear, and large force fluctuation. Fuzzy rules stored in the fuzzy rule base could be, for example, "If the temperature is high and the wear is moderate, slightly reduce the feed rate and slightly increase the coolant flow rate." Correspondingly, the adjustment suggestion from the fuzzy inference output could be: reduce the feed rate by 5%. Then, the 5% reduction in feed rate is used as the setpoint change for the PID controller. The PID controller performs precise integration and differentiation calculations based on the real-time error, ultimately generating a smooth, overshoot-free control command.

[0049] Therefore, by integrating multi-sensor information and hierarchical intelligent control, it is possible to make joint judgments and decisions based on multi-source data and trends such as temperature, wear, and stress. Furthermore, through a composite model combining fuzzy logic and PID control, expert experience is transformed into stable and accurate real-time control commands. This overcomes the limitations of traditional processing methods that rely on single-point threshold alarms and frequent interruptions for adjustment, enabling smooth and continuous adaptive optimization of parameters during processing. Consequently, it improves the consistency of processing quality, the stability of equipment operation, and the continuity of the production process.

[0050] In some embodiments, visual inspection can be performed on the target protective shell obtained based on processing parameters to obtain the defect type of the target protective shell. Based on the defect type and a preset defect cause-effect knowledge base, the target processing parameters associated with the defect type are determined. The defect cause-effect knowledge base is used to store the correlation between defect types and defect causes in historical processing. The occurrence frequency of the defect type is compared with the preset target defect rate to obtain the deviation value. The deviation value is used as input to calculate the adjustment amount of the process control threshold of the target processing parameters through a PID controller. Based on the adjustment amount, the safety upper limit or safety lower limit of the process control threshold is updated.

[0051] For example, industrial cameras at multiple angles (such as frontal and side views) can be set up, along with high-brightness LED light sources, to acquire shadowless images of the processed protective casing. These images are then input into a defect detection neural network (such as YOLO or a variant of U-Net). This defect detection neural network can be trained on tens of thousands of labeled defect images to select defects such as burrs, cracks, and scratches in the images in real time and accurately locate them to pixel coordinates.

[0052] For example, by analyzing historical data and process principles, a rule base (i.e., a defect causal knowledge base) can be established to associate defect types with processing parameters. For instance, if a burr is detected, it is associated with excessive feed rate or tool wear; if a crack is detected, it is associated with excessive cutting speed or excessive temperature. Therefore, when a defect is detected, the threshold of the corresponding parameter can be automatically corrected according to the association rules, and the corrected parameters can be applied in the next processing iteration. This forms a fully adaptive control process of detection-analysis-correction-reprocessing, improving the processing pass rate of flat panel protective shells.

[0053] For example, when processing a batch of protective shells of model E, made of magnesium alloy AZ31, with a thickness of 1.2mm, the vision inspection system identifies continuous burr defects at the outer right-angle edges of 10% of the workpieces. Then, it queries a pre-defined defect causal knowledge base to derive association rules: the primary association for continuous burrs is excessive feed per tooth, and the secondary association is excessive tool wear or insufficient cooling. The defect incidence rate (10%) is compared with a pre-defined target defect rate (e.g., 5%) to form a deviation signal, which is then input into a PID controller as a process control variable. Based on the magnitude, duration, and trend of the deviation, the controller calculates the adjustment amount for relevant parameter thresholds using a pre-defined gain coefficient. For example, if the defect incidence rate of 10% is higher than the pre-defined target defect rate of 5%, it means the current process window is too loose, so a negative adjustment is output, proportionally or according to a non-linear mapping relationship to tighten the safety upper limit of the parameters. For example, the output might be a specific correction amount to reduce the threshold from 0.08mm / tooth to 0.065mm / tooth, ensuring future processing operates under stricter constraints and pushing the defect incidence rate closer to the target value.

[0054] According to a second aspect of the present disclosure, a device for adjusting processing parameters for a flat panel protective shell is provided. Please refer to the appendix. Figure 2 The processing parameter control device 200 for the flat panel protective shell includes: The identification module 201 is used to collect the surface image and spectral data of the protective shell to be processed, and obtain the actual material characteristics and actual structural characteristics of the protective shell to be processed based on the surface image and the spectral data through a multimodal large model. The matching module 202 is used to match historical processing parameters in the processing parameter library based on the actual material characteristics and the actual structural characteristics when the model to which the protective shell to be processed is applicable is a known model that has been processed in the past. The processing parameter library is used to store the correspondence between historical processing parameters, material characteristics and structural characteristics of the historically processed protective shells. The first processing module 203 is used to obtain the processing parameters of the protective shell to be processed based on the historical processing parameters when the historical processing parameters are matched. The second processing module 204 is used to search for candidate processing materials with similar chemical properties to the protective shell to be processed in the processing parameter library when no historical processing parameters are matched, and to determine the target processing material with similar structural parameters to the protective shell to be processed from the candidate processing materials. Based on the structural parameters of the target processing material and the historical processing parameters, the processing parameters of the protective shell to be processed are obtained.

[0055] In some embodiments of this disclosure, the second processing module 204 is used for: Interpolation calculations are performed based on the structural parameters and historical processing parameters of the target material to obtain the interpolated processing parameters; The material physical parameters of the target processing material and the protective shell to be processed are obtained from the material property database. Based on the difference rate between the physical material parameters of the target processing material and the protective shell to be processed and the preset correction strategy, the interpolation processing parameters are corrected to obtain the processing parameters of the protective shell to be processed.

[0056] In some embodiments of this disclosure, the processing parameter control device 200 for the flat panel protective shell further includes a graph retrieval module, used for: If the model to which the protective shell to be processed is applicable is not the known model, the processing task information of the protective shell to be processed is obtained. Based on the processing task information, the target attribute node is located in the processing knowledge graph. The processing task information includes at least one of the applicable model, material characteristics, structural characteristics, processing equipment and processing tools. The processing knowledge graph is used to store the process logic relationship in the historical processing process. If a first processing parameter node that is connected to all target attribute nodes is found in the processing knowledge graph, then the processing parameters of the protective shell to be processed are obtained based on the processing quality and processing parameters corresponding to the first processing parameter node.

[0057] In some embodiments of this disclosure, the graph retrieval module is used for: If the processing quality corresponding to the first processing parameter node is not up to standard, the processing parameters of the first processing parameter node are used as comparison parameters, and the second processing parameter node that meets the processing quality standard and is simultaneously connected to the most target attribute nodes is queried in the processing knowledge graph. The node with the best processing quality is selected from the second processing parameter nodes, and the processing parameters of the node with the best processing quality are determined as the benchmark parameters. Based on the benchmark parameters, the comparison parameters, and the processing quality corresponding to the first processing parameter node and the second processing parameter node, the reasons why the processing quality of the first processing parameter node did not meet the standard are analyzed, and parameter compensation strategies are obtained from the predefined compensation rule library according to the reasons why the processing quality of the first processing parameter node did not meet the standard. The reference parameters are adjusted based on the parameter compensation strategy to obtain the processing parameters of the protective shell to be processed.

[0058] In some embodiments of this disclosure, the processing parameter control device 200 for the flat panel protective shell further includes a first adjustment module, used for: During the processing of the protective shell to be processed, temperature data, tool wear data, and pressure data of the processing area are collected in real time. Based on the temperature data, the tool wear data, and the pressure data, the machining parameters of the protective shell to be machined are adjusted through an adaptive control model.

[0059] In some embodiments of this disclosure, the first adjustment module is used to: Based on the numerical relationship between the temperature data and the preset temperature threshold, the numerical relationship between the tool wear data and the preset wear threshold, and the numerical relationship between the pressure data and the preset pressure threshold, the temperature data, the tool wear data, and the pressure data are converted into fuzzy language, wherein the fuzzy language is used to describe parameter deviations and parameter changes. By reasoning using a fuzzy rule base built on expert experience and the fuzzy language, parameter adjustment suggestions are obtained. These suggestions are then used as the change in setpoints and input into a PID controller for calculation, generating a numerical control instruction correction signal for adjusting the machining parameters.

[0060] In some embodiments of this disclosure, the processing parameter control device 200 for the flat panel protective shell further includes a comparison module for: The theoretical material characteristics and theoretical structural characteristics of the protective shell to be processed are obtained from the design data of the protective shell to be processed. The actual material features are compared with the theoretical material features to obtain a first comparison result, and the actual structural features are compared with the theoretical structural features to obtain a second comparison result; If the first comparison result and the second comparison result are consistent, then the protective shell to be processed is processed based on the processing parameters.

[0061] In some embodiments of this disclosure, the processing parameter control device 200 for the flat panel protective shell further includes a second adjustment module for: Visual inspection is performed on the target protective shell obtained based on the processing parameters to obtain the defect type of the target protective shell. Based on the defect type and a preset defect cause-effect knowledge base, the target processing parameters associated with the defect type are determined. The defect cause-effect knowledge base is used to store the association between defect types and defect causes in historical processing. The occurrence frequency of the defect type is compared with the preset target defect rate to obtain the deviation value. The deviation value is then used as input to calculate the adjustment amount of the process control threshold of the target processing parameter through a PID controller. Based on the adjustment amount, update the upper or lower safety limit of the process control threshold.

[0062] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments of the method in the first aspect, and will not be elaborated upon here.

[0063] According to a third aspect of the embodiments of this disclosure, please refer to the appendix. Figure 3 The diagram illustrates an exemplary block diagram of an electronic device 700, which may include a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0064] The processor 701 controls the overall operation of the electronic device 700 to complete all or part of the steps in any of the methods described above. The memory 702 stores various types of data to support the operation of the electronic device 700. This data may include, for example, instructions for any application or method operating on the electronic device 700, and application-related data, such as surface images, spectral data, and processing parameters of the protective casing to be processed. The memory 702 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 storage, flash memory, magnetic disk, or optical disk. The multimedia component 703 may include a screen and audio components. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 702 or transmitted via communication component 705. The audio component also includes at least one speaker for outputting audio signals. I / O interface 704 provides an interface between processor 701 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication may include Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof; therefore, the corresponding communication component 705 may include a Wi-Fi module, a Bluetooth module, or an NFC module.

[0065] In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method for adjusting the processing parameters of the flat panel protective shell.

[0066] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0067] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0068] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A method for adjusting processing parameters for a flat panel protective shell, characterized in that, include: The surface image and spectral data of the protective shell to be processed are collected, and the actual material characteristics and actual structural characteristics of the protective shell to be processed are obtained based on the surface image and spectral data through a multimodal large model. If the model to which the protective shell to be processed is applicable is a known model that has been processed in the past, then based on the actual material characteristics and the actual structural characteristics, historical processing parameters are matched in the processing parameter library, wherein the processing parameter library is used to store the correspondence between historical processing parameters, material characteristics and structural characteristics of historically processed protective shells; If historical processing parameters are matched, the processing parameters of the protective shell to be processed are obtained based on the historical processing parameters. If no historical processing parameters are matched, a candidate processing material with chemical properties similar to the protective shell to be processed is searched in the processing parameter library, and a target processing material with structural parameters similar to the protective shell to be processed is determined from the candidate processing materials. Based on the structural parameters of the target processing material and the historical processing parameters, the processing parameters of the protective shell to be processed are obtained.

2. The method for adjusting processing parameters for a flat panel protective shell according to claim 1, characterized in that, The processing parameters for the protective shell to be processed are obtained based on the structural parameters and historical processing parameters of the target processing material, including: Interpolation calculations are performed based on the structural parameters and historical processing parameters of the target material to obtain the interpolated processing parameters; The material physical parameters of the target processing material and the protective shell to be processed are obtained from the material property database. Based on the difference rate between the physical material parameters of the target processing material and the protective shell to be processed and the preset correction strategy, the interpolation processing parameters are corrected to obtain the processing parameters of the protective shell to be processed.

3. The method for adjusting processing parameters for a flat panel protective shell according to claim 1, characterized in that, Also includes: If the model to which the protective shell to be processed is applicable is not the known model, the processing task information of the protective shell to be processed is obtained. Based on the processing task information, the target attribute node is located in the processing knowledge graph. The processing task information includes at least one of the applicable model, material characteristics, structural characteristics, processing equipment and processing tools. The processing knowledge graph is used to store the process logic relationship in the historical processing process. If a first processing parameter node that is connected to all target attribute nodes is found in the processing knowledge graph, then the processing parameters of the protective shell to be processed are obtained based on the processing quality and processing parameters corresponding to the first processing parameter node.

4. The method for adjusting processing parameters for a flat panel protective shell according to claim 3, characterized in that, The process of obtaining the processing parameters of the protective shell to be processed based on the processing quality and processing parameters corresponding to the first processing parameter node includes: If the processing quality corresponding to the first processing parameter node is not up to standard, the processing parameters of the first processing parameter node are used as comparison parameters, and the second processing parameter node that meets the processing quality standard and is simultaneously connected to the most target attribute nodes is queried in the processing knowledge graph. The node with the best processing quality is selected from the second processing parameter nodes, and the processing parameters of the node with the best processing quality are determined as the benchmark parameters. Based on the benchmark parameters, the comparison parameters, and the processing quality corresponding to the first processing parameter node and the second processing parameter node, the reasons why the processing quality of the first processing parameter node did not meet the standard are analyzed, and parameter compensation strategies are obtained from the predefined compensation rule library according to the reasons why the processing quality of the first processing parameter node did not meet the standard. The reference parameters are adjusted based on the parameter compensation strategy to obtain the processing parameters of the protective shell to be processed.

5. The method for adjusting processing parameters for a flat panel protective shell according to any one of claims 1-4, characterized in that, Also includes: During the processing of the protective shell to be processed, temperature data, tool wear data, and pressure data of the processing area are collected in real time. Based on the temperature data, the tool wear data, and the pressure data, the machining parameters of the protective shell to be machined are adjusted through an adaptive control model.

6. The method for adjusting processing parameters for a flat panel protective shell according to claim 5, characterized in that, The step of adjusting the machining parameters of the protective shell to be machined based on the temperature data, the tool wear data, and the pressure data through an adaptive control model includes: Based on the numerical relationship between the temperature data and the preset temperature threshold, the numerical relationship between the tool wear data and the preset wear threshold, and the numerical relationship between the pressure data and the preset pressure threshold, the temperature data, the tool wear data, and the pressure data are converted into fuzzy language, wherein the fuzzy language is used to describe parameter deviations and parameter changes. By reasoning using a fuzzy rule base built on expert experience and the fuzzy language, parameter adjustment suggestions are obtained. These suggestions are then used as the change in setpoints and input into a PID controller for calculation, generating a numerical control instruction correction signal for adjusting the machining parameters.

7. The method for adjusting processing parameters for a flat panel protective shell according to any one of claims 1-4, characterized in that, Also includes: The theoretical material characteristics and theoretical structural characteristics of the protective shell to be processed are obtained from the design data of the protective shell to be processed. The actual material features are compared with the theoretical material features to obtain a first comparison result, and the actual structural features are compared with the theoretical structural features to obtain a second comparison result; If the first comparison result and the second comparison result are consistent, then the protective shell to be processed is processed based on the processing parameters.

8. The method for adjusting processing parameters for a flat panel protective shell according to any one of claims 1-4, characterized in that, Also includes: Visual inspection is performed on the target protective shell obtained based on the processing parameters to obtain the defect type of the target protective shell. Based on the defect type and a preset defect cause-effect knowledge base, the target processing parameters associated with the defect type are determined. The defect cause-effect knowledge base is used to store the association between defect types and defect causes in historical processing. The occurrence frequency of the defect type is compared with the preset target defect rate to obtain the deviation value. The deviation value is then used as input to calculate the adjustment amount of the process control threshold of the target processing parameter through a PID controller. Based on the adjustment amount, update the upper or lower safety limit of the process control threshold.

9. A device for adjusting processing parameters for a flat panel protective shell, characterized in that, include: The identification module is used to collect surface images and spectral data of the protective shell to be processed, and to obtain the actual material characteristics and actual structural characteristics of the protective shell to be processed based on the surface images and spectral data through a multimodal large model. The matching module is used to match historical processing parameters in the processing parameter library based on the actual material characteristics and the actual structural characteristics when the model to which the protective shell to be processed is applicable is a known model that has been processed in the past. The processing parameter library is used to store the correspondence between historical processing parameters, material characteristics and structural characteristics of the historically processed protective shells. The first processing module is used to obtain the processing parameters of the protective shell to be processed based on the historical processing parameters when they are matched. The second processing module is used to search for candidate processing materials with similar chemical properties to the protective shell to be processed in the processing parameter library when no historical processing parameters are matched, and to determine the target processing material with similar structural parameters to the protective shell to be processed from the candidate processing materials. Based on the structural parameters of the target processing material and the historical processing parameters, the processing parameters of the protective shell to be processed are obtained.

10. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory being used to store computer instructions executable on the processor, and the processor being used to implement the steps of the method according to any one of claims 1-8 when executing the computer instructions.

Images