A mobile phone frame production progress monitoring method and system
By constructing a standard process trajectory and two-dimensional process vector for the mobile phone framework, the problem of inaccurate production progress monitoring in existing technologies is solved, and efficient and accurate production status monitoring and quality assessment are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- DONGGUAN FAST PRECISION HARDWARE CO LTD
- Filing Date
- 2026-03-03
- Publication Date
- 2026-06-16
AI Technical Summary
Existing technologies cannot accurately monitor the production progress of mobile phone frames, and suffer from problems such as strong subjectivity, low detection efficiency, high computational complexity, inability to quantify quality assessment, and inability to continuously track process status.
By acquiring the point cloud model of the mobile phone frame, dividing key areas, constructing standard process trajectories, calculating the vertical distance between the real-time two-dimensional process vector and the standard process trajectory, and combining the smoothness of the partition and the sharpness of the key areas for quality assessment, intuitive and quantitative monitoring of production status can be achieved.
It reduces computational complexity, meets the real-time monitoring needs of industrial production lines, provides objective quality assessment indicators, and improves the accuracy and efficiency of production progress monitoring.
Smart Images
Figure CN121765671B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of data processing technology. More specifically, this invention relates to a method and system for monitoring the production progress of mobile phone frames. Background Technology
[0002] With the rapid development of intelligent manufacturing and Industry 4.0, the mobile phone frame, as a core structural component of the entire device, involves multiple complex processes in its production, including CNC machining, surface treatment, polishing, and anodizing. The quality and progress of each process directly affect the final quality and delivery time of the product.
[0003] Traditional production progress monitoring methods primarily rely on manual visual inspection and simple two-dimensional visual checks, which suffer from high subjectivity, difficulty in standardizing inspection criteria, and low efficiency, making them unsuitable for the high-speed requirements of modern production lines. Furthermore, while traditional three-dimensional inspection methods can acquire the three-dimensional geometric features of products, they typically depend on matching high-dimensional, abstract feature descriptors. These methods exhibit the following technical shortcomings:
[0004] First, the feature calculation and matching process has high algorithm complexity, involving a large number of iterative calculations such as neighborhood search and histogram construction, which places strict requirements on computing resources and makes it difficult to achieve millisecond-level real-time response on conventional industrial control equipment.
[0005] Secondly, its monitoring dimensions are limited, and it can only classify the production process in discrete states. It cannot quantify the degree of completion within the same process, nor can it provide an intuitive indicator for evaluating processing quality.
[0006] Third, high-dimensional features lack clear physical interpretability. When the detection results are abnormal, it is difficult for engineers to quickly locate the root cause of the process problem based on the abstract feature data.
[0007] Therefore, existing technologies cannot effectively correlate the geometric state of a product with the continuity of the production process, resulting in isolated and non-process-oriented monitoring results. They lack in-depth insight and predictive ability regarding production rhythm and quality fluctuations, leading to inaccurate monitoring of mobile phone frame production progress. Summary of the Invention
[0008] The purpose of this invention is to propose a method and system for monitoring the production progress of mobile phone frames, so as to solve the problem of inaccurate monitoring of the production progress of mobile phone frames in the prior art; to this end, this invention provides solutions in the following two aspects.
[0009] In a first aspect, the present invention provides a method for monitoring the production progress of a mobile phone frame, comprising:
[0010] Obtain the point cloud model of the current mobile phone frame, and divide the current mobile phone frame into regions to obtain the point cloud sub-models of each key region.
[0011] Establish standard process trajectories for several key areas of the current mobile phone framework;
[0012] Obtain the real-time two-dimensional process vectors of the point cloud sub-models of each key region of the current mobile phone frame;
[0013] Calculate the vertical distance from the real-time two-dimensional process vector to the corresponding standard process trajectory. When the vertical distance is less than or equal to the corresponding tolerance width, the production quality of the current mobile phone frame is determined to be qualified.
[0014] The standard process trajectory includes: acquiring point cloud models of multiple standard samples at different key processes; calculating a two-dimensional process vector for each key region under any key process based on the point cloud sub-model of each key region of each standard sample, wherein the two-dimensional process vector includes partition smoothness and key sharpness, wherein partition smoothness characterizes the degree of undulation within the key region, and key sharpness characterizes the change in edge features of the key region; and sequentially connecting the centroids of the clusters formed by the two-dimensional process vectors under the same key process to form the standard process trajectory.
[0015] The above scheme reduces the dimensionality of the high-dimensional point cloud model to a two-dimensional process vector space composed of partition smoothness and key sharpness, and constructs a standard process trajectory, thereby achieving intuitive and quantitative monitoring of the production status. This method not only significantly reduces computational complexity, meeting the millisecond-level real-time monitoring requirements of industrial production lines, but also provides an objective and quantifiable quality assessment index by calculating the vertical distance from the real-time vector to the standard trajectory. This overcomes the shortcomings of traditional methods, such as strong subjectivity, low efficiency, and unclear physical meaning of high-dimensional features, which makes it difficult to guide process improvement.
[0016] Optionally, the method for obtaining the partition smoothness includes:
[0017] Obtain the surface normal vectors of all points in the point cloud sub-model of the key region;
[0018] Calculate the standard deviation of the dot product of the surface normal vector of any point and the surface normal vectors of its neighboring points. Use the mean of the standard deviations of the dot products of all points within the key region as the partition smoothness of the corresponding key region. The neighboring points are k points obtained by constructing the point cloud sub-model. The data is obtained by querying a d-tree data structure.
[0019] Partition smoothness can more accurately reflect the impact of CNC machining, polishing and other processes on the surface micro-geometry.
[0020] Optionally, the method for obtaining the surface normal vector includes:
[0021] For any point within the critical region, obtain the three-dimensional coordinates of its k neighboring points and construct a covariance matrix; perform eigenvalue decomposition on the covariance matrix, and take the eigenvector corresponding to the smallest eigenvalue as the surface normal vector of the corresponding point, where k is a preset positive integer.
[0022] The above method exhibits high robustness and computational efficiency when processing unordered point cloud data, and can accurately estimate the local surface orientation of each point.
[0023] Optionally, the method for calculating the critical sharpness is as follows:
[0024] q = 1 - m; where m is the absolute value of the cosine of the included angle, and q is the critical sharpness;
[0025] The process of obtaining the absolute value of the cosine of the included angle includes:
[0026] Two plane fitting operations are performed on the key region to obtain two principal planes, and the absolute value of the cosine of the angle between the normal vectors of the two principal planes is calculated.
[0027] Key Sharpness can sensitively capture edge shape changes caused by CNC machining, polishing and other processes.
[0028] Optionally, the plane fitting employs a random sampling consensus algorithm.
[0029] Optionally, the process of dividing the current mobile phone frame into regions includes: pre-defined multiple key regions based on the CAD model of the current mobile phone frame, including chamfered areas, side frame plane areas, antenna slot areas, and camera module mounting surfaces.
[0030] Optionally, the method for obtaining the tolerance width includes:
[0031] Obtain the cluster containing the two-dimensional process vector set of the same critical region of all standard samples under the same critical process; take three times the standard deviation of the vertical distance from all data in the cluster to the standard process trajectory as the tolerance width of the standard process trajectory of the corresponding critical process.
[0032] The aforementioned tolerance width can adaptively reflect the inherent volatility of a specific process, avoiding the subjectivity and arbitrariness brought about by manually setting thresholds.
[0033] Optionally, it also includes:
[0034] Obtain the projection point of the real-time two-dimensional process vector on the standard process trajectory, and use the ratio of the length from the trajectory start point to the projection point to the total length of the standard process trajectory as the current production progress of the mobile phone frame.
[0035] Optionally, obtaining the point cloud model of the current mobile phone frame includes:
[0036] Industrial-grade structured light scanning equipment was used to scan the current mobile phone frame from at least six different perspectives;
[0037] The point cloud model of the current mobile phone frame is obtained by registering and fusing multi-view point cloud data through the iterative nearest point algorithm.
[0038] In the second aspect, a mobile phone frame production progress monitoring system includes:
[0039] processor;
[0040] The memory stores computer instructions for monitoring the production progress of a mobile phone frame, which, when executed by the processor, cause the system to perform the aforementioned method for monitoring the production progress of a mobile phone frame.
[0041] The beneficial effects of this invention are as follows:
[0042] The present invention provides a monitoring method that reduces the 3D point cloud information of a mobile phone frame to a 2D process vector space for analysis. Specifically, by constructing a standard process trajectory defined by "regional smoothness" and "critical sharpness," the complex production process is visualized as a path. By calculating the geometric relationship between the current mobile phone frame and the standard process trajectory in this space, the processing quality and production progress of the product can be continuously and objectively quantified and evaluated. This solves the problems of traditional monitoring methods being subjective, inefficient, and unable to continuously track the process status, thus improving the accuracy of mobile phone frame progress monitoring. Attached Figure Description
[0043] Figure 1 This illustration schematically shows a flowchart of the steps of a mobile phone frame production progress monitoring method in this embodiment;
[0044] Figure 2 This schematic diagram illustrates a standard process trajectory for a key area in this embodiment.
[0045] Figure 3 This schematic diagram illustrates the structural block diagram of a mobile phone frame production progress monitoring system in this embodiment.
[0046] The attached diagram shows the following labels: 1. Cluster corresponding to CNC roughing; 2. Cluster corresponding to CNC finishing; 3. Cluster corresponding to surface polishing; 4. Cluster corresponding to anodizing; 5. Point where the real-time two-dimensional process vector is located; 6. Projection point. Detailed Implementation
[0047] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
[0048] Using a mobile phone frame of a certain brand as the monitoring object, this invention provides a detailed description of the mobile phone frame production progress monitoring method. The main production processes of the entire mobile phone frame production process include four key steps: CNC rough machining, CNC precision machining, surface polishing, and anodizing.
[0049] like Figure 1 As shown, a method for monitoring the production progress of a mobile phone frame in this embodiment includes the following steps:
[0050] Step S1: Obtain the point cloud model of the current mobile phone frame in the current production process in real time.
[0051] In this embodiment, a high-precision industrial-grade structured light scanning device is used to scan the current mobile phone frame from at least 6 different perspectives to ensure that a complete point cloud without data blind spots is obtained. The iterative closest point (ICP) algorithm is used to perform high-precision registration and fusion of the multi-view point cloud data, and finally obtain the point cloud model of the current mobile phone frame.
[0052] The aforementioned industrial-grade structured light scanning equipment can be a structured light scanner from Hexagon.
[0053] Step S2: Divide the current mobile phone frame into regions and construct the standard process trajectory of each key region in the entire production process.
[0054] Taking the current mobile phone frame as an example, the current mobile phone frame can be divided into regions based on multiple key regions predefined in the computer-aided design (CAD) model of the mobile phone frame. For example, multiple key process regions include chamfered areas, side frame plane areas, antenna slot areas, camera module mounting surfaces, etc.
[0055] It should be noted that the standard samples in the standard sample set are divided into regions in the same way as the current mobile phone frame.
[0056] The process of obtaining the standard process trajectory in this embodiment is as follows:
[0057] First, obtain point cloud data models of each standard sample in the standard sample set for different key processes throughout the entire production process.
[0058] The standard samples are mobile phone frame products that have passed all four key processes: CNC rough machining, CNC fine machining, surface polishing, and anodizing.
[0059] For example, five qualified products from each of the four key processes—CNC roughing, CNC finishing, surface polishing, and anodizing—were selected, totaling 20 products, to form a standard sample set. A high-precision industrial-grade structured light scanning device was used to collect data from at least six different perspectives for each standard sample under different key processes to ensure the acquisition of a complete point cloud without data blind spots. The Iterative Closest Point (ICP) algorithm was then used for high-precision registration and fusion of the multi-view point cloud data. Ultimately, each standard sample generated a complete and dense point cloud model containing approximately 500,000 three-dimensional coordinate points in a unified coordinate system under different key processes.
[0060] The aforementioned industrial-grade structured light scanning equipment can be a structured light scanner from Hexagon.
[0061] Secondly, point cloud sub-models of key regions in each standard sample are obtained to obtain two-dimensional process vectors for the corresponding key regions. Each key region corresponds to a two-dimensional process vector, and the two-dimensional process vector includes partition smoothness and key sharpness.
[0062] Among them, partition smoothness is used to characterize the degree of microscopic geometric undulation in the key regions of the corresponding standard sample. Key sharpness is used to capture the morphological changes in the key regions of the standard sample.
[0063] Taking a critical area of a standard sample under any key process as an example, the process of obtaining the smoothness of the partition is as follows:
[0064] (1) Construct the k-value of the point cloud sub-model for any key region d-tree data structure.
[0065] (2) For any point in any critical region Using the already constructed k A d-tree allows for quick lookup of the k nearest neighbors.
[0066] In this embodiment, when the value of k is too small, it is easily affected by noise; when the value of k is too large, the computational load increases and may smooth out the real geometric details. Therefore, as a preferred option, the value of k can be set to 20.
[0067] (3) Acquisition Point The three-dimensional coordinates of the point and its k neighboring points are obtained, and the covariance matrix is constructed.
[0068] (4) Perform eigenvalue decomposition on the covariance matrix, and take the eigenvector corresponding to the smallest eigenvalue as the point. The surface normal vector, i.e., the unit normal vector.
[0069] (5) Traverse all points within the critical region and repeat steps (2) to (4) to obtain the surface normal vectors of all points within the critical region.
[0070] (6) Calculation points The dot product of the surface normal vectors of any of its neighboring points is taken as the standard deviation of all dot products. The regional smoothness is then used to determine the mean of the regional smoothness of all points in the key region, which is then used as the partition smoothness of the corresponding key region.
[0071] The above-mentioned partition smoothness is based on the fact that the smoother the surface, the higher the consistency of the local surface normal vectors, the smaller the angle between the surface normal vectors and the more concentrated their distribution.
[0072] For example, the surface normal vectors of a polished smooth surface are highly consistent, and the angle between the surface normal vectors is close to 0°, so the partition smoothness is extremely small; while the surface normal vectors of a rough surface after CNC roughing change drastically, the angle distribution is discrete, and the partition smoothness value increases significantly.
[0073] Ultimately, the partition smoothness of each key area under any key process can be obtained.
[0074] Taking any key area of the phone frame as an example, the process of obtaining key sharpness is as follows:
[0075] a. For any key region, perform two Random Sample Consensus (RANSAC) plane fitting algorithms to obtain the principal plane and extract the normal vector of the principal plane.
[0076] b. Calculate the cosine of the angle between the normal vectors of the two principal planes of the critical region, and obtain the critical sharpness.
[0077] Specifically, the calculation method for critical sharpness is as follows:
[0078] q = 1 - m; where m is the absolute value of the cosine of the included angle, and q is the critical sharpness.
[0079] It should be noted that when there are multiple R-corner regions in the critical area, such as the four R-corner regions of a mobile phone frame, the Random Sample Consensus (RANSAC) plane fitting algorithm is executed twice for each R-corner region to obtain the principal plane, and the normal vector of the principal plane is extracted. The mean of the difference between the absolute values of 1 and the cosine of the included angle of the four R-corner regions is used as the critical sharpness.
[0080] The purpose of the above-mentioned random sampling consensus plane fitting algorithm is to estimate the principal plane of the key region from a set containing a large number of data points.
[0081] It should be noted that when the edge is a sharp edge produced by CNC rough machining, the two principal planes of the area are almost perpendicular, and the included angle is close to 90°, at which point the critical sharpness is at its maximum. After the polishing process, the edge produces a small rounded corner, which causes the included angle between the two principal planes to increase and the included angle between the normal vectors to decrease. Therefore, the value of critical sharpness will decrease accordingly, thus sensitively reflecting the sharpening and blunting state of the edge.
[0082] The basis for establishing critical sharpness lies in the fact that different key processes directly affect the sharpness of the edge. For example, CNC-machined edges are sharp, with nearly perpendicular planes on both sides; while polishing creates tiny rounded corners on the edge, thus changing the angle between the two planes.
[0083] Then, based on the two-dimensional process vectors of each key area of all standard samples under different key processes, the standard process trajectory of the mobile phone frame in different key areas is drawn.
[0084] The process of drawing the standard process trajectory for each key area is as follows:
[0085] Obtain the centroid of the cluster containing the two-dimensional process vector set of the same key region under the same key process of all standard samples; and connect these four centroids in sequence according to the key process flow, with the smoothness of the partition as the x-axis and the sharpness of the key as the y-axis, to obtain a piecewise linear standard process trajectory.
[0086] For example, Figure 2 This represents the standard trajectory region for a critical area, where cluster 1 corresponds to CNC roughing, cluster 2 to CNC finishing, cluster 3 to surface polishing, cluster 4 to anodizing, point 5 to the location of the real-time 2D process vector, and projection point 6 to the foot of the perpendicular line drawn from point 5 (the location of the real-time 2D process vector) to the standard process trajectory. Figure 2 The broken line in the diagram represents the standard process trajectory, and an elliptical shaded area represents a cluster.
[0087] It should be noted that each key area corresponds to a standard process trajectory for a complete production process.
[0088] Step S3: Obtain the real-time two-dimensional process vectors of each key area of the current mobile phone frame, and calculate the vertical distance between the real-time two-dimensional process vectors of each key area and the corresponding standard process trajectory; and determine the production progress and quality based on the vertical distance.
[0089] The method for calculating the real-time two-dimensional process vector in this embodiment is the same as the method for calculating the two-dimensional process vector in step S2, and will not be described in detail here.
[0090] The vertical distance is the length of the perpendicular line from the point where the real-time two-dimensional process vector of each key region is located to the corresponding standard process trajectory.
[0091] For example, Figure 2 The length of the line connecting point 5, where the real-time two-dimensional process vector is located, to the projection point 6 is the vertical distance.
[0092] In this embodiment, the determination of production progress and quality based on vertical distance includes:
[0093] First, determining the production schedule, specifically including:
[0094] Obtain the projection point of the real-time two-dimensional process vector on the corresponding standard process trajectory, and obtain the trajectory length from the trajectory start point to the projection point. Use the ratio of the trajectory length to the total trajectory length as the production progress of the current mobile phone frame.
[0095] In this embodiment, the process stage to which the product belongs and the specific degree of completion within that process can be determined based on the numerical range of the production progress.
[0096] Second, the determination of production quality. If the vertical distance is less than or equal to the corresponding tolerance width, the current mobile phone frame is considered to be qualified in the production process; otherwise, it is considered unqualified.
[0097] The above tolerance width refers to the tolerable width on both sides of the standard process trajectory.
[0098] In one embodiment, the process of obtaining the tolerance width is as follows:
[0099] Obtain the cluster containing the two-dimensional process vector set of the same key area of all standard samples under the same key process. Take the standard deviation of the vertical distance of all data in the cluster to the standard process trajectory, and use 3 times the standard deviation as the tolerance width of the standard process trajectory of the corresponding key process.
[0100] It should be noted that the tolerance width may be the same or different for different key processes.
[0101] In another embodiment, the settings can also be manually configured according to actual circumstances.
[0102] For example, Figure 2 The width of the standard trajectory region (the shaded envelope region where the standard process trajectory is located) is the tolerance width.
[0103] The above-mentioned monitoring of the current mobile phone frame production progress is approached from two aspects: one is the determination of production progress, and the other is the determination of mobile phone frame quality. That is, by making judgments from two aspects, the current mobile phone frame production progress can be monitored more reasonably.
[0104] Furthermore, an inspection report can be generated, which includes: inspection timestamp, unique frame number, identified process, continuous progress, quality score, and judgment level (pass / abnormal). When the judgment level is abnormal, the system automatically triggers an audible and visual alarm to allow engineering technicians to intervene quickly.
[0105] The present invention divides the current mobile phone frame into different key areas and constructs a standard process trajectory for each key area. By calculating the geometric relationship (vertical distance and projected length) between the current mobile phone frame and the standard process trajectory in this space, the processing quality and production progress of the product can be evaluated.
[0106] This invention also provides a mobile phone frame production progress monitoring system. For example... Figure 3 As shown, the system includes a processor and a memory, the memory storing computer program instructions, which, when executed by the processor, implement the mobile phone frame production progress monitoring method according to the present invention.
[0107] The system also includes other components well known to those skilled in the art, such as communication buses and communication interfaces, the settings and functions of which are known in the art and therefore will not be described in detail here.
[0108] In this invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store desired information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device. Any application or module described in this invention can be implemented by computer-readable / executable instructions stored or otherwise maintained on such a computer-readable medium.
[0109] In the description of this specification, "multiple" means at least two, such as two, three or more, etc., unless otherwise expressly and specifically defined.
[0110] While various embodiments of the invention have been shown and described in this specification, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will occur to those skilled in the art without departing from the spirit and essence of the invention.
Claims
1. A method for monitoring the production progress of a mobile phone frame, characterized in that, include: Obtain the point cloud model of the current mobile phone frame, and divide the current mobile phone frame into regions to obtain the point cloud sub-models of each key region. Establish standard process trajectories for several key areas of the current mobile phone framework; Obtain the real-time two-dimensional process vectors of the point cloud sub-models of each key region of the current mobile phone frame; Calculate the vertical distance from the real-time two-dimensional process vector to the corresponding standard process trajectory. When the vertical distance is less than or equal to the corresponding tolerance width, the production quality of the current mobile phone frame is determined to be qualified. The standard process trajectory includes: acquiring point cloud models of multiple standard samples at different key processes; calculating a two-dimensional process vector for each key region under any key process based on the point cloud sub-model of each key region of each standard sample, wherein the two-dimensional process vector includes partition smoothness and key sharpness, wherein partition smoothness characterizes the degree of undulation within the key region and key sharpness characterizes the change in edge features of the key region; and sequentially connecting the centroids of the clusters formed by the two-dimensional process vectors under the same key process to form the standard process trajectory. It also includes: obtaining the projection point of the real-time two-dimensional process vector on the standard process trajectory, and using the ratio of the length from the trajectory start point to the projection point to the total length of the standard process trajectory as the current production progress of the mobile phone frame; Partition smoothness: Obtain the surface normal vectors of all points in the point cloud sub-model of the key region; Calculate the standard deviation of the dot product of the surface normal vector of any point and the surface normal vectors of its neighboring points. Use the mean of the standard deviations of the dot products of all points within the key region as the partition smoothness of the corresponding key region. The neighboring points are k points obtained by constructing the point cloud sub-model. The data is obtained by querying a d-tree data structure; Key sharpness: q = 1 - m; where m is the absolute value of the cosine of the included angle, and q is the key sharpness; the process of obtaining the absolute value of the cosine of the included angle includes: performing two plane fittings on the key region to obtain two principal planes, and calculating the absolute value of the cosine of the included angle between the normal vectors of the two principal planes; The x-axis represents the smoothness of the partition, and the y-axis represents the sharpness of the key.
2. The method for monitoring the production progress of a mobile phone frame according to claim 1, characterized in that, The method for obtaining the surface normal vector includes: For any point within the critical region, obtain the three-dimensional coordinates of its k neighboring points and construct a covariance matrix; perform eigenvalue decomposition on the covariance matrix, and take the eigenvector corresponding to the smallest eigenvalue as the surface normal vector of the corresponding point, where k is a preset positive integer.
3. The method for monitoring the production progress of a mobile phone frame according to claim 1, characterized in that, The plane fitting uses a random sampling consensus algorithm.
4. The method for monitoring the production progress of a mobile phone frame according to claim 1, characterized in that, The process of dividing the current mobile phone frame into regions includes: pre-defined key regions based on the CAD model of the current mobile phone frame, including chamfered areas, side frame plane areas, antenna slot areas, and camera module mounting surfaces.
5. The method for monitoring the production progress of a mobile phone frame according to claim 1, characterized in that, The method for obtaining the tolerance width includes: Obtain the cluster containing the two-dimensional process vector set of the same critical region of all standard samples under the same critical process; take three times the standard deviation of the vertical distance from all data in the cluster to the standard process trajectory as the tolerance width of the standard process trajectory of the corresponding critical process.
6. The method for monitoring the production progress of a mobile phone frame according to claim 1, characterized in that, The step of obtaining the point cloud model of the current mobile phone frame includes: Industrial-grade structured light scanning equipment was used to scan the current mobile phone frame from at least six different perspectives; The point cloud model of the current mobile phone frame is obtained by registering and fusing multi-view point cloud data through the iterative nearest point algorithm.
7. A mobile phone frame production progress monitoring system, characterized in that, include: processor; A memory storing computer instructions for monitoring the production progress of a mobile phone frame, wherein when the computer instructions are executed by the processor, the system performs a method for monitoring the production progress of a mobile phone frame according to any one of claims 1-6.