Silicon nanometer device processing intelligent control system and method

Through image acquisition and recognition technology, intelligent control paths are generated to monitor the processing process of silicon nanodevices in real time, solving the defective products caused by errors in silicon nanodevices processing, improving processing accuracy and efficiency, and reducing costs.

CN118919445AInactive Publication Date: 2024-11-08HEZE UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410961598.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-08
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In real-time detection during silicon nanodevices processing, resulting in parameter errors leading to large batches of defective products, increasing costs.

Method used

Image acquisition and recognition technology are used to generate intelligent control paths, monitor the processing process in real time, and determine errors by comparing the finished image with the shapes in the drawings and generate monitoring results, and automatically stop or correct the paths to avoid errors.

Benefits of technology

It effectively avoids the generation of defective products caused by parameter errors, improves the accuracy and efficiency of silicon nano-device processing, and reduces costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118919445A_ABST
    Figure CN118919445A_ABST
Patent Text Reader

Abstract

The invention is suitable for the technical field of silicon nanometer device processing, and particularly relates to an intelligent control system and method for silicon nanometer device processing, and the method comprises the steps: obtaining a to-be-processed drawing, and fixing a to-be-processed raw material on a clamp; performing image acquisition on a to-be-processed raw material, positioning the to-be-processed raw material, and generating a global processing path; the drawing to be machined is recognized, a local machining path is determined, and an intelligent control path is generated; and performing image acquisition on the silicon nanometer device according to the intelligent control path to obtain a real-time monitoring image, performing finished product comparison on the real-time monitoring image, judging whether processing errors exist or not, and generating a monitoring result. According to the method, the drawing and the raw materials are subjected to image recognition, so that the machining path is automatically planned, the error between the machined finished product and the drawing is automatically recognized in the machining process, when the error is too large, automatic stopping is conducted, and the situation that a large number of defective products appear due to the error is avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of silicon nano device processing, and in particular relates to an intelligent control system and method for silicon nano device processing. Background Art

[0002] Silicon nanodevices refer to electronic, optoelectronic or other types of micro devices made of nanoscale silicon materials. Due to their special properties at the nanoscale, these devices exhibit different functions and performances from traditional macroscale silicon devices and have broad application prospects.

[0003] In the current silicon nanodevice processing, processing is usually carried out directly according to the processing drawings. The silicon nanodevices cannot be tested during the processing, and parameter errors usually occur, resulting in a large number of defective products and increased costs. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent control method for silicon nanodevice processing, aiming to solve the problem that silicon nanodevices cannot be detected during the processing, generally parameter errors occur, a large number of defective products will appear, and the cost will increase.

[0005] The present invention is implemented as follows: a silicon nanodevice processing intelligent control method, the method comprising:

[0006] Get the drawings to be processed and fix the raw materials to be processed on the fixture;

[0007] Capture images of the raw materials to be processed, locate the raw materials to be processed, and generate a global processing path;

[0008] Identify the drawings to be processed, determine the local processing path of each raw material to be processed, and generate an intelligent control path based on the local processing path and the global processing path;

[0009] According to the intelligent control path, the silicon nanodevice is imaged to obtain a real-time monitoring image, which is then compared with the finished product to determine whether there are processing errors and generate monitoring results.

[0010] Preferably, the steps of collecting images of the raw material to be processed, positioning the raw material to be processed, and generating a global processing path specifically include:

[0011] Collect images of the raw materials to be processed to obtain raw material monitoring images;

[0012] Pre-process the raw material monitoring image and convert it into a line graph, and identify the location of the raw material to be processed by recognizing the line graph;

[0013] A two-dimensional coordinate system is constructed according to the positions of each raw material to be processed, and the two-dimensional coordinates of the raw materials are determined, thereby generating a global processing path.

[0014] Preferably, the step of identifying the drawings to be processed, determining the local processing path of each raw material to be processed, and generating an intelligent control path according to the local processing path and the global processing path specifically includes:

[0015] Retrieve the drawings to be processed, identify the lines in the drawings to be processed, and determine the finished shapes of each silicon nanodevice;

[0016] Perform local path planning according to the finished product shape of the silicon nanodevice and select the optimal path as the local processing path;

[0017] Retrieve the global processing path, add the local processing path to the global processing path, and obtain the intelligent control path by performing the shortest path calculation.

[0018] Preferably, the steps of collecting images of silicon nanodevices according to the intelligent control path to obtain real-time monitoring images, comparing the real-time monitoring images with finished products, determining whether there are errors in processing, and generating monitoring results specifically include:

[0019] The silicon nanodevice is imaged according to a preset distance step length to obtain a real-time monitoring image;

[0020] Performing image processing on the real-time monitoring image, extracting the finished product image of the silicon nanodevice, and comparing the finished product image with the finished product shape in the drawing to be processed to obtain a comparison result;

[0021] The error ratio of the silicon nanodevice is calculated based on the comparison results. When the error ratio exceeds a preset range, it is determined that there is an error in the current processing process and the processing is suspended.

[0022] Preferably, when the error ratio is within a preset range, path correction data is generated, and the error of the intelligent control path is eliminated according to the path correction data.

[0023] Another object of the present invention is to provide an intelligent control system for silicon nanodevice processing, the system comprising:

[0024] The drawing acquisition module is used to obtain the drawings to be processed and fix the raw materials to be processed on the fixture;

[0025] A global path planning module is used to collect images of the raw materials to be processed, locate the raw materials to be processed, and generate a global processing path;

[0026] The control path generation module is used to identify the processing drawings to be processed, determine the local processing path of each raw material to be processed, and generate an intelligent control path based on the local processing path and the global processing path;

[0027] The finished product monitoring module is used to collect images of silicon nanodevices according to the intelligent control path, obtain real-time monitoring images, compare the real-time monitoring images with finished products, determine whether there are errors in processing, and generate monitoring results.

[0028] Preferably, the global path planning module includes:

[0029] A raw material image acquisition unit, used to acquire images of the raw materials to be processed to obtain raw material monitoring images;

[0030] A raw material identification unit is used to pre-process the raw material monitoring image and convert it into a line graph, and identify the position of the raw material to be processed by identifying the line graph;

[0031] The raw material positioning unit is used to construct a two-dimensional coordinate system according to the positions of each raw material to be processed, determine the two-dimensional coordinates of the raw material, and thus generate a global processing path.

[0032] Preferably, the control path generation module includes:

[0033] A finished product identification unit for drawing is used to retrieve the drawing to be processed, identify the lines in the drawing to be processed, and determine the finished product shape of each silicon nanodevice;

[0034] A local path planning unit, used for performing local path planning according to the finished product shape of the silicon nanodevice, and selecting an optimal path as a local processing path;

[0035] The path synthesis unit is used to call the global processing path, add the local processing path to the global processing path, and obtain the intelligent control path by performing the shortest path calculation.

[0036] Preferably, the finished product monitoring module includes:

[0037] A monitoring image acquisition unit is used to acquire images of the silicon nanodevice according to a preset distance step length to obtain a real-time monitoring image;

[0038] A data comparison unit is used to perform image processing on the real-time monitoring image, extract the finished product image of the silicon nanodevice, compare the finished product image with the finished product shape in the drawing to be processed, and obtain a comparison result;

[0039] The error determination unit is used to calculate the error ratio of the silicon nanodevice according to the comparison result. When the error ratio exceeds a preset range, it is determined that there is an error in the current processing process and the processing is suspended.

[0040] Preferably, when the error ratio is within a preset range, path correction data is generated, and the error of the intelligent control path is eliminated according to the path correction data.

[0041] The present invention provides an intelligent control method for processing silicon nanodevices. The method automatically plans the processing path by performing image recognition on drawings and raw materials. During the processing, the method automatically identifies the error between the processed finished product and the drawing. When the error is too large, the method automatically stops, thus avoiding the occurrence of large quantities of defective products due to errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A flow chart of a silicon nanodevice processing intelligent control method provided by an embodiment of the present invention;

[0043] Figure 2 A flowchart of the steps of collecting images of a raw material to be processed, positioning the raw material to be processed, and generating a global processing path provided by an embodiment of the present invention;

[0044] Figure 3 A flowchart of the steps of identifying a drawing to be processed, determining a local processing path for each raw material to be processed, and generating an intelligent control path according to the local processing path and the global processing path provided by an embodiment of the present invention;

[0045] Figure 4 A flowchart of the steps of collecting images of silicon nanodevices according to an intelligent control path, obtaining real-time monitoring images, comparing the real-time monitoring images with finished products, determining whether there are processing errors, and generating monitoring results provided in an embodiment of the present invention;

[0046] Figure 5 An architecture diagram of an intelligent control system for processing silicon nanodevices provided by an embodiment of the present invention;

[0047] Figure 6 An architecture diagram of a global path planning module provided by an embodiment of the present invention;

[0048] Figure 7 An architecture diagram of a control path generation module provided by an embodiment of the present invention;

[0049] Figure 8 An architectural diagram of a finished product monitoring module provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0051] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0052] like Figure 1 FIG. 1 is a flow chart of a method for intelligent control of silicon nanodevice processing provided by an embodiment of the present invention, the method comprising:

[0053] S100, obtaining the drawing to be processed and fixing the raw material to be processed on a fixture.

[0054] In this step, the image to be processed is obtained. In the drawing to be processed, the finished structure of different silicon nanodevices is recorded. The drawing to be processed is recorded through a two-dimensional plane drawing, such as a CAD drawing. Then, the line information contained therein can be directly read to determine the structure of each finished silicon nanodevice. The raw material to be processed is fixed on the stage of the laser cutting equipment. The raw material to be processed is fixed on the entire base plate. The raw material to be processed is distributed in an array. When fixing, the base plate can be fixed on the stage by a clamp.

[0055] S200, collecting images of the raw material to be processed, positioning the raw material to be processed, and generating a global processing path.

[0056] In this step, images of the raw materials to be processed are captured. Specifically, a high-resolution industrial microscope camera is used to capture the images, and the captured images are processed so that the edges of the raw materials to be processed can be distinguished. After the edges are identified, the positions of the raw materials to be processed can be located. Since a plurality of raw materials to be processed are arranged on the entire bottom plate and their positions are different, in order to complete the processing of all the raw materials to be processed in one batch, it is necessary to plan the processing sequence of each raw material to be processed, so as to obtain a global processing path, that is, the global processing path records the movement path of the laser between the raw materials to be processed, and does not include the specific cutting path when processing a single raw material to be processed.

[0057] S300, identifying the drawings to be processed, determining the local processing path of each raw material to be processed, and generating an intelligent control path according to the local processing path and the global processing path.

[0058] In this step, the drawings to be processed are identified. Different silicon nanodevices have different structures. Therefore, during laser cutting, the processing paths are different. The drawings to be processed are identified to determine the processing paths of various types of silicon nanodevices, that is, to obtain the local processing paths. When the raw materials to be processed are processed, the laser light moves along the local processing paths, and a raw material to be processed can be processed into a silicon nanodevice of a corresponding shape. In order to complete the processing of all raw materials to be processed at one time, the local processing paths are added to the global processing paths according to the positions of each raw material to be processed, that is, to obtain the intelligent control path. The intelligent control path is a continuous path with only one starting position and one ending position.

[0059] S400, collecting images of silicon nanodevices according to the intelligent control path to obtain real-time monitoring images, comparing the real-time monitoring images with finished products, determining whether there are processing errors, and generating monitoring results.

[0060] In this step, images of silicon nanodevices are captured according to the intelligent control path. During the processing, the laser light moves continuously along the intelligent control path. During the movement, each silicon nanodevice is processed. However, due to the precision error of the equipment, offset may occur during the processing. At this time, image capture is performed along the intelligent control path through a high-resolution industrial microscope camera. Image capture is performed on the silicon nanodevices that have been processed on the path. By processing the captured images, the extracted finished product image is compared with the drawing to be processed, so as to calculate the error and determine whether to continue processing based on the error.

[0061] like Figure 2 As shown, as a preferred embodiment of the present invention, the steps of collecting images of the raw material to be processed, positioning the raw material to be processed, and generating a global processing path specifically include:

[0062] S201, collecting images of the raw materials to be processed to obtain raw material monitoring images.

[0063] In this step, images of the raw materials to be processed are captured, and a high-resolution industrial microscope camera is controlled to capture images to obtain a raw material monitoring image. If the coverage of the high-resolution industrial microscope camera is smaller than the size of the base plate, the captured images can be spliced ​​into a raw material monitoring image by performing multiple image capture operations.

[0064] S202, pre-processing the raw material monitoring image, converting it into a line graph, and identifying the position of the raw material to be processed by identifying the line graph.

[0065] In this step, the raw material monitoring image is preprocessed. First, the raw material monitoring image is converted into a grayscale image, and the grayscale image is used to reduce the amount of data processing. Then, the Hough transform is used to convert the entire grayscale image into a line graph. Then, the outline of each raw material to be processed can be directly identified, thereby determining the location of each raw material to be processed.

[0066] S203, constructing a two-dimensional coordinate system according to the positions of the raw materials to be processed, determining the two-dimensional coordinates of the raw materials, and thus generating a global processing path.

[0067] In step S203, a two-dimensional coordinate system is constructed according to the positions of the raw materials to be processed, and the two-dimensional coordinates of the raw materials are determined, thereby generating a global processing path, which includes the following sub-steps:

[0068] Step S2031, obtaining the area and specific attribute value of each raw material to be processed, and calculating the distance between the current processing position and each raw material to be processed;

[0069] Step S2032, calculating the processing priority score of each raw material to be processed according to the area of ​​each raw material to be processed, the specific attribute value, and the distance between the current processing position and the raw material to be processed;

[0070] Among them, the calculation function of the processing priority score of each raw material to be processed is expressed as:

[0071]

[0072] Where P(i) represents the processing priority score of each raw material to be processed, d i represents the distance from the current processing position to the i-th raw material to be processed, s i represents the area of ​​the i-th raw material to be processed, c i represents the specific attribute value of the i-th raw material to be processed; α, β and γ represent weight coefficients, which are used to balance the influence of distance, size and specific attribute value on priority; x current Indicates the horizontal coordinate of the current processing position, y current Indicates the ordinate of the current processing position, x i Represents the horizontal coordinate of the raw material to be processed, y i Represents the vertical coordinate of the raw material to be processed.

[0073] As a supplementary explanation, the distance d from the current processing position to the i-th raw material to be processed is i , the smaller d i The value means a higher priority. For the area s of the i-th raw material to be processed i , can be measured by image processing technology. Smaller s iThe value may indicate that the raw material is easier to process and is therefore given a higher priority. i , which can be the shape complexity, color or other features of the raw material that can be quantified by image processing technology. This value can be defined according to the specific application scenario to reflect the processing difficulty or priority.

[0074] Step S2033, arranging the raw materials to be processed in descending order according to the processing priority scores of each raw material to be processed to generate a global processing path.

[0075] In the present invention, by calculating the P(i) value of each raw material, a processing priority ranking can be obtained. Then, the raw material with the highest P(i) value can be selected as the next processing target, thereby generating a global processing path.

[0076] In this step, a two-dimensional coordinate system is constructed according to the positions of each raw material to be processed. The two-dimensional coordinate system can be constructed based on the raw material monitoring image. For example, a two-dimensional coordinate system is constructed with the pixel in the lower left corner of the raw material monitoring image as the origin. Then each pixel can get a specific coordinate, and the pixels contained in each raw material to be processed can also be determined accordingly. The average coordinates of all pixels contained in the raw material to be processed can be used as the coordinates of the raw material to be processed. After determining the coordinates of the raw material to be processed, path planning can be performed to determine the shortest path connecting each raw material to be processed, which is the global processing path.

[0077] like Figure 3 As shown, as a preferred embodiment of the present invention, the steps of identifying the drawings to be processed, determining the local processing path of each raw material to be processed, and generating the intelligent control path according to the local processing path and the global processing path specifically include:

[0078] S301, retrieve the drawing to be processed, identify the lines in the drawing to be processed, and determine the finished product shape of each silicon nanodevice.

[0079] In this step, the drawings to be processed are retrieved, in which the processing drawings of various silicon nanodevices, i.e., line drawings of finished silicon nanodevices, are recorded, and each finished silicon nanodevice is provided with a corresponding identification mark. By reading the identification mark, the position of the finished silicon nanodevice can be determined, thereby determining the finished shape of each silicon nanodevice.

[0080] S302, performing local path planning according to the finished product shape of the silicon nanodevice, and selecting the optimal path as the local processing path.

[0081] In step S302, in the step of selecting the optimal path as the local processing path, the corresponding function expression is:

[0082]

[0083] Among them, P′ opt (t) indicates the selection of the optimal path as the local processing path, C(S, P′, t) indicates the cost function, D(P, t) indicates the dynamic programming function, T indicates the total processing time, min P represents the minimum value of all possible local processing paths P′, t represents the processing time, S complexity Indicates the complexity of the finished product shape, P′ length (t) represents the length of the path P′ at the processing time t, V(t) represents the processing speed at the processing time t, A(t) represents the processing accuracy requirement at the processing time t, ω1, ω2, ω3 and ω4 represent the second weight coefficient, P′ j represents the jth path point on the local processing path P′, ε j With φ j Both represent the path point P′ j The related constants, represents the impact rate of processing time on path cost, dist(P′ j , P′ j+1 ) represents the path point P′ j and path point P′ j+1 The distance between them, m represents the total number of path points.

[0084] In this step, local path planning is performed according to the finished shape of the silicon nanodevice, and path planning is performed according to the lines of the silicon nanodevice to determine the processing path required for the current silicon nanodevice, which is the local processing path. If there are multiple processing paths, the processing path with the shortest path is selected as the local processing path.

[0085] S303, calling the global processing path, adding the local processing path to the global processing path, and obtaining the intelligent control path by performing the shortest path calculation.

[0086] In this step, the global processing path is called up. The global processing path records the movement path of the laser between each raw material to be processed. How to process each raw material to be processed is determined by the local processing path. The corresponding local processing path is determined according to the type of each raw material to be processed, and the local processing path is merged into the global processing path to obtain an intelligent control path.

[0087] like Figure 4As shown, as a preferred embodiment of the present invention, the steps of collecting images of silicon nanodevices according to the intelligent control path to obtain real-time monitoring images, comparing the real-time monitoring images with finished products, determining whether there are errors in processing, and generating monitoring results specifically include:

[0088] S401, collecting images of the silicon nanodevice according to a preset distance step length to obtain a real-time monitoring image.

[0089] In this step, images of silicon nanodevices are collected according to a preset distance step. For the intelligent control path, the length L of the intelligent control path is calculated, and the distance step is determined according to the quantity S of raw materials to be processed. The distance step is not less than L / S. Whenever the distance moved by the laser reaches the distance step, an image is collected to obtain a set of real-time monitoring images.

[0090] S402, performing image processing on the real-time monitoring image, extracting the finished product image of the silicon nanodevice, and comparing the finished product image with the finished product shape in the drawing to be processed to obtain a comparison result.

[0091] In step S402, the real-time monitoring image is processed to extract the finished product image of the silicon nanodevice, and the finished product image is compared with the finished product shape in the drawing to be processed. In the step of obtaining the comparison result, the comparison is performed by calculating the error value between the finished product image and the finished product shape in the drawing to be processed;

[0092] The calculation formula of the error value between the finished product image and the finished product shape in the drawing to be processed is expressed as:

[0093]

[0094] Among them, E represents the error value between the finished product image and the finished product shape in the drawing to be processed, G and H represent the maximum width and maximum height of the real-time monitoring image respectively, and I gh represents the pixel value of the real-time monitoring image at position (g, h), P gh Represents the pixel value of the finished shape image at position (g, h) in the drawing to be processed, Represents the average pixel value of the real-time monitoring image, represents the average pixel value of the drawing to be processed, g and h represent the width and height of the real-time monitoring image respectively, and N represents the total number of pixels contained in the image of the silicon nanodevice in the real-time monitoring image.

[0095] In this step, the real-time monitoring image is processed. Similarly, grayscale processing is first performed to convert the real-time monitoring image into a grayscale image, and Hough transform is used for line processing. Then, by performing line recognition, the image of the silicon nanodevice in the real-time monitoring image can be determined, and then it can be compared with the shape of the finished product in the drawing to be processed.

[0096] S403, calculating the error ratio of the silicon nanodevice according to the comparison result, when the error ratio exceeds a preset range, it is determined that there is an error in the current processing process, and the processing is suspended.

[0097] As described above, since the comparison result includes an error value, the error ratio of the silicon nanodevice can be further calculated based on the calculated error value. When the error ratio exceeds the preset range, it is determined that there is an error in the current processing process and the processing is suspended.

[0098] In this step, the error ratio of the silicon nanodevice is calculated according to the comparison result to determine whether the error ratio exceeds a preset range. If so, the processing is suspended; if not, the path is adjusted according to the error ratio.

[0099] like Figure 5 As shown, an intelligent control system for silicon nanodevice processing provided by an embodiment of the present invention includes:

[0100] The drawing acquisition module 100 is used to acquire the drawing to be processed and fix the raw material to be processed on the fixture.

[0101] In this system, the drawing acquisition module 100 acquires the image to be processed, in which the finished product structures of different silicon nanodevices are recorded. The drawing to be processed is recorded through a two-dimensional plane drawing, such as a CAD drawing, so the line information contained therein can be directly read to determine the structure of each finished silicon nanodevice. The raw material to be processed is fixed on the stage of the laser cutting equipment. The raw material to be processed is fixed on the entire bottom plate. The raw material to be processed is distributed in an array. When fixing, the bottom plate can be fixed on the stage by a clamp.

[0102] The global path planning module 200 is used to collect images of the raw materials to be processed, locate the raw materials to be processed, and generate a global processing path.

[0103] In the present system, the global path planning module 200 acquires images of the raw materials to be processed. Specifically, a high-resolution industrial microscope camera is used for image acquisition, and the acquired images are processed so as to distinguish the edges of the raw materials to be processed. After identifying the edges, the positions of the raw materials to be processed can be located. Since a plurality of raw materials to be processed are arranged on the entire bottom plate and their positions are different, in order to complete the processing of all the raw materials to be processed in one batch, it is necessary to plan the processing sequence of each raw material to be processed, so as to obtain a global processing path, that is, the global processing path records the movement path of the laser between the raw materials to be processed, and does not include the specific cutting path when processing a single raw material to be processed.

[0104] The control path generation module 300 is used to identify the drawings to be processed, determine the local processing path of each raw material to be processed, and generate an intelligent control path according to the local processing path and the global processing path.

[0105] In this system, the control path generation module 300 identifies the drawings to be processed. Different silicon nanodevices have different structures. Therefore, when laser cutting is performed, the processing paths are different. The drawings to be processed are identified to determine the processing paths of various types of silicon nanodevices, that is, to obtain a local processing path. When processing the raw materials to be processed, the laser light moves according to the local processing path, and a raw material to be processed can be processed into a silicon nanodevice of a corresponding shape. In order to complete the processing of all raw materials to be processed at one time, the local processing path is added to the global processing path according to the position of each raw material to be processed, that is, to obtain an intelligent control path. The intelligent control path is a continuous path with only one starting position and one ending position.

[0106] The finished product monitoring module 400 is used to collect images of silicon nanodevices according to the intelligent control path to obtain real-time monitoring images, compare the real-time monitoring images with finished products, determine whether there are errors in processing, and generate monitoring results.

[0107] In this system, the finished product monitoring module 400 collects images of the silicon nanodevice according to the intelligent control path. During the processing, the laser light moves continuously along the intelligent control path. During the movement, each silicon nanodevice is processed. However, due to the precision error of the equipment, offset may occur during the processing. At this time, a high-resolution industrial microscope camera is used to collect images along the intelligent control path, and images of the silicon nanodevices that have been processed on the path are collected. By processing the collected images, the extracted finished product images are compared with the drawings to be processed, so as to calculate the errors and determine whether to continue processing based on the errors.

[0108] like Figure 6 As shown, as a preferred embodiment of the present invention, the global path planning module 200 includes:

[0109] The raw material image acquisition unit 201 is used to acquire images of the raw materials to be processed to obtain raw material monitoring images.

[0110] In this module, the raw material image acquisition unit 201 acquires images of the raw materials to be processed, controls the high-resolution industrial microscope camera to acquire images, and obtains the raw material monitoring image. If the coverage of the high-resolution industrial microscope camera is smaller than the size of the base plate, the acquired images can be spliced ​​into the raw material monitoring image by performing multiple image acquisitions.

[0111] The raw material identification unit 202 is used to pre-process the raw material monitoring image and convert it into a line graph, and identify the position of the raw material to be processed by identifying the line graph.

[0112] In this module, the raw material identification unit 202 pre-processes the raw material monitoring image by first converting the raw material monitoring image into a grayscale image, using the grayscale image to reduce the amount of data processing, and then using the Hough transform to convert the entire grayscale image into a line graph, so that the contours of each raw material to be processed can be directly identified, thereby determining the location of each raw material to be processed.

[0113] The raw material positioning unit 203 is used to construct a two-dimensional coordinate system according to the positions of each raw material to be processed, determine the two-dimensional coordinates of the raw material, and thus generate a global processing path.

[0114] In this module, the raw material positioning unit 203 constructs a two-dimensional coordinate system according to the positions of each raw material to be processed. The two-dimensional coordinate system can be constructed based on the raw material monitoring image. For example, the pixel in the lower left corner of the raw material monitoring image is used as the origin to construct a two-dimensional coordinate system. Then each pixel can get a specific coordinate, and the pixels contained in each raw material to be processed can also be determined accordingly. The average coordinates of all pixels contained in the raw material to be processed can be used as the coordinates of the raw material to be processed. After determining the coordinates of the raw material to be processed, path planning can be performed to determine the shortest path connecting each raw material to be processed, which is the global processing path.

[0115] like Figure 7 As shown, as a preferred embodiment of the present invention, the control path generation module 300 includes:

[0116] The finished product identification unit 301 is used to retrieve the drawing to be processed, identify the lines in the drawing to be processed, and determine the finished product shape of each silicon nanodevice.

[0117] In this module, the finished product identification unit 301 retrieves the drawing to be processed, which records the processing drawings of various silicon nanodevices, that is, the line drawings of the finished silicon nanodevices, and each finished silicon nanodevice is provided with a corresponding identification mark. By reading the identification mark, the position of the finished silicon nanodevice can be determined, thereby determining the finished shape of each silicon nanodevice.

[0118] The local path planning unit 302 is used to perform local path planning according to the finished product shape of the silicon nanodevice and select the optimal path as the local processing path.

[0119] In this module, the local path planning unit 302 performs local path planning according to the finished product shape of the silicon nanodevice, and performs path planning according to the lines of the silicon nanodevice to determine the processing path required for the current silicon nanodevice, which is the local processing path. If there are multiple processing paths, the processing path with the shortest path is selected as the local processing path.

[0120] The path synthesis unit 303 is used to retrieve the global processing path, add the local processing path to the global processing path, and obtain the intelligent control path by performing the shortest path calculation.

[0121] In this module, the path synthesis unit 303 calls the global processing path, which records the movement path of the laser between each raw material to be processed. How to process each raw material to be processed is determined by the local processing path. The corresponding local processing path is determined according to the type of each raw material to be processed, and the local processing path is merged into the global processing path to obtain an intelligent control path.

[0122] like Figure 8 As shown, as a preferred embodiment of the present invention, the finished product monitoring module 400 includes:

[0123] The monitoring image acquisition unit 401 is used to acquire images of the silicon nanodevice according to a preset distance step to obtain a real-time monitoring image.

[0124] In this module, the monitoring graphic acquisition unit 401 performs image acquisition on the silicon nanodevice according to the preset distance step. For the intelligent control path, the length L of the intelligent control path is calculated, and the distance step is determined according to the quantity S of the raw materials to be processed. The distance step is not less than L / S. Whenever the distance moved by the laser reaches the distance step, an image acquisition is performed to obtain a set of real-time monitoring images.

[0125] The data comparison unit 402 is used to perform image processing on the real-time monitoring image, extract the finished product image of the silicon nanodevice, compare the finished product image with the finished product shape in the drawing to be processed, and obtain a comparison result.

[0126] In this module, the data comparison unit 402 performs image processing on the real-time monitoring image. Similarly, grayscale processing is first performed to convert the real-time monitoring image into a grayscale image, and Hough transform is used to perform line processing. Then, by performing line recognition, the image of the silicon nanodevice in the real-time monitoring image can be determined, so as to compare it with the shape of the finished product in the drawing to be processed. Specifically, the image of the silicon nanodevice in the real-time monitoring image is scaled, and the image of the silicon nanodevice in the real-time monitoring image has the same width and height as the finished product shape, so as to subsequently calculate the number of pixel overlaps M between the two, and the total number of pixels contained in the image of the silicon nanodevice in the real-time monitoring image is N.

[0127] The error determination unit 403 is used to calculate the error ratio of the silicon nanodevice according to the comparison result. When the error ratio exceeds a preset range, it is determined that there is an error in the current processing process and the processing is suspended.

[0128] In this module, the error judgment unit 403 calculates the error ratio of the silicon nanodevice according to the comparison result, error ratio = (NM) / N, and determines whether the error ratio exceeds the preset range. If it exceeds, the processing is suspended. If it has not exceeded, the path is adjusted according to the error ratio.

[0129] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0130] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0131] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0132] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0133] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A silicon nanodevice processing intelligent control method, characterized in that: The method comprises: Get the drawings to be processed and fix the raw materials to be processed on the fixture; Capture images of the raw materials to be processed, locate the raw materials to be processed, and generate a global processing path; Identify the drawings to be processed, determine the local processing path of each raw material to be processed, and generate an intelligent control path based on the local processing path and the global processing path; According to the intelligent control path, the silicon nanodevice is imaged to obtain a real-time monitoring image, and the real-time monitoring image is compared with the finished product to determine whether there is an error in the processing and generate a monitoring result; The steps of collecting images of the raw material to be processed, positioning the raw material to be processed, and generating a global processing path specifically include: Collect images of the raw materials to be processed to obtain raw material monitoring images; Pre-process the raw material monitoring image and convert it into a line graph, and identify the location of the raw material to be processed by recognizing the line graph; A two-dimensional coordinate system is constructed according to the positions of each raw material to be processed, and the two-dimensional coordinates of the raw materials are determined, thereby generating a global processing path.

2. The method for intelligent control of silicon nanodevice processing according to claim 1, characterized in that: The step of constructing a two-dimensional coordinate system according to the positions of each raw material to be processed, determining the two-dimensional coordinates of the raw material, and thus generating a global processing path includes the following sub-steps: Obtain the area and specific attribute value of each raw material to be processed, and calculate the distance between the current processing position and each raw material to be processed; Calculate the processing priority score of each raw material to be processed according to the area, specific attribute value and distance between the current processing position and the raw material to be processed; Among them, the calculation function of the processing priority score of each raw material to be processed is expressed as: Where P(i) represents the processing priority score of each raw material to be processed, d i represents the distance from the current processing position to the i-th raw material to be processed, S i represents the area of ​​the i-th raw material to be processed, c i represents the specific attribute value of the i-th raw material to be processed; α, β and γ represent weight coefficients, which are used to balance the influence of distance, size and specific attribute value on priority; x current Indicates the horizontal coordinate of the current processing position, y current Indicates the ordinate of the current processing position, x i Represents the horizontal coordinate of the raw material to be processed, y i The vertical coordinate representing the raw material to be processed; According to the processing priority score of each raw material to be processed, they are arranged in descending order to generate a global processing path.

3. The method for intelligent control of silicon nanodevice processing according to claim 2, characterized in that: The steps of identifying the drawings to be processed, determining the local processing path of each raw material to be processed, and generating an intelligent control path according to the local processing path and the global processing path specifically include: Retrieve the drawings to be processed, identify the lines in the drawings to be processed, and determine the finished shapes of each silicon nanodevice; Perform local path planning according to the finished product shape of the silicon nanodevice and select the optimal path as the local processing path; Retrieve the global processing path, add the local processing path to the global processing path, and obtain the intelligent control path by performing the shortest path calculation.

4. The method for intelligent control of silicon nanodevice processing according to claim 3, characterized in that: In the step of performing local path planning according to the finished product shape of the silicon nanodevice and selecting the optimal path as the local processing path, the optimal path is selected as the local processing path, and the corresponding function expression is: Among them, P′ opt (t) indicates the selection of the optimal path as the local processing path, C(S, P′, t) indicates the cost function, D(P, t) indicates the dynamic programming function, T indicates the total processing time, min P represents the minimum value of all possible local processing paths P′, t represents the processing time, S complexity Indicates the complexity of the finished product shape, P′ length (t) represents the length of the path P′ at the processing time t, V(t) represents the processing speed at the processing time t, A(t) represents the processing accuracy requirement at the processing time t, ω1, ω2, ω3 and ω4 represent the second weight coefficient, P′ j represents the jth path point on the local processing path P′, ε j With φ j Both represent the path point P′ j The related constants, represents the impact rate of processing time on path cost, dist(P′ j , P′ j+1 ) represents the path point P′ j and path point P′ j+1 The distance between them, m represents the total number of path points.

5. The method for intelligent control of silicon nanodevice processing according to claim 4, characterized in that: The steps of collecting images of silicon nanodevices according to the intelligent control path to obtain real-time monitoring images, comparing the real-time monitoring images with finished products, determining whether there are errors in processing, and generating monitoring results specifically include: The silicon nanodevice is imaged according to a preset distance step length to obtain a real-time monitoring image; Performing image processing on the real-time monitoring image, extracting the finished product image of the silicon nanodevice, and comparing the finished product image with the finished product shape in the drawing to be processed to obtain a comparison result; The error ratio of the silicon nanodevice is calculated based on the comparison results. When the error ratio exceeds a preset range, it is determined that there is an error in the current processing process and the processing is suspended.

6. The method for intelligent control of silicon nanodevice processing according to claim 5, characterized in that: In the step of performing image processing on the real-time monitoring image, extracting the finished product image of the silicon nanodevice, and comparing the finished product image with the finished product shape in the drawing to be processed to obtain the comparison result, the comparison is performed by calculating the error value between the finished product image and the finished product shape in the drawing to be processed; The calculation formula of the error value between the finished product image and the finished product shape in the drawing to be processed is expressed as: Among them, E represents the error value between the finished product image and the finished product shape in the drawing to be processed, G and H represent the maximum width and maximum height of the real-time monitoring image respectively, and I gh represents the pixel value of the real-time monitoring image at position (g, h), P gh Represents the pixel value of the finished shape image at position (g, h) in the drawing to be processed, Represents the average pixel value of the real-time monitoring image, represents the average pixel value of the drawing to be processed, g and h represent the width and height of the real-time monitoring image respectively, and N represents the total number of pixels contained in the image of the silicon nanodevice in the real-time monitoring image.

7. The method for intelligent control of silicon nanodevice processing according to claim 6, characterized in that: When the error ratio is within a preset range, path correction data is generated, and the error of the intelligent control path is eliminated according to the path correction data.

8. An intelligent control system for processing silicon nanodevices, characterized in that: The method for intelligent control of silicon nanodevice processing according to any one of claims 1 to 7 is applied, wherein the system comprises: The drawing acquisition module is used to obtain the drawings to be processed and fix the raw materials to be processed on the fixture; A global path planning module is used to collect images of the raw materials to be processed, locate the raw materials to be processed, and generate a global processing path; The control path generation module is used to identify the processing drawings to be processed, determine the local processing path of each raw material to be processed, and generate an intelligent control path based on the local processing path and the global processing path; The finished product monitoring module is used to collect images of silicon nanodevices according to the intelligent control path, obtain real-time monitoring images, compare the real-time monitoring images with finished products, determine whether there are errors in processing, and generate monitoring results.

9. The intelligent control system for silicon nanodevice processing according to claim 8, characterized in that: The global path planning module includes: A raw material image acquisition unit, used to acquire images of the raw materials to be processed to obtain raw material monitoring images; A raw material identification unit is used to pre-process the raw material monitoring image and convert it into a line graph, and identify the position of the raw material to be processed by identifying the line graph; The raw material positioning unit is used to construct a two-dimensional coordinate system according to the positions of each raw material to be processed, determine the two-dimensional coordinates of the raw material, and thus generate a global processing path.

10. The intelligent control system for processing silicon nanodevices according to claim 9, characterized in that: The control path generation module comprises: A finished product identification unit for drawing is used to retrieve the drawing to be processed, identify the lines in the drawing to be processed, and determine the finished product shape of each silicon nanodevice; A local path planning unit, used for performing local path planning according to the finished product shape of the silicon nanodevice, and selecting an optimal path as a local processing path; The path synthesis unit is used to call the global processing path, add the local processing path to the global processing path, and obtain the intelligent control path by performing the shortest path calculation; The finished product monitoring module comprises: A monitoring image acquisition unit is used to acquire images of the silicon nanodevice according to a preset distance step length to obtain a real-time monitoring image; A data comparison unit is used to perform image processing on the real-time monitoring image, extract the finished product image of the silicon nanodevice, compare the finished product image with the finished product shape in the drawing to be processed, and obtain a comparison result; The error determination unit is used to calculate the error ratio of the silicon nanodevice according to the comparison result. When the error ratio exceeds a preset range, it is determined that there is an error in the current processing process and the processing is suspended.