Cutter life cycle intelligent management method and system based on machine learning

Through the intelligent tool life cycle management method based on machine learning, the problems of confusion in quartz processing tool management and inaccurate life calculation are solved, efficient tool management and life extension are achieved, production efficiency is improved and costs are reduced.

CN118917831APending Publication Date: 2024-11-08SHANGHAI QIANGHUA IND CO LTD
View PDF 0 Cites 4 Cited by

Patent Information

Application Number
CN202410963496.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

Quartz machining tools lack a unified data management platform, resulting in confusion in tool management, inaccurate service life calculation, and low tool management efficiency, common problems such as retention and difficulty in finding spare tools.

Method used

Using machine learning-based intelligent tool life cycle management method, we use tool databases, collect initial status and usage information, establish a neural network model for wear feature extraction and life evaluation, update tool life sequence in real time, and dynamically formulate purchase and repair plans.

Benefits of technology

It realizes timely distribution and recycling of tools, avoids production line shutdown, extends tool service life, reduces replacement frequency and production costs, and improves management efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917831A_ABST
    Figure CN118917831A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of intelligent cutter management, in particular to an intelligent cutter life cycle management method and system based on machine learning, and the method specifically comprises the steps: building a quartz machining cutter database; recycling and recording cutter use and circulation information of the quartz machining cutter after the factory finishes operation every day; a machine learning model is established, and the intraday abrasion loss and intraday tool use influence coefficient of the tool are evaluated and calculated; evaluating the remaining service lives of the quartz processing cutters with different abnormal grades; the remaining service life data of the quartz machining tools of the same machining category are arranged in order to form a tool service life sequence, and the tool service life sequence is updated to the quartz machining tool database in real time; dynamically making a factory tool purchase and maintenance plan; the problems that in the prior art, quartz machining tools lack a unified data management platform, tool management on a production site is disordered, and service life calculation of each tool is inaccurate are solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of tool intelligent management, and is a tool life cycle intelligent management method and system based on machine learning. Background Art

[0002] Quartz processing tools are usually diamond tools, mainly diamond grinding heads or diamond grinding wheels. When processing quartz devices, it is necessary to select suitable diamond tools according to processing needs and install the tools on the processing equipment, adjust processing parameters such as rotation speed, feed speed, etc., to process quartz. At the same time, during the processing, it is necessary to control processing parameters and tool pressure to ensure cutting effect and processing quality. In the existing technology, there is a lack of a unified data management platform for tool parameters, the selection rate of tool by process personnel is low, the use data of tools is not related to the processing and production process, and the tool management department cannot objectively evaluate the service life of the tools supplied by suppliers; at the same time, at the production site, it is common to use tools arbitrarily, and there is a problem in tool management that a large number of tools are retained and it is difficult to find tools when they need to be prepared. How to improve the management and maintenance efficiency of tools is an important problem faced by quartz processing factories.

[0003] In the existing disclosed invention technology, for example, a Chinese patent with publication number CN115421455A discloses a photomask production management system, a supply chain management method and an electronic device, including: a feed management unit, which compares the quartz substrate parameter information with the substrate standard value to obtain a first detection result; a mask base plate management unit, including a film detection module corresponding to each layer of film, the film detection module is used to obtain the film parameter information, and compare the film parameter information with the film standard parameter value to obtain a second detection result; a photomask management unit, which is used to obtain the etching process parameters, and compare the etching process parameters with the etching process standard value to obtain a third detection result; a decision unit, which decides whether to shut down for maintenance based on the first detection result, the second detection result and the third detection result.

[0004] The above patent relies on the operator to input parameter information and make comparisons. If the operator makes mistakes or negligence, inaccurate test results may occur. Summary of the invention

[0005] The technical problem to be solved by the present invention is that in the prior art, quartz machining tools lack a unified data management platform, tool management at the production site is chaotic, and the calculation of the life of each tool is inaccurate. A tool life cycle intelligent management method and system based on machine learning is proposed.

[0006] In order to achieve the above object, the present invention discloses a tool life cycle intelligent management method based on machine learning, comprising the following steps:

[0007] S1: Classify the tools according to the information of quartz processing tools purchased by the factory in the past and establish a quartz processing tool database;

[0008] Specifically, S1 also includes the collection of the initial state of the quartz machining tool that is entered into the database for the first time. The collection of the initial state of the tool includes: the parameter information, specification, model, manufacturer, initial high-resolution image data of the tool surface, and the factory wear amount R0 obtained by comparing the initial high-resolution image of the tool surface with the factory surface image of the tool;

[0009] S2: Before the factory starts working every day, the quartz processing tools needed for pre-processing quartz devices on that day are distributed and issued, and after the factory finishes working every day, the tool usage and circulation information of the quartz processing tools are collected and recorded;

[0010] Specifically, in S2, the tool usage and circulation information of the quartz processing tool includes: the tool usage environment temperature, environment humidity, number of processed quartz devices and cumulative processing usage time on that day, and high-resolution image data of the tool surface on that day.

[0011] S3: Establish a machine learning model to extract the features of abnormal tool wear based on tool usage and circulation information, evaluate and calculate the daily wear amount of the tool and the tool usage impact coefficient of the day, and perform abnormal recycling classification and marking processing on the quartz processing tools recycled daily;

[0012] Specifically, S3 includes the following specific steps:

[0013] S311: Establish a machine learning model, wherein the neural network of the machine learning model includes: an input layer, 4 convolutional layers, 4 sampling layers, a fully connected layer, and an output layer, wherein each convolutional layer includes 10 convolution kernels of size 8×8;

[0014] S312: performing edge detection and mean filtering denoising preprocessing on the high-resolution image data of the tool surface on the day obtained in S2;

[0015] S313: Grayscale the high-resolution image of the tool surface on the day after preprocessing, and input the grayscale high-resolution image of the tool surface on the day into the machine learning model to perform grayscale threshold segmentation processing on the defect area. The formula for grayscale threshold segmentation processing in the convolution layer is:

[0016] g i,n (x n ,y n )∈[g i-1 , g i ], i∈{1, 2...4};

[0017] Among them, gi,n (x n ,y n ) is the nth coordinate on the edge line of the i-th target area (x n ,y n )’s pixel gradient value;

[0018] g i is the maximum value of the gradient values ​​of all pixels in the i-th target area;

[0019] g i-1 is the maximum value of the gradient values ​​of all pixels in the i-1th target area;

[0020] x n is the horizontal coordinate of the nth pixel point in the two-dimensional plane coordinate system of the high-resolution image of the tool surface on that day;

[0021] y n is the ordinate of the nth pixel point in the two-dimensional plane coordinate system of the high-resolution image of the tool surface on that day;

[0022] [g i-1 , g i ] is the gradient value threshold interval of the pixel point in the i-th target area; n is a subscript, indicating the number of the pixel point; i is a subscript, indicating the number of the target area; the target area division standard is: when the gradient value of a certain pixel point in the high-resolution image of the tool surface on the same day belongs to the threshold interval, the pixel point belongs to the i-th target area;

[0023] S314: Separate the tool environment background and the tool abnormal wear area, perform regional identification and manual annotation of the abnormal wear area on the high-resolution image of the tool surface on the day, extract feature information of the abnormal wear area, and evaluate and calculate the tool wear amount on the day.

[0024] Specifically, in S314, the evaluation strategy of the wear amount of the tool on the day is as follows:

[0025]

[0026] Among them, M is the total number of abnormal tool wear areas; m is a subscript, indicating the mth abnormal tool wear area; m≤M;

[0027] R x The subscript x indicates that the cumulative usage time of the tool after it is purchased and brought into the quartz processing factory is x days; R x Indicates the wear amount of the tool on the xth cumulative use day;

[0028] H m is the total number of pixels in the mth abnormal wear area;

[0029] is the pixel mean of all pixels in the m tool abnormal wear areas.

[0030] Specifically, in S3, the calculation strategy of the tool usage influence coefficient of the day is as follows:

[0031] S321: Collecting characteristic information of abnormal wear areas of the tool and obtaining a curve of the change of the wear amount of the tool on the day and the wear factor variable data during the use of the tool on the day; the wear factor variables include: cutting speed and cutting pressure;

[0032] S322: setting the use processes of multiple tools whose size similarity of quartz devices cut by the tools is greater than 95% as a control group, extracting the change curve of the wear amount of each abnormal wear area of ​​the tool in the control group with the wear factor variable, and performing curve separation processing on the change curve according to the wear factor variable level;

[0033] S323: Calculate the tool usage influence coefficients for the day corresponding to different wear factor variables respectively.

[0034] When the wear factor variable is cutting speed, the calculation strategy is as follows:

[0035] Extract the abnormal wear curve of the tool with the cutting speed when the cutting pressure is the same in the control group. There are G curves in total. Synchronously extract the cutting speed data set {v1, v2…v g …v G The tool wear data set of the day in the feature information of the tool abnormal wear area {b 1 , b 2 ...b g ...b G}, where v g is the cutting speed in the g-th variation curve; b g is the tool wear amount on the g-th change curve on that day; g∈{1, 2, ..., G};

[0036] Calculate the tool usage influence coefficient S1 for the day when the wear factor variable is the cutting speed:

[0037]

[0038] in, is the mean value of cutting speed in G variation curves; is the average value of tool wear on the day in G change curves;

[0039] When the wear factor variable is cutting pressure, the specific calculation strategy is as follows:

[0040] Extract the change curves with the same cutting speed in the control group, there are J change curves in total, and simultaneously extract the cutting pressure data set {p1, p2…pj…pJ} and the tool wear data set {c 1 , c 2 ...c j ...c J}, where p j is the cutting pressure in the jth variation curve; c j is the tool wear amount on the jth change curve on that day; j∈{1, 2, ..., J};

[0041] Calculate the tool usage influence coefficient S2 for the day when the wear factor variable is cutting pressure:

[0042]

[0043] in, is the mean value of cutting speed in J variation curves; is the average value of tool wear on the day in J change curves.

[0044] S4: Evaluate the remaining service life of quartz machining tools with different abnormality levels;

[0045] Specifically, in S4, the evaluation of the remaining service life of quartz machining tools of different abnormality levels includes:

[0046] S41: extracting the cutting speed and cutting pressure data required for the quartz device to be processed during the processing on the next working day of the quartz processing factory;

[0047] S42: predict and calculate the predicted wear amount of the tool in the next working day;

[0048]

[0049] Among them, R0 is the factory wear of the tool;

[0050] R x+1 Predicted tool wear in the next working day;

[0051] v x+1 The cutting speed during the use of the tool in the next working day;

[0052] p x+1 The cutting pressure during the use of the tool in the next working day;

[0053] S43: Evaluate the remaining useful life of quartz machining tools with different abnormality levels;

[0054] On the x+1 working day, the remaining service life of the quartz machining tool is T x+1 for:

[0055]

[0056] S5: arranging the remaining service life data of the quartz machining tools of the same machining category in order to form a tool life sequence, and updating the tool life sequence to the quartz machining tool database in real time;

[0057] Specifically, S51: arranging the remaining service life data of quartz machining tools of the same machining category in order to form a tool life sequence, and updating the tool life sequence to a quartz machining tool database in real time;

[0058] S52: providing a distribution suggestion for subsequent quartz machining tool distribution and use processing according to the tool life sequence, wherein the distribution suggestion includes: giving priority to using the quartz machining tool with the longest remaining service life among the quartz machining tools of the same machining category;

[0059] S6: Statistically analyze the remaining service life of all quartz machining tools in the factory and dynamically formulate the factory's tool purchase and maintenance plan.

[0060] Specifically, in S6, the factory tool purchase and maintenance plan includes:

[0061] When T x+1 ≥T w When the tool is worn, contact the tool manufacturer and have the tool maintained and serviced in advance according to the type of abnormal wear area;

[0062] when When the tool is needed, the tool management department will look up the tool inventory and supplier information corresponding to the tool to confirm whether the tool of this model needs to be replaced or purchased;

[0063] Among them, T w and T c is the maintenance threshold and replacement threshold corresponding to the abnormal wear area of ​​the tool, T x The remaining service life of the quartz machining tool on the xth working day.

[0064] In addition, the present invention discloses a tool life cycle intelligent management system based on machine learning, the system is implemented based on the tool life cycle intelligent management method based on machine learning, and includes the following modules:

[0065] Tool initial information collection module, tool usage flow information recording module, wear characteristic analysis module, remaining service life assessment module, life sequence update module, purchase and maintenance plan output module;

[0066] The tool initial information collection module classifies tools according to the information of quartz processing tools purchased historically by the factory, and establishes a quartz processing tool database;

[0067] The tool usage circulation information recording module is used to distribute and collect the quartz processing tools needed for pre-processing quartz devices on the day before the factory starts working every day, and to collect and record the tool usage and circulation information of the quartz processing tools after the factory finishes working every day;

[0068] The wear feature analysis module is used to establish a machine learning model, extract features of abnormal tool wear based on tool usage and circulation information, evaluate and calculate the daily wear amount of the tool and the tool usage impact coefficient of the day, and perform abnormal recycling classification and marking processing on the quartz processing tools recycled daily;

[0069] The remaining service life evaluation module is used to evaluate the remaining service life of quartz machining tools of different abnormal levels;

[0070] The life sequence updating module arranges the remaining service life data of quartz machining tools of the same machining category in order to form a tool life sequence, and updates the tool life sequence to the quartz machining tool database in real time;

[0071] The purchase and maintenance plan output module is used to statistically analyze the remaining service life of all types of quartz processing tools in the factory and dynamically formulate the factory tool purchase and maintenance plan.

[0072] The present invention also discloses a storage medium, in which instructions are stored. When a computer reads the instructions, the computer executes the tool life cycle intelligent management method based on machine learning.

[0073] The present invention also discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned intelligent tool life cycle management method based on machine learning is implemented.

[0074] Compared with the prior art, the technical effects of the present invention are as follows:

[0075] 1. The present invention can distribute and recycle the quartz processing tools in time through the management and monitoring of the tools, thus avoiding the shutdown of the production line due to insufficient or damaged tools, thereby improving the production efficiency.

[0076] 2. The present invention evaluates abnormal tool wear through a machine learning model, which can detect and handle abnormal conditions, extend the service life of the tool, reduce the frequency of tool replacement, and reduce production costs.

[0077] 3. The present invention records and updates the use of cutting tools in real time to a database, so that the cutting tool conditions can be viewed and analyzed at any time, helping managers to formulate cutting tool purchase and maintenance plans in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0079] in:

[0080] Figure 1 A schematic diagram of a process flow of a tool life cycle intelligent management method based on machine learning of the present invention;

[0081] Figure 2 It is a structural schematic diagram of a tool life cycle intelligent management system based on machine learning according to the present invention. DETAILED DESCRIPTION

[0082] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0083] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0084] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0085] Embodiment 1

[0086] like Figure 1 As shown, a tool life cycle intelligent management method based on machine learning in an embodiment of the present invention includes the following specific steps:

[0087] S1: Classify the tools according to the information of quartz processing tools purchased by the factory in the past and establish a quartz processing tool database.

[0088] S1 also includes the collection of the initial state of the quartz machining tools that are entered into the database for the first time, including: tool parameter information, specifications, models, manufacturers, initial high-resolution image data of the tool surface, and factory wear R0 obtained by comparing the initial high-resolution image of the tool surface with the factory surface image of the tool.

[0089] S2: Before the factory starts working every day, the quartz processing tools needed for pre-processing quartz devices on that day are distributed and issued, and after the factory finishes working every day, the tool usage and circulation information of the quartz processing tools are collected and recorded.

[0090] In S2, the tool usage and circulation information of the quartz processing tool includes: the tool usage environment temperature, environment humidity, number of processed quartz devices and cumulative processing usage time on that day and high-resolution image data of the tool surface on that day.

[0091] S3: Establish a machine learning model to extract features of abnormal tool wear based on tool usage and circulation information, evaluate and calculate the tool wear amount and tool usage impact coefficient of the day, and perform recycling abnormality classification and marking on the quartz processing tools recycled daily.

[0092] S311: Establish a machine learning model, the neural network of which includes: an input layer, 4 convolutional layers, 4 sampling layers, a fully connected layer and an output layer, wherein each convolutional layer contains 10 convolution kernels of size 8×8.

[0093] S312: Perform edge detection and mean filtering denoising preprocessing on the high-resolution image data of the tool surface obtained in S2 on the same day.

[0094] S313: Grayscale the high-resolution image of the tool surface on the day after preprocessing, and input the grayscale high-resolution image of the tool surface on the day into the machine learning model to perform grayscale threshold segmentation processing on the defect area. The formula for grayscale threshold segmentation processing in the convolution layer is:

[0095] g i,n (x n ,y n )∈[g i-1 , g i ], i∈{1, 2...4};

[0096] Among them, g i,n (x n ,y n ) is the nth coordinate on the edge line of the i-th target area (x n ,y n ) is the gradient value of the pixel point.

[0097] g iis the maximum value of the gradient values ​​of all pixels in the i-th target area.

[0098] g i-1 is the maximum value of the gradient values ​​of all pixels in the i-1th target area.

[0099] x n It is the horizontal coordinate of the nth pixel point in the two-dimensional plane coordinate system of the high-resolution image of the tool surface on that day.

[0100] y b It is the ordinate of the nth pixel point in the two-dimensional plane coordinate system of the high-resolution image of the tool surface on that day.

[0101] [g i-1 , g i ] is the gradient value threshold interval of the pixel point in the i-th target area; n is the subscript, indicating the number of the pixel point; i is the subscript, indicating the number of the target area; the target area division standard is: when the gradient value of a pixel point in the high-resolution image of the tool surface on the same day belongs to the threshold interval, then the pixel point belongs to the i-th target area.

[0102] S314: Separate the tool environment background and the tool abnormal wear area, perform regional identification and manual annotation of the abnormal wear area on the high-resolution image of the tool surface on the day, extract feature information of the abnormal wear area, and evaluate and calculate the tool wear amount on the day.

[0103] In S314, the evaluation strategy of the tool wear amount on the day is specifically as follows:

[0104]

[0105] Among them, M is the total number of abnormal tool wear areas; m is a subscript, indicating the mth abnormal tool wear area; m≤M;

[0106] R x The subscript x indicates that the cumulative usage time of the tool after it is purchased and brought into the quartz processing factory is x days; R x Indicates the wear amount of the tool on the xth cumulative use day;

[0107] H m is the total number of pixels in the mth abnormal wear area;

[0108] is the pixel mean of all pixels in the m tool abnormal wear areas.

[0109] is the pixel mean of all pixels in the abnormal wear area of ​​the tool.

[0110] In S3, the calculation strategy of the tool usage influence coefficient of the day is as follows:

[0111] S321: Collect characteristic information of abnormal wear areas of the tool and obtain a curve of the change of the tool wear amount on that day and wear factor variable data during the tool use process on that day; the wear factor variables include: cutting speed and cutting pressure.

[0112] S322: multiple tool usage processes whose size similarity of quartz devices cut by the tools is greater than 95% are set as a control group, and the change curves of the daily wear amount of each abnormal wear area of ​​the tool in the control group as a function of the wear factor variable are extracted, and the change curves are subjected to curve separation processing according to the wear factor variable level.

[0113] S323: Calculate the tool usage influence coefficients for the day corresponding to different wear factor variables respectively.

[0114] When the wear factor variable is cutting speed, the calculation strategy is as follows:

[0115] Extract the abnormal wear curve of the tool with the cutting speed when the cutting pressure is the same in the control group. There are G curves in total. Synchronously extract the cutting speed data set {v1, v2...v g ...v G The tool wear data set of the day in the feature information of the tool abnormal wear area {b 1 , b 2 ...b g ...b G}, where v g is the cutting speed in the g-th variation curve; b g is the tool wear amount on the gth change curve on that day; g∈{1, 2, ..., G}.

[0116] Calculate the tool usage influence coefficient S1 for the day when the wear factor variable is the cutting speed:

[0117]

[0118] in, is the mean value of cutting speed in G variation curves; is the average value of tool wear in G change curves on that day.

[0119] When the wear factor variable is cutting pressure, the specific calculation strategy is as follows:

[0120] Extract the change curves with the same cutting speed in the control group, there are J change curves in total, and extract the cutting pressure data set {p1, p2...p j ...p JThe tool wear data set of the day {c 1 , c 2 ...c j ...c J}, where p j is the cutting pressure in the jth variation curve; c j is the tool wear amount on the jth change curve on that day; j∈{1, 2, ..., J}.

[0121] Calculate the tool usage influence coefficient S2 for the day when the wear factor variable is cutting pressure:

[0122]

[0123] in, is the mean value of cutting speed in J variation curves; is the average value of tool wear on the day in J change curves.

[0124] S4: Evaluate the remaining service life of quartz machining tools with different abnormality levels.

[0125] In S4, the evaluation of the remaining service life of quartz machining tools of different abnormality levels includes:

[0126] S41: extracting the cutting speed and cutting pressure data required for the quartz device to be processed during the processing on the next working day of the quartz processing factory.

[0127] S42: Predict and calculate the predicted wear amount of the tool in the next working day.

[0128]

[0129] Among them, R0 is the factory wear of the tool.

[0130] R x+1 The predicted wear of the tool in the next working day.

[0131] v x+1 It is the cutting speed during the use of the tool in the next working day.

[0132] p x+1 It is the cutting pressure during the use of the tool in the next working day.

[0133] S43: Evaluate the remaining useful life of quartz machining tools with different abnormality levels.

[0134] On the x+1 working day, the remaining service life of the quartz machining tool is T x+1 for:

[0135]

[0136] S5: The remaining service life data of the quartz machining tools of the same machining category are arranged in order to form a tool life sequence, and the tool life sequence is updated to the quartz machining tool database in real time.

[0137] Exemplarily, in this embodiment, the processing categories of quartz processing tools include: cutting tools, grinding tools and polishing tools for different quartz device sizes and different quartz device surface hardnesses.

[0138] S5 includes the following specific steps:

[0139] S51: Arrange the remaining service life data of the quartz machining tools of the same machining category in order to form a tool life sequence, and update the tool life sequence to the quartz machining tool database in real time.

[0140] S52: providing distribution and collection suggestions for subsequent quartz machining tool distribution and collection processing according to the quartz machining tool database and the tool life sequence, wherein the distribution and collection suggestions include: giving priority to the collection of quartz machining tools with the longest remaining service life among quartz machining tools of the same machining category.

[0141] S6: Statistically analyze the remaining service life of all quartz machining tools in the factory and dynamically formulate the factory's tool purchase and maintenance plan.

[0142] In S6, the factory tool purchase and maintenance plan includes:

[0143] When T x+1 ≥T w When the tool is worn, contact the tool manufacturer and have the tool maintained and serviced in advance according to the type of abnormal wear area.

[0144] when When the tool is needed, the tool management department will look up the tool inventory and supplier information corresponding to the tool to confirm whether the tool of this model needs to be replaced or purchased.

[0145] Among them, T w and T c is the maintenance threshold and replacement threshold corresponding to the abnormal wear area of ​​the tool, T x The remaining service life of the quartz machining tool on the xth working day.

[0146] Embodiment 2

[0147] like Figure 2 As shown, an intelligent management system for tool lifecycle based on machine learning according to an embodiment of the present invention is implemented based on the intelligent management method for tool lifecycle based on machine learning, and includes the following modules:

[0148] Tool initial information collection module, tool usage flow information recording module, wear characteristic analysis module, remaining service life assessment module, life sequence update module, purchase and maintenance plan output module.

[0149] The tool initial information collection module classifies tools according to the information of quartz processing tools purchased historically by the factory, establishes a quartz processing tool database, and collects tool initial status for quartz processing tools entered into the database for the first time.

[0150] The tool usage circulation information recording module is used to distribute and collect the quartz processing tools needed for pre-processing quartz devices on the day before the factory starts work every day, and to collect and record the tool usage and circulation information of the quartz processing tools after the factory finishes work every day.

[0151] The wear feature analysis module is used to establish a machine learning model, extract features of abnormal tool wear based on tool usage and circulation information, evaluate and calculate the daily wear amount of the tool and the daily tool usage impact coefficient, and perform recycling abnormality classification and marking processing on the quartz processing tools recycled daily.

[0152] The remaining service life evaluation module is used to evaluate the remaining service life of quartz machining tools of different abnormal levels.

[0153] The life sequence updating module arranges the remaining service life data of quartz machining tools of the same machining category in order to form a tool life sequence, and updates the tool life sequence to the quartz machining tool database in real time.

[0154] The purchase and maintenance plan output module is used to statistically analyze the remaining service life of all types of quartz processing tools in the factory and dynamically formulate the factory tool purchase and maintenance plan.

[0155] Embodiment 3

[0156] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0157] The processor executes the above-mentioned intelligent tool life cycle management method based on machine learning by calling the computer program stored in the memory.

[0158] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement a tool life cycle intelligent management method based on machine learning provided by the above method embodiment. The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data. This embodiment will not be described in detail here.

[0159] Embodiment 4

[0160] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0161] When the computer program runs on a computer device, the computer device executes the above-mentioned intelligent tool life cycle management method based on machine learning.

[0162] For example, the computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0163] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0164] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0165] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0166] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0167] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0168] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0169] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0170] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0171] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0172] In summary, compared with the prior art, the technical effects of the present invention are as follows:

[0173] 1. The present invention can distribute and recycle the quartz processing tools in time through the management and monitoring of the tools, thus avoiding the shutdown of the production line due to insufficient or damaged tools, thereby improving the production efficiency.

[0174] 2. The present invention evaluates abnormal tool wear through a machine learning model, which can detect and handle abnormal conditions, extend the service life of the tool, reduce the frequency of tool replacement, and reduce production costs.

[0175] 3. The present invention records and updates the use of cutting tools in real time to a database, so that the cutting tool conditions can be viewed and analyzed at any time, helping managers to formulate cutting tool purchase and maintenance plans in a timely manner.

[0176] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. An intelligent tool life cycle management method based on machine learning, Features: The method comprises the following steps: S1: Classify the tools according to the information of quartz processing tools purchased by the factory in the past and establish a quartz processing tool database; S2: Before the factory starts working every day, the quartz processing tools needed for pre-processing quartz devices on that day are distributed and issued, and after the factory finishes working every day, the tool usage and circulation information of the quartz processing tools are collected and recorded; S3: Establish a machine learning model to extract the features of abnormal tool wear based on tool usage and circulation information, evaluate and calculate the daily wear amount of the tool and the tool usage impact coefficient of the day, and perform abnormal recycling classification and marking processing on the quartz processing tools recycled daily; S4: Evaluate the remaining service life of quartz machining tools with different abnormality levels; S5: arranging the remaining service life data of the quartz machining tools of the same machining category in order to form a tool life sequence, and updating the tool life sequence to the quartz machining tool database in real time; S6: Statistically analyze the remaining service life of all quartz machining tools in the factory and dynamically formulate the factory's tool purchase and maintenance plan.

2. According to the method for intelligent management of tool life cycle based on machine learning in claim 1, It is characterized in that The S1 also includes: collecting the initial state of the quartz machining tool that is entered into the database for the first time; the initial state of the tool collection includes: collecting the parameter information, specifications, model, manufacturer, initial high-resolution image data of the tool surface, and the factory wear amount R obtained by comparing and evaluating the initial high-resolution image of the tool surface with the factory surface image of the tool. 0 ; In S2, the tool usage and circulation information of the quartz processing tool includes: the tool usage environment temperature, environment humidity, number of processed quartz devices, cumulative processing usage time on the day, and high-resolution image data of the tool surface on the day.

3. According to the method for intelligent management of tool life cycle based on machine learning in claim 2, It is characterized in that S3 includes the following specific steps: S311: Establish a machine learning model, wherein the neural network of the machine learning model includes: an input layer, 4 convolutional layers, 4 sampling layers, a fully connected layer, and an output layer, wherein each convolutional layer includes 10 convolution kernels of size 8×8; S312: performing edge detection and mean filtering denoising preprocessing on the high-resolution image data of the tool surface on the day obtained in S2; S313: Grayscale the high-resolution image of the tool surface on the day after preprocessing, and input the grayscale high-resolution image of the tool surface on the day into the machine learning model to perform grayscale threshold segmentation processing on the defect area. The formula for grayscale threshold segmentation processing in the convolution layer is: g i,n (x n ,y n )∈[g i-1 ,g i ],i∈{1,2…4}; Among them, g i,n (x n ,y n ) is the nth coordinate on the edge line of the i-th target area (x n ,y n )’s pixel gradient value; g i is the maximum value of the gradient values ​​of all pixels in the i-th target area; g i-1 is the maximum value of the gradient values ​​of all pixels in the i-1th target area; x n is the horizontal coordinate of the nth pixel point in the two-dimensional plane coordinate system of the high-resolution image of the tool surface on that day; y n is the ordinate of the nth pixel point in the two-dimensional plane coordinate system of the high-resolution image of the tool surface on that day; [g i-1 , g i ] is the gradient value threshold interval of the pixel point in the i-th target area; n is a subscript, indicating the number of the pixel point; i is a subscript, indicating the number of the target area; the target area division standard is: when the gradient value of a certain pixel point in the high-resolution image of the tool surface on the same day belongs to the threshold interval, the pixel point belongs to the i-th target area; S314: Separate the tool environment background and the tool abnormal wear area, perform regional identification and manual annotation of the abnormal wear area on the high-resolution image of the tool surface on the day, extract feature information of the abnormal wear area, and evaluate and calculate the tool wear amount on the day.

4. According to the method for intelligent management of tool life cycle based on machine learning in claim 3, It is characterized in that In S314, the evaluation strategy of the tool wear amount on the day is specifically as follows: Wherein, M is the total number of abnormal tool wear areas; m is a subscript, indicating the mth abnormal tool wear area; m≤M; R x The subscript x indicates that the cumulative usage time of the tool after it is purchased and brought into the quartz processing factory is x days; R x Indicates the wear amount of the tool on the xth cumulative use day; H m is the total number of pixels in the mth abnormal wear area; is the pixel mean of all pixels in the m tool abnormal wear areas.

5. According to the method for intelligent management of tool life cycle based on machine learning according to claim 4, It is characterized in that In S3, the calculation strategy of the tool usage influence coefficient of the day is as follows: S321: Collecting characteristic information of abnormal wear areas of the tool and obtaining a curve of the change of the wear amount of the tool on the day and the wear factor variable data during the use of the tool on the day; the wear factor variables include: cutting speed and cutting pressure; S322: setting the use processes of multiple tools whose size similarity of quartz devices cut by the tools is greater than 95% as a control group, extracting the change curve of the wear amount of each abnormal wear area of ​​the tool in the control group with the wear factor variable, and performing curve separation processing on the change curve according to the wear factor variable level; S323: Calculate the tool usage influence coefficients for the day corresponding to different wear factor variables respectively. When the wear factor variable is cutting speed, the specific calculation strategy is as follows: Extract the abnormal wear curve of the tool with the same cutting pressure in the control group. There are G curves in total. Synchronously extract the cutting speed data set {v 1 , v 2 …v g …v G The tool wear data set of the day in the feature information of the tool abnormal wear area {b 1 , b 2 …b g …b G }, where v g is the cutting speed in the g-th variation curve; b g is the tool wear amount on the g-th change curve on that day; g∈{1, 2, ..., G}; Calculate the tool usage influence coefficient S for the day when the wear factor variable is the cutting speed 1 : in, is the mean value of cutting speed in G variation curves; is the average value of tool wear on the day in G change curves; When the wear factor variable is cutting pressure, the specific calculation strategy is as follows: Extract the change curves with the same cutting speed in the control group, there are J change curves in total, and extract the cutting pressure data set {p 1 , p 2 …p j ...p J The tool wear data set of the day {c 1 , c 2 …c j …c J }, where p j is the cutting pressure in the jth variation curve; c j is the tool wear amount on the jth change curve on that day; j∈{1, 2, ..., J}; Calculate the tool usage influence coefficient S for the day when the wear factor variable is cutting pressure 2 : in, is the mean value of cutting speed in J variation curves; is the average value of tool wear on the day in J change curves.

6. According to the method for intelligent management of tool life cycle based on machine learning according to claim 5, It is characterized in that In S4, the evaluation of the remaining service life of quartz machining tools of different abnormality levels includes: S41: extracting the cutting speed and cutting pressure data required for the quartz device to be processed during the processing on the next working day of the quartz processing factory; S42: predict and calculate the predicted wear amount of the tool in the next working day; Among them, R 0 is the factory wear of the tool; R x+1 Predicted tool wear in the next working day; v x+1 The cutting speed during the use of the tool in the next working day; p x+1 The cutting pressure during the use of the tool in the next working day; S43: Evaluate the remaining useful life of quartz machining tools with different abnormality levels; On the x+1 working day, the remaining service life of the quartz machining tool is T x+1 for:

7. According to claim 6, a tool life cycle intelligent management method based on machine learning, It is characterized in that S5 includes the following specific steps: S51: arranging the remaining service life data of quartz machining tools of the same machining category in order to form a tool life sequence, and updating the tool life sequence to a quartz machining tool database in real time; S52: providing a distribution suggestion for subsequent quartz machining tool distribution and use processing according to the tool life sequence, wherein the distribution suggestion includes: giving priority to using the quartz machining tool with the longest remaining service life among the quartz machining tools of the same machining category; In S6, the factory tool purchase and maintenance plan includes: When T x+1 ≥T w When the tool is worn, contact the tool manufacturer and have the tool maintained and serviced in advance according to the type of abnormal wear area; when When the tool is needed, the tool management department will look up the tool inventory and supplier information corresponding to the tool to confirm whether the tool of this model needs to be replaced or purchased; Among them, T w and T c is the maintenance threshold and replacement threshold corresponding to the abnormal wear area of ​​the tool, T x The remaining service life of the quartz machining tool on the xth working day.

8. A tool lifecycle intelligent management system based on machine learning, which is implemented based on a tool lifecycle intelligent management method based on machine learning as claimed in any one of claims 1 to 7, It is characterized in that The system includes the following modules: Tool initial information collection module, tool usage flow information recording module, wear characteristic analysis module, remaining service life assessment module, life sequence update module, purchase and maintenance plan output module; The tool initial information collection module is used to classify tools according to the information of quartz processing tools purchased historically by the factory, and establish a quartz processing tool database; The tool usage circulation information recording module is used to distribute and collect the quartz processing tools needed for pre-processing quartz devices on the day before the factory starts working every day, and to collect and record the tool usage and circulation information of the quartz processing tools after the factory finishes working every day; The wear feature analysis module is used to establish a machine learning model, extract features of abnormal tool wear based on tool usage and circulation information, evaluate and calculate the daily wear amount of the tool and the tool usage impact coefficient of the day, and perform abnormal recycling classification and marking processing on the quartz processing tools recycled daily; The remaining service life evaluation module is used to evaluate the remaining service life of quartz machining tools of different abnormal levels; The life sequence updating module arranges the remaining service life data of quartz machining tools of the same machining category in order to form a tool life sequence, and updates the tool life sequence to the quartz machining tool database in real time; The purchase and maintenance plan output module is used to statistically analyze the remaining service life of all types of quartz processing tools in the factory and dynamically formulate the factory tool purchase and maintenance plan.

9. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, it implements a tool lifecycle intelligent management method based on machine learning as described in any one of claims 1-7.

10. An electronic device, It is characterized in that include: A memory for storing instructions; A processor is used to execute the instructions so that the device implements a tool life cycle intelligent management method based on machine learning as described in any one of claims 1-7.

Citation Information

Cited By

  • Gas holder piston torsion and drift measurement method and system based on image recognition

    CN119146854A

  • Cutter service life evaluation method combined with cutter taking log and intelligent cutter cabinet

    CN120023687A

  • Digital twinning-based tool magazine tool health state dynamic evaluation method and system

    CN120755724A

  • Machine learning-based intelligent cutting tool life cycle management method and system

    WO2026016763A1