Automobile steel quality management method and system

Abstract

The invention relates to an automobile steel quality management method and system. The method comprises the following steps: acquiring a surface detection image of automobile steel; enhancing the surface detection image of the automobile steel to obtain an enhanced surface detection image; marking the surface defects of the automobile steel in the enhanced surface detection image to form a training sample; inputting the marked training sample into a neural network for training to obtain a surface defect detection model; grading the quality of the target automobile steel by using the surface defect detection model; and the production process of the automobile steel is optimized according to the quality grade of the target automobile steel. According to the automobile steel quality grading method, the production process can be optimized in a targeted mode according to the automobile steel quality grading result, so that the defect rate is reduced, the yield is increased, and the overall production efficiency and economic benefits are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile steel quality management, and in particular to an automobile steel quality management method and system. Background Art

[0002] Economic competition in today's world depends largely on the quality of a country's products and services. The level of quality can be said to be a comprehensive reflection of a country's economic, scientific, educational and management levels. Strengthening quality management is not only a national strategy, but also the basis for the survival and development of enterprises. Its importance is irreplaceable. At present, the quality management system of automotive steel often relies on manual inspection and experience judgment, resulting in inconsistent judgment standards and prone to deviations. Summary of the invention

[0003] To solve the above problems, an object of the embodiments of the present invention is to provide a method and system for managing automobile steel quality.

[0004] A method for managing automobile steel quality, comprising:

[0005] Step 1: Obtain the surface inspection image of automobile steel;

[0006] Step 2: enhancing the surface detection image of the automobile steel to obtain an enhanced surface detection image;

[0007] Step 3: marking the surface defects of the automobile steel in the enhanced surface inspection image to form a training sample;

[0008] Step 4: Input the labeled training samples into the neural network for training to obtain a surface defect detection model;

[0009] Step 5: Using the surface defect detection model to grade the quality of the target automotive steel;

[0010] Step 6: Optimize the production process of automotive steel according to the target automotive steel quality grade.

[0011] Preferably, the step 2: enhancing the surface detection image of the automobile steel to obtain an enhanced surface detection image comprises:

[0012] Step 2.1: grayscale the surface detection image of the automobile steel to obtain a grayscale image;

[0013] Step 2.2: Construct pixel classification function of pixels;

[0014] Step 2.3: Construct an enhancement model based on the pixel classification function of the pixel points;

[0015] Step 2.4: Process the grayscale image according to the enhancement model to obtain an enhanced surface detection image.

[0016] Preferably, in step 2.2, the formula is used:

[0017]

[0018] Construct a pixel classification function; where μ dark represents the first pixel classification function, μ birg represents the second pixel grading function, μ gray represents the third pixel binning function, x ij Represents the grayscale value at the (i, j) position.

[0019] Preferably, in step 2.3, weighted average is performed on different pixel classification functions to obtain an enhanced model; wherein the enhanced model is:

[0020]

[0021] Among them, x i ' j Indicates that when the input pixel is x ij When the enhanced pixel value is d represents the first weight, ν b represents the second weight, ν g Represents the third weight.

[0022] The present invention also provides an automobile steel quality management system, comprising:

[0023] A detection image acquisition module is used to acquire a surface detection image of automobile steel;

[0024] An image enhancement module, used for enhancing the surface detection image of the automobile steel to obtain an enhanced surface detection image;

[0025] A labeling module, used for labeling the surface defects of the automobile steel in the enhanced surface inspection image to form a training sample;

[0026] A training module is used to input the labeled training samples into the neural network for training to obtain a surface defect detection model;

[0027] A grading module, used to grade the quality of target automotive steel using the surface defect detection model;

[0028] The process optimization module is used to optimize the production process of automotive steel according to the target automotive steel quality grade.

[0029] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory and the processor are connected via the bus, and wherein the computer program, when executed by the processor, implements the steps in the above-mentioned method for managing automobile steel quality.

[0030] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in the above-mentioned automobile steel quality management method when executed by a processor.

[0031] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0032] The present invention relates to a method and system for managing automobile steel quality. Compared with the prior art, the present invention can optimize the production process in a targeted manner according to the grading results of automobile steel quality, so as to reduce the defect rate and increase the output, thereby improving the overall production efficiency and economic benefits.

[0033] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 This is a flow chart of an automobile steel quality management method in an embodiment provided by the present invention. DETAILED DESCRIPTION

[0036] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0037] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0038] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0039] See also Figure 1 , a method for managing automobile steel quality, comprising:

[0040] Step 1: Obtain the surface inspection image of automobile steel;

[0041] Step 2: enhancing the surface detection image of the automobile steel to obtain an enhanced surface detection image;

[0042] Further, step 2: enhancing the surface detection image of the automobile steel to obtain an enhanced surface detection image, comprising:

[0043] Step 2.1: grayscale the surface detection image of the automobile steel to obtain a grayscale image;

[0044] Step 2.2: Construct pixel classification function of pixels;

[0045] In step 2.2, the formula is used:

[0046]

[0047] Construct a pixel classification function; where μ dark represents the first pixel classification function, μ birg represents the second pixel grading function, μ gray represents the third pixel binning function, x ij Represents the grayscale value at the (i, j) position.

[0048] Step 2.3: Construct an enhancement model based on the pixel classification function of the pixel points;

[0049] In step 2.3, weighted average of different pixel classification functions is performed to obtain an enhanced model; wherein the enhanced model is:

[0050]

[0051] Among them, x i ' j Indicates that when the input pixel is x ij When the enhanced pixel value is d represents the first weight, ν b represents the second weight, ν g Represents the third weight.

[0052] Step 2.4: Process the grayscale image according to the enhancement model to obtain an enhanced surface detection image.

[0053] Step 3: marking the surface defects of the automobile steel in the enhanced surface inspection image to form a training sample;

[0054] Step 4: Input the labeled training samples into the neural network for training to obtain a surface defect detection model;

[0055] Step 5: Using the surface defect detection model to grade the quality of the target automotive steel;

[0056] Step 6: Optimize the production process of automotive steel according to the target automotive steel quality grade.

[0057] Furthermore, in practical applications, the present invention first studies and organizes the relevant theories of IATF16949, which serve as the basic theoretical basis. Based on the needs of the research, the principles and applications of the five major tools of IATF16949 and the interrelationships of the five major tools are studied, and an IATF16949 implementation system with APQP as the main line and the other four tools as auxiliary is obtained. The processes of the product life cycle of general enterprises and the main tasks of the processes are analyzed, and the product processes of general enterprises are distinguished from the product processes that support IATF16949. On this basis, the tasks and inputs and outputs that should be performed at each stage in the product life cycle are clarified. Finally, based on the previous foundation, the needs of the product life cycle management system that supports IATF16949 are analyzed, and the structure of the IATF16949 quality control subsystem is designed.

[0058] APQP is not only a quality plan, but also a product realization process. APQP runs through the entire product life cycle, so APQP is the entry point for integration with the product life cycle process. Through the analysis of APQP stage tasks and data flows, the foundation is laid for integrating IATF16949 quality control methods into the product life cycle management system.

[0059] From the perspective of the product life cycle, the entire APQP process is divided into five stages: planning and determining projects, product design and development, process design and development, product and process confirmation stage and feedback, assessment and corrective action stage. The main content and input and output of each task are analyzed, and the data flow diagram of the stage is given. The document types are classified into design, quality system, audit, customer input and others. This patent takes the product design and development stage as an example to specifically explain the invention content.

[0060] The product design and development phase is the phase in which all product drawings and design documents are completed and prototypes are manufactured. This phase requires the review of product design and related technical information and the initial feasibility analysis of the design to determine potential problems that may occur during manufacturing and assembly. The input to this phase is derived from the output of the first phase. The main tasks and output information of the second phase include:

[0061] 1) Design Failure Mode and Effects Analysis (DFMEA): Perform DFMEA analysis and DFMEA check in accordance with DFMEA requirements, with the inputs being the "Initial List of Product and Process Specificities" and the "Product Reliability and Quality Target Table". The output document carriers are "DFMEA" and "DFMEA Checklist".

[0062] 2) Engineering drawings and engineering specifications. Product designers design engineering drawings and compile engineering specifications based on DFMEA analysis results and samples (or samples) or technical requirements provided by customers. Engineering specifications can be written by product standards, or directly reference national standards, international standards, or standards provided by customers. The output documents are "product engineering drawings" and "product engineering specifications".

[0063] 3) Design for manufacturability and assemblability "Manufacturability" and "Assemblability" emphasize that designers must consider whether the product can be successfully produced, assembled and tested under the company's existing production conditions when designing the product. The product design and development department is responsible for confirming the manufacturability and assembly design of the product. It should be confirmed from the aspects of design, concept, function, etc., such as sensitivity to manufacturing variation, manufacturing assembly process, dimensional tolerance, performance requirements, number of parts, process adjustment and material handling. The input is "Product Initial Process Flow Chart" and "Product Engineering Drawing". The output document carrier is "Product Manufacturability and Assemblability". The above aspects should be verified and confirmed in the document.

[0064] 4) Material specifications: The project team is responsible for confirming the material specifications, and the material specifications are formed after confirmation. Confirm and review the material specifications for the special characteristics of the product involving physical properties, performance, environment, handling and storage requirements. The input documents are "Product Process Speciality List", "Initial Material List" and "Product Initial Process Flow Chart". Output "Material Specifications". Record the confirmation results in the "Material Specification Confirmation Table".

[0065] 5) Product design verification and review. After the initial design is completed, the project team will verify the design's ability to meet the design objectives of new product development, and conduct a formal, comprehensive, and systematic inspection of the design to discover its defects and deficiencies. The main contents of the design verification review include product standard compliance, material and equipment procurement feasibility, processing and manufacturing feasibility, product maintainability, easy inspection, structural rationality, aesthetics, environmental impact, product economy, etc. The review conclusion is made based on the content and results of the review, and after approval, it is issued to the relevant departments to formulate corresponding improvement measures and track and record the measures. Input "DFMEA", "Product Engineering Drawing", "Product Engineering Specification", "Product Reliability and Quality Target Table" and "Material Specification Confirmation Table". The output is "Product Design Review / Verification Record".

[0066] 6) Prototype manufacturing control plan and prototype manufacturing. The prototype manufacturing control plan is a document that controls the dimensional measurement, material and functional testing during the prototype manufacturing process. Input documents include "product engineering drawings", "product initial process flow chart", "DFMEA" and "initial material list". Outputs include "prototype control plan", "prototype control plan checklist", "prototype manufacturing plan" and "prototype confirmation form".

[0067] 7) Changes to drawings and standards When drawings and specifications need to be changed, the product design department shall submit a change application, and the changes shall be made after approval by the project leader. It should be ensured that all changes can be delivered to the relevant departments in a timely manner. Input "Product Design Verification Review Record". The output document is "Design Change Record".

[0068] 8) Equipment, tooling and equipment requirements. According to the initial product process and the initial list of product characteristics, propose the equipment, new equipment and tooling required for project development, prepare procurement, design and manufacturing plans, and ensure that they are in place before the prototype or trial production. The production department is responsible for determining the requirements for new equipment, tooling and facilities, and outputs the "Equipment, Tooling and Facilities List"; the project team fills in the new equipment, tooling and facilities list and checklist, and the project leader is responsible for approval and outputs the "Equipment, Tooling and Facilities Checklist"; for new equipment, tooling and facilities, the project team formulates a development plan and implements procurement or design and production. Output the "Equipment, Tooling and Measuring Tools, Test Equipment Development Plan".

[0069] 9) Special characteristics of products and processes. Based on the initial product and process characteristics list, the project team is responsible for finalizing the special characteristics of products and processes. When the customer has specified, the special characteristics symbols specified by the customer should be used. Special characteristics symbols should be clearly identified in DFMEA, PFMEA, control plan, work instructions including inspection procedures and drawings. The output carrier is the "Special Characteristics List of Products and Processes".

[0070] 10) Requirements for measuring tools / test equipment. The project team determines the requirements for measuring tools / test equipment used for the new product. The quality department proposes the new measuring tools / test equipment required for development, and prepares a procurement plan or development plan for the required measuring tools and test equipment. Input the "List of Special Characteristics of Products and Processes". Output the "List of Measuring Tools and Test Equipment" and the "Checklist of Measuring Tools and Test Equipment".

[0071] 11) Team Feasibility Commitment and Manager Support: The project team reviews the feasibility of the design and ensures that the design can be manufactured, assembled, tested and packaged and delivered in sufficient quantities on schedule at a price acceptable to the customer. The review results are recorded in the "Product Design Information Checklist" and "Team Feasibility Commitment" and manager support is obtained. The output documents are "Product Design Information Checklist", "Team Feasibility Commitment" and "Manager Support".

[0072] The present invention also provides an automobile steel quality management system, comprising:

[0073] A detection image acquisition module is used to acquire a surface detection image of automobile steel;

[0074] An image enhancement module, used for enhancing the surface detection image of the automobile steel to obtain an enhanced surface detection image;

[0075] A labeling module, used for labeling the surface defects of the automobile steel in the enhanced surface inspection image to form a training sample;

[0076] A training module is used to input the labeled training samples into the neural network for training to obtain a surface defect detection model;

[0077] A grading module, used to grade the quality of target automotive steel using the surface defect detection model;

[0078] The process optimization module is used to optimize the production process of automotive steel according to the target automotive steel quality grade.

[0079] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory and the processor are connected via the bus, and is characterized in that when the computer program is executed by the processor, the steps in the above-mentioned method for managing automobile steel quality are implemented. Compared with the prior art, the beneficial effects of the electronic device provided by the present invention are the same as the beneficial effects of the method for managing automobile steel quality described in the above-mentioned technical solution, and are not elaborated herein.

[0080] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the above-mentioned method for managing automobile steel quality are implemented. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present invention are the same as the beneficial effects of the method for managing automobile steel quality described in the above-mentioned technical solution, which will not be elaborated here.

[0081] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technical solution that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for quality management of automobile steel, characterized in that: include: Step 1: Obtain the surface inspection image of automobile steel; Step 2: enhancing the surface detection image of the automobile steel to obtain an enhanced surface detection image; Step 3: marking the surface defects of the automobile steel in the enhanced surface inspection image to form a training sample; Step 4: Input the labeled training samples into the neural network for training to obtain a surface defect detection model; Step 5: Using the surface defect detection model to grade the quality of the target automotive steel; Step 6: Optimize the production process of automotive steel according to the target automotive steel quality grade.

2. The automotive steel quality management method according to claim 1, characterized in that: The step 2: enhancing the surface detection image of the automobile steel to obtain an enhanced surface detection image, comprises: Step 2.1: grayscale the surface detection image of the automobile steel to obtain a grayscale image; Step 2.2: Construct pixel classification function of pixels; Step 2.3: Construct an enhancement model based on the pixel classification function of the pixel points; Step 2.4: Process the grayscale image according to the enhancement model to obtain an enhanced surface detection image.

3. The automobile steel quality management method according to claim 2, characterized in that: In step 2.2, the formula is used: Construct a pixel classification function; where μ dark represents the first pixel classification function, μ birg represents the second pixel classification function, μ gray represents the third pixel classification function, x ij Represents the grayscale value at the position (i, j).

4. The automobile steel quality management method according to claim 3, characterized in that: In step 2.3, weighted average of different pixel classification functions is performed to obtain an enhanced model; wherein the enhanced model is: Among them, x i ' j It means that when the input pixel is x ij When the enhanced pixel value is d represents the first weight, ν b represents the second weight, ν g Represents the third weight.

5. An automobile steel quality management system, characterized in that: include: A detection image acquisition module is used to acquire a surface detection image of automobile steel; An image enhancement module, used for enhancing the surface detection image of the automobile steel to obtain an enhanced surface detection image; A labeling module, used for labeling the surface defects of the automobile steel in the enhanced surface inspection image to form a training sample; A training module is used to input the labeled training samples into the neural network for training to obtain a surface defect detection model; A grading module, used to grade the quality of target automotive steel using the surface defect detection model; The process optimization module is used to optimize the production process of automotive steel according to the target automotive steel quality grade.

6. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps of the automobile steel quality management method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the automobile steel quality management method according to any one of claims 1 to 4 are implemented.

Images