Quality defect optimization method and device for copper strip surface scratches

Abstract

The invention provides a quality defect optimization method and device for copper strip surface scratches, and relates to the field of copper-based new materials. The method comprises the following steps: in response to surface quality detection operation for a target electronic copper strip, acquiring defect analysis data corresponding to the target electronic copper strip through a plurality of pieces of detection equipment; outputting a target quality defect type corresponding to the target electronic copper strip according to the quality defect identification model by inputting defect analysis data; obtaining a target quality defect improvement scheme corresponding to the target quality defect type in a preset scheme analysis database; and optimizing the surface quality of the target electronic copper strip according to the target quality defect improvement scheme. The method solves the problems that due to the fact that various defects on the surface of the rolled copper strip are overlapped, the reason for the quality defect on the surface of the copper strip is difficult to find quickly and accurately, a corresponding optimization method cannot be quickly and effectively drawn up, and the optimization efficiency is low.

Description

Technical Field

[0001] The present application relates to the field of new copper-based materials, and in particular to a method and device for optimizing quality defects of scratches on the surface of a copper strip. Background Art

[0002] Copper-based material copper strip has bright color, good conductivity, and is widely used in electronics, electricity, and electrical appliances.

[0003] After long-term production quality tracking, a large number of statistical analyses were conducted on the parts of the copper strip that are prone to scratches and the equipment that is prone to scratches on the copper strip during the production process. It was found that the rolling process of the finishing mill has a great influence on the surface quality of the copper strip. In addition, due to the superposition of various defects on the surface of the copper strip after rolling, it is difficult to quickly and accurately find the causes of the surface quality defects of the copper strip, and thus it is impossible to quickly and effectively formulate corresponding optimization methods, resulting in low optimization efficiency.

[0004] Therefore, there is an urgent need for a quality defect optimization method and device for copper strip surface scratches. Summary of the invention

[0005] The present application provides a method and device for optimizing the quality defects of scratches on the surface of a copper strip, which solves the problem that it is difficult to quickly and accurately find the causes of the quality defects on the surface of the copper strip due to the superposition of various defects on the surface of the copper strip after rolling, and thus it is impossible to quickly and effectively formulate a corresponding optimization method, resulting in low optimization efficiency.

[0006] In a first aspect of the present application, a quality defect optimization method for surface scratches of a copper strip is provided, the method comprising: in response to a surface quality detection operation for a target electronic copper strip, defect analysis data corresponding to the target electronic copper strip is obtained through a plurality of detection devices, the plurality of detection devices comprising a high-speed proximity switch, an encoder and a tension sensor; by inputting the defect analysis data, a target quality defect type corresponding to the target electronic copper strip is output according to a quality defect recognition model; a target quality defect improvement scheme corresponding to the target quality defect type is obtained from a preset scheme analysis database, the preset scheme analysis database being used to store the correspondence between the target quality defect type and the target quality defect improvement scheme; and the surface quality of the target electronic copper strip is optimized according to the target quality defect improvement scheme.

[0007] Optionally, before responding to the surface quality inspection operation for the target electronic copper tape, the method also includes: dividing the surface of the target electronic copper tape into regions, the region division being used to divide the target electronic copper tape into a plurality of regions to be inspected according to preset division rules; obtaining a plurality of susceptibility levels corresponding to the plurality of regions to be inspected, one susceptibility level corresponding to one region to be inspected; sorting the plurality of susceptibility levels from large to small according to numerical values, confirming the susceptibility level with the largest numerical value among the plurality of susceptibility levels according to the sorting result, and obtaining a high-risk damage level; and performing a surface quality inspection operation on the region to be inspected corresponding to the high-risk damage level.

[0008] Optionally, before outputting the target quality defect type corresponding to the target electronic copper strip according to the quality defect recognition model by inputting defect analysis data, it is necessary to construct a quality defect recognition model, specifically including: obtaining historical defect analysis data, the historical defect analysis data including surface scratch distribution data, roller equipment operating status data and oil squeeze roller rotation pulse signal data; obtaining historical defect features corresponding to the historical defect analysis data through preprocessing operations, and constructing a quality defect recognition model based on the historical defect analysis data.

[0009] Optionally, by inputting defect analysis data, outputting a target quality defect type corresponding to the target electronic copper strip according to a quality defect recognition model, specifically comprising: obtaining, according to the quality defect recognition model, a plurality of different types of quality defect characteristics in the defect analysis data and an influence coefficient of the quality defect characteristics on the target quality defect type; and outputting, according to the quality defect characteristics and the influence coefficient, the target quality defect type corresponding to the target electronic copper strip according to the following formula:

[0010]

[0011] Among them, T is the target quality defect type, k is the kth defect type in the quality defect type index, argmax k To select k that maximizes the function value as the target quality defect type, x i is the i-th quality defect feature, α k,i is the weight value of the i-th quality defect feature to the k-th defect type.

[0012] Optionally, before outputting the target quality defect type corresponding to the target electronic copper tape through the following formula based on the quality defect characteristics and the influence coefficient, the method also includes: calculating the overall defect occurrence probability corresponding to the target electronic copper tape through a quality defect identification model based on the quality defect characteristics; judging whether the overall defect occurrence probability is greater than a preset defect occurrence probability; if the overall defect occurrence probability is greater than the preset defect occurrence probability, confirming that the target electronic copper tape has surface quality defects.

[0013] Optionally, before obtaining the target quality defect improvement plan corresponding to the target quality defect type in the preset plan analysis database, it is necessary to construct a preset plan analysis database, specifically including: obtaining multiple quality defect types and multiple quality defect improvement plans, the multiple quality defect types include the target quality defect type, and the multiple quality defect improvement plans include the target quality defect improvement plan, and constructing a correspondence between multiple quality defect types and multiple quality defect improvement plans, one quality defect type corresponds to one quality defect improvement plan; storing multiple quality defect types, multiple quality defect improvement plans and the correspondence in the preset plan analysis database, the quality defect types include roller friction scratch types, transmission short abrasion types, other scratch / scratch types and roller system abnormality types such as rolling mill oil squeezing rollers, and the quality defect improvement plans include copper strip scratch prevention and control optimization plans, lubrication optimization plans, steel sleeve and reel precision assurance plans and roller system dynamic linear speed adjustment plans.

[0014] Optionally, when the target quality defect improvement plan is a dynamic linear speed adjustment plan for the roller system, the surface quality of the target electronic copper strip is optimized according to the target quality defect improvement plan, specifically including: obtaining the real-time linear speed data of the roller system and the actual linear speed data of the target electronic copper strip; calculating a first deviation value between the real-time linear speed data and the actual linear speed data; calculating a second deviation value between the first deviation value and a preset deviation threshold; according to the second deviation value, obtaining a comparison operating condition corresponding to the target electronic copper strip; correcting the real-time linear speed data according to the comparison operating condition, and optimizing the surface quality of the target electronic copper strip.

[0015] In a second aspect of the present application, a quality defect optimization device for copper strip surface scratches is provided, the device comprising an acquisition module and a processing module, wherein:

[0016] An acquisition module is used to respond to a surface quality inspection operation on a target electronic copper strip, obtain defect analysis data corresponding to the target electronic copper strip through multiple inspection devices, and the multiple inspection devices include a high-speed proximity switch, an encoder, and a tension sensor; obtain a target quality defect improvement plan corresponding to the target quality defect type in a preset plan analysis database, and the preset plan analysis database is used to store the correspondence between the target quality defect type and the target quality defect improvement plan.

[0017] The processing module is used to input defect analysis data and output a target quality defect type corresponding to the target electronic copper strip according to a quality defect recognition model; and optimize the surface quality of the target electronic copper strip according to a target quality defect improvement plan.

[0018] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any one of the methods described above.

[0019] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to perform any of the above methods.

[0020] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0021] 1. When performing quality inspection on the surface of a target electronic copper strip, defect analysis data corresponding to the target electronic copper strip is obtained through multiple inspection devices, and by inputting the defect analysis data, a target quality defect type corresponding to the target electronic copper strip is output according to a quality defect recognition model, thereby obtaining a target quality defect improvement plan corresponding to the target quality defect type in a preset plan analysis database, and optimizing the surface quality of the target electronic copper strip according to the target quality defect improvement plan, thereby effectively ensuring the quality of finished products of copper-based new materials with high surface requirements, and greatly improving the optimization efficiency of copper strip surface quality defects.

[0022] 2. By dividing the surface of the target electronic copper strip into regions, and obtaining multiple damage susceptibility levels corresponding to multiple areas to be inspected, and sorting the multiple damage susceptibility levels from large to small according to the numerical values, the damage susceptibility level with the largest numerical value among the multiple damage susceptibility levels is confirmed according to the sorting results, and the high-risk damage level is obtained, so as to perform surface quality inspection operations on the areas to be inspected corresponding to the high-risk damage levels, accurately locate the defect sources in the high-risk areas, and timely optimize the production process, and improve the efficiency of the surface quality inspection operations of the target electronic copper strip.

[0023] 3. By obtaining historical defect analysis data and obtaining historical defect features corresponding to the historical defect analysis data according to preprocessing operations, a quality defect identification model is constructed based on the historical defect analysis data, and the target quality defect type is output through the quality defect identification model, thereby realizing a fast and efficient quality optimization process. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flow chart of a quality defect optimization method for copper strip surface scratches provided in an embodiment of the present application;

[0025] Figure 2This is a module schematic diagram of a quality defect optimization device for copper strip surface scratches provided in an embodiment of the present application;

[0026] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0027] Explanation of the reference numerals: 21, acquisition module; 22, processing module; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0028] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0029] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more listed items.

[0030] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0031] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0032] Please refer to Figure 1 , which shows a flow chart of a quality defect optimization method for copper strip surface scratches provided in an embodiment of the present application, and the flow chart mainly includes the following steps: S101 to S104.

[0033] Step S101, in response to a surface quality inspection operation on a target electronic copper strip, defect analysis data corresponding to the target electronic copper strip is obtained through a plurality of inspection devices, wherein the plurality of inspection devices include a high-speed proximity switch, an encoder and a tension sensor.

[0034] Specifically, when the copper strip finishing mill is producing high-end copper-based new materials, the surface quality of the target electronic copper strip is inspected in real time to monitor the production quality of the copper strip. The target electronic copper strip is any copper strip used in the production of high-end copper-based new materials. At this time, defect analysis data corresponding to the target electronic copper strip is obtained through multiple detection devices. The multiple detection devices include but are not limited to high-speed proximity switches, encoders, tension sensors, roller roughness measuring instruments, microscopic surface scanners, etc. The real-time rotation pulse signals of rollers such as the oil squeezing roller, the linear speed of the oil squeezing roller and its deviation from the linear speed of the copper strip are obtained through high-speed proximity switches. The value can be used to determine the abnormal rotation of the roller system; the high-resolution speed signal of the driving rollers such as the deflector roller and the plate roller is obtained through the encoder, and the synchronization of the roller system transmission and the tension coordination relationship are analyzed; the front and rear tension values ​​and tension fluctuations of the copper strip are obtained through the tension sensor, and the influence of tension loss control on the surface quality is determined; the roughness data of the surfaces of the oil squeezing roller, tension roller and other rollers are detected through the roller system roughness measuring instrument, and the friction abnormality caused by the decrease in roughness is analyzed; the microscopic scratch image and distribution characteristics of the copper strip surface are obtained through the microscopic surface scanner, and the defect analysis data are obtained from different dimensions to provide support for the subsequent quality defect identification and improvement.

[0035] In a possible implementation, step S101 also includes: dividing the surface of the target electronic copper tape into regions, wherein the region division is used to divide the target electronic copper tape into a plurality of regions to be inspected according to preset division rules; obtaining a plurality of susceptibility levels corresponding to the plurality of regions to be inspected, wherein one region to be inspected corresponds to one susceptibility level; sorting the plurality of susceptibility levels from large to small according to numerical values, and confirming the susceptibility level with the largest numerical value among the plurality of susceptibility levels according to the sorting result to obtain a high-risk damage level; and performing the surface quality inspection operation on the region to be inspected corresponding to the high-risk damage level.

[0036] Specifically, before performing quality inspection operations on the surface of the target electronic copper strip, it is necessary to divide the target electronic copper strip into regions, and divide the target electronic copper strip into multiple areas to be inspected according to preset division rules. The steps are as follows: First, divide the multiple areas to be inspected according to the geometric characteristics of the target electronic copper strip (such as width, length, edge distance, etc.) and the damage-prone characteristics in the process (such as tension distribution, rolling pressure, contact position, etc.). Common division rules include dividing the copper strip into edge areas, middle areas, and transition areas; then, based on historical defect analysis data and empirical data, evaluate the damage-prone level of each area to be inspected. The damage-prone level can be determined according to the possibility of scratches in different areas, The severity and impact on the quality of the final product are assigned; after obtaining multiple damage susceptibility levels corresponding to multiple areas to be inspected, they are sorted from large to small according to the values, and the damage susceptibility level with the largest value is confirmed and marked as the high-risk damage level; finally, the area to be inspected corresponding to the high-risk damage level is taken as the key inspection area, and surface quality inspection operations are performed within its range, including obtaining the deviation value between the roller speed signal and the copper strip speed through a high-speed proximity switch, monitoring the tension fluctuation through a tension sensor, and detecting the scratch distribution characteristics through a microscopic scanner, so as to accurately locate the defect source in the high-risk area and optimize the production process in time, and improve the efficiency of the surface quality inspection operation of the target electronic copper strip.

[0037] Step S102: by inputting the defect analysis data, outputting the target quality defect type corresponding to the target electronic copper strip according to the quality defect recognition model.

[0038] Specifically, the defect analysis data obtained from multiple detection devices are first taken as input, including the speed deviation data of the oil squeeze roller and the copper strip, the front and rear tension fluctuation data of the tension sensor, the surface roughness data of the roller system, and the surface scratch feature data of the microscope scanner; secondly, the defect analysis data is processed using a pre-built quality defect recognition model. The model is based on machine learning algorithms or rule logic and is constructed in combination with historical defect data. It can calculate the possibility of each defect type by comprehensively analyzing variables such as speed deviation, tension fluctuation, roughness anomaly, and scratch characteristics in the input data, and take the defect type with the highest possibility as the target quality defect type.

[0039] In a possible implementation, step S102 also includes: obtaining historical defect analysis data, the historical defect analysis data including surface scratch distribution data, roller equipment operating status data, and oil squeeze roller rotation pulse signal data; obtaining historical defect features corresponding to the historical defect analysis data through a preprocessing operation, and constructing the quality defect recognition model based on the historical defect analysis data.

[0040] Specifically, firstly, the historical defect analysis data is obtained through the production record and detection system, including the following key contents: surface scratch distribution data, roller equipment operation status data and squeeze roller rotation pulse signal data; among them, the surface scratch distribution data is used to record the specific location and distribution law of the defect, the roller equipment operation status data reflects the possible operation abnormality of the rolling mill equipment during the production process, and the squeeze roller rotation pulse signal data is used to calculate the linear velocity of the squeeze roller and its deviation value from the linear velocity of the copper strip. Then, the above historical defect analysis data is preprocessed, including data cleaning, standardization and feature extraction, to obtain historical defect features. Common historical defect features include the depth and length of scratches, the maximum value of speed deviation and its fluctuation range, and the tension difference in the tension out-of-control area. Subsequently, according to the processed historical defect features, a quality defect recognition model is constructed. The model adopts a supervised learning method to generate a functional relationship that can map the input features to the defect type by training the input historical defect features with the corresponding known defect types; the model often adopts methods such as logistic regression, decision tree or neural network, and the specific selection depends on the scale and complexity of the historical data. Ultimately, the constructed quality defect identification model can accurately determine the defect type of the target electronic copper strip, providing support for defect prevention and control in subsequent production processes.

[0041] In a possible implementation, step S102 further includes: calculating the overall defect occurrence probability corresponding to the target electronic copper strip through the quality defect recognition model according to the quality defect characteristics; judging whether the overall defect occurrence probability is greater than the preset defect occurrence probability; if the overall defect occurrence probability is greater than the preset defect occurrence probability, confirming that the target electronic copper strip has surface quality defects, and obtaining a plurality of different types of quality defect characteristics in the defect analysis data and the influence coefficient of the quality defect characteristics on the target quality defect type according to the quality defect recognition model; outputting the target quality defect type corresponding to the target electronic copper strip according to the following formula according to the quality defect characteristics and the influence coefficient:

[0042]

[0043] Where T is the target quality defect type, k is the kth defect type in the quality defect type index, argmax k To select k that maximizes the function value as the target quality defect type, x i is the quality defect feature of the ith k,i is the weight value of the i-th quality defect feature to the k-th defect type.

[0044] Specifically, based on the quality defect characteristics of the target electronic copper strip, the overall defect occurrence probability is calculated through a pre-constructed quality defect recognition model. The defect occurrence probability is based on the degree of match between the input features and similar defects in historical data, and a weighted probability model is used to summarize the contribution value of each feature to the possibility of defects. If the overall defect occurrence probability is greater than the preset defect occurrence probability, it is confirmed that the target electronic copper strip has surface quality defects, and the specific defect type identification stage is entered; if the overall defect occurrence probability is less than or equal to the preset defect occurrence probability, it is considered that the surface quality of the target electronic copper strip meets the requirements and no further analysis is required. After confirming the existence of surface quality defects, multiple different types of quality defect features in the input defect analysis data and the influence coefficients of these features on specific defect types are obtained according to the quality defect recognition model. The contribution of each feature to different defect types is determined through a training process. The higher the value, the higher the recognition degree of the feature for a certain defect type. Then, according to the formula The target quality defect type corresponding to the target electronic copper tape is output.

[0045] Step S103, obtaining a target quality defect improvement solution corresponding to the target quality defect type from a preset solution analysis database, wherein the preset solution analysis database is used to store a correspondence between the target quality defect type and the target quality defect improvement solution.

[0046] Specifically, first, a preset solution analysis database is constructed. The core of the database is to store the mapping relationship between the target quality defect type and its corresponding improvement solution. Each record in the database contains two parts of information: the target quality defect type and the target quality defect improvement solution. The defect types may include: roller friction scratch type, transmission short abrasion type, other scratch / scratch types, rolling mill oil squeeze roller and other roller system abnormality types, etc. The improvement solutions include copper strip scratch prevention and control optimization solutions, lubrication optimization solutions, steel sleeve and reel precision assurance solutions, roller system dynamic linear speed adjustment solutions, etc.

[0047] After the target quality defect type is output through the quality defect recognition model, the system will automatically retrieve the preset solution analysis database based on the recognition results, and quickly locate the corresponding improvement solution for the defect type by matching the corresponding defect type index. During the database retrieval process, the adaptability of the solution can also be dynamically adjusted according to production conditions. For example, further optimization suggestions are added to the basic improvement solution based on process parameters such as copper strip thickness and rolling speed. In the end, the improvement solution output by the system not only clearly points out the source of the defect, but also provides detailed operation instructions for operators to execute, thereby achieving a fast and efficient quality optimization process.

[0048] Step S104, optimizing the surface quality of the target electronic copper strip according to the target quality defect improvement plan.

[0049] Specifically, for different defect types, different quality defect improvement solutions are implemented to optimize the surface quality of the target electronic copper strip.

[0050] For example, if the squeeze roller, tension roller, flattening roller or other rollers in contact with the copper belt are stuck or rotated poorly, scratches will be caused. Other raised parts of the frame, such as nozzles and guide plates, may also contact the copper belt and cause scratches. Through these defect characteristics, the target quality defect type is judged to be the roller friction scratch type. At this time, the target quality defect improvement plan is the copper belt scratch prevention and control optimization plan. The specific implementation steps of this plan include: the rotation flexibility and lubrication condition of each roller in contact with the copper belt must be checked every day. At the same time, foreign objects on the rolling mill must be cleaned in time to prevent serious scratches caused by roller jamming, poor rotation or contact with foreign objects; the running roughness of various roller systems is measured to Ra1.5. When rolling the copper belt, strictly follow the operating requirements and strictly control the threading process to prevent the copper belt from scratching the surface of the working roller. When setting the rolling parameters, the front tension must be greater than the rear tension. During the routine inspection process, the surface of the incoming material is manually checked during the unwinding and rotation of the copper strip on the uncoiler; the material head passes through the roll gap of the rolling mill to the coiler to build tension, first adjust the tension so that the front tension is greater than the latter, and after rolling for 3 turns, stop and check the surface of the copper strip in the rolling section. If scratches appear, carefully check the starting position of the scratches, and find the corresponding part on the equipment corresponding to the scratch starting position of the copper strip, which proves that the scratches are caused by this part, and notify the relevant maintenance personnel to deal with it. Automatically decelerate when rolling is completed, stop according to thickness, remove tension after rolling and open the roll gap to avoid the edge of the coiled material scratching the roll and causing quality problems.

[0051] The speed difference between the flattening roller, oil squeeze roller, deflector roller, profile roller, etc. and the strip material causes small scratches, such as scratches caused by the asynchrony of the profile roller or the deflection roller. The general rolling mill electrical transmission control has static friction compensation, acceleration and deceleration dynamic compensation, and actual speed display during rolling. The displayed data can be used as a reference to improve the poor synchronous control of the deflection roller transmission to avoid the phenomenon of serious degradation of the quality of copper strip foil products. However, some passive roller systems cannot judge their status, especially during high-speed rolling, short scratches are caused by asynchrony of transmission. Through these defect characteristics, it can be judged that the target quality defect type is the transmission short scratch type. At this time, the target quality defect improvement plan is the lubrication optimization plan. The specific implementation steps of this plan are: notify the maintenance personnel of the roller system to regularly use the lifting method to measure the torque, check the rotation flexibility of the roller system, whether the lubrication condition is normal, adjust the hydraulic oil station when the ambient temperature changes, or use oil and gas lubrication and other measures.

[0052] There may be other reasons for scratches in the target electronic copper tape, such as deformation of the steel sleeve causing eccentricity on the winding side, uneven wrapping of the copper tape causing scratches between the copper tapes, and secondly, changes in the position accuracy of the reel of the winder causing the copper tape to swing when it is rolled in, causing scratches, and the unwinding and winding threading head, the receiving tail and the head and tail packaging are not tightened, causing the copper tape to loosen and cause scratches, etc. Through these defect characteristics, it can be judged that the target quality defect type is other scratch / abrasion types. At this time, the target quality defect improvement plan is the steel sleeve and reel accuracy assurance plan. The specific implementation method of this method is: strict control of the sleeve, especially the deformation inspection; regular maintenance of the reel to ensure the true roundness accuracy and spatial parallel coaxial accuracy; operation is strictly carried out according to regulations to avoid loosening of materials.

[0053] In a possible implementation, when the target quality defect improvement plan is the dynamic linear speed adjustment plan of the roller system, step S104 also includes: obtaining the real-time linear speed data of the roller system and the actual linear speed data of the target electronic copper strip; calculating a first deviation value between the real-time linear speed data and the actual linear speed data; calculating a second deviation value between the first deviation value and a preset deviation threshold; according to the second deviation value, obtaining a comparative working condition corresponding to the target electronic copper strip; correcting the real-time linear speed data according to the comparative working condition, and optimizing the surface quality of the target electronic copper strip.

[0054] Specifically, the above measures are all static inspections or maintenance and standardized operation requirements. Through practice, it is found that the above flattening rollers and oil squeeze rollers are normal in static inspections, but there are abnormal scratches on the copper strip surface in dynamic conditions, such as no scratches when not pressing the rollers, abnormal pressure rollers, normal at low speeds, and abnormal at high speeds. It is difficult to inspect the quality of this machine, and it is often discovered several processes after the next process. It is very difficult to troubleshoot and the rectification cycle is also long. Take the oil squeeze roller as an example: the oil squeeze roller on the precision copper strip rolling mill is generally made of 3M material. The oil squeeze roller has significant advantages: the cut part has self-healing properties; the friction coefficient is high, which can effectively prevent the roller from slipping; due to its porous structure, it has good absorption characteristics for oil and fine residues, which can effectively avoid secondary scratches on the surface of the cold-rolled copper strip, while reducing the loss of rolling oil and improving the surface quality of the copper strip. However, due to the reduction of the roughness of the roller surface wear or the blocking of the roller bearing, the linear speed of the oil squeeze roller will deviate from the actual speed of the copper strip. The oil squeezing roller adopts passive transmission and no power drive, and the actual speed cannot be measured by driving the motor. At the same time, according to actual production practice, even if the inspection is normal when not in production and it is normal during low-speed production, there will be a large speed deviation during high-speed rolling, causing scratches on the strip surface, and it will return to normal after deceleration and troubleshooting. It is very difficult to judge that the fault or quality problem is very hidden. The existing troubleshooting scheme generally adopts methods such as checking the roughness of the oil squeezing roller Ra1.5 before production, whether the bearing rotation is blocked, and measuring the rotation torque of the oil squeezing roller by the pulling method. These are all manual experience measurements, which cannot guarantee the reliability of the rolling state. Abnormal batch quality often occurs, and it is difficult to trace the source afterwards. At this time, it is judged that the target quality defect type is an abnormal type of roller system such as the oil squeezing roller of the rolling mill. At this time, the target quality defect improvement plan is the dynamic linear speed adjustment plan of the roller system. The specific implementation steps of this plan are: using a high-speed proximity switch to obtain the rotation pulse signal of the oil squeezing roller, that is, to obtain the real-time linear speed data of the roller system; according to the obtained pulse signal, the number of pulses emitted when the oil squeezing roller rotates one circle and the pulse emission frequency are mathematically transformed according to the following formula:

[0055] V = π × D × N / n × 60;

[0056] Among them, V represents the linear speed of the rolling mill oil squeezing roller, D is the diameter unit of the rolling mill oil squeezing roller, N represents the frequency of the electric pulse signal generated in each sampling cycle, and n represents the number of electric pulse signals output by the sensor when the rolling mill oil squeezing roller rotates one circle. For example, when the oil squeezing roller rotates one circle, 4 pulses are emitted, and the emission frequency is about 66Hz. Through calculation, the real-time linear speed of the oil squeezing roller can be obtained as 600m / min. For tension rollers or flattening rollers, the same method can be used to perform real-time speed monitoring; for plate rollers or deflection rollers, the equipment body is generally equipped with a drive motor encoder or a speed encoder with a higher resolution, such as 2048PPR or 8000PPR; in the rolling mill system, the signal is sent to the transmission or thickness control system, and an encoder signal distributor needs to be added to perform frequency division and frequency reduction and send it to the independent line speed monitoring system to convert the actual line speed of the target electronic copper strip. After that, a first deviation value between the real-time line speed data and the actual line speed data is calculated, and a second deviation value between the first deviation value and a preset deviation threshold is calculated. The preset deviation threshold can be set according to historical data or experimental experience, and the deviation value and the deviation threshold are compared to obtain a comparison condition, thereby correcting the real-time line speed data according to the comparison condition and optimizing the surface quality of the target electronic copper strip.

[0057] The present application adopts the above method, when performing quality inspection operation on the surface of the target electronic copper strip, obtains the defect analysis data corresponding to the target electronic copper strip through multiple inspection devices, and outputs the target quality defect type corresponding to the target electronic copper strip according to the quality defect recognition model by inputting the defect analysis data, thereby obtaining the target quality defect improvement plan corresponding to the target quality defect type in the preset plan analysis database, and optimizing the surface quality of the target electronic copper strip according to the target quality defect improvement plan, thereby not only effectively ensuring the finished product quality of the copper-based new material with high surface requirements, but also greatly improving the optimization efficiency of the copper strip surface quality defects.

[0058] Please refer to Figure 2 , which shows a module schematic diagram of a quality defect optimization device for copper strip surface scratches provided in an embodiment of the present application, the device includes an acquisition module 21 and a processing module 22, wherein:

[0059] The acquisition module 21 is used to respond to the surface quality inspection operation on the target electronic copper strip, obtain defect analysis data corresponding to the target electronic copper strip through multiple inspection devices, and the multiple inspection devices include high-speed proximity switches, encoders and tension sensors; obtain the target quality defect improvement plan corresponding to the target quality defect type in the preset plan analysis database, and the preset plan analysis database is used to store the correspondence between the target quality defect type and the target quality defect improvement plan.

[0060] The processing module 22 is used to input defect analysis data and output a target quality defect type corresponding to the target electronic copper strip according to the quality defect recognition model; and optimize the surface quality of the target electronic copper strip according to the target quality defect improvement plan.

[0061] In a possible embodiment, the acquisition module 21 is used to respond to the surface quality detection operation on the target electronic copper tape, and the method also includes: dividing the surface of the target electronic copper tape into regions, and the region division is used to divide the target electronic copper tape into multiple areas to be detected according to preset division rules; obtaining multiple susceptibility levels corresponding to the multiple areas to be detected, and one area to be detected corresponds to one susceptibility level; sorting the multiple susceptibility levels from large to small according to the numerical values, and confirming the susceptibility level with the largest numerical value among the multiple susceptibility levels according to the sorting result to obtain a high-risk damage level; performing a surface quality detection operation on the area to be detected corresponding to the high-risk damage level.

[0062] In one possible implementation, the processing module 22 is used to construct a quality defect recognition model before outputting a target quality defect type corresponding to the target electronic copper strip according to the quality defect recognition model by inputting defect analysis data, specifically including: obtaining historical defect analysis data, the historical defect analysis data including surface scratch distribution data, roller equipment operating status data, and oil squeeze roller rotation pulse signal data; obtaining historical defect features corresponding to the historical defect analysis data through preprocessing operations, and constructing a quality defect recognition model based on the historical defect analysis data.

[0063] In a possible implementation, the processing module 22 is used to output the target quality defect type corresponding to the target electronic copper strip according to the quality defect recognition model by inputting the defect analysis data, specifically including: obtaining the quality defect characteristics of multiple different types and the influence coefficient of the quality defect characteristics on the target quality defect type in the defect analysis data according to the quality defect recognition model; outputting the target quality defect type corresponding to the target electronic copper strip according to the following formula according to the quality defect characteristics and the influence coefficient:

[0064]

[0065] Among them, T is the target quality defect type, k is the kth defect type in the quality defect type index, argmax k To select k that maximizes the function value as the target quality defect type, x i is the i-th quality defect feature, α k,i is the weight value of the i-th quality defect feature to the k-th defect type.

[0066] In a possible implementation, the processing module 22 is used to output the target quality defect type corresponding to the target electronic copper tape through the following formula according to the quality defect characteristics and the influence coefficient, and the method also includes: calculating the overall defect occurrence probability corresponding to the target electronic copper tape through a quality defect identification model according to the quality defect characteristics; judging whether the overall defect occurrence probability is greater than the preset defect occurrence probability; if the overall defect occurrence probability is greater than the preset defect occurrence probability, confirming that the target electronic copper tape has surface quality defects.

[0067] In a possible implementation manner, the processing module 22 is used to construct a preset scheme analysis database before obtaining the target quality defect improvement scheme corresponding to the target quality defect type in the preset scheme analysis database, specifically including: obtaining multiple quality defect types and multiple quality defect improvement schemes, the multiple quality defect types include the target quality defect type, and the multiple quality defect improvement schemes include the target quality defect improvement scheme, and constructing a correspondence between multiple quality defect types and multiple quality defect improvement schemes, one quality defect type corresponds to one quality defect improvement scheme; storing multiple quality defect types, multiple quality defect improvement schemes and the correspondence in the preset scheme analysis database, the quality defect types include roller friction scratch types, transmission short abrasion types, other scratch / scratch types and roller system abnormality types such as rolling mill oil squeezing rollers, and the quality defect improvement schemes include copper strip scratch prevention and control optimization schemes, lubrication optimization schemes, steel sleeve and reel precision assurance schemes and roller system dynamic linear speed adjustment schemes.

[0068] In one possible implementation, the processing module 22 is used to optimize the surface quality of the target electronic copper strip according to the target quality defect improvement plan when the target quality defect improvement plan is a dynamic linear speed adjustment plan for the roller system, specifically including: obtaining the real-time linear speed data of the roller system and the actual linear speed data of the target electronic copper strip; calculating a first deviation value between the real-time linear speed data and the actual linear speed data; calculating a second deviation value between the first deviation value and a preset deviation threshold; obtaining a comparison operating condition corresponding to the target electronic copper strip according to the second deviation value; correcting the real-time linear speed data according to the comparison operating condition, and optimizing the surface quality of the target electronic copper strip.

[0069] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0070] The present application also provides an electronic device. Figure 3 , Figure 3 30 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include: at least one processor 301, at least one communication bus 302, a user interface 303, at least one network interface 304, and a memory 305.

[0071] The communication bus 302 is used to realize the connection and communication between these components.

[0072] The user interface 303 may include a display screen (Display) and a camera (Camera). The optional user interface 303 may also include a standard wired interface and a wireless interface.

[0073] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0074] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or more combinations of central processing units (Central Processing Unit, CPU) and graphics processing units (Graphics Processing Unit, GPU). Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content that needs to be displayed on the display screen.

[0075] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 The memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for optimizing the quality defects of copper strip surface scratches.

[0076] exist Figure 3 In the electronic device shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the quality defect optimization application for scratches on the surface of the copper strip stored in the memory 305. When executed by one or more processors 301, the electronic device executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0077] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.

[0078] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0079] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. 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 service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0080] 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.

[0081] In addition, each functional unit in each embodiment of the present application 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. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0082] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the methods of each embodiment of the present application.

[0083] The above are only exemplary embodiments disclosed in this application, and the scope of the disclosure of this application cannot be limited by this. That is, any equivalent changes and modifications made according to the teachings disclosed in this application are still within the scope of the disclosure of this application. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other implementation schemes disclosed in this application.

[0084] This application is intended to cover any modifications, uses or adaptive changes disclosed in this application, which follow the general principles disclosed in this application and include common knowledge or customary technical means in the technical field not recorded in this application.

Claims

1. A quality defect optimization method for copper strip surface scratches, characterized in that: The method comprises: In response to a surface quality inspection operation for a target electronic copper strip, defect analysis data corresponding to the target electronic copper strip is obtained through a plurality of inspection devices, wherein the plurality of inspection devices include a high-speed proximity switch, an encoder, and a tension sensor; By inputting the defect analysis data, outputting the target quality defect type corresponding to the target electronic copper strip according to the quality defect recognition model; Obtaining a target quality defect improvement solution corresponding to the target quality defect type in a preset solution analysis database, wherein the preset solution analysis database is used to store a correspondence between the target quality defect type and the target quality defect improvement solution; According to the target quality defect improvement plan, the surface quality of the target electronic copper strip is optimized.

2. The method according to claim 1, characterized in that Before the step of responding to the surface quality inspection operation on the target electronic copper strip, the method further comprises: Performing area division on the surface of the target electronic copper tape, wherein the area division is used to divide the target electronic copper tape into a plurality of areas to be detected according to a preset division rule; Acquire a plurality of vulnerability levels corresponding to a plurality of the to-be-detected areas, wherein one to-be-detected area corresponds to one vulnerability level; Sorting the plurality of vulnerability levels from large to small according to the numerical values, and determining the vulnerability level with the largest numerical value among the plurality of vulnerability levels according to the sorting result to obtain a high-risk damage level; The surface quality inspection operation is performed on the area to be inspected corresponding to the high-risk damage level.

3. The method according to claim 1, characterized in that Before the defect analysis data is input and the target quality defect type corresponding to the target electronic copper strip is output according to the quality defect recognition model, the quality defect recognition model needs to be constructed, which specifically includes: Acquiring historical defect analysis data, wherein the historical defect analysis data includes surface scratch distribution data, roller system equipment operation status data, and oil squeeze roller rotation pulse signal data; The historical defect features corresponding to the historical defect analysis data are obtained through a preprocessing operation, and the quality defect recognition model is constructed based on the historical defect analysis data.

4. The method according to claim 1, characterized in that The step of inputting the defect analysis data and outputting the target quality defect type corresponding to the target electronic copper strip according to the quality defect recognition model specifically includes: According to the quality defect recognition model, a plurality of different types of quality defect features in the defect analysis data and influence coefficients of the quality defect features on the target quality defect type are obtained; According to the quality defect characteristics and the influence coefficient, the target quality defect type corresponding to the target electronic copper strip is output by the following formula: Where T is the target quality defect type, k is the kth defect type in the quality defect type index, argmax k To select k that maximizes the function value as the target quality defect type, x i is the quality defect feature of the ith k,i is the weight value of the i-th quality defect feature to the k-th defect type.

5. The method according to claim 4, characterized in that Before outputting the target quality defect type corresponding to the target electronic copper strip according to the quality defect characteristics and the influence coefficient by the following formula, the method further includes: According to the quality defect characteristics, the overall defect occurrence probability corresponding to the target electronic copper strip is calculated by the quality defect recognition model; Determining whether the overall defect occurrence probability is greater than a preset defect occurrence probability; If the overall defect occurrence probability is greater than the preset defect occurrence probability, it is confirmed that the target electronic copper strip has surface quality defects.

6. The method according to claim 1, characterized in that Before obtaining the target quality defect improvement solution corresponding to the target quality defect type in the preset solution analysis database, it is necessary to construct the preset solution analysis database, specifically including: Acquire multiple quality defect types and multiple quality defect improvement solutions, wherein the multiple quality defect types include the target quality defect type, and the multiple quality defect improvement solutions include the target quality defect improvement solution, and establish a correspondence between the multiple quality defect types and the multiple quality defect improvement solutions, wherein one quality defect type corresponds to one quality defect improvement solution; The plurality of quality defect types, the plurality of quality defect improvement plans and the corresponding relationships are stored in the preset plan analysis database, the quality defect types include roller friction scratch types, transmission short abrasion types, other scratch / scratch types and roller system abnormality types such as rolling mill oil squeeze rollers, and the quality defect improvement plans include copper strip scratch prevention and control optimization plans, lubrication optimization plans, steel sleeve and reel accuracy assurance plans and roller system dynamic linear speed adjustment plans.

7. The method according to claim 6, characterized in that When the target quality defect improvement scheme is the roller system dynamic linear speed adjustment scheme, the surface quality of the target electronic copper strip is optimized according to the target quality defect improvement scheme, specifically including: Acquiring real-time linear velocity data of the roller system and actual linear velocity data of the target electronic copper strip; Calculating a first deviation value between the real-time linear velocity data and the actual linear velocity data; Calculate a second deviation value between the first deviation value and a preset deviation threshold; According to the second deviation value, obtaining a comparison working condition corresponding to the target electronic copper strip; The real-time line speed data is corrected according to the comparison working conditions, and the surface quality of the target electronic copper strip is optimized.

8. A quality defect optimization device for copper strip surface scratches, characterized in that: The device comprises an acquisition module and a processing module, wherein: The acquisition module is used to respond to the surface quality detection operation of the target electronic copper strip, obtain the defect analysis data corresponding to the target electronic copper strip through multiple detection devices, and the multiple detection devices include a high-speed proximity switch, an encoder and a tension sensor; obtain the target quality defect improvement plan corresponding to the target quality defect type in the preset solution analysis database, and the preset solution analysis database is used to store the corresponding relationship between the target quality defect type and the target quality defect improvement plan; The processing module is used to input the defect analysis data and output the target quality defect type corresponding to the target electronic copper strip according to the quality defect recognition model; and optimize the surface quality of the target electronic copper strip according to the target quality defect improvement plan.

9. An electronic device, characterized in that: It includes a processor, a communication bus, a user interface, a network interface and a memory, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.

Images