Steel plate shape inspection methods and related equipment

Abstract

This invention discloses a method and related equipment for steel plate shape detection, relating to the field of steel plate rolling, primarily addressing the problem that current steel plate shape detection relies too heavily on manual labor and the measurement results are not accurate enough. The method includes: identifying a target steel plate, wherein the target steel plate is a medium-thick plate; acquiring the transverse arc characteristic value and the unevenness characteristic value of the target steel plate; and evaluating the shape of the target steel plate based on the transverse arc characteristic value and the unevenness characteristic value to obtain a shape evaluation result. This invention is used in the steel plate shape detection process.

Description

Technical Field

[0001] This invention relates to the field of steel plate rolling, and more particularly to a method and related equipment for detecting the shape of steel plates. Background Technology

[0002] With increasingly stringent quality requirements from users, the shape of medium and heavy plates has become one of the key indicators affecting product quality. The flatness of medium and heavy plates has traditionally relied on operators measuring it using a 2-meter-long pole. However, this method is time-consuming, labor-intensive, and inefficient, impacting production schedules. Manual measurement also suffers from low accuracy and is prone to errors. Furthermore, the measurement results are highly dependent on the measurement location, resulting in low precision. The available measurement data is limited, typically only applicable to a finite number of points, and cannot characterize the overall shape of the plate. Summary of the Invention

[0003] In view of the above problems, the present invention provides a method and related equipment for steel plate shape detection, the main purpose of which is to solve the problem that the current steel plate shape detection relies too much on manual labor and the measurement results are not accurate enough.

[0004] To solve at least one of the above-mentioned technical problems, in a first aspect, the present invention provides a method for detecting the shape of a steel plate, the method comprising:

[0005] The target steel plate is identified, wherein the target steel plate is a medium-thick plate;

[0006] Obtain the transverse arc characteristic value and unevenness characteristic value of the target steel plate;

[0007] The plate shape of the target steel plate is evaluated based on the transverse arc characteristic value and the unevenness characteristic value to obtain the plate shape evaluation result.

[0008] Optionally, obtaining the transverse arc characteristic value and unevenness characteristic value of the target steel plate includes:

[0009] Obtain the first contour data of the target steel plate surface along the length direction;

[0010] Based on the first preset standard, the target steel plate is divided into regions according to the first contour data to determine the head region, middle region and tail region of the target steel plate; the transverse arc feature values ​​corresponding to the head region, the middle region and the tail region of the target steel plate are determined respectively.

[0011] Optionally, determining the lateral arc feature values ​​corresponding to the head region, the middle region, and the tail region respectively includes:

[0012] The lateral arc characteristic value is determined based on the following formula:

[0013]

[0014] Among them, H i Let L be the lateral arc characteristic value of the i-th region, where i ranges from 1 to 3, where 1 represents the head region of the steel plate, 2 represents the middle region of the steel plate, and 3 represents the tail region of the steel plate; i Let represent the set of indices for the i-th region along the length direction; j represents the index of the i-th region along the length direction; p jk and p jl These represent the width coordinates of points k and l at the j-th length position of the steel plate, respectively; h jk and h jl w1 represents the outline height of the k-th and l-th points at the j-th length position of the steel plate, respectively; w1 represents the specified width range.

[0015] Optionally, obtaining the transverse arc characteristic value and unevenness characteristic value of the target steel plate includes:

[0016] Obtain the second contour data of the target steel plate surface along the width direction;

[0017] Based on the second preset standard, the target steel plate is divided into regions according to the second contour data to determine the left side region, the center region and the right side region of the target steel plate;

[0018] Determine the unevenness characteristic values ​​corresponding to the left side region, the center region, and the right side region of the target steel plate, respectively.

[0019] Optionally, determining the unevenness feature values ​​corresponding to the left region, the central region, and the right region respectively includes:

[0020] The roughness characteristic value is determined based on the following formula:

[0021]

[0022] Among them, U i Let W represent the unevenness of the i-th region, where i ranges from 1 to 3, where 1 represents the left side of the steel plate, 2 represents the center of the steel plate, and 3 represents the right side of the steel plate. i Let represent the set of indices for the i-th region along the width direction; j represents the index of the position belonging to the i-th region along the width direction; p kj and p lj These represent the length positions of points k and l respectively at the j-th width position of the steel plate; h kj and h lj w1 represents the outline height of the kth and lth points at the jth width position of the steel plate, respectively; w2 represents the specified length range.

[0023] Optionally, the method further includes:

[0024] Establish a process parameter database, wherein the process parameter database includes temperature field distribution, rolling torque and cooling rate;

[0025] A plate shape defect prediction model is constructed based on the aforementioned process parameter database.

[0026] Optionally, the method further includes:

[0027] The measurement data of the target steel plate are corrected in real time using a Kalman filter algorithm.

[0028] Secondly, embodiments of the present invention also provide a steel plate shape detection device, comprising:

[0029] A determining unit is used to determine a target steel plate, wherein the target steel plate is a medium-thick plate;

[0030] The acquisition unit is used to acquire the transverse arc characteristic value and the unevenness characteristic value of the target steel plate;

[0031] The calculation unit is used to evaluate the plate shape of the target steel plate based on the transverse arc characteristic value and the unevenness characteristic value, so as to obtain the plate shape evaluation result.

[0032] To achieve the above objectives, according to a third aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium comprising a stored program, wherein, when the program is executed by a processor, the steps of the above-described steel plate shape detection method are implemented.

[0033] To achieve the above objectives, according to a fourth aspect of the present invention, an electronic device is provided, comprising at least one processor and at least one memory connected to the processor; wherein the processor is configured to invoke program instructions in the memory to execute the steps of the steel plate shape detection method described above.

[0034] By employing the above technical solution, the steel plate shape detection method and related equipment provided by this invention address the problem that current steel plate shape detection relies too heavily on manual labor and the measurement results are not accurate enough. This invention identifies a target steel plate, wherein the target steel plate is a medium-thick plate; obtains the transverse arc characteristic value and the unevenness characteristic value of the target steel plate; and evaluates the plate shape based on the transverse arc characteristic value and the unevenness characteristic value to obtain the plate shape evaluation result. In the above solution, by constructing a multi-dimensional regional evaluation system, the technical limitations of the traditional single-point measurement mode are overcome. This method achieves spatial positioning and quantitative characterization of plate shape defects by calculating the transverse arc and unevenness by region. This provides a traceable data foundation for subsequent straightening process parameter optimization. Compared with manual measurement, this method improves detection efficiency while ensuring measurement accuracy and avoids the problems of missed detections and misjudgments caused by human factors.

[0035] Correspondingly, the steel plate shape detection device, equipment, and computer-readable storage medium provided in the embodiments of the present invention also have the above-mentioned technical effects.

[0036] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0037] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0038] Figure 1 A schematic flowchart of a steel plate shape detection method provided by an embodiment of the present invention is shown;

[0039] Figure 2 This diagram illustrates a steel plate shape detection method according to an embodiment of the present invention.

[0040] Figure 3 This shows a shape detection cloud map of a steel plate provided by an embodiment of the present invention;

[0041] Figure 4 This illustrates another steel plate shape detection cloud map provided by an embodiment of the present invention;

[0042] Figure 5 This diagram illustrates a downstream process flow guide for steel plate shape detection according to an embodiment of the present invention.

[0043] Figure 6 This is a schematic block diagram showing the composition of a steel plate shape detection device according to an embodiment of the present invention;

[0044] Figure 7 This diagram illustrates the composition of an electronic device for detecting the shape of a steel plate according to an embodiment of the present invention. Detailed Implementation

[0045] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0046] To address the problem that current steel plate shape inspection relies too heavily on manual labor and yields inaccurate results, this invention provides a method for steel plate shape inspection, such as... Figure 1 As shown, the method includes:

[0047] S101. Determine the target steel plate, wherein the target steel plate is a medium-thick plate; specifically, "medium-thick plate" is a standard term in the field of metal materials and steel processing, and is clearly defined in industry specifications and technical documents. Medium-thick plate refers to steel plates with a thickness of 4.5-25.0 mm, those with a thickness of 25.0-100.0 mm are called "thick plates," and those exceeding 100.0 mm are called "extra-thick plates." This application specifically targets medium-thick plates.

[0048] S102. Obtain the transverse arc characteristic value and unevenness characteristic value of the target steel plate;

[0049] For example, the aforementioned transverse arc characteristic value reflects the degree of bending of the steel plate in the width direction. The transverse arc characteristic value, characterized by a quantitative formula, represents the local extreme differences in the transverse bending of the steel plate and is used to guide the straightening process. It is typically quantified by measuring the maximum height difference in the width direction of the steel plate. For instance, if there is a significant height difference between the two edges of the steel plate and the central area, the transverse arc characteristic value will exceed the limit.

[0050] The aforementioned unevenness characteristic values ​​reflect the waviness of the steel plate along its length. These unevenness characteristic values ​​are derived by converting standard unevenness parameters into specific numerical values ​​using quantitative formulas, and are used to assess the severity of defects such as waviness and warping in different areas.

[0051] like Figure 2 As shown, the vertical distance between the camera's optical center and the steel plate surface is h1, and the vertical distance between the laser and the steel plate surface is h2. The horizontal distance between the camera and the laser forms a triangulation baseline with a baseline distance of L. A steel plate coordinate system is constructed with the steel plate surface as the XY plane, the length direction as the X-axis, the width direction as the Y-axis, and the Z-axis perpendicular to the steel plate and pointing upwards. The laser projects a line laser onto the steel plate surface at an angle α. The deformation of the line laser projected onto the steel plate surface reflects the surface undulations. An industrial camera is used to capture the laser line profile on the steel plate surface in real time, and the acquired data is transmitted to a computer for image processing and data analysis. This allows the acquisition of the profile distribution of the current steel plate length position in the width direction. After acquiring all data in the length direction of the steel plate, the plate shape characteristics in the width and length directions are calculated, ultimately yielding the overall plate shape result.

[0052] It should be noted that, Figure 2 The steel plate in the text is the target steel plate.

[0053] In one embodiment, obtaining the transverse arc characteristic value and unevenness characteristic value of the target steel plate includes:

[0054] Obtain the first contour data of the target steel plate surface along the length direction;

[0055] Based on the first preset standard, the target steel plate is divided into regions according to the first contour data to determine the head region, middle region and tail region of the target steel plate; the transverse arc feature values ​​corresponding to the head region, the middle region and the tail region of the target steel plate are determined respectively.

[0056] For example, the first preset standard can be a custom area length ratio (e.g., the head / tail each account for 10% of the total length of the steel plate, and the middle accounts for 80%), or a fixed length threshold (e.g., head: Y = 0-3.5m; tail: Y = 31.5-35m). No specific limitation is made here.

[0057] For each region (head / middle / tail), the lateral arc feature value Hj is defined as the maximum height difference in the width direction within that region. This refined regional detection avoids the overall evaluation from masking local defects, thus improving defect location accuracy.

[0058] Based on the above scheme, this application uses a high-resolution industrial camera combined with a line laser scanning device to collect laser contour data along the length direction of the surface of a medium-thick steel plate. The collected contour data is divided into a head region, a middle region, and a tail region according to a preset region division standard, and the transverse arc characteristic value of each region is calculated.

[0059] In one embodiment, determining the lateral arc feature values ​​corresponding to the head region, the middle region, and the tail region respectively includes:

[0060] The lateral arc characteristic value is determined based on the following formula:

[0061]

[0062] Among them, H i Let L be the lateral arc characteristic value of the i-th region, where i ranges from 1 to 3, where 1 represents the head region of the steel plate, 2 represents the middle region of the steel plate, and 3 represents the tail region of the steel plate; i Let represent the set of indices for the i-th region along the length direction; j represents the index of the i-th region along the length direction; p jk and p jl These represent the width coordinates of points k and l at the j-th length position of the steel plate, respectively; h jk and h jl w1 represents the outline height of the k-th and l-th points at the j-th length position of the steel plate, respectively; w1 represents the specified width range.

[0063] The above scheme introduces a local extremum difference algorithm, which eliminates the interference of edge noise on the calculation results by setting a width threshold to filter effective measurement points. Compared with the traditional arithmetic mean method, this model can more sensitively capture local bulge defects caused by uneven rolling stress distribution, thus improving the detection sensitivity of transverse arcs. At the same time, the regional calculation strategy allows the plate shape characteristics of different process sections to be presented differently, providing key input parameters for the temperature gradient control of hot straightening.

[0064] Simultaneously, it overcomes the technical bottlenecks of traditional methods in interference suppression, dynamic adaptation, and the balance between accuracy and efficiency. By deeply integrating signal processing mechanisms with the physical laws of the rolling process, a complete closed loop is achieved, from reliable feature extraction in noisy environments to intelligent process status diagnosis. This design not only improves the robustness and detection accuracy of the shape detection system but also provides a high-resolution data foundation for subsequent process optimization.

[0065] In one embodiment, obtaining the transverse arc characteristic value and unevenness characteristic value of the target steel plate includes:

[0066] Obtain the second contour data of the target steel plate surface along the width direction;

[0067] Based on the second preset standard, the target steel plate is divided into regions according to the second contour data to determine the left side region, the center region and the right side region of the target steel plate;

[0068] Determine the unevenness characteristic values ​​corresponding to the left side region, the center region, and the right side region of the target steel plate, respectively.

[0069] This application quantifies the transverse bending (such as edge waviness and center waviness) and surface flatness deviation of steel plates using width-direction profile data, providing a basis for subsequent regional analysis. The width direction of the same steel plate is then divided into a left-side region, a central region, and a right-side region, and the unevenness characteristic values ​​of each region are calculated separately. Regional analysis can distinguish defect types such as camber, edge waviness, and center waviness.

[0070] It is understandable that the second preset standard, like the first preset standard mentioned above, can be a custom area length ratio (20% of the width for the left / right side areas and 60% for the center area), or a fixed length threshold (e.g., 3 meters wide steel plate with 0.6 meters on each side). No specific limitation is made here.

[0071] In one embodiment, determining the unevenness feature values ​​corresponding to the left region, the central region, and the right region respectively includes:

[0072] The roughness characteristic value is determined based on the following formula:

[0073]

[0074] Among them, U i Let W represent the unevenness of the i-th region, where i ranges from 1 to 3, where 1 represents the left side of the steel plate, 2 represents the center of the steel plate, and 3 represents the right side of the steel plate. i Let represent the set of indices for the i-th region along the width direction; j represents the index of the position belonging to the i-th region along the width direction; p kj and p lj These represent the length positions of points k and l respectively at the j-th width position of the steel plate; h kj and h lj w1 represents the outline height of the kth and lth points at the jth width position of the steel plate, respectively; w2 represents the specified length range.

[0075] The above scheme employs a sliding window differential algorithm, dynamically adjusting the calculation window by setting a length threshold, effectively suppressing instantaneous signal fluctuations caused by the shedding of iron oxide scale from the steel plate surface. This model significantly improves the accuracy of identifying periodic wavy defects. Furthermore, the regional evaluation mechanism makes the defect weight allocation between the central and edge regions more scientific, conforming to the actual process characteristics of edge thinning during medium-thick plate rolling.

[0076] S103. The target steel plate is evaluated based on the transverse arc characteristic value and the unevenness characteristic value to obtain the plate shape evaluation result.

[0077] Specifically, the transverse arc characteristic values ​​(divided into head, middle, and tail) and the unevenness characteristic values ​​(divided into left, center, and right) are mapped by region, and then threshold judgment is performed to locate and classify defects: For regions with excessive transverse arc, if the transverse arc at the head is too large, it may be due to a large temperature gradient in the early stage of rolling; if the tail exceeds the standard, it is related to tension fluctuations in the late stage of rolling. For regions with excessive unevenness, if the unevenness on the left side is abnormal, it may be caused by roll wear or uneven distribution of cooling water; if the center region exceeds the standard, it may reflect a problem with the roll gap control of the mill. Then, the plate shape evaluation result is determined: if the characteristic values ​​of all regions are within the threshold, the steel plate can directly enter the next process; if there is a slight local exceedance (such as a slightly high transverse arc in the middle), it is recommended to optimize the rolling parameters (such as adjusting the bending roll force or roll preheating time); if there are serious exceedances in multiple regions (such as edge waviness + transverse arc exceedance), it is necessary to trigger the temperature straightening process or manual intervention for re-inspection.

[0078] Based on the above scheme, the regional distribution characteristics of transverse arc and unevenness are comprehensively considered to generate and output plate shape quality assessment results; downstream process control instructions are triggered according to the assessment results. By constructing a multi-dimensional regionalized evaluation system, the technical limitations of the traditional single-point measurement mode are overcome. This method utilizes the global perception characteristics of machine vision to divide the steel plate into three axial regions with process characteristics. By calculating the transverse arc and unevenness in each region, spatial positioning and quantitative characterization of plate shape defects are achieved. A dynamic correlation model between plate shape defects and production process parameters is established, providing a traceable data foundation for subsequent straightening process parameter optimization. Compared with manual measurement, this method improves detection efficiency while ensuring measurement accuracy, and avoids the problems of missed detections and misjudgments caused by human factors.

[0079] In one embodiment, the method further includes:

[0080] Establish a process parameter database, wherein the process parameter database includes temperature field distribution, rolling torque and cooling rate;

[0081] A plate shape defect prediction model is constructed based on the aforementioned process parameter database.

[0082] For example, this application establishes a database of process parameters including temperature field distribution, rolling torque, and cooling rate, and constructs a plate shape defect prediction model through machine learning algorithms.

[0083] Specifically, the aforementioned process parameter database adopts a hierarchical modular architecture, containing the following core fields: The temperature field distribution is determined by real-time acquisition and recording of the strip surface temperature matrix during rolling using an infrared thermal imager. The rolling torque is acquired by a PLC system at a preset sampling frequency, including parameters such as main motor torque and work roll torque. The cooling rate is recorded according to cooling zones (e.g., laminar flow cooling zone, ultra-fast cooling zone), recording water pressure, flow rate, nozzle opening, and strip temperature drop curves, stored as time-series data. Multi-source data fusion and data cleaning are performed on the above data to achieve standardized storage.

[0084] Furthermore, the input layer of the above model includes process parameters such as temperature field distribution, rolling torque, and cooling rate. Using a thermo-coupled finite element model as the physical engine, the temperature-stress field distribution is calculated, and a Transformer-GRU network is used to capture temporal dependencies. A self-attention mechanism is then used to identify abrupt changes in key process parameters. The output layer is then determined to be: defect type classification and quantitative indicators. Based on the above process parameter database, multi-source data fusion (such as temperature field, rolling torque, and cooling rate) solves the problem of scattered traditional process data. Combined with the plate shape defect prediction model, the prediction accuracy and real-time control capability are significantly improved, promoting the transformation of cold-rolled plate shape prediction from experience-based judgment to data-driven judgment.

[0085] Based on the above scheme, process parameters and plate shape quality data are deeply correlated, and neural network algorithms are used to uncover the implicit process-quality mapping relationship. This predictive model significantly improves the accuracy of early warning for abnormal plate shapes, and compared to traditional PID (Proportional Integral Derivative) control methods, it can issue corrective commands earlier, effectively reducing the scrap rate. Simultaneously, the established process parameter database provides quantifiable decision support for production line process optimization.

[0086] In one embodiment, the method further includes:

[0087] The measurement data of the target steel plate are corrected in real time using a Kalman filter algorithm.

[0088] For example, Kalman filtering is an optimal estimation algorithm based on a system dynamic model and sensor measurement data, which achieves real-time correction of noise data through a prediction-update loop. In steel plate measurement scenarios, laser scanners or line scan cameras may introduce high-frequency noise due to mechanical vibration, environmental temperature drift, or electromagnetic interference. Kalman filtering suppresses invalid noise and preserves the true contour signal by dynamically adjusting the Kalman gain.

[0089] Based on the above scheme, the measurement data is corrected in real time using a Kalman filter algorithm, effectively suppressing measurement noise caused by factors such as equipment vibration and temperature drift. After Kalman filtering, the root mean square error of the transverse arc measurement value is reduced, and the stability of unevenness measurement is improved.

[0090] For example, the data monitoring system for the target steel plate provided in this application includes: a laser projection unit configured with a semiconductor laser with a wavelength of 830nm; an imaging unit using a global shutter CMOS (Complementary Metal Oxide Semiconductor) sensor with a frame rate ≥120fps; and a data processing unit equipped with an FPGA (Field Programmable Gate Array Accelerator Card) to realize real-time image processing.

[0091] The above configuration, through multispectral collaborative design, solves the problem of interference from the oxide layer on the measurement signal of medium-thick plates. Actual measurement data shows that the system maintains a measurement accuracy of 0.05 mm even under ambient light intensity variations of ±500 lux. The FPGA parallel computing architecture reduces the data processing time for a single scan to less than 50 ms, meeting the online inspection requirements of high-speed production lines.

[0092] Through the implementation of the above technologies, refined evaluation of the shape of medium and heavy plates is achieved by region. The system can automatically calculate the transverse arc in the width direction and the unevenness in the length direction of the entire steel plate. Compared to manual measurement, it provides a comprehensive understanding of the unevenness distribution of the entire steel plate. The entire process is automated, with measurement and recording completed automatically without manual intervention. This high efficiency, reliability, and comprehensive sensing reduce the labor intensity and errors of manual measurement, significantly improving the automation, digitization, and intelligence level of medium and heavy plate shape measurement. This technology is widely applicable to the automatic shape detection and analysis of medium and heavy plate production lines, providing essential data support for shape monitoring, control, and optimization.

[0093] By employing the aforementioned technical solution and constructing a multi-dimensional regionalized evaluation system, the limitations of traditional single-point measurement methods are overcome. This method utilizes the global perception characteristics of machine vision to calculate lateral arcs and unevenness in different regions, achieving spatial localization and quantitative characterization of plate shape defects. A dynamic correlation model between plate shape defects and production process parameters is established, providing a traceable data foundation for subsequent optimization of straightening process parameters. Compared to manual measurement, this method improves detection efficiency while ensuring measurement accuracy and avoids the problems of missed detections and misjudgments caused by human factors.

[0094] The following are specific embodiments of the implementation of this application:

[0095] Example 1

[0096] The above technology was used to realize online detection and diagnosis of plate shape on a medium-thick plate production line, where w1 and w2 are both 2m. Figure 3 and Figure 4 The image shown is a cloud map of the shape detection results for two steel plates. Figure 3 and Figure 4 The X-axis is used to characterize the width of the steel plate. The negative value area (-1038mm to 0mm) is the area to the left of the center line of the steel plate, and the positive value area (0mm to 1038mm) is the area to the right of the center line of the steel plate. The Y-axis is used to characterize the length of the steel plate, from the head (starting end) to the tail (ending end). The area on the west side of the roller conveyor, with the center line of the roller conveyor as the reference, facing the west direction of the steel plate conveying, corresponds to the negative value area of ​​the X-axis in the plate shape detection cloud map. The area on the east side of the roller conveyor, with the center line of the roller conveyor as the reference, facing the east direction of the steel plate conveying, corresponds to the positive value area of ​​the X-axis in the plate shape detection cloud map.

[0097] Table 1 shows the results of transverse arc and unevenness. The results show that the shape of steel plate 1 is better than that of steel plate 2, while the shape of steel plate 2 is relatively poor in the head area, which is consistent with the results of the comparison with the actual object.

[0098] Table 1. Results of Plate Shape Testing for Medium-Thick Plates on a Certain Production Line

[0099]

[0100]

[0101] Example 2

[0102] The above technology was implemented after the cooling bed and before the temperature straightening machine on the 4300 medium and heavy plate production line of a steel plant. This enabled real-time online detection of the plate shape, which can replace manual measurement. A process specification was also established, as shown in Table 2, which is the plate shape detection process standard. When the plate shape defect exceeds the standard, an alarm is triggered to remind the operator to use temperature straightening to straighten the plate. If the defect does not exceed the standard, temperature straightening is not performed. This provides guidance for the downstream straightening process and avoids the risk of human misjudgment and omission.

[0103] Table 2 Plate Shape Inspection Process Standards

[0104] Judgment criteria ≤30mm ≤30mm ≤30mm Defect location West side unevenness Central unevenness East side unevenness Judgment criteria ≤30mm ≤30mm ≤30mm

[0105] Figure 5 The diagram shows the downstream process flow chart for medium and heavy plate shape inspection. Specifically, the above-mentioned online inspection of medium and heavy plate shape is first performed to determine whether the plate shape "exceeds the plate shape defect standard". The above-mentioned plate shape defect standard is determined based on the threshold in the process parameter database. If the plate shape defect exceeds the allowable range, the temperature straightening process is triggered. If the plate shape is qualified, the steel plate directly enters the next process (such as cutting or coiling).

[0106] Understandably, upon entering the process decision-making end box, if temperature correction is required, the temperature correction process and parameters will be optimized; if temperature correction is not required, the qualified plate shape data will be stored in the database for model training and quality traceability.

[0107] Furthermore, as a response to the above Figure 1 In addition to the method shown, this embodiment of the invention also provides a steel plate shape detection device for detecting the shape of the aforementioned steel plate. Figure 1 The method shown is implemented accordingly. This device embodiment corresponds to the foregoing method embodiment. For ease of reading, this device embodiment will not repeat the details of the foregoing method embodiment, but it should be clear that the device in this embodiment can implement all the contents of the foregoing method embodiment. Figure 6 As shown, the device includes: a determining unit 21, an acquiring unit 22, and a calculating unit 23, wherein...

[0108] Determining unit 21 is used to determine the target steel plate, wherein the target steel plate is a medium-thick plate;

[0109] Acquisition unit 22 is used to acquire the transverse arc characteristic value and unevenness characteristic value of the target steel plate;

[0110] The calculation unit 23 is used to evaluate the plate shape of the target steel plate based on the transverse arc characteristic value and the unevenness characteristic value, so as to obtain the plate shape evaluation result.

[0111] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and by adjusting kernel parameters, a method for detecting the shape of steel plates can be implemented. This method addresses the current problem that steel plate shape detection relies too heavily on manual labor and yields inaccurate measurement results.

[0112] This invention provides a computer-readable storage medium including a stored program that, when executed by a processor, implements a method for detecting the shape of a steel plate.

[0113] This invention provides a processor for running a program, wherein the program executes a method for detecting the shape of a steel plate.

[0114] This invention provides an electronic device, which includes at least one processor and at least one memory connected to the processor; wherein the processor is used to call program instructions in the memory to execute the steel plate shape detection method described above.

[0115] This invention provides an electronic device 30, such as... Figure 7 As shown, the electronic device includes at least one processor 301, and at least one memory 302 and bus 303 connected to the processor; wherein, the processor 301 and the memory 302 communicate with each other through the bus 303; the processor 301 is used to call program instructions in the memory to execute the above-mentioned steel plate shape detection method.

[0116] The smart electronic devices mentioned in this article can be PCs, tablets, mobile phones, etc.

[0117] This application also provides a computer program product that, when executed on a process management electronic device, is suitable for executing a program that initializes the plate shape detection method steps for the aforementioned steel plate.

[0118] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0119] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0120] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0121] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0122] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0123] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to perform actions such as... Figure 1 The control flow of the memory in the corresponding embodiment.

[0124] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0125] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0126] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0127] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0128] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0129] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0130] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for detecting the shape of a steel plate, characterized in that, include: The target steel plate is identified, wherein the target steel plate is a medium-thick plate; Obtain the transverse arc characteristic value and unevenness characteristic value of the target steel plate; The plate shape of the target steel plate is evaluated based on the transverse arc characteristic value and the unevenness characteristic value to obtain the plate shape evaluation result; The process of obtaining the transverse arc characteristic value and unevenness characteristic value of the target steel plate includes: Obtain the first contour data of the target steel plate surface along the length direction; Based on the first preset standard, the target steel plate is divided into regions according to the first contour data to determine the head region, middle region and tail region of the target steel plate; Determine the transverse arc feature values ​​corresponding to the head region, the middle region, and the tail region of the target steel plate, respectively; The step of determining the lateral arc feature values ​​corresponding to the head region, the middle region, and the tail region includes: The lateral arc characteristic value is determined based on the following formula: in, H i For the first i The lateral arc characteristic value of each region i The value range is 1 to 3, where 1 represents the head region of the steel plate, 2 represents the middle region of the steel plate, and 3 represents the tail region of the steel plate. L i Indicates the length direction. i A set of subscripts for each region; j Indicates the number of the length direction i The subscript of the location of the region; p jk and p jl They represent the steel plate number 1 and 2 respectively. j The first length position k , l The width coordinates of the point; h jk and h jl They represent the steel plate number 1 and 2 respectively. j The first length position k , l The height of the point's outline; w 1 indicates a specified width range; Establish a process parameter database, wherein the process parameter database includes temperature field distribution, rolling torque and cooling rate; A plate shape defect prediction model is constructed based on the process parameter database. The plate shape defect prediction model is used to input temperature field distribution, rolling torque and cooling rate, and output defect type classification and quantitative index.

2. The method according to claim 1, characterized in that, The process of obtaining the transverse arc characteristic value and unevenness characteristic value of the target steel plate includes: Obtain the second contour data of the target steel plate surface along the width direction; Based on the second preset standard, the target steel plate is divided into regions according to the second contour data to determine the left side region, the center region and the right side region of the target steel plate; Determine the unevenness characteristic values ​​corresponding to the left side region, the center region, and the right side region of the target steel plate, respectively.

3. The method according to claim 2, characterized in that, Determining the unevenness feature values ​​corresponding to the left region, the central region, and the right region respectively includes: The roughness characteristic value is determined based on the following formula: in, U i For the first i The unevenness of each area i The value range is 1 to 3, where 1 represents the left side of the steel plate, 2 represents the center of the steel plate, and 3 represents the right side of the steel plate. W i Indicates the width direction. i A set of subscripts for each region; j Indicates belonging to the width direction. i The subscript of the location of the region; p kj and p lj They represent the steel plate number 1 and 2 respectively. j The first width position k , l The length and position of the point; h kj and h lj They represent the steel plate number 1 and 2 respectively. j The first width position k , l The height of the point's outline; w 2 indicates the specified length range.

4. The method according to claim 1, characterized in that, Also includes: The measurement data of the target steel plate are corrected in real time using a Kalman filter algorithm.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed by a processor, it implements the steps of the plate shape detection method for a steel plate as described in any one of claims 1 to 4.

6. An electronic device, characterized in that, The electronic device includes at least one processor and at least one memory connected to the processor; wherein the processor is configured to call program instructions in the memory to execute the steps of the steel plate shape detection method as described in any one of claims 1 to 4.

Images