Shearing system for rectangular shearing section

Abstract

The invention relates to the field of shearing equipment, in particular to a shearing system for a rectangular shearing section. Comprising a shearing knife, a shearing base, a driving part and a controller. The shear knife is connected with the base in a hinged mode, and a telescopic positioning block is arranged on the base. The driving component drives the shear knife to shear at a preset speed, and the blade is divided into a plurality of wear evaluation areas. If the power output curve of the driving part locally fluctuates in the cut-in stage, the fluctuation judgment time and the cut-in cut-off position of the shear knife are determined. And forming a power curve prediction vector according to the wear matrix M and cut target hardness information, and inputting the power curve prediction vector into a deep learning model to generate a comparison power output curve. And if the similarity between the comparison curve and the local fluctuation area power curve is lower than a threshold value, outputting data error reporting information. Through assistance of the historical wear value and hardness information, the prediction accuracy of the shear power output curve is improved, and then the accuracy of blade wear degree judgment is improved.

Description

Technical Field

[0001] The present invention relates to the field of shearing equipment, in particular to a shearing system for rectangular shearing sections. Background Art

[0002] Shearing is a fundamental manufacturing technology widely used in industries such as metalworking, textile manufacturing, and paper processing. Its primary purpose is to separate or divide materials into predetermined sizes and shapes by applying external forces. This process can be categorized into various types, including but not limited to mechanical shearing, laser shearing, and water jet cutting. Each method has its own specific application scenarios and technical characteristics.

[0003] Mechanical shearing is one of the most traditional shearing methods, and usually uses a pair of relatively moving cutting tools (upper and lower blades or upper and blade holders) to achieve material cutting. This method is applicable to various forms of materials such as plates and block materials, and is generally more suitable for shearing materials with regular shapes. At the same time, with the increase in the number of cuts and the differences in hardness and size of different sheared materials, the degree of wear of the blade in different areas of the shear knife will usually be different. In the related art, the power output curve of the driving component that drives the shear knife to move is used to timely determine the degree of wear of the blade of the shear knife, so as to avoid using the blade in the excessively worn area for shearing as much as possible. However, in the process of collecting the output power of the driving component, there will often be abnormalities in the collection of some data due to problems such as the data collection sensor. This part of the data will affect the accuracy of the judgment of the degree of wear of the blade. Summary of the Invention

[0004] In order to solve one of the above technical problems, the present invention adopts the following technical solution: According to one aspect of the present invention, there is provided a shearing system for rectangular shearing sections, the system comprising: a shearing blade, a shearing base, a driving component and a controller; One end of the shear blade is hingedly connected to the shear base, and a plurality of retractable positioning blocks are provided on the shear base at intervals along the extension direction of the shear blade; a driving component is connected to the shear blade to drive the shear blade to cut at a preset shearing speed; the shear blade is divided into a plurality of wear evaluation zones along the extension direction of the blade; the driving component is in communication with the controller; the shearing cross-section of the target to be cut is a rectangle; The controller is used to perform the following steps: If the power output curve of the driving component corresponding to the cutting stage has a local fluctuation greater than a threshold, the time corresponding to the maximum power in the local fluctuation is used as the fluctuation determination time; the cutting stage is the period from the time when the shearing knife contacts the first corner of the cut target to the time when the shearing knife contacts the second corner of the cut target; the first corner and the second corner of the cut target are respectively the upper corner of the side close to the positioning block and the upper corner of the side away from the positioning block in the rectangular shearing section when the cut target is in the shearing station; The cutting end position of the shearing knife is determined at the fluctuation determination time according to the fluctuation determination time, the contact time t1 of the shearing knife and the first corner of the cut object, the distance L between the positioning surface of the positioning block and the hinge point of the shearing knife, and the preset shearing speed; Based on the wear matrix M corresponding to the shear cutter, the historical wear values corresponding to the multiple wear evaluation zones adjacent to and preceding the wear evaluation zone at the cut-off position, and the hardness information of the cut object, a power curve prediction vector is generated. The power curve prediction vector is used to represent the characteristics that affect the power output of the drive component during this shearing process. ; Among them, a ji is the wear value corresponding to the i-th wear evaluation zone after the j-th shearing, z is the total number of wear evaluation zones divided on the shearing knife, i=1, 2…z; m is the total number of current shearing times; j=1, 2…m; The power curve prediction vector is input into the second target deep learning model to generate a comparison power output curve; the comparison power output curve is the predicted power output curve corresponding to the local fluctuation interval to which the fluctuation determination time belongs in this shearing; If the similarity between the compared power output curve and the power output curve of the local fluctuation area is less than the similarity threshold, a power acquisition data error message is generated.

[0005] The present invention has at least one of the following beneficial effects: In the present invention, a comparison power output curve is generated by using multiple columns of historical wear values corresponding to the local fluctuation region in the wear matrix M and the hardness information of the cut object. Because the input data includes multiple columns of historical wear values and the hardness information of the cut object, the power output curve for the current cutting process can be more accurately predicted. The predicted power output curve (i.e., the comparison power output curve) is then compared with the power output curve of the local fluctuation region for similarity. Ultimately, it is determined whether the power output curve in the local fluctuation region is caused by an abnormality in the data acquisition sensor. This re-verification of the data improves the accuracy of determining the degree of wear on the blade. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0007] Figure 1 A flowchart of steps executed by a controller in an articulated shearing system provided by an embodiment of the present invention; Figure 2 A schematic diagram of the structure of the shearing system provided by an embodiment of the present invention when performing a shearing operation; Figure 3 A flowchart of steps executed by a controller in a shearing system for rectangular shearing sections provided by an embodiment of the present invention.

[0008] Reference numerals: 1. Shear blade; 2. Target to be cut; 3. Shear base; 4. Indicator light; 5. Positioning block. DETAILED DESCRIPTION

[0009] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0010] As a possible embodiment of the present invention, Figure 1 As shown, an articulated shearing system is also provided, which includes: a shearing knife 1, a shearing base 3, a driving component and a controller.

[0011] like Figure 2As shown, one end of the shear blade 1 is hinged to the shear base 3, and a plurality of retractable positioning blocks 5 are arranged at intervals on the shear base 3 along the extension direction of the shear blade 1. The driving component is connected to the shear blade 1, and is used to drive the shear blade 1 to shear according to the preset shearing speed. The driving component is a hydraulic driving component, such as a hydraulic cylinder or a hydraulic motor. This design makes the drive more stable and powerful, and can meet the force required for shearing different materials. The shear blade 1 is divided into a plurality of wear evaluation areas along the extension direction of the blade. A plurality of indicator lights 4 are provided on the shear base 3 along the extension direction of the shear blade 1, and each wear evaluation area corresponds to at least one indicator light 4. The driving component and the controller are communicatively connected. The shear blade 1 is divided into a plurality of wear evaluation areas along the extension direction of the blade, so as to accurately evaluate the wear condition of each area. The position of the indicator light 4 corresponds to the wear evaluation area, and the degree of wear of the blade can be explicitly indicated by the change in color displayed by the indicator light 4. The driving component and the controller are communicatively connected, and the controller can accurately obtain various data of the driving component.

[0012] The controller is used to perform the following steps: S100: Based on the power output curve of the drive component, the preset shearing speed, and the position information of the positioning block 5, the power impact curve information corresponding to each wear evaluation zone after the current shearing is extracted from the power output curve. The power impact curve information is the power output curve of the corresponding wear evaluation zone from the time it contacts the cut object 2 to the end of the current shearing.

[0013] Specifically, when the target is sheared, the cut cross-section of the target 2 is rectangular. In this embodiment, the target can be made of metal. Of course, the target 2 can also be made of other bulk materials besides metal, such as various types of plates made of polymer organic materials, or thicker fabrics such as hard felt.

[0014] Often, when cutting materials of varying materials, the degree of wear on the blade varies due to the varying types and hardness of the materials being cut. Furthermore, in this scenario, the types of materials being cut are complex and varied. Obtaining hardness information for each material requires specialized tools for testing, which is time-consuming and slows down processing. Therefore, in this embodiment, instead of directly measuring the hardness of each material being cut, the power output curve of the drive component is used to obtain wear information for different wear evaluation areas on the blade after each cutting operation.

[0015] Specifically, S100 includes: S101: Based on the contact time t1 between the shear blade 1 and the first corner of the object 2 being cut, the contact time t2 between the second corner and the distance L between the positioning surface of the positioning block 5 and the hinge point of the shear blade 1 in the power output curve, the initial wear point information W1 and the final wear point information W2 of the shear blade 1 corresponding to the current shearing are determined. The first corner and the second corner of the object 2 being cut are the upper corners of the side close to the positioning block 5 and the upper corners of the side away from the positioning block 5, respectively, in the rectangular shearing cross section of the object 2 when the object 2 is in the shearing station. In this embodiment, when the object 2 is in the shearing station, it is located within the angle space formed by the shear blade 1 and the shear base 3. During the shear blade's cutting process, the shear blade 1 contacts the first corner and the second corner of the object 2 one after another. If the side close to the positioning block 5 is considered left in the horizontal direction and the side away from the positioning block 5 is considered right in the horizontal direction, then the first corner and the second corner are the upper left corner and the upper right corner, respectively, of the rectangular shearing cross section of the object 2 when the object 2 is in the shearing station.

[0016] ; .

[0017] Among them, α t1 and α t2 The included angles between the shear blade 1 and the shear base 3 at t1 and t2 respectively. L×tanα t1 is the thickness of the cut object 2.

[0018] In this embodiment, the shear blade 1 cuts the material to be cut at a constant shearing speed, and the initial position of the shear blade 1 is fixed. Therefore, once the current movement time of the shear blade 1 is known, the angle between the current shear blade 1 and the shear base 3 can be calculated based on the rotation angular velocity of the shear blade 1 and the corresponding time. Based on this, the right triangle formed by the blade, the material to be cut, and the shear base 3 can be calculated, as shown in FIG. Figure 2 As shown, W1 and W2 are calculated by corresponding trigonometric functions.

[0019] During each shearing process, shear blade 1 first rotates at a constant speed from its initial position toward shear base 3. Before contacting the first corner of the object 2 being cut, the drive component only needs to maintain the uniform motion of shear blade 1 at a constant power, so the power value at this time is almost constant. However, when shear blade 1 contacts the first corner of the object 2, the output power of the drive component increases instantaneously due to the obstruction of the object 2 on shear blade 1, resulting in a slight increase in power. This is because it needs to overcome slight resistance such as the roughness of the metal surface and the oxide layer. This section of the curve shows a slight upward slope.

[0020] Cutting-in stage: As the cutter gradually presses into the metal, power consumption increases rapidly. This is because a greater force is needed to overcome the elastic deformation and plastic deformation of the metal material. This part of the curve will rise rapidly, forming a steeper slope and reaching the power peak of the entire process. In this stage, the rapid increase in power is because the area of metal contacted by the shear blade gradually increases during the shearing process. At the same time, since the shearing cross-section of the target 2 to be cut is rectangular in this embodiment, when the shear blade 1 contacts the second corner of the target 2 to be cut, the area of contact between the shear blade 1 and the target 2 to be cut will no longer increase significantly. Therefore, usually this stage of rapid power rise will tend to stabilize when the shear blade 1 cuts the second corner of the target 2 to be cut, and will no longer increase at a steeper slope. Therefore, based on the rhythmic change characteristics of the power in this stage, using existing recognition methods or manual recognition methods, t1 and t2 can be clearly determined from the power output curve.

[0021] Stable Shear Phase: Once the cutter fully penetrates the metal, the shearing process begins. During this phase, power consumption may remain relatively stable or experience only minor fluctuations. This depends on factors such as the material's hardness and thickness. During this period, the curve tends to be flat or experience slight fluctuations.

[0022] Final shearing stage: As shearing nears completion, the remaining uncut portion becomes thinner, the material's ability to resist shearing weakens, and the required force decreases, resulting in a decrease in power consumption. The curve shows a downward trend in this stage.

[0023] S102: Based on W1 and W2, determine the power cutoff time corresponding to each wear evaluation zone of the shear blade 1 during this shearing process. The power cutoff time tn corresponding to the nth wear evaluation zone satisfies the following conditions: ; Among them, △L n is the distance between the evaluation point of the nth wear evaluation zone and W1. The evaluation point is a preset point used to indicate the location of the wear evaluation zone. In this shearing operation, the evaluation point of the first wear evaluation zone where shear blade 1 is worn is the location corresponding to W1. The evaluation point of the last wear evaluation zone is the location corresponding to W2. The evaluation point of the middle wear evaluation zone is the middle point of the wear evaluation zone itself. W is the angular velocity of shear blade 1.

[0024] S103: According to the power interception time corresponding to the wear evaluation area, select the power output curve in the section after the corresponding power interception time from the power output curve as the power impact curve information corresponding to the wear evaluation area.

[0025] S200: All power impact curve information corresponding to this shearing is formed into a wear judgment vector and input into the first target deep learning model to generate the wear value corresponding to each wear evaluation area after this shearing.

[0026] Specifically, a power output point sequence corresponding to each wear evaluation area is obtained from the power influence curve according to a preset interval to form a wear evaluation vector.

[0027] The first target deep learning model can be an LSTM model and / or a CNN model.

[0028] The power output curve reflects the actual energy consumption changes of the drive components during the shearing process. Specifically, when the shear blade 1 contacts the object 2, the drive components need to provide additional power to overcome resistance due to factors such as the hardness and thickness of the material, resulting in a significant change in the power output curve.

[0029] This power variation information reflects the actual stress and wear conditions in different areas of shear blade 1 during the shearing process. By capturing the power impact curve information corresponding to each wear evaluation zone after each shearing operation, the power output characteristics corresponding to each wear evaluation zone can be more accurately matched. By combining the power output characteristics corresponding to all wear evaluation zones, a wear evaluation vector is formed, which can more accurately capture the energy consumption characteristics of each wear evaluation zone during the shearing process.

[0030] These wear evaluation vectors are then fed into a primary deep learning model (such as an LSTM (long short-term memory) network model and / or a CNN (convolutional neural network) model). By learning from a large amount of historical data, the model can identify the complex, nonlinear relationship between different power impact curves and wear severity. Therefore, the model can generate corresponding wear values based on the power impact curve information for each wear evaluation zone during the current shearing operation, thereby accurately assessing the wear severity of each wear evaluation zone.

[0031] The LSTM model effectively captures dependencies within long time series. In a shearing system, the power impact curve generated by each shearing operation can be considered a time series. By learning from this time series data, the LSTM model can identify the complex relationship between different power impact curves and wear levels, thereby generating corresponding wear values.

[0032] CNN models excel at feature extraction. In shear systems, the power impact curve information can be viewed as a one-dimensional signal. CNN models automatically extract key features from these signals through convolutional layers and reduce the data dimension through pooling layers, ultimately generating wear values.

[0033] In addition to using LSTM and CNN models independently, you can also combine CNN and LSTM models. For example, a CNN model can perform preliminary feature extraction on time series data to form a continuous sequence with more obvious features, which is then input into an LSTM model for final prediction.

[0034] In addition, in order to make the evaluation vector more clearly reflect the characteristics of wear, the wear evaluation vector may further include: the thickness value of the cut object 2, the shearing speed, and the duration of the power influence curve corresponding to each wear evaluation area.

[0035] At the same time, in order to obtain more effective information, the output value of the first target deep learning model can also include the hardness information of the cut target 2.

[0036] The above-mentioned format setting of the evaluation vector and the setting of the final output information can be achieved by setting training data of corresponding formats during the training phase.

[0037] S300: Generate a wear matrix M corresponding to the current shearing blade 1 according to the wear value corresponding to each wear evaluation area after each shearing.

[0038] ; Among them, a ji is the wear value corresponding to the i-th wear evaluation zone after the j-th shearing, z is the total number of wear evaluation zones divided on the shearing knife, i = 1, 2…z; m is the total number of current shearing times; j = 1, 2…m.

[0039] S400: If the cumulative sum of the wear values in any column in M is greater than a preset threshold, then generate wear warning information for the wear assessment area corresponding to the column.

[0040] The cumulative sum of the wear values in each column of M represents the current total wear level of the corresponding wear assessment area. Based on the cumulative values of each column, the wear level of each area of the blade can be assessed, and corresponding wear warning information can be generated to prompt the staff to replace the shear blade 1 or reposition the object 2 in a timely manner. This allows the blade in the less worn area to be used for shearing as much as possible, reducing the energy consumption of the shearing system.

[0041] In addition, the controller is also used to perform the following steps: S500: If the cumulative sum of the wear values of the wear assessment area corresponding to the column in M is greater than a preset threshold, the indicator light 4 corresponding to the wear assessment area displays a preset warning color.

[0042] In the embodiment, the arrangement of the indicator lights 4 is consistent with the extension direction of the blade. Therefore, when the display color of the indicator lights 4 in a certain area changes to a preset warning color, such as red, it indicates that the degree of wear of the blade corresponding to the area is too great.

[0043] Based on this, the object 2 to be cut can be placed in an area where the indicator light 4 displays a non-warning color. Specifically, in this embodiment, since multiple retractable positioning blocks 5 are provided on the cutter base, the positioning blocks 5 at corresponding positions can be raised according to the different colors displayed by the indicator light 4 to position the object 2 to be cut. This allows the object 2 to be placed in different positions, and the blade with less wear is used as much as possible for cutting, thereby reducing energy consumption during the cutting process.

[0044] As another possible embodiment of the present invention, the controller is further configured to perform the following steps: S310: Generate a contact power sequence corresponding to the current shearing operation based on the power output curve corresponding to the time interval [t1, t1+ΔT] in the power output curve. The contact power sequence is composed of multiple power scatter point values in the power output curve corresponding to [t1, t1+ΔT]. For example, the multiple power scatter point values can be obtained from the power output curve according to a preset collection interval. ΔT is a preset time interval. ΔT can be 1 second.

[0045] S320: Input the contact power sequence into the target binary classification model to generate the type of the first corner of the cut target 2 in the current shearing operation. The type of the first corner is a sharp corner or a chamfer.

[0046] When the first corner of the target being cut is sharp, the power curve may show a significant instantaneous peak, followed by a rapid drop, and may fluctuate somewhat throughout the process. This phenomenon is due to the small contact area at the sharp corner, which leads to increased local stress and, in turn, requires greater force to complete the shearing action. Once the cut is made, the local stress decreases rapidly, and because the material has a strong resistance to shearing, some discontinuities or fluctuations in the power output may be observed.

[0047] When the first corner of the cut object 2 is a straight angle, because the contact area is larger, high local stress is not immediately generated. The power curve tends to rise gently to a stable value and show less fluctuation throughout the shearing process. This is because the straight angle provides a larger contact area, allowing the force to be more evenly distributed over a larger area.

[0048] Based on the power variation characteristics under these different shearing conditions, the contact power sequence can be analyzed (e.g., through clustering or classification) to accurately identify the corner type of target 2. This power variation characteristic is typically most pronounced within the first few seconds after shear blade 1 makes contact with the first corner of target 2. Therefore, based on the power output curve corresponding to [t1, t1+△T], the system can quickly determine the corner type of target 2.

[0049] S330: Generate a hardness value of the cut object 2 according to the power output curve corresponding to the time interval [t1, t2] in the power output curve.

[0050] S330: Includes: S331: Generate a hardness value of the cut object 2 according to the power increase slope of the power output curve corresponding to [t1, t2].

[0051] Specifically, changes in the power output curve during the shearing process can reflect the material's characteristics. As shear blade 1 cuts into target 2, the drive component needs to provide additional power to overcome resistance due to varying material hardness, resulting in significant changes in the power output curve. Because the slope of the power increase directly reflects the material's resistance to shear force, it can be used to assess the material's hardness. By analyzing the slope of the power output curve during the time interval [t1, t2], the hardness of target 2 can be inferred. For example, a machine learning model can be used to generate hardness values.

[0052] S340: Based on the hardness of the object 2 being cut and the type of the first corner, a wear adjustment coefficient for the first wear assessment area of the shear blade 1 that is subject to wear during the current shearing operation is obtained from a preset mapping table. The wear adjustment coefficient corresponding to the sharp corner is greater than the wear adjustment coefficient corresponding to the chamfer and is greater than one.

[0053] Because sharp corners can cause localized stress concentration during shearing, the cutting edge of shear blade 1 experiences greater impact and wear. Therefore, when setting the wear adjustment coefficient in the mapping table, it's necessary to further increase the wear value at sharp corners. Therefore, the wear adjustment coefficient for sharp corners will be greater than that for chamfered corners. For example, the wear adjustment coefficient for sharp corners can be set to 1.3, while the wear adjustment coefficient for chamfered corners can be set to 1.

[0054] S350: According to the wear adjustment coefficient, the wear value of the first wear evaluation area of the shearing blade 1 that is worn during the current shearing operation is adjusted.

[0055] The adjusted wear value of the first wear evaluation zone is substituted into the corresponding position in the wear matrix M for updating. This method more accurately reflects the actual wear condition of the shear blade 1 at the first contact point with the cut object 2 under different conditions of the cut object 2. For example, if the first corner of the cut object 2 in the current shearing operation is sharp, the wear value adjusted by the wear adjustment coefficient will be relatively large. After updating the wear matrix M, the cumulative sum of the wear values corresponding to this column will approach or exceed the preset threshold more quickly, prompting the system to issue wear warning information more promptly.

[0056] In addition to adjusting the wear value based on the angular type and hardness of the object being cut 2, the material properties of the object 2 can also be considered. Different materials wear the shear blade 1 differently during the shearing process. For example, brittle materials may cause the shear blade 1 to chip, while tougher materials may cause more uniform but greater wear. For different materials, the preset mapping table can be further refined to set a specific wear adjustment coefficient calculation method for each material, thereby further optimizing the assessment of the degree of wear on the shear blade 1.

[0057] As another possible embodiment of the present invention, Figure 3 As shown, a shearing system for rectangular shearing sections is also provided, and the hardware structure of the shearing system is exactly the same as that of the shearing system disclosed in the above embodiment.

[0058] The specific difference is that in this embodiment, the controller is also used to perform the following steps: S410: If the power output curve of the drive component corresponding to the cutting phase has a local fluctuation greater than a threshold, the time corresponding to the maximum power in the local fluctuation is used as the fluctuation determination time. The cutting phase is the period from the time when the shear blade 1 contacts the first corner of the cut object 2 (i.e., t1) to the time when the shear blade 1 contacts the second corner of the cut object 2 (i.e., t2).

[0059] S420: Determine the cutting end position of the shear knife 1 at the fluctuation determination time based on the fluctuation determination time, the contact time t1 between the shear knife 1 and the first corner of the cut target 2, the distance L between the positioning surface of the positioning block 5 and the hinge point of the shear knife 1, and the preset shearing speed.

[0060] Specifically, at the fluctuation determination time T p When the shear blade 1 cuts into the end position W P The following conditions must be met: Among them, α t1 is the angle between the shear blade 1 and the shear base 3 at time t1. W is the rotational angular velocity of the shear blade 1.

[0061] Usually in the cutting stage, the cutter contacts the upper plane of the target 2 to be cut and cuts. Each new cutting position in this stage is similar to an ice-breaking operation. Usually, the hardness of the position of the target 2 to be cut that the shearing knife 1 is currently in contact with will affect the power consumed by the cutter when cutting this position. Therefore, the hardness information of the shearing position can also be clearly reflected in the power curve. If the hardness of the current shearing position is significantly higher than the hardness of other positions, there may be a local fluctuation in the power output curve. Of course, sometimes the local fluctuations in the power curve may also be caused by abnormal data collection.

[0062] At the same time, during this process, it can be calculated based on the time and the shearing speed of the shearing knife 1 to which wear evaluation area of the shearing knife 1 the current cutting-in cut-off position (as shown in S420) corresponds. In this way, the wear value status of the shearing position corresponding to the local fluctuation area can be determined more accurately in M, and the foundation is also laid for the subsequent generation of the corresponding comparative power curve based on the historical wear value.

[0063] S430: Based on the wear matrix M corresponding to shear blade 1, the historical wear values corresponding to the wear evaluation zones preceding and following the wear evaluation zone corresponding to the cut-off position, and the hardness information of cut object 2, a power curve prediction vector is generated. The power curve prediction vector represents the characteristics that affect the power output of the drive component during this shearing process.

[0064] In this step, three wear evaluation areas adjacent to and before the wear evaluation area may be selected, and their corresponding historical wear values.

[0065] S440: Input the power curve prediction vector into the second target deep learning model to generate a comparison power output curve. The comparison power output curve is the predicted power output curve corresponding to the local fluctuation interval to which the fluctuation determination time belongs during the current shearing. The specific length of the predicted power output curve can be determined based on actual needs. For example, it can be the power output curve within a preset time period after the fluctuation determination time, the power output curve within a preset time period before the fluctuation determination time, or the power output curve within a preset time period before and after the fluctuation determination time, all of which time periods include the fluctuation determination time.

[0066] The second target deep learning model can be an LSTM model and / or a CNN model. The training method of the second target deep learning model can refer to the training process of the first target deep learning model. Since this process is all existing content, it will not be repeated here.

[0067] Since there are local fluctuations, this may be caused by abnormal data collection. Therefore, the wear values of each wear evaluation area corresponding to this shear obtained in M may be abnormal.

[0068] To more accurately predict the power curve for the local fluctuation area during this solution, the wear value obtained from this shearing process is no longer used when obtaining the wear value from M. Generally, wear is a gradual accumulation process, so the historical wear data of the corresponding area can more accurately reflect the degree of wear in the corresponding area on shear blade 1 before the current shearing process.

[0069] Then, combined with the hardness information of the cut target 2, the fluctuation characteristics of the power output curve during this solution process can be more clearly reflected, thereby ensuring the accuracy of the comparative power curve predicted by the second target learning model.

[0070] In this embodiment, the hardness information of the cut object 2 can be directly obtained, that is, the hardness information output by the first target deep learning model. In addition, since local fluctuations are rare, the hardness information can also be obtained through manual measurement.

[0071] S450: If the similarity between the compared power output curve and the power output curve of the local fluctuation area is less than a similarity threshold, a power acquisition data error message is generated.

[0072] The similarity between the power output curve and the power output curve of the local fluctuation area is obtained by the following steps: S451: Align the two curves according to the maximum output power value of the two curves.

[0073] S452: Use the preset length intervals before and after the maximum output power value as the comparison interval.

[0074] S453: Taking the Euclidean distance between the two curves in the comparison interval as the similarity between the two curves.

[0075] S460: If the similarity between the compared power output curve and the power output curve of the local fluctuation area is greater than the similarity threshold, power acquisition data verification pass information is generated.

[0076] In this embodiment, a comparison power output curve is generated by using multiple columns of historical wear values corresponding to the local fluctuation region in the wear matrix M and the hardness information of the cut object 2. Because the input data includes multiple columns of historical wear values and the hardness information of the cut object 2, the power output curve for the current cutting process can be more accurately predicted. The predicted power output curve (i.e., the comparison power output curve) is then compared with the power output curve of the local fluctuation region for similarity. Ultimately, a determination is made as to whether the power output curve in the local fluctuation region is caused by an abnormality in the data acquisition sensor. This re-verification of the data improves the accuracy of determining the degree of wear on the blade.

[0077] When a power acquisition data error message is generated, the system automatically triggers further processing. For example, it prompts the operator to check the power acquisition equipment for hardware failures, such as loose sensor connections or damaged data transmission lines. The system also records detailed error information, including the time of the error and the cutting task parameters at the time of the error (such as the material, hardness, and angle type of the object being cut), to facilitate subsequent analysis of the cause of the failure.

[0078] If the power data verification passes, the system can continue the normal cutting process and store the collected power data and various analysis results (such as wear and hardness values) as historical data. This historical data can be used to optimize subsequent prediction models, such as further training the first and second target deep learning models to achieve more accurate prediction results.

[0079] At the same time, considering that in actual production environments there may be various interference factors that affect the accuracy of power acquisition data, such as electromagnetic interference and ambient temperature changes, some anti-interference measures can be studied and implemented. For example, adding shielding devices to power acquisition sensors to reduce the impact of electromagnetic interference on data; installing temperature control devices around the equipment to maintain a relatively stable operating temperature of the acquisition equipment, thereby ensuring the reliability of power acquisition data.

[0080] Furthermore, although the steps of the method of the present disclosure are described in a particular order in the accompanying drawings, this does not require or imply that the steps must be performed in this particular order, or that all steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0081] Through the description of the above embodiments, it will be readily understood by those skilled in the art that the example embodiments described herein can be implemented via software or via a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or mobile hard drive) or on a network and includes several instructions for enabling a computing device (such as a personal computer, server, mobile terminal, or network device) to execute the methods according to the embodiments of the present disclosure.

[0082] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0083] Those skilled in the art will appreciate that various aspects of the present invention may be implemented as systems, methods, or program products. Therefore, various aspects of the present invention may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, microcode, etc.), or in a combination of hardware and software, collectively referred to herein as "circuits," "modules," or "systems."

[0084] The electronic device according to this embodiment of the present invention is merely an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0085] The electronic device is implemented as a general-purpose computing device. Components of the electronic device may include, but are not limited to, the at least one processor, the at least one memory, and a bus connecting different system components (including the memory and the processor).

[0086] The storage stores program codes, which can be executed by the processor, so that the processor executes the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification.

[0087] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read only memory (ROM).

[0088] The storage may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0089] The bus may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0090] The electronic device may also communicate with one or more external devices (e.g., a keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., a router, modem, etc.). This communication may occur via an input / output (I / O) interface. Furthermore, the electronic device may communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter. The network adapter communicates with other modules of the electronic device via a bus. It should be understood that, although not shown in the figures, other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0091] Through the description of the above embodiments, it will be readily understood by those skilled in the art that the example embodiments described herein can be implemented via software or via a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or mobile hard drive) or on a network and includes several instructions for enabling a computing device (such as a personal computer, server, terminal device, or network device) to execute the methods according to the embodiments of the present disclosure.

[0092] In exemplary embodiments of the present disclosure, a computer-readable storage medium is also provided, on which is stored a program product capable of implementing the methods described above. In some possible implementations, various aspects of the present invention may also be implemented in the form of a program product comprising program code that, when executed on a terminal device, causes the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the "Exemplary Methods" section above.

[0093] The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0094] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0095] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0096] Program code for performing the operations of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, and conventional procedural programming languages such as C or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0097] Furthermore, the above-described figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention and are not intended to be limiting. It is readily understood that the processes illustrated in the above-described figures do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0098] It should be noted that although several modules or units of the device for action execution are mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0099] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A shearing system for rectangular shear sections, characterized in that: The system includes: a shearing knife, a shearing base, a driving component and a controller; One end of the shearing blade is hingedly connected to the shearing base, and a plurality of retractable positioning blocks are arranged on the shearing base at intervals along the extension direction of the shearing blade; the driving component is connected to the shearing blade, and is used to drive the shearing blade to shear according to a preset shearing speed; the shearing blade is divided into a plurality of wear evaluation areas along the extension direction of the blade; the driving component is in communication with the controller; the shearing cross-section of the cut object is rectangular; The controller is used to perform the following steps: If the power output curve of the driving component corresponding to the cutting stage has a local fluctuation greater than a threshold, the time corresponding to the maximum power in the local fluctuation is used as the fluctuation determination time; the cutting stage is the period from the time when the shearing knife contacts the first corner of the cut target to the time when the shearing knife contacts the second corner of the cut target; the first corner and the second corner of the cut target are respectively the upper vertex angle on the side close to the positioning block and the upper vertex angle on the side away from the positioning block in the rectangular shearing section when the cut target is in the shearing station; The cutting end position of the shearing knife is determined at the fluctuation determination time according to the fluctuation determination time, the contact time t1 of the shearing knife and the first corner of the cut object, the distance L between the positioning surface of the positioning block and the hinge point of the shearing knife, and the preset shearing speed; Based on the wear matrix M corresponding to the shear cutter, the historical wear values corresponding to the multiple wear evaluation zones adjacent to and preceding the wear evaluation zone at the cut-off position, and the hardness information of the cut object, a power curve prediction vector is formed; the power curve prediction vector is used to represent the characteristics that affect the power output of the drive component during this shearing process; ; Among them, a ji is the wear value corresponding to the i-th wear evaluation zone after the j-th shearing, z is the total number of wear evaluation zones divided on the shearing knife, i=1, 2…z; m is the total number of current shearing times; j=1, 2…m; Inputting the power curve prediction vector into the second target deep learning model to generate a comparison power output curve; the comparison power output curve is the predicted power output curve corresponding to the local fluctuation interval to which the fluctuation determination time belongs in this shearing; If the similarity between the compared power output curve and the power output curve of the local fluctuation area is less than the similarity threshold, a power acquisition data error message is generated.

2. A shearing system for rectangular shearing sections according to claim 1, characterized in that: After generating the comparison power output curve, the controller is further configured to perform the following steps: If the similarity between the compared power output curve and the power output curve of the local fluctuation area is greater than the similarity threshold, power acquisition data verification pass information is generated.

3. A shearing system for rectangular shearing sections according to claim 1, characterized in that: Determine the cutting end position of the shear knife at the fluctuation determination time according to the fluctuation determination time, the contact time t1 of the shear knife and the first corner of the cut object, the distance L between the positioning surface of the positioning block and the shear knife hinge point, and the preset shearing speed; including: At the fluctuation determination time T p When the shear knife cuts into the end position W P The following conditions must be met: ; Among them, α t1 is the angle between the shear blade and the shear base at t1; W is the angular velocity of the shear blade.

4. A shearing system for rectangular shearing sections according to claim 3, characterized in that: The similarity between the power output curve and the power output curve of the local fluctuation area is obtained by the following steps: Align the two curves according to their maximum output power values; The preset length interval before and after the maximum output power value is used as the comparison interval; The Euclidean distance between the two curves in the comparison interval is used as the similarity of the two curves.

5. A shearing system for rectangular shearing sections according to claim 1, characterized in that: M is obtained as follows: Based on the power output curve of the driving component, the preset shearing speed, and the position information of the positioning block, the power impact curve information corresponding to each wear evaluation area after the current shearing is intercepted from the power output curve; the power impact curve information is the power output curve of the corresponding wear evaluation area from the time it just contacts the cut target to the end of the current shearing; All the power impact curve information corresponding to this shearing is converted into a wear judgment vector and input into the first target deep learning model to generate the wear value corresponding to each wear evaluation area after this shearing; According to the wear value corresponding to each wear evaluation area after each shearing, a wear matrix M corresponding to the current shearing knife is generated.

6. A shearing system for rectangular shearing sections according to claim 5, characterized in that: The wear evaluation vector also includes: the thickness value of the cut object, the shearing speed, and the duration of the power influence curve corresponding to each wear evaluation area.

7. A shearing system for rectangular shearing sections according to claim 5, characterized in that: The output value of the first target deep learning model also includes hardness information of the cut target.

8. A shearing system for rectangular shearing sections according to claim 5, characterized in that: The first target deep learning model and the second target deep learning model are both LSTM models and / or CNN models.

9. A shearing system for rectangular shearing sections according to claim 5, characterized in that: After generating the wear matrix M corresponding to the current shear blade, the controller is further configured to perform the following steps: If the cumulative sum of the wear values in any column is greater than a preset threshold, wear warning information for the wear evaluation area corresponding to the column is generated.

10. A shearing system for rectangular shearing sections according to claim 1, characterized in that: The object to be cut is metal.

Images