Grinding tool sharpness prediction method, grinding tool sharpness prediction model training method and electronic equipment

Abstract

The invention provides a grinding tool sharpness prediction method, a grinding tool sharpness prediction model training method and electronic equipment. The grinding tool sharpness prediction method comprises the steps that surface machining information generated when machining equipment machines the surface of a product is acquired; according to the surface machining information, the friction force and the positive pressure between a grinding tool of the machining equipment and the product are determined; and inputting the positive pressure and the friction force into a sharpness prediction model to obtain the predicted sharpness of the grinding tool. By utilizing the method, the sharpness of the grinding tool can be accurately predicted, so that the residual life of the grinding tool can be accurately determined.

Description

Technical Field

[0001] The present application relates to the field of detection, and in particular to a method for predicting the sharpness of a grinding tool, a method for training a model for predicting the sharpness of a grinding tool, and electronic equipment. Background Art

[0002] In the field of sanding, abrasive tools (such as grinding wheels) are important processing tools, and their performance has a great impact on processing efficiency and product quality. Abrasive tools will experience a certain degree of wear during use. As the wear increases, the sharpness of the abrasive tools gradually decreases, which not only affects the quality of the processed surface, but also may cause the risk of damage to the workpiece. Therefore, when the sharpness of the abrasive tool decreases to a certain extent, it is necessary to replace it with a new one in time to ensure the stability of the processing process and the consistency of the product.

[0003] In the related art, the sharpness of the grinding tool is often determined by manual evaluation. However, this judgment method is limited by factors such as the operator's experience, visual perception ability, and differences in understanding of standards, resulting in the evaluation of the sharpness of the grinding tool being often not accurate enough. If the sharpness of the grinding tool cannot be accurately determined, it will be difficult to accurately determine the remaining life of the grinding tool, resulting in premature replacement of the grinding tool, resulting in waste of resources, or excessive wear of the grinding tool, resulting in affected processing quality and many other problems. Summary of the invention

[0004] In view of the above, it is necessary to provide a tool sharpness prediction method, a tool sharpness prediction model training method and an electronic device, which can solve the technical problem that the sharpness of the tool cannot be accurately determined, resulting in difficulty in accurately determining the remaining life of the tool.

[0005] On the one hand, the present application provides a method for predicting the sharpness of a grinding tool, the method comprising: obtaining surface processing information generated when a processing equipment processes the surface of a product, determining the friction force and normal pressure between the grinding tool of the processing equipment and the product based on the surface processing information, inputting the normal pressure and the friction force into a sharpness prediction model to obtain the predicted sharpness of the grinding tool.

[0006] In some embodiments of the present application, the method of obtaining the surface processing information generated when the processing equipment processes the surface of a product includes: obtaining the surface processing information carried by each time point generated when the processing equipment processes a single surface of the product, extracting the surface processing information carried by the time point corresponding to the preset time point extraction range based on the surface processing information carried by each time point and a preset time point extraction range, and determining the surface processing information carried by the time point corresponding to the preset time point extraction range as the surface processing information.

[0007] In some embodiments of the present application, the surface processing information includes a force sensor signal, and determining the friction force between the mold of the processing equipment and the product based on the surface processing information includes: performing a frequency domain transform on the force sensor signal to obtain spectrum data, determining target amplitudes corresponding to multiple frequencies from the spectrum data according to a preset frequency range, determining a maximum target amplitude based on the target amplitudes corresponding to the multiple frequencies, filtering the force sensor signal to obtain a filtered signal, and calculating the friction force based on the maximum target amplitude and the filtered signal.

[0008] In some embodiments of the present application, the surface processing information includes motor current and motor speed, and determining the positive pressure between the mold and the product based on the surface processing information includes: determining the motor power based on the motor current, and calculating the positive pressure based on the motor power and the motor speed.

[0009] In some embodiments of the present application, the method further includes: inputting the positive pressure and the friction force into a life prediction model to obtain the remaining life of the grinding tool.

[0010] In some embodiments of the present application, it also includes: determining the predicted number of uses corresponding to the predicted sharpness based on a comparison table of the predicted sharpness and the preset number of uses, and determining the remaining life of the abrasive tool based on the predicted number of uses and the standard number of uses.

[0011] In some embodiments of the present application, it also includes: judging whether the predicted sharpness is not greater than a preset standard sharpness, and if the predicted sharpness is not greater than the preset standard sharpness, determining that the remaining life of the grinding tool is a preset value.

[0012] In some embodiments of the present application, the method further includes: obtaining the product removal amount, and determining the target positive pressure corresponding to the grinding tool according to the product removal amount and the predicted sharpness, so as to perform surface processing on the next product based on the target positive pressure.

[0013] On the other hand, the present application provides a method for training a grinding tool sharpness prediction model, the method comprising: obtaining multiple historical surface processing information generated when a processing equipment processes multiple product surfaces and multiple historical removal amounts of the corresponding products, determining the historical friction and historical positive pressure between the grinding tool of the processing equipment and the product based on the historical surface processing information, determining the historical sharpness of the grinding tool of the corresponding product based on the historical removal amount and the historical positive pressure, inputting the historical sharpness, the historical friction and the historical positive pressure into the model for training, and forming a sharpness prediction model.

[0014] In some embodiments of the present application, the acquisition of multiple historical surface processing information generated when the processing equipment processes multiple product surfaces includes: acquiring the historical surface processing information carried by each historical time point generated when the processing equipment processes a single product surface, based on the historical surface processing information carried by each historical time point and a preset time point extraction range, extracting the historical surface processing information carried by the historical time point corresponding to the preset time point extraction range, and determining the historical surface processing information carried by the historical time point corresponding to the preset time point extraction range as the historical surface processing information.

[0015] In some embodiments of the present application, the historical surface processing information includes a historical force sensor signal, and determining the historical friction force between the mold of the processing equipment and the product based on the historical surface processing information includes: performing frequency domain transformation on the historical force sensor signal to obtain historical spectrum data, determining target historical amplitudes corresponding to multiple frequencies from the historical spectrum data according to a preset frequency range, determining a maximum target historical amplitude based on the target historical amplitudes corresponding to the multiple frequencies, filtering the historical force sensor signal to obtain a historical filtered signal, and calculating the historical friction force based on the maximum target historical amplitude and the historical filtered signal.

[0016] In some embodiments of the present application, the historical surface processing information includes historical motor current and historical motor speed, and determining the historical positive pressure between the mold of the processing equipment and the product based on the historical surface processing information includes: determining the historical motor power based on the historical motor current, and calculating the historical positive pressure based on the historical motor power and the historical motor speed.

[0017] On the other hand, the present application provides an electronic device, comprising: a memory storing at least one instruction; and a processor executing the at least one instruction to implement the tool sharpness prediction method or the tool sharpness prediction model training method.

[0018] Through the above implementation, since the surface processing information includes the parameters when the processing equipment performs surface processing on the product, such as the actual grinding force, etc., the friction and normal pressure between the abrasive tool and the product can be accurately determined through the surface processing information. Since the sharpness prediction model is obtained through training of data such as historical removal amount, historical sharpness, historical friction, and historical normal pressure, the accuracy of the predicted sharpness of the abrasive tool can be ensured by inputting the normal pressure and friction into the sharpness prediction model. Through accurate prediction of sharpness, the remaining life of the abrasive tool can be accurately determined. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1Schematic diagram of a grinding tool sharpness prediction system provided in one embodiment of the present application.

[0020] Figure 2 It is a flow chart of a method for predicting the sharpness of an abrasive tool provided in one embodiment of the present application.

[0021] Figure 3 It is a schematic diagram of a processing area provided in one embodiment of the present application.

[0022] Figure 4 Schematic diagram of a force sensor signal provided in an embodiment of the present application.

[0023] Figure 5 is a schematic diagram of a force sensor signal provided in another embodiment of the present application.

[0024] Figure 6 It is a schematic diagram of the attenuation of the sharpness of the grinding tool provided in one embodiment of the present application.

[0025] Figure 7 This is a schematic diagram of determining the remaining life provided by an embodiment of the present application.

[0026] Figure 8 This is a graph showing the relationship between product removal amount, sharpness and positive pressure provided in one embodiment of the present application.

[0027] Fig. 9 It is a schematic diagram of the attenuation of the sharpness of the grinding tool provided in another embodiment of the present application.

[0028] Fig.10 It is a flow chart of a method for training a grinding tool sharpness prediction model provided in one embodiment of the present application.

[0029] Fig.11 It is a flowchart of a life prediction model training method provided in one embodiment of the present application.

[0030] Fig.12 It is a structural diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0031] It should be noted that in this application, "at least one" means one or more, and "more than one" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0032] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way. The following embodiments and features in the embodiments may be combined with each other without conflict.

[0033] The embodiments of the present application provide a method for predicting the sharpness of a mold, a method for training a model for predicting the sharpness of a mold, and an electronic device. The method for predicting the sharpness of a mold and the method for training a model for predicting the sharpness of a mold can be applied to one or more electronic devices.

[0034] Electronic equipment and processing equipment can form a sharpness prediction system for abrasive tools, such as Figure 1 The electronic device 10 may be a server, a computer, a tablet computer, an industrial computer, a mobile phone, etc. The server may be a single server, a server cluster or a cloud server. The application does not limit the type of electronic device.

[0035] exist Figure 1 In the embodiment, the electronic device 10 can be connected to the processing device 20 for communication via bus, Bluetooth (BT), wireless fidelity (Wi-Fi), etc., and the present application does not limit the communication connection method.

[0036] The processing equipment 20 can be used for sanding the surface of the product. The processing equipment 20 can include a grinder and a motor for driving the grinder to rotate. The motor is used to drive the grinder to rotate, and the grinder is used to grind the product. The grinder can be a grinding wheel, a sanding belt, etc., and the present application does not limit the type of the grinder. The processing equipment 20 can send the surface processing information to the electronic device 10 so that the electronic device 10 can implement the grinder sharpness prediction method provided in the embodiment of the present application.

[0037] If, based on the received surface processing information, it is detected that there is an abnormality in the processing of the product surface, the electronic device 10 can push processing data to the processing equipment, where the processing data can be a compensation value of the positive pressure of the processing equipment for surface processing of the product, etc. Through the processing data, the processing can be adjusted and optimized to ensure the processing effect.

[0038] like Figure 2FIG. 1 is a flowchart of a method for predicting the sharpness of a grinding tool provided in an embodiment of the present application. According to different requirements, the order of each step in the flowchart can be adjusted according to actual requirements, and some steps can be omitted. The method for predicting the sharpness of a grinding tool is applied to electronic devices, such as Figure 1 The electronic device 10 is shown. The electronic device is connected to the processing equipment for communication, such as Figure 1 The processing equipment 20 is shown.

[0039] S11, obtaining surface processing information generated when processing equipment processes the surface of the product.

[0040] In some embodiments of the present application, the product may be any type of product, and the present application does not limit the type of the product. For example, the product may be a mobile phone case, a speaker case, a watch case, a computer case, etc.

[0041] In some embodiments of the present application, the surface processing information may correspond to a single surface processing or multiple surface processing.

[0042] In some embodiments, the surface processing information may include a force sensor signal.

[0043] The force sensor signal may include the real grinding force carried at each time point, where the real grinding force is the force value applied by the grinding tool in the processing equipment to at least one processing area in the product, and the grinding tool may be a grinding wheel, etc. The force sensor signal may be detected by the force sensor.

[0044] There can be one or more processing areas. In order to ensure the processing quality, the product can be divided into multiple processing areas so that the surface processing of the product can be carried out in different areas. For example, if the product is a mobile phone case, in order to stagger the surface processing of straight edges, rounded corners, buttons and interfaces, the mobile phone case can be divided into multiple processing areas. For example, Figure 3 FIG. 1 is a schematic diagram of a processing area provided in an embodiment of the present application. Figure 3 Take the mobile phone case in the example to explain, the mobile phone case is divided into 9 processing areas, the positions of the 9 processing areas can refer to Figure 3 The direction of the arrow corresponding to the index number in .

[0045] In some embodiments of the present application, the surface processing performed on each processing area may be single or multiple times. For example, following the above embodiment, if the product includes 9 processing areas, the number of processing times for each processing area is 5 times.

[0046] like Figure 4 As shown in FIG. 1 , it is a schematic diagram of a force sensor signal provided by an embodiment of the present application. Figure 5 , which is a schematic diagram of a force sensor signal provided in another embodiment of the present application. Figure 4 The force sensor signal shown corresponds to a single machining operation. Figure 5 The force sensor signals shown correspond to multiple machining operations. Figure 4 The force sensor signal shown in the figure indicates the signal segment corresponding to each processing area. The signal segment corresponding to each processing area can be referred to Figure 4 The signal ranges corresponding to the areas 0, 1, ... 8 are shown in the figure. Figure 3 The order of the index numbers shown in the figure is to perform surface processing on the 9 processing areas in sequence. The processing paths of the 9 processing areas can form a closed loop (cycle). Therefore, Figure 5 The signal segments corresponding to circles 1, 2, ... 5 in the figure represent the force sensor signals obtained by surface processing of the product. The signal segments corresponding to circles 1, 2, ... 5 can be referred to Figure 5 The signal is divided by dashed lines. Figure 4 and Figure 5 In the figure, the horizontal axis can represent the time point, and the vertical axis can represent the force sensor signal. Figure 4 and Figure 5 The force sensor signal shown may be the actual grinding force.

[0047] In other embodiments, in addition to the force sensor signal, the surface processing information may also include operating data of the motor of the processing equipment, wherein the operating data includes but is not limited to: the motor current and the motor speed carried at each time point.

[0048] In some embodiments of the present application, an electronic device obtains surface processing information generated when a processing device processes the surface of a product, including: obtaining the surface processing information carried by each time point generated when the processing equipment processes the surface of a single product, extracting the surface processing information carried by the time point corresponding to the preset time point extraction range based on the surface processing information carried by each time point and a preset time point extraction range, and determining the surface processing information carried by the time point corresponding to the preset time point extraction range as the acquired surface processing information.

[0049] The electronic device is in communication with the processing device, so the electronic device can receive the surface processing information sent by the processing device at each time point when the processing device processes the surface of a single product. The surface processing information obtained from the processing device can be the surface processing information of all processing areas in the product.

[0050] Since the lengths and other features of the processing areas in the same type of products are basically the same, the processing time point ranges corresponding to the processing areas at the same positions in the same type of products are basically the same. Therefore, the preset time point extraction range can be customized by the user based on the processing time point ranges corresponding to the various processing areas in the product according to the needs of obtaining surface processing information.

[0051] For example, if the user wants to obtain the surface processing information corresponding to the processing area whose processing path is a straight line and has the longest processing time, the following can be used: Figure 3 The processing time point range corresponding to the processing area 4 shown is defined as a preset time point extraction range. By defining the preset time point extraction range, the electronic device can extract the surface processing information of all processing areas obtained by the processing equipment as shown in FIG. Figure 3 The surface processing information corresponding to the processing area 4 is shown. For example, if the processing time point range corresponding to the processing area 4 is from the 3rd second to the 7th second, the preset time point extraction range can be determined as the 3rd second to the 7th second.

[0052] In this embodiment, the surface processing information of each processing area can be flexibly selected by presetting the time point extraction range.

[0053] S12, determining the friction force and normal pressure between the abrasive tool of the processing equipment and the product according to the surface processing information.

[0054] In some embodiments of the present application, the electronic device determines the friction between the mold of the processing equipment and the product based on the surface processing information, including: performing frequency domain transformation on the force sensor signal to obtain spectrum data, determining target amplitudes corresponding to multiple frequencies from the spectrum data according to a preset frequency range, determining the maximum target amplitude based on the target amplitudes corresponding to the multiple frequencies, filtering the force sensor signal to obtain a filtered signal, and calculating the friction based on the maximum target amplitude and the filtered signal.

[0055] The electronic device may perform frequency domain transformation on the force sensor signal using a variety of methods. For example, the electronic device may perform Fourier transformation on the force sensor signal to obtain frequency spectrum data.

[0056] The filtering process performed on the force sensor signal may be low-frequency filtering. The electronic device performs low-frequency filtering on the force sensor signal to obtain the low-frequency component of the force sensor signal, and determines the obtained low-frequency component as the filtered signal. Since the force sensor signal includes the real grinding force carried at each time point, the filtered signal obtained after filtering the force sensor signal may include the filtered grinding force carried at each time point.

[0057] The preset frequency range can be customized, and this application does not limit this. For example, if the grinding tool is a grinding wheel, the corresponding preset frequency range can be customized for the characteristics of the roughness and shape of the grinding wheel surface. Exemplarily, it is considered that the roughness or shape of the grinding wheel surface will affect its vibration characteristics and grinding effect. When the grinding wheel surface is a plane, its vibration mode is relatively uniform and stable. Therefore, when the grinding wheel surface is a plane, the frequency in the preset frequency range can be set higher to facilitate capturing the characteristics of the vibration. When the grinding wheel surface is a non-plane with a protrusion, its vibration mode is dispersed and diverse. Therefore, when the grinding wheel surface is a non-plane, the frequency in the preset frequency range can be set lower to facilitate capturing the characteristics of the vibration.

[0058] The maximum target amplitude may be the peak intensity of the spectrum data within a preset frequency range. Since the filtered signal includes the filtered polishing force carried at each time point, each time point has a corresponding friction force. Exemplarily, the electronic device may multiply the maximum target amplitude with the filtered polishing force carried at each time point in the filtered signal to obtain the surface roughness of the abrasive corresponding to each time point, and determine the calculated surface roughness as the friction force corresponding to each time point.

[0059] In this embodiment, considering that the low-frequency component can better reflect the contact state and contact force between the abrasive tool and the product during the sanding process than the high-frequency component, in this embodiment, the force sensor signal is low-frequency filtered to remove interference from factors such as noise, high-frequency vibration / rotation, and cumulative errors. Since the greater the surface roughness, the greater the corresponding friction force, the use of the surface roughness of the abrasive tool to characterize the friction force can ensure the accuracy of the friction force.

[0060] In some embodiments of the present application, if the surface processing information includes a force sensor signal and motor operation data, determining the positive pressure between the mold and the product based on the surface processing information includes: determining the motor power based on the motor current, and calculating the positive pressure based on the motor power and the motor speed.

[0061] Since the operation data of the motor includes the motor current and motor speed carried at each time point, each time point has a corresponding positive pressure. Exemplarily, the electronic device can determine the motor power corresponding to each time point based on the motor current carried at each time point in the operation data of the motor, calculate the motor torque corresponding to each time point based on the motor power and motor speed corresponding to each time point, and determine the calculated motor torque as the positive pressure corresponding to each time point. Among them, the method for determining the motor power corresponding to each time point can refer to the power calculation formula in the relevant technology, and the method for calculating the motor torque based on the motor power and motor speed can refer to the torque calculation formula in the relevant technology.

[0062] Exemplarily, the electronic device can obtain parameters such as the motor voltage and motor resistance corresponding to each time point, and determine the motor power corresponding to each time point based on the motor current carried by each time point in the operating data and the motor voltage or motor resistance corresponding to each time point.

[0063] In this embodiment, since the mold is driven by a motor, the size of the motor's operating data can reflect the positive pressure between the mold and the product. For example, the greater the motor current, the greater the positive pressure between the mold and the product. Therefore, using the motor torque to characterize the positive pressure can ensure the accuracy of the positive pressure.

[0064] In other embodiments of the present application, if the surface processing information only includes the force sensor signal, the electronic device can determine the filtered polishing force corresponding to each time point in the filtered signal as the positive pressure corresponding to each time point.

[0065] S13, inputting the normal pressure and friction force into the sharpness prediction model to obtain the predicted sharpness of the abrasive tool.

[0066] In some embodiments of the present application, before inputting the normal pressure and friction force into the sharpness prediction model, the electronic device may normalize the friction force and the normalized normal pressure, and align the normalized friction force and normal pressure.

[0067] In some embodiments of the present application, the sharpness prediction model can be obtained by training the model through data such as historical normal pressure, historical friction, and historical sharpness. The training method of the sharpness prediction model can refer to the description of steps S21 to S24 below.

[0068] In this embodiment, since the sharpness prediction model is trained by using data such as historical positive pressure, historical friction and historical sharpness, the trained sharpness prediction model can learn the correlation between historical positive pressure, historical friction and historical sharpness. Therefore, by inputting the positive pressure and friction into the sharpness prediction model, the predicted sharpness of the grinding tool can be obtained quickly and accurately.

[0069] In other embodiments of the present application, after obtaining the predicted sharpness of the grinding tool, the electronic device can determine the predicted number of uses corresponding to the predicted sharpness based on a comparison table of the predicted sharpness and the preset number of uses of the sharpness, and determine the remaining life of the grinding tool based on the predicted number of uses and the standard number of uses. The preset sharpness usage comparison table may include multiple preset sharpnesses and the number of times the abrasive tool is used corresponding to each preset sharpness. The electronic device may determine the number of times the abrasive tool is used corresponding to the preset sharpness that is the same as the predicted sharpness as the predicted number of times.

[0070] The standard number of uses can be customized, or the standard number of uses can be the number of uses corresponding to the lowest sharpness of the abrasive tool when processing qualified products, and the electronic device can determine the standard number of uses from the number of uses of the abrasive tool in the preset sharpness use number comparison table. For example, the electronic device can determine the number of uses of the abrasive tool corresponding to the lowest sharpness in the preset sharpness use number comparison table as the standard number of uses.

[0071] The electronic device may determine the difference between the standard number of uses and the predicted number of uses as the remaining life of the abrasive tool.

[0072] like Figure 6 , which is a schematic diagram of the attenuation of the sharpness of the grinding tool provided in one embodiment of the present application. Figure 6 The curve shown can represent the sharpness of the abrasive tool, wherein the horizontal axis can represent the number of times the abrasive tool is used, and the vertical axis can represent the sharpness of the abrasive tool. Figure 6 It can be seen from the curve shown that after a certain number of uses, the sharpness of the abrasive tool will show a continuous downward trend.

[0073] In this embodiment, since the sharpness prediction model is obtained through training of data such as historical sharpness, historical friction, and historical positive pressure, the accuracy of the predicted sharpness of the grinding tool can be ensured by inputting positive pressure and friction into the sharpness prediction model.

[0074] In other embodiments of the present application, the electronic device can determine whether the predicted sharpness is not greater than the preset standard sharpness. If the predicted sharpness is not greater than the preset standard sharpness, the remaining life of the grinding tool is determined to be a preset value. The preset value can be 0, or any number of 1 circle, 2 circles, or 3 circles.

[0075] Among them, the preset standard sharpness can be customized, such as 0.3, 0.4, 0.5, and this application does not impose any restrictions on this.

[0076] For example, if the preset standard sharpness is 0.4, Figure 7 , which is a schematic diagram of determining the remaining life provided by an embodiment of the present application. Figure 7 The straight line parallel to the horizontal axis indicates the preset standard sharpness of 0.400. Figure 7 The curve in represents the sharpness of the abrasive tool. When the curve corresponding to the sharpness intersects the straight line corresponding to the preset standard sharpness, it can be determined that the remaining life of the abrasive tool is 0.

[0077] In this embodiment, the predicted sharpness is compared with the preset standard sharpness, so as to quickly determine whether the remaining life of the grinding tool is 0.

[0078] In other embodiments of the present application, the electronic device may also input the normal pressure and friction force into a life prediction model to obtain the remaining life of the mold.

[0079] The life prediction model can be obtained by training the historical normal pressure, historical friction and historical remaining life of the product. The training method of the life prediction model can refer to the description of steps S31 to S35 below.

[0080] In this embodiment, since the life prediction model is obtained by training the product's historical positive pressure, historical friction and historical life data, the trained life prediction model can learn the correlation between the historical positive pressure, historical friction and historical remaining life. Therefore, by inputting the positive pressure and friction into the life prediction model, the remaining life of the mold can be accurately and quickly obtained.

[0081] In other embodiments of the present application, the electronic device can obtain the product removal amount, and determine the target positive pressure corresponding to the abrasive tool based on the product removal amount and the predicted sharpness, so as to perform surface processing on the next product based on the target positive pressure.

[0082] In order to ensure the quality of the product, the amount of product removed is often fixed and stable. When the amount of product removed is fixed, the positive pressure applied to the product by the abrasive with greater sharpness can be smaller. For example, the relationship between the amount of product removed, sharpness and positive pressure can be referred to the following formula (1): ; (1) in, Indicates the unit time of the cumulative effect within the preset time interval.

[0083] For example, Figure 8 , is a graph showing the relationship between product removal, sharpness and positive pressure provided by an embodiment of the present application. Figure 8 In the above equation, the product removal corresponds to a straight line parallel to the horizontal axis, which indicates that the product removal is constant. Figure 8 The sharpness in the medium shows a downward trend, and the positive pressure shows an upward trend.

[0084] Based on the above formula (1) and the principle that the greater the sharpness of the mold, the smaller the normal pressure applied by the mold to the product, the electronic device can determine the target normal pressure of the mold based on the product removal amount and the predicted sharpness. The target normal pressure can be used to optimize the normal pressure for the next product surface processing, thereby extending the life of the mold.

[0085] For example, Fig. 9 , which is a schematic diagram of the attenuation of the sharpness of a grinding tool provided in another embodiment of the present application. Fig. 9In the figure, the solid line indicates the sharpness corresponding to the positive pressure before optimization, and the dotted line indicates the sharpness corresponding to the target positive pressure after optimization. By comparing the two curves, it can be seen that under the same number of times the abrasive tool is used, the sharpness of the abrasive tool corresponding to the optimized target positive pressure is higher than the sharpness of the abrasive tool corresponding to the positive pressure before optimization. Therefore, surface processing of the product through the optimized target positive pressure can extend the life of the abrasive tool.

[0086] In the abrasive tool sharpness prediction method provided in this embodiment, since the surface processing information includes the parameters of the processing equipment when performing surface processing on the product, such as the actual grinding force, etc., the friction and normal pressure between the abrasive tool and the product can be accurately determined through the surface processing information. Since the sharpness prediction model is obtained through training of data such as historical removal amount, historical sharpness, historical friction, and historical normal pressure, the accuracy of the predicted sharpness of the abrasive tool can be ensured by inputting the normal pressure and friction into the sharpness prediction model. By accurately predicting the sharpness, the remaining life of the abrasive tool can be accurately determined.

[0087] like Fig.10 The figure is a flow chart of a method for training a sharpness prediction model of a grinding tool provided in an embodiment of the present application. According to different requirements, the order of each step in the flow chart can be adjusted according to actual requirements, and some steps can be omitted. The method for training a sharpness prediction model of a grinding tool is applied to electronic devices, such as Figure 1 The electronic device 10 is shown. The electronic device is connected to the processing equipment for communication, such as Figure 1 The processing equipment 20 is shown.

[0088] S21, obtaining a plurality of historical surface processing information generated when a processing device processes the surfaces of a plurality of products and a plurality of historical removal amounts of the corresponding products.

[0089] In some embodiments of the present application, the historical surface processing information may include a historical force sensor signal, wherein the historical force sensor signal may include a historical true grinding force carried at each historical time point.

[0090] In other embodiments, in addition to the historical force sensor signals, the historical surface processing information may also include historical operation data of the motor of the processing equipment, wherein the historical operation data includes but is not limited to: the current and speed carried at each historical time point.

[0091] In some embodiments of the present application, obtaining multiple historical surface processing information generated when a processing device processes the surfaces of multiple products includes: obtaining the historical surface processing information carried by each historical time point generated when the processing equipment processes the surface of a single product, extracting the historical surface processing information carried by the historical time points corresponding to the preset time point extraction range based on the historical surface processing information carried by each historical time point and a preset time point extraction range, and determining the historical surface processing information carried by the historical time points corresponding to the preset time point extraction range as the acquired historical surface processing information.

[0092] Among them, since the historical force sensor signal includes the historical real polishing force carried at each historical time point, the historical filtered signal obtained after filtering the historical force sensor signal can include the historical filtered polishing force carried at each historical time point.

[0093] For the method of acquiring historical surface processing information, reference may be made to the description of the method of acquiring surface processing information in step S11, and this application will not repeat the description.

[0094] In some embodiments of the present application, the historical removal amount may be a weight loss or mass loss of a product. For example, the historical removal amount of a product may be the difference between the mass of the product before processing and the mass of the product after processing. The mass of the product before processing may be obtained by measuring the mass of the product before processing, and the mass of the product after processing may be obtained by measuring the mass of the product after processing.

[0095] S22, determining the historical friction force and the historical normal pressure between the abrasive tool of the processing equipment and the product based on the historical surface processing information.

[0096] In some embodiments of the present application, the electronic device determines the historical friction between the mold of the processing equipment and the product based on the historical surface processing information, including: performing frequency domain transformation on the historical force sensor signal to obtain historical spectrum data, determining the target historical amplitudes corresponding to multiple frequencies from the historical spectrum data according to a preset frequency range, determining the maximum target historical amplitude based on the target historical amplitudes corresponding to the multiple frequencies, filtering the historical force sensor signal to obtain a historical filtered signal, and calculating the historical friction based on the maximum target historical amplitude and the historical filtered signal.

[0097] Among them, since the historical filtering signal includes the historical filtering grinding force carried by each historical time point, each historical time point has a corresponding historical friction force.

[0098] In some embodiments of the present application, if the historical surface processing information includes historical force sensor signals and historical operation data of the motor, the electronic device determines the historical positive pressure between the mold of the processing equipment and the product based on the historical surface processing information, including: determining the historical motor power based on the historical motor current, and calculating the historical positive pressure based on the historical motor power and the historical motor speed.

[0099] Among them, since the operation data of the motor includes the historical motor current and the historical motor speed carried by each historical time point, each historical time point has a corresponding historical positive pressure.

[0100] In other embodiments of the present application, if the historical surface processing information only includes the historical force sensor signal, the electronic device can determine the historical filtered grinding force corresponding to each historical time point in the historical filtered signal as the historical positive pressure corresponding to each historical time point.

[0101] For the description of the method for determining the historical friction force and the historical normal pressure, reference may be made to the description of the method for determining the friction force and the normal pressure in step S12.

[0102] S23, determining the historical sharpness of the abrasive tool of the corresponding product based on the historical removal amount and the historical normal pressure.

[0103] In some embodiments of the present application, the description of the method for determining the historical sharpness may refer to the description of the predicted sharpness in step S13 .

[0104] S24, inputting historical sharpness, historical friction and historical normal pressure into the model for training to form a sharpness prediction model.

[0105] In some embodiments of the present application, the model may be a neural network model or a non-neural network model, wherein the neural network model may be a recurrent neural network (RNN) model and a long short-term memory network (LSTM) model, etc., and the non-neural network model may be a linear regression and Kalman filtering, etc.

[0106] In some embodiments of the present application, the electronic device can input the historical removal amount and the corresponding historical friction force and historical positive pressure into the model to obtain the predicted sharpness of the model output, determine the loss of the model based on the predicted sharpness of the model output and the corresponding historical sharpness, adjust the parameters of the model until the loss meets the preset conditions, and obtain the sharpness prediction model.

[0107] The parameters of the model include, but are not limited to, learning rate, weight, and bias. For example, the preset condition may be that the loss drops to a preset value range. The preset value range may be customizable, and this application does not limit this.

[0108] In the tool sharpness prediction model training method provided in the embodiment of the present application, since the sharpness prediction model is obtained through training of data such as historical sharpness, historical friction, and historical positive pressure, the trained sharpness prediction model can learn the correlation between historical positive pressure, historical friction, and historical sharpness.

[0109] like Fig.11 FIG. 1 is a flowchart of a life prediction model training method provided by an embodiment of the present application. According to different requirements, the order of each step in the flowchart can be adjusted according to actual requirements, and some steps can be omitted. The life prediction model training method is applied to electronic devices, such as Figure 1 The electronic device 10 is shown. The electronic device is connected to the processing equipment for communication, such as Figure 1 The processing equipment 20 is shown.

[0110] S31, obtaining a plurality of historical surface processing information generated when a processing device processes the surfaces of a plurality of products and a plurality of historical removal amounts of the corresponding products.

[0111] In some embodiments of the present application, the method for obtaining historical surface processing information may refer to the description of step S11, and the method for obtaining historical removal amount may refer to the description of step S21.

[0112] S32, determining the historical friction force and the historical normal pressure between the abrasive tool of the processing equipment and the product according to the historical surface processing information.

[0113] In some embodiments of the present application, the description of the method for determining the historical friction force and the historical normal pressure can refer to the description of the method for determining the friction force and the normal pressure in step S12.

[0114] S33, determining the historical sharpness of the abrasive tool of the corresponding product based on the historical removal amount and the historical normal pressure.

[0115] In some embodiments of the present application, the description of the method for determining the historical sharpness may refer to the description of the predicted sharpness in step S13 .

[0116] S34, determining the historical remaining life of the abrasive tool based on the historical sharpness.

[0117] In some embodiments of the present application, the method for determining the historical remaining life of the grinding tool may refer to the description of the method for determining the remaining life of the grinding tool in step S13.

[0118] S35, inputting the historical remaining life and the corresponding historical friction force and historical normal pressure into the model for training to form a life prediction model.

[0119] In some embodiments of the present application, the model may be of the same type as the model in step S24. The electronic device may input the historical friction force and the historical normal pressure into the model, obtain the remaining life output by the model, determine the loss of the model according to the remaining life output by the model and the corresponding historical remaining life, adjust the parameters of the model until the loss meets the preset conditions, and obtain the life prediction model.

[0120] The electronic device adjusts the parameters of the model until the loss meets the preset conditions and stops. The method for obtaining the life prediction model can refer to the description of the method for obtaining the sharpness prediction model in step S24.

[0121] In the life prediction model training method provided in the embodiment of the present application, since the life prediction model is obtained by training the historical positive pressure, historical friction and historical life data of the product, the trained life prediction model can learn the correlation between the historical positive pressure, historical friction and historical remaining life.

[0122] like Fig.12 As shown in FIG. 1 , it is a structural diagram of an electronic device provided by an embodiment of the present application. Fig.12 As shown, the electronic device 10 may include a communication module 101, a memory 102, a processor 103, an input / output (I / O) interface 104 and a bus 105. The processor 103 is coupled to the communication module 101, the memory 102, and the input / output interface 104 through the bus 105.

[0123] The communication module 101 may include a wired communication module and / or a wireless communication module. The wired communication module may provide one or more wired communication solutions such as universal serial bus (USB), controller area network bus (CAN, Controller Area Network). The wireless communication module may provide one or more wireless communication solutions such as wireless fidelity, Bluetooth, mobile communication network, frequency modulation (FM), near field communication technology (NFC), infrared technology (IR), etc.

[0124] The memory 102 may include one or more random access memories (RAM) and one or more non-volatile memories (NVM). The random access memory can be directly read and written by the processor 103, and can be used to store executable programs (such as machine instructions) of other running programs, and can also be used to store user and application data. The random access memory may include static random-access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), etc.

[0125] The non-volatile memory may also store executable programs and user and application data, etc., and may be loaded into the random access memory in advance for direct reading and writing by the processor 103. The non-volatile memory may include a disk storage device and a flash memory.

[0126] The memory 102 is used to store one or more computer programs. The one or more computer programs are configured to be executed by the processor 103. The one or more computer programs include a plurality of instructions, and when the plurality of instructions are executed by the processor 103, the abrasive tool sharpness prediction method and the abrasive tool sharpness prediction model training method executed on the electronic device 10 can be implemented.

[0127] In other embodiments, Fig.12 The electronic device 10 shown also includes an external memory interface for connecting to an external memory to expand the storage capacity of the electronic device 10 .

[0128] The processor 103 may include one or more processing units, for example, the processor 103 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0129] The processor 103 provides computing and control capabilities. For example, the processor 103 is used to execute a computer program stored in the memory 102 to implement the above-mentioned tool sharpness prediction method and tool sharpness prediction model training method.

[0130] The input / output interface 104 is used to provide a channel for user input or output. For example, the input / output interface 104 can be used to connect various input and output devices, such as a mouse, keyboard, touch device, display screen, etc., so that the user can enter information or visualize information.

[0131] The bus 105 is at least used to provide a channel for mutual communication among the communication module 101 , the memory 102 , the processor 103 , and the input / output interface 104 in the electronic device 10 .

[0132] It is to be understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device 10. In other embodiments of the present application, the electronic device 10 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0133] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the methods in the above-mentioned embodiments of the present application.

[0134] The computer-readable storage medium may be an internal memory of the electronic device described in the above embodiment, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device.

[0135] In some embodiments, the computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the electronic device, etc.

[0136] It is to be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the electronic device. In other embodiments of the present application, the electronic device may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0137] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0138] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0139] In addition, each functional module in each embodiment of the present 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 above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0140] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present application is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present application. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0141] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in this application can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0142] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical solution of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present application.

Claims

1. A method for predicting the sharpness of a grinding tool, characterized in that: The method comprises: Obtain surface processing information generated by processing equipment when processing the product surface; Determining the friction force and normal pressure between the grinding tool of the processing equipment and the product according to the surface processing information; The normal pressure and the friction force are input into a sharpness prediction model to obtain the predicted sharpness of the grinding tool.

2. The method for predicting the sharpness of abrasive tools according to claim 1, wherein: The acquisition of surface processing information generated when the processing equipment processes the surface of the product includes: Acquire the surface processing information carried at each time point generated when the processing equipment processes a single surface of the product; Based on the surface processing information carried by each time point and a preset time point extraction range, extracting the surface processing information carried by the time point corresponding to the preset time point extraction range; The surface processing information carried by the time point corresponding to the preset time point extraction range is determined as the surface processing information.

3. The method for predicting the sharpness of abrasive tools according to claim 1, wherein: The surface processing information includes a force sensor signal, and determining the friction force between the grinding tool of the processing equipment and the product according to the surface processing information includes: Performing frequency domain transformation on the force sensor signal to obtain spectrum data; Determining target amplitudes corresponding to a plurality of frequencies from the spectrum data according to a preset frequency range; Determining a maximum target amplitude based on the target amplitudes corresponding to the multiple frequencies; Performing filtering processing on the force sensor signal to obtain a filtered signal; The friction force is calculated according to the maximum target amplitude and the filtered signal.

4. The method for predicting the sharpness of abrasive tools according to claim 1, wherein: The surface processing information includes a motor current and a motor speed, and determining the positive pressure between the abrasive tool and the product according to the surface processing information includes: Determining motor power according to the motor current; The positive pressure is calculated according to the motor power and the motor speed.

5. The method for predicting the sharpness of abrasive tools according to claim 1, wherein: Also includes: The positive pressure and the friction force are input into a life prediction model to obtain the remaining life of the grinding tool.

6. The method for predicting the sharpness of abrasive tools according to claim 1, wherein: Also includes: Determining the predicted number of times of use corresponding to the predicted sharpness based on a comparison table of the predicted sharpness and the number of times of use of the preset sharpness; Based on the predicted number of uses and the standard number of uses, the remaining life of the abrasive tool is determined.

7. The method for predicting the sharpness of abrasive tools according to claim 1, characterized in that: Also includes: Determining whether the predicted sharpness is not greater than a preset standard sharpness; If the predicted sharpness is not greater than the preset standard sharpness, it is determined that the remaining life of the abrasive tool is a preset value.

8. The method for predicting the sharpness of abrasive tools according to claim 1, wherein: The method further comprises: obtaining the product removal amount; According to the product removal amount and the predicted sharpness, the target positive pressure corresponding to the grinding tool is determined so as to perform surface processing on the next product based on the target positive pressure.

9. A method for training a grinding tool sharpness prediction model, characterized in that: The method comprises: Acquire multiple historical surface processing information generated when processing equipment processes the surfaces of multiple products and multiple historical removal amounts of the corresponding products; Determining historical friction and historical normal pressure between a grinding tool of the processing equipment and the product based on the historical surface processing information; Determining the historical sharpness of the abrasive tool of the corresponding product based on the historical removal amount and the historical normal pressure; The historical sharpness, the historical friction force and the historical normal pressure are input into a model for training to form a sharpness prediction model.

10. The method for training a grinding tool sharpness prediction model according to claim 9, characterized in that: The acquisition of multiple historical surface processing information generated when the processing equipment processes the surfaces of multiple products includes: Acquire the historical surface processing information carried at each historical time point generated when the processing equipment processes a single surface of the product; Based on the historical surface processing information carried by each historical time point and a preset time point extraction range, extracting the historical surface processing information carried by the historical time point corresponding to the preset time point extraction range; The historical surface processing information carried by the historical time points corresponding to the preset time point extraction range is determined as the historical surface processing information.

11. The method for training a grinding tool sharpness prediction model according to claim 9, characterized in that: The historical surface processing information includes a historical force sensor signal, and determining the historical friction force between the grinding tool of the processing equipment and the product according to the historical surface processing information includes: Performing frequency domain transformation on the historical force sensor signal to obtain historical frequency spectrum data; Determining target historical amplitudes corresponding to a plurality of frequencies from the historical spectrum data according to a preset frequency range; Determining a maximum target historical amplitude based on the target historical amplitudes corresponding to the multiple frequencies; Performing filtering processing on the historical force sensor signal to obtain a historical filtered signal; The historical friction force is calculated according to the maximum target historical amplitude and the historical filtered signal.

12. The method for training a grinding tool sharpness prediction model according to claim 9, characterized in that: The historical surface processing information includes historical motor current and historical motor speed. The determining of the historical positive pressure between the grinding tool of the processing equipment and the product according to the historical surface processing information includes: Determining historical motor power according to the historical motor current; The historical positive pressure is calculated according to the historical motor power and the historical motor speed.

13. An electronic device, characterized in that: The electronic device comprises: a memory storing at least one instruction; and The processor executes the at least one instruction to implement the tool sharpness prediction method according to any one of claims 1 to 8 or the tool sharpness prediction model training method according to any one of claims 9 to 12.

Images