Control boundary determination method, apparatus, electronic device and computer readable storage medium

Abstract

Disclosed in the present application are a control boundary determination method, an apparatus, an electronic device and a computer readable storage medium. The method comprises: acquiring actual processing parameters of a tool in the processing process and control parameters of the tool, wherein the control parameters are allowable abnormal values of the tool; on the basis of the processing scenario, calling a boundary threshold value model; and inputting the actual processing parameters and the control parameters into the boundary threshold value model, so as to acquire control boundaries. Thus, by inputting the actual processing parameters and the control parameters into the boundary threshold value model, the control boundaries can be generated, thus improving the objectivity, accuracy and generation efficiency of the control boundaries.

Description

Control boundary determination method, device, electronic device and computer-readable storage medium

[0001] The present invention claims priority to a Chinese patent application filed with the Patent Office of China on December 6, 2023, with application number 202311674662.2, entitled “Management and Control Boundary Determination Method, Device, Electronic Device and Computer Storage Medium,” the entire contents of which are incorporated herein by reference. Technical Field

[0002] The present invention relates to the technical field of machine tool processing monitoring, and in particular to a control boundary determination method, a control boundary determination device, an electronic device, and a computer-readable storage medium. Background Art

[0003] When CNC machine tools process workpieces, various parameters must be monitored and controlled to ensure machining quality, safe production, and proper operation of the equipment. A common monitoring method involves setting control boundaries for the machining process to monitor whether the actual physical quantities being processed exceed these boundaries.

[0004] At present, the method of setting control boundaries is mainly based on manual experience to directly determine the control boundaries of the workpiece to be processed. This control boundary set by experience has problems such as subjectivity, instability and lag, which may affect the quality and efficiency of processing. Summary of the Invention

[0005] The main technical problem solved by this application is to provide a control boundary determination method, a control boundary determination device, an electronic device and a computer-readable storage medium, which can determine the control boundary according to the boundary threshold model, thereby improving the objectivity and accuracy of the control boundary setting.

[0006] In order to solve the above technical problems, a technical solution adopted in this application is: to provide a method for determining a control boundary, the method comprising: obtaining the actual processing parameters of the tool during the processing and the control parameters of the tool, the control parameters being abnormal values ​​allowed for the tool; based on the processing scenario, calling a boundary threshold model; inputting the actual processing parameters and the control parameters into the boundary threshold model to obtain a control boundary.

[0007] In order to solve the above technical problems, another technical solution adopted in this application is: to provide a control boundary determination device, the model includes: an acquisition module, used to obtain the actual processing parameters of the tool during the processing process and the control parameters of the tool, the control parameters are abnormal values ​​allowed for the tool; a calling module, used to call the boundary threshold model based on the processing scenario; an input module, used to input the actual processing parameters and the control parameters into the boundary threshold model to obtain the control boundary.

[0008] To solve the above technical problems, another technical solution adopted in this application is: to provide an electronic device, including a memory and a processor, the memory storing program instructions, and the processor calling the program instructions from the memory to execute the above-mentioned control boundary determination method.

[0009] In order to solve the above technical problems, another technical solution adopted in this application is: providing a computer-readable storage medium including program data stored therein, and the program data is used to implement the above-mentioned control boundary determination method when executed by a processor.

[0010] Compared to the control boundaries currently set by experience for monitoring machine tool processing, which are subject to certain subjectivity and inaccuracy, the above scheme provides a method for determining the control boundary. The method includes: obtaining the actual processing parameters of the tool during the processing and the control parameters of the tool, where the control parameters are the values ​​that allow the tool to be abnormal; based on the processing scenario, calling a boundary threshold model; and inputting the actual processing parameters and the control parameters into the boundary threshold model to obtain the control boundary. Thus, by inputting the actual processing parameters and the control parameters into the boundary threshold model, the control boundary can be generated, which can improve the objectivity, accuracy, and generation efficiency of the control boundary. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. Those skilled in the art can also derive other drawings based on these drawings without inventive work, among which:

[0012] FIG1 is a flow chart of an exemplary embodiment of a method for determining a control boundary provided by the present application;

[0013] FIG2 is a flow chart of an exemplary embodiment of step S130 in the method for determining a control boundary shown in FIG1 ;

[0014] FIG3 is a flow chart of an exemplary embodiment of step S210 in the method for determining a control boundary shown in FIG2 ;

[0015] FIG4 is a flow chart of an exemplary embodiment of step S320 in the method for determining a control boundary shown in FIG3 ;

[0016] FIG5 is a flowchart of an exemplary embodiment of step S330 in the method for determining a control boundary shown in FIG3 ;

[0017] FIG6 is a flowchart of an exemplary embodiment of step S310 in the method for determining a control boundary shown in FIG3 ;

[0018] FIG7 is a flow chart of an exemplary embodiment of step S220 in the method for determining a control boundary shown in FIG2 ;

[0019] FIG8 is a flowchart of another exemplary embodiment of step S220 in the method for determining the control boundary shown in FIG2 ;

[0020] FIG9 is a flowchart of another exemplary embodiment of step S230 in the method for determining the control boundary shown in FIG2 ;

[0021] FIG10 is a flowchart of another exemplary embodiment of step S120 in the method for determining the control boundary shown in FIG1 ;

[0022] FIG11 is a schematic diagram of a specific flow chart of an exemplary embodiment of a method for determining a control boundary provided by the present application;

[0023] FIG12 is a schematic diagram of the specific structure of an exemplary embodiment of a control boundary determination device provided by the present application;

[0024] FIG13 is a schematic structural diagram of an electronic device according to an embodiment of the present application;

[0025] FIG14 is a schematic structural diagram of an embodiment of a computer-readable storage medium provided in the present application. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It will be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for ease of description, only some, rather than all, structures related to the present application are shown in the drawings. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0027] First, it's important to note that control boundaries refer to the boundaries within which key parameters and quality indicators are monitored and controlled during the machining process. In existing technology, control boundaries for machining are typically set by experienced on-site technicians. This approach is subjective and inaccurate, and can easily lead to different control boundaries for the same process, resulting in inconsistent workpiece quality.

[0028] This application provides a control boundary determination method applicable to machine tool processing. Specifically, the method involves obtaining the actual machining parameters of the tool during the machining process and the tool's control parameters, which are the values ​​that allow the tool to have abnormal values. Based on the machining scenario, a boundary threshold model is called; the actual machining parameters and the control parameters are input into the boundary threshold model to obtain the control boundary. This allows the control boundary to be calculated through modeling, ensuring the objectivity and accuracy of the control boundary.

[0029] The control boundary determination method of this application can be applied to the following industrial Internet scenarios.

[0030] In a possible system architecture for an industrial internet scenario, servers, edge devices, and CNC machine tools are included. The server and CNC machine tools can communicate directly, or indirectly through an edge computer. Furthermore, the server can be an industrial cloud platform, a physical server, or a physical server device. The industrial cloud platform can be a public cloud platform or an enterprise's private cloud platform. The physical server can be a single physical server or a server group formed by multiple physical servers. Edge devices are used to collect information and act as an intermediary to facilitate communication between the server and CNC machine tools. A single edge device can correspond to multiple CNC machine tools, and multiple edge devices correspond one to each CNC machine tool associated with them.

[0031] The execution subject of the control boundary determination method of the present application can directly execute the following embodiments through a CNC machine tool, or can control the CNC machine tool to execute through an edge computer, and the specific details are not limited here.

[0032] The control boundary determination method of the present application is now described in combination with the above-mentioned architecture. It should be understood that this description is only exemplary and the present application is not limited to the implementation method under this description.

[0033] Please refer to Figure 1, which is a flowchart of an exemplary embodiment of the control boundary determination method provided by this application. Specifically, the control boundary determination method of this embodiment may include the following steps:

[0034] S110: Acquire actual machining parameters of the tool during the machining process and the tool's control parameters, where the control parameters are abnormal values ​​that allow the tool to be machined.

[0035] Cutting tools refer to tools used for cutting, turning, milling, and other operations in machine tool processing. For example, cutting tools can be milling cutters, turning tools, drill bits, etc. The appropriate cutting tool can be selected based on the hardness and toughness of the workpiece material and the process requirements.

[0036] Actual machining parameters refer to a series of parameters used to control and adjust the tool during the machining process. For example, these parameters can be determined based on factors such as the workpiece material being machined, tool performance, and machining requirements. For example, these parameters may include the width of cut, depth of cut, and tool feed rate.

[0037] A control parameter can be the maximum allowable tool abnormality. For example, if a tool abnormality is caused by wear or breakage during machining, the tool wear value can be quantified, such as 1mm, 2mm, or 3mm. During machining, a certain degree of tool wear does not affect machine processing. Therefore, a maximum allowable tool abnormality value can be set to monitor the machining process. This maximum abnormality value indicates the point at which tool wear will affect machining.

[0038] The control boundary determination device obtains the actual processing parameters of the input tool during the processing and the control parameters of the tool.

[0039] S120: Based on the processing scenario, call the boundary threshold model.

[0040] A processing scenario refers to a process method selected based on processing requirements. For example, these include milling, turning, and grinding. Different processing scenarios require different tools and workpiece process requirements, leading to different methods for determining control boundaries. To this end, a processing scenario library can be pre-established, with each scenario corresponding to a boundary threshold model.

[0041] The boundary threshold model is used to generate control boundaries based on actual machining parameters and control parameters. For example, if the current machining scenario is turning, the control boundary can be the machine tool machining power corresponding to the control parameters; if the current machining scenario is milling, the control boundary can be the machine tool vibration frequency corresponding to the control parameters.

[0042] The control boundary determination device calls the boundary threshold model corresponding to the current processing scenario from a pre-established processing scenario library according to the current processing scenario of the workpiece.

[0043] S130: Inputting actual processing parameters and control parameters into the boundary threshold model to obtain the control boundary.

[0044] The control boundary is the physical quantity of the machine tool processing corresponding to the control parameter. The control boundary can include an upper boundary and a lower boundary. To ensure the quality and safety of the machine tool processing, when the processing physical quantity exceeds the control boundary, the operator or the CNC machine tool can perform a correction operation to restore the processing physical quantity to within the control boundary. Among them, the processing physical quantity can be the processing power. For example, if the cause of the abnormality is that the machine tool processing physical quantity exceeds the processing power corresponding to the control boundary during the processing process, the machine tool processing can be restored to normal by switching the tool.

[0045] For example, in order to better monitor the machine tool processing process, an alarm function can be set. When the machine tool's processing signal exceeds the control boundary, an alarm will be used to warn of the processing abnormality, serving as a warning.

[0046] The control boundary determination device inputs the actual processing parameters and the control parameters into the boundary threshold model to obtain the control boundary and can control the processing process based on the control boundary. For example, the actual processing parameters and the control parameters can be input through the processing code or by the operator using a touch screen or external input device.

[0047] As can be seen, the control boundary determination method of the embodiment of the present application obtains the actual processing parameters of the tool during the machining process and the tool's control parameters, which are the values ​​that allow the tool to be abnormal. Based on the machining scenario, a boundary threshold model is called; the actual processing parameters and the control parameters are input into the boundary threshold model to obtain the control boundary. Thus, by inputting the actual processing parameters and the control parameters into the boundary threshold model, a control boundary can be generated, which can improve the objectivity, accuracy, and generation efficiency of the control boundary.

[0048] Based on the above embodiment, the present embodiment uses the flowchart of Figure 2 to explain in detail how to obtain the control boundary based on the boundary threshold model. Please refer to Figure 2, which is a flowchart of an exemplary embodiment of step S130 in the control boundary determination method shown in Figure 1. Specifically, step S130, the process of inputting the actual processing parameters and the control parameters into the boundary threshold model to obtain the control boundary specifically includes the following steps:

[0049] First, it should be noted that the boundary threshold model includes a first sub-model and a second sub-model, wherein the first sub-model may be a physical model and the second sub-model may be a big data model, such as a neural network model.

[0050] S210: Based on the first sub-model, determine a first machining physical quantity according to actual machining parameters, where the first machining physical quantity is a machining physical quantity when there is no abnormality in the tool.

[0051] The first sub-model is determined by the processing scenario, and different processing scenarios call different first sub-models. For example, when the processing scenario is turning, the first sub-model corresponding to turning is called, and when the processing scenario is milling, the first sub-model corresponding to milling is called.

[0052] The first machining physical quantity is the result output by the first sub-model based on the actual machining parameters. For example, the first machining physical quantity may be a physical quantity such as machine tool machining power, vibration in the cutting area, or sound in the cutting area. For example, when the machining scenario is turning, the first sub-model may output machine tool machining power; when the machining scenario is milling, the first sub-model may output vibration in the cutting area.

[0053] The first sub-model of the control boundary determination device performs theoretical calculations based on the input actual processing parameters to obtain the processing physical quantity when the machine tool processing is normal, and determines it as the first processing physical quantity.

[0054] S220: Based on the second sub-model, determine a second processing physical quantity according to the control parameter, where the second processing physical quantity is the processing physical quantity when the abnormal value of the tool is the control parameter.

[0055] The second sub-model is different from the first sub-model. The second sub-model may not be determined by the processing scenario, and different processing scenarios may correspond to the same second sub-model. For example, after the processing scenario is determined, the first sub-model corresponding to the processing scenario is called, and the second sub-model is called to form the boundary threshold model.

[0056] The second processing physical quantity is the result output by the second sub-model according to the control parameters, indicating the change in the processing physical quantity of the machine tool relative to the first processing physical quantity when the abnormal value of the tool is the control parameter.

[0057] The control boundary determination device inputs the control parameters into the second sub-model, and the second sub-model determines the second processing physical quantity according to the control parameters.

[0058] S230: Determine a control boundary according to the first processing physical quantity and the second processing physical quantity.

[0059] After the control boundary determination device determines the first processing physical quantity and the second processing physical quantity by using the first sub-model and the second sub-model, the control boundary of the machine tool processing can be determined by using the first processing physical quantity and the second processing physical quantity.

[0060] It can be seen that the control boundary determination method of the embodiment of the present application is based on the first sub-model, which determines the first processing physical quantity from the actual processing parameters. The first processing physical quantity is the processing physical quantity when the tool is normal. Based on the second sub-model, the second processing physical quantity is determined from the control parameters. The second processing physical quantity is the tool abnormal value, that is, the processing physical quantity that deviates from the first processing physical quantity. The control boundary is determined based on the first and second processing physical quantities. In this way, the first and second processing physical quantities can be determined based on the first and second sub-models, which has the characteristics of simple modeling and high computational efficiency.

[0061] Based on the above embodiment, the present embodiment uses the flowchart of Figure 3 to explain in detail how to determine the first processing physical quantity based on the actual processing parameters. Please refer to Figure 3, which is a flowchart of an exemplary embodiment of step S210 in the control boundary determination method shown in Figure 2. Specifically, step S210, based on the first sub-model, the process of determining the first processing physical quantity based on the actual processing parameters specifically includes the following steps:

[0062] S310: Obtaining expected machining physical quantities when the tool in the first sub-model is normal and preset machining physical quantities of the tool in the first sub-model.

[0063] The expected machining physical quantity refers to the normal machining physical quantity in the actual machining process. For example, the expected machining physical quantity when the tool is normal can be obtained through experiments, and the obtained expected machining physical quantity is input into the first sub-model.

[0064] The preset processing physical quantity is a processing physical quantity obtained by theoretical calculation based on actual processing parameters. For example, when the same process is used for processing, the preset processing physical quantity obtained by theoretical calculation should be the same.

[0065] The control boundary determination device inputs the expected processing physical quantities and actual processing parameters obtained through experiments into the first sub-model, and the first sub-model obtains the preset processing physical quantities according to the actual processing parameters.

[0066] S320: Determine cutting correction parameters according to the desired processing physical quantity and the preset processing physical quantity.

[0067] Cutting correction parameters improve the accuracy of the first sub-model's output. The preset machining quantities calculated based on actual machining parameters are theoretically derived and may deviate from the actual machining process. Therefore, setting correction coefficients can correct for these theoretical calculation errors.

[0068] After obtaining the expected processing physical quantity and the preset processing physical quantity, the first sub-model in the control boundary determination device determines the cutting correction parameter according to the expected processing physical quantity and the preset processing physical quantity.

[0069] S330: Correcting the actual machining parameters input into the first sub-model based on the cutting correction parameters to obtain a first machining physical quantity output by the first sub-model.

[0070] The first sub-model in the control boundary determination device derives a preset machining physical quantity based on the actual machining parameters and determines a cutting correction parameter based on the desired machining physical quantity and the preset machining physical quantity. In actual applications, the cutting correction parameters for the same process are the same. Therefore, when performing the same process, the first machining physical quantity output by the first sub-model can be directly derived from the actual machining parameters and the cutting correction parameters.

[0071] As can be seen, the control boundary determination method of the embodiment of the present application obtains the expected machining physical quantity when the tool is normal in the first sub-model and the preset machining physical quantity of the tool in the first sub-model; determines the cutting correction parameter based on the expected machining physical quantity and the preset machining physical quantity; and corrects the actual machining parameter input into the first sub-model based on the cutting correction parameter to obtain the first machining physical quantity output by the first sub-model. This can improve the accuracy of the first machining physical quantity.

[0072] Based on the above embodiment, the present embodiment uses the flowchart of Figure 4 to explain in detail how to determine the cutting correction parameter. Please refer to Figure 4, which is a flowchart of an exemplary embodiment of step S320 in the control boundary determination method shown in Figure 3. Specifically, step S320, the process of determining the cutting correction parameter based on the desired processing physical quantity and the preset processing physical quantity, specifically includes the following steps:

[0073] S410: Calculating a ratio between the desired processing physical quantity and the preset processing physical quantity.

[0074] The first sub-model of the control boundary determination device obtains the expected processing physical quantity and the preset processing physical quantity and calculates the ratio between the expected processing physical quantity and the preset processing physical quantity.

[0075] S420: Use the ratio as a cutting correction parameter.

[0076] The control boundary determination device uses the ratio between the expected processing physical quantity and the preset processing physical quantity as the cutting correction parameter.

[0077] As can be seen, the control boundary determination method of the embodiment of the present application calculates the ratio between the desired machining physical quantity and the preset machining physical quantity and uses this ratio as a cutting correction parameter. This can minimize the deviation between the first machining physical quantity obtained by the first sub-model and the desired machining physical quantity, thus closer to the actual machining.

[0078] Based on the above embodiment, the present embodiment uses the flowchart of Figure 5 to further illustrate how to calculate the first machining physical quantity. Please refer to Figure 5, which is a flowchart of an exemplary embodiment of step S330 in the control boundary determination method shown in Figure 3. Specifically, step S330 corrects the actual machining parameters input into the first sub-model based on the cutting correction parameters to obtain the first machining physical quantity output by the first sub-model, which specifically includes the following steps:

[0079] First of all, it should be noted that this embodiment takes turning as an example of the processing scenario. Other processing scenarios such as milling, grinding, etc. can be processed in accordance with the turning processing examples provided in the embodiments of this application under the guidance of the turning processing examples provided in the embodiments of this application.

[0080] In turning, the actual machining parameters include the cutting width, cutting depth, linear speed and material strength of the workpiece during the tool machining process.

[0081] S510: Calculate the first product of cutting width, cutting depth, linear speed and material strength.

[0082] The cutting width refers to the width of the cut made by the tool on the workpiece; the cutting depth refers to the cutting depth of the tool perpendicular to the surface of the workpiece.

[0083] Linear velocity refers to the speed at which the cutting edge of a tool moves relative to the workpiece surface during machining. For example, the linear velocity can be calculated by the product of the diameter of the rotating body and the rotational speed.

[0084] Material strength refers to the ability of the material of the workpiece to resist deformation and damage.

[0085] The control boundary determination device obtains the actual processing parameters of cutting width, cutting depth, linear speed and material strength, and calculates the first product between the cutting width, cutting depth, linear speed and material strength.

[0086] S520: Calculate a second product of the preset multiple, the first product, and the cutting correction parameter.

[0087] For example, the preset multiple may be cutting efficiency, where cutting efficiency refers to the ability to remove material at a certain speed during a cutting process.

[0088] The control boundary determination device uses the product of the first product, the preset multiple and the cutting correction parameter as the second product.

[0089] S530: Use the second product as the first processing physical quantity output by the first sub-model.

[0090] The control boundary determination device calculates the second product based on the cutting width, cutting depth, linear speed, material strength, preset multiple and cutting correction parameters, and uses the second product as the first processing physical quantity output by the first sub-model.

[0091] As can be seen, the control boundary determination method of the embodiment of the present application calculates a first product of the cutting width, cutting depth, linear speed, and material strength; and calculates a second product of the first product, a preset multiple, and the cutting correction parameter. This allows the first machining physical quantity to be calculated in real time using the actual machining parameters.

[0092] Based on the above embodiment, the present embodiment uses the flowchart of Figure 6 to explain in detail how to calculate the preset processing physical quantity. Please refer to Figure 6, which is a flowchart of an exemplary embodiment of step S310 in the control boundary determination method shown in Figure 3. Specifically, step S310, the process of obtaining the preset processing physical quantity of the tool in the first sub-model, specifically includes the following steps:

[0093] First of all, it should be noted that this embodiment also takes turning as an example. In turning, the actual processing parameters include the cutting width, cutting depth, linear speed and material strength of the workpiece during the tool processing process.

[0094] S610: Determine the cutting cross-sectional area according to the cutting width and cutting depth.

[0095] The cutting width refers to the width of the cut made by the tool on the workpiece; the cutting depth refers to the cutting depth of the tool perpendicular to the surface of the workpiece.

[0096] Cutting cross-sectional area refers to the cross-sectional area of ​​the workpiece material per tool revolution during turning. For example, the cutting cross-sectional area can be obtained by multiplying the cutting width and cutting depth.

[0097] The control boundary determination device calculates the product between the cutting width and the cutting depth to determine the cutting cross-sectional area processed by the machine tool.

[0098] S620: Determine the main cutting resistance based on material strength and cutting cross-sectional area.

[0099] The main cutting resistance refers to the cutting force in the main motion direction, that is, the force resisting the removal of material when the tool cuts into the material. For example, the main cutting resistance can be obtained by calculating the product between the material strength and the cutting cross-sectional area.

[0100] The control boundary determination device calculates the product of material strength and cutting cross-sectional area to determine the main cutting resistance of machine tool processing.

[0101] S630: Determine the preset processing physical quantity according to the linear speed and the main cutting resistance.

[0102] The control boundary determination device can obtain the preset processing physical quantity by calculating the product of the linear speed, the main cutting resistance and the cutting efficiency.

[0103] As can be seen, the control boundary determination method of the present embodiment determines the cutting cross-sectional area based on the cutting width and cutting depth; determines the primary cutting resistance based on the material strength and cutting cross-sectional area; and determines the preset machining physical quantity based on the linear speed and primary cutting resistance. This allows the preset machining physical quantity to be obtained in real time based on the actual machining parameters of the current tool.

[0104] Based on the above embodiment, the present embodiment uses the flowchart of Figure 7 to explain in detail how to obtain the second processing physical quantity. Please refer to Figure 7, which is a flowchart of an exemplary embodiment of step S220 in the control boundary determination method shown in Figure 2. Specifically, step S220, based on the second sub-model, the process of determining the second processing physical quantity from the control parameters specifically includes the following steps:

[0105] S710: Constructing a first relationship in the second sub-model according to the historical abnormal values ​​of the tool and the tool processing physical quantities corresponding to each historical abnormal value, wherein the first relationship refers to the correspondence between the historical abnormal values ​​of the tool and the tool processing physical quantities corresponding to each historical abnormal value.

[0106] The historical abnormal value refers to the abnormal value of the tool obtained through experiments. For example, the historical abnormal value of the tool can be the wear degree of the tool, for example, the historical abnormal value can be the tool wear of 1mm, 2mm and 3mm.

[0107] Tool processing physical quantity refers to the tool processing physical quantity corresponding to the abnormal value of the tool.

[0108] The first relationship refers to the relationship between the tool's historical outliers and the tool's physical quantities corresponding to each historical outlier. As an example, the first sub-model determines that the tool's first processing physical quantity is 1 kW. When the tool's outlier value is 1 mm, the corresponding tool processing physical quantity is 1.2 kW. When the tool's outlier value is 2 mm, the corresponding tool processing physical quantity is 1.4 kW. When the tool's outlier value is 3 mm, the corresponding tool processing physical quantity is 1.6 kW. Through the relationship between the historical outliers and the tool's physical quantities corresponding to each historical outlier value, it can be found that for every 1 mm increase in wear value, the tool's processing physical quantity will increase by 0.2 kW accordingly. The second relationship between the tool's historical outliers and the change in the processing physical quantity corresponding to each historical outlier value relative to the first processing physical quantity is y = 0.2x, where y represents the change in the processing physical quantity corresponding to each historical outlier value relative to the first processing physical quantity, and x represents the historical outlier value.

[0109] The second sub-model in the control boundary determination device constructs a first relationship based on the historical abnormal values ​​of the tool and the tool processing physical quantities corresponding to each historical abnormal value, and obtains the change law of the tool processing physical quantities corresponding to each historical abnormal value from the first relationship, thereby obtaining the relationship between the historical abnormal values ​​of the tool and the processing physical quantities corresponding to each historical abnormal value relative to the change value of the first processing physical quantity.

[0110] S720: Determine, from the first relationship of the second sub-model according to the control parameter, a second machining physical quantity when the abnormal value of the tool is the control parameter.

[0111] The control parameter can be the maximum abnormal value that allows tool abnormality. The second sub-model of the control boundary determination device obtains the input control parameter and determines the second processing physical quantity based on the input control parameter. As a possible example, according to the first relationship, the relationship between the historical abnormal values ​​of the tool and the change value of the tool processing physical quantity corresponding to each historical abnormal value relative to the first processing physical quantity is y = 0.2x. If the input control parameter is 5mm, it can be concluded that the second processing physical quantity is 1kw.

[0112] The control boundary determination device obtains the control parameter and determines the second machining physical quantity when the abnormal value of the tool is the control parameter from the first relationship of the second sub-model according to the control parameter.

[0113] It can be seen that the control boundary determination method of the embodiment of the present application constructs a first relationship in the second sub-model based on the historical abnormal values ​​of the tool and the tool processing physical quantity corresponding to each historical abnormal value. The first relationship refers to the correspondence between each historical abnormal value of the tool and the tool processing physical quantity corresponding to each historical abnormal value; based on the control parameter, the second processing physical quantity when the tool abnormal value is the control parameter is determined from the first relationship of the second sub-model. This can obtain the variation pattern of the tool processing physical quantity corresponding to the tool abnormal value, and then obtain the second processing physical quantity corresponding to each abnormal value based on this variation pattern, thereby improving the computational efficiency of the second processing physical quantity and reducing the operational difficulty.

[0114] Based on the above embodiment, the present embodiment uses the flowchart of Figure 8 to explain in detail how to use the neural network model to obtain the second processing physical quantity. Please refer to Figure 8, which is a flowchart of another exemplary embodiment of step S220 in the control boundary determination method shown in Figure 2. Specifically, step S220, based on the second sub-model, the process of determining the second processing physical quantity from the control parameters specifically includes the following steps:

[0115] S810: Input the acquired abnormal value samples of the tool and the tool processing physical quantity samples corresponding to each abnormal value sample into the second sub-model to obtain the tool processing physical quantity output by the second sub-model.

[0116] An abnormal value sample refers to an abnormal value of a tool obtained through debugging or experimentation. For example, taking tool wear as an abnormality, the abnormal value of the tool may be wear of 1mm, 2mm, or 3mm.

[0117] The tool processing physical quantity refers to the change in the processing physical quantity obtained by monitoring the processing process when the tool is processed under various abnormal values. For example, taking the wear of the tool as an abnormality, when the abnormal value of the tool is 1mm of wear, the corresponding tool processing physical quantity is 2kw, when the abnormal value of the tool is 2mm of wear, the corresponding tool processing physical quantity is 4kw, when the abnormal value of the tool is 3mm of wear, the corresponding tool processing physical quantity is 6kw, and so on. It can be understood that the tool processing physical quantity and the abnormal value of the tool are not necessarily in a linear relationship, and can be obtained through training according to actual conditions. This application does not impose any restrictions on this.

[0118] In another possible example, the abnormal value sample of the tool can also be an abnormal signal, that is, a waveform diagram. The abnormal processing signal of the tool in a certain processing scenario can be input into the second sub-model for training, so as to directly generate upper and lower control boundaries based on the output results of the first sub-model.

[0119] The control boundary determination device inputs the acquired abnormal value samples of the tool and the tool processing physical quantity samples corresponding to each abnormal value sample into the second sub-model to obtain the tool processing physical quantity output by the second sub-model.

[0120] S820: Calculate the loss function between the tool processing physical quantity output by the second sub-model and the tool processing physical quantity sample.

[0121] The loss function is a function that measures the difference between the tool processing physical quantity output by the second sub-model and the tool processing physical quantity. For example, it can be calculated using a mean square error loss function, a cross entropy loss function, or the like.

[0122] After obtaining the tool processing physical quantity output by the second sub-model, the control boundary determination device calculates the loss function between the tool processing physical quantity output by the second sub-model and the tool processing physical quantity sample.

[0123] S830: Train the second sub-model with the goal of reducing the loss value of the loss function to obtain a trained second sub-model.

[0124] The smaller the loss function, the closer the tool processing physical quantity output by the second sub-model is to the tool processing physical quantity, and the more accurate the output of the second sub-model is. The loss function can be reduced by updating the model parameters to complete the training of the second sub-model.

[0125] The control boundary determination device continuously updates the parameters of the second sub-model with the goal of reducing the loss value of the loss function until the loss function drops to an acceptable level, thereby obtaining a trained second sub-model.

[0126] S840: Input the control parameters into the trained second sub-model to obtain the tool processing physical quantity corresponding to the control parameters output by the second sub-model, and use the tool processing physical quantity corresponding to the control parameters as the second processing physical quantity.

[0127] The trained second sub-model can determine the tool processing physical quantity corresponding to the input tool abnormality value based on the abnormal value. The control boundary determination device inputs the control parameters into the trained second sub-model. The second sub-model outputs the corresponding tool processing physical quantity based on the control parameters, and determines the tool processing physical quantity as the second processing physical quantity.

[0128] It can be seen that the control boundary determination method of the embodiment of the present application inputs the acquired outlier value samples of the tool and the tool processing physical quantity samples corresponding to each outlier sample into the second sub-model to obtain the tool processing physical quantity output by the second sub-model; calculates the loss function between the tool processing physical quantity output by the second sub-model and the tool processing physical quantity samples; trains the second sub-model with the goal of minimizing the loss value of the loss function to obtain a trained second sub-model; inputs the control parameters into the trained second sub-model to obtain the tool processing physical quantity corresponding to the control parameters output by the second sub-model, and uses the tool processing physical quantity corresponding to the control parameters as the second processing physical quantity. The above method can improve the accuracy and generation efficiency of the second processing physical quantity.

[0129] Based on the above embodiment, the present embodiment uses the flowchart of FIG9 to explain in detail how to determine the control boundary based on the first processing physical quantity and the second processing physical quantity. Please refer to FIG9, which is a flowchart of another exemplary embodiment of step S230 in the control boundary determination method shown in FIG2. Specifically, step S230, the process of determining the control boundary based on the first processing physical quantity and the second processing physical quantity, specifically includes the following steps:

[0130] S910: Calculate the physical quantity sum between the first processing physical quantity and the second processing physical quantity.

[0131] The control boundary determination device obtains a first processing physical quantity output by the first sub-model and a second processing physical quantity output by the second sub-model, and calculates a physical quantity sum between the first processing physical quantity and the second processing physical quantity.

[0132] S920: Use physical quantities and as control boundaries.

[0133] Since the second machining physical quantity is the change value corresponding to when the tool's abnormal value is the control parameter, the sum of the first and second machining physical quantities can be expressed as the tool machining physical quantity corresponding to when the tool's abnormal value is the control parameter. Using the sum of the physical quantities as the control boundary means that the tool's machining physical quantity during actual machining cannot exceed the tool machining physical quantity corresponding to when the tool's abnormal value is the control parameter.

[0134] The control boundary determination device uses the sum of the physical quantities between the first processing physical quantity and the second processing physical quantity as the control boundary to monitor whether the tool processing physical quantity exceeds the maximum abnormal value allowed for the tool during the processing.

[0135] As can be seen, the control boundary determination method of the embodiment of the present application calculates the physical quantity sum between the first processing physical quantity and the second processing physical quantity and uses the physical quantity sum as the control boundary. This allows the control boundary to be determined directly from the sum of the two, thereby simplifying the method for determining the control boundary.

[0136] Based on the above embodiment, the present embodiment uses the flowchart of Figure 10 to explain in detail how to determine the control boundary based on the first processing physical quantity and the second processing physical quantity. Please refer to Figure 10, which is a flowchart of another exemplary embodiment of step S120 in the control boundary determination method shown in Figure 1. Specifically, step S120, based on the processing scenario, the process of calling the boundary threshold model specifically includes the following steps:

[0137] S1010: calling a boundary threshold model based on a processing scene classification model, wherein the processing scene classification model is trained using the processing scene as a label and the boundary threshold model corresponding to the processing scene as input.

[0138] The processing scenario classification model is used to call the corresponding boundary threshold model according to different processing scenarios.

[0139] Machine tool processing uses different processing scenarios based on different process requirements. For example, these scenarios can include milling, turning, and grinding. Therefore, these processing scenarios and their corresponding boundary threshold models can be used as inputs to a processing scenario classification model. The model is then trained using the processing scenarios as labels to produce a trained processing scenario classification model.

[0140] After the training is completed, the processing scene classification model can obtain the corresponding boundary threshold model through the processing scene.

[0141] The control boundary determination device inputs the processing scene and the boundary threshold model corresponding to the processing scene into the processing scene classification model for training, obtains the trained processing scene classification model, and calls the boundary threshold model based on the trained processing scene classification model.

[0142] As can be seen, the control boundary determination method of the embodiment of the present application calls the boundary threshold model based on the processing scenario classification model. The processing scenario classification model uses the processing scenario as a label and is trained using the boundary threshold model corresponding to the processing scenario as input. Therefore, the boundary threshold model corresponding to the current processing scenario is obtained through the processing scenario classification model, which can improve the adaptability and flexibility of the boundary threshold model.

[0143] In order to elaborate on the method for determining the control boundary of the present application, the flowchart shown in FIG11 is used to further illustrate it. The details are as follows:

[0144] The first is the modeling process. The cutting parameters and control parameters are input into the first sub-model without abnormal processing signals. The control parameters without abnormal processing signals are also the expected processing physical quantities. The non-abnormal signals under the cutting parameters are calculated according to the classical signal model theory, which are also the preset processing physical quantities. Among them, K in the cutting parameters represents material strength, Vc represents linear speed, ae represents cutting width, and ap represents cutting depth. The correction coefficient is calculated based on the control parameters without abnormal processing signals and the theoretically calculated non-abnormal signals, that is, the cutting correction parameters are calculated based on the expected processing physical quantities and the preset processing physical quantities. The second sub-model is used to fit the input abnormal processing signals and the corresponding control parameters to obtain the change law of the abnormal processing signals. The corresponding control parameters here refer to the historical abnormal values, and the abnormal processing signals are also the tool processing physical quantities corresponding to each historical abnormal value. Finally, the total parameter correction model, that is, the boundary threshold model, is obtained by combining the first and second sub-models.

[0145] Secondly, the cutting parameters and target control parameters are input into the total parameter correction model to obtain the target process signal control boundary, where the cutting parameters are the actual processing parameters, the target control parameters are the control parameters, and the target process signal control boundary is the control boundary.

[0146] Please refer to Figure 12, which is a schematic diagram of an exemplary embodiment of a control boundary determination device provided in this application. Control boundary determination device 12 includes an acquisition module 1201, a call module 1202, and an input module 1403. Acquisition module 1201 is used to obtain the actual machining parameters of the tool during the machining process and the tool's control parameters, which are the values ​​that allow the tool to have abnormal values. Call module 1202 is used to call the boundary threshold model based on the machining scenario. Input module 1403 is used to input the actual machining parameters and the control parameters into the boundary threshold model to obtain the control boundary.

[0147] In the above scheme, the control boundary determination device 12 of the embodiment of the present application obtains the actual processing parameters of the tool during the machining process and the control parameters of the tool. The control parameters are the values ​​that allow the tool to be abnormal. Based on the machining scenario, the boundary threshold model is called. The actual processing parameters and the control parameters are input into the boundary threshold model to obtain the control boundary. Therefore, by inputting the actual processing parameters and the control parameters into the boundary threshold model, the control boundary can be generated, which can improve the objectivity, accuracy, and generation efficiency of the control boundary.

[0148] Among them, the functions of each module can be found in the implementation example of the control boundary determination method, which will not be repeated here.

[0149] In order to implement the control boundary determination method of the above embodiment, the present application proposes another electronic device. Please refer to Figure 13 for details. Figure 13 is a structural diagram of an embodiment of the electronic device provided by the present application.

[0150] The electronic device 13 includes a memory 1301 and a processor 1302 , wherein the memory 1301 and the processor 1302 are coupled.

[0151] The memory 1301 is used to store program data, and the processor 1302 is used to execute the program data to implement the control boundary determination method of the above embodiment.

[0152] In this embodiment, processor 1302 may also be referred to as a CPU (Central Processing Unit). Processor 1302 may be an integrated circuit chip with signal processing capabilities. Processor 1302 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. A general-purpose processor may be a microprocessor, or processor 1302 may be any conventional processor.

[0153] The present application also provides a computer-readable storage medium 14. As shown in FIG14 , the computer-readable storage medium 14 is used to store program data 1401. When the program data 1401 is executed by the processor, it is used to implement the control boundary determination method in the method embodiment of the present application.

[0154] The method involved in the embodiment of the method for determining the control boundary of the present application, when implemented in the form of a software functional unit and sold or used as an independent product, can be stored in a device, such as a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program code, such as a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0155] The above description is only an implementation method of the present application and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of this application, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for determining a control boundary, characterized in that: The method comprises: Acquire actual machining parameters of the tool during machining and control parameters of the tool, wherein the control parameters are abnormal values ​​that allow the tool; Based on the processing scenario, the boundary threshold model is called; The actual processing parameters and the control parameters are input into the boundary threshold model to obtain the control boundary.

2. The method for determining the control boundary according to claim 1, characterized in that: The boundary threshold model includes a first sub-model and a second sub-model; The step of inputting the actual processing parameters and the control parameters into the boundary threshold model to obtain the control boundary includes: Based on the first sub-model, determining a first machining physical quantity from the actual machining parameters, the first machining physical quantity being a machining physical quantity when the tool is normal; Based on the second sub-model, determining the second machining physical quantity by the control parameter, the second machining physical quantity being the machining physical quantity when the abnormal value of the tool is the control parameter; A control boundary is determined according to the first processing physical quantity and the second processing physical quantity.

3. The method for determining the control boundary according to claim 2, characterized in that: The step of determining the first processing physical quantity from the actual processing parameters based on the first sub-model includes: Acquire the expected machining physical quantity of the tool in the first sub-model when there is no abnormality and the preset machining physical quantity of the tool in the first sub-model; Determining a cutting correction parameter according to the desired processing physical quantity and the preset processing physical quantity; The actual processing parameters input into the first sub-model are corrected based on the cutting correction parameters to obtain the first processing physical quantity output by the first sub-model.

4. The method for determining the control boundary according to claim 3, characterized in that: The step of determining the cutting correction parameter according to the desired processing physical quantity and the preset processing physical quantity comprises: Calculating a ratio between the desired processing physical quantity and the preset processing physical quantity; The ratio is used as the cutting correction parameter.

5. The method for determining the control boundary according to claim 3, characterized in that: The actual processing parameters include the cutting width, cutting depth, linear speed and material strength of the workpiece during the tool processing; The step of correcting the actual processing parameters input into the first sub-model based on the cutting correction parameters to obtain the first processing physical quantity output by the first sub-model includes: Calculating a first product among the cutting width, the cutting depth, the linear speed and the material strength; Calculating a second product between the preset multiple, the first product and the cutting correction parameter; The second product is used as the first processing physical quantity output by the first sub-model.

6. The method for determining the control boundary according to claim 3, characterized in that: The actual processing parameters include: cutting width, cutting depth, linear speed and material strength of the processing material during the tool processing process; the step of obtaining the preset processing physical quantity of the tool in the first sub-model includes: Determine the cutting cross-sectional area according to the cutting width and cutting depth; Determining the main cutting resistance according to the material strength and the cutting cross-sectional area; The preset machining physical quantity is determined according to the linear speed and the main cutting resistance.

7. The method for determining the control boundary according to claim 2, characterized in that: The step of determining the second processing physical quantity by the control parameter based on the second sub-model includes: Constructing a first relationship in the second sub-model according to the historical abnormal values ​​of the tool and the tool processing physical quantities corresponding to each historical abnormal value, wherein the first relationship refers to the corresponding relationship between the historical abnormal values ​​of the tool and the tool processing physical quantities corresponding to each historical abnormal value; A second machining physical quantity when the abnormal value of the tool is the control parameter is determined from the first relationship of the second sub-model according to the control parameter.

8. The method for determining a control boundary according to claim 2, characterized in that: The step of determining the second processing physical quantity by the control parameter based on the second sub-model includes: Inputting the acquired abnormal value samples of the tool and the tool processing physical quantity samples corresponding to each abnormal value sample into the second sub-model to obtain the tool processing physical quantity output by the second sub-model; Calculating a loss function between a tool processing physical quantity output by the second sub-model and a sample of the tool processing physical quantity; Training the second sub-model with the goal of reducing the loss value of the loss function to obtain a trained second sub-model; The control parameters are input into the trained second sub-model to obtain the tool processing physical quantity corresponding to the control parameters output by the second sub-model, and the tool processing physical quantity corresponding to the control parameters is used as the second processing physical quantity.

9. The method for determining a control boundary according to claim 2, characterized in that: The step of determining the control boundary according to the first processing physical quantity and the second processing physical quantity comprises: calculating a physical quantity sum between the first processing physical quantity and the second processing physical quantity; The physical quantities and are used as the control boundaries.

10. The method for determining a control boundary according to claim 1, characterized in that: The step of calling the boundary threshold model based on the processing scenario includes: The boundary threshold model is called based on a processing scene classification model, wherein the processing scene classification model is trained by taking the processing scene as a label and taking the boundary threshold model corresponding to the processing scene as an input.

11. A control boundary determination device, characterized in that: The device comprises: An acquisition module, used for acquiring actual processing parameters of the tool during the processing and control parameters of the tool, wherein the control parameters are abnormal values ​​that allow the tool; A calling module is used to call the boundary threshold model based on the processing scenario; An input module is used to input the actual processing parameters and the control parameters into the boundary threshold model to obtain the control boundary.

12. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores program instructions, and the processor retrieves the program instructions from the memory to execute the method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: include: Program data is stored, and when the program data is executed by a processor, it is used to implement the method according to any one of claims 1 to 10.

Images