WO2023077275A1 - Machine tool machining precision prediction method and apparatus, storage medium, and electronic device - Google Patents

Machine tool machining precision prediction method and apparatus, storage medium, and electronic device Download PDF

Info

Publication number
WO2023077275A1
WO2023077275A1 PCT/CN2021/128236 CN2021128236W WO2023077275A1 WO 2023077275 A1 WO2023077275 A1 WO 2023077275A1 CN 2021128236 W CN2021128236 W CN 2021128236W WO 2023077275 A1 WO2023077275 A1 WO 2023077275A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
machine tool
simulation
machining accuracy
value
Prior art date
Application number
PCT/CN2021/128236
Other languages
French (fr)
Chinese (zh)
Inventor
林燕凌
周晓舟
傅玲
李婧
Original Assignee
西门子股份公司
西门子（中国）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 西门子股份公司, 西门子（中国）有限公司 filed Critical 西门子股份公司
Priority to CN202180102057.0A priority Critical patent/CN117940927A/en
Priority to PCT/CN2021/128236 priority patent/WO2023077275A1/en
Publication of WO2023077275A1 publication Critical patent/WO2023077275A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model

Definitions

  • the invention mainly relates to the field of machine tool machining accuracy prediction, and in particular to a machine tool machining accuracy prediction method, device, storage medium and electronic equipment.
  • Machine tool is the mother machine of the manufacturing system and the foundation of the manufacturing industry. At present, the level of intelligence and digitalization of most machine tools is generally low, which leads to the problems of insufficient machining accuracy and inaccurate prediction of machining accuracy of machine tools.
  • the machining accuracy of machine tools is usually judged by manually measuring the accuracy of machine tool parts samples, and the normal machining accuracy of machine tools is guaranteed by routine maintenance of machine tools and regular replacement of core components.
  • Another way is to install specific sensors near key parts to collect corresponding status signals during machine tool operation, and analyze the signal data to monitor the machining accuracy of the machine tool.
  • none of the related methods can accurately predict the machining accuracy of the machine tool, and it is difficult to effectively guarantee the continuous stability of the machining accuracy of the machine tool.
  • the present invention provides a machine tool machining accuracy prediction method, device, storage medium and electronic equipment, so as to achieve the purpose of accurately predicting the machine tool machining accuracy, and further ensure the continuous stability of machine tool machining accuracy.
  • the present invention proposes a method for predicting machining accuracy of machine tools, including: establishing a simulation model of the machining process of the machine tool; simplifying the simulation model to establish a first proxy model; accuracy for prediction. If the simulation through the simulation model of the complete machine tool processing process takes a long time to calculate, and by simplifying the simulation model to obtain a proxy model with a smaller amount of calculation, the simulation speed can be improved, so as to achieve real-time or quasi-real-time prediction The precision of machine tool processing.
  • the present invention also proposes a machine tool processing accuracy prediction device, including: a simulation module configured to establish a simulation model of the machine tool processing process; a simplification module configured to simplify the simulation model to establish a first proxy model; a prediction module, It is configured to predict the machining accuracy of the machine tool through the first proxy model.
  • the present invention also proposes an electronic device, including a processor, a memory, and instructions stored in the memory, wherein the instructions implement the method as described above when executed by the processor.
  • the present invention also proposes a computer-readable storage medium on which computer instructions are stored, and the computer instructions execute the method according to the above when executed.
  • Fig. 1 is a flow chart of a method for predicting machining accuracy of a machine tool according to an embodiment of the present invention
  • Fig. 2 is a schematic diagram of a machine tool machining accuracy prediction device according to an embodiment of the present invention
  • Fig. 3 is a schematic diagram of an electronic device according to an embodiment of the present invention.
  • Machine tool processing accuracy prediction device 210 Simulation module 220: Simplification module
  • Fig. 1 is a flow chart of a method for predicting machining accuracy of a machine tool according to an embodiment of the present invention. As shown in Fig. 1, the method for predicting machining accuracy of a machine tool includes:
  • Step 110 establishing a simulation model of the machining process of the machine tool.
  • the simulation model includes the simulation model of the mechanical system of the machine tool, the simulation model of the processed workpiece, and the processing path.
  • the parameters for establishing the simulation model of the mechanical system of the machine tool include the control parameters of the machine tool, the geometric model of the machine tool, and the material parameters of the machine tool.
  • the parameters of the simulation model of the workpiece include the geometric model of the workpiece and the material parameters of the workpiece.
  • Step 120 simplify the simulation model to establish a first agent model.
  • the simulation calculation of establishing a complete machine tool processing process is very large, time-consuming, and requires high computing power of the equipment, it is impossible to perform real-time or quasi-real-time processing during the operation of the machine tool through the simulation model of the complete machine tool processing process Accuracy of predictive operations.
  • the first proxy model is established, thereby improving the simulation speed and realizing real-time or quasi-real-time simulation.
  • the first surrogate model can be established by polynomial response surface method, kriging method, gradient enhanced kriging method, support vector machine, spatial mapping or artificial neural network, etc.
  • the first proxy model is established by means of deep learning.
  • the simulation data set is obtained by using the simulation model, and the preset agent model is trained by using the simulation data set to obtain the first agent model.
  • using the simulation model to obtain the simulation data set may include: selecting at least one influencing factor in the simulation environment, respectively setting the numerical range of the influencing factor, changing the numerical value of the influencing factor within the numerical range, and then using the simulation model to obtain the first evaluation parameter value; record the value of the influencing factor, the value of the first evaluation parameter and the mapping relationship between them, so as to obtain the simulation data set. Repeat the above steps for each influencing factor, and all the recorded simulation data sets can be used as the training set and test set for establishing the proxy model.
  • the influence of the above factors on the final machining accuracy is often coupled together, and it is difficult to decouple, and the degree of influence of the above factors on the prediction accuracy is different.
  • the decoupling of multiple influencing factors can be achieved.
  • the output of wherein the evaluation parameters may include: machining position error, stress and strain of the workpiece to be processed, vibration of the whole machine tool, vibration of the workpiece to be processed, etc.
  • the proxy model is established using a data-driven, bottom-up approach. The calculation results of the first proxy model are very close to the simulation model of the machine tool process, but the calculation volume is greatly reduced.
  • Step 130 predict the machining accuracy of the machine tool through the first proxy model.
  • At least one influencing factor is input into the first proxy model, and the first proxy model outputs the value of at least one evaluation parameter, combined with the preset weight value, to predict the machining accuracy of the machine tool.
  • the preset weight value can be obtained based on the degree of influence of each evaluation parameter on the final machining accuracy in the stage of establishing the simulation model, and can also be further adjusted through the simulation data set in the training stage. Therefore, the predicted value of the machining accuracy of the machine tool is more accurate and closer to the actual value.
  • the machine tool processing accuracy prediction method may also include: step 140, performing data fusion of the value of the evaluation parameter obtained through the first proxy model and the on-site measurement value corresponding to the evaluation parameter to obtain the second
  • the proxy model is used to predict the machining accuracy of the machine tool through the second proxy model.
  • the value of the evaluation parameter output by the proxy model can be more accurate and closer to the actual value.
  • the actual vibration value of the machine tool can be obtained through on-site measurement, and the on-site measurement value is fused with the vibration value of the machine tool obtained through the first proxy model.
  • the on-site measurement value is also used as a new training data set to continuously iterate the proxy model, and more accurate machining accuracy results can be calculated through the iterated proxy model.
  • the method for predicting machine tool machining accuracy may also include: step 150, performing data fusion of the value of the evaluation parameter obtained through the first proxy model and the value of the influencing factors collected on site to obtain the first The three-agent model, and then through the third-agent model, predict the machining accuracy of the machine tool.
  • the value of the influencing factors collected on site such as: the size of the machine tool end drive jacking force, temperature, humidity and current, etc.
  • the evaluation parameters obtained through the first proxy model such as: processing position error, stress and strain of the workpiece to be processed, etc. Fusion, so as to further improve the accuracy of machining accuracy prediction.
  • the method for predicting machining accuracy of machine tools may further include: performing data fusion of the values of the evaluation parameters obtained through the second proxy model and the values of the influencing factors collected on site to obtain a fourth proxy model , and then use the fourth surrogate model to predict the machining accuracy of the machine tool.
  • the machine tool machining accuracy prediction method may further include: performing data fusion of the value of the evaluation parameter obtained through the third proxy model and the on-site measurement value corresponding to the evaluation parameter to obtain the fifth proxy model, Then through the fifth surrogate model, the machining accuracy of the machine tool is predicted.
  • the predicted machining accuracy of the machine tool can also be used to optimize the control parameters of the machine tool before machining, so as to improve the actual machining accuracy of the workpiece.
  • the following embodiment provides a method for predicting the accuracy of crankshaft end drives processed by a grinding machine.
  • the grinding machine has three axes of motion: X, C, and Z.
  • the X-axis is driven by a linear motor to drive the grinding wheel frame;
  • the Z-axis is equipped with a head frame.
  • the tailstock clamps the parts in the form of end drive;
  • the C axis drives the end drive thimble and the workpiece to rotate.
  • the type of workpiece to be processed is shaft parts.
  • each simulation requires a long calculation time, so it is not suitable for real-time calculation, and the corresponding proxy model based on the complete grinding machine system model can be used for real-time or quasi-real-time simulation.
  • the simulation model environment select the grinder voltage, current, control parameters in the grinder controller, processing path, and tailstock fuel tank pressure as the influencing factors, and set the corresponding variation ranges, for example, set the range of the tailstock fuel tank pressure as 0.6Mpa ⁇ 0.7Mpa, select multiple tailstock fuel tank pressure values in this range, such as 0.6Mpa, 0.65Mpa and 0.7Mpa, and use the simulation model to output the corresponding evaluation parameter values under the condition that the values of other influencing factors remain unchanged. It includes the overall vibration value V 1 of the grinding machine, the vibration value V 2 of the workpiece to be processed, the overall deformation value D 1 of the grinding machine, and the deformation value D 2 of the processed workpiece.
  • the simulation data set is obtained according to different tailstock fuel tank pressure values, corresponding evaluation parameter values and the mapping relationship between them, and then the first proxy model is trained with the simulation data set.
  • the first proxy model Input the real tailstock oil tank pressure value on site into the first proxy model, and the first proxy model outputs the values of multiple evaluation parameters, including: the overall vibration value V 1 of the grinding machine, the vibration value V 2 of the processed workpiece, the overall grinding machine Deformation value D 1 and workpiece deformation value D 2 .
  • the evaluation parameter data obtained by the first proxy model with the weight values (K 1 , K 2 , K 3 , K 4 ) of each evaluation parameter respectively, the predicted machining accuracy value of the crankshaft end drive processed by the grinding machine is output
  • the value of the evaluation parameter obtained by the first proxy model can be fused with the corresponding on-site measurement value and data to obtain the second proxy model, and then use the second proxy model to predict the machining accuracy of the crankshaft end drive processed by the grinding machine.
  • Edge computing devices are deployed at the grinding machine site to provide nearby computing services, including the calculation of simulation models and proxy models, and real-time processing of status data from the grinding machine system site, and can also achieve collaboration with the cloud.
  • the on-site state data of the grinding machine system includes two parts, one part of the data is obtained by the controller of the grinding machine system, including control parameters and control status, such as PID parameters, processing trajectory, etc.
  • the other part is obtained from the sensors deployed on the grinding machine site, through which the real evaluation parameters on the site can be collected, such as: sensors for measuring voltage, sensors for measuring current, sensors for measuring temperature and humidity, sensors for measuring sound, and sensors for measuring digital pressure sensors etc.
  • the sensor for measuring pressure can be installed on the output pipeline of the hydraulic oil tank of the end drive tailstock of the grinding machine, and is used to measure the real end drive jacking force of the grinding machine site.
  • the noise-measuring sensor can be installed around the drive chain of the grinding machine, such as around the ball screw and the motor shaft, to measure the real noise on the grinding machine site.
  • the sensor for measuring vibration can be installed on the grinding wheel and frame of the grinding machine to collect the vibration value of the processed workpiece and frame, and the vibration value includes vibration frequency and vibration amplitude.
  • the on-site status data of the grinding machine system is input to the edge device through the communication interface, such as Ethernet, USB, serial port, etc.
  • the data is first analyzed, and after processing different data sources and types of data, a unified format is formed and stored in the operating database.
  • the operation database also records the parameters of the whole life cycle of the equipment, such as the factory year, service life and maintenance records of the whole equipment and each core component.
  • the speed of simulation can be improved, so as to achieve real-time or quasi-real-time prediction of the accuracy of the crankshaft end drive processed by the grinding machine.
  • the method of training the proxy model through the simulation data set and the means of data fusion can make the predicted processing accuracy more accurate.
  • FIG. 2 is a schematic diagram of a machine tool machining accuracy prediction device 200 according to an embodiment of the present invention. As shown in FIG. 2 , the machine tool machining accuracy prediction device 200 includes:
  • a simplification module (220), configured to simplify the simulation model to create a first proxy model
  • the prediction module (230) is configured to predict the machining accuracy of the machine tool through the first proxy model.
  • FIG. 3 is a schematic diagram of an electronic device 300 according to an embodiment of the present invention.
  • the electronic device 300 includes a processor 310 and a memory 320 , and the memory 320 stores instructions, wherein the instructions are executed by the processor 310 to implement the method 100 as described above.
  • the present invention also proposes a computer-readable storage medium on which computer instructions are stored, and when executed, the computer instructions execute the method 100 as described above.
  • Some aspects of the method and apparatus of the present invention may be entirely implemented by hardware, may be entirely implemented by software (including firmware, resident software, microcode, etc.), or may be implemented by a combination of hardware and software.
  • the above hardware or software may be referred to as “block”, “module”, “engine”, “unit”, “component” or “system”.
  • the processor can be one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DAPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), processors , a controller, a microcontroller, a microprocessor, or a combination thereof.
  • ASICs Application Specific Integrated Circuits
  • DSPs Digital Signal Processors
  • DAPDs Digital Signal Processing Devices
  • PLDs Programmable Logic Devices
  • FPGAs Field Programmable Gate Arrays
  • processors a controller, a microcontroller, a microprocessor, or a combination thereof.
  • aspects of the present invention may be embodied as a computer product comprising computer readable program code on one or more computer readable media.
  • computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disk, floppy disk, magnetic tape, ...), optical disks (e.g., compact disk (CD), digital versatile disk (DVD) %), smart cards And flash memory devices (eg, cards, sticks, key drives).
  • a flow chart is used here to illustrate operations performed by the method according to the embodiment of the present application. It should be understood that the preceding operations are not necessarily performed in an exact order. Instead, various steps may be processed in reverse order or concurrently. At the same time, other operations are either added to these procedures, or a certain step or steps are removed from these procedures.

Abstract

The present invention provides a machine tool machining precision prediction method, comprising: establishing a simulation model of a machine tool machining process; simplifying the simulation model to establish a first surrogate model; and predicting the machining precision of the machine tool by means of the first surrogate model. According to the present invention, the simulation speed can be improved, so that the machining precision of the machine tool is predicted in real time or quasi-real-time.

Description

机床加工精度预测方法、装置、存储介质和电子设备Machine tool processing accuracy prediction method, device, storage medium and electronic equipment 技术领域technical field
本发明主要涉及机床加工精度预测领域，尤其涉及一种机床加工精度预测方法、装置、存储介质和电子设备。The invention mainly relates to the field of machine tool machining accuracy prediction, and in particular to a machine tool machining accuracy prediction method, device, storage medium and electronic equipment.
背景技术Background technique
机床是制造系统的母机，是制造行业的根基。目前大多数机床的智能化和数字化水平普遍较低，从而导致机床存在加工精度不够高以及加工精度预测不准确的问题。Machine tool is the mother machine of the manufacturing system and the foundation of the manufacturing industry. At present, the level of intelligence and digitalization of most machine tools is generally low, which leads to the problems of insufficient machining accuracy and inaccurate prediction of machining accuracy of machine tools.
目前，通常采用手动测量机床加工零件样本的精度来判断机床加工精度，并通过对机床进行例行维护保养，并定期更换核心部件的方法来保证机床的正常加工精度。另一种方式是通过在关键部位附近安装特定传感器以收集机床运行中的相应状态信号，并对信号数据进行分析，从而对机床的加工精度进行监控。然而，相关方法都不能准确预测机床的加工精度，也难以有效保证机床加工精度的持续稳定。At present, the machining accuracy of machine tools is usually judged by manually measuring the accuracy of machine tool parts samples, and the normal machining accuracy of machine tools is guaranteed by routine maintenance of machine tools and regular replacement of core components. Another way is to install specific sensors near key parts to collect corresponding status signals during machine tool operation, and analyze the signal data to monitor the machining accuracy of the machine tool. However, none of the related methods can accurately predict the machining accuracy of the machine tool, and it is difficult to effectively guarantee the continuous stability of the machining accuracy of the machine tool.
发明内容Contents of the invention
为了解决上述技术问题，本发明提供一种机床加工精度预测方法、装置、存储介质和电子设备，从而达到准确预测机床加工精度的目的，并进一步地保证机床加工精度的持续稳定。In order to solve the above technical problems, the present invention provides a machine tool machining accuracy prediction method, device, storage medium and electronic equipment, so as to achieve the purpose of accurately predicting the machine tool machining accuracy, and further ensure the continuous stability of machine tool machining accuracy.
为实现上述目的，本发明提出了一种机床加工精度预测方法，包括：建立机床加工过程的仿真模型；简化所述仿真模型以建立第一代理模型；通过所述第一代理模型，对机床加工精度进行预测。若通过完整的机床加工过程的仿真模型进行仿真需要较长的运算时间，而通过将仿真模型进行简化从而得到运算量更小的代理模型，可以提高仿真的速度，从而实现实时或准实时地预测机床加工的精度。In order to achieve the above object, the present invention proposes a method for predicting machining accuracy of machine tools, including: establishing a simulation model of the machining process of the machine tool; simplifying the simulation model to establish a first proxy model; accuracy for prediction. If the simulation through the simulation model of the complete machine tool processing process takes a long time to calculate, and by simplifying the simulation model to obtain a proxy model with a smaller amount of calculation, the simulation speed can be improved, so as to achieve real-time or quasi-real-time prediction The precision of machine tool processing.
本发明还提出了一种机床加工精度预测装置，包括：仿真模块，被配置为建立机床加工过程的仿真模型；简化模块，被配置为简化所述仿真模型以建立第一代理模型；预测模块，被配置为通过所述第一代理模型，对机床加工精度进行预测。The present invention also proposes a machine tool processing accuracy prediction device, including: a simulation module configured to establish a simulation model of the machine tool processing process; a simplification module configured to simplify the simulation model to establish a first proxy model; a prediction module, It is configured to predict the machining accuracy of the machine tool through the first proxy model.
本发明还提出了一种电子设备，包括处理器、存储器和存储在所述存储器中的指令，其中所述指令被所述处理器执行时实现如上文所述的方法。The present invention also proposes an electronic device, including a processor, a memory, and instructions stored in the memory, wherein the instructions implement the method as described above when executed by the processor.
本发明还提出了一种计算机可读存储介质，其上存储有计算机指令，所述计算机指令 在被运行时执行根据上文所述的方法。The present invention also proposes a computer-readable storage medium on which computer instructions are stored, and the computer instructions execute the method according to the above when executed.
附图说明Description of drawings
以下附图仅旨在于对本发明做示意性说明和解释，并不限定本发明的范围。其中：The following drawings are only intended to illustrate and explain the present invention schematically, and do not limit the scope of the present invention. in:
图1是根据本发明的一实施例的一种机床加工精度预测方法的流程图；Fig. 1 is a flow chart of a method for predicting machining accuracy of a machine tool according to an embodiment of the present invention;
图2是根据本发明的一实施例的一种的机床加工精度预测装置的示意图；Fig. 2 is a schematic diagram of a machine tool machining accuracy prediction device according to an embodiment of the present invention;
图3是根据本发明的一实施例的一种电子设备的示意图。Fig. 3 is a schematic diagram of an electronic device according to an embodiment of the present invention.
附图标记说明Explanation of reference signs
100：机床加工精度预测方法  110-150：方法步骤100: Machine Tool Machining Accuracy Prediction Method 110-150: Method Steps
200：机床加工精度预测装置  210：仿真模块  220：简化模块200: Machine tool processing accuracy prediction device 210: Simulation module 220: Simplification module
230：预测模块230: Prediction module
300：电子设备  310：处理器  320：存储器300: Electronics 310: Processor 320: Memory
具体实施方式Detailed ways
为了对本发明的技术特征、目的和效果有更加清楚的理解，现对照附图说明本发明的具体实施方式。In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific implementation manners of the present invention will now be described with reference to the accompanying drawings.
在下面的描述中阐述了很多具体细节以便于充分理解本发明，但是本发明还可以采用其它不同于在此描述的其它方式来实施，因此本发明不受下面公开的具体实施例的限制。In the following description, many specific details are set forth in order to fully understand the present invention, but the present invention can also be implemented in other ways than those described here, so the present invention is not limited by the specific embodiments disclosed below.
如本申请和权利要求书中所示，除非上下文明确提示例外情形，“一”、“一个”、“一种”和/或“该”等词并非特指单数，也可包括复数。一般说来，术语“包括”与“包含”仅提示包括已明确标识的步骤和元素，而这些步骤和元素不构成一个排它性的罗列，方法或者设备也可能包含其他的步骤或元素。As indicated in this application and claims, the terms "a", "an", "an" and/or "the" do not refer to the singular and may include the plural unless the context clearly indicates an exception. Generally speaking, the terms "comprising" and "comprising" only suggest the inclusion of clearly identified steps and elements, and these steps and elements do not constitute an exclusive list, and the method or device may also contain other steps or elements.
图1是根据本发明的一实施例的一种机床加工精度预测方法的流程图，如图1所示，机床加工精度预测方法包括：Fig. 1 is a flow chart of a method for predicting machining accuracy of a machine tool according to an embodiment of the present invention. As shown in Fig. 1, the method for predicting machining accuracy of a machine tool includes:
步骤110，建立机床加工过程的仿真模型。 Step 110, establishing a simulation model of the machining process of the machine tool.
仿真模型包含机床的机械系统的仿真模型、被加工工件的仿真模型以及加工路径，其中建立机床的机械系统的仿真模型的参数包括机床的控制参数、机床的几何模型以及机床的材料参数等，被加工工件的仿真模型的参数包括工件的几何模型和工件的材料参数等。The simulation model includes the simulation model of the mechanical system of the machine tool, the simulation model of the processed workpiece, and the processing path. The parameters for establishing the simulation model of the mechanical system of the machine tool include the control parameters of the machine tool, the geometric model of the machine tool, and the material parameters of the machine tool. The parameters of the simulation model of the workpiece include the geometric model of the workpiece and the material parameters of the workpiece.
步骤120，简化仿真模型以建立第一代理模型。 Step 120, simplify the simulation model to establish a first agent model.
由于建立完整的机床加工过程的仿真运算量非常大，耗时长，对设备的算力要求高， 因此，无法通过完整的机床加工过程的仿真模型在机床运行过程中进行实时或准实时地进行加工精度的预测运算。通过对机床加工过程的仿真模型进行简化，以建立第一代理模型，从而提高仿真速度，实现实时或准实时地仿真。Since the simulation calculation of establishing a complete machine tool processing process is very large, time-consuming, and requires high computing power of the equipment, it is impossible to perform real-time or quasi-real-time processing during the operation of the machine tool through the simulation model of the complete machine tool processing process Accuracy of predictive operations. By simplifying the simulation model of the machining process of the machine tool, the first proxy model is established, thereby improving the simulation speed and realizing real-time or quasi-real-time simulation.
在一些实施例中，可以通过多项式响应曲面法、克里金法、梯度增强法克里金法、支持向量机、空间映射或人工神经网络等来建立第一代理模型。在一些实施例中，鉴于机床加工过程中涉及机、电、材料、热等众多影响因素，通过深度学习的方法来建立第一代理模型。In some embodiments, the first surrogate model can be established by polynomial response surface method, kriging method, gradient enhanced kriging method, support vector machine, spatial mapping or artificial neural network, etc. In some embodiments, in view of many influencing factors such as mechanics, electricity, materials, heat, etc. involved in the machining process of the machine tool, the first proxy model is established by means of deep learning.
在一些实施例中，利用仿真模型得到仿真数据集，采用仿真数据集对预设代理模型进行训练，得到第一代理模型。其中，利用仿真模型得到仿真数据集可以包括：在仿真环境中选取至少一个影响因素，分别设定影响因素的数值范围，在数值范围内改变影响因素的数值，再利用仿真模型得到第一评价参数的数值；记录影响因素的数值、第一评价参数的数值以及两者之间的映射关系，从而得到仿真数据集。针对每一影响因素均重复以上步骤，所记录的所有的仿真数据集可以作为建立代理模型的训练集和测试集。In some embodiments, the simulation data set is obtained by using the simulation model, and the preset agent model is trained by using the simulation data set to obtain the first agent model. Wherein, using the simulation model to obtain the simulation data set may include: selecting at least one influencing factor in the simulation environment, respectively setting the numerical range of the influencing factor, changing the numerical value of the influencing factor within the numerical range, and then using the simulation model to obtain the first evaluation parameter value; record the value of the influencing factor, the value of the first evaluation parameter and the mapping relationship between them, so as to obtain the simulation data set. Repeat the above steps for each influencing factor, and all the recorded simulation data sets can be used as the training set and test set for establishing the proxy model.
在现实物理世界中，有许多对机床的最终加工精度产生影响的因素，例如机床的几何形状、机床端驱顶持力大小、温度、湿度、电流、机床控制策略、被加工工件的几何形状和材料特性以及加工曲线等，上述因素对最终加工精度的影响往往是耦合在一起，而难以解偶的，并且上述因素对预测精度的影响的程度是不同的。然而，在数字世界中可以实现多影响因素的解耦，通过利用仿真模型得到仿真数据集的方式，将至少一个影响因素作为第一代理模型的输入，仿真结果的评价参数作为第一代理代理模型的输出，其中，评价参数可以包括：加工位置误差、被加工工件的应力应变、机床的整机振动、被加工工件的振动等。由此得到高精度的第一代理模型。相比完整的机床加工过程的仿真模型而言，代理模型采用的是数据驱动的、自下而上的办法来建立，第一代理模型的计算结果与机床加工过程的仿真模型非常接近，但是计算量大大降低。In the real physical world, there are many factors that affect the final machining accuracy of the machine tool, such as the geometric shape of the machine tool, the size of the end-drive jacking force of the machine tool, temperature, humidity, current, machine tool control strategy, the geometric shape of the machined workpiece and Material characteristics and processing curves, etc., the influence of the above factors on the final machining accuracy is often coupled together, and it is difficult to decouple, and the degree of influence of the above factors on the prediction accuracy is different. However, in the digital world, the decoupling of multiple influencing factors can be achieved. By using the simulation model to obtain the simulation data set, at least one influencing factor is used as the input of the first proxy model, and the evaluation parameters of the simulation results are used as the first proxy model. The output of , wherein the evaluation parameters may include: machining position error, stress and strain of the workpiece to be processed, vibration of the whole machine tool, vibration of the workpiece to be processed, etc. As a result, a high-precision first surrogate model is obtained. Compared with the simulation model of the complete machine tool processing process, the proxy model is established using a data-driven, bottom-up approach. The calculation results of the first proxy model are very close to the simulation model of the machine tool process, but the calculation volume is greatly reduced.
步骤130，通过第一代理模型，对机床加工精度进行预测。 Step 130, predict the machining accuracy of the machine tool through the first proxy model.
将至少一个影响因素输入到第一代理模型中，第一代理模型输出至少一个评价参数的数值，结合预设的权重值，对机床加工精度进行预测。其中，预设的权重值可以在建立仿真模型的阶段基于各个评价参数对最终加工精度的影响程度获得，还可以在训练阶段通过仿真数据集进一步地进行调整。从而使机床加工精度的预测值更加准确、更接近实际值。At least one influencing factor is input into the first proxy model, and the first proxy model outputs the value of at least one evaluation parameter, combined with the preset weight value, to predict the machining accuracy of the machine tool. Among them, the preset weight value can be obtained based on the degree of influence of each evaluation parameter on the final machining accuracy in the stage of establishing the simulation model, and can also be further adjusted through the simulation data set in the training stage. Therefore, the predicted value of the machining accuracy of the machine tool is more accurate and closer to the actual value.
在一些实施例之后，在步骤130之后，机床加工精度预测方法还可以包括：步骤140，将通过第一代理模型得到的评价参数的数值与评价参数对应的现场测量值进行数据融合，得到第二代理模型，再通过第二代理模型，对机床加工精度进行预测。通过数据融合的技 术，可以使代理模型输出的评价参数的数值更加准确，更接近实际值。例如：通过现场测量可以获取机床的实际振动数值，将该现场测量值与通过第一代理模型得到的机床振动的数值进行数据融合。现场测量值也作为新的训练数据集不断地迭代代理模型，通过迭代后的代理模型可以计算得到更准确的加工精度结果。After some embodiments, after step 130, the machine tool processing accuracy prediction method may also include: step 140, performing data fusion of the value of the evaluation parameter obtained through the first proxy model and the on-site measurement value corresponding to the evaluation parameter to obtain the second The proxy model is used to predict the machining accuracy of the machine tool through the second proxy model. Through the technology of data fusion, the value of the evaluation parameter output by the proxy model can be more accurate and closer to the actual value. For example, the actual vibration value of the machine tool can be obtained through on-site measurement, and the on-site measurement value is fused with the vibration value of the machine tool obtained through the first proxy model. The on-site measurement value is also used as a new training data set to continuously iterate the proxy model, and more accurate machining accuracy results can be calculated through the iterated proxy model.
在一些实施例之后，在步骤130之后，机床加工精度预测方法还可以包括：步骤150，将通过第一代理模型得到的评价参数的数值与现场采集得到的影响因素的数值进行数据融合，得到第三代理模型，再通过第三代理模型，对机床加工精度进行预测。将现场采集得到的影响因素的数值例如：机床端驱顶持力大小、温度、湿度和电流等与通过第一代理模型得到的评价参数例如：加工位置误差、被加工工件的应力应变等进行数据融合，从而进一步提高加工精度预测的准确性。After some embodiments, after step 130, the method for predicting machine tool machining accuracy may also include: step 150, performing data fusion of the value of the evaluation parameter obtained through the first proxy model and the value of the influencing factors collected on site to obtain the first The three-agent model, and then through the third-agent model, predict the machining accuracy of the machine tool. The value of the influencing factors collected on site, such as: the size of the machine tool end drive jacking force, temperature, humidity and current, etc., and the evaluation parameters obtained through the first proxy model, such as: processing position error, stress and strain of the workpiece to be processed, etc. Fusion, so as to further improve the accuracy of machining accuracy prediction.
在一些实施例中，在步骤140之后，机床加工精度预测方法还可以包括：将通过第二代理模型得到的评价参数的数值与现场采集得到的影响因素的数值进行数据融合，得到第四代理模型，再通过第四代理模型，对机床加工精度进行预测。In some embodiments, after step 140, the method for predicting machining accuracy of machine tools may further include: performing data fusion of the values of the evaluation parameters obtained through the second proxy model and the values of the influencing factors collected on site to obtain a fourth proxy model , and then use the fourth surrogate model to predict the machining accuracy of the machine tool.
在一些实施例中，在步骤150之后，机床加工精度预测方法还可以包括：将通过第三代理模型得到的评价参数的数值与评价参数对应的现场测量值进行数据融合，得到第五代理模型，再通过第五代理模型，对机床加工精度进行预测。In some embodiments, after step 150, the machine tool machining accuracy prediction method may further include: performing data fusion of the value of the evaluation parameter obtained through the third proxy model and the on-site measurement value corresponding to the evaluation parameter to obtain the fifth proxy model, Then through the fifth surrogate model, the machining accuracy of the machine tool is predicted.
在一些实施例中，还可以将预测的机床加工精度用于在加工前对机床的控制参数进行优化，从而提高加工工件的实际加工精度。In some embodiments, the predicted machining accuracy of the machine tool can also be used to optimize the control parameters of the machine tool before machining, so as to improve the actual machining accuracy of the workpiece.
下面的实施例中提供了一种磨床加工曲轴端驱的精度预测方法，该磨床拥有X、C、Z三个运动轴，其中，X轴由直线电机驱动砂轮架；Z轴上安装有头架、尾架以端驱形式夹持零件；C轴带动端驱顶针及工件转动。被加工工件类型为轴类零件。首先，建立磨床、被加工工件以及加工路径的仿真模型。由于仿真模型包含多系统联合仿真，每一次的仿真需要较长的运算时间，因此不适合进行实时运算，而基于完整的磨床系统模型生成相应的代理模型可以用于实时或准实时仿真。The following embodiment provides a method for predicting the accuracy of crankshaft end drives processed by a grinding machine. The grinding machine has three axes of motion: X, C, and Z. Among them, the X-axis is driven by a linear motor to drive the grinding wheel frame; the Z-axis is equipped with a head frame. , The tailstock clamps the parts in the form of end drive; the C axis drives the end drive thimble and the workpiece to rotate. The type of workpiece to be processed is shaft parts. First, establish the simulation model of the grinding machine, the workpiece to be processed and the processing path. Since the simulation model includes multi-system co-simulation, each simulation requires a long calculation time, so it is not suitable for real-time calculation, and the corresponding proxy model based on the complete grinding machine system model can be used for real-time or quasi-real-time simulation.
在仿真模型环境下选取磨床电压、电流、磨床控制器中的控制参数、加工路径、尾架油箱压力作为影响因素，分别设定相应的变化范围，例如设定尾架油箱压力值的变化范围为0.6Mpa～0.7Mpa，在该范围内选取多个尾架油箱压力值例如0.6Mpa、0.65Mpa和0.7Mpa，在其他影响因素数值不变的情况下，利用仿真模型输出对应的评价参数的数值，其中包括磨床整体的振动值V 1、被加工工件的振动值V 2、磨床整体形变值D 1和被加工工件形变值D 2。根据不同的尾架油箱压力值、对应的评价参数的数值以及两者之间的映射关系得到仿真数据集，再用仿真数据集训练第一代理模型。 In the simulation model environment, select the grinder voltage, current, control parameters in the grinder controller, processing path, and tailstock fuel tank pressure as the influencing factors, and set the corresponding variation ranges, for example, set the range of the tailstock fuel tank pressure as 0.6Mpa～0.7Mpa, select multiple tailstock fuel tank pressure values in this range, such as 0.6Mpa, 0.65Mpa and 0.7Mpa, and use the simulation model to output the corresponding evaluation parameter values under the condition that the values of other influencing factors remain unchanged. It includes the overall vibration value V 1 of the grinding machine, the vibration value V 2 of the workpiece to be processed, the overall deformation value D 1 of the grinding machine, and the deformation value D 2 of the processed workpiece. The simulation data set is obtained according to different tailstock fuel tank pressure values, corresponding evaluation parameter values and the mapping relationship between them, and then the first proxy model is trained with the simulation data set.
将现场真实的尾架油箱压力值输入到第一代理模型中，第一代理模型输出多个评价参数的数值，包括：磨床整体的振动值V 1、被加工工件的振动值V 2、磨床整体形变值D 1和被加工工件形变值D 2。将第一代理模型得到的评价参数的数据分别与各个评价参数的权重值(K 1，K 2，K 3，K 4)相结合，输出磨床加工曲轴端驱的预测加工精度值
Figure PCTCN2021128236-appb-000001
Figure PCTCN2021128236-appb-000002
Input the real tailstock oil tank pressure value on site into the first proxy model, and the first proxy model outputs the values of multiple evaluation parameters, including: the overall vibration value V 1 of the grinding machine, the vibration value V 2 of the processed workpiece, the overall grinding machine Deformation value D 1 and workpiece deformation value D 2 . Combining the evaluation parameter data obtained by the first proxy model with the weight values (K 1 , K 2 , K 3 , K 4 ) of each evaluation parameter respectively, the predicted machining accuracy value of the crankshaft end drive processed by the grinding machine is output
Figure PCTCN2021128236-appb-000001
Figure PCTCN2021128236-appb-000002
还可以通过第一代理模型得到的评价参数的数值与对应的现场测量值及进行数据融合，得到第二代理模型，再通过第二代理模型，对磨床加工曲轴端驱的加工精度进行预测。The value of the evaluation parameter obtained by the first proxy model can be fused with the corresponding on-site measurement value and data to obtain the second proxy model, and then use the second proxy model to predict the machining accuracy of the crankshaft end drive processed by the grinding machine.
在磨床现场部署有边缘计算设备，用于就近提供计算服务，包括仿真模型和代理模型的计算，并实时处理来自磨床系统现场的的状态数据，此外还可以实现与云端协同。Edge computing devices are deployed at the grinding machine site to provide nearby computing services, including the calculation of simulation models and proxy models, and real-time processing of status data from the grinding machine system site, and can also achieve collaboration with the cloud.
磨床系统现场的状态数据包括两部分，一部分数据由磨床系统的控制器得到，包括控制参数及控制状态，例如PID参数、加工轨迹等。The on-site state data of the grinding machine system includes two parts, one part of the data is obtained by the controller of the grinding machine system, including control parameters and control status, such as PID parameters, processing trajectory, etc.
另一部分由磨床现场部署的传感器得到，通过磨床现场部署传感器可以采集现场真实的评价参数，例如：测量电压的传感器、测量电流的传感器、测量温湿度的传感器、测量声音的传感器以及测量数字压力的传感器等。The other part is obtained from the sensors deployed on the grinding machine site, through which the real evaluation parameters on the site can be collected, such as: sensors for measuring voltage, sensors for measuring current, sensors for measuring temperature and humidity, sensors for measuring sound, and sensors for measuring digital pressure sensors etc.
其中，测量压力的传感器可以安装于磨床端驱尾架的液压油箱的输出管路上，用于测量磨床现场真实的端驱顶持力的大小。测量噪声的传感器可以安装于磨床传动链的周围，例如珠丝杆、电机轴周围等，用于测量磨床现场真实的噪音。测量振动的传感器可以安装于磨床的砂轮和机架上，用于收集被加工工件和机架的振动值，振动值包括振动频率和振动幅度。Among them, the sensor for measuring pressure can be installed on the output pipeline of the hydraulic oil tank of the end drive tailstock of the grinding machine, and is used to measure the real end drive jacking force of the grinding machine site. The noise-measuring sensor can be installed around the drive chain of the grinding machine, such as around the ball screw and the motor shaft, to measure the real noise on the grinding machine site. The sensor for measuring vibration can be installed on the grinding wheel and frame of the grinding machine to collect the vibration value of the processed workpiece and frame, and the vibration value includes vibration frequency and vibration amplitude.
磨床系统的现场状态数据通过通讯接口，如以太网、USB、串口等，输入边缘设备。进入边缘计算设备后的数据，首先进行解析，对不同数据来源及种类的数据进行处理后，形成统一的格式，存储进运行数据库。在运行数据库中还记录有设备全生命周期参数，如设备整机及各个核心零部件的出厂年限、使用寿命、维修记录等。The on-site status data of the grinding machine system is input to the edge device through the communication interface, such as Ethernet, USB, serial port, etc. After entering the edge computing device, the data is first analyzed, and after processing different data sources and types of data, a unified format is formed and stored in the operating database. The operation database also records the parameters of the whole life cycle of the equipment, such as the factory year, service life and maintenance records of the whole equipment and each core component.
通过将完整的磨床系统模型进行简化得到代理模型的方式可以提高仿真的速度，从而实现实时或准实时地预测磨床加工曲轴端驱的精度。通过仿真数据集训练代理模型的方式，以及数据融合的手段可以使预测的加工精度更加准确。By simplifying the complete grinding machine system model to obtain a proxy model, the speed of simulation can be improved, so as to achieve real-time or quasi-real-time prediction of the accuracy of the crankshaft end drive processed by the grinding machine. The method of training the proxy model through the simulation data set and the means of data fusion can make the predicted processing accuracy more accurate.
图2是根据本发明的一实施例的一种机床加工精度预测装置200的示意图，如图2所示，机床加工精度预测装置200包括：FIG. 2 is a schematic diagram of a machine tool machining accuracy prediction device 200 according to an embodiment of the present invention. As shown in FIG. 2 , the machine tool machining accuracy prediction device 200 includes:
仿真模块(210)，被配置为建立机床加工过程的仿真模型；A simulation module (210), configured to establish a simulation model of the machining process of the machine tool;
简化模块(220)，被配置为简化所述仿真模型以建立第一代理模型；a simplification module (220), configured to simplify the simulation model to create a first proxy model;
预测模块(230)，被配置为通过所述第一代理模型，对机床加工精度进行预测。The prediction module (230) is configured to predict the machining accuracy of the machine tool through the first proxy model.
本发明还提出一种电子设备300。图3是根据本发明的一实施例的一种电子设备300的示意图。如图3所示，电子设备300包括处理器310和存储器320，存储器320中存储有指令，其中指令被处理器310执行时实现如上文所述的方法100。The present invention also proposes an electronic device 300 . FIG. 3 is a schematic diagram of an electronic device 300 according to an embodiment of the present invention. As shown in FIG. 3 , the electronic device 300 includes a processor 310 and a memory 320 , and the memory 320 stores instructions, wherein the instructions are executed by the processor 310 to implement the method 100 as described above.
本发明还提出一种计算机可读存储介质，其上存储有计算机指令，计算机指令在被运行时执行如上文所述的方法100。The present invention also proposes a computer-readable storage medium on which computer instructions are stored, and when executed, the computer instructions execute the method 100 as described above.
本发明的方法和装置的一些方面可以完全由硬件执行、可以完全由软件(包括固件、常驻软件、微码等)执行、也可以由硬件和软件组合执行。以上硬件或软件均可被称为“数据块”、“模块”、“引擎”、“单元”、“组件”或“系统”。处理器可以是一个或多个专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理器件(DAPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、处理器、控制器、微控制器、微处理器或者其组合。此外，本发明的各方面可能表现为位于一个或多个计算机可读介质中的计算机产品，该产品包括计算机可读程序编码。例如，计算机可读介质可包括，但不限于，磁性存储设备(例如，硬盘、软盘、磁带……)、光盘(例如，压缩盘(CD)、数字多功能盘(DVD)……)、智能卡以及闪存设备(例如，卡、棒、键驱动器……)。Some aspects of the method and apparatus of the present invention may be entirely implemented by hardware, may be entirely implemented by software (including firmware, resident software, microcode, etc.), or may be implemented by a combination of hardware and software. The above hardware or software may be referred to as "block", "module", "engine", "unit", "component" or "system". The processor can be one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DAPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), processors , a controller, a microcontroller, a microprocessor, or a combination thereof. Furthermore, aspects of the present invention may be embodied as a computer product comprising computer readable program code on one or more computer readable media. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disk, floppy disk, magnetic tape, ...), optical disks (e.g., compact disk (CD), digital versatile disk (DVD) ...), smart cards And flash memory devices (eg, cards, sticks, key drives...).
在此使用了流程图用来说明根据本申请的实施例的方法所执行的操作。应当理解的是，前面的操作不一定按照顺序来精确地执行。相反，可以按照倒序或同时处理各种步骤。同时，或将其他操作添加到这些过程中，或从这些过程移除某一步或数步操作。A flow chart is used here to illustrate operations performed by the method according to the embodiment of the present application. It should be understood that the preceding operations are not necessarily performed in an exact order. Instead, various steps may be processed in reverse order or concurrently. At the same time, other operations are either added to these procedures, or a certain step or steps are removed from these procedures.
应当理解，虽然本说明书是按照各个实施例描述的，但并非每个实施例仅包含一个独立的技术方案，说明书的这种叙述方式仅仅是为清楚起见，本领域技术人员应当将说明书作为一个整体，各实施例中的技术方案也可以经适当组合，形成本领域技术人员可以理解的其他实施方式。It should be understood that although this description is described according to various embodiments, not each embodiment only includes an independent technical solution, and this description of the description is only for clarity, and those skilled in the art should take the description as a whole , the technical solutions in the various embodiments can also be properly combined to form other implementations that can be understood by those skilled in the art.
以上所述仅为本发明示意性的具体实施方式，并非用以限定本发明的范围。任何本领域的技术人员，在不脱离本发明的构思和原则的前提下所作的等同变化、修改与结合，均应属于本发明保护的范围。The above descriptions are only illustrative specific implementations of the present invention, and are not intended to limit the scope of the present invention. Any equivalent changes, modifications and combinations made by those skilled in the art without departing from the concept and principle of the present invention shall fall within the protection scope of the present invention.

Claims (10)

  1. 一种机床加工精度预测方法，包括：A method for predicting machining accuracy of a machine tool, comprising:
    建立(110)机床加工过程的仿真模型；Establish (110) a simulation model of the machine tool machining process;
    简化(120)所述仿真模型以建立第一代理模型：Simplifying (120) the simulation model to create a first surrogate model:
    通过所述第一代理模型，对机床加工精度进行预测(130)。Predict the machining accuracy of the machine tool through the first proxy model (130).
  2. 根据权利要求1所述的方法，其特征在于，所述建立第一代理模型包括：通过深度学习的方法来建立第一代理模型。The method according to claim 1, wherein said establishing the first agent model comprises: establishing the first agent model by means of deep learning.
  3. 根据权利要求1所述的机床精度预测方法，其特征在于，所述建立第一代理模型包括：利用所述仿真模型得到仿真数据集，采用所述仿真数据集对预设代理模型进行训练，得到第一代理模型。The machine tool accuracy prediction method according to claim 1, wherein said establishing a first proxy model comprises: using said simulation model to obtain a simulation data set, using said simulation data set to train a preset proxy model to obtain First surrogate model.
  4. 根据权利要求3所述的方法，其特征在于，所述利用所述仿真模型得到仿真数据集包括：在仿真环境中选取至少一个影响因素，分别设定所述影响因素的数值范围，在所述数值范围内改变所述影响因素的数值，利用所述仿真模型得到第一评价参数的数值；记录所述影响因素的数值、所述第一评价参数的数值以及两者之间的映射关系，得到所述仿真数据集。The method according to claim 3, wherein said obtaining a simulation data set by using said simulation model comprises: selecting at least one influencing factor in a simulation environment, respectively setting the numerical ranges of said influencing factors, in said Change the value of the influencing factor within the value range, and use the simulation model to obtain the value of the first evaluation parameter; record the value of the influencing factor, the value of the first evaluation parameter and the mapping relationship between the two, and obtain The simulation data set.
  5. 根据权利要求1所述的方法，其特征在于，所述通过所述第一代理模型，对机床加工精度进行预测(130)，包括：将至少一个影响因素输入到所述第一代理模型中，所述第一代理模型输出至少一个评价参数的数值，结合预设的权重值，对机床加工精度进行预测。The method according to claim 1, characterized in that, predicting (130) the machining accuracy of the machine tool through the first proxy model comprises: inputting at least one influencing factor into the first proxy model, The first proxy model outputs the value of at least one evaluation parameter, combined with the preset weight value, to predict the machining accuracy of the machine tool.
  6. 根据权利要求1所述的方法，其特征在于，在所述通过所述第一代理模型，对机床加工精度进行预测(130)后，所述方法还包括：将通过所述第一代理模型得到的评价参数的数值与所述评价参数对应的现场测量值进行数据融合，得到第二代理模型；通过所述第二代理模型，对机床加工精度进行预测。The method according to claim 1, characterized in that, after predicting (130) the machining accuracy of the machine tool through the first surrogate model, the method further comprises: using the first surrogate model to obtain The value of the evaluation parameter is fused with the on-site measurement value corresponding to the evaluation parameter to obtain a second proxy model; through the second proxy model, the machining accuracy of the machine tool is predicted.
  7. 根据权利要求1所述的方法，其特征在于，在所述通过所述第一代理模型，对机床加工精度进行预测(130)后，所述方法还包括：将通过所述第一代理模型得到的评价参数的数值与现场采集得到的影响因素的数值进行数据融合，得到第三代理模型，通过所述第三代理模型，对机床加工精度进行预测。The method according to claim 1, characterized in that, after predicting (130) the machining accuracy of the machine tool through the first surrogate model, the method further comprises: using the first surrogate model to obtain The value of the evaluation parameter is fused with the value of the influencing factors collected on site to obtain a third proxy model, and the machining accuracy of the machine tool is predicted through the third proxy model.
  8. 一种机床加工精度预测装置(200)，包括：A machine tool machining accuracy prediction device (200), comprising:
    仿真模块(210)，被配置为建立机床加工过程的仿真模型；A simulation module (210), configured to establish a simulation model of the machining process of the machine tool;
    简化模块(220)，被配置为简化所述仿真模型以建立第一代理模型；a simplification module (220), configured to simplify the simulation model to create a first proxy model;
    预测模块(230)，被配置为通过所述第一代理模型，对机床加工精度进行预测。The prediction module (230) is configured to predict the machining accuracy of the machine tool through the first proxy model.
  9. 一种电子设备(300)，包括处理器(310)、存储器(320)和存储在所述存储器(320)中的指令，其中所述指令被所述处理器(310)执行实现如权利要求1-7任一项所述的方法。An electronic device (300), comprising a processor (310), a memory (320) and instructions stored in the memory (320), wherein the instructions are executed by the processor (310) to implement claim 1 - the method described in any one of 7.
  10. 一种计算机可读存储介质，其上存储有计算机指令，所述计算机指令在被运行时执行根据权利要求1-7中任一项所述的方法。A computer-readable storage medium having stored thereon computer instructions which, when executed, perform the method according to any one of claims 1-7.
PCT/CN2021/128236 2021-11-02 2021-11-02 Machine tool machining precision prediction method and apparatus, storage medium, and electronic device WO2023077275A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202180102057.0A CN117940927A (en) 2021-11-02 2021-11-02 Machine tool machining precision prediction method and device, storage medium and electronic equipment
PCT/CN2021/128236 WO2023077275A1 (en) 2021-11-02 2021-11-02 Machine tool machining precision prediction method and apparatus, storage medium, and electronic device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/128236 WO2023077275A1 (en) 2021-11-02 2021-11-02 Machine tool machining precision prediction method and apparatus, storage medium, and electronic device

Publications (1)

Publication Number Publication Date
WO2023077275A1 true WO2023077275A1 (en) 2023-05-11

Family

ID=86240470

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/128236 WO2023077275A1 (en) 2021-11-02 2021-11-02 Machine tool machining precision prediction method and apparatus, storage medium, and electronic device

Country Status (2)

Country Link
CN (1) CN117940927A (en)
WO (1) WO2023077275A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005250985A (en) * 2004-03-05 2005-09-15 Gunma Prefecture Diagnostic method of mechanical system and diagnosis device for mechanical system
CN112446110A (en) * 2020-11-06 2021-03-05 电子科技大学 Application method of EOASM algorithm in proxy model construction of robot palletizer driving arm seat
CN112668227A (en) * 2020-12-31 2021-04-16 华中科技大学 Thin-wall part cutter relieving deformation error prediction model establishing method and application thereof
CN112784451A (en) * 2020-11-27 2021-05-11 北京工业大学 Thin-wall part machining deformation prediction method based on finite element and support vector machine
CN113051831A (en) * 2021-04-01 2021-06-29 重庆大学 Machine tool thermal error self-learning prediction model modeling method and machine tool thermal error control method based on digital twins

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005250985A (en) * 2004-03-05 2005-09-15 Gunma Prefecture Diagnostic method of mechanical system and diagnosis device for mechanical system
CN112446110A (en) * 2020-11-06 2021-03-05 电子科技大学 Application method of EOASM algorithm in proxy model construction of robot palletizer driving arm seat
CN112784451A (en) * 2020-11-27 2021-05-11 北京工业大学 Thin-wall part machining deformation prediction method based on finite element and support vector machine
CN112668227A (en) * 2020-12-31 2021-04-16 华中科技大学 Thin-wall part cutter relieving deformation error prediction model establishing method and application thereof
CN113051831A (en) * 2021-04-01 2021-06-29 重庆大学 Machine tool thermal error self-learning prediction model modeling method and machine tool thermal error control method based on digital twins

Also Published As

Publication number Publication date
CN117940927A (en) 2024-04-26

Similar Documents

Publication Publication Date Title
CN109615113B (en) Digital twin-based marine diesel engine heavy part machining quality prediction method
CN110900307B (en) Numerical control machine tool cutter monitoring system driven by digital twin
CN112668227B (en) Thin-wall part cutter relieving deformation error prediction model establishment method and application thereof
CN116380166A (en) Equipment abnormality monitoring method, electronic equipment and storage medium
CN103955576B (en) A kind of method and device of lathe chuck dynamic balance weight
CN102279126B (en) Method for determining material performance parameter by combination of testing and CAE simulation
US20230315043A1 (en) System and method for instantaneous performance management of a machine tool
Wu et al. Investigate on computer-aided fixture design and evaluation algorithm for near-net-shaped jet engine blade
WO2023077275A1 (en) Machine tool machining precision prediction method and apparatus, storage medium, and electronic device
Shang et al. The experimental test and FEA of a PKM (Exechon) in a flexible fixture application for aircraft wing assembly
Zou et al. The Modeling Method of Digital Twin Models for Machining Parts
CN114741999B (en) Digital twinning technology-based lead bonding online monitoring method
Zhu et al. A tool wear condition monitoring approach for end milling based on numerical simulation
Mohring et al. Simulation aided design of intelligent machine tool components
Denkena et al. Simulation based parameterization for process monitoring of machining operations
Eyvazian et al. Surface Roughness Prediction and Minimization in 5-Axis Milling Operations of Gas Turbine Blades
Sicard et al. Design Considerations for Building an IoT Enabled Digital Twin Machine Tool Sub-System
Huang et al. AI-Driven Digital Process Twin via Networked Digital Process Chain
CN117592223B (en) Intelligent design method of hole machining tool for aerospace materials
CN109324570B (en) Machine tool design optimization method based on machining appearance pre-configuration
Miao et al. Design of Digital Twin Cutting Experiment System for Shearer
Yin et al. Local parameter identification with neural ordinary differential equations
Zhang et al. Performance-oriented digital twin assembly of high-end equipment: a review
Zhou Research on Digital Engineering Modeling System under Computer Virtual Reality Technology
Zhu et al. Full compensation method of thermal error of NC machine tool based on sequence depth learning

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21962796

Country of ref document: EP

Kind code of ref document: A1