Error compensation method and system for processing equipment

Abstract

The invention discloses an error compensation method and system for machining equipment, relates to the technical field of equipment machining error compensation, and solves the technical problems that in the prior art, mutual influence during simultaneous machining of all channels is not dynamically considered, so that all the channels cannot be accurately compensated, and the machining precision is affected. According to the method, the historical processing data is collected to train the artificial intelligence model to obtain the deviation prediction model, and the mapping relation between the processing environment and the ratio of the extra influence error amount suffered by each channel and the actual extra compensation amount during multi-channel simultaneous processing is constructed through the deviation prediction model; the mapping relation determines whether the amount of additional compensation required by each channel on the basis of original compensation can be accurately determined in the machining process or not, and the error compensation accuracy of each channel can be improved when multiple channels are machined at the same time; compared with the prior art in which additional error influence is distributed to each channel according to a fixed proportion, the compensation method provided by the invention is obviously more in line with a complex processing environment.

Description

Technical Field

[0001] This application belongs to the technical field of equipment processing error compensation, and specifically relates to an error compensation method and system for processing equipment. Background Art

[0002] The numerical control system is an intelligent manufacturing technology controlled by a computer, which is used to automate and precisely control the machining process of machine tools. The data system precisely controls various movements and machining parameters on the machine tool through pre-written program instructions to complete complex machining tasks. However, when the numerical control system controls the machining of the machine tool, errors usually occur due to mechanical factors, environmental factors, tool factors, material properties, etc. In order to make up for these errors to ensure the machining progress, it is necessary to compensate for these errors.

[0003] In the existing error compensation method in a multi-channel machining scenario, by calculating the mutual influence between channels during simultaneous multi-channel machining, the additional error amount that each channel is affected by other channels during machining is obtained, and this error amount is multiplied by a preset proportional coefficient to obtain the compensation amount. The existing technology ignores the influence of external factors when calculating the additional error amount, and the compensation amount calculated through the preset proportional coefficient cannot adapt to the influence of changes in machining conditions, resulting in inaccurate compensation for each channel and affecting the machining accuracy.

[0004] This application provides an error compensation method and system for processing equipment to solve the above technical problems. Summary of the Invention

[0005] This application aims to solve at least one of the technical problems existing in the prior art; for this purpose, this application proposes an error compensation method and system for processing equipment, which is used to solve the technical problem that the prior art does not dynamically consider the mutual influence between channels during simultaneous machining, resulting in inaccurate compensation for each channel and affecting the machining accuracy.

[0006] To achieve the above object, the first aspect of this application provides an error compensation method for processing equipment, including: Collect historical machining data to train an artificial intelligence model to obtain a deviation prediction model; wherein, the deviation prediction model is used to construct a mapping relationship between the machining environment and the compensation ratio during multi-channel machining; Collect the basic equipment parameters and machining environment parameters of the target equipment; wherein, the basic equipment parameters include equipment model, service life, total machining duration, and the machining environment parameters include single machining duration and environmental parameters, and the machining channels of the target equipment include at least Channel 1 and Channel 2; Test the error parameters of the target device during processing; integrate the basic device parameters and processing environment parameters and input them into the deviation prediction model to obtain the deviation distribution ratio; among them, the error parameters include the error amount during single-channel processing and the influence error amount on each channel during multi-channel simultaneous processing. Calculate the error compensation amount for each channel based on the deviation distribution ratio and error parameters; among them, the error compensation amount includes the error compensation amount during single-channel processing and the error compensation amount during multi-channel processing.

[0007] Preferably, collect historical processing data to train the artificial intelligence model, including: Collect the basic processing data of the processing device of the same model as the target device; among them, the basic processing data includes basic device parameters, processing environment parameters and error parameters. Integrate the basic device parameters and processing environment parameters into model input data, and obtain model output data based on the integration of error parameters; integrate the model input data and model output data into historical processing data. Train the artificial intelligence model through historical processing data; among them, the artificial intelligence model includes a BP neural network model or an RBF neural network model.

[0008] Preferably, integrating the basic device parameters and processing environment parameters into model input data includes: Add the total processing duration in the basic device parameters to the single processing duration in the processing environment parameters to obtain the updated total processing duration. Perform model adaptation processing on the device number, service duration, total processing duration, single processing duration and environmental parameters to obtain model input data; among them, the model adaptation processing includes setting marks and normalization processing.

[0009] Preferably, obtaining model output data based on the integration of error parameters includes: Extract the influence error amount on each channel during multi-channel simultaneous processing in the error parameters, and the corresponding influence compensation amount for the influence error amount; among them, the influence compensation amount is used to make up for the influence error amount. Take the ratio of the influence compensation amount to the influence error amount as the deviation distribution ratio, and mark the deviation distribution ratio of each channel as model output data after performing model adaptation processing.

[0010] Preferably, testing the error parameters of the target device during processing includes: First, let channel one perform processing. After the processing time of channel one, channel two joins and processes simultaneously with channel one; after time two, channel one stops processing, and channel two processes alone. During the machining process, a laser interferometer is used to monitor the movement trajectory of the machine tool; based on the movement trajectory, the error amounts of Channel 1 and Channel 2 are calculated, as well as the influence error amount of Channel 2 on Channel 1 and the influence error amount of Channel 1 on Channel 2 during simultaneous machining.

[0011] Preferably, the basic equipment parameters and machining environment parameters are integrated and input into the deviation prediction model, including: After performing appropriate model processing on the basic equipment parameters and the machining environment parameters collected in real time, they are marked as deviation prediction parameters; The deviation prediction parameters are input into the deviation prediction model to obtain the deviation allocation ratio.

[0012] Preferably, based on the deviation allocation ratio and the error parameters, the error compensation amounts for each channel are calculated, including: Channel 1 and Channel 2 are sequentially used as the target channels; the error amounts and their corresponding influence error amounts during the separate machining of the channels are extracted from the error parameters; The ratio corresponding to the target channel is extracted from the deviation allocation ratio, and after multiplying this ratio by the influence error amount and adding it to the error amount, the error compensation amount for the target channel is obtained.

[0013] Preferably, when Channel 1 is the target channel, the error amount during the separate machining of Channel 1 and the influence error amount of Channel 2 on Channel 1 during simultaneous machining are extracted from the error parameters; The ratio corresponding to the target channel is extracted from the obtained deviation allocation ratio and marked as PFB; The error compensation amount WBL of the target channel is calculated through the formula WBL = WC + PFB × YWC; where WC is the error amount and YWC is the influence error amount.

[0014] Preferably, after obtaining the error compensation amounts for each channel, the machining process of each channel is adjusted in real time based on the error compensation amounts.

[0015] The second aspect of the present application provides an error compensation system for a machining device, including a data analysis module and a data acquisition module connected thereto; Data acquisition module: used to collect historical machining data; and, collect the basic equipment parameters and machining environment parameters of the target device; where the basic equipment parameters include the equipment model, service life, total machining duration, the machining environment parameters include the single machining duration and environmental parameters, and the machining channels of the target device include at least Channel 1 and Channel 2; Data analysis module: used to train an artificial intelligence model based on historical machining data to obtain a deviation prediction model; where the deviation prediction model is used to construct a mapping relationship between the machining environment and the compensation ratio during multi-channel machining; and, During processing, the error parameters of the target device are tested, and the basic device parameters and processing environment parameters are integrated and input into the deviation prediction model to obtain the deviation distribution ratio; among them, the error parameters include the error amount during single-channel processing and the influence error amount on each channel during multi-channel simultaneous processing. Based on the deviation distribution ratio and error parameters, the error compensation amount for each channel is calculated; among them, the error compensation amount includes the error compensation amount during single-channel processing and the error compensation amount during multi-channel processing.

[0016] Compared with the prior art, the beneficial effects of this application are as follows: 1. This application collects historical processing data to train an artificial intelligence model to obtain a deviation prediction model, and constructs a mapping relationship between the processing environment during multi-channel simultaneous processing and the ratio of the additional influence error amount received by each channel to the actual additional compensation amount through the deviation prediction model. This mapping relationship determines whether it is possible to accurately determine the amount that each channel needs to be additionally compensated on the basis of the original compensation during the processing process, and can improve the error compensation accuracy of each channel during multi-channel simultaneous processing; compared with the prior art where the additional error influence is distributed to each channel according to a fixed ratio, it is obvious that the compensation method provided by this application is more in line with the complex processing environment.

[0017] 2. This application tests the error parameters of the target device during processing, integrates the basic device parameters and processing environment parameters and inputs them into the deviation prediction model to obtain the deviation distribution ratio; calculates the error compensation amount for each channel based on the deviation distribution ratio and error parameters, and compensates each channel according to the error compensation amount; this application independently determines the error parameters each time processing is performed, and the dynamic error compensation of each channel can be realized in cooperation with the dynamically determined deviation distribution ratio, and the parameter prediction model can be deployed in advance, which is convenient for operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 It is a schematic diagram of the method steps of the error compensation method in Embodiment 1 of the present application; Figure 2 It is a schematic diagram of the system principle of the error compensation system in Embodiment 1 of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] The technical solution of the present application will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without making creative efforts belong to the scope of protection of the present application.

[0021] During the machining process of the numerical control system, errors that occur will be compensated to improve the machining accuracy of the workpiece. However, the current compensation method mainly targets single-channel machining, that is, detecting the machining error of a single channel and compensating for this machining error. However, when multi-channel machining is performed on a workpiece, each channel will affect each other. If the machining error of a single channel is still detected and compensated, the final machining accuracy will be affected. Moreover, the mutual influence between channels is greatly related to the machining environment, the service life of the machining equipment, etc. Therefore, how to perform dynamic compensation on each channel while considering the mutual influence between channels is an important way to improve machining accuracy. Embodiment 1

[0022] Please refer to Figure 1 - Figure 2 , an embodiment of the first aspect of the present application provides an error compensation method for a machining device, including: Collect historical machining data to train an artificial intelligence model to obtain a deviation prediction model; collect the basic equipment parameters and machining environment parameters of the target device; test the error parameters of the target device during machining, integrate the basic equipment parameters and machining environment parameters and input them into the deviation prediction model to obtain a deviation distribution ratio; calculate the error compensation amount for each channel based on the deviation distribution ratio and the error parameters.

[0023] The target device refers to the machining device that needs to perform error compensation, and this machining device can be controlled and compensated through a numerical control system. Since the machining error of the target device comes from multiple aspects, such as the working state of the device itself, the environment corresponding to the machining process, etc. The longer the target device is used, the errors brought about by equipment aging, material factors, etc. will also change accordingly, but these factors are slow for error changes and generally will not cause sudden changes in errors during normal operation. During the machining process of the target device, as the continuous working time increases, the changes in environmental factors such as temperature and humidity of each component will affect the machining error, and since environmental factors such as temperature and humidity change greatly during the entire machining process and are superimposed on the influence of equipment aging, it may cause the machining error to increase rapidly. Therefore, if high-precision error compensation is to be achieved, it is necessary to comprehensively consider the state of the target device itself and the state of the machining environment during each machining process.

[0024] If the current state of the target device is analyzed before each processing, the amount of data to be analyzed is large, which may take a lot of time. Therefore, in this embodiment, a reasonable model is pre-constructed through an artificial intelligence model, and applying this model to the target device can reduce the data calculation amount of each error compensation.

[0025] In this embodiment, the artificial intelligence model is trained through the collected historical processing data to obtain a deviation prediction model for error compensation of the target device. This deviation prediction model is used to construct the mapping relationship between the processing environment and the compensation ratio during multi-channel processing. This is because the error of a single channel can be detected through a preset degree before processing, and the processing error during single-channel processing does not change greatly during a single processing process. Therefore, the deviation prediction model is mainly used to determine the mutual influence between channels during multi-channel processing.

[0026] During multi-channel processing, there is an additional error amount compared with single-channel processing. This additional error amount is caused by the simultaneous processing of other channels, but this additional error amount is not equivalent to the compensation amount. Generally, this additional error amount is multiplied by a set proportionality coefficient for compensation. However, during the working process of the target device, it is surely impossible to use a fixed proportionality coefficient throughout the life of the target device. And how to determine this proportionality coefficient becomes the key to error compensation, which is also the work to be done by the deviation prediction model.

[0027] The historical processing data includes basic equipment parameters, processing environment parameters, and error parameters. The basic equipment parameters, processing environment parameters, and error parameters are consistent with the data types collected in the solution, except that the historical processing data is obtained by collecting data from other processing devices of the same model as the target device.

[0028] The basic equipment parameters include equipment model, service life, and total processing time. The equipment model is used to determine the equipment type to avoid mixing data of different devices and affecting the accuracy of the deviation prediction model; the service life refers to the time from the factory of the processing equipment to the statistical moment. This service life has an important impact on equipment aging and material characteristics; the total processing time is the total time for the processing equipment to process workpieces, which is significantly different from the service life, and the total processing time is also an important factor affecting the accuracy of the processing equipment. The influence of the basic equipment parameters on the processing error is slow, but its influence degree cannot be ignored over time.

[0029] The processing environment parameters include the single - processing duration and the environmental parameters. The single - processing duration refers to the total duration of the processing equipment from the start of this processing to the statistical moment. The single - processing duration also affects the processing accuracy of the processing equipment. The environmental parameters mainly refer to the temperature, humidity, etc. of the processing environment. The changes in the environmental parameters will also continuously affect the processing accuracy of the processing equipment. Compared with the basic equipment parameters, the changes in the processing environment parameters will have a more direct and rapid impact on the processing error.

[0030] The error parameters mainly include the influence error amount on each channel when multiple channels are processed simultaneously, and the corresponding influence compensation amount. Of course, the error parameters can also include the error amounts corresponding to each channel when it works alone. The influence error amount refers to the additional error influence on a certain channel when other channels are working while multiple channels are working simultaneously. The influence compensation amount refers to the additional compensation amount added to the affected channel on the basis of the original compensation amount due to the appearance of this additional error influence. As mentioned above, the influence error amount is not equivalent to the amount that needs to be compensated, so the influence error amount cannot be directly used as the influence compensation amount.

[0031] When training an artificial intelligence model, first construct the artificial intelligence model. For example, construct a basic model based on a BP neural network model or an RBF neural network model. The specific model structure can be adjusted according to the input data and output data, and will not be elaborated here too much.

[0032] To ensure the reliability of the data, add the total processing duration in the basic equipment parameters and the single - processing duration in the processing environment parameters, and update the total processing duration in the basic equipment parameters. Perform a model - fitting process on the equipment model, service duration, and the updated total processing duration in the basic equipment parameters to generate model input data. Of course, the single - processing duration can also be added to the service duration to update the service duration.

[0033] Take the ratio of the influence compensation amount to the corresponding influence error amount in the error parameters as the deviation distribution ratio, and use the deviation distribution ratio after the model - fitting process as the model output data. It should be noted that the model - fitting process is mainly to eliminate the influence of data dimensions so that the artificial intelligence model can recognize the mutual relationship between data. For parameters such as the equipment model, the data processing volume can be reduced by setting flags. For example, set a digital mark for each equipment model, and use this digital mark to replace the equipment model.

[0034] It should be noted that the technical solution claimed in the present invention is mainly applicable to multi - channel processing. Therefore, the processing channels of the processing equipment may be 2 or more than 2. If it is multi - channel, the error parameters are also the error parameters of multiple channels. The deviation distribution ratios calculated according to the error parameters also correspond to multiple channels. Each channel corresponds to a deviation distribution ratio, and multiple deviation distribution ratios are combined into the model output data.

[0035] After generating the model input data and model output data according to the corresponding basic equipment parameters, processing environment parameters, and error parameters, the constructed artificial intelligence model can be trained, and the trained artificial intelligence model is marked as a deviation prediction model. The training process of the artificial intelligence model has been disclosed in the existing solutions and can be referred to for training. The specific training process will not be elaborated here.

[0036] After obtaining the deviation prediction model through training, the deviation prediction model can be deployed in the numerical control system to perform error compensation on the target equipment at any time during the processing of the target equipment, improving the processing accuracy of the target equipment at each stage.

[0037] Next, how to perform error compensation according to the deviation prediction model will be described in detail.

[0038] Take the processing equipment that needs to be compensated as the target equipment. Before processing the target equipment, test it to obtain the error parameters. The test process can be referred to as follows: First, process by Channel 1. After the processing time of Channel 1 is over, Channel 2 joins and processes simultaneously with Channel 1. After time 2, Channel 1 stops processing, and Channel 2 processes alone. During the processing, use a laser interferometer to monitor the movement trajectory of the machine tool during the processing. Based on the movement trajectory, calculate the error amounts of Channel 1 and Channel 2, as well as the influence error amount of Channel 2 on Channel 1 and the influence error amount of Channel 1 on Channel 2 when processing simultaneously.

[0039] Through the above test process, the error amount of Channel 1 or Channel 2 of the target equipment when working alone, and the total error amount of Channel 1 or Channel 2 when Channels 1 and 2 are working simultaneously can be obtained. Subtract the error amount of Channel 1 when working alone from the total error amount of Channel 1 when working simultaneously to obtain the influence error amount of Channel 1. Similarly, the influence error amount of Channel 2 can be calculated. Time 1 and time 2 in the test process are preset to ensure that error data can be detected within the set time period.

[0040] Then, collect the basic equipment parameters and processing environment parameters corresponding to the target equipment, perform appropriate model processing on the basic equipment parameters and processing environment parameters, and input them into the deviation prediction model to obtain the corresponding deviation distribution ratio. If the error amount when Channel 1 works alone is WC, and the influence error amount when both channels work simultaneously is YWC, extract the ratio FPB corresponding to this moment of Channel 1 from the deviation distribution ratio, and calculate the error compensation amount WBL of the target channel through the formula WBL = WC + PFB × YWC. This error compensation amount WBL is the total error compensation amount of Channel 1. Similarly, the error compensation amount of Channel 2 can be calculated.

[0041] It should be noted that during the processing of the target device, continuous processing will cause changes in the processing environment parameters. In particular, parameters such as temperature and humidity in the environment will cause changes in the deviation distribution ratio. Therefore, during the processing, the processing environment parameters are collected in real time, and the real-time collected processing environment parameters and the basic device parameters are combined to form new deviation prediction parameters, which are input into the deviation prediction model to obtain a new deviation distribution ratio. Real-time compensation of the processing process of the target device according to the deviation distribution ratio obtained in real time can improve the compensation accuracy.

[0042] Embodiment 2 Compared with Embodiment 1, in this embodiment, the influence error amount of the target device is dynamically predicted, and the dynamic prediction result is combined with the dynamically determined deviation distribution ratio to compensate each channel in real time.

[0043] The relationship between the influence error amount and the processing environment parameters during a single processing of historical data can be analyzed, that is, a mathematical relationship between the total influence error amount (established for each channel) and the single processing duration, environmental temperature, environmental humidity, etc. is established through a mathematical model. Of course, it can also be established through an artificial intelligence model.

[0044] When performing compensation, first predict the influence error amount of each channel according to the real-time collected processing environment parameters, multiply the influence error amount by the real-time determined deviation distribution ratio, and then combine it with the error amount during single-channel independent processing to obtain the error compensation amount required for the corresponding channel.

[0045] The influence error amount in this embodiment changes dynamically, that is, the influence error amount of each channel is dynamically determined according to the processing environment parameters of the target device. Compared with Embodiment 1 where the influence error amount is determined by testing at the start of processing and subsequent compensation is based on the test data, obviously the compensation accuracy of this embodiment is higher.

[0046] Furthermore, the error amount of each channel can also be determined by establishing a mathematical model. By establishing the mapping relationship between the error amount of each channel and the processing environment parameters, dynamic prediction of the error amount can be achieved. Combining the dynamically predicted error amount of each channel and the influence error amount with the real-time determined deviation distribution ratio can ensure that the error compensation amount is more in line with the actual situation and further improve the error compensation accuracy.

[0047] Embodiment 3 Compared with Embodiment 1 or Embodiment 2, the historical processing data in this embodiment can be obtained through simulation tests, such as through Siemens machine tool simulation software SinuTrain, five-axis machine tool rotary axis error analyzer R-TEST, etc. By using these software to simulate the individual error amounts of each channel and the influence error amounts of each channel during simultaneous processing under different basic device parameters and processing environment parameters, the difficulty of obtaining historical processing data can be reduced, and the sufficiency of the data volume can be ensured, improving the reliability of the deviation prediction model.

[0048] In the embodiment of the second aspect of the present application, an error compensation system for a processing device is provided, including a data analysis module and a data acquisition module connected thereto; Data acquisition module: used to collect historical processing data; and collect the basic equipment parameters and processing environment parameters of the target device; wherein, the basic equipment parameters include the equipment model, service duration, total processing duration, the processing environment parameters include the single processing duration and environmental parameters, and the processing channels of the target device include at least channel one and channel two; Data analysis module: used to train an artificial intelligence model based on historical processing data to obtain a deviation prediction model; wherein, the deviation prediction model is used to construct a mapping relationship between the processing environment and the compensation ratio during multi-channel processing; and, During processing, test the error parameters of the target device, integrate the basic equipment parameters and processing environment parameters and input them into the deviation prediction model to obtain a deviation distribution ratio; wherein, the error parameters include the error amount during single-channel processing and the influence error amount on each channel during multi-channel simultaneous processing; Calculate the error compensation amount for each channel based on the deviation distribution ratio and the error parameters; wherein, the error compensation amount includes the error compensation amount during single-channel processing and the error compensation amount during multi-channel processing.

[0049] The above embodiments are only used to illustrate the technical method of the present application and not to limit it. Although the present application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present application can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present application.

Claims

1. An error compensation method for a processing device, characterized in that Including: Collect historical processing data to train an artificial intelligence model, obtaining a deviation prediction model; wherein, the deviation prediction model is used to construct a mapping relationship between the processing environment and the compensation ratio during multi-channel processing. Collect the basic equipment parameters and processing environment parameters of the target equipment; wherein, the basic equipment parameters include the equipment model, service life, total processing duration, and the processing environment parameters include the single processing duration and environmental parameters. The processing channels of the target equipment include at least Channel 1 and Channel 2. During processing, test the error parameters of the target equipment; integrate the basic equipment parameters and the processing environment parameters and input them into the deviation prediction model to obtain the deviation allocation ratio; wherein, the error parameters include the error amount during single-channel processing and the influence error amount on each channel during multi-channel simultaneous processing. Calculate the error compensation amount for each channel based on the deviation allocation ratio and the error parameters; wherein, the error compensation amount includes the error compensation amount during single-channel processing and the error compensation amount during multi-channel processing.

2. The error compensation method of a processing device according to claim 1, characterized in that Collecting historical processing data to train an artificial intelligence model includes: Collect the basic processing data of the processing equipment of the same model as the target equipment; wherein, the basic processing data includes basic equipment parameters, processing environment parameters, and error parameters. Integrate the basic equipment parameters and the processing environment parameters into model input data, and integrally obtain model output data based on the error parameters; integrate the model input data and the model output data into historical processing data. Train an artificial intelligence model with the historical processing data; wherein, the artificial intelligence model includes a BP neural network model or an RBF neural network model.

3. The error compensation method of a processing device according to claim 2, characterized in that, Integrating the basic equipment parameters and the processing environment parameters into model input data includes: Add the total processing duration in the basic equipment parameters to the single processing duration in the processing environment parameters to obtain the updated total processing duration. Perform model adaptation processing on the equipment number, service life, total processing duration, single processing duration, and environmental parameters to obtain model input data; wherein, the model adaptation processing includes setting marks and normalization processing.

4. The error compensation method of a processing device according to claim 3, characterized in that, Integrally obtaining model output data based on the error parameters includes: Extract the influence error amount on each channel during multi-channel simultaneous processing in the error parameters, and the corresponding influence compensation amount for the influence error amount; wherein, the influence compensation amount is used to make up for the influence error amount. Take the ratio of the influence compensation amount to the influence error amount as the deviation allocation ratio, and mark it as model output data after performing model adaptation processing on the deviation allocation ratio of each channel.

5. A method for error compensation of a processing device according to claim 1, characterized in that Testing the error parameters of the target equipment during processing includes: First, let Channel 1 perform processing. After the processing time of Channel 1, Channel 2 joins and processes simultaneously with Channel 1; after time 2, Channel 1 stops processing, and Channel 2 processes alone. During the processing, use a laser interferometer to monitor the motion trajectory of the machine tool during processing; calculate the error amounts of Channel 1 and Channel 2 based on the motion trajectory, as well as the influence error amount of Channel 2 on Channel 1 and the influence error amount of Channel 1 on Channel 2 during simultaneous processing.

6. The error compensation method of a processing device according to claim 4, wherein, Integrating and inputting the basic equipment parameters and the processing environment parameters into the deviation prediction model includes: After performing appropriate model processing on the basic equipment parameters and the real-time collected processing environment parameters, marking them as deviation prediction parameters; Inputting the deviation prediction parameters into the deviation prediction model to obtain the deviation allocation ratio.

7. A method for error compensation of a processing device according to claim 6, characterized in that Calculating the error compensation amount for each channel based on the deviation allocation ratio and the error parameters, including: Sequentially taking the first channel and the second channel as the target channels; extracting the error amount during the separate processing of the channel and the corresponding influencing error amount from the error parameters; Extracting the ratio corresponding to the target channel from the deviation allocation ratio, multiplying the ratio by the influencing error amount, and adding the result to the error amount to obtain the error compensation amount for the target channel.

8. A method for error compensation of a processing device according to claim 7, characterized in that, When the first channel is the target channel, extracting the error amount during the separate processing of the first channel and the influencing error amount of the second channel on the first channel during simultaneous processing; Extracting the ratio corresponding to the target channel from the obtained deviation allocation ratio and marking it as PFB; Calculating the error compensation amount WBL for the target channel through the formula WBL = WC + PFB × YWC; where WC is the error amount and YWC is the influencing error amount.

9. A method for error compensation of a processing device according to claim 1, characterized in that After obtaining the error compensation amount for each channel, performing real-time adjustment on the processing process of each channel based on the error compensation amount.

10. An error compensation system for a processing device, which is used to execute the error compensation method for a processing device according to any one of claims 1 to 9, characterized in that, Including a data analysis module and a data acquisition module connected thereto; Data acquisition module: used to collect historical processing data; and collect the basic equipment parameters and processing environment parameters of the target equipment; where the basic equipment parameters include equipment model, service life, total processing duration, and the processing environment parameters include single processing duration and environmental parameters, and the processing channels of the target equipment include at least the first channel and the second channel; Data analysis module: used to train an artificial intelligence model based on historical processing data to obtain a deviation prediction model; where the deviation prediction model is used to construct a mapping relationship between the processing environment and the compensation ratio during multi-channel processing; and, During processing, testing the error parameters of the target equipment, integrating and inputting the basic equipment parameters and the processing environment parameters into the deviation prediction model to obtain the deviation allocation ratio; where the error parameters include the error amount during single-channel processing and the influencing error amount on each channel during multi-channel simultaneous processing; Calculating the error compensation amount for each channel based on the deviation allocation ratio and the error parameters; where the error compensation amount includes the error compensation amount during single-channel processing and the error compensation amount during multi-channel processing.

Images