CN-121997715-A - Thermal error modeling and compensation method for blade five-axis machining center

CN121997715ACN 121997715 ACN121997715 ACN 121997715ACN-121997715-A

Abstract

The invention discloses a thermal error modeling and compensating method for a blade five-axis machining center, which relates to the technical field of temperature compensation, and comprises the steps of constructing a blade five-axis machining three-dimensional model through a blade structure and a machining flow, uniformly setting a plurality of monitoring points in the constructed blade five-axis machining three-dimensional model, simultaneously arranging temperature acquisition equipment based on the set plurality of monitoring points, acquiring historical temperature data of corresponding monitoring points based on the arranged temperature acquisition equipment, after the acquisition is completed, and processing the historical temperature data of the corresponding monitoring points, simultaneously acquiring the thermal deformation data corresponding to the processed historical temperature data, constructing a thermal error prediction model based on the processed historical temperature data, finally acquiring the temperature data of the corresponding monitoring points in real time, verifying the thermal error prediction model, and determining the thermal error compensation of the blade five-axis machining center based on the thermal error prediction model after verification, thereby improving the thermal error compensation accuracy of the blade five-axis machining center.

Inventors

HOU CHUNMING
CHENG LIANG
TIAN ZHUANG

Assignees

沈阳工学院

Dates

Publication Date: 20260508
Application Date: 20251229

Claims (9)

1. The thermal error modeling and compensation method for the blade five-axis machining center is characterized by comprising the following steps of: S1, constructing a blade five-axis machining three-dimensional model based on a blade structure and a machining flow, and uniformly setting a plurality of monitoring points in the constructed blade five-axis machining three-dimensional model after construction; s2, distributing temperature acquisition equipment based on the set plurality of monitoring points, and acquiring historical temperature data of corresponding monitoring points based on the distributed temperature acquisition equipment; S3, processing the collected historical temperature data of the corresponding monitoring points in a data processing mode to obtain processed historical temperature data; S4, acquiring thermal deformation data corresponding to the processed historical temperature data, and constructing a thermal error prediction model in a data simulation mode based on the processed historical temperature data; S5, temperature data of corresponding monitoring points are collected in real time, the constructed thermal error prediction model is verified in a multi-group verification mode, and after verification is passed, thermal error compensation of the blade five-axis machining center is determined based on the thermal error prediction model.
2. The thermal error modeling and compensation method for a five-axis blade machining center according to claim 1, wherein the steps of constructing a five-axis blade machining three-dimensional model based on a blade structure and a machining flow, and uniformly setting a plurality of monitoring points in the constructed five-axis blade machining three-dimensional model after the construction is completed, comprise the following steps: collecting blade structure and processing flow data, and inputting the blade structure and processing flow data into three-dimensional model construction software to obtain a three-dimensional model of a corresponding blade; Based on the obtained three-dimensional model of the corresponding blade, dividing the three-dimensional model by a slicing and dividing mode to obtain a blade image after the three-dimensional model of the corresponding blade is divided; Based on the segmented blade image, a plurality of monitoring points are uniformly arranged on the segmented blade image.
3. The thermal error modeling and compensation method for a blade five-axis machining center according to claim 1, wherein the step of arranging temperature acquisition equipment based on the set plurality of monitoring points and acquiring historical temperature data of corresponding monitoring points based on the arranged temperature acquisition equipment comprises the following steps: based on the positions of all monitoring points on the segmented blade image, fixing the relative positions of the temperature acquisition equipment, so that all the monitoring points on the segmented blade image are uniformly distributed in the field of view of the temperature acquisition equipment; setting an acquisition period of the temperature acquisition equipment, and acquiring historical temperature data of corresponding monitoring points based on the set acquisition period.
4. The thermal error modeling and compensation method for a blade five-axis machining center according to claim 1, wherein the data processing method is used for processing collected historical temperature data of corresponding monitoring points to obtain processed historical temperature data, and the method comprises the following steps: S31, screening historical temperature data of corresponding monitoring points in a measuring point screening mode to obtain screened historical temperature data; The thermal deformation of the blade is caused by the temperature change, and thermal deformation data generated by the blade under the corresponding historical temperature data are collected; analyzing shared information among historical temperature data of corresponding monitoring points in a maximum mutual information coefficient calculation mode; the maximum mutual information coefficient calculation formula is as follows: ; Wherein, the Values representing the thermal deformation data variable and the historical temperature data variable respectively, Representing variables The amount of mutual information between the two, Representing variables Is a function of the joint probability density of (c), Representing variables Is defined in the specification, the edge probability density of (a), Representing variables Is defined in the specification, the edge probability density of (a), Representing variables Is a derivative of (2); Screening corresponding monitoring points based on shared information among the historical temperature data of the corresponding monitoring points to obtain screened historical temperature data; S32, processing the screened historical temperature data in a data processing mode to obtain processed historical temperature data.
5. The thermal error modeling and compensation method for a blade five-axis machining center according to claim 4, wherein the step of processing the screened historical temperature data by a data processing method to obtain the processed historical temperature data comprises the following steps: the normalized calculation formula is as follows: ; Wherein, the Representing the minimum in the post-screening historical temperature data, Represents the maximum value in the historical temperature data after screening, Representing historical temperature data after the S-th screening, Representing normalized S-th historical temperature data.
6. The thermal error modeling and compensation method for a blade five-axis machining center according to claim 1, wherein the collecting the thermal deformation data corresponding to the processed historical temperature data, and constructing the thermal error prediction model by a data simulation mode based on the processed historical temperature data comprises the following steps: s41, constructing a thermal error relation by a data simulation mode based on the processed historical temperature data; recording thermal deformation data of the corresponding position of every 1 ℃ of temperature rise through a control variable method and a data simulation mode; Constructing a thermal error relationship based on the recorded corresponding position thermal deformation data; The thermal error relationship is shown below ; Wherein, the The relationship of the thermal error is indicated, Representing the thermal deformation data of the corresponding position, Representing temperature change data of the corresponding position; S42, constructing a thermal error prediction model through a neural network based on the constructed thermal error relation.
7. The method for modeling and compensating thermal error in a five-axis machining center for a blade according to claim 6, wherein the constructing a thermal error prediction model through a neural network based on the constructed thermal error relation comprises the steps of: S421, setting a neural network structure, and collecting the history temperature data after corresponding processing, the thermal deformation data of the corresponding position and the thermal error relation; Setting an LSTM network to comprise an input door, an output door and a forget door; setting the input set of the input gate as Wherein Represent the first The output set of the output layer is that the historical temperature data after the group corresponding position is processed Wherein Representing the first based on thermal error relationship and output Thermal deformation data of the corresponding position predicted by the group; S422, inputting the collected and processed historical temperature data into an LSTM network, and inputting the thermal error relation and the thermal deformation data of the corresponding position into the LSTM network as candidate values; s423, processing the input of the current moment and the thermal deformation data of the corresponding position at the previous moment through a forgetting door, and updating; s424, outputting the thermal deformation data of the corresponding position processed by the forgetting door through an output door to obtain predicted thermal deformation data of the corresponding position at the next moment; S425, iteratively using the LSTM network, and determining and obtaining the trained LSTM network; Setting an error threshold between the thermal deformation data of the corresponding position predicted by the LSTM network and the thermal deformation data of the acquired corresponding position, and when the error between the thermal deformation data of the corresponding position predicted by the LSTM network and the thermal deformation data of the acquired corresponding position is within the set error threshold range, stopping iteration to obtain the trained LSTM network; S426, setting an LSTM network which accords with an error threshold range as a thermal error prediction model, and outputting the thermal deformation data of the corresponding position predicted at the next moment.
8. The thermal error modeling and compensation method for a blade five-axis machining center according to claim 1, wherein the real-time acquisition of temperature data of corresponding monitoring points verifies the constructed thermal error prediction model by a plurality of verification modes, and after verification, the thermal error compensation of the blade five-axis machining center is determined based on the thermal error prediction model, and the method comprises the following steps: acquiring temperature data of corresponding monitoring points in real time, and inputting the temperature data of the corresponding monitoring points into a constructed thermal error prediction model to obtain predicted thermal deformation data of corresponding positions; summarizing the predicted thermal deformation data of the corresponding position to construct a verification population; verifying the constructed thermal error prediction model by an ant lion algorithm; construction of solution space based on constructed verification population The positions of each ant in the solution space are set as follows: ; Setting each ant to randomly select to surround the prey or drive the prey by using a trap, wherein the probability of each ant to select the two behaviors is equal; setting the temperature data and the corresponding thermal deformation data of a group of corresponding monitoring points represented by the position of each ant in the solution space; The surrounding prey comprises the following steps: ants can choose to move towards the optimal position or move towards a random ant when surrounding the prey; When moving towards the optimal position ant: the location update formula of ants is as follows: ; Wherein, the The optimal ant position at time t is indicated, In the form of a random number, Represents the position of the z-th ant at the time t+1, The position of the z-th ant at the time t is shown; The use of traps to repel prey includes the steps of: when the ant drives the prey by using the trap, the ant can also continuously update the position of the ant; when using traps, the location update formula for ants is as follows: ; Wherein, the A default of 1 is taken for the constant, E represents a natural constant, which is a random number uniformly distributed in [ -1,1 ]; iterative use ant optimization algorithm, until the position of each ant in the solution space converges, output the temperature data and correspondent thermal deformation data of the correspondent monitoring point; And setting and outputting temperature data corresponding to the monitoring points and corresponding thermal deformation data as thermal error compensation data of the blade five-axis machining center at the next moment.
9. The thermal error modeling and compensation method for the blade-oriented five-axis machining center is characterized by further comprising a data acquisition module, a data processing module, a thermal error prediction module and a thermal error compensation module; The data acquisition module is used for acquiring temperature data and thermal deformation data corresponding to the monitoring points; the data processing module is used for processing the acquired temperature data to obtain processed temperature data; the thermal error prediction module is used for constructing a thermal error prediction module according to the processed temperature data and the acquired thermal deformation data; The thermal error compensation module is used for determining thermal error compensation data according to the constructed thermal error prediction module.

Description

Thermal error modeling and compensation method for blade five-axis machining center Technical Field The invention relates to the technical field of temperature compensation, in particular to a thermal error modeling and compensation method for a blade five-axis machining center. Background The blade is used as key equipment for wind power generation, the machining precision of the blade directly determines the quality and performance of a product, and the main shaft of the blade is used as one of core components of wind power generation, bears the rotation and positioning tasks of a workpiece or a cutter in the machining process, and is a position reference and a movement reference in actual machining. The precision and stability of the spindle have a crucial influence on the machining precision of the workpiece. However, during actual machining of the blade, the main shaft is affected by a number of factors, among which the temperature effect is particularly pronounced. The effect of temperature on the blade spindle is mainly in terms of thermal errors. Thermal errors are variations in the size, shape, and relative position of the various components of the blade caused by temperature variations, resulting in machining errors. Disclosure of Invention The invention aims to provide a thermal error modeling and compensation method for a blade five-axis machining center, which solves the problems in the background technology. In order to solve the technical problems, the invention adopts the following technical scheme that the invention provides a thermal error modeling and compensation method for a blade five-axis machining center, which specifically comprises the following steps: S1, constructing a blade five-axis machining three-dimensional model based on a blade structure and a machining flow, and uniformly setting a plurality of monitoring points in the constructed blade five-axis machining three-dimensional model after construction; s2, distributing temperature acquisition equipment based on the set plurality of monitoring points, and acquiring historical temperature data of corresponding monitoring points based on the distributed temperature acquisition equipment; S3, processing the collected historical temperature data of the corresponding monitoring points in a data processing mode to obtain processed historical temperature data; S4, acquiring thermal deformation data corresponding to the processed historical temperature data, and constructing a thermal error prediction model in a data simulation mode based on the processed historical temperature data; S5, temperature data of corresponding monitoring points are collected in real time, the constructed thermal error prediction model is verified in a multi-group verification mode, and after verification is passed, thermal error compensation of the blade five-axis machining center is determined based on the thermal error prediction model. Preferably, the construction of the blade five-axis machining three-dimensional model based on the blade structure and the machining flow, and uniformly setting a plurality of monitoring points in the constructed blade five-axis machining three-dimensional model after the construction is completed, comprises the following steps: collecting blade structure and processing flow data, and inputting the blade structure and processing flow data into three-dimensional model construction software to obtain a three-dimensional model of a corresponding blade; Based on the obtained three-dimensional model of the corresponding blade, dividing the three-dimensional model by a slicing and dividing mode to obtain a blade image after the three-dimensional model of the corresponding blade is divided; Based on the segmented blade image, a plurality of monitoring points are uniformly arranged on the segmented blade image. Preferably, the step of arranging the temperature acquisition equipment based on the set plurality of monitoring points and acquiring the historical temperature data of the corresponding monitoring points based on the arranged temperature acquisition equipment comprises the following steps: based on the positions of all monitoring points on the segmented blade image, fixing the relative positions of the temperature acquisition equipment, so that all the monitoring points on the segmented blade image are uniformly distributed in the field of view of the temperature acquisition equipment; setting an acquisition period of the temperature acquisition equipment, and acquiring historical temperature data of corresponding monitoring points based on the set acquisition period. Preferably, the data processing method processes the collected historical temperature data of the corresponding monitoring point, and the obtained processed historical temperature data comprises the following steps: S31, screening historical temperature data of corresponding monitoring points in a measuring point screening mode to obtain screened historical