阅读说明：本技术 基于大数据分析和预判的机床运动温差补偿方法 (machine tool motion temperature difference compensation method based on big data analysis and prejudgment ) 是由 刁思勉 唐小琦 周华民 贺爱林 周向东 于 2019-09-13 设计创作，主要内容包括：一种基于大数据分析和预判的机床运动温差补偿方法,包括S1、采集样本数据；S2、将若干相同型号的数控机床的相应的样本数据上传至云平台；S3、利用云平台建立基于样本数据的大数据热误差预测模型；S4、实时检测被监测的数控机床热源测量点的温度值,并上传至云平台,云平台实时分析和预判热误差值；S5、根据预判的结果,将热误差值转变为数控机床坐标系原点的补偿平移量,通过坐标系原点偏移实现热误差实时补偿。本发明有效地利用了大数据和云平台对机床运动温差进行建模,并通过大数据和云平台对机床运动温差进行分析和预判,从而根据分析和预判的结果来控制网络中任意一台数控机床,减小温度对数控机床的制造精度的影响。(a machine tool motion temperature difference compensation method based on big data analysis and prejudgment comprises the steps of S1, collecting sample data; s2, uploading corresponding sample data of a plurality of numerically-controlled machine tools with the same model to a cloud platform; s3, establishing a big data thermal error prediction model based on sample data by using a cloud platform; s4, detecting the temperature value of the monitored heat source measuring point of the numerical control machine tool in real time, uploading the temperature value to a cloud platform, and analyzing and pre-judging a heat error value in real time by the cloud platform; and S5, converting the thermal error value into a compensation translation amount of the origin of the coordinate system of the numerical control machine tool according to the pre-judging result, and realizing real-time compensation of the thermal error through the offset of the origin of the coordinate system. The invention effectively utilizes the big data and the cloud platform to model the movement temperature difference of the machine tool, and analyzes and pre-judges the movement temperature difference of the machine tool through the big data and the cloud platform, thereby controlling any numerical control machine tool in a network according to the analysis and pre-judgment results and reducing the influence of the temperature on the manufacturing precision of the numerical control machine tool.)

1. a machine tool motion temperature difference compensation method based on big data analysis and prejudgment is characterized by comprising the following steps:

S1, collecting sample data: selecting a plurality of heat source measuring points on a numerical control machine tool, and respectively establishing spindle thermal error values corresponding to time points for temperature values of the plurality of heat source measuring points to be used as sample data;

S2, uploading corresponding sample data of a plurality of numerically-controlled machine tools with the same model to a cloud platform;

S3, establishing a big data thermal error prediction model based on sample data by using a cloud platform;

S4, detecting the temperature value of the monitored heat source measuring point of the numerical control machine tool in real time, uploading the temperature value to a cloud platform, and analyzing and prejudging the heat error value in real time by the cloud platform through the big data heat error prediction model;

and S5, converting the thermal error value into a compensation translation amount of the origin of the coordinate system of the numerical control machine tool according to the pre-judging result, and realizing real-time compensation of the thermal error through the offset of the origin of the coordinate system.

2. The method for compensating temperature difference of machine tool motion based on big data analysis and prejudgment according to claim 1, wherein in step S1, the input temperature sample data is normalized to the interval [0, 1 ].

3. The machine tool motion temperature difference compensation method based on big data analysis and prejudgment according to claim 1 or 2, wherein the plurality of numerically controlled machine tools of the same model are all numerically controlled machine tools of the same model in a network.

4. The method for compensating temperature difference between machine tool motions based on big data analysis and prediction of claim 3, wherein in step S1, each NC machine tool selects at least 10 heat source measurement points, and collects at least 300 sets of temperature values and corresponding thermal error values as sample data.

5. The method for compensating temperature difference between machine tool motions based on big data analysis and prejudgment according to claim 1 or 2, wherein in step S1, each nc machine tool selects at least 10 heat source measurement points, and collects at least 300 sets of temperature values and corresponding heat error values as sample data.

6. The machine tool motion temperature difference compensation method based on big data analysis and prejudgment according to claim 1 or 2, wherein the heat source measurement points are mainly distributed at a main shaft of a numerical control machine tool, each feed shaft screw nut pair, a machine body and cooling liquid.

Technical Field

the invention relates to the technical field of precision control in the numerical control machine tool industry, in particular to a machine tool motion temperature difference compensation method based on big data analysis and prejudgment.

background

According to statistics, the machining error caused by thermal deformation of a process system in the machining process of the numerical control machine tool accounts for more than 50% of the machining error of the whole workpiece. The reasonable and effective thermal error control is an important guarantee for improving the processing precision of the numerical control machine tool. Thermal error compensation is one of the most commonly used and effective methods. The thermal error compensation is premised on establishing a mapping relation between the thermal error of the machine tool and the temperature of the machine tool as accurately as possible, so that the thermal error is forecasted by the temperature value of the machine tool in the real-time compensation process.

Since the thermal error itself has the comprehensive characteristics of quasi-static time variation, nonlinearity, attenuation delay and coupling, it is difficult to establish an accurate thermal error mathematical model by using theoretical analysis. The currently common thermal error modeling method is an experimental modeling method, namely, performing correlation analysis on thermal error data and a machine tool temperature value according to a statistical theory and performing fitting modeling by using a least square principle.

The existing thermal error modeling method of the numerical control machine tool has the defect that the final thermal error model has poor precision due to the fact that the number of the numerical control machine tools with the same model is limited.

Disclosure of Invention

In order to solve the problems, the invention provides a machine tool motion temperature difference compensation method based on big data analysis and prejudgment for the society, which can effectively utilize big data and a cloud platform to model the machine tool motion temperature difference, and analyze and prejudge the machine tool motion temperature difference through the big data and the cloud platform, thereby controlling any one numerical control machine tool in a network according to the analysis and prejudgment results, and reducing the influence of the temperature on the manufacturing precision of the numerical control machine tool.

The technical scheme of the invention is as follows: the method for compensating the motion temperature difference of the machine tool based on big data analysis and prejudgment comprises the following steps:

s1, collecting sample data: selecting a plurality of heat source measuring points on a numerical control machine tool, and respectively establishing spindle thermal error values corresponding to time points for temperature values of the plurality of heat source measuring points to be used as sample data;

S2, uploading corresponding sample data of a plurality of numerically-controlled machine tools with the same model to a cloud platform;

S3, establishing a big data thermal error prediction model based on sample data by using a cloud platform;

S4, detecting the temperature value of the monitored heat source measuring point of the numerical control machine tool in real time, uploading the temperature value to a cloud platform, and analyzing and prejudging the heat error value in real time by the cloud platform through the big data heat error prediction model;

and S5, converting the thermal error value into a compensation translation amount of the origin of the coordinate system of the numerical control machine tool according to the pre-judging result, and realizing real-time compensation of the thermal error through the offset of the origin of the coordinate system.

as a modification of the present invention, in step S1, the input temperature sample data is normalized to the interval [0, 1 ].

As an improvement to the present invention, said number of numerically controlled machine tools of the same model are all numerically controlled machine tools of the same model in the network.

As an improvement to the present invention, in step S1, each nc machine tool selects at least 10 heat source measurement points, and collects at least 300 sets of temperature values and corresponding heat error values as sample data.

As an improvement of the invention, the heat source measuring points are mainly distributed at the main shaft of the numerical control machine tool, the feed shaft screw nut pairs, the machine body and the cooling liquid.

the invention effectively utilizes the big data and the cloud platform to model the movement temperature difference of the machine tool, and analyzes and pre-judges the movement temperature difference of the machine tool through the big data and the cloud platform, thereby controlling any numerical control machine tool in a network according to the analysis and pre-judgment results and reducing the influence of the temperature on the manufacturing precision of the numerical control machine tool.

drawings

FIG. 1 is a schematic block flow diagram of one embodiment of the method of the present invention.

Detailed Description

referring to fig. 1, fig. 1 discloses a method for compensating a temperature difference of a machine tool motion based on big data analysis and prediction, which includes the following steps:

S1, collecting sample data: selecting a plurality of heat source measuring points on a numerical control machine tool, and respectively establishing spindle thermal error values corresponding to time points for temperature values of the plurality of heat source measuring points to be used as sample data; the key point of the step is that a plurality of heat source measuring points are designed on a monitored numerical control machine tool, for example, the heat source measuring points can be arranged at a main shaft, each feed shaft screw rod nut pair, a machine body, cooling liquid and the like of the numerical control machine tool; selecting at least 10 heat source measuring points for each numerical control machine tool, and collecting at least 300 groups of temperature values and corresponding thermal error values as sample data; respectively establishing a main shaft thermal error value mapping table of a time point for the acquired temperature values of the heat source measurement points, storing and uploading the main shaft thermal error value mapping table to a cloud platform;

S2, uploading corresponding sample data of a plurality of numerically-controlled machine tools of the same model in the same network to a cloud platform to form a large spindle thermal error value database of numerically-controlled machine tools of the same model; the numerical control machines with the same model can be thousands of numerical control machines with the same model distributed all over the world, and also can be hundreds of numerical control machines with the same model in the same local area network;

s3, establishing a big data thermal error prediction model based on sample data by using distributed processing, a distributed database, cloud storage and virtualization technologies of cloud computing of a cloud platform;

S4, for each monitored numerical control machine, uploading the temperature value of the real-time heat source measuring point of the monitored numerical control machine to a cloud platform in time, and analyzing and pre-judging the heat error value in real time by the cloud platform through the big data heat error prediction model;

and S5, converting the thermal error value into a compensation translation amount of the origin of the coordinate system of the numerical control machine tool by the cloud platform according to the pre-judged result, transmitting the compensation translation amount to the controlled numerical control machine tool through a network, and realizing real-time compensation of the thermal error of the numerical control machine tool by the numerical control machine tool according to the origin offset of the coordinate system.

Preferably, in step S1, the input temperature sample data is normalized to an interval [0, 1] to facilitate cloud computing.

Preferably, the plurality of numerically controlled machine tools of the same model are all numerically controlled machine tools of the same model in the network.