Pipe joint turning machining precision control method and system

Abstract

The embodiment of the application provides a pipe joint turning machining precision control method and system, and relates to the technical field of pipe joint turning machining precision control.The method comprises the following steps: before pipe joint turning machining, inertia sliding data of a main shaft and micro-motion response data of a feed shaft are acquired; according to the inertia sliding data of the main shaft, an operation condition index of the main shaft is obtained; according to the micro-motion response data of the feed shaft, a clearance condition index of the feed shaft is obtained; the operation condition index of the main shaft and the clearance condition index of the feed shaft are combined to obtain a machine tool state index; according to the machine tool state index, the machining parameters of pipe joint turning are adjusted; the quality inspection result after pipe joint turning machining is acquired; and according to the quality inspection result, the adjustment strategy of the machining parameters is optimized.The pipe joint turning machining precision control method and system provided by the application can improve the precision and the qualified rate of pipe joint turning machining.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pipe joint turning machining precision control, in particular to a pipe joint turning machining precision control method and system. BACKGROUND

[0002] In modern industrial production, in order to ensure the machining quality and production efficiency of precision parts, an advanced intelligent control system is usually adopted, which contains application data analysis to optimize machining parameters. Such a system learns and recommends the best machining settings by collecting various information in the machining process and combining the final product quality data. However, as the equipment runs for a long time, the mechanical parts of the machine tool will inevitably have slight wear or performance drift. These cumulative changes are often difficult to be directly captured by existing sensors and cannot be perceived by traditional parameter optimization logic. This causes the "ideal" state on which the intelligent system recommends machining parameters to deviate from the actual running state of the machine tool, thereby affecting the machining precision and qualification rate of the product, and the problem is progressive and hidden, which is difficult to diagnose and solve by conventional means. SUMMARY

[0003] The present application aims to at least solve one of the technical problems existing in the prior art. To this end, the present application provides a pipe joint turning machining precision control method and system, which aims to improve the precision and qualification rate of pipe joint turning machining.

[0004] In a first aspect, the pipe joint turning machining precision control method provided by the embodiments of the present application comprises:

[0005] Before pipe joint turning machining, inertia sliding data of a main shaft and micro-motion response data of a feed shaft are obtained;

[0006] According to the inertia sliding data of the main shaft, an operating condition index of the main shaft is obtained;

[0007] According to the micro-motion response data of the feed shaft, a clearance condition index of the feed shaft is obtained;

[0008] The operating condition index of the main shaft and the clearance condition index of the feed shaft are combined to obtain a machine tool state index;

[0009] According to the machine tool state index, the machining parameters of the pipe joint turning are adjusted;

[0010] The quality inspection result after pipe joint turning machining is obtained;

[0011] According to the quality inspection result, the adjustment strategy of the machining parameters is optimized.

[0012] According to some embodiments of the present application, the step of obtaining the micro-motion response data of the feed shaft comprises:

[0013] collecting baseline motion data of the feed shaft during a non-cutting movement stroke when the machining program is first executed;

[0014] collecting current motion data of the feed shaft during a non-cutting movement stroke when the machining program is subsequently executed;

[0015] obtaining a position-related motion deviation according to the current motion data and the baseline motion data;

[0016] obtaining the micro-motion response data of the feed shaft according to the motion deviation.

[0017] According to some embodiments of the present application, the step of obtaining the health index of the spindle according to the inertia sliding data of the spindle comprises:

[0018] collecting a sequence of instantaneous speed data of the spindle during the inertia sliding process;

[0019] establishing a reference curve describing the decay trend of the spindle according to the sequence of instantaneous speed data;

[0020] calculating a sequence of residual signals between the sequence of instantaneous speed data and the reference curve;

[0021] obtaining a local damage index of the spindle according to the sequence of residual signals;

[0022] obtaining the health index of the spindle according to the local damage index and the sequence of instantaneous speed data.

[0023] According to some embodiments of the present application, the step of obtaining the clearance condition index of the feed shaft according to the micro-motion response data of the feed shaft comprises:

[0024] collecting the micro-motion response data of the feed shaft, wherein the micro-motion response data comprises instantaneous current data of a feed shaft servo motor and instantaneous position data of a motor encoder;

[0025] obtaining drift information of a current sensor according to the instantaneous current data;

[0026] obtaining degradation information of the motor encoder according to the instantaneous position data;

[0027] obtaining corrected micro-motion response data according to the drift information of the current sensor and the degradation information of the motor encoder;

[0028] obtaining the clearance condition index of the feed shaft according to the corrected micro-motion response data.

[0029] According to some embodiments of this application, the step of optimizing the adjustment strategy of the processing parameters based on the quality inspection results includes:

[0030] Establish a mapping relationship between the quality inspection results and the adjustment strategy of the processing parameters;

[0031] Based on the quality inspection results, the mapping relationship is iterated to obtain an updated mapping relationship;

[0032] Based on the updated mapping relationship, the adjustment strategy for the processing parameters is optimized.

[0033] According to some embodiments of this application, the step of iterating the mapping relationship based on the quality inspection result to obtain an updated mapping relationship includes:

[0034] Based on the quality inspection results, calculate the performance error of the mapping relationship;

[0035] Based on the performance error, the parameters in the mapping relationship are iteratively adjusted until the performance error reaches the preset minimization condition, thus obtaining the mapping relationship.

[0036] According to some embodiments of this application, when the components of the machine tool condition index indicate conflicting parameter adjustment directions, the step of adjusting the machining parameters for turning the pipe fitting joint based on the machine tool condition index includes:

[0037] Obtain the machine tool status index;

[0038] The spindle influence index is obtained based on the influence of the spindle operating condition index in the machine tool condition index on the surface quality of the pipe joint;

[0039] The feed axis influence index is obtained based on the influence of the feed axis clearance condition index in the machine tool condition index on the dimensional accuracy and thread profile integrity of the pipe fitting joint.

[0040] Based on the preset quality requirements of the pipe fitting turning task, the priorities of surface quality, dimensional accuracy, thread profile integrity, and tool life are determined.

[0041] Based on the spindle influence index, the feed axis influence index, and the priority, the turning parameters of the pipe fitting joint are adjusted, including the spindle speed, feed rate, and depth of cut.

[0042] According to some embodiments of this application, the step of adjusting the turning parameters of the pipe fitting joint based on the spindle influence index, the feed axis influence index, and the priority includes:

[0043] when the machine tool state index indicates a local mechanical abnormality,

[0044] dividing the pipe joint turning process into multiple machining stroke segments;

[0045] for each machining stroke segment, adjusting pipe joint turning process parameters according to the spindle influence index, the feed axis influence index, and the priority.

[0046] According to some embodiments of the present application, the step of obtaining a spindle influence index according to the influence of the running condition index of the spindle in the machine tool state index on pipe joint surface quality comprises:

[0047] collecting wear state data of a cutting tool, physical property data of a workpiece material, and fluid state data of a cooling liquid;

[0048] when the wear state of the cutting tool, the physical properties of the workpiece material, and the fluid state of the cooling liquid are all within a preset normal range, obtaining a spindle influence index according to the influence of the running condition index of the spindle on pipe joint surface quality.

[0049] In a second aspect, embodiments of the present application provide a pipe joint turning machining precision control system for applying a machine learning model to analyze historical machining data to improve pipe joint turning machining qualification rate, which comprises:

[0050] a non-cutting test data acquisition module for acquiring inertia coasting data of a spindle and micro-motion response data of a feed axis before pipe joint turning machining;

[0051] a machine tool state index generation module for obtaining a running condition index of the spindle according to the inertia coasting data of the spindle, obtaining a clearance condition index of the feed axis according to the micro-motion response data of the feed axis, and combining the running condition index of the spindle and the clearance condition index of the feed axis to obtain a machine tool state index;

[0052] a machining parameter adjustment module for adjusting pipe joint turning machining parameters according to the machine tool state index;

[0053] an adjustment strategy optimization module for obtaining quality inspection results after pipe joint turning machining, and optimizing an adjustment strategy of the machining parameters according to the quality inspection results.

[0054] According to the technical scheme of the embodiment of the present application, at least the following beneficial effects are achieved: the present application evaluates the health state of the machine tool in advance, and takes it into account in the adjustment of the machining parameters, effectively solving the problem of difficult-to-diagnose marginal defects caused by mechanical wear of the machine tool itself, significantly improving the precision and qualification rate of pipe joint turning machining, overcoming the bottleneck of lagging quality loss in the prior art, and achieving the goal of higher precision and more stable production.

[0055] Additional aspects and advantages of the present application will be made apparent by the following description and the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0056] The accompanying drawings are included to provide a further understanding of the technical scheme of the present application, and constitute a part of the specification, and are used together with the embodiments of the present application to explain the technical scheme of the present application, and do not constitute a limitation on the technical scheme of the present application.

[0057] Figure 1 A flowchart of a pipe joint turning machining precision control method provided by an embodiment of the present application is shown in the figure.

[0058] Figure 2 A schematic diagram of a pipe joint turning machining precision control system provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical method and advantages of the present application more clear and explicit, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and do not limit the present application.

[0060] It should be noted that the meaning of multiple (or multiple items) involved in the description of the embodiments of the present application is more than two, greater than, less than, more than, etc. are understood as not including the number, above, below, etc. are understood as including the number. If there is a description of "first", "second", etc., it is only used for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features or the sequence of indicated technical features.

[0061] In the description of the present application, unless otherwise explicitly limited, the words such as setting, installing, connecting, etc. should be understood broadly, and the person skilled in the art can reasonably determine the specific meaning of the above words in the present application in combination with the specific content of the technical scheme.

[0062] Based on the above situation, the present application proposes a pipe joint turning machining precision control method and system, which aims to improve the precision and qualification rate of pipe joint turning machining.

[0063] Referring to Figure 1 , Figure 1 A flowchart of a pipe joint turning machining precision control method provided by an embodiment of the present application is shown. The embodiment of the present application includes but is not limited to steps S110 to S170, which are introduced one by one as follows.

[0064] In step S110, before pipe joint turning machining, inertia sliding data of the spindle and micro-motion response data of the feed shaft are obtained.

[0065] In step S120, the running condition index of the spindle is obtained according to the inertia sliding data of the spindle.

[0066] In step S130, the clearance condition index of the feed shaft is obtained according to the micro-motion response data of the feed shaft.

[0067] In step S140, the running condition index of the spindle and the clearance condition index of the feed shaft are combined to obtain the machine tool state index.

[0068] In step S150, the machining parameters of pipe joint turning are adjusted according to the machine tool state index.

[0069] In step S160, the quality inspection result after pipe joint turning machining is obtained.

[0070] In step S170, the adjustment strategy of the machining parameters is optimized according to the quality inspection result.

[0071] It should be noted that the inertia sliding data of the spindle refers to a series of data of the change of the speed of the spindle with time during the gradual stopping process of the spindle after power-off or disengagement from driving due to inertia. These data can reflect the friction, lubrication condition of the spindle bearing and whether there is abnormal resistance, and thus indirectly indicate the health condition of the spindle.

[0072] The micro-motion response data of the feed shaft refers to the actual response condition data of the servo system (including the motor, encoder, screw, etc.) of the feed shaft when a small displacement instruction is performed. These data can reveal the problems such as clearance, reverse clearance and stiffness change in the transmission chain of the feed shaft, which will directly affect the positioning accuracy and trajectory tracking ability of the tool.

[0073] The running condition index of the spindle is a quantitative index calculated according to the inertia sliding data of the spindle, which is used to evaluate the overall running health condition of the spindle, such as the wear degree of the bearing and poor lubrication. The higher the index, the worse the running condition of the spindle.

[0074] Clearance condition index of feed shaft: a quantitative indicator calculated from the micro-motion response data of the feed shaft, used to assess the size and stability of the clearance in the feed shaft transmission chain. The higher the index, the larger the clearance of the feed shaft, and the greater the impact on machining precision.

[0075] Machine tool condition index: a combination of the spindle condition index and the clearance condition index of the feed shaft, comprehensively reflecting the overall health of the key moving parts of the machine tool. This index provides a comprehensive basis for subsequent adjustment of machining parameters.

[0076] Machining parameters: process parameters that can be adjusted during the turning of pipe fittings, such as spindle speed, feed rate, cutting depth, tool compensation, etc.

[0077] Quality inspection results: quality data obtained through measurement, detection, etc. on product dimensional accuracy, surface roughness, thread profile integrity, etc. after pipe fitting turning is completed.

[0078] The implementation environment of the present application is generally a CNC lathe equipped with sensors capable of collecting spindle speed, feed shaft position, servo motor current, etc. and capable of communicating with a data processing unit (such as an industrial computer or a built-in computing module of a CNC system) to achieve data acquisition, processing and parameter adjustment.

[0079] Before turning of pipe fittings, the inertia coast-down data of the spindle and the micro-motion response data of the feed shaft need to be obtained. For example, by instructing the spindle to reach a certain speed under the no-load state of the machine tool, the drive is disconnected, and high-precision encoders or speed sensors are used to continuously collect the instantaneous speed of the spindle until it completely stops, thereby obtaining the inertia coast-down data of the spindle. According to the inertia coast-down data of the spindle, the spindle condition index can be obtained. For example, the collected spindle inertia coast-down data can be curve-fitted to analyze its decay characteristics, such as decay rate, smoothness of decay curve, etc. The spindle condition index can be obtained by calculating the deviation between the actual decay curve and the ideal decay curve, or by analyzing the speed fluctuations during the decay process. Larger deviations or fluctuations may indicate problems such as spindle bearing wear, poor lubrication, etc., resulting in an increase in the spindle condition index.

[0080] According to the micro-motion response data of the feed shaft, the clearance condition index of the feed shaft can be obtained. For example, the hysteresis, reverse clearance, vibration, etc. of the feed shaft during micro-motion can be analyzed. By calculating the maximum deviation between the commanded position and the actual position, or analyzing the fluctuations of the servo motor current, the clearance condition of the feed shaft can be quantified. For example, when the feed shaft changes direction, if there is a large reverse clearance, the actual position response will lag behind the commanded position, and this amount of lag can be used as a component of the clearance condition index.

[0081] Combining the spindle health index and the feed axis clearance condition index, the machine tool status index can be obtained. This combination can be achieved through weighted average, fuzzy logic reasoning or machine learning model, etc. According to the machine tool status index, the machining parameters of pipe joint turning can be adjusted. For example, if the machine tool status index shows that the spindle running condition is poor (such as bearing wear), the spindle speed can be appropriately reduced to reduce the bearing load and avoid overheating or further wear, and the feed speed may need to be adjusted to maintain cutting efficiency. If the feed axis clearance is large, the feed speed can be adjusted, or reverse clearance compensation can be added in the numerical control program to ensure the accuracy of the tool path. The adjustment of machining parameters can be a lookup table of preset rules, or an intelligent recommendation based on a machine learning model.

[0082] After the pipe joint turning process is completed, quality inspection results need to be obtained. For example, a three-coordinate measuring machine can be used to measure the dimensional accuracy of the processed pipe joint, a surface roughness meter can be used to detect the surface finish, and an optical projector or microscope can be used to check the integrity of the thread profile. These inspection results will be used as feedback for subsequent parameter optimization.

[0083] According to the quality inspection results, the adjustment strategy of the machining parameters can be optimized. For example, if the quality inspection results show that the product size is out of tolerance, the previously adjusted machining parameters can be traced back and the relationship between the machine tool status index and the quality results can be analyzed. Through iterative learning, the mapping relationship between the machine tool status index and the optimal machining parameter adjustment amount can be established or updated. This optimization process can use reinforcement learning, genetic algorithm or neural network, etc. so that the system can learn from historical data and continuously improve its accuracy and effectiveness of parameter adjustment.

[0084] Specifically, the inertia coast-down data of the spindle can reflect the friction characteristics and lubrication condition of the spindle bearing, and the change of its decay curve is directly related to the health degree of the bearing. The micro-motion response data of the feed shaft can accurately reveal the micro-clearance and reverse clearance in the transmission chain, which are key factors affecting the accuracy of tool trajectory and the integrity of thread profile. By converting these data into operating condition indexes and clearance condition indexes, and further combining them into a machine tool state index. Based on this machine tool state index, the system can actively adjust the spindle speed, feed speed, cutting depth and other machining parameters before or during machining. For example, when the spindle operating condition index is detected to be too high, the system can appropriately reduce the spindle speed to reduce vibration and heat, thereby protecting the tool and improving surface quality; when the feed shaft clearance condition index is too high, the system can adjust the feed speed or introduce a more fine clearance compensation strategy to ensure dimensional accuracy and thread profile. This proactive adjustment avoids machining defects caused by machine tool state drift, thereby significantly improving the first-pass yield.

[0085] In addition, the application also introduces a feedback mechanism of quality inspection results for optimizing the adjustment strategy of machining parameters. This means that the system not only adjusts according to preset rules, but also learns and improves from actual machining results. Compared with the prior art, the advantages of the application are:

[0086] First, it can perceive and quantify the "internal state drift" of the machine tool, not just monitor macro machining parameters. This allows the system to address gradual and hidden quality problems that traditional methods cannot diagnose.

[0087] Second, it realizes "proactive" adjustment of machining parameters, i.e. taking into account the current health status of the machine tool before machining starts, thereby actively preventing the occurrence of machining defects, rather than just passively compensating after problems occur.

[0088] Third, through feedback optimization of quality inspection results, the application builds an adaptive and self-learning system that can continuously improve the accuracy and effectiveness of parameter adjustment, thereby maintaining high levels of machining precision and yield during long-term operation of the machine tool.

[0089] In summary, the pipe joint turning machining precision control method of the application provides a more intelligent, efficient and robust solution for precision pipe joint manufacturing through deep perception, quantitative evaluation of machine tool key component state, and adaptive adjustment and strategy optimization of machining parameters, significantly improving product quality and production efficiency.

[0090] An embodiment of the present application provides the steps of obtaining the inertia sliding data of the spindle and the micro-motion response data of the feed shaft before the pipe joint turning machining in the step S110, which include but are not limited to steps S210 to S240, and each step will be introduced in turn.

[0091] Step S210, when the machining program is executed for the first time, the baseline motion data of the feed shaft in the non-cutting movement stroke is collected.

[0092] Step S220, when the machining program is executed subsequently, the current motion data of the feed shaft in the non-cutting movement stroke is collected.

[0093] Step S230, the position-related motion deviation is obtained according to the current motion data and the baseline motion data.

[0094] Step S240, the micro-motion response data of the feed shaft is obtained according to the motion deviation.

[0095] Specifically, in the pipe joint turning machining process, the micro-motion response data of the feed shaft is crucial for evaluating its running state. In order to accurately obtain the data, first, when a specific machining program is executed for the first time, the motion of the feed shaft in the non-cutting movement stroke needs to be recorded in detail, so as to collect the baseline motion data of the feed shaft. The baseline motion data can be understood as the collection of parameters such as the motion trajectory, speed and acceleration of the feed shaft on a specific path in an ideal or initial state, and its purpose is to establish a standard reference.

[0096] Subsequently, when the same machining program is executed subsequently each time, the motion data of the feed shaft in the same non-cutting movement stroke is collected again as the current motion data of the feed shaft. The current motion data reflects the actual performance of the feed shaft under the current running condition.

[0097] Further, by comparing the current motion data with the baseline motion data collected in advance, the position-related motion deviation can be calculated. The motion deviation quantifies the difference between the actual running of the feed shaft and the ideal baseline, for example, which can be manifested as position lag, overshoot or vibration, etc. These deviations can directly reflect the mechanical clearance, friction change or servo system response abnormality of the feed shaft.

[0098] Finally, according to the obtained motion deviation, the micro-motion response data of the feed shaft can be obtained. The micro-motion response data is the dynamic response characteristic of the feed shaft under small displacement or load change, which can accurately characterize the clearance condition and motion accuracy of the feed shaft.

[0099] By the technical solution, accurate and reliable acquisition of the feed shaft micro-motion response data can be realized. Compared with simply collecting data, the scheme significantly improves the accuracy and sensitivity of data collection by introducing baseline comparison and motion deviation analysis, so that even slight mechanical gap changes or motion abnormalities can be effectively detected. Thus, high-quality input data is provided for subsequent machine tool state index generation, thereby improving the overall reliability and effectiveness of pipe joint turning machining precision control, which helps to timely discover and correct potential machining precision problems.

[0100] An embodiment of the present application provides a step for obtaining a running condition index of the spindle according to the inertia coasting data of the spindle in step S120, including but not limited to steps S310 to S350, which will be introduced one by one as follows.

[0101] Step S310, collecting a transient speed data sequence of the spindle during inertia coasting;

[0102] Step S320, establishing a reference curve describing the attenuation trend of the spindle according to the transient speed data sequence;

[0103] Step S330, calculating a residual signal sequence between the transient speed data sequence and the reference curve;

[0104] Step S340, obtaining a local damage index of the spindle according to the residual signal sequence;

[0105] Step S350, obtaining a running condition index of the spindle according to the local damage index and the transient speed data sequence.

[0106] Wherein, collecting the transient speed data sequence of the spindle during inertia coasting refers to continuously or periodically acquiring the speed value of the spindle through a sensor (such as an encoder or a tachometer) during the inertia coasting of the spindle, and arranging the data set in time sequence. The data sequence can reflect the natural deceleration characteristics of the spindle under the condition of no external power input.

[0107] Further, according to the transient speed data sequence, a reference curve describing the attenuation trend of the spindle is established, which can be completed by fitting, modeling the transient speed data sequence, or using a preset attenuation model (such as an exponential attenuation model or a polynomial model). The reference curve aims to characterize the inertia coasting attenuation law of the spindle in an ideal or normal state, serving as a benchmark for subsequent analysis.

[0108] Thus, calculating the residual signal sequence between the instantaneous speed data sequence and the reference curve refers to subtracting the actual collected instantaneous speed data sequence from the values of the established reference curve at the corresponding time points, thereby obtaining a series of differences. These differences reflect the deviation between the actual running state and the ideal decay trend.

[0109] Specifically, according to the residual signal sequence, the local damage index of the main shaft is obtained, which is achieved by statistical analysis (such as calculating the root mean square value, peak value, variance, etc.), spectral analysis or time domain feature extraction of the residual signal sequence. Larger residual or abnormal residual pattern usually indicates that there may be local wear, looseness or imbalance inside the main shaft.

[0110] Finally, according to the local damage index and the instantaneous speed data sequence, the running condition index of the main shaft is obtained, which is obtained by comprehensively considering the local damage index and the overall characteristics (such as average speed, speed fluctuation, etc.) of the instantaneous speed data sequence. For example, the severity of local damage and the overall performance of the main shaft can be combined by weighted average, fuzzy logic reasoning or machine learning model, so as to quantify the health status or performance level of the main shaft.

[0111] Through the above technical solution, the running condition of the main shaft can be finely and quantitatively evaluated. Compared with the method of relying only on a single index or experience, the present solution can more sensitively detect early or local damage of the main shaft by introducing the reference curve and residual analysis, thereby avoiding the decline of machining precision or equipment failure caused by deterioration of the main shaft. Thus, the accuracy and reliability of the main shaft running condition index can be improved, and a more solid data basis for precision control of pipe joint turning is provided.

[0112] An embodiment of the present application provides a step of obtaining a gap condition index of the feed shaft according to the micro-motion response data of the feed shaft, which includes but is not limited to steps S410 to S450. Each step will be introduced in turn.

[0113] Step S410, collecting micro-motion response data of the feed shaft, wherein the micro-motion response data includes instantaneous current data of the feed shaft servo motor and instantaneous position data of the motor encoder;

[0114] Step S420, obtaining drift information of the current sensor according to the instantaneous current data;

[0115] Step S430, obtaining degradation information of the motor encoder according to the instantaneous position data;

[0116] Step S440, according to the drift information of the current sensor and the degradation information of the motor encoder, the corrected micro-motion response data is obtained;

[0117] Step S450, according to the corrected micro-motion response data, the clearance condition index of the feed shaft is obtained.

[0118] Among them, collecting the micro-motion response data of the feed shaft aims to obtain the original signal reflecting the motion characteristics of the feed shaft. The instantaneous current data of the feed motor can reflect the load change and driving torque of the motor in the micro-motion process, and the instantaneous position data of the motor encoder accurately records the actual displacement of the feed shaft. These data are the basis for evaluating the clearance condition of the feed shaft.

[0119] Further, the drift information of the current sensor refers to the unintended deviation of the sensor output signal over time or environmental conditions. By analyzing the instantaneous current data, this drift can be identified and quantified for compensation in subsequent processing. The degradation information of the motor encoder refers to the accuracy decline or signal distortion of the encoder that may occur during long-term use, such as due to wear, contamination, or electronic component aging. By analyzing the instantaneous position data, the health status and potential degradation of the encoder can be evaluated.

[0120] Thus, using the drift information of the current sensor and the degradation information of the motor encoder to correct the original micro-motion response data can eliminate or reduce measurement errors introduced by sensor and encoder defects, thereby obtaining more realistic and accurate feed shaft motion response data. The corrected micro-motion response data can more accurately reflect the actual mechanical characteristics of the feed shaft, such as its internal clearance, friction or stiffness changes.

[0121] Finally, based on the corrected micro-motion response data, the clearance condition index of the feed shaft can be calculated or derived. This index is a quantitative evaluation of the mechanical clearance state of the feed shaft, such as reflecting the axial clearance of the ball screw pair, the radial clearance of the guide pair, etc., and its numerical value is directly related to the positioning accuracy and motion stability of the feed shaft.

[0122] Through the above technical solution, when obtaining the clearance condition index of the feed shaft, the measurement errors introduced by current sensor drift and motor encoder degradation can be effectively eliminated or reduced. This makes the obtained clearance condition index of the feed shaft more accurate and reliable, avoiding misjudgment due to sensor or encoder problems. Thus, based on more accurate clearance condition index, the evaluation of machine tool state index will be more accurate, and then more refined and effective adjustment of pipe joint turning machining parameters can be realized, which ultimately helps to significantly improve the precision and yield of pipe joint turning machining.

[0123] The embodiment of the present application provides a step of adjusting the machining parameter according to the quality inspection result, and the step includes but is not limited to steps S510 to S530.

[0124] Step S510, mapping relationship between the quality inspection result and the adjustment strategy of the machining parameter is established.

[0125] Step S520, the mapping relationship is iterated based on the quality inspection result to obtain an updated mapping relationship.

[0126] Step S530, the adjustment strategy of the machining parameter is optimized according to the updated mapping relationship.

[0127] Specifically, the mapping relationship between the quality inspection result and the adjustment strategy of the machining parameter is that a mathematical model or a rule set is constructed, and the model or the rule can associate the quality inspection result after pipe joint turning machining with the strategy for adjusting the machining parameter. For example, the mapping relationship can be a machine learning model trained based on historical data, such as a regression model, a neural network or a decision tree, the input of the model can be the quality inspection result (such as size deviation, surface roughness, thread accuracy and the like), and the output is the recommended adjustment direction and amplitude of the machining parameter (such as spindle speed, feed speed, cutting depth and the like). The purpose is to convert the complex empirical adjustment into a quantifiable and learnable intelligent decision-making process.

[0128] The mapping relationship is iterated based on the quality inspection result to obtain an updated mapping relationship, which can be understood as that the established mapping relationship is continuously corrected and optimized according to the actual quality inspection feedback. Specifically, when a new quality inspection result is generated, the result is used as training data, and the parameters of the existing mapping model are adjusted through a specific algorithm (for example, gradient descent, reinforcement learning, adaptive control algorithm and the like) to reduce the error between the model prediction and the actual result, so that the mapping relationship more accurately reflects the internal relationship between the quality inspection result and the adjustment strategy of the machining parameter. The purpose is to make the adjustment strategy of the machining parameter evolve and improve adaptively with the change of the actual machining condition.

[0129] In practical applications, the adjustment strategy of the machining parameters is optimized according to the updated mapping relationship, specifically, a more accurate and effective machining parameter adjustment scheme is generated or recommended by using the mapping relationship updated through iteration. For example, when a certain quality defect is detected in the pipe joint, the updated mapping relationship can intelligently give specific machining parameter adjustment suggestions, such as increasing or decreasing the spindle speed, adjusting the feed speed or cutting depth, etc., in order to eliminate or reduce the defect in subsequent machining. The purpose is to ensure that the adjustment of the machining parameters is based on data-driven and continuous learning, thereby continuously improving the machining precision.

[0130] In some preferred embodiments, the following is described by a specific example. Suppose that during the turning machining of the pipe joint, the spindle speed and the feed speed (machining parameter adjustment strategy) need to be optimized according to the size accuracy after machining (quality inspection result). First, a polynomial regression model based on historical machining data can be established as the initial mapping relationship. The model takes the historical size deviation as the input and the machining parameter adjustment amount resulting in the deviation as the output. For example, the model can be represented as: adjustment amount = a*size deviation^2 + b*size deviation + c. Second, after the first execution of the machining program and the acquisition of the quality inspection result after the turning machining of the pipe joint (for example, there is a 0.05mm deviation between the actual size and the target size), the deviation data is input into the above regression model to calculate the machining parameter adjustment amount predicted by the current model. At the same time, the actual size deviation and the actual adjustment measures (if there is manual intervention) are used as new data points to iteratively update the coefficients a, b, c of the regression model. For example, the least squares method or the gradient descent method can be used so that the model can better fit the new data points. Finally, according to the regression model updated through iteration, when the subsequent quality inspection result again shows a size deviation, the model can provide more accurate and reliable adjustment suggestions for the spindle speed and the feed speed. For example, if the model predicts after updating that in order to correct the 0.05mm deviation to 0, the spindle speed needs to be increased by 50rpm and the feed speed needs to be reduced by 10mm / min, then the system will adjust the machining parameters according to this suggestion. Through this continuous feedback and learning mechanism, the adjustment strategy of the machining parameters will become more and more accurate, thereby effectively improving the precision and the pass rate of the turning machining of the pipe joint.

[0131] By the technical solution, the intelligence and self-adaptability of the machining parameter adjustment strategy can be realized, and the precision control level of the pipe joint turning machining is significantly improved. Compared with the basic scheme of only making a simple adjustment according to the quality inspection result, the mapping relationship is established and iterated in the present application, so that the optimization process of the machining parameter is more systematic and data-driven, thereby effectively avoiding the uncertainty and inefficiency caused by artificial experience judgment. This not only can improve the machining qualification rate and reduce the scrap rate, but also can quickly respond and provide the optimal machining parameter when facing complex and variable machining conditions, thereby reducing the production cost and improving the production efficiency and product quality stability.

[0132] An embodiment of the present application provides a step of updating the mapping relationship based on the quality inspection result, which is related to the above step S520, and includes but is not limited to steps S610 to S620. Each step will be introduced in turn.

[0133] In step S610, the performance error of the mapping relationship is calculated based on the quality inspection result.

[0134] In step S620, the parameters in the mapping relationship are iteratively adjusted according to the performance error until the performance error reaches a preset minimum condition, and the mapping relationship is obtained.

[0135] It should be noted that the performance error can be understood as the deviation between the predicted machining parameter adjustment effect by the current mapping relationship and the actual quality inspection result. This error quantifies the accuracy of the current mapping relationship in guiding the machining parameter adjustment. For example, when there is a large difference between the actual quality of the machined pipe joint and the quality predicted by the mapping relationship, the performance error will increase accordingly. The preset minimum condition refers to a threshold value that is set in advance. When the performance error is lower than the threshold value, it is considered that the mapping relationship has been optimized enough, and the iteration can be stopped. This condition can be set according to the actual machining precision requirement, production efficiency, and calculation resources, etc. For example, it can be set that the performance error is less than a very small positive number, or the performance error change rate is lower than a certain threshold value after continuous multiple iterations.

[0136] By the technical solution, the self-adaptive optimization of the machining parameter adjustment strategy can be realized, and the mapping relationship can be continuously learned and improved. This iterative adjustment mechanism based on the performance error makes the adjustment of the machining parameter no longer static or empirical, but can be dynamically adjusted according to the actual machining feedback, thereby significantly improving the precision and qualification rate of the pipe joint turning machining, and effectively dealing with the influence of dynamic changes such as machine tool state and tool wear on the machining quality.

[0137] The embodiment of the present application provides the step of adjusting the machining parameter of the pipe joint turning according to the machine tool state index in the step S150, which includes but is not limited to the steps S710 to S750, and each step is introduced as follows.

[0138] The step S710, acquiring the machine tool state index;

[0139] The step S720, obtaining the spindle influence index according to the influence of the running state index of the spindle in the machine tool state index on the pipe joint surface quality;

[0140] The step S730, obtaining the feed shaft influence index according to the influence of the gap state index of the feed shaft in the machine tool state index on the pipe joint size accuracy and thread profile integrity;

[0141] The step S740, determining the priority of the surface quality, the size accuracy, the thread profile integrity and the tool life according to the preset quality requirement of the pipe joint turning machining task;

[0142] The step S750, adjusting the pipe joint turning machining parameter according to the spindle influence index, the feed shaft influence index and the priority, and the machining parameter includes the spindle speed, the feed speed and the cutting depth.

[0143] Specifically, when the components of the machine tool state index indicate conflicting parameter adjustment directions, it means that the spindle operation condition index and the feed shaft gap condition index can respectively indicate different or even opposite adjustments to the machining parameters. For example, if the spindle operation condition index indicates that the spindle has abnormal vibration, it may suggest reducing the spindle speed to improve the surface roughness; and if the feed shaft gap condition index indicates that the feed shaft has a large gap, it may suggest reducing the feed speed to ensure dimensional accuracy. At this time, a conflict in the adjustment direction occurs. Among them, the spindle influence index is the result of quantitatively evaluating the potential influence of the spindle operation condition index on the surface quality of the pipe joint. For example, if the spindle operation condition index indicates that the spindle has abnormal vibration, the influence degree on the surface quality will be quantified as a higher spindle influence index. The feed shaft influence index is the result of quantitatively evaluating the potential influence of the feed shaft gap condition index on the dimensional accuracy and thread profile integrity of the pipe joint. For example, if the feed shaft gap condition index indicates that the feed shaft has a large gap, the influence degree on the dimensional accuracy and thread profile integrity will be quantified as a higher feed shaft influence index. In practical applications, the preset quality requirements of the pipe joint turning machining task will determine the priority of surface quality, dimensional accuracy, thread profile integrity and tool life. For example, for high-precision sealing parts, the priority of dimensional accuracy and thread profile integrity may be higher than that of surface quality; and for appearance parts, the priority of surface quality may be higher. The priority of tool life can be set according to the requirements of production cost and efficiency. These priorities can be preset by the operator according to experience, or automatically determined by a machine learning model according to historical data and task type. Therefore, the adjustment of the machining parameters is no longer a simple linear mapping, but a multi-objective optimization process considering the spindle influence index, the feed shaft influence index and the preset priority. The machining parameters include spindle speed, feed speed and cutting depth, and the adjustment of these parameters will directly affect the machining process and the quality of the final product.

[0144] In some preferred embodiments, the following is illustrated by a specific example. Suppose before a pipe joint turning process, the system detects that the spindle running condition index indicates that the spindle has slight axial runout, which usually affects the surface quality of the pipe joint, and suggests reducing the spindle speed. At the same time, the micro-motion response data of the feed shaft shows that it has a small gap, which may cause the dimensional accuracy and thread profile integrity to decline, and suggests reducing the feed speed. At this time, the conditions of the spindle and the feed shaft respectively indicate different parameter adjustment directions. Specifically, the system first obtains the current machine tool state index. Then, according to the spindle running condition index, the spindle influence index is calculated, for example, quantified as the degree of influence on the surface quality is 0.7 (between 0 and 1, 1 is the maximum influence). At the same time, according to the gap condition index of the feed shaft, the feed shaft influence index is calculated, for example, quantified as the degree of influence on the dimensional accuracy and thread profile integrity is 0.8. Suppose the preset quality requirements of the current pipe joint turning process task are: the dimensional accuracy has the highest priority (weight 0.5), followed by the thread profile integrity (weight 0.3), then the surface quality (weight 0.1), and finally the tool life (weight 0.1). Based on these indexes and priorities, the system will make a comprehensive judgment. Since the priorities of the dimensional accuracy and the thread profile integrity are high, the system will give priority to the influence of the feed shaft gap on these indicators. Therefore, although the spindle condition also needs attention, in order to ensure the high-priority dimensional accuracy and thread profile integrity, the system may decide to moderately reduce the feed speed, for example, from 1000 mm / min to 950 mm / min. At the same time, in order to take into account the surface quality, the system may fine-tune the spindle speed, for example, from 2000 rpm to 1980 rpm, or compensate by optimizing the cutting depth.

[0145] Through the above technical solutions, the application can effectively deal with the complex situation where the components of the machine tool state index indicate mutual conflict, and avoid suboptimal results or quality defects caused by simple adjustment. The scheme makes the adjustment of machining parameters more intelligent and refined, and can optimize the spindle speed, feed speed and cutting depth according to the specific processing task requirements and quality priorities, so as to effectively prolong the tool life while ensuring the surface quality, dimensional accuracy and thread profile integrity of the pipe joint, and significantly improve the overall pass rate and production efficiency of the pipe joint turning process.

[0146] An embodiment of the application provides the step of adjusting the pipe joint turning process parameters according to the spindle influence index, the feed shaft influence index and the priority, the machining parameters including the spindle speed, the feed speed and the cutting depth, which includes but is not limited to steps S810 to S820. Each step will be introduced in turn.

[0147] Step S810, when the machine tool state index indicates a local mechanical abnormality, divide the pipe joint turning process program into multiple machining stroke segments.

[0148] Step S820, for each machining stroke segment, adjust the pipe joint turning process parameters according to the spindle influence index, the feed axis influence index, and the priority.

[0149] The "local mechanical abnormality" can be understood as a deviation in mechanical performance of the machine tool in a specific work area or a specific machining stage, such as screw rod wear, local bearing wear, or poor lubrication in a certain stroke segment, which may cause machining precision to decline in that specific stroke segment. The "dividing the pipe joint turning process program into multiple machining stroke segments" means that the entire numerical control machining program of the pipe joint turning is logically or physically divided into several independent, continuous machining sub-tasks or areas according to the geometric characteristics of the workpiece, the cutting path, the machining stage (such as rough machining, finishing machining, thread machining, etc.), or the preset stroke length. Each machining stroke segment can correspond to a specific position on the pipe joint or a specific machining operation. The "adjusting the pipe joint turning process parameters for each machining stroke segment according to the spindle influence index, the feed axis influence index, and the priority" means that instead of using a set of uniform machining parameters for the entire machining process, the machining parameters of each divided machining stroke segment are dynamically and locally adjusted according to the machine tool state corresponding to that stroke segment (especially the indication of local mechanical abnormality), combined with the spindle influence index, the feed axis influence index, and the preset quality priority of that stroke segment. For example, if there is a local gap abnormality in the feed axis of a certain stroke segment, the feed speed or the cutting depth of that stroke segment can be appropriately reduced to compensate for the precision loss caused by the gap.

[0150] Through this scheme, the spindle speed, feed speed, and cutting depth of each machining stroke segment can be adjusted according to the specific machine tool state (reflected by the spindle influence index and the feed axis influence index) and the quality priority of that stroke segment. For example, if there is a local gap problem in the feed axis of a certain stroke segment, the feed speed of that stroke segment can be appropriately reduced to reduce vibration and improve positioning accuracy; if there is a local instability in the spindle operation in that stroke segment, the spindle speed can be adjusted to optimize the surface quality. This fine-tuned adjustment avoids excessive intervention in the entire machining process, ensuring that only the affected local area is optimized when necessary, thereby improving the overall machining precision and efficiency.

[0151] In some preferred embodiments, the following is described by a specific example. It is assumed that a pipe joint needs to be processed, one end of which has a high-precision thread structure, and the other end is a smooth sealing surface. After long-term use, the feed shaft of the machine tool may have a slight gap anomaly in the specific stroke range of processing the thread segment due to local wear, while the stroke range of processing the smooth sealing surface remains normal. According to the scheme of the present application, first, when the machine tool state index indicates the local mechanical anomaly, the entire pipe joint turning process is divided into at least two processing stroke segments: a thread processing stroke segment and a sealing surface processing stroke segment. For the thread processing stroke segment, due to the local gap anomaly of the feed shaft, the system will automatically adjust the processing parameters of this stroke segment according to the feed shaft influence index and the preset thread precision priority, for example, appropriately reducing the feed speed to reduce the influence of the gap on the thread profile precision. For the sealing surface processing stroke segment, since the machine tool state is normal, the original or more optimized processing parameters can be maintained to ensure the surface quality and processing efficiency. Through this segmented adjustment, the local defects of the thread processing segment can be accurately compensated, and unnecessary parameter adjustment of the sealing surface processing segment is avoided, thereby significantly improving the processing precision of the thread part and the overall qualification rate of the pipe joint while ensuring the overall processing efficiency.

[0152] Through the above technical scheme, the present application can effectively solve the problem of insufficient processing precision caused by the lack of fine adjustment capability when the traditional method handles local mechanical anomalies of machine tools. By segmenting the processing program and adjusting the processing parameters of each stroke segment, accurate compensation for local mechanical anomalies can be achieved, avoiding unnecessary global adjustment of the entire processing process that may lead to performance degradation in other areas. As a result, the processing quality of the pipe joint in the local abnormal area is significantly improved.

[0153] An embodiment of the present application provides a step for obtaining the spindle influence index according to the influence of the spindle running condition index in the machine tool state index on the surface quality of the pipe joint, including but not limited to steps S910 to S920, which will be introduced one by one as follows.

[0154] Step S910, collecting wear state data of the cutting tool, physical property data of the workpiece material, and fluid state data of the cooling liquid;

[0155] Step S920, when the wear state of the cutting tool, the physical properties of the workpiece material, and the fluid state of the cooling liquid are all within the preset normal range, obtaining the spindle influence index according to the influence of the change of the spindle running condition index on the surface quality of the pipe joint.

[0156] It should be noted that collecting the wear state data of the cutting tool can be understood as obtaining the wear degree information of the tool during use through various sensors or detection methods. For example, a visual detection system can be used to analyze the image of the tool edge, or a force sensor, acoustic emission sensor, etc. can be used to monitor the change of cutting force or acoustic signal in real time, so as to indirectly or directly evaluate the wear condition of the tool. The purpose is to identify whether the tool has reached the degree of needing to be replaced or ground, so as to avoid the decline of machining quality caused by tool wear. The physical property data of the workpiece material refers to various physical parameters of the material used for the pipe joint, such as hardness, toughness, thermal conductivity, etc. These data can be obtained through pre-material detection, data table provided by the supplier or sampling detection before machining. The purpose is to ensure that the machined workpiece material meets the design requirements, and its characteristics will not have abnormal influence on the machining process. The fluid state data of the cooling liquid refers to the parameters such as flow rate, temperature, concentration and cleanliness of the cooling liquid. These data can be monitored in real time by flow meter, temperature sensor, concentration meter and turbidity sensor, etc. The purpose is to ensure that the cooling liquid can effectively cool, lubricate and remove chips, and maintain a stable machining environment.

[0157] Among them, when the wear state of the cutting tool, the physical properties of the workpiece material and the fluid state of the cooling liquid are all within the preset normal range, it means that before obtaining the spindle influence index, the system will judge the above collected data to ensure that they are all within the pre-set acceptable threshold or range.

[0158] In some preferred embodiments, the following is illustrated by a specific example. Assume that when performing a batch of pipe joint turning machining of a specific model, in order to accurately evaluate the influence of the spindle on the surface quality, the system first collects the wear state data of the cutting tool in real time through the sensors and data interfaces integrated in the machine tool, such as monitoring the tool wear amount through a visual recognition system or a force sensor; at the same time, the material batch information of the current batch of workpieces is obtained from the production management system, and is compared with the preset material physical property database to confirm that the physical properties of the workpiece material are within the normal range; in addition, the flow rate, temperature and concentration of the cooling liquid are monitored through flow meters and temperature sensors to ensure that the fluid state meets the process requirements. Only when these external factors (tool wear, workpiece material, cooling liquid) are confirmed to be within the preset normal range, the system will further calculate and obtain the spindle influence index of the spindle on the surface quality of the pipe joint according to the spindle running condition index obtained from the inertia coasting data of the spindle. For example, if it is detected that the tool wear has exceeded the normal threshold, the system will prompt to replace the tool or adjust the evaluation strategy, rather than directly associating the spindle running condition index with the surface quality, thereby avoiding the deviation of the spindle influence evaluation caused by the tool problem. In this way, the purity and accuracy of the spindle influence index are ensured, and a reliable basis is provided for subsequent machining parameter adjustment.

[0159] Through the above technical solution, the calculation accuracy of the spindle influence index can be significantly improved. Since the interference of external factors such as cutting tool wear, workpiece material properties and cooling liquid state is excluded. This makes the subsequent machining parameter adjustment based on the spindle influence index more accurate and effective, thereby helping to more stably control the surface quality of the pipe joint, reduce the scrap rate and improve the overall machining qualification rate.

[0160] Referring to Figure 2 , Figure 2 A schematic diagram of a pipe joint turning machining precision control system is provided for an embodiment of the present application. The pipe joint turning machining precision control system 1000 is used to apply a machine learning model to analyze historical machining data to improve the pipe joint turning machining qualification rate, comprising:

[0161] The non-cutting test data acquisition module 1010 is used to acquire the inertia coasting data of the spindle and the micro-motion response data of the feed shaft before the pipe joint turning machining;

[0162] The machine tool state index generation module 1020 is used to obtain the running condition index of the spindle according to the inertia coasting data of the spindle; obtain the gap condition index of the feed shaft according to the micro-motion response data of the feed shaft; and combine the running condition index of the spindle and the gap condition index of the feed shaft to obtain the machine tool state index;

[0163] The processing parameter adjustment module 1030 is configured to adjust the pipe joint turning processing parameter according to the machine tool state index.

[0164] The adjustment strategy optimization module 1040 is configured to obtain the quality inspection result after pipe joint turning processing, and optimize the adjustment strategy of the processing parameter according to the quality inspection result.

[0165] The present application proposes a pipe joint turning processing precision control system, which aims to improve the pipe joint turning processing yield by applying machine learning model to analyze historical processing data. The system realizes the continuous evaluation of the running state of the key components of the machine tool (such as the spindle and the feed shaft) through the modular method, and dynamically adjusts the processing parameter in combination with the quality inspection result after processing, so as to adapt to the actual running state of the machine tool, thereby improving the precision and yield of the pipe joint turning processing. The system forms a closed-loop intelligent control architecture by integrating the data acquisition, state evaluation, parameter adjustment and strategy optimization function modules, effectively solving the problem of processing precision decline caused by mechanical performance drift in the long-term running of the traditional system.

[0166] Specifically, the core of the pipe joint turning processing precision control system of the present application lies in the cooperative work of various function modules, which realizes the deep perception of the machine tool state and the self-adaptive adjustment of the processing parameter.

[0167] The non-cutting test data acquisition module is configured to obtain the inertia sliding data of the spindle and the micro-motion response data of the feed shaft before pipe joint turning processing. It should be emphasized that this module can be realized as a data acquisition unit integrated in the numerical control system, or a combination of an independent external sensor network and a data acquisition card. For example, this module can include a series of high-precision sensors such as encoders, accelerometers, current sensors, etc., and is connected to the host unit through a data bus. In one implementation, this module can be configured to interact with the machine tool controller through wired connection; in another implementation, this module can be configured to transmit the collected data to the central processing unit through wireless communication (such as Wi-Fi or Bluetooth).

[0168] The machine tool state index generation module is configured to obtain the running state index of the spindle according to the inertia sliding data of the spindle, obtain the gap state index of the feed shaft according to the micro-motion response data of the feed shaft, and combine the running state index of the spindle and the gap state index of the feed shaft to obtain the machine tool state index. It should be emphasized that this module can be realized as a software program running on an industrial computer, or a special processing chip embedded in the numerical control system.

[0169] The processing parameter adjustment module is configured to adjust the pipe joint turning processing parameters according to the machine tool state index. It is emphasized that the module can be implemented as a parameter management interface in the numerical control system, or a separate parameter optimization engine. In one implementation, the module can be configured to directly send parameter modification instructions to the numerical control system; in another implementation, the module can be configured to generate recommended processing parameters, which are applied after being manually confirmed by the operator.

[0170] The adjustment strategy optimization module is configured to obtain the quality inspection result after the pipe joint turning processing, and optimize the adjustment strategy of the processing parameters according to the quality inspection result. It is emphasized that the module can be implemented as an offline data analysis platform, or an online learning system. For example, the module can use a reinforcement learning algorithm to optimize the parameter adjustment strategy through continuous trial and error and feedback; or the module can use historical processing data and quality inspection results to train a prediction model through supervised learning to guide future parameter adjustment. In one implementation, the module can be configured to periodically perform batch learning and strategy updating on historical data; in another implementation, the module can be configured to fine-tune and optimize the strategy immediately after each processing task is completed.

[0171] Compared with the prior art system which mainly relies on macro sensor data and historical experience for parameter optimization, the system of the present application can prospectively obtain the inertia sliding data of the spindle and the micro-motion response data of the feed shaft through the non-cutting test data acquisition module. These data can accurately reflect the micro wear and performance drift of the key mechanical components of the machine tool. The machine tool state index generation module quantifies these difficult-to-directly-perceive micro changes into operable machine tool state indexes, thereby breaking through the limitations of traditional systems that cannot perceive gradual and hidden quality problems.

[0172] Further, the processing parameter adjustment module can actively adjust the processing parameters based on the quantified machine tool state index, rather than passively compensate after quality problems occur. This proactive adjustment mechanism significantly improves the first-time processing pass rate. In addition, the adjustment strategy optimization module introduces a feedback mechanism of quality inspection results, so that the system can continuously learn and improve its parameter adjustment strategy from actual processing results. This closed-loop adaptive capability enables the system to maintain a high level of processing precision and pass rate for a long time, effectively addressing the challenges brought by machine tool aging and working condition changes.

[0173] In summary, the system of the present application not only can perceive and quantify the internal state drift of the machine tool, realize the proactive adjustment of the processing parameters, but also through the adaptive learning mechanism, ensures the continuous optimization and stability of the processing precision during the long-term operation of the machine tool, thereby providing a more intelligent, efficient and robust solution for precision pipe joint manufacturing.

Claims

1. A pipe joint turning accuracy control method characterized by comprising: The method comprises the following steps: Before pipe joint turning, inertia sliding data of a spindle and micro-motion response data of a feed shaft are obtained; According to the inertia sliding data of the spindle, an operating condition index of the spindle is obtained; According to the micro-motion response data of the feed shaft, a clearance condition index of the feed shaft is obtained; The operating condition index of the spindle and the clearance condition index of the feed shaft are combined to obtain a machine tool state index; According to the machine tool state index, a machining parameter of the pipe joint turning is adjusted; After the pipe joint turning, a quality inspection result is obtained; According to the quality inspection result, an adjustment strategy of the machining parameter is optimized; The step of obtaining the clearance condition index of the feed shaft according to the micro-motion response data of the feed shaft comprises the following steps: The micro-motion response data of the feed shaft is collected, wherein the micro-motion response data comprises instantaneous current data of a feed shaft servo motor and instantaneous position data of a motor encoder; According to the instantaneous current data, drift information of a current sensor is obtained; According to the instantaneous position data, degradation information of the motor encoder is obtained; According to the drift information of the current sensor and the degradation information of the motor encoder, corrected micro-motion response data is obtained; According to the corrected micro-motion response data, the clearance condition index of the feed shaft is obtained.

2. The pipe joint turning machining precision control method according to claim 1, characterized in that, The step of obtaining the micro-motion response data of the feed shaft comprises the following steps: When a machining program is executed for the first time, baseline motion data of the feed shaft in a non-cutting movement stroke is collected; When the machining program is executed subsequently, current motion data of the feed shaft in the non-cutting movement stroke is collected; According to the current motion data and the baseline motion data, a position-related motion deviation is obtained; According to the motion deviation, the micro-motion response data of the feed shaft is obtained.

3. The pipe joint turning accuracy control method according to claim 1, characterized by, The step of obtaining the operating condition index of the spindle according to the inertia sliding data of the spindle comprises the following steps: A sequence of instantaneous speed data of the spindle during inertia sliding is collected; According to the sequence of instantaneous speed data, a reference curve describing a decay trend of the spindle is established; A sequence of residual signals between the sequence of instantaneous speed data and the reference curve is calculated; According to the sequence of residual signals, a local damage index of the spindle is obtained; According to the local damage index and the sequence of instantaneous speed data, the operating condition index of the spindle is obtained.

4. The pipe joint turning accuracy control method according to claim 1, characterized by, The step of optimizing the adjustment strategy of the machining parameter according to the quality inspection result comprises the following steps: A mapping relationship between the quality inspection result and the adjustment strategy of the machining parameter is established; Based on the quality inspection result, the mapping relationship is iterated to obtain an updated mapping relationship; According to the updated mapping relationship, the adjustment strategy of the machining parameter is optimized.

5. The pipe joint turning accuracy control method according to claim 4, characterized by, The step of iterating the mapping relationship based on the quality inspection result to obtain an updated mapping relationship comprises the following steps: Based on the quality inspection result, a performance error of the mapping relationship is calculated; According to the performance error, parameters in the mapping relationship are iteratively adjusted until the performance error reaches a preset minimization condition, and the mapping relationship is obtained.

6. The pipe joint turning accuracy control method according to claim 1, characterized by, When the components of the machine tool state index indicate conflicting parameter adjustment directions, the step of adjusting the machining parameters of the pipe joint turning according to the machine tool state index comprises: obtaining the machine tool state index; obtaining a spindle influence index according to an influence of a spindle running condition index in the machine tool state index on pipe joint surface quality; obtaining a feed axis influence index according to an influence of a feed axis clearance condition index in the machine tool state index on pipe joint dimensional accuracy and thread profile integrity; determining priorities of the surface quality, the dimensional accuracy, the thread profile integrity and tool life according to preset quality requirements of a pipe joint turning machining task; adjusting pipe joint turning machining parameters including spindle speed, feed speed and cutting depth according to the spindle influence index, the feed axis influence index and the priorities.

7. The pipe joint turning accuracy control method according to claim 6, wherein The step of adjusting the pipe joint turning machining parameters according to the spindle influence index, the feed axis influence index and the priorities comprises: when the machine tool state index indicates local mechanical abnormalities, dividing a pipe joint turning program into multiple machining stroke segments; for each machining stroke segment, adjusting pipe joint turning machining parameters according to the spindle influence index, the feed axis influence index and the priorities.

8. The pipe joint turning accuracy control method according to claim 6, characterized by, The step of obtaining a spindle influence index according to an influence of a spindle running condition index in the machine tool state index on pipe joint surface quality comprises: collecting wear state data of a cutting tool, physical property data of a workpiece material and fluid state data of a cooling liquid; when the wear state of the cutting tool, the physical property of the workpiece material and the fluid state of the cooling liquid are all within preset normal ranges, obtaining a spindle influence index according to an influence of a change in the spindle running condition index on pipe joint surface quality.

9. A pipe joint turning machining precision control system for improving the pipe joint turning machining yield rate by applying a machine learning model to analyze historical machining data, characterized in that, The system comprises: a non-cutting test data acquisition module configured to acquire inertia sliding data of a spindle and micro-motion response data of a feed axis before pipe joint turning machining; a machine tool state index generation module configured to obtain a spindle running condition index according to the inertia sliding data of the spindle, obtain a feed axis clearance condition index according to the micro-motion response data of the feed axis, and combine the spindle running condition index and the feed axis clearance condition index to obtain a machine tool state index; a machining parameter adjustment module configured to adjust pipe joint turning machining parameters according to the machine tool state index; an adjustment strategy optimization module configured to obtain quality inspection results after pipe joint turning machining, and optimize an adjustment strategy of the machining parameters according to the quality inspection results; The non-cutting test data acquisition module is further configured to obtain a feed axis clearance condition index according to the micro-motion response data of the feed axis, including: acquiring micro-motion response data of the feed axis, wherein the micro-motion response data includes instantaneous current data of a feed axis servo motor and instantaneous position data of a motor encoder; obtaining drift information of a current sensor according to the instantaneous current data; According to the instantaneous position data, degradation information of a motor encoder is obtained; According to the drift information of the current sensor and the degradation information of the motor encoder, corrected micro-motion response data is obtained; According to the corrected micro-motion response data, a clearance condition index of the feed shaft is obtained.

Images