Pipe fitting joint turning precision control method and system

Abstract

The embodiment of the invention provides a pipe fitting connector turning precision control method and system, and relates to the technical field of pipe fitting connector turning precision control. The method comprises the following steps: before turning a pipe fitting joint, acquiring inertial sliding data of a main shaft and micro-motion response data of a feed shaft; according to the inertial sliding data of the main shaft, obtaining an operation condition index of the main shaft; according to the micro-motion response data of the feed shaft, a gap condition index of the feed shaft is obtained; the operation condition index of the main shaft and the gap condition index of the feed shaft are combined to obtain a machine tool state index; according to the machine tool state index, adjusting machining parameters of turning of the pipe fitting connector; obtaining a quality inspection result after the pipe fitting joint is turned; and according to the quality inspection result, the adjustment strategy of the machining parameters is optimized. According to the pipe fitting connector turning precision control method and system, the turning precision of the pipe fitting connector can be improved, and the qualification rate of the pipe fitting connector can be increased.

Description

Technical Field

[0001] The present application relates to the technical field of turning precision control of pipe fittings and joints, and in particular to a method and system for controlling turning precision of pipe fittings and joints. Background Art

[0002] In modern industrial production, advanced intelligent control systems, including those that use data analytics to optimize machining parameters, are often employed to ensure machining quality and production efficiency for precision parts. These systems collect a variety of information during the machining process and, combined with final product quality data, learn and recommend optimal machining settings. However, with long-term operation, the mechanical components of the machine tool inevitably experience subtle wear and performance drift. These cumulative changes are often difficult to capture directly with existing sensors and are imperceptible to traditional parameter optimization logic. This results in a discrepancy between the "ideal" state used by the intelligent system when recommending machining parameters and the actual operating conditions of the machine tool, compromising product machining accuracy and yield. These issues are also progressive and subtle, making them difficult to diagnose and resolve through conventional means. Summary of the Invention

[0003] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a method and system for controlling the turning precision of pipe joints, aiming to improve the turning precision and pass rate of pipe joints.

[0004] In a first aspect, an embodiment of the present application provides a method for controlling the turning accuracy of a pipe joint, comprising: Before turning the pipe joint, obtain the spindle's coasting data and the feed axis's micro-motion response data; Obtaining an operating condition index of the main shaft according to the freewheeling data of the main shaft; Obtaining a clearance condition index of the feed shaft according to the micro-motion response data of the feed shaft; Combining the operating condition index of the spindle and the clearance condition index of the feed axis to obtain a machine tool status index; adjusting the processing parameters of the pipe joint turning according to the machine tool status index; Obtaining a quality inspection result of the pipe joint after turning; According to the quality inspection results, the adjustment strategy of the processing parameters is optimized.

[0005] According to some embodiments of the present application, the step of obtaining the micro-motion response data of the feed axis includes: When the machining program is first executed, baseline motion data of the feed axis in the non-cutting movement stroke is collected; When the machining program is subsequently executed, current motion data of the feed axis in the non-cutting movement stroke is collected; Obtaining a position-related motion deviation based on the current motion data and the baseline motion data; According to the motion deviation, the micro-motion response data of the feed axis is obtained.

[0006] According to some embodiments of the present application, the step of obtaining the operating status index of the main shaft according to the coasting data of the main shaft includes: Collecting a sequence of instantaneous speed data of the spindle during the freewheeling process; Establishing a reference curve describing the spindle attenuation trend based on the instantaneous speed data sequence; Calculating a residual signal sequence between the instantaneous rotational speed data sequence and the reference curve; obtaining a local damage index of the spindle according to the residual signal sequence; An operating condition index of the main shaft is obtained according to the local damage index and the instantaneous rotational speed data sequence.

[0007] According to some embodiments of the present application, the step of obtaining the gap condition index of the feed shaft based on the micro-motion response data of the feed shaft includes: 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; Obtaining drift information of the current sensor according to the instantaneous current data; Obtaining degradation information of the motor encoder according to the instantaneous position data; Obtaining corrected micro-motion response data according to the drift information of the current sensor and the degradation information of the motor encoder; A clearance condition index of the feed shaft is obtained according to the corrected micro-motion response data.

[0008] According to some embodiments of the present application, the step of optimizing the adjustment strategy of the processing parameters according to the quality inspection results includes: Establishing a mapping relationship between the quality inspection results and the adjustment strategy of the processing parameters; Iterating the mapping relationship to obtain an updated mapping relationship based on the quality inspection result; The adjustment strategy of the processing parameters is optimized according to the updated mapping relationship.

[0009] According to some embodiments of the present application, the step of iterating the mapping relationship to obtain an updated mapping relationship based on the quality inspection result includes: Calculating a performance error of the mapping relationship based on the quality inspection result; According to the performance error, the parameters in the mapping relationship are iteratively adjusted until the performance error reaches a preset minimization condition, thereby obtaining the mapping relationship.

[0010] According to some embodiments of the present application, when the components of the machine tool status index indicate conflicting parameter adjustment directions, the step of adjusting the processing parameters for turning the pipe joint according to the machine tool status index includes: Obtaining the machine tool status index; Obtaining a spindle influence index according to the influence of the spindle operation status index in the machine tool status index on the surface quality of the pipe joint; Obtaining a feed axis influence index according to the influence of the feed axis clearance condition index in the machine tool condition index on the pipe joint dimensional accuracy and thread profile integrity; Determining the priorities of the surface quality, the dimensional accuracy, the thread profile integrity, and the tool life according to the preset quality requirements of the pipe fitting turning task; According to the spindle influence index, the feed axis influence index and the priority, the pipe joint turning processing parameters are adjusted, and the processing parameters include spindle speed, feed speed and cutting depth.

[0011] According to some embodiments of the present application, the step of adjusting the pipe joint turning parameters according to the spindle influence index, the feed axis influence index, and the priority includes: When the machine tool status index indicates a local mechanical abnormality, Dividing the pipe joint turning process into a plurality of processing stroke segments; For each of the machining stroke segments, the pipe joint turning machining parameters are adjusted according to the spindle influence index, the feed axis influence index and the priority.

[0012] According to some embodiments of the present application, the step of obtaining a spindle influence index based on the influence of the spindle operation status index in the machine tool status index on the surface quality of the pipe joint includes: Collecting cutting tool wear data, workpiece material physical property data, and coolant fluid state data; When the wear state of the cutting tool, the physical properties of the workpiece material, and the fluid state of the coolant are all within a preset normal range, the spindle influence index is obtained according to the influence of the change of the spindle operation condition index on the surface quality of the pipe joint.

[0013] In a second aspect, an embodiment of the present application provides a pipe fitting turning precision control system for applying a machine learning model to analyze historical processing data to improve the pipe fitting turning precision rate. The system includes: The non-cutting test data acquisition module is used to obtain the spindle's coasting data and the feed axis's micro-motion response data before turning the pipe joint; a machine tool status index generating module, configured to obtain an operating status index of the spindle based on the freewheeling data of the spindle; obtain a clearance status index of the feed axis based on the micro-motion response data of the feed axis; and combine the operating status index of the spindle and the clearance status index of the feed axis to obtain a machine tool status index; a processing parameter adjustment module, configured to adjust the pipe joint turning processing parameters according to the machine tool status index; The adjustment strategy optimization module is used to obtain the quality inspection results of the pipe joint after turning, and optimize the adjustment strategy of the processing parameters according to the quality inspection results.

[0014] According to the technical solution of the embodiment of the present application, there are at least the following beneficial effects: the present application effectively solves the problem of difficult-to-diagnose marginal defects caused by mechanical wear of the machine tool itself by prospectively evaluating the health status of the machine tool and incorporating it into the consideration of processing parameter adjustment, significantly improves the accuracy and pass rate of pipe fitting turning, overcomes the bottleneck of lagging quality loss in the existing technology, and achieves the goal of higher precision and more stable production.

[0015] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide a further understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.

[0017] Figure 1 A schematic flow chart of a method for controlling the turning accuracy of a pipe joint provided in one embodiment of the present application; Figure 2 A schematic diagram of a pipe fitting turning precision control system provided in one embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical methods and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0019] It should be noted that the term "multiple" (or multiple items) used in the description of the embodiments of this application means more than two. "greater than," "less than," and "exceed" are to be understood as excluding the number indicated, while "above," "below," and "within" are to be understood as inclusive. The use of terms such as "first" and "second" is solely for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance, implicitly specifying the number of the indicated technical features, or implicitly specifying the order of the indicated technical features.

[0020] In the description of this application, unless otherwise clearly defined, terms such as setting, installing, and connecting should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in this application based on the specific content of the technical solution.

[0021] Based on the above situation, the present application proposes a method and system for controlling the turning processing accuracy of pipe fittings and joints, aiming to improve the turning processing accuracy and qualification rate of pipe fittings and joints.

[0022] See also Figure 1 , Figure 1 This is a flow chart of a method for controlling the turning accuracy of a pipe joint provided in one embodiment of the present application. This embodiment of the present application includes but is not limited to steps S110 to S170, and each step is described in sequence below.

[0023] Step S110: Before turning the pipe joint, obtain the inertial sliding data of the main spindle and the micro-motion response data of the feed axis; Step S120: Obtaining a spindle operation status index based on the spindle's coasting data; Step S130: Obtaining a clearance condition index of the feed shaft according to the micro-motion response data of the feed shaft; Step S140: combining the spindle operation status index and the feed axis clearance status index to obtain a machine tool status index; Step S150: adjusting the processing parameters for turning the pipe joint according to the machine tool status index; Step S160, obtaining the quality inspection result of the pipe joint after turning; Step S170: Optimize the adjustment strategy of processing parameters according to the quality inspection results.

[0024] It's important to note that spindle coasting data refers to a series of data showing the time-varying spindle speed as the spindle gradually comes to a stop due to inertia after power is removed or the drive is disconnected. This data can reveal the friction and lubrication conditions of the spindle bearings, as well as any abnormal resistance, and indirectly indicate the health of the spindle.

[0025] Feed axis micro-response data: This refers to the actual response of the feed axis's servo system (including the motor, encoder, and leadscrew) to tiny displacement commands. This data can reveal issues such as backlash, backlash, and stiffness variations in the feed axis's drive train, which can directly affect the tool's positioning accuracy and trajectory tracking capabilities.

[0026] Spindle Health Index: This is a quantitative indicator calculated based on the spindle's coasting data. It is used to assess the spindle's overall health, such as bearing wear and lubrication issues. A higher index may indicate worse spindle health.

[0027] The feed axis clearance index is a quantitative indicator calculated based on the feed axis's micro-response data. It is used to assess the clearance size and stability within the feed axis's drive train. A higher index may indicate greater clearance in the feed axis, which can have a greater impact on machining accuracy.

[0028] The Machine Tool Condition Index (MACHINE CONDITION INDEX) is a combination of the spindle's operating condition index and the feed axis's clearance condition index, comprehensively reflecting the overall health of the machine tool's key moving components. This index provides a comprehensive basis for adjusting subsequent machining parameters.

[0029] Processing parameters: refers to the process parameters that can be adjusted during the turning process of pipe fittings, such as spindle speed, feed rate, cutting depth, tool compensation, etc.

[0030] Quality inspection results: refers to the quality data on product dimensional accuracy, surface roughness, thread profile integrity, etc. obtained through measurement, testing and other means after the pipe fittings are turned.

[0031] The implementation environment of this application is usually a CNC lathe, which is equipped with sensors that can collect data such as spindle speed, feed axis position, servo motor current, etc., and can communicate with a data processing unit (such as an industrial computer or a computing module built into a CNC system) to achieve data acquisition, processing and parameter adjustment.

[0032] Before turning pipe joints, it is necessary to obtain the spindle's coasting data and the feed axis's micro-motion response data. For example, when the machine tool is in an unloaded state, the spindle can be instructed to reach a certain speed and then disconnect the drive. A high-precision encoder or speed sensor can be used to continuously collect the instantaneous speed of the spindle until it stops completely, thereby obtaining the spindle's coasting data. Based on the spindle's coasting data, the spindle's operating status index can be obtained. For example, the collected spindle coasting data can be curve-fitted to analyze its attenuation characteristics, such as the attenuation rate and the smoothness of the attenuation curve. The spindle's operating status index can be obtained by calculating the deviation between the actual attenuation curve and the ideal attenuation curve, or by analyzing the speed fluctuations during the attenuation process. Large deviations or fluctuations may indicate problems such as spindle bearing wear and poor lubrication, which will lead to an increase in the operating status index.

[0033] The feed axis's clearance condition index can be derived from the feed axis's micro-motion response data. For example, characteristics such as hysteresis, backlash, and vibration during micro-motion can be analyzed. The feed axis's clearance condition can be quantified by calculating the maximum deviation between the command position and actual position or analyzing servo motor current fluctuations. For example, when the feed axis switches direction and there is significant backlash, the actual position response will lag behind the command position. This lag can be used as a component of the clearance condition index.

[0034] The machine tool status index can be obtained by combining the spindle operating condition index and the feed axis clearance condition index. This combination can be achieved through weighted averaging, fuzzy logic reasoning, or machine learning models. Based on the machine tool status index, the processing parameters for pipe fitting turning can be adjusted. For example, if the machine tool status index shows that the spindle is in poor operating condition (such as bearing wear), the spindle speed can be appropriately reduced to reduce the bearing load and avoid overheating or further wear. At the same time, the feed rate may need to be adjusted to maintain cutting efficiency. If the feed axis clearance is large, the feed rate can be adjusted, or backlash compensation can be added to the CNC program to ensure the accuracy of the tool path. The adjustment of the processing parameters can be a lookup table with preset rules or an intelligent recommendation based on a machine learning model.

[0035] After turning pipe fittings, quality inspection results are required. For example, a coordinate measuring machine can be used to measure the dimensional accuracy of the machined pipe fittings, a surface roughness tester can be used to check the surface finish, and an optical projector or microscope can be used to check the integrity of the thread profile. These inspection results serve as feedback for subsequent parameter optimization.

[0036] Based on quality inspection results, machining parameter adjustment strategies can be optimized. For example, if quality inspection results indicate a product dimension 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 between the machine tool status index and the optimal machining parameter adjustment can be established or updated. This optimization process can utilize methods such as reinforcement learning, genetic algorithms, or neural networks, enabling the system to learn from historical data and continuously improve the accuracy and effectiveness of its parameter adjustments.

[0037] Specifically, spindle coasting data can reveal the friction characteristics and lubrication condition of the spindle bearings, with changes in its decay curve directly correlated to bearing health. Feed axis micro-response data accurately reveals minute backlash and clearance in the drive train, critical factors affecting tool path accuracy and thread profile integrity. By converting this data into an operating condition index and a clearance condition index, which are then combined into a machine condition index, the system can proactively adjust machining parameters such as spindle speed, feed rate, and depth of cut before or during machining. For example, if the spindle operating condition index is detected to be high, the system can appropriately reduce the spindle speed to reduce vibration and heat, thereby protecting the tool and improving surface quality. If the feed axis clearance condition index is high, the system can adjust the feed rate or implement a more refined clearance compensation strategy to ensure dimensional accuracy and thread profile. This proactive adjustment avoids machining defects caused by machine condition drift, significantly improving first-pass yield.

[0038] In addition, this application also introduces a feedback mechanism for quality inspection results to optimize the adjustment strategy of processing parameters. This means that the system not only adjusts according to preset rules, but can also learn and improve from actual processing results. Compared with existing technologies, the advantages of this application are: First, it can sense and quantify the "internal state drift" of the machine tool, rather than just monitoring macro-machining parameters. This enables the system to address gradual and hidden quality problems that are difficult to diagnose with traditional methods.

[0039] Second, it enables “forward-looking” adjustment of machining parameters, that is, the current health status of the machine tool is taken into account before machining begins, thereby proactively preventing the occurrence of machining defects, rather than just passively compensating after problems occur.

[0040] Third, through feedback optimization of quality inspection results, this application constructs an adaptive, self-learning system that can continuously improve the accuracy and effectiveness of parameter adjustment, thereby maintaining a high level of processing accuracy and pass rate during the long-term operation of the machine tool.

[0041] To sum up, the pipe fitting turning processing accuracy control method of this application provides a more intelligent, efficient and robust solution for the manufacturing of precision pipe fittings through deep perception and quantitative evaluation of the status of key components of machine tools, as well as adaptive adjustment and strategy optimization of processing parameters, thereby significantly improving product quality and production efficiency.

[0042] An embodiment of the present application provides steps for obtaining the inertial sliding data of the spindle and the micro-motion response data of the feed axis before turning the pipe joint in the above-mentioned step S110, including but not limited to steps S210 to S240. Each step is introduced in turn below.

[0043] Step S210: When the machining program is first executed, baseline motion data of the feed axis in the non-cutting movement stroke is collected; Step S220: When the machining program is subsequently executed, the current motion data of the feed axis in the non-cutting movement stroke is collected; Step S230: obtaining a position-related motion deviation based on the current motion data and the baseline motion data; Step S240: Acquire the micro-motion response data of the feed axis according to the motion deviation.

[0044] Specifically, during the turning process of pipe fittings, the micro-motion response data of the feed axis is crucial for evaluating its operating status. To accurately obtain this data, the first step is to record the motion of the feed axis during its non-cutting travel when executing a specific machining program for the first time. This data is then used to collect baseline motion data for the feed axis. This baseline motion data can be understood as a collection of parameters such as the motion trajectory, velocity, and acceleration of the feed axis along a specific path under an ideal or initial state. The purpose of this data is to establish a standard reference.

[0045] Subsequently, each time the same machining program is executed, the motion data of the feed axis during the same non-cutting travel is collected again and used as the current motion data of the feed axis. The current motion data reflects the actual performance of the feed axis under the current operating conditions.

[0046] Furthermore, by comparing the current motion data with pre-collected baseline motion data, position-related motion deviations can be calculated. This motion deviation quantifies the difference between the feed axis's actual operation and the ideal baseline, and may manifest as position lag, overshoot, or vibration, for example. These deviations can directly reflect problems such as mechanical backlash, friction changes, or abnormal servo system response in the feed axis.

[0047] Finally, the obtained motion deviation can be used to obtain the feed axis's micro-motion response data. This micro-motion response data is the dynamic response characteristics of the feed axis under small displacement or load changes, which can accurately characterize the feed axis's clearance condition and motion accuracy.

[0048] The above technical solution enables accurate and reliable acquisition of feed axis micro-motion response data. Compared to simple data collection, this solution significantly improves the accuracy and sensitivity of data acquisition by introducing baseline comparison and motion deviation analysis, effectively detecting even minor mechanical clearance changes or motion anomalies. This provides high-quality input data for subsequent machine tool status index generation, thereby improving the overall reliability and effectiveness of precision control in pipe fitting turning, and facilitating the timely identification and correction of potential machining accuracy issues.

[0049] An embodiment of the present application provides steps for obtaining the spindle's operating status index based on the spindle's inertial coasting data in the above-mentioned step S120, including but not limited to steps S310 to S350. Each step is introduced in turn below.

[0050] Step S310: collecting a sequence of instantaneous speed data of the spindle during the coasting process; Step S320: establishing a reference curve describing the spindle attenuation trend based on the instantaneous speed data sequence; Step S330, calculating a residual signal sequence between the instantaneous speed data sequence and the reference curve; Step S340: Obtaining a local damage index of the main shaft according to the residual signal sequence; Step S350: Obtain the spindle operation status index according to the local damage index and the instantaneous speed data sequence.

[0051] Collecting the instantaneous spindle speed data sequence during the spindle's coasting process refers to continuously or periodically acquiring spindle speed values ​​via a sensor (e.g., an encoder or tachometer) during the spindle's coasting process and arranging the resulting data in chronological order. This data sequence can reflect the natural deceleration characteristics of the spindle in the absence of external power input.

[0052] Furthermore, based on the instantaneous speed data sequence, a reference curve describing the spindle's decay trend is established. This can be accomplished by fitting or modeling the instantaneous speed data sequence, or by employing a preset decay model (e.g., an exponential decay model or a polynomial model). This reference curve is intended to characterize the spindle's coasting decay behavior under an ideal or normal state, serving as a benchmark for subsequent analysis.

[0053] Therefore, calculating the residual signal sequence between the instantaneous speed data sequence and the reference curve involves subtracting the values ​​of the actual instantaneous speed data sequence from the established reference curve at corresponding time points point by point, thereby obtaining a series of differences. These differences reflect the deviation between the actual operating state and the ideal attenuation trend.

[0054] Specifically, a local damage index for the spindle is derived from the residual signal sequence. This is achieved by performing statistical analysis (e.g., calculating the root mean square value, peak value, and variance), spectral analysis, or time-domain feature extraction on the residual signal sequence. Large residuals or abnormal residual patterns typically indicate possible damage within the spindle, such as localized wear, looseness, or imbalance.

[0055] Ultimately, the spindle's operating condition index is derived based on the local damage index and the instantaneous speed data series. This index is derived by comprehensively considering the overall characteristics of the local damage index and the instantaneous speed data series (e.g., average speed, speed fluctuation, etc.). For example, the severity of local damage can be combined with the spindle's overall operating performance through weighted averaging, fuzzy logic reasoning, or machine learning models to quantify the spindle's health or performance level.

[0056] The above technical solution enables a refined, quantitative assessment of the spindle's operating condition. Compared to methods that rely solely on a single indicator or empirical judgment, this solution, by introducing reference curves and residual analysis, can more sensitively detect early or localized spindle damage, thereby avoiding the degradation of machining accuracy or equipment failure caused by spindle deterioration. This improves the accuracy and reliability of the spindle operating condition index, providing a more solid data foundation for precision control in pipe fitting turning.

[0057] An embodiment of the present application provides steps for obtaining the gap condition index of the feed shaft based on the micro-motion response data of the feed shaft in the above-mentioned step S130, including but not limited to steps S410 to S450, and each step is introduced in turn below.

[0058] Step S410: collecting the micro-motion response data of the feed axis, wherein the micro-motion response data includes the instantaneous current data of the feed axis servo motor and the instantaneous position data of the motor encoder; Step S420: Obtain drift information of the current sensor according to the instantaneous current data; Step S430: Obtaining degradation information of the motor encoder according to the instantaneous position data; Step S440: Obtaining corrected micro-motion response data based on the drift information of the current sensor and the degradation information of the motor encoder; Step S450: Obtain the clearance condition index of the feed axis according to the corrected micro-motion response data.

[0059] The purpose of collecting the feed axis's micro-motion response data is to obtain raw signals reflecting the axis's motion characteristics. The feed axis servo motor's instantaneous current data reflects the motor's load changes and drive torque during micro-motion, while the motor encoder's instantaneous position data accurately records the feed axis's actual displacement. This data is fundamental to assessing the feed axis's clearance condition.

[0060] Furthermore, current sensor drift refers to the unexpected shift in the sensor's output signal over time or over changing environmental conditions. By analyzing instantaneous current data, this drift can be identified and quantified, allowing compensation to be implemented in subsequent processing. Motor encoder degradation refers to the loss of accuracy or signal distortion that may occur over time due to wear, contamination, or aging of electronic components. Analysis of instantaneous position data allows assessment of the encoder's health and potential degradation.

[0061] Therefore, 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 the measurement errors introduced by the sensor and encoder's inherent defects, thereby obtaining more realistic and accurate feed axis motion response data. The corrected micro-motion response data can more accurately reflect the actual mechanical characteristics of the feed axis, such as its internal clearance, friction, or stiffness changes.

[0062] Finally, based on the corrected micro-motion response data, the feed axis clearance index can be calculated or derived. This index quantitatively evaluates the mechanical clearance status of the feed axis, reflecting, for example, the axial clearance of a ball screw pair or the radial clearance of a guideway pair. Its value is directly related to the positioning accuracy and motion smoothness of the feed axis.

[0063] The above technical solution effectively eliminates or reduces measurement errors introduced by current sensor drift and motor encoder degradation when obtaining the feed shaft clearance index. This makes the obtained feed shaft clearance index more accurate and reliable, avoiding misjudgments caused by sensor or encoder issues. Consequently, based on a more precise clearance index, the machine tool condition index can be more accurately assessed, enabling more refined and effective adjustments to pipe fitting turning parameters, ultimately significantly improving the accuracy and yield rate of pipe fitting turning.

[0064] An embodiment of the present application provides steps for optimizing the adjustment strategy of processing parameters according to the quality inspection results in the above-mentioned step S170, including but not limited to steps S510 to S530, and each step is introduced in turn below.

[0065] Step S510: establishing a mapping relationship between quality inspection results and adjustment strategies for processing parameters; Step S520: based on the quality inspection result, iterate the mapping relationship to obtain an updated mapping relationship; Step S530: Optimize the adjustment strategy of the processing parameters according to the updated mapping relationship.

[0066] Specifically, establishing a mapping relationship between the quality inspection results and the machining parameter adjustment strategy involves constructing a mathematical model or set of rules that can link the quality inspection results after turning pipe fittings with the strategy for adjusting machining parameters. For example, this mapping relationship can be a machine learning model trained on historical data, such as a regression model, a neural network, or a decision tree. Its input can be quality inspection results (such as dimensional deviation, surface roughness, thread accuracy, etc.), and its output is the recommended direction and magnitude of machining parameter adjustments (such as spindle speed, feed rate, depth of cut, etc.). The goal is to transform complex empirical adjustments into a quantifiable and learnable intelligent decision-making process.

[0067] The mapping relationship is iterated based on the quality inspection results to obtain an updated mapping relationship. This can be understood as the continuous correction and optimization of the established mapping relationship based on actual quality inspection feedback. Specifically, when new quality inspection results are generated, they are used as training data. The parameters of the existing mapping model are adjusted through specific algorithms (such as gradient descent, reinforcement learning, and adaptive control algorithms) to reduce the error between the model prediction and the actual results. This allows the mapping relationship to more accurately reflect the inherent connection between the quality inspection results and the processing parameter adjustment strategy. The goal is to enable the processing parameter adjustment strategy to adaptively evolve and improve as actual processing conditions change.

[0068] In practical applications, optimizing the machining parameter adjustment strategy based on the updated mapping relationship specifically involves utilizing the iteratively updated mapping relationship to generate or recommend more accurate and effective machining parameter adjustment solutions. For example, when a quality defect is detected in a pipe joint, the updated mapping relationship can intelligently provide specific machining parameter adjustment recommendations based on the defect's characteristics, such as increasing or decreasing the spindle speed, adjusting the feed rate, or depth of cut, in order to eliminate or mitigate the defect in subsequent processing. This is intended to ensure that machining parameter adjustments are data-driven and based on continuous learning, thereby achieving continuous improvement in machining accuracy.

[0069] In some preferred embodiments, a specific example is provided below. Suppose that during the turning process of a pipe joint, the spindle speed and feed rate need to be optimized (a machining parameter adjustment strategy) based on the post-process dimensional accuracy (quality inspection results). First, a polynomial regression model based on historical machining data can be established as an initial mapping relationship. This model takes historical dimensional deviations as input and outputs the machining parameter adjustments resulting from these deviations. For example, the model might be expressed as: Adjustment = a * Dimension Deviation^2 + b * Dimension Deviation + c. Next, after the machining program is first executed and the post-turning quality inspection results of the pipe joint are obtained (for example, a 0.05 mm deviation between the actual and target dimensions), this deviation data is input into the regression model to calculate the machining parameter adjustments predicted by the current model. Simultaneously, the actual dimensional deviation and the actual adjustment measures taken (if manual intervention was involved) are used as new data points to iteratively update the coefficients a, b, and c of the regression model. For example, the least squares method or gradient descent method can be employed to ensure a better fit of the model even for new data points. Finally, based on the iteratively updated regression model, when subsequent quality inspection results again indicate dimensional deviations, the model can provide more accurate and reliable spindle speed and feed rate adjustment recommendations. For example, if the updated model predicts that in order to correct a 0.05mm deviation to 0, the spindle speed needs to be increased by 50rpm and the feed rate needs to be reduced by 10mm / min, the system will adjust the machining parameters accordingly. Through this continuous feedback and learning mechanism, the machining parameter adjustment strategy will become increasingly precise, effectively improving the accuracy and pass rate of pipe fitting turning.

[0070] Through the above technical solutions, this application can realize the intelligence and adaptability of the processing parameter adjustment strategy, and significantly improve the precision control level of the turning processing of pipe fittings and joints. Compared with the basic solution that only makes simple adjustments based on the quality inspection results, this application makes the optimization process of processing parameters more systematic and data-driven by establishing and iterating mapping relationships, thereby effectively avoiding the uncertainty and inefficiency brought about by manual experience judgment. This can not only improve the processing qualification rate and reduce the scrap rate, but also quickly respond and provide the optimal processing parameters when faced with complex and changing processing conditions, thereby reducing production costs, improving production efficiency and product quality stability.

[0071] An embodiment of the present application provides the above-mentioned step S520, and the steps of iterating the mapping relationship to obtain an updated mapping relationship based on the quality inspection result, including but not limited to steps S610 to S620. Each step is introduced in turn below.

[0072] Step S610: Calculate the performance error of the mapping relationship based on the quality inspection result; Step S620: Iteratively adjust the parameters in the mapping relationship according to the performance error until the performance error reaches a preset minimization condition, thereby obtaining the mapping relationship.

[0073] It should be noted that the performance error can be understood as the deviation between the processing parameter adjustment effect predicted by the current mapping relationship and the actual quality inspection result. This error quantifies the accuracy of the current mapping relationship in guiding the adjustment of processing parameters. For example, when there is a large difference between the quality of the pipe joint actually processed and the quality predicted by the mapping relationship, the performance error will increase accordingly. The preset minimization condition refers to a pre-set threshold. When the performance error is lower than the threshold, it is considered that the mapping relationship has been sufficiently optimized and the iteration can be stopped. This condition can be set according to factors such as actual processing accuracy requirements, production efficiency, and computing resources. For example, it can be set so that the performance error is less than a very small positive number, or the performance error change rate is lower than a certain threshold after multiple consecutive iterations.

[0074] The above technical solution enables adaptive optimization of machining parameter adjustment strategies, ensuring that mapping relationships can be continuously learned and improved. This iterative adjustment mechanism based on performance errors eliminates static or empirical adjustments to machining parameters, enabling dynamic adjustments based on actual machining feedback. This significantly improves the accuracy and pass rate of pipe fitting turning, and effectively addresses the impact of dynamic changes in machine tool status, tool wear, and other factors on machining quality.

[0075] An embodiment of the present application provides steps for adjusting the processing parameters for pipe joint turning according to the machine tool status index in the above-mentioned step S150, including but not limited to steps S710 to S750, and each step is introduced in turn below.

[0076] Step S710: Obtaining a machine tool status index; Step S720: Obtain a spindle influence index according to the influence of the spindle operation status index in the machine tool status index on the surface quality of the pipe joint; Step S730: Obtain a feed axis influence index according to the influence of the feed axis clearance condition index in the machine tool status index on the pipe joint dimensional accuracy and thread profile integrity; Step S740: Determine the priorities of surface quality, dimensional accuracy, thread profile integrity, and tool life according to the preset quality requirements of the pipe joint turning task; Step S750: Adjust the pipe joint turning processing parameters according to the spindle influence index, the feed axis influence index and the priority, where the processing parameters include the spindle speed, feed speed and cutting depth.

[0077] Specifically, when the components of the machine tool status index indicate conflicting parameter adjustment directions, the spindle health index and the feed axis clearance index may indicate different or even opposing adjustments to machining parameters. For example, if the spindle health index indicates abnormal spindle vibration, it may be recommended to reduce the spindle speed to improve surface roughness; whereas, if the feed axis clearance index indicates large clearance, it may be recommended to reduce the feed rate to ensure dimensional accuracy. This creates a conflict in adjustment direction. The spindle impact index quantifies the potential impact of the spindle health index on the surface quality of pipe fittings. For example, if the spindle health index indicates abnormal spindle vibration, its impact on surface quality is quantified as a high spindle impact index. The feed axis impact index quantifies the potential impact of the feed axis clearance index on the dimensional accuracy and thread profile integrity of pipe fittings. For example, if the feed axis clearance index indicates large clearance, its impact on dimensional accuracy and thread profile integrity is quantified as a high feed axis impact index. In actual applications, the preset quality requirements of the pipe fitting turning task will determine the priority of surface quality, dimensional accuracy, thread profile integrity, and tool life. For example, for high-precision seals, dimensional accuracy and thread profile integrity may have a higher priority than surface quality; while for appearance parts, surface quality may have a higher priority. The priority of tool life may be set according to production cost and efficiency requirements. These priorities can be preset by the operator based on experience, or they can be automatically determined by a machine learning model based on historical data and task type. As a result, the adjustment of machining parameters is no longer a simple linear mapping, but a multi-objective optimization process that comprehensively considers the spindle influence index, feed axis influence index, and preset priorities. The machining parameters include spindle speed, feed rate, and cutting depth. Adjustment of these parameters will directly affect the machining process and the quality of the final product.

[0078] In some preferred embodiments, a specific example is provided below for illustration. Assume that before a pipe joint turning process, the system detects that the spindle's operating status index indicates that the spindle has slight axial movement, which usually affects the surface quality of the pipe joint. It is recommended to reduce the spindle speed. At the same time, the micro-response data of the feed shaft shows that it has a small gap, which may lead to a decrease in dimensional accuracy and thread profile integrity. It is recommended to reduce the feed speed. At this time, the conditions of the spindle and feed shaft respectively indicate different parameter adjustment directions. Specifically, the system first obtains the current machine tool status index. Then, based on the spindle's operating status index, the spindle influence index is calculated, for example, quantified as the degree of influence on surface quality is 0.7 (between 0 and 1, 1 is the maximum influence). At the same time, based on the feed shaft's clearance condition index, the feed shaft influence index is calculated, for example, quantified as the degree of influence on dimensional accuracy and thread profile integrity is 0.8. Suppose the preset quality requirements for the current pipe fitting turning task are: dimensional accuracy has the highest priority (weight 0.5), followed by thread profile integrity (weight 0.3), then surface quality (weight 0.1), and finally tool life (weight 0.1). Based on these indices and priorities, the system will make a comprehensive judgment. Because dimensional accuracy and thread profile integrity have higher priority, the system will prioritize the impact of feed axis clearance on these indicators. Therefore, although the spindle condition also requires attention, in order to ensure the high priority dimensional accuracy and thread profile integrity, the system may decide to moderately reduce the feed rate, for example, from 1000mm / min to 950mm / min. At the same time, to take into account surface quality, the system may fine-tune the spindle speed, for example, from 2000rpm to 1980rpm, or compensate by optimizing the cutting depth.

[0079] Through the above-mentioned technical solution, this application can effectively deal with the complex situation where the various components of the machine tool status index indicate conflicting indicators, avoiding suboptimal results or quality defects caused by simple adjustments. This solution makes the adjustment of machining parameters more intelligent and refined, and can optimize the spindle speed, feed rate and cutting depth in a targeted manner according to the specific machining task requirements and quality priorities. This effectively extends tool life while ensuring the surface quality, dimensional accuracy and thread profile integrity of pipe fittings, significantly improving the overall qualification rate and production efficiency of pipe fitting turning.

[0080] An embodiment of the present application provides the above-mentioned step S750, which adjusts the pipe joint turning processing parameters according to the spindle influence index, the feed axis influence index and the priority. The processing parameters include the spindle speed, feed speed, and cutting depth, including but not limited to steps S810 to S820. Each step is introduced in turn below.

[0081] Step S810: When the machine tool status index indicates a local mechanical abnormality, the pipe joint turning process is divided into a plurality of processing stroke segments; Step S820: For each machining stroke segment, adjust the pipe joint turning parameters according to the spindle influence index, the feed axis influence index, and the priority.

[0082] The aforementioned “local mechanical anomalies” can be understood as non-global mechanical performance deviations that occur in a specific working range or specific processing stage of the machine tool, such as screw wear, local bearing wear, or poor lubrication in a certain stroke segment. These anomalies may lead to a decrease in processing accuracy within that specific stroke segment. The aforementioned “dividing the pipe joint turning process into multiple processing stroke segments” refers to logically or physically dividing the entire pipe joint turning CNC machining program into several independent, continuous processing subtasks or areas based on the geometric features of the workpiece, cutting path, processing stage (such as roughing, finishing, threading, etc.) or preset stroke length. Each processing stroke segment can correspond to a specific part or a specific processing operation on the pipe joint. The phrase "adjusting the pipe joint turning parameters for each machining segment based on the spindle influence index, the feed axis influence index, and the priority" means that instead of using a single set of machining parameters for the entire machining process, the machining parameters for each segment are dynamically and locally adjusted based on the machine tool status corresponding to that segment (particularly any indication of local mechanical anomalies), combined with the spindle influence index, feed axis influence index, and preset quality priority for that segment. For example, if a feed axis in a particular segment has a localized clearance anomaly, the feed speed can be appropriately reduced or the cutting depth adjusted for that segment to compensate for the loss of precision caused by the clearance.

[0083] This solution allows for targeted adjustments to machining parameters such as spindle speed, feed rate, and depth of cut for each machining segment based on the specific machine tool status (reflected by the spindle influence index and feed axis influence index) and the quality priority of that segment. For example, if the feed axis of a particular segment has a local clearance issue, the feed rate can be appropriately reduced to reduce vibration and improve positioning accuracy. If the spindle is experiencing localized operational instability within that segment, the spindle speed can be adjusted to optimize surface quality. This refined adjustment avoids excessive intervention in the overall machining process, ensuring that affected local areas are optimized only when necessary, thereby improving overall machining accuracy and efficiency.

[0084] In some preferred embodiments, a specific example is provided below for illustration. Assume that a pipe joint needs to be processed, one end of which has a high-precision threaded structure and the other end has a smooth sealing surface. After long-term use, the feed shaft of the machine tool may have a slight gap abnormality due to local wear within a specific stroke range for processing the threaded section, while the stroke section for processing the smooth sealing surface remains normal. According to the solution of the present application, first, when the machine tool status index indicates the local mechanical abnormality, the entire pipe joint turning process is divided into at least two processing stroke sections: a thread processing stroke section and a sealing surface processing stroke section. For the thread processing stroke section, due to the presence of a local gap abnormality of the feed shaft, the system will automatically adjust the processing parameters of the stroke section according to the feed shaft influence index and the preset thread accuracy priority, for example, appropriately reducing the feed speed to reduce the impact of the gap on the thread profile accuracy. For the sealing surface processing stroke section, since the machine tool is in normal condition, the original or more optimized processing parameters can be maintained to ensure surface quality and processing efficiency. Through this segmented adjustment, local defects in the thread processing section can be accurately compensated, while avoiding unnecessary parameter adjustments to the sealing surface processing section. This significantly improves the processing accuracy of the threaded part and the overall qualification rate of pipe joints while ensuring overall processing efficiency.

[0085] Through the above-mentioned technical solution, this application effectively addresses the problem of insufficient machining accuracy caused by the lack of fine-tuning capabilities when addressing localized mechanical anomalies in machine tools using traditional methods. By segmenting the machining program and specifically adjusting the machining parameters for each stroke segment, precise compensation for localized mechanical anomalies can be achieved, avoiding unnecessary global adjustments to the entire machining process that could potentially degrade performance in other areas. As a result, the machining quality of pipe fittings in areas with localized anomalies is significantly improved.

[0086] An embodiment of the present application provides the steps of obtaining the spindle influence index according to the influence of the spindle operation status index in the machine tool status index on the surface quality of the pipe joint in the above-mentioned step S720, including but not limited to steps S910 to S920. Each step is introduced in turn below.

[0087] Step S910: collecting wear state data of the cutting tool, physical property data of the workpiece material, and fluid state data of the coolant; Step S920: When the wear state of the cutting tool, the physical properties of the workpiece material, and the fluid state of the coolant are all within a preset normal range, a spindle influence index is obtained according to the influence of the change of the spindle operation condition index on the surface quality of the pipe joint.

[0088] It should be noted that collecting cutting tool wear data can be understood as obtaining information about the degree of tool wear during use through various sensors or detection methods. For example, visual inspection systems can be used to analyze tool edge images, or force sensors, acoustic emission sensors, and other devices can be used to monitor changes in cutting forces or acoustic signals in real time, thereby indirectly or directly assessing tool wear. The purpose of this data is to identify whether the tool has reached the point where it needs to be replaced or resharpened, thereby preventing degradation in machining quality due to tool wear. Workpiece material physical property data refers to the various physical parameters of the materials used in pipe fittings and joints, such as hardness, toughness, and thermal conductivity. This data can be obtained through pre-processing material testing, supplier-provided data sheets, or pre-processing sampling. The purpose is to ensure that the workpiece material being processed meets design requirements and that its properties do not adversely affect the machining process. Coolant fluid state data refers to parameters such as coolant flow rate, temperature, concentration, and cleanliness. This data can be monitored in real time using devices such as flow meters, temperature sensors, concentration meters, and turbidity sensors. The purpose of this data is to ensure that the coolant effectively cools, lubricates, and removes chips, maintaining a stable machining environment.

[0089] Among them, when the wear state of the cutting tool, the physical properties of the workpiece material and the fluid state of the coolant are all within the preset normal range, it means that before obtaining the spindle influence index, the system will judge the above-mentioned collected data to ensure that they are all within the preset acceptable threshold or range.

[0090] In some preferred embodiments, a specific example is provided below. Suppose, during the turning process of a batch of pipe fittings of a specific model, to accurately assess the spindle's impact on surface quality, the system first collects real-time cutting tool wear data using sensors and data interfaces integrated into the machine tool. For example, tool wear is monitored using a visual recognition system or force sensor. Simultaneously, material batch information for the current batch of workpieces is obtained from the production management system and compared with a pre-set database of material physical properties to confirm that the workpiece material's physical properties are within normal ranges. Furthermore, the coolant's flow rate, temperature, and concentration are monitored using a flow meter and temperature sensor to ensure that its fluid state meets process requirements. Only when these external factors (tool wear, workpiece material, and coolant) are confirmed to be within pre-set normal ranges does the system further calculate and determine the spindle impact index (SHI) based on the spindle's coasting data, reflecting its impact on the pipe fitting's surface quality. For example, if tool wear is detected to have exceeded a normal threshold, the system prompts a tool replacement or adjusts the assessment strategy, rather than directly correlating the SHI with surface quality. This avoids spindle impact assessment bias caused by tool issues. In this way, the purity and accuracy of the spindle influence index are ensured, providing a reliable basis for subsequent adjustment of processing parameters.

[0091] Through the above technical solution, the present application can significantly improve the calculation accuracy of the spindle influence index. By eliminating interference from external factors such as cutting tool wear, workpiece material properties, and coolant status, this makes subsequent machining parameter adjustments based on the spindle influence index more accurate and effective, thereby helping to more stably control the surface quality of pipe fittings, reduce scrap rates, and improve the overall machining pass rate.

[0092] See also Figure 2 , Figure 2 This is a schematic diagram of a pipe fitting turning precision control system according to one embodiment of the present application. The pipe fitting turning precision control system 1000 is used to improve the pipe fitting turning precision rate by analyzing historical processing data using a machine learning model, including: The non-cutting test data acquisition module 1010 is used to acquire the freewheeling data of the spindle and the micro-motion response data of the feed axis before the turning process of the pipe joint; The machine tool status index generating module 1020 is configured to obtain a spindle operation status index based on the spindle's coasting data; obtain a feed axis clearance status index based on the feed axis's micro-motion response data; and combine the spindle operation status index and the feed axis clearance status index to obtain a machine tool status index. A processing parameter adjustment module 1030 is used to adjust the pipe joint turning processing parameters according to the machine tool status index; The adjustment strategy optimization module 1040 is used to obtain the quality inspection results of the pipe joint after turning processing, and optimize the adjustment strategy of the processing parameters based on the quality inspection results.

[0093] This application proposes a precision control system for turning pipe joints. This system aims to improve the pass rate of pipe joint turning by applying machine learning models to analyze historical processing data. This system uses a modular approach to continuously evaluate the operating status of key machine tool components (such as the spindle and feed axis). Combined with post-processing quality inspection results, it dynamically adjusts processing parameters to adapt to the machine's actual operating conditions, thereby improving the precision and pass rate of pipe joint turning. By integrating functional modules such as data acquisition, status assessment, parameter adjustment, and strategy optimization, this system forms a closed-loop intelligent control architecture, effectively addressing the problem of reduced precision in traditional systems caused by mechanical performance drift during long-term machine operation.

[0094] Specifically, the core of the pipe joint turning precision control system of the present application lies in achieving in-depth perception of the machine tool status and adaptive adjustment of processing parameters through the coordinated work of various functional modules.

[0095] Among them, the non-cutting test data acquisition module is used to obtain the inertial sliding data of the main spindle and the micro-motion response data of the feed axis before turning the pipe joint. It should be emphasized that this module can be implemented as a data acquisition unit integrated into the CNC system, or as a combination of an independent external sensor network and a data acquisition card. For example, the module can include a series of high-precision sensors, such as encoders, accelerometers, current sensors, etc., and be connected to the main control unit via a data bus. In one implementation, the module can be configured to exchange data with the machine tool controller via a wired connection; in another implementation, the module can be configured to transmit the collected data to the central processing unit via wireless communication (such as Wi-Fi or Bluetooth).

[0096] The machine tool status index generation module is used to obtain the spindle's operating condition index based on the spindle's coasting data; obtain the feed axis's clearance condition index based on the feed axis's micro-response data; and combine the spindle's operating condition index and the feed axis's clearance condition index to obtain the machine tool status index. It should be emphasized that this module can be implemented as a software program running on an industrial computer or as a dedicated processing chip embedded in a CNC system.

[0097] The machining parameter adjustment module is used to adjust the machining parameters for pipe joint turning based on the machine tool status index. It is important to note that this module can be implemented as a parameter management interface within a CNC system or as a standalone parameter optimization engine. In one implementation, the module can be configured to directly send parameter modification instructions to the CNC system; in another implementation, the module can be configured to generate recommended machining parameters for manual operator confirmation and application.

[0098] The adjustment strategy optimization module is used to obtain the quality inspection results after the turning process of the pipe fittings, and optimize the adjustment strategy of the processing parameters based on the quality inspection results. It should be emphasized that this 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 adjustments. In one implementation, the module can be configured to regularly perform batch learning and strategy updates on historical data; in another embodiment, the module can be configured to immediately fine-tune and optimize the strategy after each processing task is completed.

[0099] Compared to existing systems that rely primarily on macroscopic sensor data and historical experience for parameter optimization, the system in this application proactively acquires spindle coasting data and feed axis micro-response data through a non-cutting test data acquisition module. This data accurately reflects the microscopic wear and performance drift of key machine tool components. The machine tool status index generation module quantifies these difficult-to-perceive microscopic changes into actionable machine tool status indices, thus overcoming the limitations of traditional systems that cannot detect gradual and hidden quality issues.

[0100] Furthermore, the machining parameter adjustment module proactively adjusts machining parameters based on a quantified machine tool status index, rather than passively compensating for quality issues after they arise. This proactive adjustment mechanism significantly improves the first-time machining pass rate. Furthermore, the adjustment strategy optimization module incorporates a feedback mechanism based on quality inspection results, enabling the system to continuously learn and improve its parameter adjustment strategy from actual machining results. This closed-loop adaptive capability enables the system to maintain high levels of machining accuracy and pass rates over the long term, effectively addressing the challenges posed by machine tool aging and changing operating conditions.

[0101] To sum up, the system of the present application can not only perceive and quantify the internal state drift of the machine tool and realize forward-looking adjustment of the processing parameters, but also ensure the continuous optimization and stability of the processing accuracy during the long-term operation of the machine tool through an adaptive learning mechanism, thereby providing a more intelligent, efficient and robust solution for the manufacturing of precision pipe fittings.

Claims

1. A method for controlling the turning accuracy of a pipe joint, characterized in that: include: Before turning the pipe joint, obtain the spindle's coasting data and the feed axis's micro-motion response data; Obtaining an operating condition index of the main shaft according to the freewheeling data of the main shaft; Obtaining a clearance condition index of the feed shaft according to the micro-motion response data of the feed shaft; Combining the operating condition index of the spindle and the clearance condition index of the feed axis to obtain a machine tool status index; adjusting the processing parameters of the pipe joint turning according to the machine tool status index; Obtaining a quality inspection result of the pipe joint after turning; According to the quality inspection results, the adjustment strategy of the processing parameters is optimized.

2. A method for controlling the turning accuracy of a pipe joint according to claim 1, characterized in that: The step of obtaining the micro-motion response data of the feed axis includes: When the machining program is first executed, baseline motion data of the feed axis in the non-cutting movement stroke is collected; When the machining program is subsequently executed, current motion data of the feed axis in the non-cutting movement stroke is collected; Obtaining a position-related motion deviation based on the current motion data and the baseline motion data; According to the motion deviation, the micro-motion response data of the feed axis is obtained.

3. The method for controlling the turning accuracy of a pipe joint according to claim 1, characterized in that: The step of obtaining the operating status index of the main shaft according to the freewheeling data of the main shaft comprises: Collecting a sequence of instantaneous speed data of the spindle during the freewheeling process; Establishing a reference curve describing the spindle attenuation trend based on the instantaneous speed data sequence; Calculating a residual signal sequence between the instantaneous rotational speed data sequence and the reference curve; obtaining a local damage index of the spindle according to the residual signal sequence; An operating condition index of the main shaft is obtained according to the local damage index and the instantaneous rotational speed data sequence.

4. A method for controlling the turning accuracy of a pipe joint according to claim 1, characterized in that: The step of obtaining the clearance condition index of the feed shaft according to the micro-motion response data of the feed shaft comprises: 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; Obtaining drift information of the current sensor according to the instantaneous current data; Obtaining degradation information of the motor encoder according to the instantaneous position data; Obtaining corrected micro-motion response data according to the drift information of the current sensor and the degradation information of the motor encoder; A clearance condition index of the feed shaft is obtained according to the corrected micro-motion response data.

5. The method for controlling the turning accuracy of a pipe joint according to claim 1, wherein: The step of optimizing the adjustment strategy of the processing parameters according to the quality inspection results includes: Establishing a mapping relationship between the quality inspection results and the adjustment strategy of the processing parameters; Iterating the mapping relationship to obtain an updated mapping relationship based on the quality inspection result; The adjustment strategy of the processing parameters is optimized according to the updated mapping relationship.

6. A method for controlling the turning accuracy of a pipe joint according to claim 5, characterized in that: The step of iterating the mapping relationship to obtain an updated mapping relationship based on the quality inspection result includes: Calculating a performance error of the mapping relationship based on the quality inspection result; According to the performance error, the parameters in the mapping relationship are iteratively adjusted until the performance error reaches a preset minimization condition, thereby obtaining the mapping relationship.

7. The method for controlling the turning accuracy of a pipe joint according to claim 1, characterized in that: When the components of the machine tool status index indicate conflicting parameter adjustment directions, the step of adjusting the processing parameters for turning the pipe joint according to the machine tool status index includes: Obtaining the machine tool status index; Obtaining a spindle influence index according to the influence of the spindle operation status index in the machine tool status index on the surface quality of the pipe joint; Obtaining a feed axis influence index according to the influence of the feed axis clearance condition index in the machine tool condition index on the pipe joint dimensional accuracy and thread profile integrity; Determining the priorities of the surface quality, the dimensional accuracy, the thread profile integrity, and the tool life according to the preset quality requirements of the pipe fitting turning task; According to the spindle influence index, the feed axis influence index and the priority, the pipe joint turning processing parameters are adjusted, and the processing parameters include spindle speed, feed speed and cutting depth.

8. A method for controlling turning accuracy of a pipe joint according to claim 7, characterized in that: The step of adjusting the pipe joint turning parameters according to the spindle influence index, the feed axis influence index and the priority includes: When the machine tool status index indicates a local mechanical abnormality, Dividing the pipe joint turning process into a plurality of processing stroke segments; For each of the machining stroke segments, the pipe joint turning machining parameters are adjusted according to the spindle influence index, the feed axis influence index and the priority.

9. The method for controlling the turning accuracy of a pipe joint according to claim 7, characterized in that: The step of obtaining the spindle influence index according to the influence of the spindle operation status index in the machine tool status index on the surface quality of the pipe joint comprises: Collecting cutting tool wear data, workpiece material physical property data, and coolant fluid state data; When the wear state of the cutting tool, the physical properties of the workpiece material, and the fluid state of the coolant are all within a preset normal range, the spindle influence index is obtained according to the influence of the change of the spindle operation condition index on the surface quality of the pipe joint.

10. A pipe fitting turning precision control system for applying a machine learning model to analyze historical processing data to improve the pipe fitting turning precision rate, characterized in that: The system includes: The non-cutting test data acquisition module is used to obtain the spindle's coasting data and the feed axis's micro-motion response data before turning the pipe joint; a machine tool status index generating module, configured to obtain an operating status index of the spindle based on the freewheeling data of the spindle; obtain a clearance status index of the feed axis based on the micro-motion response data of the feed axis; and combine the operating status index of the spindle and the clearance status index of the feed axis to obtain a machine tool status index; a processing parameter adjustment module, configured to adjust the pipe joint turning processing parameters according to the machine tool status index; The adjustment strategy optimization module is used to obtain the quality inspection results of the pipe joint after turning, and optimize the adjustment strategy of the processing parameters according to the quality inspection results.

Images