Chuck run-out compensation method and device for pipe cutting

Abstract

The embodiment of the invention provides a chuck bounce compensation method and device for pipe cutting. The method comprises the following steps: acquiring first sensing data of a target chuck in a gap period of cutting a to-be-processed pipe, preprocessing the first sensing data to obtain second sensing data, determining dynamic run-out data, static coaxiality data and temperature correction of the target chuck according to the second sensing data, and cutting the to-be-processed pipe according to the dynamic run-out data, the static coaxiality data and the temperature correction. Performing fusion processing on the dynamic bounce data, the static coaxiality data and the temperature correction to obtain a bounce deviation value, determining a chuck adhesion risk level of the target chuck, determining a compensation trigger threshold according to the chuck adhesion risk level, determining a first compensation value according to the bounce deviation value and the compensation trigger threshold, and determining a second compensation value according to the first compensation value; and compensating the target chuck according to the first compensation value. According to the method provided by the embodiment of the invention, the intelligent level of chuck bounce compensation is improved, accurate compensation of chuck bounce is realized, and the precision and stability of pipe cutting are improved.

Description

Technical Field

[0001] This application relates to the field of pipe cutting technology, and in particular to a chuck runout compensation method and device for pipe cutting. Background Technology

[0002] Chuck runout calibration is a crucial step in ensuring the processing accuracy, product qualification rate, and equipment stability of laser tube cutting machines. It directly determines the precision of cutting dimensions and the quality of the cross-section, and is a core prerequisite for avoiding batch scrap, reducing unplanned downtime, and achieving intelligent production.

[0003] In related technologies, chuck runout is usually compensated based on the operator's experience.

[0004] However, in the process of realizing this application, the inventors discovered at least the following problems in the related technology: the above-mentioned chuck compensation calibration method has a low level of intelligence, which affects production efficiency and accuracy. Summary of the Invention

[0005] This application provides a chuck runout compensation method and device for pipe cutting, so as to improve the intelligence level of chuck runout compensation calibration.

[0006] In a first aspect, embodiments of this application provide a chuck runout compensation method for pipe cutting, comprising:

[0007] During the interval between cutting the pipe to be processed, the first sensor data of the target chuck is collected, and the first sensor data is preprocessed to obtain the second sensor data.

[0008] Based on the second sensing data, the dynamic runout data, static coaxiality data, and temperature correction amount of the target chuck are determined. The dynamic runout data, the static coaxiality data, and the temperature correction amount are then fused to obtain the runout deviation value.

[0009] Determine the chuck adhesion risk level of the target chuck, and determine the compensation trigger threshold based on the chuck adhesion risk level;

[0010] Based on the fluctuation deviation value and the compensation trigger threshold, a first compensation value is determined, and the target chuck is compensated according to the first compensation value.

[0011] In one possible design, applied to a laser tube cutting machine, the laser tube cutting machine is equipped with a spindle encoder, a laser alignment instrument, a temperature sensor, and a vibration sensor; the first sensing data includes: radial displacement data acquired by the spindle encoder, chuck center distance data acquired by the laser alignment instrument, chuck temperature data acquired by the temperature sensor, and chuck vibration data acquired by the vibration sensor.

[0012] The step of preprocessing the first sensing data to obtain the second sensing data includes:

[0013] The screening threshold is determined based on the vibration data;

[0014] The time period of vibration exceeding the standard is determined based on the aforementioned screening threshold;

[0015] The data in the radial displacement data, the chuck center distance data, and the temperature data that occurred during the period when the vibration exceeded the standard were deleted to obtain the second sensing data.

[0016] In one possible design, determining the dynamic runout data, static coaxiality data, and temperature correction amount of the target chuck based on the second sensing data includes:

[0017] Based on the maximum radial displacement value within a preset number of revolutions in the radial displacement data, the dynamic runout data of the target chuck is determined;

[0018] Based on the chuck center distance data, determine the average value of the front and rear center distance deviations, and determine the static coaxiality data of the target chuck based on the average value;

[0019] Based on the temperature data and the first correspondence, the temperature correction amount corresponding to the temperature data is determined; the first correspondence includes the temperature correction amounts corresponding to different temperature data respectively.

[0020] In one possible design, the process of fusing the dynamic runout data, the static coaxiality data, and the temperature correction to obtain the runout deviation value includes:

[0021] The runout deviation value of the target chuck is determined by weighting the dynamic runout data, static coaxiality data, and temperature correction amount; the first weight corresponding to the dynamic runout data is greater than the second weight corresponding to the static coaxiality data.

[0022] In one possible design, the compensation trigger threshold includes a first threshold and a second threshold; determining the first compensation value based on the fluctuation deviation value and the compensation trigger threshold includes:

[0023] If the fluctuation deviation value is greater than the first threshold, then the fluctuation deviation value is recorded;

[0024] If the runout deviation value is greater than the first threshold and less than the second threshold, then an initial compensation amount is determined based on the pipe parameters of the pipe to be processed and the runout deviation value; the initial compensation amount is adjusted based on the temperature correction amount to obtain a first compensation amount; the first threshold is less than the second threshold;

[0025] If the fluctuation deviation value is greater than the second threshold, an alarm message is sent.

[0026] In one possible design, the compensation trigger threshold includes a third threshold; the compensation processing of the target chuck based on the first compensation value includes:

[0027] A drive command is generated based on the first compensation amount; the drive command is used to instruct the shim push rod to drive the shim of the target chuck to move to the target position corresponding to the first compensation amount;

[0028] After compensation is completed, determine the new runout deviation value;

[0029] If the new fluctuation deviation value is less than the third threshold, the compensation is determined to be successful, and the new fluctuation deviation value is recorded; the third threshold is less than the first threshold.

[0030] If the new runout deviation value is greater than the third threshold and less than the first threshold, then the target chuck is compensated based on a preset compensation amount; the preset compensation amount is less than the third threshold.

[0031] If the new fluctuation deviation value is greater than the first threshold, an alarm message is sent.

[0032] In one possible design, determining the chuck adhesion risk level of the target chuck includes:

[0033] Collect the third sensor data of the target chuck in the current opening and closing cycle;

[0034] Obtain the historical runout deviation value of the target chuck;

[0035] The corresponding feature data is determined based on the third sensor data and the historical fluctuation deviation value;

[0036] The feature data is input into a neural network model to obtain the chuck adhesion risk level of the target chuck.

[0037] In one possible design, the third sensing data includes: current data, air pressure data, vibration data, and coolant concentration; the feature data includes: a current anomaly coefficient determined based on the current data, an air pressure anomaly coefficient determined based on the air pressure data, a vibration change rate determined based on the vibration data, and a coolant deviation rate determined based on the coolant concentration.

[0038] In one possible design, the method further includes:

[0039] If the risk level of chuck adhesion is less than or equal to the first preset level, and the runout deviation value is less than the first threshold, then the working state is determined to be normal.

[0040] If the chuck adhesion risk level is greater than the first preset level and less than the second preset level, and the fluctuation deviation value is greater than the first threshold, then a cleaning instruction is generated; the second preset level is greater than the first preset level.

[0041] If the risk level of chuck adhesion is greater than the third preset level, a stop command is generated; the third preset level is greater than the second preset level.

[0042] Secondly, embodiments of this application provide a chuck runout compensation device for pipe cutting, comprising:

[0043] During the interval between cutting the pipe to be processed, the first sensor data of the target chuck is collected, and the first sensor data is preprocessed to obtain the second sensor data.

[0044] Based on the second sensing data, the dynamic runout data, static coaxiality data, and temperature correction amount of the target chuck are determined. The dynamic runout data, the static coaxiality data, and the temperature correction amount are then fused to obtain the runout deviation value.

[0045] Determine the chuck adhesion risk level of the target chuck, and determine the compensation trigger threshold based on the chuck adhesion risk level;

[0046] Based on the fluctuation deviation value and the compensation trigger threshold, a first compensation value is determined, and the target chuck is compensated according to the first compensation value.

[0047] Thirdly, embodiments of this application provide a chuck runout compensation device for pipe cutting, comprising: at least one processor and a memory;

[0048] The memory stores computer-executed instructions;

[0049] The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the method described in the first aspect above and various possible designs of the first aspect.

[0050] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the method described in the first aspect and various possible designs of the first aspect.

[0051] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect and various possible designs of the first aspect.

[0052] This embodiment provides a chuck runout compensation method and device for pipe cutting. The method involves acquiring first sensor data from the target chuck during the interval between pipe cutting operations, preprocessing the first sensor data to obtain second sensor data, determining the dynamic runout data, static coaxiality data, and temperature correction amount of the target chuck based on the second sensor data, fusing the dynamic runout data, static coaxiality data, and temperature correction amount to obtain a runout deviation value, determining the chuck adhesion risk level of the target chuck, determining a compensation trigger threshold based on the chuck adhesion risk level, determining a first compensation value based on the runout deviation value and the compensation trigger threshold, and then compensating the target chuck based on the first compensation value. The method provided in this embodiment, by acquiring multi-dimensional sensor data of the chuck during the cutting interval, performing preprocessing, feature extraction, and fusion analysis, and finally adaptively determining a compensation strategy based on the runout deviation value and the chuck adhesion risk level, improves the intelligence level of runout compensation, achieves accurate compensation for chuck runout, and improves the accuracy and stability of pipe cutting. Attached Figure Description

[0053] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0054] Figure 1 A schematic diagram illustrating an application scenario of the chuck runout compensation method for pipe cutting provided in this application embodiment;

[0055] Figure 2 A flowchart illustrating the chuck runout compensation method for pipe cutting provided in this application embodiment. Figure 1 ;

[0056] Figure 3 A flowchart illustrating the chuck runout compensation method for pipe cutting provided in this application embodiment. Figure 2 ;

[0057] Figure 4 A schematic diagram of a chuck runout compensation device for pipe cutting provided in an embodiment of this application;

[0058] Figure 5 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application.

[0059] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0061] It should be noted that the chuck runout compensation method and equipment for pipe cutting provided in this application can be used in the field of pipe cutting technology, or in any field other than the field of pipe cutting technology. The application field of the chuck runout compensation method and equipment for pipe cutting provided in this application is not limited.

[0062] The chuck runout compensation method for pipe cutting involved in this application can be applied to the intelligent operation and maintenance system of a three-chuck laser pipe cutting machine. This intelligent operation and maintenance system is mainly used in the field of high-precision industrial manufacturing, especially in scenarios where the pipe cutting accuracy and the continuous operation stability of the equipment are extremely important.

[0063] For example, in the automotive manufacturing industry, it can be used to cut precision pipes such as exhaust pipes and fuel pipes. The surface roughness of the cut section is required to be ≤12.5μm, and the pipes must maintain high coaxiality (±0.03mm) during the cutting process to avoid assembly errors.

[0064] In the aerospace field, it can process key components such as fuel pipes and hydraulic lines for aircraft engines. It needs to meet the high-precision cutting requirements of complex pipes (such as aluminum alloys and titanium alloys) while ensuring that the equipment can operate continuously for a long time without failure.

[0065] In the construction and energy sectors, stainless steel pipes, carbon steel pipes, and other pipes used in building structures and piping systems can be cut. It is necessary to balance cutting efficiency and cross-sectional quality while minimizing production interruptions caused by equipment failure.

[0066] In these scenarios, the equipment needs to use a "three-chuck structure" to clamp and correct the pipe at three points. However, the chuck runout problem during long-term operation will significantly affect the cutting accuracy and equipment availability, and an intelligent operation and maintenance solution is urgently needed.

[0067] In related technologies, chuck runout compensation is usually based on the operator's experience, which has a low level of intelligence and affects production efficiency and accuracy.

[0068] To address the aforementioned technical problems, the inventors of this application have discovered that multi-source data from the chuck can be collected and fused, and then automatic compensation can be performed based on the fusion result. Furthermore, the inventors have found that chuck adhesion has a certain impact on chuck runout; for example, chuck adhesion may lead to uneven chuck clamping force, exacerbating runout deviation. Therefore, chuck adhesion can be taken into account to further improve the accuracy and effectiveness of chuck runout compensation. Based on this, embodiments of this application provide a chuck runout compensation method for pipe cutting.

[0069] Figure 1 This is a schematic diagram illustrating an application scenario of the chuck runout compensation method for pipe cutting provided in this application embodiment. For example... Figure 1 As shown, the laser tube cutting machine includes a main structure (not shown, such as a spindle system, a three-chuck structure, and a laser cutting head), a spindle encoder, a laser alignment instrument, a temperature sensor, a vibration sensor, and a controller.

[0070] In the actual implementation process, the pipe to be processed is clamped and fixed by a three-chuck structure, and the laser cutting head cuts the pipe along a preset trajectory. During the intervals between cutting operations, the spindle encoder, laser alignment instrument, temperature sensor, and vibration sensor collect the operating data of each chuck in real time. The controller performs data fusion analysis and risk level assessment, and dynamically adjusts the chuck position compensation amount to ensure that the pipe maintains high-precision coaxiality and positional stability during the cutting process.

[0071] It should be noted that, Figure 1 The schematic diagram shown is merely an example. The chuck runout compensation method and scenario for pipe cutting described in this application are intended to more clearly illustrate the technical solutions of this application and do not constitute a limitation on the technical solutions provided in this application. As those skilled in the art will know, with the evolution of the system and the emergence of new business scenarios, the technical solutions provided in this application are also applicable to similar technical problems.

[0072] The technical solutions of this application will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0073] Figure 2 A flowchart illustrating the chuck runout compensation method for pipe cutting provided in this application embodiment. Figure 1 .like Figure 2 As shown, the method includes:

[0074] 201. During the interval between cutting the pipe to be processed, the first sensor data of the target chuck is collected. The first sensor data is preprocessed to obtain the second sensor data.

[0075] The execution subject in this embodiment can be a laser tube cutting machine or a three-card intelligent operation and maintenance system in a laser switching machine.

[0076] Specifically, by collecting the first sensor data during the intermittent period, highly reliable chuck status data can be obtained under non-interference conditions, providing an accurate data foundation for subsequent precise calculation of runout deviation.

[0077] In this embodiment, the gap period refers to the idle time window after the laser tube cutting machine has completed the cutting of the previous section of tube but has not yet started cutting the next section. During this time, the equipment is in a non-processing state, which avoids interference from cutting vibration and thermal deformation on data acquisition.

[0078] The target chuck can be any one or more of the front, middle, and rear chucks, depending on the actual runout monitoring requirements.

[0079] The first sensing data is raw, multi-source data obtained from the device's sensor network, including but not limited to physical quantities such as displacement, temperature, and vibration.

[0080] Preprocessing refers to cleaning, filtering, and format standardization of the raw first-sensor data to eliminate outliers and environmental noise, thereby improving data quality.

[0081] In some embodiments, the laser tube cutting machine is equipped with a spindle encoder, a laser alignment instrument, a temperature sensor, and a vibration sensor; the first sensing data includes: radial displacement data acquired by the spindle encoder, chuck center distance data acquired by the laser alignment instrument, chuck temperature data acquired by the temperature sensor, and chuck vibration data acquired by the vibration sensor.

[0082] The chuck temperature data can include both the chuck's operating temperature and the ambient temperature. In addition to collecting chuck vibration data, vibration data of the cutting head can also be collected.

[0083] Preprocessing the first sensing data to obtain the second sensing data may include: determining a screening threshold based on the vibration data; determining the time period of vibration exceeding the standard based on the screening threshold; deleting data from the radial displacement data, chuck center distance data, and temperature data that falls within the time period of vibration exceeding the standard to obtain the second sensing data.

[0084] Specifically, the spindle encoder is used to acquire the radial displacement sequence during chuck rotation in real time, reflecting dynamic runout. The laser alignment instrument obtains the center distance deviation between the front and rear chucks through non-contact optical measurement, assessing static coaxiality. Temperature sensors are used to detect the operating temperature of the chuck jaw area and the ambient temperature for thermal deformation compensation. Vibration sensors can be placed near the chuck support structure and the cutting head to identify external vibration interference.

[0085] During the preprocessing process, a screening threshold can be set first based on the statistical characteristics of vibration data (such as the 3σ criterion). Based on this screening threshold, the time period of vibration exceeding the standard (such as the time period when the amplitude continuously exceeds the normal operating range of the equipment) can be marked. Then, the associated data of other sensors within this time period can be removed to ensure that subsequent calculations are based only on stable operating condition data.

[0086] In this embodiment, by collecting sensor data during the interval period, external vibration interference can be effectively isolated, the signal-to-noise ratio of the vibration data can be improved, and false compensation caused by abnormal vibration can be avoided. At the same time, the system's anti-interference capability and robustness can be enhanced through multi-sensor collaborative verification.

[0087] 202. Based on the second sensor data, determine the dynamic runout data, static coaxiality data, and temperature correction amount of the target chuck. Then, fuse the dynamic runout data, static coaxiality data, and temperature correction amount to obtain the runout deviation value.

[0088] Specifically, after preprocessing, three influencing factors of the runout deviation value can be determined based on the second sensing data obtained from the preprocessing: dynamic runout data, static coaxiality data, and temperature correction amount, so as to determine the final runout deviation value according to these three influencing factors.

[0089] In this embodiment, the fusion processing of the three influencing factors can be achieved through a deep model or based on an algorithmic formula. This embodiment does not limit the specific implementation.

[0090] In some embodiments, determining the dynamic runout data, static coaxiality data, and temperature correction amount of the target chuck based on the second sensing data may include: determining the dynamic runout data of the target chuck based on the maximum radial displacement value within a preset number of revolutions in the radial displacement data.

[0091] Based on the chuck center distance data, the average value of the front and rear center distance deviations is determined, and the static coaxiality data of the target chuck is determined based on the average value. The laser alignment instrument can calculate the difference between the actual and theoretical center distances. Center distance refers to the distance between the centerlines of the two measured axes at corresponding cross-sections. The deviation value reflects the degree of asymmetry between the two axes at that cross-section (the larger the deviation, the worse the coaxiality). In other words, the front and rear center distance deviations can be a collective term for the center distance deviation values ​​of the front and rear measuring points.

[0092] Based on the temperature data and the first correspondence, determine the temperature correction amount corresponding to the temperature data; the first correspondence includes the temperature correction amount corresponding to different temperature data respectively.

[0093] Specifically, the method for determining the dynamic runout data, static coaxiality data, and temperature correction amount of the target chuck based on the second sensor data can be as follows: First, based on the radial displacement data, the maximum value of the radial displacement within a preset number of revolutions (e.g., 10 revolutions) can be extracted as the dynamic runout data, which reflects the instantaneous runout amplitude of the chuck during rotation. Then, using the chuck center distance data, the average value of the center distance deviation between the front, middle, and rear chucks can be calculated, which serves as the static coaxiality data, characterizing the static alignment accuracy of the chuck when clamping the pipe. Finally, based on the chuck temperature and ambient temperature data collected by the temperature sensor, combined with a preset first correspondence (e.g., through an experimentally calibrated temperature-correction table), the corresponding temperature correction amount can be queried. This correction amount is used to compensate for the runout deviation caused by thermal deformation.

[0094] In some embodiments, fusing dynamic runout data, static coaxiality data, and temperature correction to obtain a runout deviation value may include: performing a weighted average of dynamic runout data, static coaxiality data, and temperature correction to determine the runout deviation value of the target chuck; wherein the first weight corresponding to the dynamic runout data is greater than the second weight corresponding to the static coaxiality data.

[0095] Specifically, a weighted average algorithm can be used to fuse dynamic fluctuation data, static coaxiality data, and temperature correction. Dynamic fluctuation data is assigned a first weight (e.g., 0.6), and static coaxiality data is assigned a second weight (e.g., 0.4), with the first weight being greater than the second weight to highlight the dominant role of dynamic fluctuation in the overall deviation. Temperature correction can be treated as an independent item and directly added together.

[0096] The weighted average formula can be expressed as: runout deviation value = first weight × dynamic runout data + second weight × static coaxiality data + temperature correction amount.

[0097] In this embodiment, the hierarchical fusion method enables the fluctuation deviation value to comprehensively cover dynamic, static and environmental factors, thereby improving the accuracy of compensation decisions.

[0098] In some embodiments, an adaptive weight adjustment mechanism based on the risk level of chuck adhesion can be introduced on the basis of weighted average fusion processing.

[0099] For example, if the chuck adhesion risk level is high (e.g., level 2 or above), the weight of dynamic runout data is further increased (e.g., increased to 0.7), while the weight of static coaxiality data is reduced accordingly (e.g., reduced to 0.3) to more sensitively respond to dynamic runout changes caused by increased adhesion. At the same time, the adhesion risk coefficient (e.g., risk level coefficient multiplied by the base temperature correction) is added to the calculation of the temperature correction amount to make the fusion result more consistent with the actual working conditions.

[0100] In this embodiment, a higher level of accuracy optimization is achieved through dynamic weight adjustment.

[0101] 203. Determine the chuck adhesion risk level of the target chuck, and determine the compensation trigger threshold based on the chuck adhesion risk level.

[0102] Specifically, chuck sticking is a key issue affecting normal production. Therefore, the risk level of chuck sticking can be determined to provide early warning. Considering that chuck sticking has a certain impact on runout compensation, the compensation trigger threshold can be determined based on the degree of chuck sticking to correct runout compensation.

[0103] In some embodiments, determining the chuck adhesion risk level of the target chuck may include: acquiring third sensor data of the target chuck in the current opening and closing cycle; obtaining historical runout deviation values ​​of the target chuck; determining corresponding feature data based on the third sensor data and historical runout deviation values; and inputting the feature data into a neural network model to obtain the chuck adhesion risk level of the target chuck.

[0104] Specifically, during the chuck's opening and closing action, third-sensor data from the current opening and closing cycle can be collected simultaneously; at the same time, historical runout deviation values ​​of the target chuck can be retrieved from the system database. Based on the third-sensor data and historical runout deviation values, corresponding multi-dimensional feature data is calculated using a feature extraction algorithm. The extracted feature data is then input into a pre-trained neural network model for real-time inference, and the neural network model outputs the chuck adhesion risk level of the target chuck.

[0105] For example, the risk level can be divided into 0-3 levels, where level 0 represents the normal state and level 3 represents a severe adhesion risk.

[0106] It should be noted that the synchronization of the acquisition of third-sensor data with each opening and closing action of the chuck is not a simple simultaneous start, but a precise, event-triggered data acquisition strategy that is event-driven rather than time-driven. Specifically, the start and end of data acquisition, as well as the definition of the acquired data segments, are all bound to a specific physical event: a complete opening and closing action of the chuck (i.e., one work cycle).

[0107] For example, the initial trigger signal for data acquisition is the instruction signal issued by the CNC system to clamp or release the chuck.

[0108] The end point is defined as the completion of the opening and closing action (such as the signal feedback that the clamp is in place or the release is in place).

[0109] A data segment refers to all the data collected within this specific time period that is marked as the same opening and closing action.

[0110] Based on this, the collected third-sensor data is not a data fragment at random time points, but a complete capture of the dynamic response of the chuck during the execution of a single specific task, which facilitates data comparison and helps improve data processing efficiency.

[0111] In practical implementation, the chuck opening and closing control signal can be output from the programmable logic controller (PLC) or input / output (I / O) module of the CNC system of the laser tube cutting machine. This signal is connected to the external trigger port of the data acquisition card. The data acquisition card is set to hardware trigger mode. Once the trigger signal is received, all sensors (current, air pressure, vibration, etc.) are immediately activated to synchronously acquire data at a preset frequency of 100Hz until the action completion signal is received and then stops.

[0112] In some embodiments, the third sensing data includes: current data, air pressure data, vibration data, and coolant concentration; the feature data includes: a current anomaly coefficient determined based on the current data, an air pressure anomaly coefficient determined based on the air pressure data, a vibration change rate determined based on the vibration data, and a coolant deviation rate determined based on the coolant concentration.

[0113] Specifically, the third sensing data may include: current data of the chuck opening and closing servo motor collected by a current transformer, air pressure data of the chuck pneumatic control circuit collected by an air pressure sensor, vibration data of the chuck support structure collected by a vibration sensor, and coolant concentration data collected by a coolant concentration sensor.

[0114] The corresponding characteristic data may include: a current anomaly coefficient calculated based on current data, which reflects the degree of deviation of the current peak value from the initial calibration value; a pressure anomaly coefficient calculated based on pressure data, which characterizes the attenuation of pressure control performance; a vibration change rate calculated based on vibration data, which reflects the stability of the chuck's operating state; and a coolant deviation rate calculated based on coolant concentration, which reflects the maintenance status of the cooling medium's performance.

[0115] In some more specific embodiments, the process for determining the risk level of chuck adhesion can be further optimized as follows: First, a deep learning-based neural network model architecture is established, which includes an input layer, at least one hidden layer, and an output layer. The input layer receives five core feature parameters, including current anomaly coefficient, air pressure anomaly coefficient, vibration change rate, coolant deviation rate, and historical fluctuation trend coefficient. The hidden layer adopts a 32-node fully connected structure, and nonlinear mapping is achieved through an activation function. The output layer outputs the probability distribution of four risk levels through a softmax function.

[0116] During model training, three types of sample data—normal, mildly adhered, and severely adhered—collected during device operation can be used. Parameter optimization is performed using the cross-entropy loss function and the Adaptive Moment Estimation (Adam) optimizer. In practical applications, the model inference time is controlled within 0.1 seconds to ensure real-time requirements.

[0117] 204. Determine the first compensation value based on the runout deviation value and the compensation trigger threshold, and perform compensation processing on the target chuck based on the first compensation value.

[0118] In some embodiments, the compensation trigger threshold includes a first threshold and a second threshold; determining the compensation value based on the fluctuation deviation value and the compensation trigger threshold may include: if the fluctuation deviation value is greater than the first threshold, then the fluctuation deviation value is recorded.

[0119] If the runout deviation value is greater than the first threshold and less than the second threshold, the initial compensation amount is determined based on the pipe parameters and runout deviation value of the pipe to be processed; the initial compensation amount is adjusted based on the temperature correction amount to obtain the first compensation amount; the first threshold is less than the second threshold.

[0120] If the fluctuation deviation value is greater than the second threshold, an alarm message will be sent.

[0121] The compensation trigger threshold can include a first threshold and a second threshold, which are used to classify and judge the runout deviation value to achieve differentiated compensation strategies. The first threshold and the second threshold can be set according to the equipment accuracy requirements and actual working conditions. For example, the first threshold can be set to 0.05mm and the second threshold can be set to 0.1mm.

[0122] During the process of determining the compensation value, if the runout deviation value is greater than the first threshold, it indicates that the chuck runout has exceeded the normal range and needs to be recorded for subsequent analysis and model optimization.

[0123] If the runout deviation value is between the first threshold and the second threshold, the initial compensation amount is determined based on the pipe parameters (such as diameter, wall thickness, material, etc.) and the runout deviation value, combined with the preset compensation knowledge base. Then, the initial compensation amount is fine-tuned based on the temperature correction amount to obtain the final first compensation amount.

[0124] If the fluctuation deviation value is greater than the second threshold, it indicates that the fluctuation is abnormally severe and may involve equipment failure. At this time, an alarm message is sent to prompt the operator to intervene and check.

[0125] In this embodiment, the graded compensation strategy achieves the accuracy and timeliness of compensation, avoiding the problems of over-compensation or under-compensation. At the same time, the combination of temperature correction and pipe parameters further improves the adaptability and effectiveness of compensation.

[0126] In some embodiments, the compensation trigger threshold includes a third threshold; compensating the target chuck according to the first compensation value may include: generating a drive command according to the first compensation amount; the drive command is used to instruct the shim push rod to drive the shim of the target chuck to move to the target position corresponding to the first compensation amount.

[0127] After compensation is completed, a new runout deviation value is determined.

[0128] If the new fluctuation deviation value is less than the third threshold, the compensation is considered successful and the new fluctuation deviation value is recorded; the third threshold is less than the first threshold.

[0129] If the new runout deviation value is greater than the third threshold but less than the first threshold, the target chuck is compensated based on the preset compensation amount; the preset compensation amount is less than the third threshold.

[0130] If the new fluctuation deviation value is greater than the first threshold, an alarm message will be sent.

[0131] Specifically, the compensation trigger threshold may also include a third threshold for verifying the effect after compensation. The third threshold is usually smaller than the first threshold, for example, it can be set to 0.03mm, to determine whether the compensation has achieved the expected effect.

[0132] During the specific compensation process, a drive command can be generated based on the first compensation amount to control the shim push rod to move the shim of the target chuck to the target position, thus achieving mechanical compensation. After compensation is completed, data is immediately collected and a new runout deviation value is calculated to verify the compensation effect. If the new runout deviation value is less than the third threshold, it indicates successful compensation, and the relevant data is recorded. If the new runout deviation value is between the third threshold and the first threshold, it indicates that the compensation effect has not fully met expectations, and fine-tuning is performed based on a preset compensation amount (e.g., ±0.005mm). If the new runout deviation value is greater than the first threshold, it indicates compensation failure or other equipment problems, and an alarm message is sent.

[0133] This embodiment ensures the reliability and stability of the compensation effect through real-time verification and iterative fine-tuning after compensation. At the same time, the automatic fine-tuning of the preset compensation amount reduces manual intervention and improves the automation level of equipment operation.

[0134] In some embodiments, the setting of the compensation trigger threshold can be optimized by combining the risk level of chuck adhesion, so as to achieve linkage control between jumping and adhesion.

[0135] The risk level of chuck adhesion can be assessed in real time using multi-source data (such as current, air pressure, vibration, coolant concentration, etc.) and neural network models. For example, it can be divided into levels 0-3, with higher risk levels indicating a greater likelihood of chuck adhesion.

[0136] The compensation trigger threshold can be dynamically adjusted according to the risk level of chuck adhesion. For example: Risk level 0: the compensation threshold is set to 0.05mm; Risk level 1: the compensation threshold is adjusted to 0.04mm to improve compensation sensitivity; Risk level 2: the compensation threshold is adjusted to 0.03mm and pre-compensation measurement is forced; Risk level 3: the 0.03mm threshold is maintained, but alarm processing is the main function.

[0137] This embodiment improves the accuracy and timeliness of compensation by linking jumping and adhesion, and also realizes comprehensive monitoring and early warning of equipment status, effectively reducing unplanned downtime and maintenance costs.

[0138] The chuck runout compensation method for pipe cutting provided in this embodiment collects multi-dimensional sensor data of the chuck during the cutting interval, performs preprocessing, feature extraction and fusion analysis, and finally adaptively determines the compensation strategy based on the runout deviation value and the chuck adhesion risk level, thereby improving the intelligence level of runout compensation, realizing accurate compensation for chuck runout, and improving the accuracy and stability of pipe cutting.

[0139] Figure 3 A flowchart illustrating the chuck runout compensation method for pipe cutting provided in this application embodiment. Figure 2 .like Figure 3 As shown, the method includes:

[0140] 301. During the interval between cutting the pipe to be processed, the first sensor data of the target chuck is collected, and the first sensor data is preprocessed to obtain the second sensor data.

[0141] 302. Based on the second sensor data, determine the dynamic runout data, static coaxiality data, and temperature correction amount of the target chuck. Then, fuse the dynamic runout data, static coaxiality data, and temperature correction amount to obtain the runout deviation value.

[0142] Specifically, the dynamic runout data can be calculated by extracting the radial displacement data of the spindle encoder within a preset 10-rotation cycle and taking the maximum value as the dynamic runout index D.

[0143] The static coaxiality data can be determined by calculating the average of the front-to-middle chuck center distance deviation and the middle-to-rear chuck center distance deviation collected by the laser alignment instrument, and using this average as the static coaxiality index S.

[0144] The temperature correction amount can be calculated using the formula. ,in Temperature near the chuck jaws. For ambient temperature, The standard reference temperature is 20℃, and a and b are temperature influence coefficients calibrated through experiments, which can be 0.003 and 0.001 respectively.

[0145] A weighted average algorithm can be used for fusion processing: The weight of dynamic runout data can be 0.6, and the weight of static coaxiality data can be 0.4. This weight allocation is determined based on the experimental calibration results of the equipment's X-axis repeatability (e.g., ±0.03mm), reflecting the dominant influence of dynamic factors on runout deviation.

[0146] 303. Determine the chuck adhesion risk level of the target chuck, and determine the compensation trigger threshold based on the chuck adhesion risk level;

[0147] 304. Determine the first compensation value based on the runout deviation value and the compensation trigger threshold, and perform compensation processing on the target chuck based on the first compensation value.

[0148] Steps 301 to 304 in this embodiment are similar to steps 201 to 204 in the above embodiment, and will not be repeated here.

[0149] 305. Based on the preset strategy, generate corresponding control commands according to the chuck adhesion risk level and runout deviation value.

[0150] Specifically, collaborative maintenance decisions can be made so that when abnormal fluctuations and adhesion warnings occur simultaneously, the system generates joint alarms and targeted maintenance work orders, enabling root cause analysis and intelligent scheduling.

[0151] In some embodiments, based on a preset strategy, a corresponding control command is generated according to the chuck adhesion risk level and the runout deviation value. This may include: if the chuck adhesion risk level is less than or equal to a first preset level and the runout deviation value is less than a first threshold, then the working state is determined to be normal.

[0152] If the risk level of chuck adhesion is greater than the first preset level but less than the second preset level, and the fluctuation deviation value is greater than the first threshold, a cleaning instruction is generated; the second preset level is greater than the first preset level.

[0153] If the risk level of chuck adhesion is greater than the third preset level, a stop command will be generated; the third preset level is greater than the second preset level.

[0154] Specifically, the preset strategy may include a three-level linkage control mechanism: when the risk level of chuck adhesion is less than or equal to the first preset level (which may correspond to level 0), and the runout deviation is less than the first threshold (e.g., 0.05mm), the equipment is determined to be in normal working condition, and only routine data recording is performed.

[0155] When the chuck adhesion risk level is greater than the first preset level and less than the second preset level (which can correspond to level 1-2), and the runout deviation value is greater than the first threshold (e.g., 0.05mm), a cleaning instruction is generated. This instruction automatically generates a cleaning work order through the MES system, specifying the cleaning scope and standard operating procedures.

[0156] When the risk level of chuck adhesion is greater than the third preset level (which can correspond to level 3), regardless of the size of the runout deviation, a stop command will be generated immediately. This command will restrict the opening and closing of the chuck, trigger a red audible and visual alarm, and urgently notify maintenance personnel via SMS and email.

[0157] The chuck runout compensation method for pipe cutting provided in this embodiment achieves precise compensation for chuck runout and early warning of adhesion risks through multi-source data fusion, intelligent risk rating, and hierarchical compensation control. Multi-dimensional sensor data is collected during intermittent periods, and data quality is improved through vibration screening and temperature correction. Adhesion risk rating based on a neural network model enables intelligent processing from feature extraction to risk assessment. A compensation threshold is adaptively adjusted according to the risk level, establishing a compensation mechanism with variable sensitivity. Closed-loop control is formed through compensation effect verification and iterative optimization. Finally, hierarchical control commands are generated based on the joint analysis of adhesion risk and runout deviation, achieving intelligent operation and maintenance decision-making. This method significantly improves the cutting accuracy and equipment availability of laser pipe cutters, reducing the traditional manual calibration time from 4-8 hours to less than 5 minutes. Simultaneously, early warning reduces unplanned downtime by more than 85%, demonstrating significant industrial application value.

[0158] Figure 4 This is a schematic diagram of a chuck runout compensation device for pipe cutting provided in an embodiment of this application. Figure 4 As shown, the chuck runout compensation device 40 for pipe cutting includes: a data acquisition module 401, a fusion module 402, a determination module 403, and a compensation module 404.

[0159] The acquisition module 401 is used to acquire the first sensor data of the target chuck during the interval of cutting the pipe to be processed, and to preprocess the first sensor data to obtain the second sensor data.

[0160] The fusion module 402 is used to determine the dynamic runout data, static coaxiality data and temperature correction amount of the target chuck based on the second sensor data, and to fuse the dynamic runout data, static coaxiality data and temperature correction amount to obtain the runout deviation value.

[0161] The determination module 403 is used to determine the chuck adhesion risk level of the target chuck and determine the compensation trigger threshold based on the chuck adhesion risk level.

[0162] The compensation module 404 is used to determine a first compensation value based on the runout deviation value and the compensation trigger threshold, and to perform compensation processing on the target chuck based on the first compensation value.

[0163] The chuck runout compensation device for pipe cutting provided in this application collects multi-dimensional sensor data of the chuck during the cutting interval, performs preprocessing, feature extraction and fusion analysis, and finally adaptively determines the compensation strategy based on the runout deviation value and the chuck adhesion risk level, thereby improving the intelligence level of runout compensation, realizing accurate compensation for chuck runout, and improving the accuracy and stability of pipe cutting.

[0164] In some embodiments, the laser tube cutting machine is equipped with a spindle encoder, a laser alignment device, a temperature sensor, and a vibration sensor. The first sensing data includes: radial displacement data acquired by the spindle encoder, chuck center distance data acquired by the laser alignment device, chuck temperature data acquired by the temperature sensor, and chuck vibration data acquired by the vibration sensor.

[0165] The acquisition module 401 is specifically used for:

[0166] The screening threshold is determined based on vibration data.

[0167] The time period of excessive vibration was determined based on the screening threshold.

[0168] The data from the radial displacement data, chuck center distance data, and temperature data that were generated during the period when the vibration exceeded the standard were deleted to obtain the second sensing data.

[0169] In some embodiments, the fusion module 402 is specifically used to: determine the dynamic runout data of the target chuck based on the maximum radial displacement value within a preset number of revolutions in the radial displacement data.

[0170] Based on the chuck center distance data, determine the average value of the front and rear center distance deviations, and then determine the static coaxiality data of the target chuck based on the average value.

[0171] Based on the temperature data and the first correspondence, determine the temperature correction amount corresponding to the temperature data. The first correspondence includes the temperature correction amounts corresponding to different temperature data.

[0172] In some embodiments, the fusion module 402 is specifically used to: perform a weighted average of the dynamic runout data, static coaxiality data, and temperature correction to determine the runout deviation value of the target chuck. The first weight corresponding to the dynamic runout data is greater than the second weight corresponding to the static coaxiality data.

[0173] In some embodiments, the compensation trigger threshold includes a first threshold and a second threshold. The compensation module 404 is specifically configured to: if the fluctuation deviation value is greater than the first threshold, record the fluctuation deviation value.

[0174] If the runout deviation is greater than the first threshold but less than the second threshold, the initial compensation amount is determined based on the pipe parameters and the runout deviation. The initial compensation amount is then adjusted according to the temperature correction to obtain the first compensation amount. The first threshold is less than the second threshold.

[0175] If the fluctuation deviation value is greater than the second threshold, an alarm message will be sent.

[0176] In some embodiments, the compensation trigger threshold includes a third threshold. The compensation module 404 is specifically configured to: generate a drive command based on a first compensation amount. The drive command is used to instruct the shim push rod to drive the shim of the target chuck to move to the target position corresponding to the first compensation amount.

[0177] After compensation is completed, a new runout deviation value is determined.

[0178] If the new fluctuation deviation value is less than the third threshold, the compensation is considered successful, and the new fluctuation deviation value is recorded. The third threshold is less than the first threshold.

[0179] If the new runout deviation value is greater than the third threshold but less than the first threshold, then the target chuck is compensated based on a preset compensation amount. The preset compensation amount is less than the third threshold.

[0180] If the new fluctuation deviation value is greater than the first threshold, an alarm message will be sent.

[0181] In some embodiments, the determining module 403 is specifically used to: acquire third sensor data of the target chuck in the current opening and closing cycle.

[0182] Obtain the historical runout deviation value of the target chuck.

[0183] The corresponding feature data is determined based on the third sensor data and historical fluctuation deviation values.

[0184] The feature data is input into the neural network model to obtain the chuck adhesion risk level of the target chuck.

[0185] In some embodiments, the third sensing data includes: current data, air pressure data, vibration data, and coolant concentration. Feature data includes: a current anomaly coefficient determined based on the current data, an air pressure anomaly coefficient determined based on the air pressure data, a vibration change rate determined based on the vibration data, and a coolant deviation rate determined based on the coolant concentration.

[0186] In some embodiments, the compensation module 404 is further configured to: determine that the working state is normal if the chuck adhesion risk level is less than or equal to the first preset level and the runout deviation value is less than the first threshold.

[0187] If the risk level of chuck adhesion is greater than the first preset level but less than the second preset level, and the runout deviation is greater than the first threshold, a cleaning command is generated. The second preset level is greater than the first preset level.

[0188] If the risk level of chuck adhesion is greater than the third preset level, a stop command will be generated. The third preset level is greater than the second preset level.

[0189] The chuck runout compensation device for pipe cutting provided in this application embodiment can be used to perform the above-described method embodiment. Its implementation principle and technical effect are similar, and will not be described again here.

[0190] Figure 5 A schematic diagram of the structure of the electronic device provided in this application. Figure 5 As shown, the electronic device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the electronic device 50 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus.

[0191] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0192] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0193] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0194] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0195] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0196] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0197] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0198] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0199] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0200] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0201] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0202] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0203] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0204] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0205] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A chuck runout compensation method for pipe cutting, characterized in that, include: During the interval between cutting the pipe to be processed, the first sensor data of the target chuck is collected, and the first sensor data is preprocessed to obtain the second sensor data. Based on the second sensing data, the dynamic runout data, static coaxiality data, and temperature correction amount of the target chuck are determined. The dynamic runout data, the static coaxiality data, and the temperature correction amount are then fused to obtain the runout deviation value. Determine the chuck adhesion risk level of the target chuck, and determine the compensation trigger threshold based on the chuck adhesion risk level; Based on the fluctuation deviation value and the compensation trigger threshold, a first compensation value is determined, and the target chuck is compensated according to the first compensation value.

2. The method according to claim 1, characterized in that, This invention is applied to a laser tube cutting machine, which is equipped with a spindle encoder, a laser alignment instrument, a temperature sensor, and a vibration sensor. The first sensing data includes: radial displacement data collected by the spindle encoder, chuck center distance data collected by the laser alignment instrument, chuck temperature data collected by the temperature sensor, and chuck vibration data collected by the vibration sensor. The step of preprocessing the first sensing data to obtain the second sensing data includes: Determine the screening threshold based on the vibration data; The time period of vibration exceeding the standard is determined based on the aforementioned screening threshold; The data in the radial displacement data, the chuck center distance data, and the temperature data that occurred during the period when the vibration exceeded the standard were deleted to obtain the second sensing data.

3. The method according to claim 2, characterized in that, The step of determining the dynamic runout data, static coaxiality data, and temperature correction amount of the target chuck based on the second sensing data includes: Based on the maximum radial displacement value within a preset number of revolutions in the radial displacement data, the dynamic runout data of the target chuck is determined; Based on the chuck center distance data, determine the average value of the front and rear center distance deviations, and determine the static coaxiality data of the target chuck based on the average value; Based on the temperature data and the first correspondence, the temperature correction amount corresponding to the temperature data is determined; the first correspondence includes the temperature correction amounts corresponding to different temperature data respectively.

4. The method according to claim 1, characterized in that, The process of fusing the dynamic runout data, the static coaxiality data, and the temperature correction to obtain the runout deviation value includes: The runout deviation value of the target chuck is determined by weighting the dynamic runout data, static coaxiality data, and temperature correction amount; the first weight corresponding to the dynamic runout data is greater than the second weight corresponding to the static coaxiality data.

5. The method according to claim 1, characterized in that, The compensation trigger threshold includes a first threshold and a second threshold; determining the first compensation value based on the fluctuation deviation value and the compensation trigger threshold includes: If the fluctuation deviation value is greater than the first threshold, then the fluctuation deviation value is recorded; If the runout deviation value is greater than the first threshold and less than the second threshold, then an initial compensation amount is determined based on the pipe parameters of the pipe to be processed and the runout deviation value; the initial compensation amount is adjusted based on the temperature correction amount to obtain a first compensation amount; the first threshold is less than the second threshold; If the fluctuation deviation value is greater than the second threshold, an alarm message is sent.

6. The method according to claim 5, characterized in that, The compensation trigger threshold includes a third threshold; the compensation process for the target chuck based on the first compensation value includes: A drive command is generated based on the first compensation amount; the drive command is used to instruct the shim push rod to drive the shim of the target chuck to move to the target position corresponding to the first compensation amount; After compensation is completed, determine the new runout deviation value; If the new fluctuation deviation value is less than the third threshold, the compensation is determined to be successful, and the new fluctuation deviation value is recorded; the third threshold is less than the first threshold. If the new runout deviation value is greater than the third threshold and less than the first threshold, then the target chuck is compensated based on a preset compensation amount; the preset compensation amount is less than the third threshold. If the new fluctuation deviation value is greater than the first threshold, an alarm message is sent.

7. The method according to any one of claims 1-6, characterized in that, Determining the chuck adhesion risk level of the target chuck includes: Collect the third sensor data of the target chuck in the current opening and closing cycle; Obtain the historical runout deviation value of the target chuck; The corresponding feature data is determined based on the third sensor data and the historical fluctuation deviation value; The feature data is input into a neural network model to obtain the chuck adhesion risk level of the target chuck.

8. The method according to claim 7, characterized in that, The third sensing data includes: current data, air pressure data, vibration data, and coolant concentration; the feature data includes: current anomaly coefficient determined based on the current data, air pressure anomaly coefficient determined based on the air pressure data, vibration change rate determined based on the vibration data, and coolant deviation rate determined based on the coolant concentration.

9. The method according to any one of claims 1-6, characterized in that, The method further includes: If the risk level of chuck adhesion is less than or equal to the first preset level, and the runout deviation value is less than the first threshold, then the working state is determined to be normal. If the chuck adhesion risk level is greater than the first preset level and less than the second preset level, and the fluctuation deviation value is greater than the first threshold, then a cleaning instruction is generated; the second preset level is greater than the first preset level. If the risk level of chuck adhesion is greater than the third preset level, a stop command is generated; the third preset level is greater than the second preset level.

10. An electronic device, characterized in that, include: At least one processor and memory; The memory stores computer-executed instructions; The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the chuck runout compensation method for pipe cutting as described in any one of claims 1 to 9.

Images