Quality control method and system for laser surface treatment of valve workpieces

Abstract

The present invention relates to the field of laser processing technology for valve workpieces, and proposes a quality control method and system for laser surface treatment of valve workpieces, including: collecting path point cloud data and distance data of semi-finished valve workpieces, setting initial laser power, and establishing a distance sequence at the current collection moment; determining the cumulative influence of the current collection moment according to the value of the distance data contained in the distance sequence at the current collection moment and the collection moment; determining the shape influence at the current collection moment in combination with the path point cloud data; and realizing quality control of laser surface treatment of valve workpieces according to the initial laser power and the shape influence at the current collection moment. The present invention solves the problem of improving the adaptability of laser cladding to the distance between the valve workpiece and the laser, and ensures the quality of laser surface treatment of the valve workpiece.

Description

Technical Field

[0001] The invention relates to the technical field of laser processing of valve workpieces, and in particular to a quality control method and system suitable for laser surface processing of valve workpieces. Background Art

[0002] Laser surface treatment technology changes the physical and chemical properties of the valve workpiece surface through non-contact processing, enhances the wear resistance, corrosion resistance and high temperature resistance of the valve workpiece, and can improve the overall performance of the valve workpiece. Therefore, the quality control of the laser surface treatment of the valve workpiece is directly related to the safety and reliability of the valve workpiece, and real-time quality control is required during the laser surface treatment of the valve workpiece. The laser surface treatment process of the valve workpiece includes laser cladding, and it is necessary to ensure that the distance between the laser and the valve workpiece is constant. However, the structure of the valve workpiece is irregular, which makes it difficult to maintain a constant distance, which will directly affect the energy distribution of the laser and the cladding effect.

[0003] Laser power and scanning speed are key factors affecting the morphology of the cladding layer, and together determine the width, depth and height of the cladding layer. When the laser power is constant, increasing the scanning speed will lead to a decrease in the depth of penetration, and too fast a scanning speed may cause the alloy powder to fail to melt completely, affecting the cladding effect. Existing laser power adjustment strategies generally use a light intensity feedback control system to adjust the output power of the laser in real time, focusing on power regulation. However, irregular valve workpieces often lead to unstable distances between the valve workpiece and the laser, making laser cladding insufficiently adaptable to the distance between the valve workpiece and the laser, and unable to guarantee ideal energy distribution and cladding effects. Summary of the invention

[0004] The present invention provides a quality control method and system for laser surface treatment of valve workpieces, so as to solve the problem that the laser cladding is not sufficiently adaptable to the distance between the valve workpiece and the laser, resulting in unsatisfactory quality of the laser surface treatment of the valve workpiece. The technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present invention provides a quality control method for laser surface treatment of a valve workpiece, the method comprising the following steps:

[0006] Collect the three-dimensional point cloud data of the semi-finished valve workpiece and extract the path point cloud data, set the initial laser power, and in the process of laser cladding the semi-finished valve workpiece, collect the distance data at the current collection time and the preset number of distances before, and obtain the distance sequence at the current collection time according to the distance data;

[0007] According to the adjacent distance data of any distance data contained in the distance sequence at the current collection moment, a first difference of the any distance data is obtained; according to the values ​​of all distance data contained in the distance sequence at the current collection moment and the collection moment, a second difference at the current collection moment is determined; according to the second difference at the current collection moment, all distance data contained in the distance sequence at the current collection moment, and the first difference of the distance data, a cumulative influence degree at the current collection moment is determined;

[0008] According to the path point cloud data, determine the curvature of each point in the path point cloud data and the curvature change degree at the current acquisition time, and determine the shape influence degree at the current acquisition time according to the curvature, curvature change degree and cumulative influence degree at the current acquisition time;

[0009] According to the initial laser power and the shape influence at the current acquisition moment, quality control of laser surface treatment suitable for valve workpieces is achieved.

[0010] Furthermore, the specific method for extracting path point cloud data is:

[0011] A 3D scanner is used to perform a 3D scan on the semi-finished valve workpiece to obtain 3D point cloud data of the semi-finished valve workpiece, a 3D reconstruction algorithm is used on the 3D point cloud data to obtain a 3D model of the semi-finished valve workpiece, and a cladding path is generated using a 3D path planning algorithm based on ant colonies according to the 3D model and the process requirements of the cladding layer;

[0012] The cladding path is matched with the three-dimensional point cloud data of the semi-finished valve workpiece, and the matching results of each point in the cladding path and the points in the three-dimensional point cloud data of the semi-finished valve workpiece are determined. According to the matching results, the point cloud data located on the cladding path in the three-dimensional point cloud data of the semi-finished valve workpiece is extracted, and the extracted point cloud data is recorded as path point cloud data.

[0013] Further, the method of obtaining the first difference of any distance data according to the adjacent distance data of any distance data included in the distance sequence at the current acquisition moment includes the following specific methods:

[0014] Any distance data contained in the distance sequence at the current collection time is recorded as the target collection data; the collection time corresponding to the target collection data is recorded as the target collection time;

[0015] Intercepting the distance data of the target acquisition moment and the first preset threshold number of consecutive acquisition moments before the target acquisition moment in the distance data sequence to obtain the distance sequence of the target acquisition moment;

[0016] The standard deviation of all distance data contained in the distance sequence at the target acquisition time is recorded as the first difference at the target acquisition time.

[0017] Further, the method for determining the second difference at the current collection moment is:

[0018] The absolute value of the difference between the distance data of the two collection times with the farthest collection time interval included in the distance sequence of the current collection time is recorded as the second difference of the current collection time.

[0019] Furthermore, the method for determining the cumulative influence at the current collection moment is:

[0020]

[0021] In the formula, Indicates the cumulative impact at the current collection moment; Indicates the first difference at the current acquisition moment; Indicates the second difference of the current acquisition moment; Indicates the distance sequence at the current acquisition time. The first difference of distance data; represents a natural constant; represents the first tuning parameter coefficient; represents the softmax function; Indicates that in the distance sequence at the current acquisition time, the The number of distance data between the distance data and the distance data at the current collection moment; Indicates the number of distance data contained in the distance sequence at the current acquisition time.

[0022] Furthermore, the method for obtaining the curvature of each point in the path point cloud data is:

[0023] The path point cloud data is fitted with the least square method to obtain the surface where the path point cloud data is located. The surface where the path point cloud data is located is calculated using the three-point parameter equation method to obtain the curvature of each point in the path point cloud data.

[0024] Furthermore, the method for obtaining the curvature change degree at the current acquisition moment is:

[0025] The absolute value of the difference between the curvature at the current acquisition moment and the curvature at the immediately preceding acquisition moment is recorded as the curvature variation degree at the current acquisition moment.

[0026] Furthermore, the method for obtaining the shape influence at the current acquisition moment is:

[0027] The product of the curvature at the current acquisition moment and the curvature variation is recorded as the shape influence coefficient at the current acquisition moment, and the normalized value of the product of the shape influence coefficient at the current acquisition moment and the cumulative influence is recorded as the shape influence degree at the current acquisition moment.

[0028] Furthermore, the quality control of laser surface treatment for valve workpieces is realized according to the initial laser power and the shape influence at the current acquisition moment, and the specific method includes:

[0029] The sum of the shape influence degree at the current acquisition moment and the second parameter adjustment coefficient is recorded as the power adjustment coefficient at the current acquisition moment, and the product of the power adjustment coefficient at the current acquisition moment and the initial laser power is recorded as the target power at the next adjacent acquisition moment of the current acquisition moment;

[0030] The target power at the next adjacent acquisition moment of the current acquisition moment is used as the laser power value at the next adjacent acquisition moment of the current acquisition moment, so as to realize the quality control of the laser surface treatment suitable for the valve workpiece.

[0031] In a second aspect, an embodiment of the present invention further provides a quality control system suitable for laser surface processing of valve workpieces, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above-mentioned methods when executing the computer program.

[0032] The beneficial effects of the present invention are:

[0033] The distance data collected during the laser cladding process has a significant impact on the cladding accuracy and effect. According to the characteristics of the accumulated deviation of the distance data during the laser cladding process, the present application analyzes the accumulated influence of the distance change contained in the distance sequence at the current acquisition moment, and determines the cumulative influence degree at the current acquisition moment in combination with the fluctuation degree of all the distance data contained in the distance sequence at the acquisition moment; according to the characteristics that the focusing and energy distribution of the laser beam will be affected by the curvature and shape of the valve workpiece semi-finished product, resulting in uneven thickness of the cladding layer, the severity of the shape change of the position where the valve workpiece semi-finished product is laser clad and the discontinuity of the surface curvature change of the valve workpiece semi-finished product are evaluated, and the shape influence degree at the current acquisition moment is determined in combination with the cumulative influence degree; finally, according to the initial laser power and the shape influence degree at the current acquisition moment, the quality control of the laser surface treatment suitable for the valve workpiece is realized, the uniformity and quality of the cladding layer are improved, and the cladding defects caused by the complex shape of the valve workpiece semi-finished product or the change of the laser distance data are avoided, and the problem of insufficient adaptability of the laser cladding to the distance between the valve workpiece and the laser, resulting in unsatisfactory quality of the laser surface treatment of the valve workpiece, is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0035] Figure 1 A schematic flow chart of a quality control method for laser surface treatment of a valve workpiece provided by an embodiment of the present invention;

[0036] Figure 2 A flow chart of obtaining shape influence provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] See also Figure 1 , which shows a flow chart of a quality control method for laser surface treatment of a valve workpiece provided by an embodiment of the present invention, the method comprising the following steps:

[0039] Step S001, collect the three-dimensional point cloud data of the semi-finished valve workpiece and extract the path point cloud data, set the initial laser power, and in the process of performing laser cladding on the semi-finished valve workpiece, collect the distance data of the current collection time and the preset number before, and obtain the distance sequence of the current collection time according to the distance data.

[0040] According to the detailed drawings of the valve plate and valve seat, the blank is processed into a semi-finished valve workpiece using lathes, milling machines, grinders and other mechanical processing equipment. During the processing, the size and shape of the semi-finished valve workpiece are ensured to meet the design requirements, and the size of the subsequent laser cladding additive part is reserved. The semi-finished valve workpiece is thoroughly cleaned to remove oil, dust and rust on the surface of the semi-finished valve workpiece, and the surface of the cleaned semi-finished valve workpiece is polished or sandblasted to increase the roughness of the semi-finished surface and improve the bonding strength between the cladding material and the semi-finished substrate.

[0041] A 3D scanner is used to perform a three-dimensional scan on the semi-finished valve workpiece to obtain three-dimensional point cloud data of the semi-finished valve workpiece. A three-dimensional reconstruction algorithm is used on the three-dimensional point cloud data to obtain a three-dimensional model of the semi-finished valve workpiece. According to the three-dimensional model and the process requirements of the cladding layer, a three-dimensional path planning algorithm based on ant colonies is used to generate a cladding path to ensure that the cladding path can cover the surface of the semi-finished valve workpiece that needs to be clad.

[0042] The cladding path is matched with the three-dimensional point cloud data of the semi-finished valve workpiece, and the matching results of each point in the cladding path and the points in the three-dimensional point cloud data of the semi-finished valve workpiece are determined. According to the matching results, the point cloud data located on the cladding path in the three-dimensional point cloud data of the semi-finished valve workpiece is extracted, and the extracted point cloud data is recorded as path point cloud data.

[0043] The purpose of extracting path point cloud data is to ensure that at each data sampling moment, the laser position for laser cladding is on the preset cladding path to prevent the laser position of laser cladding from deviating. When the laser position of laser cladding deviates, the laser surface treatment of the valve workpiece is directly stopped.

[0044] Among them, the method of processing the semi-finished valve workpiece and the cladding path is a well-known technology and will not be described in detail.

[0045] According to the properties of the cladding material and the thickness requirements of the cladding layer, in this embodiment, the laser power range is set to 1000-3000W, the initial laser power is 2000W, the scanning speed is 15mm / s, and the powder feeding rate is 25g / min. In actual application, as other implementation methods, the implementer can determine the above process parameters according to actual conditions.

[0046] Laser cladding is performed according to the cladding path and process parameters to fully cover the area on the surface of the semi-finished valve workpiece that needs to be clad. During the laser cladding process, the laser surface treatment of the valve workpiece is quality controlled.

[0047] A distance sensor is installed at the laser emitter for laser cladding, and the installation direction of the distance sensor is consistent with the laser emission direction. During the laser cladding process, the distance sensor is used to collect distance data between the laser emission position and the cladding position of the semi-finished valve workpiece.

[0048] Preferably, in one embodiment of the present application, when collecting distance data, the distance data sampling frequency in this embodiment is 10 Hz. In actual application, as other implementation methods, the implementer can determine the sampling rate of the distance data according to actual conditions, and this application does not impose any special restrictions.

[0049] It should be noted that, in order to facilitate calculation, all distance data involved in the calculation in this embodiment are pre-processed to eliminate the dimension effect. This embodiment uses the Z-Score standard normalization method to remove the dimension of the distance data. In actual application, the implementer can use other methods such as the existing technology of the maximum and minimum value normalization method to remove the dimension, which is not limited here.

[0050] All distance data collected from the start of laser cladding to the current collection time are arranged in the order of the collection time to obtain a distance data sequence.

[0051] Since laser cladding is a dynamic process, the cladding state at each acquisition moment may be affected by the change of distance data in the local range. The distance data at the current acquisition moment and the first preset threshold acquisition moments before the current acquisition moment in the distance data sequence are intercepted to obtain the distance sequence at the current acquisition moment.

[0052] In this embodiment, the value of the first preset threshold is 10, that is, the distance sequence at the current collection moment includes the distance data at the current collection moment and 10 collection moments before the current collection moment, and the distance sequence at the current collection moment includes the distance data at 11 collection moments in total.

[0053] It should be noted that when the continuous collection moments before the current collection moment are less than the first preset threshold, the average of the distance data of all the continuous collection moments before the current collection moment is used for filling.

[0054] At this point, the distance sequence at the current acquisition moment is obtained.

[0055] Step S002, obtaining a first difference of any distance data contained in the distance sequence of the current acquisition moment according to adjacent distance data of the any distance data, determining a second difference at the current acquisition moment according to the values ​​of all distance data contained in the distance sequence of the current acquisition moment and the acquisition moment, and determining a cumulative influence at the current acquisition moment according to the second difference at the current acquisition moment, all distance data contained in the distance sequence of the current acquisition moment, and the first difference of the distance data.

[0056] The distance data collected during the laser cladding process has a significant impact on the cladding accuracy and effect. When the distance data is too small, the laser energy is too concentrated, which may cause the cladding material to overheat or even burn, affecting the uniformity and adhesion of the cladding layer; when the distance data is too large, the laser energy is unevenly distributed, which may cause the cladding material to fail to fully melt, resulting in a weak bond between the cladding layer and the substrate, affecting the mechanical properties and wear resistance of the cladding layer.

[0057] Any distance data contained in the distance sequence of the current collection moment is recorded as the target collection data, and the collection moment corresponding to the target collection data is recorded as the target collection moment. The distance data of the target collection moment and the first preset threshold collection moments before the target collection moment are intercepted in the distance data sequence to obtain the distance sequence of the target collection moment. The standard deviation of all distance data contained in the distance sequence of the target collection moment is recorded as the first difference of the target collection moment.

[0058] Among them, in this embodiment, the value of the first preset threshold is 10, that is, the distance sequence of the target acquisition moment includes the distance data of the target acquisition moment and the 10 acquisition moments before the target acquisition moment, and the distance sequence of the target acquisition moment includes the distance data of 11 acquisition moments in total. It should also be noted that when the continuous acquisition moments before the current acquisition moment are less than the first preset threshold, the average of the distance data of all continuous acquisition moments before the current acquisition moment is used for filling.

[0059] The first difference at the target acquisition time is used to evaluate the fluctuation degree of all distance data contained in the distance sequence at the target acquisition time. The greater the fluctuation degree, the greater the first difference at the target acquisition time.

[0060] During the laser cladding process, the deviation of distance data is cumulative. Each deviation of distance data may be amplified in the subsequent laser cladding process, and finally the quality of the entire cladding layer will be reduced. Therefore, it is necessary to analyze the accumulated impact of distance changes contained in the distance sequence at the current acquisition moment.

[0061] The absolute value of the difference between the distance data of the two collection times with the farthest collection time interval included in the distance sequence of the current collection time is recorded as the second difference of the current collection time.

[0062] The second difference at the current acquisition moment is used to evaluate the cumulative impact of the distance change contained in the distance sequence at the current acquisition moment. The greater the cumulative impact, the greater the second difference at the target acquisition moment.

[0063] The cumulative influence degree of the current collection moment is determined according to the second difference of the current collection moment, all distance data included in the distance sequence of the current collection moment, and the first difference of the distance data.

[0064]

[0065] In the formula, Indicates the cumulative impact at the current collection moment; Indicates the first difference at the current acquisition moment; Indicates the second difference of the current acquisition moment; Indicates the distance sequence at the current acquisition time. The first difference of distance data; represents a natural constant; represents the first parameter adjustment coefficient. In this embodiment, the value of the first parameter adjustment coefficient is 0.1, which is used to adjust the value of the cumulative influence; Represents the softmax function, which is used for normalization; Indicates that in the distance sequence at the current acquisition time, the The number of distance data between the distance data and the distance data at the current collection moment; Indicates the number of distance data contained in the distance sequence at the current acquisition time.

[0066] The greater the second difference at the current acquisition moment, the greater the cumulative impact of the distance change contained in the distance sequence at the current acquisition moment; the greater the first differences of all distance data contained in the distance sequence at the current acquisition moment, the greater the fluctuation degree of all distance data contained in the distance sequence at the target acquisition moment, wherein the distance data with fewer distance data intervals between the distance data at the current acquisition moment in the distance sequence has a greater impact on the fluctuation degree evaluation, and the greater the cumulative impact at the current acquisition moment, at this time, the greater the cumulative impact of the distance data change in the laser cladding process on the quality of the cladding layer, the greater the possibility that the melting state of the cladding material is affected, and the greater the possibility of uneven laser energy distribution.

[0067] At this point, the cumulative influence at the current collection moment is obtained.

[0068] Step S003, determining the curvature of each point in the path point cloud data and the curvature change at the current acquisition time according to the path point cloud data, and determining the shape influence at the current acquisition time according to the curvature, curvature change and cumulative influence at the current acquisition time.

[0069] When performing laser cladding on curved surfaces or semi-finished valve workpieces with complex geometries, the focusing and energy distribution of the laser beam may be affected, resulting in uneven thickness of the cladding layer. Changes in surface curvature will intensify changes in the distance between the laser beam and the semi-finished valve workpiece, affecting the laser energy input and cladding effect.

[0070] Each data in the path point cloud data represents the laser position at the corresponding acquisition moment. In order to analyze the curvature change of the valve workpiece near the laser position at the current acquisition moment, the path point cloud data is fitted with the least squares method to obtain the surface where the path point cloud data is located. The three-point parameter equation method is used to calculate the surface where the path point cloud data is located to obtain the curvature of each point in the path point cloud data.

[0071] The curvature of a point describes the degree of shape change at the position where the valve workpiece semi-finished product is laser clad at the acquisition moment corresponding to the point. The more drastic the shape change, the greater the curvature of the point.

[0072] The absolute value of the difference between the curvature at the current acquisition moment and the curvature at the immediately preceding acquisition moment is recorded as the curvature variation degree at the current acquisition moment.

[0073] The curvature variation degree is an evaluation of the discontinuity of the surface curvature change of the semi-finished position of the valve workpiece subjected to laser cladding at the corresponding acquisition moment. The more drastic the change in the surface curvature of the semi-finished position of the valve workpiece processed at the acquisition moment corresponding to the curvature variation degree, the greater the curvature variation degree.

[0074] The shape influence at the current acquisition moment is determined according to the curvature, curvature change and cumulative influence at the current acquisition moment.

[0075] Preferably, as an embodiment of the present application, the product of the curvature at the current acquisition moment and the curvature change degree is recorded as the shape influence coefficient at the current acquisition moment, and the normalized value of the product of the shape influence coefficient at the current acquisition moment and the cumulative influence degree is recorded as the shape influence degree at the current acquisition moment.

[0076] It should be noted that this embodiment uses the Z-Score standard normalization method to calculate the normalized value. In actual application, the implementer may use other methods in the prior art such as the maximum and minimum value normalization method, the sigmoid function, etc. to calculate the normalized value, which is not limited here.

[0077] The greater the curvature, curvature change and cumulative influence at the current acquisition moment, the greater the shape influence at the current acquisition moment. At this time, the possibility of material accumulation due to the accumulation of influence caused by distance changes and the change of curvature on the surface of the semi-finished valve workpiece during the cladding process is greater, and the possibility of affecting the cladding quality is greater.

[0078] At this point, the shape influence degree at the current acquisition time is obtained. The shape influence degree acquisition flow chart is as follows: Figure 2 shown.

[0079] Step S004, implementing quality control of laser surface treatment applicable to the valve workpiece according to the initial laser power and the shape influence degree at the current acquisition moment.

[0080] According to the initial laser power and the shape influence degree at the current acquisition moment, the target power at the next adjacent acquisition moment of the current acquisition moment is determined.

[0081] Preferably, as an embodiment of the present application, the sum of the shape influence degree at the current acquisition moment and the second parameter adjustment coefficient is recorded as the power adjustment coefficient at the current acquisition moment, and the product of the power adjustment coefficient at the current acquisition moment and the initial laser power is recorded as the target power at the next adjacent acquisition moment of the current acquisition moment.

[0082] Among them, the second tuning parameter coefficient is a preset parameter value. In this embodiment, the value of the second tuning parameter coefficient is 0.5, which is used to adjust the value of the target power. At the same time, it maintains the stability of the laser cladding process to avoid inconsistent quality of the cladding layer due to drastic fluctuations in laser power.

[0083] When the value of the shape influence degree at the current acquisition moment is greater than 0.5, the power adjustment coefficient at the current acquisition moment is greater than 1, and the laser power at the next adjacent acquisition moment of the current acquisition moment needs to be increased, and the target power at the next adjacent acquisition moment of the current acquisition moment is greater than the initial laser power; when the value of the shape influence degree at the current acquisition moment is less than 0.5, the power adjustment coefficient at the current acquisition moment is less than 1, and the laser power at the next adjacent acquisition moment of the current acquisition moment needs to be reduced, and the target power at the next adjacent acquisition moment of the current acquisition moment is less than the initial laser power; when the value of the shape influence degree at the current acquisition moment is equal to 0.5, the power adjustment coefficient at the current acquisition moment is equal to 1, and the laser power at the next adjacent acquisition moment of the current acquisition moment is equal to the initial laser power.

[0084] The target power at the next adjacent acquisition moment of the current acquisition moment is used as the laser power value at the next adjacent acquisition moment of the current acquisition moment, and the unit of the laser power remains unchanged, thereby improving the uniformity and quality of the cladding layer and avoiding cladding defects caused by the complex shape of the valve workpiece semi-finished product or the change of the laser distance data.

[0085] It should be noted that the laser power range is 1000-3000W. When the target power is less than 1000W, the target power value is assigned to 1000. When the target power is greater than 3000W, the target power value is assigned to 3000.

[0086] At this point, quality control of laser surface treatment applicable to valve workpieces is achieved.

[0087] Based on the same inventive concept as the above method, an embodiment of the present invention also provides a quality control system suitable for laser surface treatment of valve workpieces, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of any one of the above-mentioned quality control methods suitable for laser surface treatment of valve workpieces are implemented.

[0088] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A quality control method for laser surface treatment of valve workpieces, characterized in that: The method comprises the following steps: Collect the three-dimensional point cloud data of the semi-finished valve workpiece and extract the path point cloud data, set the initial laser power, and in the process of laser cladding the semi-finished valve workpiece, collect the distance data at the current collection time and the preset number of distances before, and obtain the distance sequence at the current collection time according to the distance data; According to the adjacent distance data of any distance data contained in the distance sequence at the current collection moment, a first difference of the any distance data is obtained; according to the values ​​of all distance data contained in the distance sequence at the current collection moment and the collection moment, a second difference at the current collection moment is determined; according to the second difference at the current collection moment, all distance data contained in the distance sequence at the current collection moment, and the first difference of the distance data, a cumulative influence degree at the current collection moment is determined; According to the path point cloud data, determine the curvature of each point in the path point cloud data and the curvature change degree at the current acquisition time, and determine the shape influence degree at the current acquisition time according to the curvature, curvature change degree and cumulative influence degree at the current acquisition time; According to the initial laser power and the shape influence at the current acquisition moment, quality control of laser surface treatment suitable for valve workpieces is achieved.

2. The quality control method for laser surface treatment of valve workpieces according to claim 1, characterized in that: The specific method for extracting path point cloud data is: A 3D scanner is used to perform a 3D scan on the semi-finished valve workpiece to obtain 3D point cloud data of the semi-finished valve workpiece, a 3D reconstruction algorithm is used on the 3D point cloud data to obtain a 3D model of the semi-finished valve workpiece, and a cladding path is generated using a 3D path planning algorithm based on ant colonies according to the 3D model and the process requirements of the cladding layer; The cladding path is matched with the three-dimensional point cloud data of the semi-finished valve workpiece, and the matching results of each point in the cladding path and the points in the three-dimensional point cloud data of the semi-finished valve workpiece are determined. According to the matching results, the point cloud data located on the cladding path in the three-dimensional point cloud data of the semi-finished valve workpiece is extracted, and the extracted point cloud data is recorded as path point cloud data.

3. The quality control method for laser surface treatment of valve workpieces according to claim 1, characterized in that: The specific method of obtaining the first difference of any distance data according to the adjacent distance data of any distance data included in the distance sequence at the current acquisition moment includes: Any distance data contained in the distance sequence at the current collection time is recorded as the target collection data; the collection time corresponding to the target collection data is recorded as the target collection time; Intercepting the distance data of the target acquisition moment and the first preset threshold number of consecutive acquisition moments before the target acquisition moment in the distance data sequence to obtain the distance sequence of the target acquisition moment; The standard deviation of all distance data contained in the distance sequence at the target acquisition time is recorded as the first difference at the target acquisition time.

4. The quality control method for laser surface treatment of valve workpieces according to claim 1, characterized in that: The method for determining the second difference at the current acquisition moment is: The absolute value of the difference between the distance data of the two collection times with the farthest collection time interval included in the distance sequence of the current collection time is recorded as the second difference of the current collection time.

5. The quality control method for laser surface treatment of valve workpieces according to claim 1, characterized in that: The method for determining the cumulative influence of the current collection moment is: In the formula, Indicates the cumulative impact at the current collection moment; Indicates the first difference at the current acquisition moment; Indicates the second difference of the current acquisition moment; Indicates the distance sequence at the current acquisition time. The first difference of distance data; represents a natural constant; represents the first tuning parameter coefficient; represents the softmax function; Indicates that in the distance sequence at the current acquisition time, the The number of distance data between the distance data and the distance data at the current collection moment; Indicates the number of distance data contained in the distance sequence at the current acquisition time.

6. The quality control method for laser surface treatment of valve workpieces according to claim 1, characterized in that: The method for obtaining the curvature of each point in the path point cloud data is: The path point cloud data is fitted with the least square method to obtain the surface where the path point cloud data is located. The surface where the path point cloud data is located is calculated using the three-point parameter equation method to obtain the curvature of each point in the path point cloud data.

7. The quality control method for laser surface treatment of valve workpieces according to claim 1, characterized in that: The method for obtaining the curvature change degree at the current acquisition moment is: The absolute value of the difference between the curvature at the current acquisition moment and the curvature at the immediately preceding acquisition moment is recorded as the curvature variation degree at the current acquisition moment.

8. The quality control method for laser surface treatment of valve workpieces according to claim 1, characterized in that: The method for obtaining the shape influence at the current acquisition moment is: The product of the curvature at the current acquisition moment and the curvature variation is recorded as the shape influence coefficient at the current acquisition moment, and the normalized value of the product of the shape influence coefficient at the current acquisition moment and the cumulative influence is recorded as the shape influence degree at the current acquisition moment.

9. The quality control method for laser surface treatment of valve workpieces according to claim 1, characterized in that: The method of implementing quality control of laser surface treatment for valve workpieces according to the initial laser power and the shape influence at the current acquisition moment includes the following specific methods: The sum of the shape influence degree at the current acquisition moment and the second parameter adjustment coefficient is recorded as the power adjustment coefficient at the current acquisition moment, and the product of the power adjustment coefficient at the current acquisition moment and the initial laser power is recorded as the target power at the next adjacent acquisition moment of the current acquisition moment; The target power at the next adjacent acquisition moment of the current acquisition moment is used as the laser power value at the next adjacent acquisition moment of the current acquisition moment, so as to realize the quality control of the laser surface treatment suitable for the valve workpiece.

10. A quality control system for laser surface treatment of valve workpieces, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

Images