Grinding quality real-time evaluation and adjustment system for speed reducer gear

Abstract

The invention discloses a real-time evaluation and adjustment system for the grinding quality of a speed reducer gear, and relates to the technical field of evaluation and adjustment of the grinding quality of the speed reducer gear, an industrial camera is combined with an infrared light curtain for surveying and mapping, firstly, the geometric center of the gear is determined, and a gear tooth image is segmented; the pixel deviation ratio and the angle deviation ratio are analyzed, and a polishing quality index is generated; meanwhile, a grinding machine tool model is built through the digital twinning technology, and an optimal grinding parameter combination is recognized in combination with a good and bad index algorithm; the system adjusts other machine tools according to the parameters, and it is ensured that the grinding quality of all the machine tools is consistent and continuously optimized; in the whole process, closed-loop control from image acquisition to quality evaluation to parameter adjustment is achieved, and the grinding precision and efficiency of the gear of the speed reducer are effectively improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of evaluating and adjusting the grinding quality of a reducer gear, in particular to a real-time evaluation and adjustment system for the grinding quality of a reducer gear. BACKGROUND

[0002] With the global economy transforming into high-end manufacturing, the demand for precision machining technology is increasing; as a core component in mechanical transmission systems, reducer gears play a crucial role in key fields such as automobiles, aerospace, and industrial automation.

[0003] In the prior art, the evaluation and regulation of the grinding quality of reducer gears usually rely on discrete, post-detection means and isolated machine parameter management; first, in the image acquisition link, the traditional method often uses a fixed-position industrial camera for shooting, lacks an active positioning and calibration mechanism, and cannot accurately determine the geometric center of the gear, leading to image reference drift and subsequent analysis prone to errors; at the same time, two-dimensional images lack the auxiliary mapping of three-dimensional profile information, making it difficult to accurately segment the single gear region, especially for complex structure gears, the segmentation accuracy is limited; secondly, in the quality evaluation level, the existing technology relies on manual sampling or simple image comparison, which is not only inefficient, but also subjective, and cannot real-time and quantitatively evaluate key indicators such as inter-tooth volume uniformity and graduation accuracy, defect detection is lagging, and it is impossible to form a continuous quality index to support online decision-making; in addition, for the coordinated management of multiple grinding machines, the existing technology can only adjust parameters based on single machine historical data or experience, and cannot real-time correlate processing parameters, environmental parameters and final grinding quality across machines, leading to isolated and lagging optimization and adjustment, making it difficult to achieve quality consistency and efficiency optimization of the overall production line.

[0004] To solve the above problems, the application provides a real-time evaluation and adjustment system for the grinding quality of a reducer gear. SUMMARY

[0005] In view of the deficiencies of the prior art, the application provides a real-time evaluation and adjustment system for the grinding quality of a reducer gear, which solves the problems of quality evaluation lag and isolated equipment regulation in the prior art of evaluating and adjusting the grinding quality of a reducer gear.

[0006] The purpose of the application can be achieved by the following technical solutions: A real-time evaluation and adjustment system for the grinding quality of a reducer gear, the system comprising: The reducer gear image acquisition module acquires the reducer gear image through an industrial camera, and determines the geometric center of the reducer gear by combining the pre-constructed infrared light curtain. The reducer gear polishing quality evaluation module segments the reducer gear image after mapping the geometric center, determines a plurality of tooth images associated with the reducer gear, and evaluates the polishing quality of the corresponding reducer gear by performing correlation analysis on all tooth images. The polishing machine digital twin construction module acquires all polishing machines and extracts the machining parameter group and the environment parameter group associated with all polishing machines to construct the polishing machine digital twin model associated with all polishing machines. The polishing quality of the reducer gear polished by any one polishing machine is bound to the polishing machine digital twin model associated with the corresponding polishing machine to construct the polishing processing feature. The polishing machine machining parameter adjustment module performs correlation analysis based on the determined plurality of polishing processing features, evaluates the polishing machine digital twin model associated with the optimal polishing quality, and acquires the machining parameter group and the environment parameter group associated with the polishing machine digital twin model to combine as the optimal adjustment parameter set. The polishing machine digital twin model associated with the remaining polishing machines is adjusted, and the adjustment result is output by each polishing machine digital twin model. The remaining polishing machines are adjusted based on the adjustment result.

[0007] As a further scheme of the present application, in the reducer gear image acquisition module, the specific way to acquire the reducer gear image is: Take any reducer gear A; Place A on the industrial shooting table and use the industrial camera to take a picture to acquire the reducer gear image G_A of A; The industrial shooting table includes a built-in three-axis MEMS gravity sensor for bearing the reducer gear, and the object carrier has a horizontal calculation function to determine the inclination of the object carrier in the horizontal plane and output the normal vector n of the object carrier; When the object carrier detects A, it sends a detection start signal to the infrared light curtain; The infrared light curtain is four beams of infrared fan-shaped light curtains, which simultaneously scan the tooth profile outer edge of A to obtain four polar coordinate sets {P1, P2, P3, P4} of the addendum circle of A in the light curtain coordinate system; Determine the geometric center Q1 of the addendum circle based on {P1, P2, P3, P4}, and send an adjustment signal to the industrial camera; The industrial camera adjusts the optical axis direction to coincide with the normal vector n, vertically ascends along the Z axis, and performs a shooting operation when the pixel distance between the projection point of the geometric center Q1 on the imaging target surface of the industrial camera and the physical center of the target surface is less than a preset pixel distance threshold.

[0008] As a further scheme of the present application, in the reducer gear polishing quality evaluation module, the specific way of determining the plurality of tooth images of the reducer gear associated with the reducer gear is: The three-dimensional point cloud data of the reducer gear A measured by the infrared light curtain is projected to the imaging plane of the industrial camera by using a preset spatial mapping matrix to determine the reducer gear pixel image G_A` of A in G_A; The geometric center Q1 is determined in G_A`, and an outward expanding circle U is formed with Q1 as the center and a pixel point as the step length for increasing the radius until U reaches the maximum state in G_A`, wherein the pixel points in U belong to G_A`; The U is cropped from G_A` and removed to obtain a remaining pixel region; The remaining pixel region contains a plurality of closed regions, and the total number of closed regions is counted and denoted as j; The j closed regions are the tooth images of the j teeth on A; The tooth image directly above the remaining pixel region is denoted as TG1, and the j tooth images are arranged in a clockwise order to obtain a tooth image sequence TG1, TG2,..., TGj.

[0009] As a further scheme of the present application, in the reducer gear polishing quality evaluation module, the specific way of evaluating the polishing quality of the corresponding reducer gear includes: The tooth image sequence TG1, TG2,..., TGj is taken; The total number of pixel points in each tooth image in TG1, TG2,..., TGj is counted and denoted as a pixel point total sequence SUM1, SUM2,..., SUMj in the order of TG1, TG2,..., TGj; The average value of the j pixel point totals in SUM1, SUM2,..., SUMj is taken to obtain a pixel point total average SUM_avg; The pixel point total SUMi of any tooth image TGi is taken, the absolute value of the difference between SUMi and SUM_avg is calculated, and the absolute value is divided by SUM_avg and multiplied by 100% to obtain the pixel deviation rate δ of SUMi, wherein i is a count index, 1≤i≤j; The δ is compared with a preset pixel deviation rate threshold δ_yu; If δ≥δ_yu, it is determined that the reducer gear A has a tooth volume difference defect, and the first type of defect flag F1 is incremented by one, wherein the initial value of F1 is 0; Conversely, no processing is done. Similarly, j tooth images in TG1, TG2,..., TGj are processed, and the first type of defect flag F1 is updated.

[0010] As a further scheme of the present application, the specific way of evaluating the polishing quality of the corresponding reducer gear in the reducer gear polishing quality evaluation module further comprises: Take the tooth image sequence TG1, TG2,..., TGj; Determine the j tooth geometrical centers of the j tooth images, and obtain j tooth geometries; Map the j tooth geometrical centers to the reducer gear pixel image G_A` and label them; Get the geometrical center Q1 of G_A` and label it; Respectively, take the j tooth geometrical centers as the starting point, and the geometrical center Q1 as the end point to connect, and obtain j lines; The j lines and the geometrical center Q1 form j angles; Divide the angle by j to get the reference angle value; Get the angle value of any one of the j angles, calculate the absolute value of the difference between the angle value and the reference angle value, divide by the reference angle value, and multiply by 100% to get the angle value difference rate between the angle value and the reference angle value; If the angle value difference rate is greater than or equal to the preset angle value difference rate threshold, it is determined that the reducer gear A has a graduation uneven defect, and the second type of defect flag F2 is incremented by one, wherein the initial value of F2 is 0; Conversely, no processing is done; Similarly, the angle values of the j angles are processed, and F2 is updated; Take F1 and F2, and calculate the polishing quality index E of A using E=w1*F1+w2*F2, wherein w1 and w2 are preset calculation weights, w1 and w2 are greater than 0, and w1+w2=1; If E is less than the preset polishing quality index threshold E_yu, the reducer gear A is qualified, otherwise, A is unqualified.

[0011] As a further scheme of the present application, the specific way of constructing all the polishing machine tool digital twin models in the polishing machine tool digital twin construction module is: Get all the polishing machine tools, and count the total number as u; Arrange the u polishing machine tools in the order of acquisition as a polishing machine tool sequence MT1, MT2,..., MTu; Get the environmental parameters of each polishing machine tool processing the reducer gear, and combine them as an environmental parameter group; Get the processing parameters predefined by the operator for each polishing machine tool, and combine them as a processing parameter group; constructing a digital twin model of each of the u grinding machines based on digital twin technology, and performing parameter injection on the digital twin model of each grinding machine based on the machining parameters and environmental parameters of the grinding machine; obtaining a sequence of digital twin models of grinding machines PMT1, PMT2,..., PMTu.

[0012] As a further scheme of the present application, in the grinding machine digital twin construction module, the specific way of constructing the grinding processing feature is: obtaining any one of the grinding machines MTo in the sequence of grinding machines MT1, MT2,..., MTu and the corresponding digital twin model PMTo of the grinding machine, wherein o is a count index, 1≤o≤u; taking the total number of grinding H preset by the operator; determining the total number of qualified Cout1, the total number of unqualified Cout2 and the average grinding quality index E_avg of the grinding quality index E of the H reduction machine gears that are ground by the grinding machine MTo closest to the current time, and recording the average grinding quality index E_avg as the grinding processing feature PPFo; binding E_avg, Cout1 and Cout2 with PMTo as the grinding processing feature PPFo; Similarly, the grinding machines in the sequence of grinding machines MT1, MT2,..., MTu are processed synchronously, u grinding processing features are determined, and the sequence of grinding processing features PPF1, PPF2,..., PPFu is recorded in the order of MT1, MT2,..., MTu.

[0013] As a further scheme of the present application, in the grinding machine processing parameter adjustment module, the specific way of evaluating the digital twin model of the grinding machine associated with the optimal grinding quality is: taking the sequence of grinding processing features PPF1, PPF2,..., PPFu; extracting the average grinding quality index E_avg, the total number of qualified Cout1 and the total number of unqualified Cout2 in any one of the grinding processing features PPFo; calculating the grinding machine merit index YL of PPFo using YL=(Cout1–Cout2) / (Cout1+Cout2)-λ*E_avg, wherein λ is a dimensionless scaling constant; Similarly, the grinding machine merit indexes of the grinding processing features in PPF1, PPF2,..., PPFu are determined; arranging PPF1, PPF2,..., PPFu in descending order according to the grinding machine merit indexes to obtain the sequence of grinding processing features PPF1`, PPF2`,..., PPFu`; Take the first polishing processing feature PPF1` in PPF1`, PPF2`,..., PPFu` and its associated polishing machine digital twin model PMT1`; The polishing machine digital twin model PMT1` is the polishing machine digital twin model associated with the optimal polishing quality.

[0014] As a further scheme of the present application, in the polishing machine processing parameter adjustment module, the specific way of determining the dimensionless scaling constant λ is: The operator pre-acquires k full qualified-zero defect reduction gear and k full unqualified-high defect reduction gear as limit samples, k is a preset value; Full qualified-zero defect corresponds to Cout2=0 and E_avg=0, let λ be 1; Full unqualified-high defect corresponds to Cout1=0 and E_avg=E_max, let λ be-1; In summary, solve λ, λ∈[-1,1]; λ is a fixed value and no longer changes.

[0015] As a further scheme of the present application, in the polishing machine processing parameter adjustment module, the specific way of adjusting the remaining polishing machine based on the adjustment result is: Get the processing parameter set and the environment parameter set of the polishing machine digital twin model PMT1` with the optimal polishing quality, and combine them as the optimal adjustment parameter set; Take u-1 polishing machine digital twin models from the u polishing machine digital twin models except PMT1`; Adjust the processing parameter set and the environment parameter set of the u-1 polishing machine digital twin models to the processing parameter set and the environment parameter set in the optimal adjustment parameter set; Continuously monitor the adjustment result output by the u-1 polishing machine digital twin models after polishing H reduction gears, and the adjustment result is the average polishing quality index; If the average polishing quality index output by any polishing machine digital twin model is better than the current average polishing quality index of the corresponding polishing machine, adjust and control the corresponding polishing machine according to the optimal adjustment parameter set; Otherwise, do nothing.

[0016] The present application has the following advantages: (1) The present application realizes high-precision positioning and adaptive shooting control of the gear of a speed reducer by integrating a built-in three-axis MEMS gravity sensor carrier and four infrared fan-shaped light curtains; real-time monitoring of the inclination of the carrier and automatic calibration of the optical axis direction of the industrial camera ensure that image acquisition is always perpendicular to the gear plane, effectively avoiding image distortion and measurement errors caused by tilting; at the same time, the infrared light curtain non-contact scans the tooth profile and quickly calculates the geometric center of the addendum circle to guide the camera to accurately center, thereby improving image consistency and detection reliability, and providing a complete structure and a standard position high-quality image basis for subsequent gear quality analysis; (2) The present application accurately positions the independent image area of each tooth by using the tooth profile data obtained by the infrared light curtain, and effectively identifies the tooth shape volume difference defects caused by uneven polishing by calculating the total pixel deviation rate; at the same time, by analyzing the uniformity of the angle between the geometric center of each tooth and the overall center of the gear, the division accuracy defects can be reliably detected; this dual-index fusion evaluation strategy (tooth shape consistency + division uniformity) significantly improves the comprehensiveness and accuracy of quality determination, avoids human subjective errors, and improves detection efficiency and objectivity based on automatic processing of image and geometric data; (3) The present application realizes precise digital mapping of the production process by constructing a digital twin model that is in real-time linkage with the physical polishing machine tool and injecting processing and environmental parameters; then, by collecting and analyzing the quality data of multiple gears polished by the machine tool in the near future, polishing processing features reflecting the comprehensive processing state are automatically generated; this feature binding method based on historical performance data can objectively and quantitatively evaluate the stability and processing capacity of each machine tool; (4) The present application automatically identifies the polishing machine tool with the best processing quality in the current production system and its digital twin model by defining a machine tool performance automatic sorting mechanism based on the polishing machine tool merit index; the machine tool merit is objectively evaluated by innovatively using the comprehensive calculation of the pass rate and the average quality index, and the key parameter λ is pre-calibrated based on the limit sample to ensure the rationality and stability of the evaluation algorithm; then, by synchronizing the processing and environmental parameters of the optimal machine tool to the digital twin models of other machine tools and tracking and dynamically adjusting the effect, the production parameter cluster optimization and self-iteration are realized, thereby improving the polishing quality consistency, equipment comprehensive efficiency and intelligent management level of the entire production line. BRIEF DESCRIPTION OF DRAWINGS

[0017] The present application will be further described below with reference to the accompanying drawings.

[0018] Figure 1 is a structural schematic diagram of the system described in the present application; Figure 2 is a flowchart of the method described in embodiment 2 of the present application; Figure 3This is a flowchart illustrating the method described in Embodiment 3 of the present invention; Figure 4 This is a flowchart illustrating the method described in Embodiment 4 of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Example 1 A real-time evaluation and adjustment system for grinding quality of gear reducer gears, such as... Figure 1 As shown, this system includes the following: This system is mainly implemented by combining four modules: a reducer gear image acquisition module, a reducer gear grinding quality assessment module, a grinding machine tool digital twin construction module, and a grinding machine tool processing parameter adjustment module. The reducer gear image acquisition module uses an industrial camera to capture real-time images of the reducer gear after the grinding operation, and combines this with a pre-constructed infrared light curtain to map the reducer gear, determine the geometric center of the reducer gear, and map the geometric center onto the reducer gear image to obtain the reducer gear image. Specifically, firstly, any gear reducer that has undergone grinding is obtained, denoted as A. It should be noted that the gear reducer needs to be screened for faults before grinding to ensure that only non-faulty gear reducers are ground. The subsequent grinding quality is then evaluated and adjusted in real time. If any gear reducer has a fault, it is discarded and does not proceed to the grinding operation or subsequent processes.

[0021] Next, place reducer gear A on the pre-built industrial camera stand and use an industrial camera to take a picture of reducer gear A. This will give you an image of the reducer gear associated with reducer gear A, denoted as G_A. The industrial camera platform mentioned above consists of a tray with a built-in three-axis MEMS gravity sensor, an infrared light curtain, and an industrial camera. The built-in triaxial MEMS gravity sensor can determine whether the reducer gear is placed on the disk. The disk also has a level measurement function, which can output the tilt angle of the disk in the horizontal plane in real time and determine the normal vector n associated with the disk at the current position.

[0022] If the carrier disc detects that the reducer gear A is placed in it, a detection start signal will be generated and transmitted to the infrared light curtain; The infrared light curtain is four infrared fan-shaped light curtains, and after the infrared light curtain receives the detection start signal, it will control the four infrared fan-shaped light curtains to scan the tooth profile of the reducer gear A at the same time; Based on the scanning results of the four infrared fan-shaped light curtains, four sets of polar coordinates of the addendum circle of the reducer gear A in the light curtain coordinate system (formed by the four infrared fan-shaped light curtains after scanning) can be obtained, which are sequentially recorded as {P1, P2, P3, P4}.

[0023] Based on the four sets of polar coordinates determined, a closed circle is fitted, the center of the closed circle is determined based on the fitted closed circle, and the center is taken as the geometric center of the addendum circle associated with the reducer gear A, and is recorded as Q1.

[0024] At this point, the infrared light curtain determines the geometric center Q1 of the reducer gear A, generates an adjustment signal from the infrared light curtain, and transmits it to the industrial camera; After the industrial camera receives the adjustment signal, it will first adjust the optical axis direction of the industrial camera to coincide with the normal vector n determined by the carrier disc, ensuring that the carrier disc (i.e. the reducer gear) is shot directly.

[0025] Then, after the optical axis direction is adjusted to coincide with the normal vector n determined by the carrier disc, the industrial camera is operated vertically along the Z-axis until the pixel distance between the projection point of the geometric center Q1 on the imaging target surface of the industrial camera and the physical center of the target surface is less than the pixel distance threshold preset by the operator (this step is a focusing process for the industrial camera to achieve clear shooting), and the shooting operation is performed to obtain the reducer gear image.

[0026] The reducer gear grinding quality evaluation module segments the reducer gear image after mapping the geometric center, determines the associated tooth images of the reducer gear, and performs correlation analysis on all tooth images to evaluate the grinding quality of the corresponding reducer gear; Specifically, this module is a complete step from "one whole image" to "full-tooth defect quantification" of the reducer gear image. The purpose of segmenting the reducer gear image to obtain all tooth images on the reducer gear is to analyze each tooth on the reducer gear. Based on the analysis results of the teeth on the reducer gear, the grinding quality of the reducer gear is comprehensively evaluated.

[0027] The polishing machine digital twin construction module acquires all polishing machines and extracts all polishing machine associated machining parameter groups and environment parameter groups to construct all polishing machine associated polishing machine digital twin models; The polishing quality of any one polishing machine polished reduction gear is bound to the polishing machine digital twin model associated with the corresponding polishing machine to construct the polishing processing feature; Specifically, the method of extracting machining parameter groups and environment parameter groups from all polishing machines to construct all polishing machine associated polishing machine digital twin models can avoid the trial and error cost caused by polishing machine parameter adjustment; It should be noted that the machining parameter group includes machine tool motion parameters such as grinding wheel spindle speed and workpiece spindle speed; grinding process parameters such as single grinding depth and grinding method; The environment parameter group includes temperature, humidity, air cleanliness, and wind speed; Then, the polishing quality of any one polishing machine polished reduction gear is bound to the polishing machine digital twin model associated with the polishing machine to construct the polishing processing feature. The polishing machine digital twin model is bound to the actual polishing quality using the solidified polishing processing feature. By doing so, the machining parameter group and the environment parameter group of the physical polishing machine are also bound to the polishing quality.

[0028] The polishing machine processing parameter adjustment module first performs correlation analysis according to the above determined several groups of polishing processing features, and evaluates the optimal polishing quality and the polishing machine digital twin model associated with the optimal polishing quality through correlation analysis; Then, the machining parameter group and the environment parameter group associated with the polishing machine digital twin model associated with the optimal polishing quality are obtained; The obtained machining parameter group and environment parameter group are combined, and the combined result is recorded as the optimal adjustment parameter set. The optimal adjustment parameter set is used to adjust the polishing machine digital twin model associated with the remaining polishing machines (that is, to use the polishing machine digital twin model to try and error). Each polishing machine digital twin model outputs an adjustment result, and the remaining polishing machines (the machining parameter group and the environment parameter group of the actual polishing machine) are adjusted based on the adjustment result.

[0029] This embodiment binds the "quality-working condition" of a single gear to the machine tool virtual model through industrial vision, infrared mapping, and digital twin cooperation, forms reusable polishing processing features, and then uses these features to quickly try and error in the twin body, reversely outputs the optimal parameter set, and batch calibrates the remaining machines, thereby realizing "one-time yield replication" under the premise of zero physical trial and error, and finally stabilizing the reduction gear polishing quality in the optimal interval and reducing the scrap rate and parameter adjustment cost.

[0030] Example 2 This embodiment further discloses a method for evaluating the grinding quality of reducer gears based on Embodiment 1, such as... Figure 2 As shown, it specifically includes the following: Based on the content described in Example 1, it is known that the infrared light curtain performed a mapping operation on the reducer gear A, thus obtaining the three-dimensional point cloud data associated with the reducer gear A. The determined three-dimensional point cloud data is then projected onto the imaging plane of the industrial camera (that is, the reducer gear image G_A captured by the industrial camera) through a spatial mapping matrix preset by the operator (which is actually a transformation matrix between three-dimensional and two-dimensional coordinates, converting 3D points in the world coordinate system into 2D pixel coordinates on the camera imaging plane; this is existing technology and will not be elaborated on in this solution). The two-dimensional pixel area in the reducer gear image G_A is further determined to obtain the reducer gear pixel image, denoted as G_A`. The purpose of this step is to separate the part that is only the pixels of the reducer gear A from the reducer gear image G_A and remove the background pixels.

[0031] Next, determine the geometric center Q1 in the reducer gear pixel image G_A`, that is, the geometric center Q1 in the reducer gear image G_A, and use the determined geometric center Q1 as the center to draw an outer circle U; It is important to note that the radius of the outer circle U increases in increments of one pixel. The system continuously checks whether all pixels covered by the outer circle U are contained within the pixel image G_A' of the reducer gear. When increasing the radius by another pixel causes the outer circle U to touch pixels outside the G_A' area, the outer circle U at this point is an approximation of the maximum inscribed circle of the reducer gear A. At this point, the outer circle U covers the central body of the gear (spokes / core) to the maximum extent, but does not contain any teeth.

[0032] Next, the outer circle U is cropped and removed from the reducer gear pixel image G_A`, leaving only the remaining pixel area with the gear teeth; Each tooth's pixel area is a closed region. The total number of all closed regions in the remaining pixel areas is counted and denoted as j. The total number of closed regions j is also the total number of teeth on gear A of the reducer. Each closed region is a tooth image, so j tooth images can be obtained in the end.

[0033] Then, the first tooth image directly above the remaining pixel area is denoted as TG1, and the subsequent tooth images are recorded and sorted in clockwise order to obtain the tooth image sequence, represented as: TG1, TG2, ..., TGj.

[0034] Then, the total pixel points of each gear tooth image in the gear tooth image sequence TG1, TG2,..., TGj are calculated, so that j total pixel points associated with the j gear tooth images are obtained, and the j total pixel points are recorded in the order of the gear tooth image sequence TG1, TG2,..., TGj as a total pixel point sequence, denoted as: SUM1, SUM2,..., SUMj.

[0035] Then, the j total pixel points are extracted again, and the average value is calculated, and the obtained average value is recorded as the total pixel point average value, denoted as: SUM_avg.

[0036] Then, an example processing is performed on any one gear tooth image TGi from the gear tooth image sequence TG1, TG2,..., TGj, and the remaining gear tooth images are processed in the same way as the gear tooth image TGi, where i is a count index, and the value range is 1 to j; The pixel deviation rate δ between the total pixel point SUMi and the total pixel point average value SUM_avg is calculated by using |SUMi-SUM_avg| / SUM_avg*100%=δ; The calculated pixel deviation rate δ is compared with the pixel deviation rate threshold δ_yu preset by the operator: If there is a pixel deviation rate δ greater than or equal to the pixel deviation rate threshold δ_yu, it is determined that the gear A of the speed reducer has an inter-tooth volume difference defect, and the first type of defect flag F1 is incremented by one, and the first type of defect refers to the inter-tooth volume difference defect, where the initial value of the first type of defect flag F1 is 0; If there is a pixel deviation rate δ less than the pixel deviation rate threshold δ_yu, no processing is performed, and the other gear tooth images are traversed, and the same processing is performed on all the gear tooth images in the gear tooth image sequence TG1, TG2,..., TGj, and the first type of defect flag F1 is updated after the processing is completed.

[0037] Then, the j gear tooth geometric centers of the j gear tooth images in the gear tooth image sequence TG1, TG2,..., TGj are determined, and a total of j gear tooth geometric centers are obtained, and the obtained j gear tooth geometric centers are recorded in the order of the gear tooth image sequence TG1, TG2,..., TGj as a gear tooth geometric center sequence, denoted as: GC1, GC2,..., GCj.

[0038] Then, the j gear tooth geometric centers in the gear tooth geometric center sequence GC1, GC2,..., GCj are mapped to the speed reducer gear pixel image G_A` and labeled; The geometric center Q1 of the speed reducer gear pixel image G_A` is determined and labeled; At this time, j+1 points marked in the reducer gear pixel image G_A` can be obtained, that is, j gear geometric centers and 1 geometric center Q1.

[0039] The j gear geometric centers in the gear geometric center sequence GC1, GC2,..., GCj are taken as starting points respectively, and the geometric center Q1 is taken as an ending point. The j lines are finally obtained by connecting the starting points to the ending points in the direction from the starting points to the ending points.

[0040] At this time, the j lines and the geometric center Q1 will form j angles. The reference angle value is obtained by dividing the circumferential angle (360 degrees) by j. If each gear is standard, the angle values of the j angles obtained will be close to the reference angle value, otherwise it indicates that the gears are not standard. Then, the angle value of any one of the j angles is obtained, and the angle value difference rate calculation is performed between the angle value and the reference angle value. The calculation steps are as follows: First, the absolute value of the difference between the angle value and the reference angle value is calculated, and then the absolute value of the difference is divided by the reference angle value and multiplied by 100%. The final value obtained is the angle value difference rate between the angle value of the angle and the reference angle value.

[0041] The angle value difference rate threshold value set by the operator in combination with the actual situation is obtained, and the calculated angle value difference rate is compared with the angle value difference rate threshold value set by the operator: If the angle value difference rate is greater than or equal to the angle value difference rate threshold value, it indicates that the reducer gear A has a division uneven defect, and the second type of defect flag F2 is incremented by one. The second type of defect refers to the division uneven defect, and the initial value of the second type of defect flag F2 is 0.

[0042] If the angle value difference rate is less than the angle value difference rate threshold value, no processing is performed, and the other angles and angle values are iterated to calculate the angle value difference rates associated with the angle values of the other angles until all the angle values of the angles are processed, and the second type of defect flag F2 is updated.

[0043] At this time, the first type of defect flag F1 and the second type of defect flag F2 can be obtained (it should be noted that the first type of defect flag F1 and the second type of defect flag F2 have no dimension concept, and are only numerical values). The polishing quality index E associated with the reducer gear A is calculated by E=w1*F1+w2*F2, wherein the calculation weights w1 and w2 are obtained by the operator, and the calculation weights w1 and w2 satisfy w1, w2>0 and w1+w2=1.

[0044] Then, the polishing quality index E is determined again. If the polishing quality index E is less than the polishing quality index threshold E yu preset by the operator, it is determined that the speed reducer gear A is qualified (the smaller the polishing quality index E is, the smaller the defect is, and vice versa).

[0045] If the polishing quality index E is greater than or equal to the polishing quality index threshold E yu preset by the operator, it is determined that the speed reducer gear A is unqualified.

[0046] It should be noted that although the embodiment is to determine the qualification of the speed reducer gear by counting the defects, it has been clearly pointed out in embodiment 1 that the qualified speed reducer gear with obvious faults will be invalidated, so the embodiment mainly deals with the speed reducer gears without obvious faults or the speed reducer gears that cannot be identified by artificial means, so there is no case in which a speed reducer gear is invalidated due to a significant fault in this step.

[0047] In this embodiment, three-dimensional point cloud data of the speed reducer gear is collected by an infrared curtain and an industrial camera, and is projected onto a two-dimensional image plane to separate the gear pixel area to remove background interference. Based on the gear pixel image, the number of teeth is accurately identified and counted by geometric center determination, outer expansion circle operation and tooth pixel area clipping, and the total number of pixel points of each tooth and the deviation rate from the average value are calculated to determine the inter-tooth volume difference defect. In addition, the angle between the tooth geometric center and the gear geometric center is analyzed to evaluate the division uniformity and determine the division unevenness defect. Finally, the polishing quality index is calculated by using a weighted formula combining the two types of defect markers, to realize automatic quantitative evaluation of the polishing quality of the speed reducer gear and quickly determine whether the gear is qualified.

[0048] Embodiment 3 This embodiment further discloses a method for constructing a digital twin model of a polishing machine tool and a polishing processing feature based on embodiment 2, as shown in Figure 3 which specifically comprises the following steps: First, all the polishing machine tools are obtained, and the total number is counted as u. It should be noted that the polishing machine tools are polishing machine tools for processing the same type of speed reducer gear, and need to meet the same model, otherwise they are not comparable.

[0049] The obtained u polishing machine tools are recorded in the order of acquisition as a polishing machine tool sequence, denoted as MT1, MT2,..., MTu. According to the content described in embodiment 1, the environmental parameters associated with the processing of the speed reducer gear by each of the u polishing machine tools in the polishing machine tool sequence MT1, MT2,..., MTu are extracted in real time, and are combined as an environmental parameter group. Similarly, real-time extraction of the machining parameters associated with each of the u grinding machines in the grinding machine sequence MT1, MT2,..., MTu when machining the gear of the speed reducer is combined to form a machining parameter group.

[0050] Based on the digital twin technology, a grinding machine digital twin model associated with each of the u grinding machines is constructed (at this time, the grinding machine digital twin model constructed does not have simulation capability), and the machining parameter group and the environment parameter group obtained in the above steps are injected into the grinding machine digital twin model associated with each grinding machine, that is, the grinding machine digital twin model is matched with the actual grinding machine.

[0051] Finally, the u injected grinding machine digital twin models are obtained, and the u grinding machine digital twin models are sorted according to the order of the grinding machine sequence MT1, MT2,..., MTu, and the sorted result is recorded as the grinding machine digital twin model sequence, denoted as: PMT1, PMT2,..., PMTu.

[0052] Then, any grinding machine MTo in the grinding machine sequence MT1, MT2,..., MTu is extracted, and the grinding machine digital twin model PMTo associated with the grinding machine MTo is obtained, where o is a count index, and the value range is 1 to u.

[0053] The total number of polishing H preset by the operator is obtained; Next, the polishing quality of the H gears of the speed reducer polished by the grinding machine MTo closest to the current time in the past is determined as the end time, and the total number of qualified gears Cout1, the total number of unqualified gears Cout2, and the polishing quality index E associated with each of the H gears of the speed reducer are determined. And calculate the average of the H polishing quality indexes E, denoted as the average polishing quality index E_avg.

[0054] Next, the determined average polishing quality index E_avg, the total number of qualified gears Cout1, and the total number of unqualified gears Cout2 are combined and bound with the grinding machine digital twin model PMTo, and the combined and bound result is used as a polishing processing feature, denoted as PPFo.

[0055] Similarly, the polishing processing features associated with each of the u grinding machines in the grinding machine sequence MT1, MT2,..., MTu are determined, and a total of u polishing processing features are obtained. The u polishing processing features are recorded as a polishing processing feature sequence according to the order of the grinding machine sequence MT1, MT2,..., MTu, and denoted as: PPF1, PPF2,..., PPFu.

[0056] Example 4 This embodiment continues to disclose a method for adjusting a grinding machine based on embodiment 3, as shown, specifically including the following: Figure 4 Based on the content described in embodiment 3, the grinding machine sequence MT1, MT2,..., MTu and the grinding process feature sequence PPF1, PPF2,..., PPFu associated with the grinding machine digital twin model sequence PMT1, PMT2,..., PMTu can be obtained; From the grinding process feature sequence PPF1, PPF2,..., PPFu, any grinding process feature PPFo is extracted, and the average grinding quality index E_avg, the total number of qualified Cout1, and the total number of unqualified Cout2 in the grinding process feature PPFo are further determined. According to the formula:

[0057] YL=(Cout1–Cout2) / (Cout1+Cout2)-λ*E_avg The grinding machine merit index YL associated with the grinding process feature PPFo is calculated, where λ is a dimensionless scaling constant; The determination method of the dimensionless scaling constant λ includes the following steps: First, the operator needs to pre-obtain k full-qualified zero-defect reduction machine gears and k full-unqualified high-defect reduction machine gears as limit samples, where the value of k is determined by the operator in combination with the actual situation; Based on the determined limit samples, when the full-qualified zero-defect is obtained, Cout2=0 and E_avg=0, and at this time, λ is set to 1; When the full-unqualified high-defect is obtained, Cout1=0 and E_avg=E_max, and at this time, λ is set to -1; In summary, λ can be solved, and λ∈[-1,1], the dimensionless scaling constant λ is a fixed value and will not change, and λ*E_avg will eliminate the dimension of E_avg itself to obtain a numerical value part; Here it needs to be explained that the purpose of determining the dimensionless scaling constant λ is to balance the qualified proportion and the grinding quality index E_avg when calculating the merit index YL, which are data of different dimensions, eliminate the dimensional difference between them, ensure that the weights in the formula are reasonable, and accurately reflect the merit degree of the machine tool. By limiting the dimensionless scaling constant λ in the interval [-1, 1], it can adapt to the two extreme cases of full-qualified and full-unqualified, ensure that the formula can reasonably output under various quality scenarios, and avoid logical contradictions or misjudgments.

[0058] ​The remaining u-1 polishing processing features in the polishing processing feature sequence PPF1, PPF2,..., PPFu are processed in the same way according to the method of determining the polishing machine bed merit index YL associated with the polishing processing feature PPFo, and finally the polishing machine bed merit indexes associated with the u polishing processing features are obtained. Then, the polishing processing feature sequence PPF1, PPF2,..., PPFu is reordered according to the polishing machine bed merit index from large to small corresponding to each polishing processing feature, and the reordered polishing processing feature sequence is obtained, denoted as PPF1`, PPF2`,..., PPFu`.

[0059] The first polishing processing feature PPF1` and its associated polishing machine bed digital twin model PMT1` and polishing machine MT1` in the polishing processing feature sequence PPF1`, PPF2`,..., PPFu` are extracted. At this time, the extracted polishing machine bed digital twin model PMT1` is the polishing machine bed digital twin model associated with the optimal polishing quality, and the polishing machine MT1` is the polishing machine associated with the optimal polishing quality.

[0060] Next, the polishing machine bed digital twin model PMT1` associated with the optimal polishing quality and its associated processing parameter set and environmental parameter set are obtained, and the obtained processing parameter set and environmental parameter set are combined again, and the combined result is recorded as the optimal adjustment parameter set.

[0061] The u-1 polishing machine bed digital twin models other than the polishing machine bed digital twin model PMT1` among the u polishing machine bed digital twin models, that is, the polishing machine bed digital twin models with the second best polishing quality, are obtained.

[0062] The processing parameter set and environmental parameter set of the u-1 polishing machine bed digital twin models are adjusted to the processing parameter set and environmental parameter set in the optimal adjustment parameter set, and the adjustment result (here, the adjustment result is the polishing quality index of polishing H reduction machine gears) output by the u-1 polishing machine bed digital twin models after polishing H reduction machine gears is continuously monitored.

[0063] If there is any polishing machine bed digital twin model outputting an average polishing quality index (i.e., adjustment result) better than the current average polishing quality index of the corresponding polishing machine, the current processing parameter set and environmental parameter set of the corresponding polishing machine are immediately adjusted to the processing parameter set and environmental parameter set in the optimal adjustment parameter set.

[0064] If the average polishing quality index output by any one of the polishing machine digital twin models (i.e., the adjustment result) is not better than the current average polishing quality index of the corresponding polishing machine, the current machining parameter set and the environmental parameter set are kept unchanged.

[0065] In addition to the above steps, the operator can also select cascade adjustment, obtain the optimal adjustment parameter set associated with the second polishing processing feature PPF2` of the polishing machine digital twin model in the polishing processing feature sequence PPF1`, PPF2`,..., PPFu`, and perform adjustment operation on the polishing machine digital twin model associated with the polishing machine associated with PPF1` and PPF2`, and repeat this step until the last polishing processing feature PPFu` associated with the polishing machine, thereby realizing cascade adjustment.

[0066] The embodiment optimizes the machining parameters of the polishing machine to improve the polishing quality through digital modeling and quality evaluation. First, based on the merit index calculation method of the polishing machine, the qualified product quantity and the quality index are combined to determine the merit ranking of each machine. The dimensionless scaling constant λ is calibrated through the limit sample to ensure the scientificity of the merit index calculation. Then, the digital twin model is used to extract the machine and its parameter set corresponding to the optimal polishing quality, and the parameters of other machines are adjusted based on this. The polishing quality after adjustment is monitored to dynamically optimize the parameter settings. If the adjustment effect is better than the current quality, the machine parameters are updated; otherwise, the original parameters are kept. In addition, a cascade adjustment mechanism is introduced to gradually optimize the suboptimal machine, and finally the overall polishing quality is improved.

[0067] Some of the data in the formulas described above are dimensionless for numerical calculation, and the contents not described in detail in the specification all belong to the existing technology known to those skilled in the art.

[0068] The above is only an example and description of the present application. Those skilled in the art can make various modifications or supplements to the described specific embodiments or use similar ways to replace them, as long as they do not deviate from the invention or exceed the scope defined by the present claims, and they should belong to the protection scope of the present application.

[0069] It needs to be declared that all user data collected in this application are collected with the consent and authorization of the user. The use of user data is legal and compliant, and the use and processing of user data comply with relevant laws, regulations and standards in the relevant region.

Claims

1. A real-time evaluation and adjustment system for grinding quality of a gear of a speed reducer, characterized in that, The system comprises: A reducer gear image acquisition module, which acquires the reducer gear image by real-time shooting the reducer gear after polishing operation through an industrial camera, measures and maps the reducer gear in combination with a pre-constructed infrared light curtain, determines the geometric center of the reducer gear, maps the geometric center to the reducer gear image, and acquires the reducer gear image; A reducer gear polishing quality evaluation module, which segments the reducer gear image after mapping the geometric center, determines a plurality of tooth images associated with the reducer gear, and performs correlation analysis on all the tooth images to evaluate the polishing quality of the corresponding reducer gear; A polishing machine digital twin construction module, which acquires all the polishing machines, extracts the machining parameter set and the environmental parameter set associated with all the polishing machines, and constructs the polishing machine digital twin model associated with all the polishing machines; The polishing quality of the reducer gear polished by any one of the polishing machines is bound to the polishing machine digital twin model associated with the corresponding polishing machine, and a polishing processing feature is constructed; A polishing machine machining parameter adjustment module, which performs correlation analysis based on a plurality of sets of polishing processing features determined, evaluates the polishing machine digital twin model associated with the optimal polishing quality, acquires the machining parameter set and the environmental parameter set associated with the polishing machine digital twin model, combines them as an optimal adjustment parameter set, adjusts the polishing machine digital twin models associated with the remaining polishing machines, and outputs the adjustment results of the polishing machine digital twin models, based on which the remaining polishing machines are adjusted.

2. The system of claim 1, wherein, In the reducer gear image acquisition module, the specific way of acquiring the reducer gear image is as follows: Take any reducer gear A; Place A on an industrial shooting table and use an industrial camera to shoot A to acquire the reducer gear image G_A of A; The industrial shooting table comprises a built-in three-axis MEMS gravity sensor for bearing the reducer gear, and the bearing disc has a horizontal calculation function to determine the inclination of the bearing disc in the horizontal plane and output the normal vector n of the bearing disc; When the bearing disc detects A, it sends a detection start signal to the infrared light curtain; The infrared light curtain is a four-beam infrared fan-shaped light curtain, which simultaneously scans the tooth profile outer edge of A to obtain four polar coordinate sets {P1, P2, P3, P4} of the addendum circle of A in the light curtain coordinate system; Determine the geometric center Q1 of the addendum circle based on {P1, P2, P3, P4}, and send an adjustment signal to the industrial camera; Adjust the optical axis direction of the industrial camera to coincide with the normal vector n, and vertically lift along the Z axis. When the pixel distance between the projection point of the geometric center Q1 on the imaging target surface of the industrial camera and the physical center of the target surface is less than a preset pixel distance threshold, perform the shooting operation.

3. The system of claim 1, wherein, In the reducer gear polishing quality evaluation module, the specific way of determining a plurality of tooth images associated with the reducer gear is as follows: Project the three-dimensional point cloud data of the reducer gear A measured and mapped by the infrared light curtain to the imaging plane of the industrial camera using a preset spatial mapping matrix to determine the reducer gear pixel image G_A` of A in G_A; Determine the geometric center Q1 in G_A`, take Q1 as the center, and increase the radius by one pixel point as the step to make the outer expansion circle U, until U reaches the maximum state in G_A`, wherein the pixel points in U all belong to G_A`; Crop U from G_A` and remove it, and obtain the remaining pixel region; The remaining pixel region contains several closed regions, count the total number of closed regions, and record j; The j closed regions are the tooth images of the j teeth on A; Record the tooth image directly above the remaining pixel region as TG1, arrange the j tooth images in clockwise order to obtain the tooth image sequence TG1, TG2,..., TGj.

4. The system of claim 3, wherein, In the reducer gear polishing quality evaluation module, the specific way of evaluating the polishing quality of the corresponding reducer gear includes: Take the tooth image sequence TG1, TG2,..., TGj; Count the total number of pixel points in each tooth image in TG1, TG2,..., TGj, and record them in the order of TG1, TG2,..., TGj as the total pixel point sequence SUM1, SUM2,..., SUMj; Take the average of the j total pixel points in SUM1, SUM2,..., SUMj to obtain the total pixel point average SUM_avg; Take the total pixel point SUMi of any tooth image TGi, calculate the absolute value of the difference between SUMi and SUM_avg, divide the absolute value by SUM_avg, and multiply by 100% to obtain the pixel deviation rate δ of SUMi, wherein i is the count index, 1≤i≤j; Compare δ with the preset pixel deviation rate threshold δ_yu; If δ≥δ_yu, it is determined that the reducer gear A has an inter-tooth volume difference defect, and the first type of defect flag F1 is incremented by one, wherein the initial value of F1 is 0; Otherwise, do nothing; Similarly, process the j tooth images in TG1, TG2,..., TGj and update the first type of defect flag F1.

5. The system of claim 4, wherein, In the reducer gear polishing quality evaluation module, the specific way of evaluating the polishing quality of the corresponding reducer gear includes: Take the tooth image sequence TG1, TG2,..., TGj; Determine the tooth geometric center of each of the j tooth images to obtain j tooth geometries; Map the j tooth geometric centers to the reducer gear pixel image G_A` and label them; Get the geometric center Q1 of G_A` and label it; Connect the j tooth geometric centers to the geometric center Q1 to obtain j lines; The j lines and the geometric center Q1 form j angles; Divide the central angle by j to obtain the reference angle value; Get the angle value of any one of the j angles, calculate the absolute value of the difference between this angle value and the reference angle value, divide the absolute value by the reference angle value, and multiply by 100% to obtain the angle value difference rate between this angle value and the reference angle value; If the angle value difference rate is greater than or equal to the preset angle value difference rate threshold, it is determined that the reducer gear A has a non-uniform indexing defect, and the second type of defect flag F2 is incremented by one, wherein the initial value of F2 is 0; Otherwise, do nothing; Similarly, process the angle values of the j angles and update F2. Taking F1 and F2, the grinding quality index E of A is calculated by E = w1*F1 + w2*F2, wherein w1 and w2 are preset calculation weights, w1 and w2 are greater than 0, and w1 + w2 = 1; If E < a preset grinding quality index threshold E_yu, the gear reducer gear A is qualified, otherwise, A is unqualified.

6. The system of claim 1, wherein, In the digital twin construction module of the grinding machine tool, the specific way of constructing the grinding machine tool digital twin model associated with all grinding machine tools is: Get all grinding machine tools, and count the total number as u; The u grinding machine tools are recorded as a grinding machine tool sequence MT1, MT2,..., MTu in the order of acquisition; Get the environmental parameters of each grinding machine tool processing the gear reducer, and combine them as an environmental parameter group; Get the processing parameters predefined by the operator for each grinding machine tool, and combine them as a processing parameter group; Based on the digital twin technology, construct the grinding machine tool digital twin model associated with each of the u grinding machine tools, and inject parameters into the grinding machine tool digital twin model associated with each grinding machine tool based on the processing parameters and environmental parameters of each grinding machine tool. Get the grinding machine tool digital twin model sequence PMT1, PMT2,..., PMTu.

7. The system of claim 6, wherein, In the digital twin construction module of the grinding machine tool, the specific way of constructing the grinding processing feature is: Get any grinding machine tool MTo in the grinding machine tool sequence MT1, MT2,..., MTu and its corresponding grinding machine tool digital twin model PMTo, wherein o is a count index, 1 ≤ o ≤ u; Take the total number of grinding H preset by the operator; Determine the total number of qualified Cout1, the total number of unqualified Cout2, and the average grinding quality index E_avg of the grinding quality index E of the H gear reducers associated with the grinding machine tool MTo closest to the current time; Bind E_avg, Cout1, Cout2 and PMTo as a grinding processing feature PPFo; Similarly, each grinding machine tool in the grinding machine tool sequence MT1, MT2,..., MTu is processed synchronously to determine u grinding processing features, and the grinding processing feature sequence PPF1, PPF2,..., PPFu is recorded in the order of MT1, MT2,..., MTu.

8. The system of claim 7, wherein, In the grinding machine tool processing parameter adjustment module, the specific way of evaluating the grinding machine tool digital twin model associated with the optimal grinding quality is: Take the grinding processing feature sequence PPF1, PPF2,..., PPFu; Extract the average grinding quality index E_avg, the total number of qualified Cout1, and the total number of unqualified Cout2 in any grinding processing feature PPFo; Calculate the grinding machine tool merit index YL of PPFo by YL = (Cout1 - Cout2) / (Cout1 + Cout2) - λ * E_avg, wherein λ is a dimensionless scaling constant; Similarly, determine the grinding machine tool merit index of each grinding processing feature in PPF1, PPF2,..., PPFu; PPF1, PPF2, …, PPFu are arranged in descending order of polishing machine bed merit index, and a polishing treatment feature sequence PPF1`, PPF2`, …, PPFu` is obtained; PPF1` and the polishing machine digital twin model PMT1` associated with PPF1` are taken from the first polishing treatment feature PPF1` in PPF1`, PPF2`, …, PPFu` and the polishing machine digital twin model PMT1` associated with PPF1`; The polishing machine digital twin model PMT1` is the polishing machine digital twin model associated with the optimal polishing quality.

9. The system of claim 8, wherein, In the polishing machine processing parameter adjustment module, the specific way to determine the dimensionless scaling constant λ is: The operator pre-acquires k full qualified-zero defect reduction gears and k full unqualified-high defect reduction gears as limit samples, and k is a preset value; Full qualified-zero defect corresponds to Cout2=0 and E_avg=0, and λ is 1; Full unqualified-high defect corresponds to Cout1=0 and E_avg=E_max, and λ is -1; In summary, λ is solved, and λ∈[-1, 1]; λ is a fixed value and no longer changes.

10. The system of claim 8, wherein, In the polishing machine processing parameter adjustment module, the specific way to adjust the remaining polishing machines based on the adjustment result is: Obtain the processing parameter set and the environment parameter set of the polishing machine digital twin model PMT1` with the optimal polishing quality, and combine them as the optimal adjustment parameter set; Take u-1 polishing machine digital twin models from the u polishing machine digital twin models except PMT1`; Adjust the processing parameter set and the environment parameter set of the u-1 polishing machine digital twin models to the processing parameter set and the environment parameter set in the optimal adjustment parameter set; Continuously monitor the adjustment results output by the u-1 polishing machine digital twin models after polishing H reduction gears, and the adjustment result is the average polishing quality index; If the average polishing quality index output by any polishing machine digital twin model is better than the current average polishing quality index of the corresponding polishing machine, the corresponding polishing machine is adjusted according to the optimal adjustment parameter set; Otherwise, no processing is performed.

Images