A full-automatic detection method applied to flywheel machining

Abstract

The application relates to a full-automatic detection method applied to flywheel machining, which comprises the following steps: Q1. A manipulator places a machined flywheel on a detection production line, real-time image data information of the flywheel is acquired based on an online camera, real-time point cloud data information of the flywheel is acquired based on an online laser radar sensor, and real-time distance data information of the flywheel is acquired based on an online laser displacement sensor; Q2. Based on the image data information of the flywheel and the point cloud data information of the flywheel, a first detection parameter function F1 of flywheel machining is constructed, the detection parameters of the flywheel machining are characterized, and data information of a first detection parameter matrix of the flywheel machining is obtained. The application can not only rapidly and comprehensively detect the flywheel machining, guarantee that the quality of the flywheel product meets the requirements, but also detect the flywheel by using multiple sensors, improve the precision of the flywheel detection, and reduce the occurrence of substandard products.

Description

Technical Field

[0001] This invention relates to the technical field of flywheel machining inspection, and in particular to a fully automated inspection method for flywheel machining. Background Technology

[0002] With the increasing automation of automotive flywheel processing, automotive flywheel production lines are becoming more personalized. Testing processes using instruments that only measure single data points require significant manpower and resources, are unsuitable for rapid testing, and lack high accuracy. Meanwhile, the automotive flywheel, as a crucial component of the car engine, plays a vital role. As an energy storage device, the flywheel stores excess kinetic energy when the cylinders' work is discontinuous during engine operation, causing crankshaft speed fluctuations. This energy is released when the speed decreases, effectively smoothing engine operation and improving its stability and smoothness. Defects in flywheel processing can affect the overall engine performance. Therefore, how to accurately inspect flywheel processing has become a pressing issue. Summary of the Invention

[0003] In view of the above problems, the present invention provides a fully automatic inspection method for flywheel processing, which can not only quickly and comprehensively inspect flywheel processing to ensure that the quality of flywheel products meets the requirements, but also improve the accuracy of flywheel inspection and reduce the defect rate by using multiple sensors to inspect the flywheel.

[0004] To achieve the above and other related objectives, the present invention provides the following technical solution:

[0005] A fully automated inspection method for flywheel machining, the method comprising:

[0006] Q1. The robotic arm places the processed flywheel on the inspection production line. The online camera acquires the image data information of the flywheel in real time, the online lidar sensor acquires the point cloud data information of the flywheel in real time, and the online laser displacement sensor acquires the distance data information of the flywheel in real time.

[0007] Q2. Based on the image data information and point cloud data information of the flywheel, construct the first detection parameter function F1 for flywheel processing, characterize the detection parameters of flywheel processing, and obtain the data information of the first detection parameter matrix for flywheel processing;

[0008] Q3. Based on the image data information and distance data information of the flywheel, construct the second detection parameter function F2 for flywheel processing, characterize the detection parameters of flywheel processing, and obtain the data information of the second detection parameter matrix for flywheel processing;

[0009] Q4. Based on the point cloud data information and the distance data information of the flywheel, construct the third detection parameter function F3 for flywheel processing, characterize the detection parameters of flywheel processing, and obtain the data information of the third detection parameter matrix for flywheel processing;

[0010] Q5. Based on the data information of the third detection parameter matrix, the second detection parameter matrix, and the first detection parameter matrix of the flywheel processing, an improved BP neural network regression prediction algorithm is used to predict the processing quality of the flywheel, and the predicted processing quality data information of the flywheel is obtained.

[0011] Q6. Based on the predicted flywheel machining quality data, construct an evaluation model for flywheel machining quality, evaluate the flywheel machining quality, and output the evaluation data for flywheel machining quality.

[0012] Furthermore, in step Q2, the first detection parameter function F1 for flywheel machining is,

[0013]

[0014] Where x1 is the image data information of the flywheel, x2 is the point cloud data information of the flywheel, f1 is the relationship function between the image and the point cloud of the flywheel, and α1 and α2 are the first detection factors for flywheel processing.

[0015] Furthermore, the relationship function f1 between the flywheel image and the point cloud is,

[0016]

[0017] Where x1 is the image data information of the flywheel, and x2 is the point cloud data information of the flywheel.

[0018] Furthermore, in step Q3, the second detection parameter function F2 for flywheel machining is,

[0019]

[0020] Where x1 is the image data of the flywheel, x3 is the distance data of the flywheel, f2 is the relationship function between the image and distance of the flywheel, and β1 and β2 are the second detection factors for flywheel processing.

[0021] Furthermore, in step Q4, the third detection parameter function F3 for flywheel machining is,

[0022]

[0023]

[0024] Where x2 is the point cloud data of the flywheel, x3 is the distance data of the flywheel, f3 is the relationship function between the point cloud and the distance of the flywheel, and λ1 and λ2 are the third detection factors for flywheel processing.

[0025] Furthermore, the relationship function f3 between the point cloud of the flywheel and the distance is,

[0026]

[0027] Where x2 represents the point cloud data of the flywheel, and x3 represents the distance data of the flywheel.

[0028] Furthermore, in step Q5, the prediction of the flywheel's machining quality using the improved BP neural network regression prediction algorithm includes:

[0029] Q51. Based on the data information of the third detection parameter matrix, the second detection parameter matrix, and the first detection parameter matrix of the flywheel machining, establish a detection parameter fusion function G for flywheel machining.

[0030]

[0031] Where a represents the data information of the third detection parameter matrix of flywheel machining, b represents the data information of the second detection parameter matrix of flywheel machining, c represents the data information of the first detection parameter matrix of flywheel machining, and ω1, ω2 and ω3 are data fusion factors of flywheel machining. The detection parameter matrices of flywheel machining are fused to obtain the data information of the fused detection parameter matrix of flywheel machining.

[0032] Q52. Input the data information of the fusion detection parameter matrix of the flywheel processing into the improved BP neural network regression prediction model for training and learning, and determine the improved neuron kernel function R.

[0033]

[0034] Where y represents the data information of the fusion detection parameter matrix for flywheel machining, and ρ1, ρ2, and ρ3 are the learning factors for flywheel machining detection, thus obtaining the trained and improved BP neural network regression prediction model.

[0035] Q53. Based on the trained and improved BP neural network regression prediction model, input the data information of the fusion detection parameter matrix of the flywheel processing, predict the processing quality of the flywheel, and obtain the predicted processing quality data information of the flywheel.

[0036] Furthermore, the learning factor ρ1 for the flywheel machining detection is,

[0037]

[0038] The learning factor ρ2 for the flywheel machining detection is,

[0039]

[0040] The learning factor ρ3 for the flywheel machining detection is:

[0041]

[0042] Where y represents the data information of the fusion detection parameter matrix for flywheel processing.

[0043] Furthermore, in step Q6, the construction of the flywheel machining quality evaluation model and the evaluation of the flywheel machining quality include:

[0044] Q61. Obtain the predicted flywheel machining quality data information, construct a flywheel machining quality dataset, and divide it into a flywheel machining training dataset and a flywheel machining test dataset;

[0045] Q62. Input the aforementioned flywheel machining training dataset into the flywheel machining quality evaluation model for training and learning, and determine the evaluation function W for flywheel machining quality.

[0046]

[0047] Where g is the flywheel machining training dataset, η1 and η2 are the evaluation factors of flywheel machining quality, and the evaluation model of flywheel machining quality after training is obtained;

[0048] Q63. Based on the trained flywheel machining quality evaluation model, input the flywheel machining test dataset for optimization to obtain a trained flywheel machining quality evaluation model;

[0049] Q64. Based on the trained flywheel machining quality evaluation model, input the predicted flywheel machining quality data, evaluate the flywheel machining quality, and output the flywheel machining quality evaluation data.

[0050] Furthermore, the method also includes:

[0051] Q7. Based on the evaluation data of the flywheel's processing quality, a preset threshold is set. If the evaluation of the flywheel's processing quality is less than the preset threshold, the quality requirements are not met and the flywheel is unqualified. If the evaluation of the flywheel's processing quality is greater than the preset threshold, the quality requirements are met and the flywheel is qualified.

[0052] The present invention has the following positive effects:

[0053] 1. This invention constructs a first detection parameter function F1, a second detection parameter function F2, and a third detection parameter function F3 for flywheel machining, thereby comprehensively characterizing the overall detection parameters of flywheel machining. This not only enables rapid and comprehensive detection of flywheel machining, ensuring that the quality of flywheel products meets requirements, but also improves the accuracy of flywheel detection and reduces the defect rate by using multiple sensors to detect the flywheel.

[0054] 2. This invention uses an improved BP neural network regression prediction algorithm to predict the processing quality of flywheels and combines it with a flywheel processing quality evaluation model to evaluate the processing quality of flywheels. This not only allows for continuous changes based on the requirements of flywheel processing quality, improving the detection accuracy of flywheel inspection, but also eliminates the need for manual intervention during the flywheel inspection process, reducing labor costs and increasing the efficiency of flywheel processing. Attached Figure Description

[0055] Figure 1 This is a schematic diagram of the method flow of the present invention;

[0056] Figure 2 This is a flowchart illustrating the improved BP neural network regression prediction algorithm of the present invention.

[0057] Figure 3 This is a schematic diagram of the process for constructing an evaluation model for the processing quality of a flywheel according to the present invention;

[0058] Figure 4 This is a schematic diagram of the structure of the present invention.

[0059] The labels in the diagram are as follows: 1-robotic arm, 2-on the inspection production line, 3-camera, 4-LiDAR sensor, 5-laser displacement sensor, 6-flywheel. Detailed Implementation

[0060] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0061] Example 1: As Figure 1 or Figure 4 As shown, a fully automated inspection method for flywheel machining is described, the method comprising:

[0062] Q1. The robotic arm 1 places the processed flywheel 6 on the inspection production line 2. The online camera 3 acquires the image data information of the flywheel in real time, the online lidar sensor 4 acquires the point cloud data information of the flywheel in real time, and the online laser displacement sensor 5 acquires the distance data information of the flywheel in real time.

[0063] Q2. Based on the image data information and point cloud data information of the flywheel, construct the first detection parameter function F1 for flywheel processing, characterize the detection parameters of flywheel processing, and obtain the data information of the first detection parameter matrix for flywheel processing;

[0064] Q3. Based on the image data information and distance data information of the flywheel, construct the second detection parameter function F2 for flywheel processing, characterize the detection parameters of flywheel processing, and obtain the data information of the second detection parameter matrix for flywheel processing;

[0065] Q4. Based on the point cloud data information and the distance data information of the flywheel, construct the third detection parameter function F3 for flywheel processing, characterize the detection parameters of flywheel processing, and obtain the data information of the third detection parameter matrix for flywheel processing;

[0066] Q5. Based on the data information of the third detection parameter matrix, the second detection parameter matrix, and the first detection parameter matrix of the flywheel processing, an improved BP neural network regression prediction algorithm is used to predict the processing quality of the flywheel, and the predicted processing quality data information of the flywheel is obtained.

[0067] Q6. Based on the predicted flywheel machining quality data, construct an evaluation model for flywheel machining quality, evaluate the flywheel machining quality, and output the evaluation data for flywheel machining quality.

[0068] In this embodiment, in step Q2, the first detection parameter function F1 for flywheel machining is,

[0069]

[0070] Where x1 is the image data information of the flywheel, x2 is the point cloud data information of the flywheel, f1 is the relationship function between the image and the point cloud of the flywheel, and α1 and α2 are the first detection factors for flywheel processing.

[0071] In this embodiment, the relationship function f1 between the flywheel image and the point cloud is,

[0072]

[0073] Where x1 is the image data information of the flywheel, and x2 is the point cloud data information of the flywheel.

[0074] In this embodiment, in step Q3, the second detection parameter function F2 for flywheel machining is,

[0075]

[0076] Where x1 is the image data of the flywheel, x3 is the distance data of the flywheel, f2 is the relationship function between the image and distance of the flywheel, and β1 and β2 are the second detection factors for flywheel processing.

[0077] In this embodiment, in step Q4, the third detection parameter function F3 for flywheel machining is,

[0078]

[0079] Where x2 is the point cloud data of the flywheel, x3 is the distance data of the flywheel, f3 is the relationship function between the point cloud and the distance of the flywheel, and λ1 and λ2 are the third detection factors for flywheel processing.

[0080] In this embodiment, the relationship function f3 between the point cloud of the flywheel and the distance is,

[0081]

[0082] Where x2 represents the point cloud data of the flywheel, and x3 represents the distance data of the flywheel.

[0083] Example 2: Based on the fully automated inspection method for flywheel processing in Example 1, the present invention will be further explained and described below.

[0084] like Figure 1 or Figure 4 As shown, a fully automated inspection method for flywheel machining is described, the method comprising:

[0085] Q1. The robotic arm 1 places the processed flywheel 6 on the inspection production line 2. The online camera 3 acquires the image data information of the flywheel in real time, the online lidar sensor 4 acquires the point cloud data information of the flywheel in real time, and the online laser displacement sensor 5 acquires the distance data information of the flywheel in real time.

[0086] Q2. Based on the image data information and point cloud data information of the flywheel, construct the first detection parameter function F1 for flywheel processing, characterize the detection parameters of flywheel processing, and obtain the data information of the first detection parameter matrix for flywheel processing;

[0087] Q3. Based on the image data information and distance data information of the flywheel, construct the second detection parameter function F2 for flywheel processing, characterize the detection parameters of flywheel processing, and obtain the data information of the second detection parameter matrix for flywheel processing;

[0088] Q4. Based on the point cloud data information and the distance data information of the flywheel, construct the third detection parameter function F3 for flywheel processing, characterize the detection parameters of flywheel processing, and obtain the data information of the third detection parameter matrix for flywheel processing;

[0089] Q5. Based on the data information of the third detection parameter matrix, the second detection parameter matrix, and the first detection parameter matrix of the flywheel processing, an improved BP neural network regression prediction algorithm is used to predict the processing quality of the flywheel, and the predicted processing quality data information of the flywheel is obtained.

[0090] Q6. Based on the predicted flywheel machining quality data, construct an evaluation model for flywheel machining quality, evaluate the flywheel machining quality, and output the evaluation data for flywheel machining quality.

[0091] In this embodiment, as Figure 2 As shown, in step Q5, the prediction of the flywheel's machining quality using the improved BP neural network regression prediction algorithm includes:

[0092] Q51. Based on the data information of the third detection parameter matrix, the second detection parameter matrix, and the first detection parameter matrix of the flywheel machining, establish a detection parameter fusion function G for flywheel machining.

[0093]

[0094] Where a represents the data information of the third detection parameter matrix of flywheel machining, b represents the data information of the second detection parameter matrix of flywheel machining, c represents the data information of the first detection parameter matrix of flywheel machining, and ω1, ω2 and ω3 are data fusion factors of flywheel machining. The detection parameter matrices of flywheel machining are fused to obtain the data information of the fused detection parameter matrix of flywheel machining.

[0095] Q52. Input the data information of the fusion detection parameter matrix of the flywheel processing into the improved BP neural network regression prediction model for training and learning, and determine the improved neuron kernel function R.

[0096]

[0097] Where y represents the data information of the fusion detection parameter matrix for flywheel machining, and ρ1, ρ2, and ρ3 are the learning factors for flywheel machining detection, thus obtaining the trained and improved BP neural network regression prediction model.

[0098] Q53. Based on the trained and improved BP neural network regression prediction model, input the data information of the fusion detection parameter matrix of the flywheel processing, predict the processing quality of the flywheel, and obtain the predicted processing quality data information of the flywheel.

[0099] In this embodiment, the learning factor ρ1 for the flywheel machining detection is,

[0100]

[0101] The learning factor ρ2 for the flywheel machining detection is,

[0102]

[0103] The learning factor ρ3 for the flywheel machining detection is:

[0104]

[0105] Where y represents the data information of the fusion detection parameter matrix for flywheel processing.

[0106] In this embodiment, as Figure 3 As shown, in step Q6, the construction of the flywheel machining quality evaluation model and the evaluation of the flywheel machining quality include:

[0107] Q61. Obtain the predicted flywheel machining quality data information, construct a flywheel machining quality dataset, and divide it into a flywheel machining training dataset and a flywheel machining test dataset;

[0108] Q62. Input the aforementioned flywheel machining training dataset into the flywheel machining quality evaluation model for training and learning, and determine the evaluation function W for flywheel machining quality.

[0109]

[0110] Where g is the flywheel machining training dataset, η1 and η2 are the evaluation factors of flywheel machining quality, and the evaluation model of flywheel machining quality after training is obtained;

[0111] Q63. Based on the trained flywheel machining quality evaluation model, input the flywheel machining test dataset for optimization to obtain a trained flywheel machining quality evaluation model;

[0112] Q64. Based on the trained flywheel machining quality evaluation model, input the predicted flywheel machining quality data, evaluate the flywheel machining quality, and output the flywheel machining quality evaluation data.

[0113] In this embodiment, the method further includes:

[0114] Q7. Based on the evaluation data of the flywheel's processing quality, a preset threshold is set. If the evaluation of the flywheel's processing quality is less than the preset threshold, the quality requirements are not met and the flywheel is unqualified. If the evaluation of the flywheel's processing quality is greater than the preset threshold, the quality requirements are met and the flywheel is qualified.

[0115] In this embodiment, the present invention provides a computer-readable storage medium storing a computer program programmed or configured to perform any of the fully automated inspection methods for flywheel machining described in the present invention.

[0116] Any references to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0117] In summary, this invention not only enables rapid and comprehensive inspection of flywheel processing, ensuring that the quality of flywheel products meets requirements, but also improves the accuracy of flywheel inspection and reduces the defect rate by using multiple sensors to inspect the flywheel.

[0118] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A full-automatic detection method applied to flywheel machining, characterized in that, The method comprises: Q1. The manipulator places the finished flywheel on the detection production line, obtains real-time image data information of the flywheel based on the on-line camera, obtains real-time point cloud data information of the flywheel based on the on-line laser radar sensor, and obtains real-time distance data information of the flywheel based on the on-line laser displacement sensor; Q2. Based on the image data information of the flywheel and the point cloud data information of the flywheel, a first detection parameter function F1 of flywheel processing is constructed to characterize the detection parameters of flywheel processing, and data information of a first detection parameter matrix of flywheel processing is obtained; Q3. Based on the image data information of the flywheel and the distance data information of the flywheel, a second detection parameter function F2 of flywheel processing is constructed to characterize the detection parameters of flywheel processing, and data information of a second detection parameter matrix of flywheel processing is obtained; Q4. Based on the point cloud data information of the flywheel and the distance data information of the flywheel, a third detection parameter function F3 of flywheel processing is constructed to characterize the detection parameters of flywheel processing, and data information of a third detection parameter matrix of flywheel processing is obtained; Q5. Based on the data information of the third detection parameter matrix, the data information of the second detection parameter matrix and the data information of the first detection parameter matrix of flywheel processing, an improved BP neural network regression prediction algorithm is used to predict the processing quality of the flywheel, and data information of the predicted processing quality of the flywheel is obtained; Q6. Based on the data information of the predicted processing quality of the flywheel, an evaluation model of flywheel processing quality is constructed to evaluate the processing quality of the flywheel, and evaluation data information of the processing quality of the flywheel is output; In step Q5, the improved BP neural network regression prediction algorithm is used to predict the processing quality of the flywheel, which comprises: Q51. Based on the data information of the third detection parameter matrix, the data information of the second detection parameter matrix and the data information of the first detection parameter matrix of flywheel processing, a detection parameter fusion function G of flywheel processing is established, ， Wherein, a is the data information of the third detection parameter matrix of flywheel processing, b is the data information of the second detection parameter matrix of flywheel processing, c is the data information of the first detection parameter matrix of flywheel processing, ω1, ω2 and ω3 are data fusion factors of flywheel processing, the detection parameter matrix of flywheel processing is fused, and the data information of the fused detection parameter matrix of flywheel processing is obtained; Q52. The data information of the fused detection parameter matrix of flywheel processing is input into the improved BP neural network regression prediction model for training and learning, and the improved neuron kernel function R is determined, ， Wherein, y is the data information of the fused detection parameter matrix of flywheel processing, ρ1, ρ2 and ρ3 are learning factors of flywheel processing detection, and the trained improved BP neural network regression prediction model is obtained; Q53. Based on the trained improved BP neural network regression prediction model, the data information of the fused detection parameter matrix of flywheel processing is input, the processing quality of the flywheel is predicted, and the data information of the predicted processing quality of the flywheel is obtained.

2. The full-automatic detection method applied to flywheel machining according to claim 1, characterized in that, In step Q2, the first detection parameter function F1 of flywheel processing is ， ， Where x1 is the image data information of the flywheel, x2 is the point cloud data information of the flywheel, f1 is the relationship function between the image and the point cloud of the flywheel, and α1 and α2 are the first detection factors for flywheel processing.

3. The fully automatic detection method applied to flywheel machining according to claim 2, characterized in that: The relationship function f1 between the image of the flywheel and the point cloud is: ， Where x1 is the image data information of the flywheel, and x2 is the point cloud data information of the flywheel.

4. The full-automatic detection method applied to flywheel machining according to claim 1, characterized in that, In step Q3, the second detection parameter function F2 for flywheel machining is, ， , , Where x1 is the image data of the flywheel, x3 is the distance data of the flywheel, f2 is the relationship function between the image and distance of the flywheel, and β1 and β2 are the second detection factors for flywheel processing.

5. The full-automatic detection method applied to flywheel machining according to claim 1, characterized in that, In step Q4, the third detection parameter function F3 for flywheel machining is, ， ， Where x2 is the point cloud data of the flywheel, x3 is the distance data of the flywheel, f3 is the relationship function between the point cloud and the distance of the flywheel, and λ1 and λ2 are the third detection factors for flywheel processing.

6. The full-automatic detection method applied to flywheel machining according to claim 5, characterized in that: The relationship function f3 between the point cloud of the flywheel and the distance is: ， Where x2 represents the point cloud data of the flywheel, and x3 represents the distance data of the flywheel.

7. The full automatic detection method applied to flywheel machining according to claim 1, characterized in that: The learning factor ρ1 for the flywheel machining detection is, ， The learning factor ρ2 for the flywheel machining detection is, ， The learning factor ρ3 for the flywheel machining detection is: ， Where y represents the data information of the fusion detection parameter matrix for flywheel processing.

8. The full-automatic detection method applied to flywheel machining according to claim 1, characterized in that, In step Q6, the construction of the flywheel machining quality evaluation model and the evaluation of the flywheel machining quality include: Q61. Obtain the predicted flywheel machining quality data information, construct a flywheel machining quality dataset, and divide it into a flywheel machining training dataset and a flywheel machining test dataset; Q62. Input the aforementioned flywheel machining training dataset into the flywheel machining quality evaluation model for training and learning, and determine the evaluation function W for flywheel machining quality. ， Where g is the flywheel machining training dataset, η1 and η2 are the evaluation factors of flywheel machining quality, and the evaluation model of flywheel machining quality after training is obtained; Q63. Based on the trained flywheel machining quality evaluation model, input the flywheel machining test dataset for optimization to obtain a trained flywheel machining quality evaluation model; Q64. Based on the trained flywheel machining quality evaluation model, input the predicted flywheel machining quality data, evaluate the flywheel machining quality, and output the flywheel machining quality evaluation data.

9. The full-automatic detection method applied to flywheel machining according to claim 1, characterized in that, The method further includes: Q7. Based on the evaluation data of the flywheel's processing quality, a preset threshold is set. If the evaluation of the flywheel's processing quality is less than the preset threshold, the quality requirements are not met and the flywheel is unqualified. If the evaluation of the flywheel's processing quality is greater than the preset threshold, the quality requirements are met and the flywheel is qualified.

Images