Bicycle intermediate shaft press fitting processing system based on machine vision positioning

Abstract

The application discloses a bicycle middle shaft press fitting processing system based on machine vision positioning, which comprises a servo press fitting module, a data acquisition module, a data processing module, a machine vision positioning module, a press fitting control module, a quality detection module and a data management module; the system acquires image data and assembly quality data, extracts initial coordinates of mounting holes by using median filtering, Canny edge detection and Hough circle transformation, further adopts RANSAC algorithm to fit the inner wall cylindrical surface of the five-way pipe, accurately calculates the spatial coordinates of the center point and the axial direction vector, and converts to the press fitting coordinate system through hand-eye calibration; the press fitting process is dynamically regulated in three stages of pre-pressing, main pressing and final pressing, the press fitting speed is dynamically adjusted, and online assembly quality determination is realized through displacement-pressure curve analysis; the system solves the bearing wear problem caused by axis alignment deviation in traditional press fitting, and improves the press fitting precision and the yield.

Description

Technical Field

[0001] This invention belongs to the field of intelligent manufacturing technology for bicycles, and specifically discloses a bicycle bottom bracket press-fitting system based on machine vision positioning. Background Technology

[0002] The press-fit accuracy of the bicycle bottom bracket assembly directly affects the overall performance of the bicycle and the life of the bearings. Traditional press-fitting processes rely on mechanical clamps to fix the frame and determine the position of the bottom bracket tube manually by visual inspection or simple positioning fixtures, which has the following drawbacks:

[0003] Low positioning accuracy: Manufacturing tolerances and clamping deformation of the frame bottom bracket tube cause deviation between the axis of the bottom bracket mounting hole and the press-fit axis. The press-fit process can easily cause uneven wear of the bearings and shorten their service life.

[0004] The process control is crude: the press-fitting process often uses constant speed or simple pressure threshold control, which cannot adapt to the interference fit requirements of different frame materials and is prone to cause damage to parts due to sudden changes in press-fitting force.

[0005] Lack of quality traceability: Assembly quality relies on post-assembly spot checks, lacking real-time analysis of displacement-pressure curves during the pressing process, making it difficult to pinpoint the root cause of defects.

[0006] Existing solutions, such as laser positioning or contact probe measurement, suffer from high cost, low efficiency, and the inability to acquire three-dimensional data of the inner wall. A few solutions using machine vision can only extract two-dimensional center coordinates, failing to address the three-dimensional spatial attitude calibration problem of the bottom bracket, and the press-fitting process lacks closed-loop control based on environmental data and real-time mechanical feedback. Therefore, it is necessary to invent a machine vision-based bicycle bottom bracket press-fitting system to solve these problems. Summary of the Invention

[0007] To overcome the aforementioned deficiencies of the prior art, this invention provides a machine vision-based positioning system for pressing and fitting bicycle bottom brackets, including...

[0008] Data acquisition module: used to acquire image data and assembly quality data;

[0009] Data processing module: used to perform image denoising, edge detection, and feature coordinate extraction;

[0010] Machine vision positioning module: Based on the image data acquired by the data acquisition module, the spatial coordinates (X, Y, Z) of the center point of the bottom bracket and the direction vector of the central axis are accurately calculated through image processing algorithms;

[0011] Data management module: used for data storage and traceability during the processing;

[0012] Pressing control module: Used to control the servo pressing module to perform pressing based on visual coordinates, and to adjust the pressing speed in real time;

[0013] Servo press-fit module: integrates frame support device and bottom bracket press-fit device. The frame support device is used to fix the bicycle frame and provide initial positioning, and the bottom bracket press-fit device is used to perform the press-fit operation of the bottom bracket assembly.

[0014] Quality inspection module: used to determine assembly quality by analyzing displacement-pressure curves;

[0015] The image data includes a global image of the bottom bracket area of ​​the frame, a local feature image of the bottom bracket mounting hole, and three-dimensional point cloud data of the bottom bracket inner wall; the assembly quality data includes: real-time displacement and pressure data of the bottom bracket during the press-fit process; the specific method for the data acquisition module to acquire image data is as follows: a global image of the bottom bracket area of ​​the bicycle frame and a local feature image of the bottom bracket mounting hole are acquired using a high-resolution industrial camera, and three-dimensional point cloud data of the bottom bracket inner wall are acquired using a 3D structured light camera; the assembly quality data is acquired using displacement sensors and pressure sensors.

[0016] The specific operation process of the servo press-fit module is as follows:

[0017] Based on the calculated bottom bracket axis direction vector (i,j,k), the drive frame bearing device performs pose compensation to align the bottom bracket axis with the press-fit axis.

[0018] The press-fitting control module controls the servo press-fitting module to press the central shaft in. During the process, the pressure value Pi is detected in real time. In the main press stage, the speed is dynamically adjusted according to the pressure feedback to keep the pressure value within the range of ±10% of the standard curve.

[0019] After reaching the target position, maintain the holding pressure for a fixed period of time;

[0020] The specific control logic of the press-fitting control module is as follows:

[0021] Pre-pressing stage: Pressing in at a constant speed for the first 30% of the total stroke;

[0022] Main pressure stage: Press in 30%-80% of the total stroke, and dynamically adjust the pressing speed according to pressure feedback;

[0023] Final pressing stage: During the last 20% of the total pressing stroke, switch to displacement control mode to press the material to the target position with fixed step accuracy;

[0024] The adjustment logic of the dynamically adjusted speed satisfies: In the formula, v t Let P be the pressing speed at time t. ta P is the standard pressure value corresponding to the current displacement. t K represents the measured pressure value at time t. p K is the proportionality coefficient.i K is the integral coefficient. d Here, θ is the differential coefficient, and θ is the integral dummy variable; the formula for calculating the holding pressure is: In the formula, α is the material creep coefficient, and σ is the creep coefficient. y D is the yield strength of the bottom bracket material, D is the diameter of the central shaft assembly, L is the press-in contact length, and F is the bottom bracket material. h To maintain pressure.

[0025] In one possible design, the specific processing flow of the data processing module is as follows:

[0026] The median filtering algorithm is used to denoise the original image;

[0027] Edge detection and generation of binary contour images based on the Canny operator;

[0028] The initial coordinates of the center of the mounting hole of the central shaft are extracted using the Hough circle transformation.

[0029] In one possible design, the specific analysis method for the machine vision positioning module is as follows:

[0030] The RANSAC algorithm was used to fit the cylindrical surface of the inner wall of the bottom duct to the 3D point cloud data.

[0031] Calculate the spatial coordinates (X, Y, Z) of the center point and the direction vector (i, j, k) of the axis based on the equation of the central axis of the cylindrical surface.

[0032] The coordinates are transformed to the base coordinate system of the servo press-fit module using a hand-eye calibration matrix.

[0033] In one possible design, the specific operation process of the quality inspection module is as follows:

[0034] The system receives and analyzes displacement-pressure curve data acquired by the data acquisition module in real time.

[0035] The real-time displacement-pressure curve is compared with the preset standard qualified curve;

[0036] Based on the comparison results, determine whether the assembly quality is qualified and generate the corresponding quality judgment result signal;

[0037] If an abnormal curve shape or a deviation from the preset tolerance range is detected, a corresponding abnormal alarm code will be generated.

[0038] In one possible design, the pressing control module and the quality detection module are also equipped with an anomaly handling unit; when the real-time pressure value Pi exceeds the preset safety threshold, the displacement-pressure curve deviates significantly from the standard curve, or an abnormal alarm code is received from the sensor, the anomaly handling unit controls the servo pressing module to immediately stop the pressing operation.

[0039] In one possible design, the data management module stores at least the following data: original image data, processed image feature data, calculated center coordinates and axis vector of the five-way pipe, displacement-pressure curve of the entire pressing process, set and actual values ​​of pressing speed at each stage, environmental data, quality judgment results, abnormal alarm codes and processing records.

[0040] The technical effects and advantages of this invention are as follows:

[0041] 1. High-precision spatial positioning: It integrates 2D images and 3D point cloud data, and fits the cylindrical surface through the RANSAC algorithm to solve the defect that traditional two-dimensional vision cannot obtain the axis direction vector; hand-eye calibration and coordinate transformation eliminate the pose error of the camera and mechanical system, ensuring that the press-fit axis and the bottom tube axis are accurately aligned, and avoiding bearing wear.

[0042] 2. Adaptive dynamic press-fitting control: A three-stage press-fitting strategy is adopted. During the main press-fitting stage, the speed is dynamically adjusted based on the material characteristics. Finally, the holding pressure is applied to suppress material creep and springback, ensuring assembly stability.

[0043] 3. Full-process closed-loop quality inspection: Online analysis of displacement-pressure curves, automatic comparison with standard qualified curves, real-time output of quality judgment signals, and abnormal alarm codes associated with specific failure modes to accelerate fault diagnosis. Attached Figure Description

[0044] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0045] Figure 1 This is a schematic diagram of the overall structure of the present invention.

[0046] Figure 2 This is the main workflow of the present invention. Detailed Implementation

[0047] 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.

[0048] This invention provides, for example Figure 1The bicycle bottom bracket press-fitting system based on machine vision positioning shown includes: a data acquisition module, a data processing module, a machine vision positioning module, a data management module, a press-fitting control module, and a servo press-fitting module.

[0049] The data acquisition module is connected to the data processing module, the data processing module is connected to the machine vision positioning module, the machine vision positioning module is connected to the data management module, the data management module is connected to the data acquisition module, the machine vision positioning module, the pressing control module and the servo pressing module respectively, and the pressing control module is connected to the servo pressing module.

[0050] The main workflow of this invention is as follows: Figure 2 As shown, the specific description is as follows:

[0051] The data acquisition module is used to acquire image data and assembly quality data;

[0052] In a preferred embodiment of this application, the image data includes a global image of the bottom bracket area of ​​the frame, a local feature image of the bottom bracket mounting hole, and three-dimensional point cloud data of the inner wall of the bottom bracket; the assembly quality data includes real-time displacement and pressure data of the bottom bracket during the press-fitting process; the specific method by which the data acquisition module acquires the image data is as follows: a global image of the bottom bracket area of ​​the bicycle frame and a local feature image of the bottom bracket mounting hole are acquired using a high-resolution industrial camera, and three-dimensional point cloud data of the inner wall of the bottom bracket is acquired using a 3D structured light camera; the assembly quality data is acquired using displacement sensors and pressure sensors.

[0053] The data processing module is used to perform image denoising, edge detection, and feature coordinate extraction;

[0054] In the preferred embodiment of this application, the specific processing flow of the data processing module is as follows:

[0055] The median filtering algorithm is used to denoise the original image;

[0056] Edge detection and generation of binary contour images based on the Canny operator;

[0057] The initial coordinates of the center of the mounting hole of the central shaft are extracted using the Hough circle transformation.

[0058] In the preferred embodiment of this application, median filtering uses a 5×5 pixel square filter kernel to perform nonlinear filtering on the original image. After sorting all pixel values ​​in the kernel, the median value is used to replace the center pixel value, which effectively eliminates impulse noise in industrial images, such as metal reflections and CCD thermal noise, while preserving edge sharpness. The noise standard deviation of the processed image is reduced by 67%, providing a clean input for subsequent edge detection.

[0059] In the preferred technical solution of this application, the specific process of edge detection and generation of binary contour image based on Canny operator is as follows: First, Gaussian smoothing is performed to eliminate micro-vibration blur. Then, effective edges are extracted through gradient calculation and double threshold hysteresis. The low threshold captures weak edge features, and the high threshold suppresses false edges, generating a single-pixel wide, continuous closed contour line. Finally, by fixed threshold binarization, a binary contour image containing only 0 / 255 values ​​is output, which significantly improves the robustness of subsequent geometric feature extraction.

[0060] In the preferred technical solution of this application, the specific process of Hough circle transformation is as follows: a probabilistic Hough transformation is applied to the binary contour image, with the following core parameter settings: the accumulator resolution is consistent with the image resolution, dp=1.0, the minimum distance between the two circles is 30 pixels, the center accumulation threshold is 30, the radius range is 15-25 pixels, and the output result includes the center coordinates (x,y) and the radius r, thereby achieving sub-pixel-level positioning of the mounting hole with a positioning accuracy of ±0.2mm.

[0061] The machine vision positioning module is used to accurately calculate the spatial coordinates (X, Y, Z) of the center point of the five-way pipe and the direction vector of the central axis based on the image data collected by the data acquisition module and through image processing algorithms.

[0062] In the preferred embodiment of this application, the specific analysis method of the machine vision positioning module is as follows:

[0063] The RANSAC algorithm was used to fit the cylindrical surface of the inner wall of the bottom duct to the 3D point cloud data.

[0064] Calculate the spatial coordinates (X, Y, Z) of the center point and the direction vector (i, j, k) of the axis based on the equation of the central axis of the cylindrical surface.

[0065] The coordinates are transformed to the base coordinate system of the servo press-fit module using a hand-eye calibration matrix.

[0066] It should be further noted that the parameters of the RANSAC algorithm are defined as follows: The cylindrical model is described by 7 parameters:

[0067] The central axis direction vector is (i,j,k), a point on the central axis is (x0,y0,z0), and the radius is r.

[0068] The iterative process is as follows:

[0069] 1) Random sampling: 7 points are randomly selected in each iteration;

[0070] 2) Model estimation: Calculate the axis direction using sampling points, project the points onto the axis direction, and fit the center point and radius;

[0071] 3) Inner point determination: Calculate the distance from all points to the cylindrical surface. If the distance is less than the threshold, such as 1mm, then mark it as an inner point.

[0072] 4) Model scoring: The model with the most interior points is retained.

[0073] Termination conditions: Reaching the preset number of iterations or the proportion of interior points exceeds 90%.

[0074] Furthermore, the preset number of iterations is 1000.

[0075] In the preferred embodiment of this application, the hand-eye calibration matrix is ​​set to a 4×4 homogeneous transformation matrix T. , where R is a 3×3 rotation matrix and t is a 3×1 translation vector.

[0076] Center point coordinate transformation: ; Axis direction vector transformation: The coordinates of the center point in the base coordinate system are: (X b Y b Z b ), the axis direction vector in the base coordinate system: (i b j b k b ).

[0077] The data management module is used for data storage and traceability during the processing.

[0078] Furthermore, in the above technical solution, the data stored by the data management module includes at least: original image data, processed image feature data, calculated center coordinates and axis vector of the five-way pipe, displacement-pressure curve of the entire pressing process, set values ​​and actual values ​​of pressing speed at each stage, environmental data, quality judgment results, abnormal alarm codes and processing records.

[0079] The press-fit control module is used to control the servo press-fit module to perform press-fit according to visual coordinates and to adjust the pressing speed in real time;

[0080] In the preferred embodiment of this application, the specific control logic of the press-fitting control module is as follows:

[0081] Pre-pressing stage: Pressing in at a constant speed for the first 30% of the total stroke;

[0082] Main pressure stage: Press in 30%-80% of the total stroke, and dynamically adjust the pressing speed according to pressure feedback;

[0083] Final pressing stage: During the last 20% of the total pressing stroke, switch to displacement control mode to press the material to the target position with fixed step accuracy.

[0084] In the preferred embodiment of this application, the constant speed during the pre-pressing stage is 0.5-2 mm / s; and the pressing speed to the target position with fixed step accuracy during the final pressing stage is 0.1 mm / s.

[0085] The servo press-fit module integrates a frame support device and a bottom bracket press-fit device. The frame support device is used to fix the bicycle frame and provide initial positioning, while the bottom bracket press-fit device is used to perform the press-fit operation of the bottom bracket assembly.

[0086] In the preferred embodiment of this application, the specific operation process of the servo press-fit module is as follows:

[0087] Based on the calculated bottom bracket axis direction vector (i,j,k), the drive frame bearing device performs pose compensation to align the bottom bracket axis with the press-fit axis.

[0088] The press-fitting control module controls the servo press-fitting module to press the central shaft in. During the process, the pressure value Pi is detected in real time. In the main press stage, the speed is dynamically adjusted according to the pressure feedback to keep the pressure value within the range of ±10% of the standard curve.

[0089] After reaching the target position, maintain the pressure for a fixed duration.

[0090] Furthermore, in the above technical solution, the adjustment logic of the dynamically adjustable speed satisfies: In the formula, v t Let P be the pressing speed at time t. ta P is the standard pressure value corresponding to the current displacement. t K represents the measured pressure value at time t. p K is the proportionality coefficient. i K is the integral coefficient. d Here, θ is the differential coefficient, and θ is the integral dummy variable; the formula for calculating the holding pressure is: In the formula, α is the material creep coefficient, and σ is the creep coefficient. y D is the yield strength of the bottom bracket material, D is the diameter of the central shaft assembly, L is the press-in contact length, and F is the bottom bracket material. h To maintain pressure.

[0091] In the preferred embodiment of this application, the proportionality coefficient K is determined experimentally based on historical data. p =0.3, integral coefficient K i =0.05, differential coefficient K d =0.01, the material creep coefficient is determined based on the frame, preferably 0.7-0.9 for carbon fiber frames and 0.5-0.7 for aluminum alloy frames; the fixed time length in the phrase "maintaining pressure for a fixed duration after reaching the target position" is 300-500ms.

[0092] The quality inspection module is used to determine the assembly quality by analyzing the displacement-pressure curve.

[0093] In the preferred embodiment of this application, the specific operation process of the quality inspection module is as follows:

[0094] The system receives and analyzes displacement-pressure curve data acquired by the data acquisition module in real time.

[0095] The real-time displacement-pressure curve is compared with the preset standard qualified curve;

[0096] Based on the comparison results, determine whether the assembly quality is qualified and generate the corresponding quality judgment result signal;

[0097] If an abnormal curve shape or a deviation from the preset tolerance range is detected, a corresponding abnormal alarm code will be generated.

[0098] It should be further explained that the criteria for determining whether a product is of acceptable quality are as follows:

[0099] Aluminum alloy frame: the displacement-compression curve deviates from the preset standard qualified curve by less than ±5%; carbon fiber frame: the displacement-compression curve deviates from the preset standard qualified curve by less than ±8%.

[0100] Below are some examples of alarm codes:

[0101] Alarm code P_OVER: Curve characteristics: Pressure remains higher than the standard curve; Handling measures: Trigger deceleration compensation;

[0102] Alarm code P_DROP: Curve characteristics: Pressure drop > 30%; Handling measures: Emergency stop and audible and visual alarm;

[0103] Alarm code P_ALERT: Curve characteristics: High-frequency pressure oscillation, greater than 50Hz; Handling measures: Pause and check the vibration source;

[0104] Alarm code P_ERR: Curve characteristics: Displacement meets the standard but pressure is insufficient; Handling measures: Start the secondary pressing procedure.

[0105] Furthermore, in the above technical solution, the pressing control module and the quality detection module are also equipped with an anomaly handling unit; when the real-time pressure value Pi exceeds the preset safety threshold, the displacement-pressure curve deviates significantly from the standard curve, or an abnormal alarm code is received from the sensor, the anomaly handling unit controls the servo pressing module to immediately stop the pressing operation.

[0106] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A bicycle bottom bracket press-fitting system based on machine vision positioning, characterized in that, include: Data acquisition module: used to acquire image data and assembly quality data; Data processing module: used to perform image denoising, edge detection, and feature coordinate extraction; Machine vision positioning module: Based on the image data acquired by the data acquisition module, the spatial coordinates (X, Y, Z) of the center point of the bottom bracket and the direction vector of the central axis are accurately calculated through image processing algorithms; Data management module: used for data storage and traceability during the processing; Pressing control module: Used to control the servo pressing module to perform pressing based on visual coordinates, and to adjust the pressing speed in real time; Servo press-fit module: integrates frame support device and bottom bracket press-fit device. The frame support device is used to fix the bicycle frame and provide initial positioning, and the bottom bracket press-fit device is used to perform the press-fit operation of the bottom bracket assembly. Quality inspection module: used to determine assembly quality by analyzing displacement-pressure curves; The image data includes a global image of the bottom bracket area of ​​the frame, a local feature image of the bottom bracket mounting hole, and three-dimensional point cloud data of the bottom bracket inner wall; the assembly quality data includes: real-time displacement and pressure data of the bottom bracket during the press-fit process; the specific method for the data acquisition module to acquire image data is as follows: a global image of the bottom bracket area of ​​the bicycle frame and a local feature image of the bottom bracket mounting hole are acquired using a high-resolution industrial camera, and three-dimensional point cloud data of the bottom bracket inner wall are acquired using a 3D structured light camera; the assembly quality data is acquired using displacement sensors and pressure sensors. The specific operation process of the servo press-fit module is as follows: Based on the calculated bottom bracket axis direction vector (i,j,k), the drive frame bearing device performs pose compensation to align the bottom bracket axis with the press-fit axis. The press-fitting control module controls the servo press-fitting module to press the central shaft in. During the process, the pressure value Pi is detected in real time. In the main press stage, the speed is dynamically adjusted according to the pressure feedback to keep the pressure value within the range of ±10% of the standard curve. After reaching the target position, maintain the holding pressure for a fixed period of time; The specific control logic of the press-fitting control module is as follows: Pre-pressing stage: Pressing in at a constant speed for the first 30% of the total stroke; Main pressure stage: Press in 30%-80% of the total stroke, and dynamically adjust the pressing speed according to pressure feedback; Final pressing stage: During the last 20% of the total pressing stroke, switch to displacement control mode to press the material to the target position with fixed step accuracy; The adjustment logic of the dynamically adjusted speed satisfies: In the formula, v t Let P be the pressing speed at time t. ta P is the standard pressure value corresponding to the current displacement. t K represents the measured pressure value at time t. p K is the proportionality coefficient. i K is the integral coefficient. d Here, θ is the differential coefficient, and θ is the integral dummy variable; the formula for calculating the holding pressure is: In the formula, α is the material creep coefficient, and σ is the creep coefficient. y D is the yield strength of the bottom bracket material, D is the diameter of the central shaft assembly, L is the press-in contact length, and F is the bottom bracket material. h To maintain pressure.

2. The bicycle bottom bracket press-fitting system based on machine vision positioning as described in claim 1, characterized in that: The specific processing flow of the data processing module is as follows: The median filtering algorithm is used to denoise the original image; Edge detection and generation of binary contour images based on the Canny operator; The initial coordinates of the center of the mounting hole of the central shaft are extracted using the Hough circle transformation.

3. The bicycle bottom bracket press-fitting system based on machine vision positioning as described in claim 1, characterized in that: The specific analysis method for the machine vision positioning module is as follows: The RANSAC algorithm was used to fit the cylindrical surface of the inner wall of the bottom duct to the 3D point cloud data. Calculate the spatial coordinates (X, Y, Z) of the center point and the direction vector (i, j, k) of the axis based on the equation of the central axis of the cylindrical surface. The coordinates are transformed to the base coordinate system of the servo press-fit module using a hand-eye calibration matrix.

4. The bicycle bottom bracket press-fitting system based on machine vision positioning as described in claim 1, characterized in that: The specific operation process of the quality inspection module is as follows: The system receives and analyzes displacement-pressure curve data acquired by the data acquisition module in real time. The real-time displacement-pressure curve is compared with the preset standard qualified curve; Based on the comparison results, determine whether the assembly quality is qualified and generate the corresponding quality judgment result signal; If an abnormal curve shape or a deviation from the preset tolerance range is detected, a corresponding abnormal alarm code will be generated.

5. The bicycle bottom bracket press-fitting system based on machine vision positioning as described in claim 1, characterized in that: The pressing control module and the quality detection module are also equipped with an anomaly handling unit; when the real-time pressure value Pi exceeds the preset safety threshold, the displacement-pressure curve deviates significantly from the standard curve, or an abnormal alarm code is received from the sensor, the anomaly handling unit controls the servo pressing module to immediately stop the pressing operation.

6. The bicycle bottom bracket press-fitting system based on machine vision positioning as described in claim 1, characterized in that: The data stored in the data management module includes at least: original image data, processed image feature data, calculated center coordinates and axis vector of the five-way pipe, displacement-pressure curve of the entire pressing process, set and actual values ​​of pressing speed at each stage, environmental data, quality judgment results, abnormal alarm codes and processing records.

Images